Prerpints.org logo
Preprint
Review

This version is not peer-reviewed.

AI in Robot Manipulator Control: A Systematic Review

A peer-reviewed version of this preprint was published in:
Processes 2026, 14(9), 1401. https://doi.org/10.3390/pr14091401

Submitted:

30 March 2026

Posted:

31 March 2026

You are already at the latest version

Abstract
This study presents a structured analysis of 343 publications on artificial intelligence-based methods for robot manipulator control published between 2015 and 2025. The review examines how AI has been incorporated into the control pipeline by organizing prior work according to functional roles, including perception and estimation, planning, learning based control, interaction and safety, and learning and adaptation. In addition to this functional taxonomy, the study analyzes publication growth, application do-mains, robot types, evaluation settings, and methodological patterns to characterize the evolution of the field over the past decade. The results show that research activity has been concentrated primarily in learning control, while other functional roles have received comparatively less attention. The literature also reveals an uneven distribution across ap-plication areas and robot platforms, with a strong reliance on simulation and limited evidence of integrated real-world deployment. These patterns indicate that, despite rapid growth and methodological diversity, the field remains imbalanced in both research focus and validation maturity. Rather than summarizing individual studies in isolation, this review provides a high-level perspective on where effort has been concentrated, where major gaps persist, and which directions are most critical for advancing AI-based robot manipulator control toward reliable and scalable real-world use.
Keywords: 
artificial intelligent
;  
control
;  
robot manipulator
;  
robot control
;  
planning
;  
learning control
Subject: 
Engineering  -   Control and Systems Engineering

1. Introduction

Over six decades of development, robotic manipulators (RMs) have expanded far beyond structured manufacturing environments into military, aerospace, construction, agriculture, healthcare, and other industries with complex operations [1,2,3,4,5,6,7]. This progression represents not merely an expansion of application, but a substantial increase in control complexity, introducing control requirements that classical strategies were not designed to meet. Controllers such as PID replied heavily on linearized system models and predictable disturbances [8]. These conditions are rarely satisfied in modern applications, where manipulators must handle nonlinearities, high uncertainty, high speed, and direct human-robot interaction in unstructured environments [9]. As a result, the gap between what classical control can reliably guarantee and what modern robotic applications require has become increasingly apparent. This has motivated substantial research into AI-based control strategies capable of handling model uncertainty, continuously adapting to changing conditions, learning autonomously from interaction with their surroundings, and updating toward optimal solutions without relying on predefined models or manual retuning.
Interest in AI-based approaches to manipulator control dates to the early 1990s, when data-driven adaptation and learning approaches began complementing classical control and gave rise to adaptive and intelligent control frameworks [10,11]. Subsequent developments in reinforcement learning (RL), deep learning (DL), and hybrid architectures have considerably expanded the scope of these applications. Hierarchical RL has been applied to learn joint-specific motor dynamics without manual tuning, achieving robust trajectory tracking under variable loads [12]. Neural network-based methods have been used to tune PID gains online in dual-arm systems, improving tracking accuracy under parametric uncertainty [13]. More recently, language-vision models have been applied to decompose manipulation demonstrations into executable action primitives and estimate latent task properties, such as contact forces and load distribution, that are not directly measurable from sensor data [14]. These developments have been accelerated by advanced literature research of AI and supporting infrastructure, including specialized accelerators, sensors, large-scale data centers, and expansive training data [15,16].
Many existing reviews addressed parts of this landscape, either by focusing on specific techniques [17,18] or by specific application areas [19,20]. A comparative summary of these reviews with ours is given d in Table 1.
Although these reviews provide valuable depth, they do not provide cross-domain statistical analysis of the current literature. Without this high-level overview, it is difficult to identify which roles have received disproportionate research attention, which technique families are associated with which application contexts, and where the most persistent methodological gaps exist. This paper addresses that gap by presenting key statistics to highlight the trends about AI-based control techniques in robot manipulator control from 2015 to present.
This paper is organized into five sections. Section 1 introduces the topic and summarizes the existing review literature. Section 2 describes the data collection process and study selection methodology. Section 3 presents the included studies and their quantitative analysis. Section 4 and Section 5 provide the discussion and conclusion, respectively.

2. Materials and Methods

This study provides a retrospective mapping of 343 studies on AI-based control for RMs published between 2015 and 2025. The selection process included identifying potentially relevant studies across major online databases, deduplication, title and abstract screening for eligibility assessments, and full-text screening for categorization and statistical analysis.

2.1. Search Strategy

The literature search for this review followed the modified PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) framework to ensure the transparency, reproducibility, and comprehensiveness in reporting search strategy and findings [23]. Explicated Boolean search strings were performed across multiple online databases, including IEEEXplore, PubMed, Scopus, and Google Scholar, to identify potentially relevant studies. Only for IEEEXplore that the search was conducted twice with the same query: first without content-type restrictions, then excluding conference proceedings. The search period was from 2015 to present, including early-access and online-first. The relevant Boolean strings applied are presented in Table 2.

2.2. Search Execution and Screening Process

The final search was completed on December 31, 2025, yielding a combined total of 800 records across all databases. Records were exported and de-duplicated in Zotero using its automatic duplicate-detection function, resulting in 672 unique records. Title and abstract screening were then conducted against the predefined inclusion and exclusion criteria. To maximize efficiency and consistency, Anara AI, an AI-powered research assistant, was used as a decision-support tool during this stage. All AI-assisted decisions were manually verified prior to inclusion or exclusion. After this screening stage, 343 studies were subjected for full-text assessment. Full texts were reviewed in detail to confirm eligibility, further analysis, and categorized according to the five functional modules in RM control: perception/estimation, planning, learning control, interaction/safety, and learning/adaptation.

2.2.1. Inclusion Criteria

  • Published 2025 or later
  • Written in English
  • Proposed or applied AI-based techniques explicitly for control of RMs

2.2.2. Exclusion Criteria

  • Soft robots, hydraulic robot, continuum systems, or quadrotor
  • Simulation platforms evaluations using robot learning methods
  • General/high-level control discussions without AI approaches
  • Book chapters, reviews, editorials, patents, letters, abstracts, or other scientific journal formats
The selection process from 800 identified records to the final set of 343 selected studies was documented using the PRISMA-2020 flow diagram and presented in Figure 1.

2.3. Data Extraction

An additional systematic extraction was conducted on 343 selected studies to capture the following data:
  • Authors and year of publication
  • The functional role of implemented strategy within the robot manipulator control system, categorized as one of the following:
    o
    Perception and Estimation: outputs state estimates such as pose, velocity, maps, or object identity for downstream use
    o
    Planning: outputs a plan/trajectory/waypoints/goals or select actions at a symbolic/task level that are then tracked by a controller.
    o
    Learning Control: outputs low-level commands or a control policy that directly drives the robot’s motion (joint velocities/torques/actions each timestep).
    o
    Interaction and Safety: outputs safety constraints or regulates contact/force/compliance, including human-aware limits and safe-set filtering
    o
    Learning and Adaptation: updates models or policies online/continually across conditions, improving with new deployment data
  • Robot type
  • Application area
  • Control techniques
  • AI/ML methods
  • Learning paradigm (supervised, unsupervised, reinforcement learning, hybrid)
  • Evaluation method (simulation, experiments, both)

2.4. Research Question

This review is guided by the following four research questions:
RQ1: How has the volume and distribution of AI/ML-based robot manipulator control research evolved over the last decade in terms of publication trends and temporal shifts in method adoption?
RQ2: Which functional control roles, spanning perception and estimation, planning, learning-based control, interaction and safety, and online adaptation, have attracted the greatest research concentration, and are those concentrations proportionate to the demands of the application domains they serve?
RQ3: Across which application domains has AI/ML-based robot manipulator control been most actively studied, measured by publication volume and methodological diversity, and which domains remain comparatively underserved relative to their real-world significance?
RQ4: Based on observed publication trends, shifts in method adoption, and gaps between research concentration and application demand, what emerging directions are most likely to define the next stage of AI/ML-enabled robot manipulator control?

3. Review of Publications

Table 3, Table 4, Table 5, Table 6 and Table 7 list the selected studies on AI-based control techniques in robot manipulator control from 2015 to 2025, organized by functional category and summarizing their key aspects

3.1. Publications

Figure 2 demonstrates a clear increase in publication output on AI-based robot manipulator control from 2015 to 2025. This indicates a progressive expansion of the field over the review period. The annual number of publications remained relatively low and variable during 2015–2019, suggesting that research activity was still limited and not yet consolidated. Beginning in 2020, publication output increased sharply, marking a clear inflection point in the development of the literature. This growth continued through 2023, where the annual count reached its maximum, followed by a slight decline in 2024–2025. Despite this modest reduction, the number of publications in the final years remained substantially higher than that observed in the earlier period. Overall, the trend indicates that AI-based robot manipulator control has emerged as a rapidly expanding research area over the past decade.

3.2. Research Interest

Figure 3 shows that the included studies were unevenly distributed across functional roles. learning control accounted for 75.5% of the literature, far exceeding planning (11.4%), perception and estimation (6.1%), learning and adaptation (5.8%), and interaction and safety (1.2%). These results indicate that AI-based robot manipulator control research was concentrated predominantly in learning control, whereas the other functional roles were represented at much lower levels. The year-by-year distribution of publications across these roles is presented in Figure 4.
Figure 4 shows that the five functional-role categories followed different patterns over the review period. Learning control remained the dominant category in nearly every year and accounted for the largest share of publications throughout the dataset. Planning, perception and estimation, and learning and adaptation were represented at lower but recurring levels, although their annual counts remained comparatively small. Interaction and safety was the least represented category across the full period. Overall, the increase in annual publication output was associated primarily with continued growth in learning control, whereas the other functional roles remained limited in frequency.

3.3. Robot Types

Table 4 summarizes the distribution of studies by robot type. The literature was strongly dominated by serial manipulators, which accounted for 74% of the included studies. Robotic hands (9.3%) and flexible-joint robots (4.4%) formed the next largest categories, while all remaining robot types each represented only a small share of the dataset. This distribution indicates that the field has been centered primarily on conventional serial robotic platforms, with comparatively limited representation of more specialized configurations such as parallel manipulators, exoskeletons, humanoids, magnetic systems, and mobile manipulators.

3.4. Applications

Table 5 summarizes the distribution of studies by application domain. The largest share of the literature fell under Not Specified, indicating that more than half of the included studies were not linked to a clearly defined end-use setting. Among the explicitly reported domains, Manufacturing accounted for the largest proportion with 18.7% of the total studies, while all other application areas were represented less frequently. This distribution indicates that AI-based robot manipulator control has been investigated across multiple sectors, but that explicit domain-specific application has been concentrated primarily in Manufacturing.

3.5. Control Techniques

Table 6 presents the grouping of 44 distinct control techniques into higher-order control families. The resulting distribution was strongly concentrated in learning-based control, which accounted for 90.7% of all publications, while the remaining families each represented only a small proportion of the dataset. Within this dominant family, deep reinforcement learning (DRL) based control comprised 150 studies, corresponding to approximately 48% of learning-based studies and 43.7% of the full dataset. Other learning-based subgroups, including hybrid RL–neutral networks (NN), adaptive dynamic programming (ADP) based, and deep NN-based visual servoing, were represented at lower frequencies. This pattern indicates that the methodological concentration of the literature occurred not only at the family level, but also within the learning-based family itself, where reinforcement-learning-oriented approaches formed the principal subgroup.

3.4. AI-based Methods

A total of 278 distinct AI methods were identified across the dataset. The complete list is provided in supplementary material, while the present figure reports only the 20 most frequently used methods for clarity in Figure 5. The distribution shows that the literature has been dominated by reinforcement-learning-based approaches, particularly soft actor-critic (SAC), proximal policy optimization (PPO), deep deterministic policy gradient (DDPG), and related variants, whereas other methods occurred less frequently. Because individual studies could employ multiple methods, these frequencies do not correspond directly to the number of studies. Overall, the results indicate both methodological diversity across the dataset and concentration around a small core of recurrent RL-based techniques.

3.5. Learning Paradigm

The distribution of the learning paradigm across studies is presented in Table 7 by frequency and percentage. The learning-paradigm distribution shows that RL was the dominant paradigm, accounting for 58.9% of the included studies. Supervised learning represented 12.2%, whereas self-supervised and unsupervised learning were only rarely reported. Combined learning formulations were also common with hybrid approaches (14.0%) using two paradigms and multi-paradigm approaches (8.5%). The most common hybrid combinations involved RL and imitation learning (IL), followed by RL with supervised learning and RL with self-supervised learning. These results indicate that the literature was centered primarily on RL, either as a standalone paradigm or as the core element of integrated learning frameworks.

3.6. Trends in Evaluation Method

Figure 6 shows that the evaluation-method distribution is tied between both simulation and experiment (42.3%) and simulation-only (42.0%), whereas experiment-only studies represented 15.7% of the dataset. This indicates that the current literature still relies heavily on simulation for development and validation, while experimental testing is growing as an important step toward practical deployment. The fact that simulation-only studies greatly outnumber experiment-only studies also suggests that much of the literature remains closer to the proof-of-concept or pre-deployment stage than to full real-world implementation.

4. Discussion

4.1. Limitations in AI-Based Robot Manipulator Control

A recurring pattern across the analyzed literature is that the reported limitations were not confined to individual studies, but reflected broader weaknesses in how AI-based control strategies are currently developed and validated for robot manipulators. Although many studies reported favorable control performance, the supporting evidence was often constrained by simplified validation settings, narrowly defined tasks, and limited demonstration of deployment readiness. These limitations were observed across reinforcement learning, supervised learning, imitation learning, adaptive learning, and hybrid AI-control approaches.
The most common limitations can be grouped into several recurring categories. First, validation maturity remained limited, as many studies relied on simulation-only evaluation, while experimental studies were often restricted to controlled laboratory settings, simplified workspaces, small datasets, or narrowly scoped tasks. Second, sim-to-real transfer remained a persistent challenge, with many studies reporting degraded performance during hardware deployment or not evaluating transfer at all. Third, low sample efficiency and high training burden were especially common in DRL-based studies, where training often required extensive exploration, large numbers of episodes, and repeated retraining under modified conditions. Fourth, generalizability remained limited, as many controllers were validated on a single robot, task, object set, or workspace and were not assessed under broader environmental or task variation. Fifth, performance was often sensitive to reward design, hyperparameter tuning, dataset quality, and other task-specific configuration choices, which reduced reproducibility and complicated cross-study comparison. Finally, in perception-dependent pipelines, control performance was frequently constrained by upstream sensing limitations, including occlusion, clutter, calibration drift, noisy signals, and limited data diversity.
Additional limitations were reported less consistently but remained important, including the lack of formal stability or safety guarantees, simplified physical assumptions, computational and real-time constraints, and system-integration issues such as communication delay, hardware limitations, and execution jitter. Collectively, these limitations restrict confidence in whether reported performance can be reproduced outside the original test conditions or maintained under more realistic manipulator operating environments. Overall, the literature demonstrates substantial algorithmic potential, but the evidence for robust, transferable, and deployment-ready manipulator control remains limited.

4.2. General Challenges in AI-Based Robot Manipulator Control

A recurrent pattern across the analyzed literature is that the main challenges of AI-based robot manipulator control are not confined to individual methods, but reflect broader barriers to achieving robust, generalizable, and practically deployable systems. Across reinforcement learning, supervised learning, imitation learning, adaptive learning, and hybrid approaches, authors repeatedly identified difficulties that extend beyond algorithmic performance under bounded test conditions.
The reported challenges can be grouped into several recurring categories. First, generalization beyond narrow training conditions remained a major challenge, as many studies reported difficulty extending learned controllers across new tasks, objects, robot platforms, workspaces, or environmental conditions. Second, data efficiency and scalable learning remained problematic, particularly in DRL-based methods, where sparse rewards, large exploration spaces, expensive demonstration collection, long training times, and unstable optimization limited scalability. Third, sim-to-real transfer and domain mismatch continued to constrain deployment, with visual domain gaps, physics mismatch, calibration error, sensing differences, and hardware variability repeatedly identified as barriers to reliable transfer from simulation to physical systems. Fourth, robustness under uncertainty and nonlinear dynamics remained a central challenge, especially in the presence of external disturbances, friction, payload variation, delays, partial observability, and time-varying operating conditions. Fifth, perception reliability in unstructured environments was frequently identified as a limiting factor, particularly under occlusion, clutter, illumination variation, noisy sensing, or dynamic scenes. Finally, many studies highlighted the joint challenge of safety, stability, and real-time deployment, emphasizing the need for safe exploration, collision-aware operation, computational efficiency, and compatibility with control-theoretic requirements.
Additional field-level challenges were reported less consistently but remained important, including scalability to high- degree of freedom (DOF), redundant, bimanual, or closed-chain systems, integration of perception, planning, and control within unified architectures, reduced dependence on structured environments and handcrafted assumptions, interpretability and verification of learned policies, and adaptation to contact-rich, long-horizon, and multi-stage manipulation tasks. Collectively, these challenges indicate that the field has advanced beyond demonstrating isolated algorithmic success, but continues to face substantial barriers to building manipulator controllers that are simultaneously generalizable, data-efficient, robust, safe, and deployment-ready.

4.3. Future Directions

A notable pattern identified across the analyzed literature is that proposed future work did not diverge into isolated directions, but instead converged around a relatively consistent set of developmental priorities. Across different AI methodologies, authors repeatedly pointed to similar next-step needs, indicating a shared maturation trajectory for AI-based robot manipulator control.
The reported future directions can be grouped into several recurring categories. First, many studies proposed expansion from constrained evaluation toward real-world and real-robot validation, including testing on physical platforms, broader industrial settings, and more realistic manipulation scenarios. Second, improving sim-to-real transfer and deployment readiness remained a frequent priority, with recommendations including domain randomization, real-world fine-tuning, calibration improvement, synthetic data generation, and more rigorous transfer protocols. Third, many studies emphasized extension to more complex tasks, richer environments, and broader generalization, including cluttered scenes, deformable objects, dynamic settings, long-horizon tasks, dexterous manipulation, and broader cross-robot evaluation. Fourth, authors frequently identified the need to improve data efficiency, training stability, and learning scalability, particularly through better reward design, curriculum learning, hierarchical learning, imitation learning integration, and more efficient training strategies. Fifth, many future-work statements emphasized stronger perception and multimodal sensing integration, including improved visual backbones, larger datasets, tactile and force sensing, RGB-D systems, and multimodal sensor fusion. Finally, a consistent direction was the development of safer, more adaptive, and more unified control architectures that integrate perception, planning, adaptation, and control more tightly while incorporating online adaptation, uncertainty handling, and safety-aware behavior.
Additional future directions were reported less consistently but remained important, including extension to high-DOF, redundant, flexible, soft, underactuated, or multi-robot systems, greater use of advanced computational infrastructure, increased methodological hybridization, and stronger attention to interpretability, verification, and practical usability. Collectively, these trends indicate that the field is moving beyond isolated algorithmic improvement toward broader goals of real-world validation, transferability, efficiency, robustness, multimodal integration, and deployment-oriented system design. Overall, the future-work statements suggest that the next stage of progress in AI-based robot manipulator control will depend less on achieving higher benchmark performance alone and more on building systems that are generalizable, efficient, safety-aware, and practically deployable.

5. Conclusions

This systematic review, conducted in accordance with the PRISMA framework, identified 343 studies published between 2015 and 2025 on AI based control for RMs. By synthesizing evidence across functional roles, control techniques, robot types, application settings, learning paradigms, and evaluation methods, the review provided a high-level view of how this research area has developed in the literature. Overall, AI based RM control has expanded rapidly over the past decade, particularly since 2020, confirming its emergence as a rapid growing area of research. However, this growth has been markedly uneven, with research activity concentrated in a limited set of functional and methodological directions.
The main trends identified are as follows:
  • Uneven functional development: The literature was concentrated predominantly in learning control, with substantially lower representation of planning, perception and estimation, learning and adaptation, and especially interaction and safety.
  • Methodological concentration: Learning-based control overwhelmingly dominates the field, particularly RL and DRL. Although many distinct AI methods were identified overall, recurrent use remained centered on a relatively small core of RL oriented techniques.
  • Narrow robot and application coverage: The reviewed studies focused primarily on serial manipulators, while many specialized robotic configurations remained sparsely represented. A large proportion of studies also lacked a clearly specified application setting. Among the explicitly reported domains, manufacturing was the most represented.
  • Strong reliance on simulation-based evaluation: Most studies relied simulation only or combined simulation and experiment for validation, whereas fully experimental evaluation remained comparatively limited.
Taken together, these findings indicated that AI based control for RMs has achieved substantial methodological growth, but its development remained uneven in scope, validation maturity, and deployment readiness. Building on this descriptive trend analysis, future work can perform more advanced relational analyses to further assess the impact of AI on RM control. Key potential areas for investigation include method evolution and co-occurrence, cross-variable patterns, limitation clustering, hybrid versus single-paradigm performance, technique-outcome alignment, and future direction mapping.

Supplementary Materials

The following supporting information can be downloaded at the website of this paper posted on Preprints.org. The complete list of all AI methods was identified across the dataset can be found here.

Author Contributions

Conceptualization, C.C.N., L.S. and H.T.T.N.; methodology, C.C.N.; software, T.T.N.; validation, T.T.C.D, T.T.N and T.M.N; formal analysis, C.C.N and H.T.T.N.; investigation, T.T.C.D; resources, T.T.C.D; data curation, T.M.N.; writing—original draft preparation, H.T.T.N; writing—review and editing, C.C.N., H.T.T.N. and L.S.; visualization, H.T.T.N; supervision, C.C.N. and L.S; project administration, C.C.N. All authors have read and agreed to the published version of the manuscript.

Funding

This research received no external funding.

Data Availability Statement

No new data were created or analyzed in this study. All data supporting the findings of this study are available within the cited literature.

Acknowledgments

During the preparation of this manuscript/study, Anara AI for the purposes of summarize and categorize the studies during the data extraction and screening process. The models used were GPT OSS and Grok 4.1. The authors have reviewed and edited the output and take full responsibility for the content of this publication.

Conflicts of Interest

The authors declare no conflicts of interest.

References

  1. Hockstein, N.G.; Gourin, C.G.; Faust, R.A.; Terris, D.J. A History of Robots: From Science Fiction to Surgical Robotics. J. Robot. Surg. 2007, 1, 113–118. [Google Scholar] [CrossRef]
  2. Lin, P.; Bekey, G.; Abney, K. Autonomous Military Robotics: Risk, Ethics, and Design; Defense Technical Information Center: Fort Belvoir, VA, 2008. [Google Scholar]
  3. Nguyen, C.C.; Ngo, H.T.T.; Duong, T.T.C.; Nabili, A. Mechanical Design and Kinematic Analysis of an Autonomous Wrist with DC Motor Actuators for Space Assembly. Actuators 2025, 14, 542. [Google Scholar] [CrossRef]
  4. Halder, S.; Afsari, K. Robots in Inspection and Monitoring of Buildings and Infrastructure: A Systematic Review. Appl. Sci. 2023, 13, 2304. [Google Scholar] [CrossRef]
  5. Jin, T.; Han, X. Robotic Arms in Precision Agriculture: A Comprehensive Review of the Technologies, Applications, Challenges, and Future Prospects. Comput. Electron. Agric. 2024, 221, 108938. [Google Scholar] [CrossRef]
  6. Aggarwal, S.; Gupta, D.; Saini, S. A Literature Survey on Robotics in Healthcare. In Proceedings of the 2019 4th International Conference on Information Systems and Computer Networks (ISCON), November 2019; IEEE: Mathura, India; pp. 55–58. [Google Scholar]
  7. Ngo, H.T.T.; Nguyen, C.C.; Duong, T.T.C.; Nguyen, T.T. Trends in Control Strategies of Parallel Robot Manipulators for Robot-Assisted Rehabilitation. Eng 2026, 7, 44. [Google Scholar] [CrossRef]
  8. Slotine, J.-J.E.; Li, W. Applied Nonlinear Control; Prentice Hall: Englewood Cliffs, NJ, 1991; ISBN 978-0-13-040890-7. [Google Scholar]
  9. Kroemer, O.; Niekum, S.; Konidaris, G. A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms. [CrossRef]
  10. Zomaya, A.Y.; Suddaby, M.E.; Morris, A.S. Direct Neuro-Adaptive Control of Robot Manipulators. In Proceedings of the Proceedings 1992 IEEE International Conference on Robotics and Automation; IEEE Comput. Soc. Press: Nice, France, 1992; pp. 1902–1907. [Google Scholar]
  11. Harib, M.; Chaoui, H.; Miah, S. Evolution of Adaptive Learning for Nonlinear Dynamic Systems: A Systematic Survey. Intell. Robot. 2022. [Google Scholar] [CrossRef]
  12. Yagi, S.; Morimoto, J. Learning-Based Joint Control With Hierarchical Reinforcement Learning and On-Device Execution. IEEE Robot. Autom. Lett. 2025, 10, 12493–12500. [Google Scholar] [CrossRef]
  13. Elsisi, M.; Mahmoud, K.; Lehtonen, M.; Darwish, M.M.F. An Improved Neural Network Algorithm to Efficiently Track Various Trajectories of Robot Manipulator Arms. IEEE Access 2021, 9, 11911–11920. [Google Scholar] [CrossRef]
  14. Lu, Y.; Wu, C.; Yao, W.; Sun, G.; Liu, J.; Wu, L. Deep Reinforcement Learning Control of Fully-Constrained Cable-Driven Parallel Robots. IEEE Trans. Ind. Electron. 2023, 70, 7194–7204. [Google Scholar] [CrossRef]
  15. Reuther, A.; Michaleas, P.; Jones, M.; Gadepally, V.; Samsi, S.; Kepner, J. AI and ML Accelerator Survey and Trends. In Proceedings of the 2022 IEEE High Performance Extreme Computing Conference (HPEC), Waltham, MA, USA, September 19 2022; IEEE; pp. 1–10. [Google Scholar]
  16. Zhu, S.; Yu, T.; Xu, T.; Chen, H.; Dustdar, S.; Gigan, S.; Gunduz, D.; Hossain, E.; Jin, Y.; Lin, F.; et al. Intelligent Computing: The Latest Advances, Challenges, and Future. Intell. Comput. 2023, 2, 0006. [Google Scholar] [CrossRef]
  17. Waseem, S.; Adnan, M.; Iqbal, M.S.; Amin, A.A.; Shah, A.; Tariq, M. From Classical to Intelligent Control: Evolving Trends in Robotic Manipulator Technology. Comput. Electr. Eng. 2025, 127, 110559. [Google Scholar] [CrossRef]
  18. Swetha Danthala Et Al., S.D.E.Al.; TJPRC Robotic Manipulator Control by Using Machine Learning Algorithms, A Review. Int. J. Mech. Prod. Eng. Res. Dev. 2018, 8, 305–310. [CrossRef]
  19. Benotsmane, R.; Dudás, L.; Kovács, G. Survey on Artificial Intelligence Algorithms Used in Industrial Robotics. Multidiszcip. Tudományok 2020, 10, 194–205. [Google Scholar] [CrossRef]
  20. Cho, J.; Jung, S. Reinforcement Learning-Based Motion Planning for Robotic Manipulators in Smart Industry. In Proceedings of the 2024 15th International Conference on Information and Communication Technology Convergence (ICTC), October 16 2024; IEEE: Jeju Island, Korea, Republic of; pp. 1166–1168. [Google Scholar]
  21. Fernández Mareco, E.R.; Pinto-Roa, D. Application of Artificial Intelligence in Control Systems: Trends, Challenges, and Opportunities. AI 2025, 6, 326. [Google Scholar] [CrossRef]
  22. Nahavandi, S.; Alizadehsani, R.; Nahavandi, D.; Lim, C.P.; Kelly, K.; Bello, F. Machine Learning Meets Advanced Robotic Manipulation. Inf. Fusion 2024, 105, 102221. [Google Scholar] [CrossRef]
  23. Page, M.J.; Moher, D.; Bossuyt, P.M.; Boutron, I.; Hoffmann, T.C.; Mulrow, C.D.; Shamseer, L.; Tetzlaff, J.M.; Akl, E.A.; Brennan, S.E.; et al. PRISMA 2020 Explanation and Elaboration: Updated Guidance and Exemplars for Reporting Systematic Reviews. BMJ 2021, n160. [Google Scholar] [CrossRef] [PubMed]
  24. Bertino, A.; Bagheri, M.; Krstić, M.; Naseradinmousavi, P. Experimental Autonomous Deep Learning-Based 3D Path Planning for a 7-DOF Robot Manipulator. In Proceedings of the Volume 2: Modeling and Control of Engine and Aftertreatment Systems; Modeling and Control of IC Engines and Aftertreatment Systems; Modeling and Validation; Motion Planning and Tracking Control; Multi-Agent and Networked Systems; Renewable and Smart Energy Systems; Thermal Energy Systems; Uncertain Systems and Robustness; Unmanned Ground and Aerial Vehicles; Vehicle Dynamics and Stability; Vibrations: Modeling, Analysis, and Control; American Society of Mechanical Engineers: Park City, Utah, USA, 8 October 2019; Volume 2, p. V002T14A002. [Google Scholar]
  25. Catalán, J.M.; Trigili, E.; Nann, M.; Blanco-Ivorra, A.; Lauretti, C.; Cordella, F.; Ivorra, E.; Armstrong, E.; Crea, S.; Alcañiz, M.; et al. Hybrid Brain/Neural Interface and Autonomous Vision-Guided Whole-Arm Exoskeleton Control to Perform Activities of Daily Living (ADLs). J. NeuroEngineering Rehabil. 2023, 20, 61. [Google Scholar] [CrossRef]
  26. Chen, C.-S.; Hu, N.-T. Eye-in-Hand Robotic Arm Gripping System Based on Machine Learning and State Delay Optimization. Sensors 2023, 23, 1076. [Google Scholar] [CrossRef]
  27. Chen, X.; Guhl, J. Industrial Robot Control with Object Recognition Based on Deep Learning. Procedia CIRP 2018, 76, 149–154. [Google Scholar] [CrossRef]
  28. Ghiasvand, S.; Xie, W.-F.; Mohebbi, A. Deep Neural Network-Based Robotic Visual Servoing for Satellite Target Tracking. Front. Robot. AI 2024, 11, 1469315. [Google Scholar] [CrossRef] [PubMed]
  29. Gul, A.N.A.; Sahin, M.; Kandis, T.; Kavrak, K.; Oner, Z. Robotic Arm Control Using Machine Learning-Based EOG Signal Classifier. In Proceedings of the 2023 Medical Technologies Congress (TIPTEKNO), November 10 2023; IEEE: Famagusta, Cyprus; pp. 1–4. [Google Scholar]
  30. Kazemzadeh Heris, P.; Khamesee, M. Design and Fabrication of a Magnetic Actuator for Torque and Force Control Estimated by the ANN/SA Algorithm. Micromachines 2022, 13, 327. [Google Scholar] [CrossRef]
  31. Kirda, A.W.; Majewski, P.; Bursy, G.; Bartoszuk, M.; Yassin, H.; Królczyk, G.; Akbar, N.A.; Caesarendra, W. Integrating YOLOv5, Jetson Nano Microprocessor, and Mitsubishi Robot Manipulator for Real-Time Machine Vision Application in Manufacturing: A Lab Experimental Study. Adv. Sci. Technol. Res. J. 2025, 19, 248–270. [Google Scholar] [CrossRef]
  32. Kondratenko, Y.; Atamanyuk, I.; Sidenko, I.; Kondratenko, G.; Sichevskyi, S. Machine Learning Techniques for Increasing Efficiency of the Robot’s Sensor and Control Information Processing. Sensors 2022, 22, 1062. [Google Scholar] [CrossRef]
  33. Kruzic, S.; Music, J.; Kamnik, R.; Papic, V. Estimating Robot Manipulator End-Effector Forces Using Deep Learning. In Proceedings of the 2020 43rd International Convention on Information, Communication and Electronic Technology (MIPRO), September 28 2020; IEEE: Opatija, Croatia; pp. 1163–1168. [Google Scholar]
  34. Liu, J.; Balatti, P.; Ellis, K.; Hadjivelichkov, D.; Stoyanov, D.; Ajoudani, A.; Kanoulas, D. Garbage Collection and Sorting with a Mobile Manipulator Using Deep Learning and Whole-Body Control. In Proceedings of the 2020 IEEE-RAS 20th International Conference on Humanoid Robots (Humanoids), July 19 2021; IEEE: Munich, Germany; pp. 408–414. [Google Scholar]
  35. Liu, Y.; Xu, H.; Liu, D.; Wang, L. A Digital Twin-Based Sim-to-Real Transfer for Deep Reinforcement Learning-Enabled Industrial Robot Grasping. Robot. Comput.-Integr. Manuf. 2022, 78, 102365. [Google Scholar] [CrossRef]
  36. Luo, Y.; Li, S.; Li, D. Intelligent Perception System of Robot Visual Servo for Complex Industrial Environment. Sensors 2020, 20, 7121. [Google Scholar] [CrossRef]
  37. Marchionna, L.; Pugliese, G.; Martini, M.; Angarano, S.; Salvetti, F.; Chiaberge, M. Deep Instance Segmentation and Visual Servoing to Play Jenga with a Cost-Effective Robotic System. Sensors 2023, 23, 752. [Google Scholar] [CrossRef]
  38. Martin, J.B.; Moutarde, F. Real-Time Gestural Control of Robot Manipulator Through Deep Learning Human-Pose Inference. In Computer Vision Systems; Lecture Notes in Computer Science; Tzovaras, D., Giakoumis, D., Vincze, M., Argyros, A., Eds.; Springer International Publishing: Cham, 2019; Vol. 11754, pp. 565–572. ISBN 978-3-030-34994-3. [Google Scholar]
  39. Panasiuk, J. Controlling an Industrial Robot Using Stereo 3D Vision Systems with AI Elements. Sensors 2025, 25, 6402. [Google Scholar] [CrossRef]
  40. Piltan, F.; Prosvirin, A.E.; Sohaib, M.; Saldivar, B.; Kim, J.-M. An SVM-Based Neural Adaptive Variable Structure Observer for Fault Diagnosis and Fault-Tolerant Control of a Robot Manipulator. Appl. Sci. 2020, 10, 1344. [Google Scholar] [CrossRef]
  41. Piltan, F.; Prosvirin, A.E.; Kim, J.-M. Robot Manipulator Active Fault-Tolerant Control Using a Machine Learning-Based Automated Robust Hybrid Observer. J. Intell. Fuzzy Syst. 2020, 39, 6443–6463. [Google Scholar] [CrossRef]
  42. Sacchi, N.; Incremona, G.P.; Ferrara, A. Sliding Mode Based Fault Diagnosis with Deep Reinforcement Learning Add-ons for Intrinsically Redundant Manipulators. Int. J. Robust Nonlinear Control 2023, 33, 9109–9127. [Google Scholar] [CrossRef]
  43. Shukla, P.; Kumar, H.; Nandi, G.C. Robotic Grasp Manipulation Using Evolutionary Computing and Deep Reinforcement Learning. Intell. Serv. Robot. 2021, 14, 61–77. [Google Scholar] [CrossRef]
  44. Wang, Z.; Huang, W.; Qi, Z.; Yin, S. MS-CLSTM: Myoelectric Manipulator Gesture Recognition Based on Multi-Scale Feature Fusion CNN-LSTM Network. Biomimetics 2024, 9, 784. [Google Scholar] [CrossRef] [PubMed]
  45. Ahn, W.-J.; Choi, K.; Kang, S.-W.; Rho, C.-K.; Pae, D.-S.; Lim, M.-T. Practical Mixed Palletizing Manipulator System: Incorporating Practical Reinforcement Learning and Configuration-Space Motion Planning. IEEE Trans. Autom. Sci. Eng. 2026, 23, 455–469. [Google Scholar] [CrossRef]
  46. Ak, A.; Topuz, V.; Midi, I. Motor Imagery EEG Signal Classification Using Image Processing Technique over GoogLeNet Deep Learning Algorithm for Controlling the Robot Manipulator. Biomed. Signal Process. Control 2022, 72, 103295. [Google Scholar] [CrossRef]
  47. Andersen, T.T.; Amor, H.B.; Andersen, N.A.; Ravn, O. Measuring and Modelling Delays in Robot Manipulators for Temporally Precise Control Using Machine Learning. In Proceedings of the 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), Miami, FL, USA, December 2015; IEEE; pp. 168–175. [Google Scholar]
  48. Andriyanov, N. Development of Apple Detection System and Reinforcement Learning for Apple Manipulator. Electronics 2023, 12, 727. [Google Scholar] [CrossRef]
  49. Azizi, A. Applications of Artificial Intelligence Techniques to Enhance Sustainability of Industry 4.0: Design of an Artificial Neural Network Model as Dynamic Behavior Optimizer of Robotic Arms. Complexity 2020, 2020, 1–10. [Google Scholar] [CrossRef]
  50. Batzianoulis, I.; Iwane, F.; Wei, S.; Correia, C.G.P.R.; Chavarriaga, R.; Millán, J.D.R.; Billard, A. Customizing Skills for Assistive Robotic Manipulators, an Inverse Reinforcement Learning Approach with Error-Related Potentials. Commun. Biol. 2021, 4, 1406. [Google Scholar] [CrossRef]
  51. Bucinskas, V.; Dzedzickis, A.; Sumanas, M.; Sutinys, E.; Petkevicius, S.; Butkiene, J.; Virzonis, D.; Morkvenaite-Vilkonciene, I. Improving Industrial Robot Positioning Accuracy to the Microscale Using Machine Learning Method. Machines 2022, 10, 940. [Google Scholar] [CrossRef]
  52. Cheng, S.; Jin, Y.; Wang, H. Deep Learning-Based Control Framework for Dynamic Contact Processes in Humanoid Grasping. Front. Neurorobotics 2024, 18, 1349752. [Google Scholar] [CrossRef]
  53. Chen, Y.-H.; Yang, W.-T.; Chen, B.-H.; Lin, P.-C. Manipulator Trajectory Optimization Using Reinforcement Learning on a Reduced-Order Dynamic Model with Deep Neural Network Compensation. Machines 2023, 11, 350. [Google Scholar] [CrossRef]
  54. Chi, W.; Liu, J.; Abdelaziz, M.E.M.K.; Dagnino, G.; Riga, C.; Bicknell, C.; Yang, G.-Z. Trajectory Optimization of Robot-Assisted Endovascular Catheterization with Reinforcement Learning. In Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 2018; IEEE: Madrid; pp. 3875–3881. [Google Scholar]
  55. Ebert, F.; Finn, C.; Dasari, S.; Xie, A.; Lee, A.; Levine, S. Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control 2018.
  56. Emamzadeh, M.M.; Sadati, N. A Fuzzy Based Model Coordination for Two-Level Optimal Control of Robot Manipulators. In Proceedings of the 2015 IEEE 27th International Conference on Tools with Artificial Intelligence (ICTAI), November 2015; IEEE: Vietri sul Mare, Italy; pp. 1122–1128. [Google Scholar]
  57. Jaquier, N.; Rozo, L.; Caldwell, D.G.; Calinon, S. Geometry-Aware Manipulability Learning, Tracking, and Transfer. Int. J. Robot. Res. 2021, 40, 624–650. [Google Scholar] [CrossRef] [PubMed]
  58. Karimi, M.; Ahmadi, M. A Reinforcement Learning Approach in Assignment of Task Priorities in Kinematic Control of Redundant Robots. IEEE Robot. Autom. Lett. 2022, 7, 850–857. [Google Scholar] [CrossRef]
  59. Kim, M.; Han, D.-K.; Park, J.-H.; Kim, J.-S. Motion Planning of Robot Manipulators for a Smoother Path Using a Twin Delayed Deep Deterministic Policy Gradient with Hindsight Experience Replay. Appl. Sci. 2020, 10, 575. [Google Scholar] [CrossRef]
  60. Kwon, Y.-T.; Kim, H.; Mahmood, M.; Kim, Y.-S.; Demolder, C.; Yeo, W.-H. Printed, Wireless, Soft Bioelectronics and Deep Learning Algorithm for Smart Human–Machine Interfaces. ACS Appl. Mater. Interfaces 2020, 12, 49398–49406. [Google Scholar] [CrossRef] [PubMed]
  61. Lee, J.Y.; Lee, S.; Mishra, A.; Yan, X.; McMahan, B.; Gaisford, B.; Kobashigawa, C.; Qu, M.; Xie, C.; Kao, J.C. Brain–Computer Interface Control with Artificial Intelligence Copilots. Nat. Mach. Intell. 2025, 7, 1510–1523. [Google Scholar] [CrossRef] [PubMed]
  62. Liu, H.; Li, X.; Dong, M.; Gu, Y.; Shen, B. Robotic Motion Planning Based on Deep Reinforcement Learning and Artificial Neural Networks. IEEE Trans. Autom. Sci. Eng. 2025, 22, 8465–8479. [Google Scholar] [CrossRef]
  63. Liu, W.; Niu, H.; Pan, W.; Herrmann, G.; Carrasco, J. Sim-and-Real Reinforcement Learning for Manipulation: A Consensus-Based Approach. In Proceedings of the 2023 IEEE International Conference on Robotics and Automation (ICRA), May 29 2023; pp. 3911–3917. [Google Scholar]
  64. Liu, W.; Niu, H.; Skilton, R.; Carrasco, J. Sim-to-Real Deep Reinforcement Learning with Manipulators for Pick-and-Place; 2023; Vol. 14136, pp. 240–252. [Google Scholar]
  65. Li, X.; Liu, H.; Dong, M. A General Framework of Motion Planning for Redundant Robot Manipulator Based on Deep Reinforcement Learning. IEEE Trans. Ind. Inform. 2022, 18, 5253–5263. [Google Scholar] [CrossRef]
  66. Li, Q.; Nie, J.; Wang, H.; Lu, X.; Song, S. Manipulator Motion Planning Based on Actor-Critic Reinforcement Learning. In Proceedings of the 2021 40th Chinese Control Conference (CCC), July 26 2021; IEEE: Shanghai, China; pp. 4248–4254. [Google Scholar]
  67. Li, H.; Gong, D.; Yu, J. An Obstacles Avoidance Method for Serial Manipulator Based on Reinforcement Learning and Artificial Potential Field. Int. J. Intell. Robot. Appl. 2021, 5, 186–202. [Google Scholar] [CrossRef]
  68. Parag, A.; Mansard, N.; Misimi, E. Optimizing Complex Control Systems with Differentiable Simulators: A Hybrid Approach to Reinforcement Learning and Trajectory Planning. In Proceedings of the 2025 IEEE International Conference on Robotics and Automation (ICRA), Atlanta, GA, USA, May 19 2025; IEEE; pp. 9214–9220. [Google Scholar]
  69. Parák, R.; Kůdela, J.; Matoušek, R.; Juříček, M. Deep-Reinforcement-Learning-Based Motion Planning for a Wide Range of Robotic Structures. Computation 2024, 12, 116. [Google Scholar] [CrossRef]
  70. Prianto, E.; Park, J.-H.; Bae, J.-H.; Kim, J.-S. Deep Reinforcement Learning-Based Path Planning for Multi-Arm Manipulators with Periodically Moving Obstacles. Appl. Sci. 2021, 11, 2587. [Google Scholar] [CrossRef]
  71. Sacchi, N.; Sangiovanni, B.; Incremona, G.P.; Ferrara, A. Scenario-Based Collision Avoidance Control with Deep Q-Networks for Industrial Robot Manipulators. In Proceedings of the 2021 60th IEEE Conference on Decision and Control (CDC), December 14 2021; IEEE: Austin, TX, USA; pp. 4388–4393. [Google Scholar]
  72. Solowjow, E.; Ugalde, I.; Shahapurkar, Y.; Aparicio, J.; Mahler, J.; Satish, V.; Goldberg, K.; Claussen, H. Industrial Robot Grasping with Deep Learning Using a Programmable Logic Controller (PLC). In Proceedings of the 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE), August 2020; IEEE: Hong Kong, Hong Kong; pp. 97–103. [Google Scholar]
  73. Sunwoo, Y.; Lee, W.C. Optimal Path Search for Robot Manipulator Using Deep Reinforcement Learning. In Smart Process. Comput.; IEIE, Translator; 2021; Volume 10, pp. 424–430. [Google Scholar] [CrossRef]
  74. Wang, Y.; Beltran-Hernandez, C.C.; Wan, W.; Harada, K. An Adaptive Imitation Learning Framework for Robotic Complex Contact-Rich Insertion Tasks. Front. Robot. AI 2022, 8, 777363. [Google Scholar] [CrossRef]
  75. Wang, X.; Cao, J.; Cao, Y.; Zou, F. Energy-Efficient Trajectory Planning for a Class of Industrial Robots Using Parallel Deep Reinforcement Learning. Nonlinear Dyn. 2025, 113, 8491–8511. [Google Scholar] [CrossRef]
  76. Wang, H.; Zhu, H.; Cao, F. Trajectory Planning Algorithm of Manipulator in Small Space Based on Reinforcement Learning. In Proceedings of the 2023 China Automation Congress (CAC), November 17 2023; IEEE: Chongqing, China; pp. 5780–5785. [Google Scholar]
  77. Sara Wilson, K.; Saravanan, K.K. Artificial Intelligent Based Control Strategy for Reach and Grasp of Multi-Objects Using Brain-Controlled Robotic Arm System. Netw. Comput. Neural Syst. 2025, 36, 1253–1281. [Google Scholar] [CrossRef]
  78. Wong, C.-C.; Feng, H.-M.; Lai, Y.-C.; Yu, C.-J. Ant Colony Optimization and Image Model-Based Robot Manipulator System for Pick-and-Place Tasks. J. Intell. Fuzzy Syst. 2019, 36, 1083–1098. [Google Scholar] [CrossRef]
  79. Yang, C.; Chen, C.; He, W.; Cui, R.; Li, Z. Robot Learning System Based on Adaptive Neural Control and Dynamic Movement Primitives. IEEE Trans. Neural Netw. Learn. Syst. 2019, 30, 777–787. [Google Scholar] [CrossRef]
  80. Zhang, B. Research on Trajectory Optimization and Adaptive Control of Manipulator Based on Deep Reinforcement Learning. 2025, 14. [Google Scholar] [CrossRef]
  81. Zhao, B.; Wu, Y.; Wu, C.; Sun, R. Deep Reinforcement Learning Trajectory Planning for Robotic Manipulator Based on Simulation-Efficient Training. Sci. Rep. 2025, 15, 8286. [Google Scholar] [CrossRef] [PubMed]
  82. Zhong, J.; Wang, T.; Cheng, L. Collision-Free Path Planning for Welding Manipulator via Hybrid Algorithm of Deep Reinforcement Learning and Inverse Kinematics. Complex Intell. Syst. 2022, 8, 1899–1912. [Google Scholar] [CrossRef]
  83. Ahmed, S.; Azar, A.T.; Tounsi, M. Design of Adaptive Fractional-Order Fixed-Time Sliding Mode Control for Robotic Manipulators. Entropy 2022, 24, 1838. [Google Scholar] [CrossRef] [PubMed]
  84. Robotic Arm Pick-and-Place Tasks.
  85. Al-Shanoon, A.; Lang, H.; Wang, Y.; Zhang, Y.; Hong, W. Learn to Grasp Unknown Objects in Robotic Manipulation. Intell. Serv. Robot. 2021, 14, 571–582. [Google Scholar] [CrossRef]
  86. Alhousani, N.; Saveriano, M.; Sevinc, I.; Abdulkuddus, T.; Kose, H.; Abu-Dakka, F.J. Geometric Reinforcement Learning for Robotic Manipulation. IEEE Access 2023, 11, 111492–111505. [Google Scholar] [CrossRef]
  87. Aljalbout, E.; Frank, F.; Karl, M.; Van Der Smagt, P. On the Role of the Action Space in Robot Manipulation Learning and Sim-to-Real Transfer. IEEE Robot. Autom. Lett. 2024, 9, 5895–5902. [Google Scholar] [CrossRef]
  88. Alles, M.; Aljalbout, E. Learning to Centralize Dual-Arm Assembly. Front. Robot. AI 2022, 9, 830007. [Google Scholar] [CrossRef]
  89. Amaya, L.; Von Arnim, A. Neurorobotic Reinforcement Learning for Domains with Parametrical Uncertainty. Front. Neurorobotics 2023, 17, 1239581. [Google Scholar] [CrossRef] [PubMed]
  90. An, T.; Zhu, X.; Ma, B.; Jiang, H.; Dong, B. Hierarchical Approximate Optimal Interaction Control of Human-Centered Modular Robot Manipulator Systems: A Stackelberg Differential Game-Based Approach. Neurocomputing 2024, 585, 127573. [Google Scholar] [CrossRef]
  91. Avhad, P.; Kumar, G.P.; Sunil, A.T.; Rallapalli, M.; Kumar, B.H.; Kumar, V. Adaptive Deep Reinforcement Learning for Robotic Manipulation in Dynamic Environments. In Proceedings of the 2024 International Conference on Data Science and Network Security (ICDSNS), July 26 2024; IEEE: Tiptur, India; pp. 1–5. [Google Scholar]
  92. Azimirad, V.; Khodkam, S.Y.; Bolouri, A. A New Hybrid Learning Control System for Robots Based on Spiking Neural Networks. Neural Netw. 2024, 180, 106656. [Google Scholar] [CrossRef]
  93. Valarezo Añazco, E.; Rivera Lopez, P.; Park, N.; Oh, J.; Ryu, G.; Al-antari, M.A.; Kim, T.-S. Natural Object Manipulation Using Anthropomorphic Robotic Hand through Deep Reinforcement Learning and Deep Grasping Probability Network. Appl. Intell. 2021, 51, 1041–1055. [Google Scholar] [CrossRef]
  94. Baek, S.; Baek, J.; Choi, J.; Han, S. A Reinforcement Learning-Based Adaptive Time-Delay Control and Its Application to Robot Manipulators. In Proceedings of the 2022 American Control Conference (ACC), Atlanta, GA, USA, June 8 2022; IEEE; pp. 2722–2729. [Google Scholar]
  95. Barnoy, Y.; Erin, O.; Raval, S.; Pryor, W.; Mair, L.O.; Weinberg, I.N.; Diaz-Mercado, Y.; Krieger, A.; Hager, G.D. Control of Magnetic Surgical Robots With Model-Based Simulators and Reinforcement Learning. IEEE Trans. Med. Robot. Bionics 2022, 4, 945–956. [Google Scholar] [CrossRef]
  96. Bashabsheh, M. Reinforcement Learning for Multi-Task Manipulation in Robotic Arm Systems Operating in Dynamic Environments.
  97. Bejar, E.; Moran, A. Predictive Control of a Robot Manipulator with Deep Reinforcement Learning. In Proceedings of the 2021 7th International Conference on Control, Automation and Robotics (ICCAR), April 23 2021; IEEE: Singapore; pp. 127–130. [Google Scholar]
  98. Blaise, J.; Bazzocchi, M.C.F. Space Manipulator Collision Avoidance Using a Deep Reinforcement Learning Control. Aerospace 2023, 10, 778. [Google Scholar] [CrossRef]
  99. Brito, T.; Queiroz, J.; Piardi, L.; Fernandes, L.A.; Lima, J.; Leitão, P. A Machine Learning Approach for Collaborative Robot Smart Manufacturing Inspection for Quality Control Systems. Procedia Manuf. 2020, 51, 11–18. [Google Scholar] [CrossRef]
  100. Calderón-Cordova, C.; Sarango, R.; Castillo, D.; Lakshminarayanan, V. A Deep Reinforcement Learning Framework for Control of Robotic Manipulators in Simulated Environments. IEEE Access 2024, 12, 103133–103161. [Google Scholar] [CrossRef]
  101. Cao, S.; Sun, L.; Jiang, J.; Zuo, Z. Reinforcement Learning-Based Fixed-Time Trajectory Tracking Control for Uncertain Robotic Manipulators With Input Saturation. IEEE Trans. Neural Netw. Learn. Syst. 2023, 34, 4584–4595. [Google Scholar] [CrossRef]
  102. Carron, A.; Arcari, E.; Wermelinger, M.; Hewing, L.; Hutter, M.; Zeilinger, M.N. Data-Driven Model Predictive Control for Trajectory Tracking With a Robotic Arm. IEEE Robot. Autom. Lett. 2019, 4, 3758–3765. [Google Scholar] [CrossRef]
  103. Castelli, F.; Michieletto, S.; Ghidoni, S.; Pagello, E. A Machine Learning-Based Visual Servoing Approach for Fast Robot Control in Industrial Setting. Int. J. Adv. Robot. Syst. 2017, 14, 1729881417738884. [Google Scholar] [CrossRef]
  104. Chen, D.; Zhang, Y.; Li, S. Zeroing Neural-Dynamics Approach and Its Robust and Rapid Solution for Parallel Robot Manipulators against Superposition of Multiple Disturbances. Neurocomputing 2018, 275, 845–858. [Google Scholar] [CrossRef]
  105. Chen, H. Robotic Manipulation with Reinforcement Learning, State Representation Learning, and Imitation Learning (Student Abstract). Proc. AAAI Conf. Artif. Intell. 2021, 35, 15769–15770. [Google Scholar] [CrossRef]
  106. Chen, L.; Jiang, Z.; Cheng, L.; Knoll, A.C.; Zhou, M. Deep Reinforcement Learning Based Trajectory Planning Under Uncertain Constraints. Front. Neurorobotics 2022, 16, 883562. [Google Scholar] [CrossRef] [PubMed]
  107. Chen, Y.; Ma, G.; Lin, S.; Ning, S.; Gao, J. Computed-Torque plus Robust Adaptive Compensation Control for Robot Manipulator with Structured and Unstructured Uncertainties. IMA J. Math. Control Inf. 2016, 33, 37–52. [Google Scholar] [CrossRef]
  108. Chen, P.; Pei, J.; Lu, W.; Li, M. A Deep Reinforcement Learning Based Method for Real-Time Path Planning and Dynamic Obstacle Avoidance. Neurocomputing 2022, 497, 64–75. [Google Scholar] [CrossRef]
  109. Chen, P.; Lu, W. Deep Reinforcement Learning Based Moving Object Grasping. Inf. Sci. 2021, 565, 62–76. [Google Scholar] [CrossRef]
  110. Chen, S.; Wen, J.T. Industrial Robot Trajectory Tracking Control Using Multi-Layer Neural Networks Trained by Iterative Learning Control. Robotics 2021, 10, 50. [Google Scholar] [CrossRef]
  111. Chen, X. Robotic Arm Control Method Based on Reinforcement Learning Optimization. In Proceedings of the 2025 IEEE 5th International Conference on Electronic Technology, Communication and Information (ICETCI), Changchun, China, May 23 2025; IEEE; pp. 221–225. [Google Scholar]
  112. Chen, Y.-L.; Cai, Y.-R.; Cheng, M.-Y. Vision-Based Robotic Object Grasping—A Deep Reinforcement Learning Approach. Machines 2023, 11, 275. [Google Scholar] [CrossRef]
  113. Chen, Y.; Wu, T.; Wang, S.; Feng, X.; Jiang, J.; McAleer, S.M.; Dong, H.; Lu, Z.; Zhu, S.-C.; Yang, Y. Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning.
  114. Chen, Y.; Geng, Y.; Zhong, F.; Ji, J.; Jiang, J.; Lu, Z.; Dong, H.; Yang, Y. Bi-DexHands: Towards Human-Level Bimanual Dexterous Manipulation. IEEE Trans. Pattern Anal. Mach. Intell. 2024, 46, 2804–2818. [Google Scholar] [CrossRef]
  115. Chen, Y.; Zeng, C.; Wang, Z.; Lu, P.; Yang, C. Zero-Shot Sim-to-Real Transfer of Reinforcement Learning Framework for Robotics Manipulation with Demonstration and Force Feedback. Robotica 2023, 41, 1015–1024. [Google Scholar] [CrossRef]
  116. Chen, Y.; Su, S.; Ni, K.; Li, C. Integrated Intelligent Control of Redundant Degrees-of-Freedom Manipulators via the Fusion of Deep Reinforcement Learning and Forward Kinematics Models. Machines 2024, 12, 667. [Google Scholar] [CrossRef]
  117. Christen, S.; Stevsic, S.; Hilliges, O. Demonstration-Guided Deep Reinforcement Learning of Control Policies for Dexterous Human-Robot Interaction. In Proceedings of the 2019 International Conference on Robotics and Automation (ICRA), May 2019; IEEE: Montreal, QC, Canada; pp. 2161–2167. [Google Scholar]
  118. Chu, C.; Takahashi, K.; Hashimoto, M. Comparison of Deep Reinforcement Learning Algorithms in a Robot Manipulator Control Application. In Proceedings of the 2020 International Symposium on Computer, Consumer and Control (IS3C), November 2020; IEEE: Taichung City, Taiwan; pp. 284–287. [Google Scholar]
  119. Cotrim, L.P.; José, M.M.; Cabral, E.L.L. Reinforcement Learning Control of Robot Manipulator. Rev. Bras. Comput. Apl. 2021, 13, 42–53. [Google Scholar] [CrossRef]
  120. Cui, Y.; Xu, Z.; Zhong, L.; Xu, P.; Shen, Y.; Tang, Q. A Task-Adaptive Deep Reinforcement Learning Framework for Dual-Arm Robot Manipulation. IEEE Trans. Autom. Sci. Eng. 2025, 22, 466–479. [Google Scholar] [CrossRef]
  121. Cutler, E.; Xing, Y.; Cui, T.; Zhou, B.; van Rijnsoever, K.; Hart, B.; Valencia, D.; Ong, L.V.C.; Gee, T.; Liarokapis, M.; et al. Benchmarking Reinforcement Learning Methods for Dexterous Robotic Manipulation with a Three-Fingered Gripper 2024.
  122. Ding, Z.; Tsai, Y.-Y.; Lee, W.W.; Huang, B. Sim-to-Real Transfer for Robotic Manipulation with Tactile Sensory. In Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 27 2021; IEEE: Prague, Czech Republic; pp. 6778–6785. [Google Scholar]
  123. Dong, H. Intelligent Adaptive Control Algorithm Based on Reinforcement Learning in the Field of Robotics. In Proceedings of Fifth Doctoral Symposium on Computational Intelligence; Lecture Notes in Networks and Systems; Swaroop, A., Kansal, V., Fortino, G., Hassanien, A.E., Eds.; Springer Nature Singapore: Singapore, 2024; Vol. 1085, pp. 143–152. ISBN 978-981-97-6725-0. [Google Scholar]
  124. Dong, R.; Du, J.; Liu, Y.; Heidari, A.A.; Chen, H. An Enhanced Deep Deterministic Policy Gradient Algorithm for Intelligent Control of Robotic Arms. Front. Neuroinformatics 2023, 17, 1096053. [Google Scholar] [CrossRef]
  125. Salt Ducaju, J.M.; Olofsson, B.; Johansson, R. Iterative Reference Learning for Cartesian Impedance Control of Robot Manipulators. In Proceedings of the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 14 2024; IEEE: Abu Dhabi, United Arab Emirates; pp. 11171–11178. [Google Scholar]
  126. Du, Z.; Wang, W.; Yan, Z.; Dong, W.; Wang, W. Variable Admittance Control Based on Fuzzy Reinforcement Learning for Minimally Invasive Surgery Manipulator. Sensors 2017, 17, 844. [Google Scholar] [CrossRef] [PubMed]
  127. Ehrlich, M.; Zaidel, Y.; Weiss, P.L.; Melamed Yekel, A.; Gefen, N.; Supic, L.; Ezra Tsur, E. Adaptive Control of a Wheelchair Mounted Robotic Arm with Neuromorphically Integrated Velocity Readings and Online-Learning. Front. Neurosci. 2022, 16, 1007736. [Google Scholar] [CrossRef] [PubMed]
  128. Enayati, A.M.S.; Dershan, R.; Zhang, Z.; Richert, D.; Najjaran, H. Facilitating Sim-to-Real by Intrinsic Stochasticity of Real-Time Simulation in Reinforcement Learning for Robot Manipulation. IEEE Trans. Artif. Intell. 2024, 5, 1791–1804. [Google Scholar] [CrossRef]
  129. Fareh, R.; Siddique, T.; Choutri, K.; Dylov, D.V. Physics-Informed Reward Shaped Reinforcement Learning Control of a Robot Manipulator. Ain Shams Eng. J. 2025, 16, 103595. [Google Scholar] [CrossRef]
  130. Filho, E.; Campos, M.F.M.; Neto, A.A. Kinematic Control of Manipulators Using Multi Deep Q-Learning. In Proceedings of the 2025 Brazilian Conference on Robotics (CROS), Belo Horizonte, Brazil, April 28 2025; IEEE; pp. 1–6. [Google Scholar]
  131. Franceschetti, A.; Tosello, E.; Castaman, N.; Ghidoni, S. Robotic Arm Control and Task Training through Deep Reinforcement Learning 2020.
  132. Fu, Z.; Cheng, X.; Pathak, D. Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion 2022.
  133. Ganie, I.; Sarangapani, J. Lifelong Deep Learning-based Control of Robot Manipulators. Int. J. Adapt. Control Signal Process. 2023, 37, 3169–3192. [Google Scholar] [CrossRef]
  134. Gao, X. Design of Intelligent Control System of Manipulator Based on Deep Learning. In Proceedings of the 2022 2nd International Conference on Computers and Automation (CompAuto), Paris, France, August 2022; IEEE; pp. 99–102. [Google Scholar]
  135. Garcia-Hernando, G.; Johns, E.; Kim, T.-K. Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learning. In Proceedings of the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 24 2020; IEEE: Las Vegas, NV, USA; pp. 9561–9568. [Google Scholar]
  136. Gawali, M.B.; Gawali, S.S.; Patil, M.; Khandare, A. A Novel Human-to-Robot Interaction Model Based on Transfer Expert Reinforcement Learning with Recurrent Neural Network. J. Auton. Intell. 2023, 7. [Google Scholar] [CrossRef]
  137. Ghediri, A.; Lamamra, K. Adaptive PID Computed-Torque Control of Robot Manipulators Based on DDPG Reinforcement Learning. [CrossRef]
  138. Grandesso, G. Reinforcement Learning and Trajectory Optimization for the Concurrent Design of High-Performance Robotic Systems.
  139. Gupta, R.K.; Chauhan, S. Comparision of PID Controller & Adaptive Neuro Fuzzy Controller for Robot Manipulator. In Proceedings of the 2015 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), December 2015; IEEE: Madurai, India; pp. 1–4. [Google Scholar]
  140. Gu, S.; Holly, E.; Lillicrap, T.; Levine, S. Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates. In Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA), May 2017; IEEE: Singapore, Singapore; pp. 3389–3396. [Google Scholar]
  141. Haiderbhai, M.; Gondokaryono, R.; Wu, A.; Kahrs, L.A. Sim2Real Rope Cutting With a Surgical Robot Using Vision-Based Reinforcement Learning. IEEE Trans. Autom. Sci. Eng. 2025, 22, 4354–4365. [Google Scholar] [CrossRef]
  142. Hardman, D.; George Thuruthel, T.; Iida, F. Manipulation of Free-Floating Objects Using Faraday Flows and Deep Reinforcement Learning. Sci. Rep. 2022, 12, 335. [Google Scholar] [CrossRef]
  143. Hazem, Z.B.; Saidi, F.; Guler, N.; Altaif, A.H. Reinforcement Learning-Based Intelligent Trajectory Tracking for a 5-DOF Mitsubishi Robotic Arm: Comparative Evaluation of DDPG, LC-DDPG, and TD3-ADX. Int. J. Intell. Robot. Appl. 2025, 9, 1982–2002. [Google Scholar] [CrossRef]
  144. Heaton, J.; Givigi, S. A Deep Reinforcement Learning Solution for the Low Level Motion Control of a Robot Manipulator System. In Proceedings of the 2023 IEEE International Systems Conference (SysCon), Vancouver, BC, Canada, April 17 2023; IEEE; pp. 1–7. [Google Scholar]
  145. He, W.; Huang, H.; Ge, S.S. Adaptive Neural Network Control of a Robotic Manipulator With Time-Varying Output Constraints. IEEE Trans. Cybern. 2017, 47, 3136–3147. [Google Scholar] [CrossRef] [PubMed]
  146. He, W.; Gao, H.; Zhou, C.; Yang, C.; Li, Z. Reinforcement Learning Control of a Flexible Two-Link Manipulator: An Experimental Investigation. IEEE Trans. Syst. Man Cybern. Syst. 2021, 51, 7326–7336. [Google Scholar] [CrossRef]
  147. He, W.; Yan, Z.; Sun, Y.; Ou, Y.; Sun, C. Neural-Learning-Based Control for a Constrained Robotic Manipulator With Flexible Joints. IEEE Trans. Neural Netw. Learn. Syst. 2018, 29, 5993–6003. [Google Scholar] [CrossRef]
  148. Al Homsi, M.; Trumić, M.; Fagiolini, A.; Cirrincione, G. Comparative Analysis of Deep Q-Learning Algorithms for Object Throwing Using a Robot Manipulator. Front. Robot. AI 2025, 12, 1567211. [Google Scholar] [CrossRef]
  149. Hosny, Z.; Nassar, A.; AboElyazeed, A.; Mohamed, M.; Abouheaf, M.; Gueaieb, W. An Online Model-Free Reinforcement Learning Approach for 6-DOF Robot Manipulators. In Proceedings of the 2023 IEEE International Symposium on Robotic and Sensors Environments (ROSE), November 6 2023; IEEE: Tokyo, Japan; pp. 1–7. [Google Scholar]
  150. Huang, Y.; Liu, D.; Liu, Z.; Wang, K.; Wang, Q.; Tan, J. A Novel Robotic Grasping Method for Moving Objects Based on Multi-Agent Deep Reinforcement Learning. Robot. Comput.-Integr. Manuf. 2024, 86, 102644. [Google Scholar] [CrossRef]
  151. Hu, J.; Wang, F.; Yi, J.; Li, X.; Xie, Z. Trajectory Tracking Control Based on Deep Reinforcement Learning and Ensemble Random Network Distillation for Robotic Manipulator. J. Phys. Conf. Ser. 2024, 2850, 012007. [Google Scholar] [CrossRef]
  152. Hu, J.; Mao, J.; Zhou, X.; Zhang, C. Real-Time Obstacle Avoidance and Pathfinding for Robot Manipulators Based on Deep Reinforcement Learning. In Intelligent Robotics and Applications; Lecture Notes in Computer Science; Lan, X., Mei, X., Jiang, C., Zhao, F., Tian, Z., Eds.; Springer Nature Singapore: Singapore, 2025; Vol. 15203, pp. 154–166. ISBN 978-981-96-0794-5. [Google Scholar]
  153. Hu, Y.; Si, B. A Reinforcement Learning Neural Network for Robotic Manipulator Control. Neural Comput. 2018, 30, 1983–2004. [Google Scholar] [CrossRef]
  154. Hu, Y.; Wang, W.; Liu, H.; Liu, L. Reinforcement Learning Tracking Control for Robotic Manipulator With Kernel-Based Dynamic Model. IEEE Trans. Neural Netw. Learn. Syst. 2020, 31, 3570–3578. [Google Scholar] [CrossRef]
  155. Hu, Z.; Zheng, Y.; Pan, J. Grasping Living Objects With Adversarial Behaviors Using Inverse Reinforcement Learning. IEEE Trans. Robot. 2023, 39, 1151–1163. [Google Scholar] [CrossRef]
  156. Hwang, J.-H.; Kang, Y.-C.; Park, J.-W.; Kim, D.W. Advanced Interval Type-2 Fuzzy Sliding Mode Control for Robot Manipulator. Comput. Intell. Neurosci. 2017, 2017, 1–11. [Google Scholar] [CrossRef]
  157. Incremona, G.P.; Sacchi, N.; Sangiovanni, B.; Ferrara, A. Experimental Assessment of Deep Reinforcement Learning for Robot Obstacle Avoidance: A LPV Control Perspective. IFAC-Pap. 2021, 54, 89–94. [Google Scholar] [CrossRef]
  158. Iqdymat, A.; Stamatescu, G. Reinforcement Learning of a Six-DOF Industrial Manipulator for Pick-and-Place Application Using Efficient Control in Warehouse Management. Sustainability 2025, 17, 432. [Google Scholar] [CrossRef]
  159. Iriondo, A.; Lazkano, E.; Susperregi, L.; Urain, J.; Fernandez, A.; Molina, J. Pick and Place Operations in Logistics Using a Mobile Manipulator Controlled with Deep Reinforcement Learning. Appl. Sci. 2019, 9, 348. [Google Scholar] [CrossRef]
  160. Iwasaki, H.; Okuyama, A. Development of a Reference Signal Self-Organizing Control System Based on Deep Reinforcement Learning. In Proceedings of the 2021 IEEE International Conference on Mechatronics (ICM), March 7 2021; IEEE: Kashiwa, Japan; pp. 1–5. [Google Scholar]
  161. James, S.; Johns, E. 3D Simulation for Robot Arm Control with Deep Q-Learning 2016.
  162. Jeong, J.-H.; Shim, K.-H.; Kim, D.-J.; Lee, S.-W. Brain-Controlled Robotic Arm System Based on Multi-Directional CNN-BiLSTM Network Using EEG Signals. IEEE Trans. Neural Syst. Rehabil. Eng. 2020, 28, 1226–1238. [Google Scholar] [CrossRef]
  163. Jiang, D.; Wang, H.; Lu, Y. Mastering the Complex Assembly Task With a Dual-Arm Robot: A Novel Reinforcement Learning Method. IEEE Robot. Autom. Mag. 2023, 30, 57–66. [Google Scholar] [CrossRef]
  164. Jiang, H.; An, T.; Zhang, Z.; Zhu, M.; Li, Y.; Dong, B. Adaptive Fuzzy Optimal Control of Modular Robot Manipulators Systems via Integral Reinforcement Learning-Based Value Iteration Algorithm. In Proceedings of the 2024 IEEE 14th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), July 16 2024; IEEE: Copenhagen, Denmark; pp. 388–393. [Google Scholar]
  165. Jiang, R.; He, B.; Wang, Z.; Zhou, Y.; Xu, S.; Li, X. A Novel Simulation-Reality Closed-Loop Learning Framework for Autonomous Robot Skill Learning. IEEE Trans. Cogn. Dev. Syst. 2022, 14, 1520–1531. [Google Scholar] [CrossRef]
  166. Jin, L.; Huang, R.; Liu, M.; Ma, X. Cerebellum-Inspired Learning and Control Scheme for Redundant Manipulators at Joint Velocity Level. IEEE Trans. Cybern. 2024, 54, 6297–6306. [Google Scholar] [CrossRef]
  167. Joshi, S.; Kumra, S.; Sahin, F. Robotic Grasping Using Deep Reinforcement Learning. In Proceedings of the 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE), August 2020; IEEE: Hong Kong, Hong Kong; pp. 1461–1466. [Google Scholar]
  168. Josifovski, J.; Malmir, M.; Klarmann, N.; Žagar, B.L.; Navarro-Guerrero, N.; Knoll, A. Analysis of Randomization Effects on Sim2Real Transfer in Reinforcement Learning for Robotic Manipulation Tasks. In Proceedings of the 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 23 2022; IEEE: Kyoto, Japan; pp. 10193–10200. [Google Scholar]
  169. Kalashnikov, D.; Irpan, A.; Pastor, P.; Ibarz, J.; Herzog, A.; Jang, E.; Quillen, D.; Holly, E.; Kalakrishnan, M.; Vanhoucke, V.; et al. Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation. 2018. [Google Scholar] [CrossRef]
  170. Kamali, K.; Bonev, I.A.; Desrosiers, C. Real-Time Motion Planning for Robotic Teleoperation Using Dynamic-Goal Deep Reinforcement Learning. In Proceedings of the 2020 17th Conference on Computer and Robot Vision (CRV), Ottawa, ON, Canada, May 2020; IEEE; pp. 182–189. [Google Scholar]
  171. Kang, E.; Qiao, H.; Gao, J.; Yang, W. Neural Network-Based Model Predictive Tracking Control of an Uncertain Robotic Manipulator with Input Constraints. ISA Trans. 2021, 109, 89–101. [Google Scholar] [CrossRef] [PubMed]
  172. Kankashvar, M.R.; Kharrati, H.; Asl, R.M.; Sadeghiani, A.B. Designing PID Controllers for a Five-Bar Linkage Robot Manipulator Using BBO Algorithm. In Proceedings of the 2015 6th International Conference on Modeling, Simulation, and Applied Optimization (ICMSAO), May 2015; IEEE: Istanbul, Turkey; pp. 1–6. [Google Scholar]
  173. Kataoka, S.; Ghasemipour, S.K.S.; Freeman, D.; Mordatch, I. Bi-Manual Manipulation and Attachment via Sim-to-Real Reinforcement Learning 2022.
  174. Katyal, K.; Wang, I.-J.; Burlina, P. Leveraging Deep Reinforcement Learning for Reaching Robotic Tasks. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), July 2017; IEEE: Honolulu, HI, USA; pp. 490–491. [Google Scholar]
  175. Kaur, C.; Balobaid, A. Artificial Intelligence in Robotics: Revolutionizing Industrial Automation and Beyond. In Proceedings of the 2025 International Conference on Frontier Technologies and Solutions (ICFTS), Chennai, India, March 27 2025; IEEE; pp. 1–7. [Google Scholar]
  176. Khan, A.H.; Li, S.; Luo, X. Obstacle Avoidance and Tracking Control of Redundant Robotic Manipulator: An RNN-Based Metaheuristic Approach. IEEE Trans. Ind. Inform. 2020, 16, 4670–4680. [Google Scholar] [CrossRef]
  177. Khodamipour, G.; Khorashadizadeh, S.; Farshad, M. Observer-Based Adaptive Control of Robot Manipulators Using Reinforcement Learning and the Fourier Series Expansion. Trans. Inst. Meas. Control 2021, 43, 2307–2320. [Google Scholar] [CrossRef]
  178. Kilinc, O.; Montana, G. Reinforcement Learning for Robotic Manipulation Using Simulated Locomotion Demonstrations. Mach. Learn. 2022, 111, 465–486. [Google Scholar] [CrossRef]
  179. Kim, M.; Yang, S.; Kim, B.; Kim, J.; Kim, D. Human-to-Robot Handover Based on Reinforcement Learning. Sensors 2024, 24, 6275. [Google Scholar] [CrossRef]
  180. Kuang, Y. Deep Reinforcement Learning and Transfer Learning of Robot In-Hand Dexterous Manipulation; 2023. [Google Scholar]
  181. Kumar, S.; Rani, K.; Banga, K.V. Robotic Arm Movement Optimization Using Soft Computing. IAES Int. J. Robot. Autom. IJRA 2017, 6, 1. [Google Scholar] [CrossRef]
  182. Kumar, V.; Hoeller, D.; Sundaralingam, B.; Tremblay, J.; Birchfield, S. Joint Space Control via Deep Reinforcement Learning. In Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 27 2021; IEEE: Prague, Czech Republic; pp. 3619–3626. [Google Scholar]
  183. Kunal, K.; Kathiravan, M.; Madeshwaren, V.; Chandrakala, T.; Ganesan, V.; Gupta, S. AI-Driven Intelligent Control Strategies for Industrial Robotics: A Reinforcement Learning Approach. Int. J. Basic Appl. Sci. 2025, 14, 429–440. [Google Scholar] [CrossRef]
  184. Kurrek, P.; Zoghlami, F.; Jocas, M.; Stoelen, M.; Salehi, V. Q-Model: An Artificial Intelligence Based Methodology for the Development of Autonomous Robots. J. Comput. Inf. Sci. Eng. 2020, 20, 061006. [Google Scholar] [CrossRef]
  185. Lahmann, J.; Erwin, A. Series Elastic Actuation Improves Dynamic Performance after Reinforcement Learning. IFAC-Pap. 2025, 59, 479–484. [Google Scholar] [CrossRef]
  186. Lee, C.; An, D. AI-Based Posture Control Algorithm for a 7-DOF Robot Manipulator. Machines 2022, 10, 651. [Google Scholar] [CrossRef]
  187. Lee, D.; Kim, H.; Kim, S.; Park, C.-W.; Park, J.H. Learning Control Policy with Previous Experiences from Robot Simulator. In Proceedings of the 2020 International Conference on Information and Communication Technology Convergence (ICTC), October 21 2020; IEEE: Jeju, Korea (South); pp. 863–865. [Google Scholar]
  188. Lee, J.Y.; Lee, S.; Mishra, A.; Yan, X.; McMahan, B.; Gaisford, B.; Kobashigawa, C.; Qu, M.; Xie, C.; Kao, J.C. Non-Invasive Brain-Machine Interface Control with Artificial Intelligence Copilots 2024.
  189. Liang, X.; Yao, Z.; Ge, Y.; Yao, J. Reinforcement Learning Based Adaptive Control for Uncertain Mechanical Systems with Asymptotic Tracking. Def. Technol. 2024, 34, 19–28. [Google Scholar] [CrossRef]
  190. Lin, T.; Sachdev, K.; Fan, L.; Malik, J.; Zhu, Y. Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids 2025.
  191. Lin, X.; Liu, R. A Distributed Cerebellar-Inspired Learning Model for Robotic Arm Control. In Proceedings of the 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), July 2017; IEEE: Seogwipo; pp. 929–932. [Google Scholar]
  192. Lin, Y.; Church, A.; Yang, M.; Li, H.; Lloyd, J.; Zhang, D.; Lepora, N.F. Bi-Touch: Bimanual Tactile Manipulation With Sim-to-Real Deep Reinforcement Learning. IEEE Robot. Autom. Lett. 2023, 8, 5472–5479. [Google Scholar] [CrossRef]
  193. Lin, Y.; Lloyd, J.; Church, A.; Lepora, N.F. Tactile Gym 2.0: Sim-to-Real Deep Reinforcement Learning for Comparing Low-Cost High-Resolution Robot Touch. IEEE Robot. Autom. Lett. 2022, 7, 10754–10761. [Google Scholar] [CrossRef]
  194. Liu, A.; Zhao, H.; Song, T.; Liu, Z.; Wang, H.; Sun, D. Adaptive Control of Manipulator Based on Neural Network. Neural Comput. Appl. 2021, 33, 4077–4085. [Google Scholar] [CrossRef]
  195. Liu, D.; Wang, Z.; Lu, B.; Cong, M.; Yu, H.; Zou, Q. A Reinforcement Learning-Based Framework for Robot Manipulation Skill Acquisition. IEEE Access 2020, 8, 108429–108437. [Google Scholar] [CrossRef]
  196. Liu, J.; Yap, H.J.; Khairuddin, A.S.M. Path Planning for the Robotic Manipulator in Dynamic Environments Based on a Deep Reinforcement Learning Method. J. Intell. Robot. Syst. 2024, 111, 3. [Google Scholar] [CrossRef]
  197. Liu, N.; Lu, T.; Cai, Y.; Wang, R.; Wang, S. Real-World Robot Reaching Skill Learning Based on Deep Reinforcement Learning. In Proceedings of the 2020 Chinese Control And Decision Conference (CCDC), August 2020; IEEE: Hefei, China; pp. 4780–4784. [Google Scholar]
  198. Liu, N.; Li, L.; Hao, B.; Yang, L.; Hu, T.; Xue, T.; Wang, S. Modeling and Simulation of Robot Inverse Dynamics Using LSTM-Based Deep Learning Algorithm for Smart Cities and Factories. IEEE Access 2019, 7, 173989–173998. [Google Scholar] [CrossRef]
  199. Liu, W.; Niu, H.; Mahyuddin, M.N.; Herrmann, G.; Carrasco, J. A Model-Free Deep Reinforcement Learning Approach for Robotic Manipulators Path Planning. In Proceedings of the 2021 21st International Conference on Control, Automation and Systems (ICCAS), October 12 2021; IEEE: Jeju, Korea, Republic of; pp. 512–517. [Google Scholar]
  200. Liu, X.; Wang, G.; Liu, Z.; Liu, Y.; Liu, Z.; Huang, P. Hierarchical Reinforcement Learning Integrating With Human Knowledge for Practical Robot Skill Learning in Complex Multi-Stage Manipulation. IEEE Trans. Autom. Sci. Eng. 2024, 21, 3852–3862. [Google Scholar] [CrossRef]
  201. Li, C.; Liu, Z.; Li, L.; Ji, Z.; Li, C.; Liang, J.; Li, Y. Improved PPO Optimization for Robotic Arm Grasping Trajectory Planning and Real-Robot Migration. Sensors 2025, 25, 5253. [Google Scholar] [CrossRef]
  202. Li, Q.; Pang, Y.; Wang, Y.; Han, X.; Li, Q.; Zhao, M. CBMC: A Biomimetic Approach for Control of a 7-Degree of Freedom Robotic Arm. Biomimetics 2023, 8, 389. [Google Scholar] [CrossRef] [PubMed]
  203. Li, R. Image Features for Vision-Based Robot Manipulation Based on Deep Reinforcement Learning. In Proceedings of the 2021 IEEE 17th International Conference on Intelligent Computer Communication and Processing (ICCP), October 28 2021; IEEE: Cluj-Napoca, Romania; pp. 359–364. [Google Scholar]
  204. Li, X.; Serlin, Z.; Yang, G.; Belta, C. A Formal Methods Approach to Interpretable Reinforcement Learning for Robotic Planning. Sci. Robot. 2019, 4, eaay6276. [Google Scholar] [CrossRef]
  205. Li, X.; Zhong, J.; Kamruzzaman, M.M. Complicated Robot Activity Recognition by Quality-Aware Deep Reinforcement Learning. Future Gener. Comput. Syst. 2021, 117, 480–485. [Google Scholar] [CrossRef]
  206. Li, X.; Zhao, J.; Wang, A.; Huang, Y. Sliding Mode Control for Uncertain Robot Manipulators Based on Reinforcement Learning. In Proceedings of the 2024 6th International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI), December 6 2024; IEEE: Nanjing, China; pp. 74–79. [Google Scholar]
  207. Li, Y.; Chen, L.; Tee, K.P.; Li, Q. Reinforcement Learning Control for Coordinated Manipulation of Multi-Robots. Neurocomputing 2015, 170, 168–175. [Google Scholar] [CrossRef]
  208. Li, Y.; Hao, X.; She, Y.; Li, S.; Yu, M. Constrained Motion Planning of Free-Float Dual-Arm Space Manipulator via Deep Reinforcement Learning. Aerosp. Sci. Technol. 2021, 109, 106446. [Google Scholar] [CrossRef]
  209. Li, Z.; Li, S. Neural Network Model-Based Control for Manipulator: An Autoencoder Perspective. IEEE Trans. Neural Netw. Learn. Syst. 2023, 34, 2854–2868. [Google Scholar] [CrossRef] [PubMed]
  210. Li, Z.; Zhao, T.; Chen, F.; Hu, Y.; Su, C.-Y.; Fukuda, T. Reinforcement Learning of Manipulation and Grasping Using Dynamical Movement Primitives for a Humanoidlike Mobile Manipulator. IEEEASME Trans. Mechatron. 2018, 23, 121–131. [Google Scholar] [CrossRef]
  211. Lobbezoo, A.; Kwon, H.-J. Simulated and Real Robotic Reach, Grasp, and Pick-and-Place Using Combined Reinforcement Learning and Traditional Controls. Robotics 2023, 12, 12. [Google Scholar] [CrossRef]
  212. Luo, J.; Solowjow, E.; Wen, C.; Ojea, J.A.; Agogino, A.M. Deep Reinforcement Learning for Robotic Assembly of Mixed Deformable and Rigid Objects. In Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 2018; IEEE: Madrid; pp. 2062–2069. [Google Scholar]
  213. Luo, J.; Xu, C.; Wu, J.; Levine, S. Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning 2025.
  214. Luo, Y.; Cong, Y.; Du, H.; Zhu, W.; Shen, Z. Finite-Time Active Disturbance Rejection Trajectory Tracking Control of Robot Manipulators via PPO Algorithm. In Proceedings of the 2025 44th Chinese Control Conference (CCC), Chongqing, China, July 28 2025; IEEE; pp. 552–557. [Google Scholar]
  215. Majumder, S.; Sahoo, S.R. Enhancing 3D Trajectory Tracking of Robotic Manipulator Using Sequential Deep Reinforcement Learning with Disturbance Rejection. In Proceedings of the 2024 European Control Conference (ECC), Stockholm, Sweden, June 25 2024; IEEE; pp. 2512–2517. [Google Scholar]
  216. Majumder, S.; Sahoo, S.R. A Reinforcement-Learning Approach to Control Robotic Manipulator Based on Improved DDPG. In Proceedings of the 2023 Ninth Indian Control Conference (ICC), December 18 2023; IEEE: Visakhapatnam, India; pp. 281–286. [Google Scholar]
  217. Maldonado-Ramirez, A.; Rios-Cabrera, R.; Lopez-Juarez, I. A Visual Path-Following Learning Approach for Industrial Robots Using DRL. Robot. Comput.-Integr. Manuf. 2021, 71, 102130. [Google Scholar] [CrossRef]
  218. Malik, A.; Lischuk, Y.; Henderson, T.; Prazenica, R. A Deep Reinforcement-Learning Approach for Inverse Kinematics Solution of a High Degree of Freedom Robotic Manipulator. Robotics 2022, 11, 44. [Google Scholar] [CrossRef]
  219. Mannaa, A.S.; Zarubin, A.O. Manipulators with Machine Learning-Based Control with Reinforcement. In Proceedings of the 2023 V International Conference on Control in Technical Systems (CTS), September 21 2023; IEEE: Saint Petersburg, Russian Federation; pp. 232–234. [Google Scholar]
  220. Mao, J.; Hu, J.; Zhou, X.; Zhang, C.; Yang, J.; Wang, H. Real-Time Safe and Smooth Visual Servoing for Robot Manipulators via Reinforcement Learning. IEEE Trans. Ind. Electron. 2025, 1–12. [Google Scholar] [CrossRef]
  221. Matas, J.; James, S.; Davison, A.J. Sim-to-Real Reinforcement Learning for Deformable Object Manipulation.
  222. Mazzaglia, P.; Backshall, N.; Ma, X.; James, S. Redundancy-Aware Action Spaces for Robot Learning. IEEE Robot. Autom. Lett. 2024, 9, 6912–6919. [Google Scholar] [CrossRef]
  223. Ma, X.; Wen, Z.; Hu, T.; Zheng, X. Bridging Embodiment and Learning: A Machine Learning Framework for Next-Generation Embodied Intelligence. In Proceedings of the 2025 7th International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), October 24 2025; IEEE: Hangzhou, China; pp. 68–71. [Google Scholar]
  224. Mellatshahi, N.; Mozaffari, S.; Saif, M.; Alirezaee, S. Inverted Pendulum Control with a Robotic Arm Using Deep Reinforcement Learning. In Proceedings of the 2021 International Symposium on Signals, Circuits and Systems (ISSCS), Iasi, Romania, July 15 2021; IEEE; pp. 1–6. [Google Scholar]
  225. Meyes, R.; Tercan, H.; Roggendorf, S.; Thiele, T.; Büscher, C.; Obdenbusch, M.; Brecher, C.; Jeschke, S.; Meisen, T. Motion Planning for Industrial Robots Using Reinforcement Learning. Procedia CIRP 2017, 63, 107–112. [Google Scholar] [CrossRef]
  226. Molina, A.M. Learning Robotic Manipulation Tasks Using Relational Reinforcement Learning and Human Demonstrations.
  227. Moon, J.; Bae, S.-H.; Cashmore, M. Meta Reinforcement Learning Based Underwater Manipulator Control. In Proceedings of the 2021 21st International Conference on Control, Automation and Systems (ICCAS), October 12 2021; IEEE: Jeju, Korea, Republic of; pp. 1473–1476. [Google Scholar]
  228. Mueangprasert, M.; Chermprayong, P.; Boonlong, K. Robot Arm Movement Control by Model-Based Reinforcement Learning Using Machine Learning Regression Techniques and Particle Swarm Optimization. In Proceedings of the 2023 Third International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics (ICA-SYMP), January 18 2023; IEEE: Bangkok, Thailand; pp. 83–86. [Google Scholar]
  229. Naranjo-Campos, F.J.; Victores, J.G.; Balaguer, C. Method for Bottle Opening with a Dual-Arm Robot. Biomimetics 2024, 9, 577. [Google Scholar] [CrossRef] [PubMed]
  230. Nguyen Nguyen, L.H.; Dao, M.K.; Hua, H.Q.B.; Pham, P.-T.; Ngo, X.-K.; Nguyen, Q.C. Motion Navigation Algorithm Based on Deep Reinforcement Learning for Manipulators. In Proceedings of the 2023 IEEE 3rd International Conference on Electronic Communications, Internet of Things and Big Data (ICEIB), April 14 2023; IEEE: Taichung, Taiwan; pp. 537–541. [Google Scholar]
  231. Rahimi Nohooji, H.; Zaraki, A.; Voos, H. Actor–Critic Learning Based PID Control for Robotic Manipulators. Appl. Soft Comput. 2024, 151, 111153. [Google Scholar] [CrossRef]
  232. Ouyang, Y.; He, W.; Li, X. Reinforcement Learning Control of a Single-link Flexible Robotic Manipulator. IET Control Theory Appl. 2017, 11, 1426–1433. [Google Scholar] [CrossRef]
  233. Pane, Y.P.; Nageshrao, S.P.; Babuska, R. Actor-Critic Reinforcement Learning for Tracking Control in Robotics. In Proceedings of the 2016 IEEE 55th Conference on Decision and Control (CDC), December 2016; IEEE: Las Vegas, NV, USA; pp. 5819–5826. [Google Scholar]
  234. Pane, Y.P.; Nageshrao, S.P.; Kober, J.; Babuška, R. Reinforcement Learning Based Compensation Methods for Robot Manipulators. Eng. Appl. Artif. Intell. 2019, 78, 236–247. [Google Scholar] [CrossRef]
  235. Pantoja-Garcia, L.; Garcia-Rodriguez, R.; Parra-Vega, V. A Novel Adaptive Actor-Critic Reinforcement Learning Controller for Constrained Robots. In Proceedings of the 2022 IEEE International Conference on Automation/XXV Congress of the Chilean Association of Automatic Control (ICA-ACCA), October 24 2022; IEEE: Curicó, Chile; pp. 1–6. [Google Scholar]
  236. Pan, S.; Cao, F. Deep Reinforcement Learning-Based Control Strategy for Underwater Manipulator Systems. IFAC-Pap. 2025, 59, 430–435. [Google Scholar] [CrossRef]
  237. Pan, Z.; Zhou, J.; Fan, Q.; Feng, Z.; Gao, X.; Su, M. Robotic Control Mechanism Based on Deep Reinforcement Learning. In Proceedings of the 2023 2nd International Symposium on Control Engineering and Robotics (ISCER), February 2023; IEEE: Hangzhou, China; pp. 70–74. [Google Scholar]
  238. Park, S.-Y.; Lee, C.; Kim, H.; Ahn, S.-H. Enhancement of Control Performance for Degraded Robot Manipulators Using Digital Twin and Proximal Policy Optimization. IEEE Access 2024, 12, 19569–19583. [Google Scholar] [CrossRef]
  239. Pavlichenko, D.; Behnke, S. Real-Robot Deep Reinforcement Learning: Improving Trajectory Tracking of Flexible-Joint Manipulator with Reference Correction. In Proceedings of the 2022 International Conference on Robotics and Automation (ICRA), Philadelphia, PA, USA, May 23 2022; IEEE; pp. 2671–2677. [Google Scholar]
  240. Pedersen, O.-M.; Misimi, E.; Chaumette, F. Grasping Unknown Objects by Coupling Deep Reinforcement Learning, Generative Adversarial Networks, and Visual Servoing. In Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, France, May 2020; IEEE; pp. 5655–5662. [Google Scholar]
  241. Perrusquia, A.; Yu, W. Human-Behavior Learning for Infinite-Horizon Optimal Tracking Problems of Robot Manipulators. In Proceedings of the 2021 60th IEEE Conference on Decision and Control (CDC), Austin, TX, USA, December 14 2021; IEEE; pp. 57–62. [Google Scholar]
  242. Perrusquia, A.; Yu, W.; Soria, A. Large Space Dimension Reinforcement Learning for Robot Position/Force Discrete Control. In Proceedings of the 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT), April 2019; IEEE: Paris, France; pp. 91–96. [Google Scholar]
  243. Pham, P.-C.; Kuo, Y.-L. Online Reinforcement Learning Based Real-Time Robust Adaptive Control Design for Robot Manipulators. Int. J. Control Autom. Syst. 2025, 23, 3048–3059. [Google Scholar] [CrossRef]
  244. Polydoros, A.S.; Nalpantidis, L.; Kruger, V. Real-Time Deep Learning of Robotic Manipulator Inverse Dynamics. In Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 2015; IEEE: Hamburg, Germany; pp. 3442–3448. [Google Scholar]
  245. Popov, I.; Heess, N.; Lillicrap, T.; Hafner, R.; Barth-Maron, G.; Vecerik, M.; Lampe, T.; Tassa, Y.; Erez, T.; Riedmiller, M. Data-Efficient Deep Reinforcement Learning for Dexterous Manipulation. [CrossRef]
  246. Qiao, D.; Zhong, Z.; Zhang, H.; Zhao, Y. Trajectory Planning of Manipulator Based on DQN Algorithm Guided by MPC Sampling. In Proceedings of the 2021 3rd International Symposium on Robotics & Intelligent Manufacturing Technology (ISRIMT), September 24 2021; IEEE: Changzhou, China; pp. 319–323. [Google Scholar]
  247. Qin, Y.; Huang, B.; Yin, Z.-H.; Su, H.; Wang, X. DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation.
  248. Qi, G.; Li, Y. Reinforcement Learning Control for Robot Arm Grasping Based on Improved DDPG. In Proceedings of the 2021 40th Chinese Control Conference (CCC), July 26 2021; IEEE: Shanghai, China; pp. 4132–4137. [Google Scholar]
  249. Quillen, D.; Jang, E.; Nachum, O.; Finn, C.; Ibarz, J.; Levine, S. Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods. In Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, QLD, May 2018; IEEE; pp. 6284–6291. [Google Scholar]
  250. Rajeswaran, A.; Kumar, V.; Gupta, A.; Vezzani, G.; Schulman, J.; Todorov, E.; Levine, S. Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations 2018.
  251. Ramirez, J.; Yu, W. Redundant Robot Control with Learning from Expert Demonstrations. In Proceedings of the 2022 IEEE Symposium Series on Computational Intelligence (SSCI), December 4 2022; IEEE: Singapore, Singapore; pp. 715–720. [Google Scholar]
  252. Ramirez, J.; Yu, W. Reinforcement Learning from Expert Demonstrations with Application to Redundant Robot Control. Eng. Appl. Artif. Intell. 2023, 119, 105753. [Google Scholar] [CrossRef]
  253. Ren, B.; Wang, Y.; Chen, J. Trajectory-Tracking-Based Adaptive Neural Network Sliding Mode Controller for Robot Manipulators. J. Comput. Inf. Sci. Eng. 2020, 20, 031009. [Google Scholar] [CrossRef]
  254. Ren, H.; Ben-Tzvi, P. Learning Inverse Kinematics and Dynamics of a Robotic Manipulator Using Generative Adversarial Networks. Robot. Auton. Syst. 2020, 124, 103386. [Google Scholar] [CrossRef]
  255. Rizzardo, C.; Chen, F.; Caldwell, D. Sim-to-Real via Latent Prediction: Transferring Visual Non-Prehensile Manipulation Policies. Front. Robot. AI 2023, 9, 1067502. [Google Scholar] [CrossRef]
  256. Rubagotti, M.; Sangiovanni, B.; Nurbayeva, A.; Incremona, G.P.; Ferrara, A.; Shintemirov, A. Shared Control of Robot Manipulators With Obstacle Avoidance: A Deep Reinforcement Learning Approach. IEEE Control Syst. 2023, 43, 44–63. [Google Scholar] [CrossRef]
  257. Saeed, M.; Nagdi, M.; Rosman, B.; Ali, H.H.S.M. Deep Reinforcement Learning for Robotic Hand Manipulation. In Proceedings of the 2020 International Conference on Computer, Control, Electrical, and Electronics Engineering (ICCCEEE), February 26 2021; IEEE: Khartoum, Sudan; pp. 1–5. [Google Scholar]
  258. Sahu, U.K.; Patra, D.; Subudhi, B. Deep Reinforcement Learning Controller for Vision-Based Serial Flexible Link Manipulator. In Proceedings of the 2021 International Symposium of Asian Control Association on Intelligent Robotics and Industrial Automation (IRIA), September 20 2021; IEEE: Goa, India; pp. 331–336. [Google Scholar]
  259. Saidi, K.; Boumediene, A.; Boubekeur, D. An Optimal GA-Based Backstepping Control Scheme for a MIMO Nonlinear System. J. Eur. Systèmes Autom. 2023, 56, 89–96. [Google Scholar] [CrossRef]
  260. Said, A.; Khalil, A.; Petra, R.; Yunus, S.; Peng, A.S.; Khan, S. PID Controller Optimization of Teleoperated 2DOF Robot Manipulator Using Artificial Bee Colony Algorithm. In Proceedings of the 2019 IEEE 6th International Conference on Engineering Technologies and Applied Sciences (ICETAS), December 2019; IEEE: Kuala Lumpur, Malaysia; pp. 1–6. [Google Scholar]
  261. Sajadi, S.M.; Karbasi, S.M.; Brun, H.; Tørresen, J.; Elle, O.J.; Mathiassen, K. Towards Autonomous Robotic Biopsy—Design, Modeling and Control of a Robot for Needle Insertion of a Commercial Full Core Biopsy Instrument. Front. Robot. AI 2022, 9, 896267. [Google Scholar] [CrossRef]
  262. Sangiovanni, B.; Incremona, G.P.; Piastra, M.; Ferrara, A. Self-Configuring Robot Path Planning With Obstacle Avoidance via Deep Reinforcement Learning. IEEE Control Syst. Lett. 2021, 5, 397–402. [Google Scholar] [CrossRef]
  263. Sangiovanni, B.; Rendiniello, A.; Incremona, G.P.; Ferrara, A.; Piastra, M. Deep Reinforcement Learning for Collision Avoidance of Robotic Manipulators. In Proceedings of the 2018 European Control Conference (ECC), June 2018; IEEE: Limassol; pp. 2063–2068. [Google Scholar]
  264. Sangiovanni, B.; Incremona, G.P.; Ferrara, A.; Piastra, M. Deep Reinforcement Learning Based Self-Configuring Integral Sliding Mode Control Scheme for Robot Manipulators. In Proceedings of the 2018 IEEE Conference on Decision and Control (CDC), December 2018; IEEE: Miami Beach, FL; pp. 5969–5974. [Google Scholar]
  265. Scheikl, P.M.; Tagliabue, E.; Gyenes, B.; Wagner, M.; Dall’Alba, D.; Fiorini, P.; Mathis-Ullrich, F. Sim-to-Real Transfer for Visual Reinforcement Learning of Deformable Object Manipulation for Robot-Assisted Surgery. IEEE Robot. Autom. Lett. 2023, 8, 560–567. [Google Scholar] [CrossRef]
  266. Sekkat, H.; Tigani, S.; Saadane, R.; Chehri, A. Vision-Based Robotic Arm Control Algorithm Using Deep Reinforcement Learning for Autonomous Objects Grasping. Appl. Sci. 2021, 11, 7917. [Google Scholar] [CrossRef]
  267. Shahid, A.A.; Piga, D.; Braghin, F.; Roveda, L. Continuous Control Actions Learning and Adaptation for Robotic Manipulation through Reinforcement Learning. Auton. Robots 2022, 46, 483–498. [Google Scholar] [CrossRef]
  268. Shahna, M.H.; Adel Alizadeh Kolagar, S.; Mattila, J. Integrating DeepRL with Robust Low-Level Control in Robotic Manipulators for Non-Repetitive Reaching Tasks. In Proceedings of the 2024 IEEE International Conference on Mechatronics and Automation (ICMA), August 4 2024; IEEE: Tianjin, China; pp. 329–336. [Google Scholar]
  269. Shao, H.; Hu, W.; Yang, L.; Wang, W.; Suzuki, S.; Gao, Z. Intelligent Impedance Strategy for Force–Motion Control of Robotic Manipulators in Unknown Environments via Expert-Guided Deep Reinforcement Learning. Processes 2025, 13, 2526. [Google Scholar] [CrossRef]
  270. Shetty, M.; Vishishta, B.; Choragi, S.; Subramanian, K.; George, K. Continuous Control of a Robot Manipulator Using Deep Deterministic Policy Gradient. In Proceedings of the 2021 Seventh Indian Control Conference (ICC), December 20 2021; IEEE: Mumbai, India; pp. 213–218. [Google Scholar]
  271. Shiferaw, B.A.; Agidew, T.F.; Alzahrani, A.S.; Srinivasagan, R. Synergistic Pushing and Grasping for Enhanced Robotic Manipulation Using Deep Reinforcement Learning. Actuators 2024, 13, 316. [Google Scholar] [CrossRef]
  272. Shin, C.; Ferguson, P.W.; Pedram, S.A.; Ma, J.; Dutson, E.P.; Rosen, J. Autonomous Tissue Manipulation via Surgical Robot Using Learning Based Model Predictive Control. In Proceedings of the 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada, May 2019; IEEE; pp. 3875–3881. [Google Scholar]
  273. Siddique, T.; Choutri, K.; Fareh, R.; Dylov, D.; Bettayeb, M. Tracking Control Using Standalone Reinforcement Learning for a Robot Manipulator. In Proceedings of the 2024 Advances in Science and Engineering Technology International Conferences (ASET), June 3 2024; IEEE: Abu Dhabi, United Arab Emirates; pp. 1–6. [Google Scholar]
  274. Simon, J.; Gogolák, L.; Sárosi, J. Deep Reinforcement Learning-Assisted Teaching Strategy for Industrial Robot Manipulator. Appl. Sci. 2024, 14, 10929. [Google Scholar] [CrossRef]
  275. Sivertsvik, M.; Sumskiy, K.; Misimi, E. Learning Active Manipulation to Target Shapes with Model-Free, Long-Horizon Deep Reinforcement Learning. In Proceedings of the 2024 IEEE International Conference on Robotics and Automation (ICRA), May 13 2024; IEEE: Yokohama, Japan; pp. 5411–5418. [Google Scholar]
  276. Song, X.; Xu, P.; Xu, W.; Li, B. Skill Acquisition Framework in Multi-Robot Precision Assembly Based on Cooperative Compliant Control. ISA Trans. 2024, 155, 319–336. [Google Scholar] [CrossRef]
  277. Song, Y.; Li, Z.; Li, B.; Wen, G. Optimized Leader-follower Consensus Control Using Combination of Reinforcement Learning and Sliding Mode Mechanism for Multiple Robot Manipulator System. Int. J. Robust Nonlinear Control 2024, 34, 5212–5228. [Google Scholar] [CrossRef]
  278. Staley, E.W.; Katyal, K.D.; Burlina, P. DRL Based Intelligent Joint Manipulator and Viewing Camera Control for Reaching Tasks and Environments with Obstacles and Occluders. In Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), July 2018; IEEE: Rio de Janeiro; pp. 1–7. [Google Scholar]
  279. Sun, C.; Ovtcharova, J. AI-Based Regression Analysis for Optimizing the Performance of Robot Manipulator Trajectory Tracking. In Proceedings of the 2021 21st International Conference on Control, Automation and Systems (ICCAS), Jeju, Korea, Republic of, October 12 2021; IEEE; pp. 489–495. [Google Scholar]
  280. Sun, X.; Li, J.; Kovalenko, A.V.; Feng, W.; Ou, Y. Integrating Reinforcement Learning and Learning From Demonstrations to Learn Nonprehensile Manipulation. IEEE Trans. Autom. Sci. Eng. 2023, 20, 1735–1744. [Google Scholar] [CrossRef]
  281. Sun, Z.; Yuan, K.; Hu, W.; Yang, C.; Li, Z. Learning Pregrasp Manipulation of Objects from Ungraspable Poses. In Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA), May 2020; IEEE: Paris, France; pp. 9917–9923. [Google Scholar]
  282. Su, E.; Jia, C.; Qin, Y.; Zhou, W.; Macaluso, A.; Huang, B.; Wang, X. Sim2Real Manipulation on Unknown Objects with Tactile-Based Reinforcement Learning. In Proceedings of the 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan, May 13 2024; IEEE; pp. 9234–9241. [Google Scholar]
  283. Su, H.; Zhang, Z.; Zhang, W. Adaptive Backstepping Optimal Tracking Control of Interconnected Robotic Manipulator System Based on Reinforcement Learning. IEEE Trans. Autom. Sci. Eng. 2025, 22, 19555–19567. [Google Scholar] [CrossRef]
  284. Su, H.; Qi, W.; Gao, H.; Hu, Y.; Shi, Y.; Ferrigno, G.; Momi, E.D. Machine Learning Driven Human Skill Transferring for Control of Anthropomorphic Manipulators. In Robot. Mechatron.; 2020. [Google Scholar]
  285. Tajdari, F.; Kabganian, M.; Khodabakhshi, E.; Golgouneh, A. Design, Implementation and Control of a Two-Link Fully-Actuated Robot Capable of Online Identification of Unknown Dynamical Parameters Using Adaptive Sliding Mode Controller. In Proceedings of the 2017 Artificial Intelligence and Robotics (IRANOPEN), April 2017; IEEE: Qazvin, Iran; pp. 91–96. [Google Scholar]
  286. Takeda, S.; Yamamori, S.; Yagi, S.; Morimoto, J. Hierarchically Connecting Modularly-Learned Policies to Generate a Controller for a Combined Robot System. In Proceedings of the 2025 IEEE 21st International Conference on Automation Science and Engineering (CASE), Los Angeles, CA, USA, August 17 2025; IEEE; pp. 1722–1727. [Google Scholar]
  287. Tang, W.; Cheng, C.; Ai, H.; Chen, L. Dual-Arm Robot Trajectory Planning Based on Deep Reinforcement Learning under Complex Environment. Micromachines 2022, 13, 564. [Google Scholar] [CrossRef] [PubMed]
  288. Uchibe, E.; Doya, K. Forward and Inverse Reinforcement Learning Sharing Network Weights and Hyperparameters. Neural Netw. 2021, 144, 138–153. [Google Scholar] [CrossRef] [PubMed]
  289. Valencia, D.; Jia, J.; Li, R.; Hayashi, A.; Lecchi, M.; Terezakis, R.; Gee, T.; Liarokapis, M.; MacDonald, B.A.; Williams, H. Comparison of Model-Based and Model-Free Reinforcement Learning for Real-World Dexterous Robotic Manipulation Tasks. In Proceedings of the 2023 IEEE International Conference on Robotics and Automation (ICRA), May 29 2023; IEEE: London, United Kingdom; pp. 871–878. [Google Scholar]
  290. Vijay, M.; Jena, D. Backstepping Terminal Sliding Mode Control of Robot Manipulator Using Radial Basis Functional Neural Networks. Comput. Electr. Eng. 2018, 67, 690–707. [Google Scholar] [CrossRef]
  291. Vu, V.T.; Dao, P.N.; Loc, P.T.; Huy, T.Q. Sliding Variable-Based Online Adaptive Reinforcement Learning of Uncertain/Disturbed Nonlinear Mechanical Systems. J. Control Autom. Electr. Syst. 2021, 32, 281–290. [Google Scholar] [CrossRef]
  292. J.K., V; Elumalai, V.K. A Proximal Policy Optimization Based Deep Reinforcement Learning Framework for Tracking Control of a Flexible Robotic Manipulator. Results Eng. 2025, 25, 104178. [Google Scholar] [CrossRef]
  293. Wang, C.; Zhang, Q.; Tian, Q.; Li, S.; Wang, X.; Lane, D.; Petillot, Y.; Wang, S. Learning Mobile Manipulation through Deep Reinforcement Learning. Sensors 2020, 20, 939. [Google Scholar] [CrossRef]
  294. Wang, F.; Hu, J.; Qin, Y.; Guo, F.; Jiang, M. Trajectory Tracking Control Based on Deep Reinforcement Learning for a Robotic Manipulator with an Input Deadzone. Symmetry 2025, 17, 149. [Google Scholar] [CrossRef]
  295. Wang, G.; Xin, M.; Wu, W.; Liu, Z.; Wang, H. Learning of Long-Horizon Sparse-Reward Robotic Manipulator Tasks With Base Controllers. IEEE Trans. Neural Netw. Learn. Syst. 2024, 35, 4072–4081. [Google Scholar] [CrossRef] [PubMed]
  296. Wang, H.; Dong, Z.; Zhu, T.; Lei, H.; Shi, W.; Zhang, Z.; Luo, W.; Wan, W.; Chen, X.; Huang, J. Robot Deformable Object Manipulation via NMPC-Generated Demonstrations in Deep Reinforcement Learning. IEEE Trans. Autom. Sci. Eng. 2025, 22, 23566–23578. [Google Scholar] [CrossRef]
  297. Wang, J.; Zhao, W.; Cao, J.; Park, J.H.; Shen, H. Reinforcement Learning-Based Predefined-Time Tracking Control for Nonlinear Systems Under Identifier-Critic–Actor Structure. IEEE Trans. Cybern. 2024, 54, 6345–6357. [Google Scholar] [CrossRef] [PubMed]
  298. Wang, M.; Yang, A. Dynamic Learning From Adaptive Neural Control of Robot Manipulators With Prescribed Performance. IEEE Trans. Syst. Man Cybern. Syst. 2017, 47, 2244–2255. [Google Scholar] [CrossRef]
  299. Wang, Q.; Sanchez, F.R.; McCarthy, R.; Bulens, D.C.; McGuinness, K.; O’Connor, N.; Wüthrich, M.; Widmaier, F.; Bauer, S.; Redmond, S.J. Dexterous Robotic Manipulation Using Deep Reinforcement Learning and Knowledge Transfer for Complex Sparse Reward-based Tasks. Expert Syst. 2023, 40, e13205. [Google Scholar] [CrossRef]
  300. Wang, S.; Shao, X.; Yang, L.; Liu, N. Deep Learning Aided Dynamic Parameter Identification of 6-DOF Robot Manipulators. IEEE Access 2020, 8, 138102–138116. [Google Scholar] [CrossRef]
  301. Wang, T.; Wang, F.; Xie, Z.; Qin, F. Curiosity Model Policy Optimization for Robotic Manipulator Tracking Control with Input Saturation in Uncertain Environment. Front. Neurorobotics 2024, 18, 1376215. [Google Scholar] [CrossRef]
  302. Wang, Y.; An, T.; Dong, B.; Zhu, M.; Li, Y. A-C-I Fuzzy Logic System Structure-Based Reconfigurable Robot Manipulators Finite-Time Optimal Backstepping Force/Position Control. IEEE Robot. Autom. Lett. 2025, 10, 8730–8737. [Google Scholar] [CrossRef]
  303. Wang, Y.; Wu, Z. Machine Learning Model-based Optimal Tracking Control of Nonlinear Affine Systems with Safety Constraints. Int. J. Robust Nonlinear Control 2025, 35, 511–535. [Google Scholar] [CrossRef]
  304. Wang, Y.; Sagawa, R.; Yoshiyasu, Y. A Hierarchical Robot Learning Framework for Manipulator Reactive Motion Generation via Multi-Agent Reinforcement Learning and Riemannian Motion Policies. IEEE Access 2023, 11, 126979–126994. [Google Scholar] [CrossRef]
  305. Weber, J.; Schmidt, M. An Improved Approach for Inverse Kinematics and Motion Planning of an Industrial Robot Manipulator with Reinforcement Learning. In Proceedings of the 2021 Fifth IEEE International Conference on Robotic Computing (IRC), Taichung, Taiwan, November 2021; IEEE; pp. 10–17. [Google Scholar]
  306. Wu, P.; Su, H.; Dong, H.; Liu, T.; Li, M.; Chen, Z. An Obstacle Avoidance Method for Robotic Arm Based on Reinforcement Learning. Ind. Robot Int. J. Robot. Res. Appl. 2025, 52, 9–17. [Google Scholar] [CrossRef]
  307. Wu, T.; Zhong, F.; Geng, Y.; Wang, H.; Zhu, Y.; Wang, Y.; Dong, H. GraspARL: Dynamic Grasping via Adversarial Reinforcement Learning 2022.
  308. Wu, Y.; Niu, W.; Kong, L.; Yu, X.; He, W. Fixed-Time Neural Network Control of a Robotic Manipulator with Input Deadzone. ISA Trans. 2023, 135, 449–461. [Google Scholar] [CrossRef]
  309. Wu, Y.; Zhang, L.; Wang, Z.; Feng, Y. Output Feedback Control for Uncertain Robot Manipulators Based on Reinforcement Learning. In Proceedings of the Proceedings of the 2024 7th International Conference on Artificial Intelligence and Pattern Recognition, September 20 2024; ACM: Xiamen China; pp. 1136–1140. [Google Scholar]
  310. Wu, Y.; Pan, L.; Wu, W.; Wang, G.; Miao, Y.; Xu, F.; Wang, H. RL-GSBridge: 3D Gaussian Splatting Based Real2Sim2Real Method for Robotic Manipulation Learning. In Proceedings of the 2025 IEEE International Conference on Robotics and Automation (ICRA), Atlanta, GA, USA, May 19 2025; IEEE; pp. 192–198. [Google Scholar]
  311. Xhin, O.Y.; Jo, H.S. Self-Learning Robot Manipulator Controller Using Reinforcement Learning. In Proceedings of the TENCON 2024 - 2024 IEEE Region 10 Conference (TENCON), December 1 2024; IEEE: Singapore, Singapore; pp. 707–710. [Google Scholar]
  312. Xiao, R.; Yang, C.; Jiang, Y.; Zhang, H. One-Shot Sim-to-Real Transfer Policy for Robotic Assembly via Reinforcement Learning with Visual Demonstration. Robotica 2024, 42, 1074–1093. [Google Scholar] [CrossRef]
  313. Xie, J.; Shao, Z.; Li, Y.; Guan, Y.; Tan, J. Deep Reinforcement Learning With Optimized Reward Functions for Robotic Trajectory Planning. IEEE Access 2019, 7, 105669–105679. [Google Scholar] [CrossRef]
  314. Xu, B.; Hassan, T.; Hussain, I. Seg-CURL: Segmented Contrastive Unsupervised Reinforcement Learning for Sim-to-Real in Visual Robotic Manipulation. IEEE Access 2023, 11, 50195–50204. [Google Scholar] [CrossRef]
  315. Xu, S.; Wu, Z. Adaptive Learning Control of Robot Manipulators via Incremental Hybrid Neural Network. Neurocomputing 2024, 568, 127045. [Google Scholar] [CrossRef]
  316. Yang, D.; Miao, C.; Liu, Y.; Du, X.; Zheng, Y. Improved DQN-Based Intelligent Trajectory Control for Coal Gangue Sorting Robotic Manipulators. IEEE Sens. J. 2025, 25, 40632–40650. [Google Scholar] [CrossRef]
  317. Yang, M.; Lin, Y.; Church, A.; Lloyd, J.; Zhang, D.; Barton, D.A.W.; Lepora, N.F. Sim-to-Real Model-Based and Model-Free Deep Reinforcement Learning for Tactile Pushing. IEEE Robot. Autom. Lett. 2023, 8, 5480–5487. [Google Scholar] [CrossRef]
  318. Yang, P.; Zhang, S.; Yu, X.; He, W. Reinforcement-Learning-Based Finite Time Fault Tolerant Control for a Manipulator With Actuator Faults. IEEE Trans. Cybern. 2025, 55, 2621–2632. [Google Scholar] [CrossRef]
  319. Yang, Q.; Zhang, F.; He, W.; Wang, C. Deterministic Learning-Based Knowledge Fusion Neural Control for Robot Manipulators with Predefined Performance. In Intelligent Robotics and Applications; Lecture Notes in Computer Science; Lan, X., Mei, X., Jiang, C., Zhao, F., Tian, Z., Eds.; Springer Nature Singapore: Singapore, 2025; Vol. 15208, pp. 174–188. ISBN 978-981-96-0782-2. [Google Scholar]
  320. Yang, Y.; Ding, Z.; Wang, R.; Modares, H.; Wunsch, D.C. Data-Driven Human-Robot Interaction Without Velocity Measurement Using Off-Policy Reinforcement Learning. IEEECAA J. Autom. Sin. 2022, 9, 47–63. [Google Scholar] [CrossRef]
  321. Yuan, Z.; Wei, T.; Gu, L.; Hua, P.; Liang, T.; Chen, Y.; Xu, H. HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation 2025.
  322. Zhang, F.; Leitner, J.; Milford, M.; Upcroft, B.; Corke, P. Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control 2015.
  323. Zhang, J.; Zhou, X.; Zhou, J.; Qiu, S.; Liang, G.; Cai, S.; Bao, G. A High-Efficient Reinforcement Learning Approach for Dexterous Manipulation. Biomimetics 2023, 8, 264. [Google Scholar] [CrossRef]
  324. Zhang, J. Research on Precise Control and Optimization of Intelligent Robotic Arm Based on Artificial Intelligence. In Proceedings of the 2025 IEEE 7th International Conference on Power, Intelligent Computing and Systems (ICPICS), Shenyang, China, August 29 2025; IEEE; pp. 197–203. [Google Scholar]
  325. Zhang, P.; Zhang, J.; Kan, J. A Research on Manipulator-Path Tracking Based on Deep Reinforcement Learning. Appl. Sci. 2023, 13, 7867. [Google Scholar] [CrossRef]
  326. Zhang, S.; Xia, Q.; Chen, M.; Cheng, S. Multi-Objective Optimal Trajectory Planning for Robotic Arms Using Deep Reinforcement Learning. Sensors 2023, 23, 5974. [Google Scholar] [CrossRef] [PubMed]
  327. Zhang, T.; Zhang, K.; Lin, J.; Louie, W.-Y.G.; Huang, H. Sim2real Learning of Obstacle Avoidance for Robotic Manipulators in Uncertain Environments. IEEE Robot. Autom. Lett. 2022, 7, 65–72. [Google Scholar] [CrossRef]
  328. Zhang, Z.; Chen, Z. Modeling and Control of Robotic Manipulators Based on Symbolic Regression. IEEE Trans. Neural Netw. Learn. Syst. 2023, 34, 2440–2450. [Google Scholar] [CrossRef]
  329. Zhang, Z.; Zheng, C. Simulation of Robotic Arm Grasping Control Based on Proximal Policy Optimization Algorithm. J. Phys. Conf. Ser. 2022, 2203, 012065. [Google Scholar] [CrossRef]
  330. Zhan, A.; Zhao, R.; Pinto, L.; Abbeel, P.; Laskin, M. A Framework for Efficient Robotic Manipulation 2022.
  331. Zhao, C.; Wei, Y.; Xiao, J.; Sun, Y.; Zhang, D.; Guo, Q.; Yang, J. Inverse Kinematics Solution and Control Method of 6-Degree-of-Freedom Manipulator Based on Deep Reinforcement Learning. Sci. Rep. 2024, 14, 12467. [Google Scholar] [CrossRef]
  332. Zhao, W.; Queralta, J.P.; Qingqing, L.; Westerlund, T. Towards Closing the Sim-to-Real Gap in Collaborative Multi-Robot Deep Reinforcement Learning. In Proceedings of the 2020 5th International Conference on Robotics and Automation Engineering (ICRAE), November 20 2020; IEEE: Singapore, Singapore; pp. 7–12. [Google Scholar]
  333. Zheng, L.; Wang, Y.; Yang, R.; Wu, S.; Guo, R.; Dong, E. An Efficiently Convergent Deep Reinforcement Learning-Based Trajectory Planning Method for Manipulators in Dynamic Environments. J. Intell. Robot. Syst. 2023, 107, 50. [Google Scholar] [CrossRef]
  334. Zhou, J.; Zheng, H.; Zhao, D.; Chen, Y. Intelligent Control of Manipulator Based on Deep Reinforcement Learning. In Proceedings of the 2021 12th International Conference on Mechanical and Aerospace Engineering (ICMAE), Athens, Greece, July 16 2021; IEEE; pp. 275–279. [Google Scholar]
  335. Zhu, A.; Ai, H.; Chen, L. A Fuzzy Logic Reinforcement Learning Control with Spring-Damper Device for Space Robot Capturing Satellite. Appl. Sci. 2022, 12, 2662. [Google Scholar] [CrossRef]
  336. Zhu, H.; Gupta, A.; Rajeswaran, A.; Levine, S.; Kumar, V. Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost. In Proceedings of the 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada, May 2019; IEEE; pp. 3651–3657. [Google Scholar]
  337. Zhu, Q.; Bian, J. Reinforcement Learning-Based Optimized Tracking Control for Uncertain Robot Manipulators with Composite Constraints. In Proceedings of the 2025 6th International Conference on Artificial Intelligence and Electromechanical Automation (AIEA), Hefei, China, August 1 2025; IEEE; pp. 432–439. [Google Scholar]
  338. Zong, X.; Tan, S. Deep Reinforcement Learning-Based Multi-Task Optimization Algorithm for Industrial Robots. In Proceedings of the 2025 IEEE 2nd International Conference on Electronics, Communications and Intelligent Science (ECIS), Yueyang, China, May 23 2025; IEEE; pp. 1–5. [Google Scholar]
  339. Modares, H.; Ranatunga, I.; Lewis, F.L.; Popa, D.O. Optimized Assistive Human–Robot Interaction Using Reinforcement Learning. IEEE Trans. Cybern. 2016, 46, 655–667. [Google Scholar] [CrossRef]
  340. Perrusquía, A.; Yu, W.; Soria, A. Position/Force Control of Robot Manipulators Using Reinforcement Learning. Ind. Robot Int. J. Robot. Res. Appl. 2019, 46, 267–280. [Google Scholar] [CrossRef]
  341. Sasaki, M.; Muguro, J.; Kitano, F.; Njeri, W.; Matsushita, K. Sim–Real Mapping of an Image-Based Robot Arm Controller Using Deep Reinforcement Learning. Appl. Sci. 2022, 12, 10277. [Google Scholar] [CrossRef]
  342. Wang, X.; Guo, S.; Xu, Z.; Zhang, Z.; Sun, Z.; Xu, Y. A Robotic Teleoperation System Enhanced by Augmented Reality for Natural Human–Robot Interaction. Cyborg Bionic Syst. 2024, 5, 0098. [Google Scholar] [CrossRef] [PubMed]
  343. AlAttar, A.; Chappell, D.; Kormushev, P. Kinematic-Model-Free Predictive Control for Robotic Manipulator Target Reaching With Obstacle Avoidance. Front. Robot. AI 2022, 9, 809114. [Google Scholar] [CrossRef] [PubMed]
  344. Baselizadeh, A.; Khaksar, W.; Torresen, J. Motion Planning and Obstacle Avoidance for Robot Manipulators Using Model Predictive Control-Based Reinforcement Learning. In Proceedings of the 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC), October 9 2022; IEEE: Prague, Czech Republic; pp. 1584–1591. [Google Scholar]
  345. Ding, Z.; Song, C.; Xu, J.; Dou, Y. Human-Robot Interaction System Design for Manipulator Control Using Reinforcement Learning. In Proceedings of the 2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC), May 28 2021; IEEE: Nanchang, China; pp. 660–665. [Google Scholar]
  346. Haddad, G.S.Q.; Akkar, R.H.A. Intelligent Swarm Algorithms for Optimizing Nonlinear Sliding Mode Controller for Robot Manipulator. Int. J. Electr. Comput. Eng. IJECE 2021, 11, 3943. [Google Scholar] [CrossRef]
  347. Jeong, R.; Aytar, Y.; Khosid, D.; Zhou, Y.; Kay, J.; Lampe, T.; Bousmalis, K.; Nori, F. Self-Supervised Sim-to-Real Adaptation for Visual Robotic Manipulation. In Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, France, May 2020; IEEE; pp. 2718–2724. [Google Scholar]
  348. Jhan, Z.-Y.; Lee, C.-H.; Lin, C.-M. A New Adaptive Fuzzy Neural Force Controller for Robots Manipulator Interacting with Environments. In Proceedings of the 2015 International Conference on Machine Learning and Cybernetics (ICMLC), July 2015; IEEE: Guangzhou, China; pp. 572–577. [Google Scholar]
  349. Kallel, H.; Iqbal, K. Online Estimation of Manipulator Dynamics for Computed Torque Control of Robotic Systems. Sensors 2025, 25, 6831. [Google Scholar] [CrossRef]
  350. Kuang, C.; Han, L.; Liang, K.; Mao, J.; Zhang, C. Self-Optimization Composite Dynamic Control for Trajectory Tracking of Robot Manipulators via Deep Reinforcement Learning. J. Control Decis. 2025, 1–18. [Google Scholar] [CrossRef]
  351. Li, C.; Liu, F.; Wang, Y.; Buss, M. Concurrent Learning-Based Adaptive Control of an Uncertain Robot Manipulator With Guaranteed Safety and Performance. IEEE Trans. Syst. Man Cybern. Syst. 2022, 52, 3299–3313. [Google Scholar] [CrossRef]
  352. Li, J.; Peng, X.; Li, B.; Sreeram, V.; Wu, J.; Chen, Z.; Li, M. Model Predictive Control for Constrained Robot Manipulator Visual Servoing Tuned by Reinforcement Learning. Math. Biosci. Eng. 2023, 20, 10495–10513. [Google Scholar] [CrossRef] [PubMed]
  353. Li, Z.; Liu, J.; Huang, Z.; Peng, Y.; Pu, H.; Ding, L. Adaptive Impedance Control of Human–Robot Cooperation Using Reinforcement Learning. IEEE Trans. Ind. Electron. 2017, 64, 8013–8022. [Google Scholar] [CrossRef]
  354. Lu, T.; Zhang, K.; Shi, Y. Robust Data-Driven Model Predictive Control via On-Policy Reinforcement Learning for Robot Manipulators. In Proceedings of the 2024 IEEE 7th International Conference on Industrial Cyber-Physical Systems (ICPS), St. Louis, MO, USA, May 12 2024; IEEE; pp. 1–6. [Google Scholar]
  355. Pradhan, S.K.; Subudhi, B. Position Control of a Flexible Manipulator Using a New Nonlinear Self-Tuning PID Controller. IEEECAA J. Autom. Sin. 2020, 7, 136–149. [Google Scholar] [CrossRef]
  356. Sacchi, N.; Incremona, G.P.; Ferrara, A. Integral Sliding Modes Generation via DRL-Assisted Lyapunov-Based Control for Robot Manipulators. In Proceedings of the 2023 European Control Conference (ECC), Bucharest, Romania, June 13 2023; IEEE; pp. 1–6. [Google Scholar]
  357. Shcherbakov, V.; Bragina, A.; Shiryaev, V. Robot Manipulator Control Using Predictive Model under Conditions of Incomplete Information. In Proceedings of the 2020 Global Smart Industry Conference (GloSIC), November 17 2020; IEEE: Chelyabinsk, Russia; pp. 281–286. [Google Scholar]
  358. Wu, H.; Yang, J.; Huang, S.; Li, J. Adaptive Optimal Admittance Control for Robotic Precision Grinding Based on Improved Normalized Advantage Function. IEEEASME Trans. Mechatron. 2025, 30, 5166–5178. [Google Scholar] [CrossRef]
  359. Xie, Z.; Sun, T.; Kwan, T.; Wu, X. Motion Control of a Space Manipulator Using Fuzzy Sliding Mode Control with Reinforcement Learning. Acta Astronaut. 2020, 176, 156–172. [Google Scholar] [CrossRef]
  360. Yousef, H.; Siddique, T.; Fareh, R.; Choutri, K.; Dylov, D.; Khadraoui, S. Reinforcement Learning-Tuned Active Disturbance Rejection Controller for Tracking Control of a 4-DoF Robot Manipulator. In Proceedings of the 2024 12th International Conference on Control, Mechatronics and Automation (ICCMA), November 11 2024; IEEE: London, United Kingdom; pp. 125–130. [Google Scholar]
  361. Zhang, Y.; Mo, K.; Shen, F.; Xu, X.; Zhang, X.; Yu, J.; Yu, C. Self-Adaptive Robust Motion Planning for High DoF Robot Manipulator Using Deep MPC. In Proceedings of the 2024 3rd International Conference on Robotics, Artificial Intelligence and Intelligent Control (RAIIC), July 5 2024; IEEE: Mianyang, China; pp. 139–143. [Google Scholar]
Preprints 205721 g001
Figure 1. PRISMA flow diagram of the search and selection process.
Figure 1. PRISMA flow diagram of the search and selection process.
Preprints 205721 g001
Preprints 205721 g002
Figure 2. The distribution of publications in AI-based robot manipulator control from 2015 to 2015.
Figure 2. The distribution of publications in AI-based robot manipulator control from 2015 to 2015.
Preprints 205721 g002
Preprints 205721 g003
Figure 3. The distribution of publications in AI-based robot manipulator control by functional roles.
Figure 3. The distribution of publications in AI-based robot manipulator control by functional roles.
Preprints 205721 g003
Preprints 205721 g004
Figure 4. The distribution of publications across five categories from 2015 to 2015.
Figure 4. The distribution of publications across five categories from 2015 to 2015.
Preprints 205721 g004
Preprints 205721 g005
Figure 5. Distribution of the top 20 most employed AI methods. (SAC: Soft Actor-Critic; PPO: Proximal Policy Optimization; DDPG: Deep Deterministic Policy Gradient; RL: Reinforcement Learning; DQN: Deep Q-Network; NN: Neural Networks).
Figure 5. Distribution of the top 20 most employed AI methods. (SAC: Soft Actor-Critic; PPO: Proximal Policy Optimization; DDPG: Deep Deterministic Policy Gradient; RL: Reinforcement Learning; DQN: Deep Q-Network; NN: Neural Networks).
Preprints 205721 g005
Preprints 205721 g006
Figure 7. The distribution of evaluation methods among publications.
Figure 7. The distribution of evaluation methods among publications.
Preprints 205721 g006
Table 1. Overview of existing reviews and the scope of this present review.
Table 1. Overview of existing reviews and the scope of this present review.
Review ID Summary Contribution
Mareco et al. [21] This review analyzes the use of AI enabled methods in control systems, focusing on control-oriented techniques such as fuzzy logic, neuro fuzzy control, neural networks, and swarm or evolutionary optimization. The analysis is mainly qualitative and centered on methodological characteristics within specific application settings. Provides a structured mapping of 188 studies across renewable energy, robotics, agriculture, and industrial processes, highlighting how AI has been adopted in application specific control problems. Its value lies in identifying major methodological trends, limitations, and research gaps in intelligent control design.
Nahavandi et al. [22] This review evaluates machine learning for robotic manipulators, covering deep learning, RL, and imitation learning. It analyzes sim-to-real transfer and practical deployment across industrial, medical, and space sectors. Provides a qualitative synthesis of machine learning strategies in robotic manipulation, utilizing algorithmic complexity estimates and tabulated comparisons instead of formal statistical analysis. It offers researchers a structured framework for evaluating the computational trade-offs and practical requirements of various control architectures across diverse operational domains.
Waseem et al. [17] This qualitative review surveys the evolution of robotic manipulator control technologies from 2016 to 2024, spanning methods from classical PID and linear models to intelligent AI, hybrid, and quantum-inspired frameworks. No statistical analysis was performed; the study taxonomizes these strategies by their underlying architecture and optimization logic to highlight current operational trend Provides a foundational mapping of control theories against emerging paradigms such as digital twins, federated learning, and blockchain to address persistent challenges in non-linear dynamics and real-time performance. It informs future research directions by identifying critical gaps in multi-agent system integration and scalable control for unstructured environments.
Our review This review analyzes 343 studies on AI-based robot manipulator control published between 2015 and 2025, focusing on research trends across functional roles, application domains, robot types, and evaluation approaches. It highlights major patterns in the distribution and development of AI methods within the manipulator control pipeline. Provides the first structured quantitative mapping of AI based robot manipulator control over the past decade, together with a unified taxonomy of functional AI roles in the control pipeline. The review identifies major research concentrations and persistent gaps, providing a data driven reference for future development in underrepresented control functions.
Table 2. Databases and boolean search strings.
Table 2. Databases and boolean search strings.
Databases Search Strings
IEEEXplore, PubMed, Scopus ("robot manipulator" OR "robotic arm" OR "industrial robot" OR manipulator) AND (AI OR "artificial intelligence" OR "machine learning" OR "deep learning" OR "reinforcement learning") AND ("control" OR "adaptive control" OR "intelligent control" OR "learning-based control")
Google Scholar ("robot manipulator" OR "robotic arm" OR "industrial robot" OR manipulator) AND (AI OR "artificial intelligence" OR "machine learning" OR "deep learning" OR "reinforcement learning") AND ("control" OR "adaptive control" OR "intelligent control" OR "learning-based control")
"robot manipulator" AND ("reinforcement learning" OR DRL) AND ("trajectory optimization" OR "motion planning" OR control)
"robot manipulator" OR "robotic arm" OR "robotic manipulation" AND ("reinforcement learning" OR DRL OR "deep reinforcement learning") AND (grasping OR "dexterous manipulation" OR "sim-to-real" OR sim2real)
Table 3. AI-based control techniques in robot manipulator control from 2015–2025.
Table 3. AI-based control techniques in robot manipulator control from 2015–2025.
Functional Role Authors Year Robot Types Application Area Control Technique Methods Learning Paradigm Evaluation Method
Perception and Estimation Bertono et al. [24] 2019 Serial NS Learning-based pose estimation CNN Supervised Experiment
Catalán et al. [25] 2023 Exoskeleton Rehabilitation Vision-guided learning-based EEG/EOG classification, RGB-D object pose estimation, DMP Supervised Experiment
Chen et al. [26] 2023 Serial Manufacturing Learning-based grasp planning Min-Pnet, 1D CNN Supervised Both
Chen et al. [27] 2018 Serial Manufacturing Vision-guided learning-based Faster R-CNN Supervised Experiment
Ghiasvand et al. [28] 2024 Serial Aerospace DNN-based visual servoing DNN Supervised Both
Gul et al.[29] 2023 Serial Rehabilitation Learning-based KNN, LSTM, SVM, DT Supervised Experiment
Heris et al. [30] 2022 Magnetic Healthcare Learning-based magnetic field estimation ANN, Simulated Annealing Supervised Both
Kirda et al. [31] 2025 Serial Manufacturing Vision-guided YOLOv5 Supervised Experiment
Kondratenko et al. [32] 2022 Mobile NS ML-based sensor processing Fuzzy logic, neuro-fuzzy, YOLOv2, ResNet34 Supervised Experiment
Kružić et al. [33] 2020 Serial NS Sensorless force estimation for interaction control MLP, 1D CNN, LSTM Supervised Experiment
Liu et al. [34] 2021 Mobile Garbage Management Learning-based YOLACT, GPD Supervised Experiment
Liu et al. [35] 2022 Serial Manufacturing Vision-guided DRL-based DQN, FCN (DenseNet-121) RL Both
Luo et al. [36] 2020 Industrial Manufacturing Vision-guided learning-based YOLO-v2-ROI Supervised Experiment
Marchionna et al. [37] 2023 Serial Dexterity Game Vision-guided visual servoing YOLACT++ Supervised Experiment
Martin et al. [38] 2018 Serial Manufacturing Pose estimation-based OpenPose, HMR Supervised Experiment
Panasiuk [39] 2025 NS Manufacturing Vision-guided positioning YOLOv8 Supervised Experiment
Piltan [40] 2020 Serial Multiple Neuro-fuzzy-based fault-tolerant SVM, NN, Fuzzy logic Supervised Experiment
Pitan et al. [41] 2020 Serial Multiple Adaptive fuzzy fault-tolerant DT, TSK fuzzy Supervised Experiment
Sacchi et al. [42] 2023 Serial NS DRL-based fault estimation TD3 RL Simulation
Shukla et al. [43] 2021 Serial Multiple Learning-based grasp pose estimation GA, DQN RL, Supervised, Evolutionary Experiment
Wang et al. [44] 2024 Myoelectric Rehabilitation sEMG gesture recognition MS-CLSTM, CNN-LSTM Supervised Experiment
Planning Ahn et al. [45] 2025 Serial Logistics Learning-based planning PPO, CMPNet RL, IL Both
Ak et al. [46] 2022 Serial Rehabilitation Learning-based GoogLeNet Supervised Experiment
Andersen et al. [47] 2015 Serial Manufacturing Learning-based predictive NN, RT, GP Supervised Experiment
Andriyanov [48] 2023 Serial Agriculture RL-based planning Q-learning, YOLOv5 RL, Supervised Both
Azizi [49] 2020 Serial Manufacturing Learning-based optimization ANN, GA Supervised Simulation
Batzianouis et al. [50] 2021 Serial Rehabilitation IRL-based planning GP IRL, LDA RL, Supervised Experiment
Bucinskas et al. [51] 2022 Serial Manufacturing DRL-based DQN RL Experiment
Chen et al. [52] 2023 Serial Heatlhcare DRL-based planning PPO, DNN RL, Supervised Both
Cheng et al. [53] 2024 Humanoid NS Learning-based planning CNN Supervised Both
Chi et al. [54] 2018 Platform Healthcare RL-based PI2, DMP RL, IL Both
Ebert et al. [55] 2018 Serial NS Learning-based Video prediction model, Registration network, Meta-learned classifier Self-supervised Both
Emamzadeh et al. [56] 2015 Serial NS Fuzzy-based hierarchical TSK fuzzy predictor Supervised Simulation
Jaquier et al. [57] 2021 Humanoid NS Learning-based Tensor-based GMM, GMR IL, Unsupervised Both
Karimi et al. [58] 2022 Redundant Serial NS DRL-based DQN RL Simulation
Kim et al. [59] 2020 Serial Manufacturing DRL-based planning TD3, HER RL Both
Kwon et al. [60] 2020 Robotic Hand Rehabilitation Learning-based CNN Supervised Experiment
Lee et al. [61] 2025 serial Rehabilitation Copilot-assisted EEGNet, PPO, Grounding DINO RL Experiment
Liu et al. [62] 2022 Serial Manufacturing Learning-based TAC-CA, ANN RL, Hybrid Both
Liu et al. [63] 2021 Serial Manufacturing RL-based AC, Double Q-Learning RL Both
Liu et al. [64] 2021 Serial NS RL-based RL, Q-learning RL, Hybrid Both
Li et al. [65] 2024 Redundant Serial Manufacturing DRL-based planning AC DRL, ANN RL, Hybrid Both
Li et al. [66] 2023 Serial Manufacturing DRL-based DQN, Consensus-based training RL Both
Li et al. [67] 2023 Serial NS DRL-based DRL, ResNet-50 RL, Self-supervised Both
Parag et al. [68] 2025 Serial NS Learning-based Sobolev regression, NN Hybrid Simulation
Parák et al. [69] 2024 Serial Manufacturing DRL-based DDPG, TD3, Soft AC RL Simulation
Prianto et al. [70] 2021 Serial Manufacturing Learning-based planning Soft AC, HER RL, Hybrid Both
Sacchi et al. [71] 2021 Serial Manufacturing DRL-based DQN, Q-learning RL Simulation
Solowjow et al. [72] 2020 Serial Multiple Learning-based grasping planning MobileNet-SSD, FC-GQ-CNN Supervised Both
Sunwoo et al. [73] 2021 Serial Manufacturing DRL-based D3QN, PER RL Simulation
Wang et al. [74] 2022 Serial Manufacturing Hybrid imitation-RL HGCIL, DMP, Soft AC RL, IL, Hybrid Both
Wang et al. [75] 2025 Serial Manufacturing DRL-based trajectory planning DDPG, Autoencoder RL, Unsupervised Both
Wang et al. [76] 2023 Serial Manufacturing DRL-based planning DDQN, Q-learning RL Simulation
Wilson et al. [77] 2025 NS Rehabilitation DRL-based DRL-ANN, Improved ResNet, MSBO RL, Supervised Both
Wong et al. [78] 2019 Serial Manufacturing ACO-based planning ACO, k-means clusterin Unsupervised Both
Yang et al. [79] 2019 Serial NS Learning-based DMP, GMM, GMR, RBFNN IL, Supervised, Hybrid Experiment
Zeng et al. [79] 2018 Serial NS DRL-based with MP Q-learning, FCN, DenseNet RL, Self-supervised Both
Zhang [80] 2025 Serial NS Hierarchical DRL-based TCN-attention, dDRL, RL parameter adaptatio RL Both
Zhao et al. [81] 2025 serial Multiple DRL-based planning M2ACD Supervised Both
Zhong et al. [82] 2022 serial Manufacturing DRL-based DDPG RL, Hybrid Simulation
Learning Control Ahmed et al. [83] 2022 Serial NS Adaptive sliding mode Adaptive Law - Simulation
Aiello [84] 2020 Serial Service DRL-based DDPG, HER RL Simulation
Al-Shanoon et al. [85] 2021 Serial NS DRL-based DRL, Q-learning, Fully convolutional network RL, Self-supervised Both
Alhousani et al. [86] 2023 Serial NS Geometric RL-based Geometric RL, Soft AC, PPO, PoWER, CMA-ES RL Both
Aljalbout et al. [87] 2024 Serial NS RL-based PPO, RL RL Both
Alles et al. [88] 2022 Serial Manufacturing DRL-based Soft AC, HER RL Both
Amaya et al. [89] 2023 Redundant Serial Manufacturing Neuromorphic RL-based Soft AC, SNN RL Simulation
An et al. [90] 2024 Serial Rahabilitation ADP-based optima ADP, Critic NN, RBFNN RL Experiment
Avhad et al. [91] 2024 Serial NS Adaptive DRL-based DRL, Model ensembles, Q-networks RL Both
Azimirad et al. [92] 2024 Mobile Serial NS Learning-based SNN, RL, STDP RL Simulation
Añazco et al. [93] 2021 Anthropomorphic Hand Service DRL-based DRL, 3D CNN RL, Supervised Simulation
Baek et al. [94] 2022 Serial NS DRL-based Soft AC RL Simulation
Barnoy et al. [95] 2022 Mobile magnetic needle Healthcare Learning-based TD3, NN dynamics model RL, Supervised Both
Bashabsheh [96] 2025 Serial NS RL-based Policy-gradient RL RL Simulation
Bejar et al. [97] 2021 Serial NS DRL-based DDPG RL Simulation
Blaise et al. [98] 2023 Serial Aerospace DRL-based DDPG RL Simulation
Brito et al. [99]3/28/2026 4:13:00 AM 2020 Serial Manufacturing RL-based AC, LSTM RL, Supervised Experiment
Calderón-Cordova et al. [100] 2024 Serial Industrial DRL-based DDPG, DRL RL Simulation
Cao et al. [101] 2023 Serial NS Learning-based RL, AC, RBFNN RL Both
Carron et al. [102] 2019 Compliant Serial NS Learning-based model predictiv GP Supervised Experiment
Castelli et al. [103] 2017 Serial Manufacturing Learning-based visual servoing GMM, GMR Supervised Experiment
Chen et al. [104] 2018 Parallel NS Neural-dynamics-based Zeroing neural-dynamics, ZND model - Simulation
Chen [105] 2021 Dexterous Hand Multiple Learning-based DQN, PPO, Soft AC, DAPG RL, IL, Self-supervised Simulation
Chen et al. [106] 2022 Redundant Serial NS DRL-based Soft AC, DDPG RL Simulation
Chen et al. [107] 2016 Serial NS Robust adaptive compensation Adaptive fuzzy Hybrid Both
Chen et al. [108] 2022 Redundant Serial NS DRL-based Soft AC, Prioritized Experience Replay RL Simulation
Chen et al. [109] 2021 Redundant Serial Manufacturing DRL-based Soft AC RL Both
Chen et al. [110] 2021 Serial Manufacturing Learning-based multi-layer NN Supervised Both
Chen [111] 2025 Serial NS DRL-based DDPG RL Simulation
Chen et al. [112] 2023 Serial NS Vision-guided DRL-based YOLOv3, Soft AC RL Both
Chen et al. [113] 2021 Dexterous Hand NS RL-based PPO, TRPO, Soft AC, MAPPO, HAPPO RL Simulation
Chen et al. [114] 2024 Dexterous Hand NS Learning-based PPO, Soft AC, TRPO, DAPG, HAPPO, HATRPO, MAPPO, BCQ, TD3+BC, IQL, ProMP RL, IL Simulation
Chen et al. [115] 2023 Serial NS DRL-based Soft AC, MLP RL, IL Both
Chen et al. [116] 2024 Redundant Serial NS DRL-based DDPG, TD3, Soft AC RL Both
Christen et al. [117] 2019 Dexterous Hand NS DRL-based DDPG, DRL RL, IL Simulation
Chu et al. [118] 2020 Redundant Serial NS DRL-based DDPG, D4PG RL Simulation
Cotrim et al. [119] 2021 Serial Manufacturing RL-based REINFORCE, DQN RL Simulation
Cui et al. [120] 2025 Serial Multiple DRL-based Soft AC RL Both
Cutler et al. [121] 2024 Serial NS DRL-based TD3, Soft AC, DDPG RL Experiment
Ding et al. [122] 2021 Serial NS DRL-based TD3 RL Both
Dong [123] 2024 NS NS RL-based adaptive RL, PG RL Both
Dong et al. [124] 2023 Redundant Serial NS DRL-based DDPG RL Simulation
Ducaju et al. [125] 2024 Redundant Serial Manufacturing Iterative learning-based Iterative Learning Control - Experiment
Du et al. [126] 2017 Serial with RCM Healthcare Fuzzy RL-based admittance Fuzzy Sarsa(λ), RL RL Experiment
Ehrlich et al. [127] 2022 Serial Rehabilitation Neuromorphic learning-based NEF, SNN, PES Supervised Both
Enayati et al. [128] 2024 Serial NS Learning-based PPO, RL RL Both
Fareh et al. [129] 2025 Serial NS DRL-based DDPG, PINNs RL Both
Filho et al. [130] 2025 Serial NS Multi-agent DRL-based Multi DQN, DQN RL Both
Franceschetti et al. [131] 2020 Serial NS DRL-based TRPO, DQN-NAF RL Both
Fu et al. [132] 2022 Quadruped NS RL-based whole-body PPO, RL RL Both
Ganie et al. [133] 2023 Serial NS Learning-based DNN, Elastic weight consolidation Hybrid Simulation
Gao [134] 2022 Serial NS DRL-based DDPG RL Both
Garcia-Hernando et al. [135] 2020 Dexterous Hand NS Residual RL-based PPO, Adversarial IL RL, IL, Hybrid Simulation
Gawali et al. [136] 2023 NS NS Learning-based TERL, RNN, RL RL Simulation
Ghediri et al. [137] 2022 Serial NS DRL-based DDPG, DRL RL Simulation
Grandesso [138] 2023 Redundant Serial NS RL-based AC RL, DDPG variant RL Simulation
Gupta et al. [139] 2015 Serial Manufacturing Neuro-fuzzy-based ANFIS Hybrid Simulation
Gu et al. [140] 2017 Serial NS DRL-based NAF, DDPG RL Both
Haiderbhai et al. [141] 2025 Serial Healthcare Vision-guided learning-based PPO, RL RL Both
Hardman et al. [142] 2022 Serial NS DRL-based DDPG RL Experiment
Hazem et al. [143] 2025 Serial NS DRL-based DDPG, LC-DDPG, TD3-ADX RL Simulation
Heaton et al. [144] 2023 Redundant Serial NS DRL-based Soft AC RL Simulation
He et al. [145] 2017 Serial NS Learning-based RBFNN - Simulation
He et al. [146] 2021 Serial NS RL-based AC, RBFNN RL Both
He et al. [147] 2018 Flexible-joint Serial Manufacturing Learning-based NN Hybrid Both
Homsi et al. [148] 2025 Serial Logistics DRL-based DQN, DQN variants, Self-attention RL Simulation
Hosny et al. [149] 2023 Serial Manufacturing Learning-based RL, AC, Value iteration RL Simulation
Huang et al. [150] 2024 Serial Manufacturing DRL-based Multi-agent TD3, H-memory RL Both
Hu et al. [150] 2024 Serial NS DRL-based Soft AC, GAIL, LSTM RL, IL Simulation
Hu et al. [151] 2024 Serial NS DRL-based Soft AC, ERND RL Simulation
Hu et al. [152] 2024 Serial NS DRL-based Soft AC, HER RL Simulation
Hu et al. [153] 2018 Serial NS RL NN RL, AC NN RL Simulation
Hu et al. [154] 2020 Serial NS MBRL-based RL, kernel methods RL Simulation
Hu et al. [155] 2023 Dexterous Hand NS Learning-based IRL, RL, Graph convolutional network RL Both
Hwang et al. [156] 2017 Serial NS Neuro-fuzzy-based Interval type-2 fuzzy logic - Simulation
Incremona et al. [157] 2021 Serial Manufacturing DRL-based DQN, NAF RL Both
Iqdymat et al. [158] 2025 Serial Logistics DRL-based DDPG, AC RL Both
Iriondo et al. [159] 2019 Mobile Logistics DRL-based DDPG, PPO RL Simulation
Iwasaki et al. [160] 2021 Inverted Pendulum NS DRL-based DDPG RL Simulation
James et al. [161] 2016 Serial NS DRL-based DQN RL Both
Jeong et al. [162] 2020 Serial Rehabilitation Learning-based MDCBN, CNN-BiLSTM Supervised Experiment
Jiang et al. [163] 2023 Serial Manufacturing DRL-based PPO, GAIL, Transformer RL, IL Both
Jiang et al. [164] 2024 Serial NS Fuzzy RL-based optimal fuzzy logic system, Integral RL, Value iteration RL Experiment
Jiang et al. [165] 2022 Serial Service Vision-guided DRL-based Asym-DDPG, Position-CycleGAN, Supervised learning RL, Supervised, Hybrid Both
Jin et al. [166] 2024 Redundant Serial NS Learning-based Echo State Network, Kalman Filter Supervised Both
Joshi et al. [167] 2020 Hybrid NS DRL-based DDQN, Grasp-Q-Network RL, Off-policy Both
Josifovski et al. [168] 2022 Serial NS Learning-based PPO RL Both
Kalashnikov et al. [169] 2018 Serial NS Vision-guided DRL-based QT-Opt, DQN, CEM RL, Self-supervised Both
Kamali et al. [170] 2020 Serial Industrial DRL-based PPO, DRL RL Both
Kang et al. [171] 2021 Serial NS NN-based MPC RBFNN, AC NN RL, Hybrid Simulation
Kankashvar et al. [172] 2015 Parallel NS BBO-based PID modified BBO - Simulation
Kataoka et al. [173] 2022 Serial NS Learning-based PPO, MLP RL Both
Katyal et al. [174] 2017 Serial NS DRL-based DRL, DQN RL Simulation
Kaur et al. [175] 2025 Serial Industrial DRL-based DRL, DQN RL Simulation
Khan et al. [176] 2020 Redundant Serial NS Metaheuristic-based BAORNN, RNN, Beetle antennae olfactory - Simulation
Khodamipour et al. [177] 2021 Serial NS RL-based adaptive RL, Fourier series expansion RL Simulation
Kilinc et al. [178] 2022 Dexterous Hand NS RL-based DDPG, HER RL Simulation
Kim et al. [179] 2024 Anthropomorphic Gripper NS Learning-based PPO RL Both
Kuang [180] 2023 Anthropomorphic Gripper NS Learning-based DDPG+HER, GAIL, GDP, PL-CGS, Goal-SGAIL RL, IL Simulation
Kumar et al. [181] 2017 Serial Multiple GA-optimized fuzzy GA, Fuzzy logic, Neuro-fuzzy Unsupervised, Hybrid Simulation
Kumar et al. [182] 2021 Redundant Serial NS DRL-based PPO, Deep neural policy RL Both
Kunal et al. [183] 2025 Serial Manufacturing DRL-based PPO, DNN RL Both
Kurrek et al. [184] 2020 Serial Manufacturing DRL-based Q-learning, DQN, PPO RL Simulation
Lahmann et al. [185] 2025 Serial NS DRL-based PPO RL Simulation
Lee et al. [186] 2022 Redundant Serial NS Learning-based RL, ANN RL, Supervised Simulation
Lee et al. [187] 2020 Serial NS DRL-based HER, DDPG RL Simulation
Lee et al. [188] 2024 Serial Rehabilitation Learning-based CNN-KF, PPO, Grounding DINO RL, Supervised Experiment
Liang et al. [189] 2024 Serial NS RL-based adaptive AC, NN RL Both
Lin et al. [190] 2025 Humanoid Service Vision-guided learning-based RL, PPO, Diffusion policy, Policy distillation RL, IL Both
Lin et al. [191] 2017 Serial NS Cerebellar-inspired learning-based Distributed cerebellar model, Spike-timing-dependent plasticity RL Both
Lin et al. [192] 2023 Serial NS DRL-based PPO, DRL, Pix2Pix GAN RL Both
Lin et al. [193] 2022 Serial NS DRL-based PPO, GAN RL Both
Liu et al. [194] 2021 Serial Multiple Learning-based RBFNN Supervised, Hybrid Simulation
Liu et al. [195] 2020 Serial NS RL-based MAPPO RL Both
Liu et al. [196] 2024 Serial NS DRL-based TD3 RL Simulation
Liu et al. [197] 2020 Serial NS DRL-based DQN RL Both
Liu et al. [198] 2019 Redundant Serial Multiple Learning-based LSTM Supervised Simulation
Liu et al. [199] 2021 Serial NS DRL-based Off-policy AC, DRL RL Simulation
Liu et al. [200] 2024 Serial NS HRL-based Hierarchical RL, PGPE RL Both
Li et al. [201] 2025 Serial Manufacturing DRL-based PPO, Simulated Annealing RL Both
Li et al. [202] 2023 Redundant Serial NS Biomimetic learning-based SNN, DDPG, STDP RL, Unsupervised Both
Li [203] 2021 Serial Manufacturing DRL-based DQN RL Simulation
Li et al. [204] 2019 Serial NS Automaton-guided RL RL, PPO RL Both
Li et al. [205] 2021 Serial Service DRL-based DRL, CNN, Policy search RL Experiment
Li et al. [206] 2024 Serial NS RL-based sliding mode RL, AC NN, RBFNN RL Simulation
Li et al. [207] 2015 Serial NS Learning-based AC, RBFNN RL Simulation
Li et al. [208] 2021 Serial Aerospace DRL-based DDPG RL Simulation
Li et al. [209] 2023 Redundant Serial NS Autoencoder-based kinematic sparse autoencoder, RNN - Simulation
Li et al. [210] 2018 Humanoid NS RL-based RL, DMP RL Experiment
Lobbezoo et al. [211] 2023 Serial Manufacturing Learning-based PPO, Soft AC RL Both
Luo et al. [212] 2018 Serial Manufacturing DRL-based MDGPS, DNN RL Experiment
Luo et al. [213] 2025 Serial Manufacturing Vision-guided learning-based Off-policy RL, RLPD, Soft AC RL, IL, Hybrid Experiment
Luo et al. [214] 2025 Serial NS RL-based PPO RL Simulation
Lu et al. [14] 2023 Parallel NS DRL-based DRL, Soft AC RL Both
Majumder et al. [215] 2024 Serial NS DRL-based DDPG, AC RL Simulation
Majumder et al. [216] 2023 Serial NS DRL-based Improved DDPG RL Simulation
Maldonado-Ramirez et al. [217] 2021 Serial Manufacturing Vision-guided DRL-based PPO, A2C, TRPO RL Both
Malik et al. [218] 2022 Redundant Serial NS DRL-based DQN RL Both
Mannaa et al. [219] 2023 Serial Manufacturing DRL-based DDPG, HER RL Both
Mao et al. [220] 2025 Serial NS Vision-guided learning-based Soft AC RL Both
Matas et al. [221] 2018 Serial Service DRL-based DDPG RL, IL Both
Mazzaglia et al. [222] 2024 Redundant Serial NS Learning-based RL, IL RL, IL Both
Ma et al. [223] 2025 Serial Multiple Learning-based Multimodal contrastive learning, Diffusion models RL, Self-supervised Simulation
Mellatshahi et al. [224] 2021 Serial NS DRL-based DQN RL Simulation
Meyes et al. [225] 2017 Serial Manufacturing RL-based Q-learning RL Both
Molina [226] 2018 Serial Service RL-based Relational RL, Q-Learning RL, IL Both
Moon et al. [227] 2021 Redundant Serial Underwater Construction Meta-RL-based control meta-RL, Model-based RL RL Simulation
Mueangprasert et al. [228] 2023 Serial NS MBRL-based GPR, ANN, SVR, PSO RL Simulation
Naranjo-Campos et al. [229] 2024 Mobile Rehabilitation DRL-based PPO, DRL RL Both
Nguyen et al. [230] 2023 Serial NS DRL-based DDPG, HER RL Both
Nohooji et al. [231] 2024 Serial Multiple RL-based PID AC, RBFNN RL Simulation
Ouyang et al. [232] 2017 Serial NS RL-based RBFNN, AC RL Both
Pane et al. [233] 2016 Serial Manufacturing RL-based AC RL Experiment
Pane et al. [234] 2019 Serial Manufacturing RL-based compensation AC, RBFNN RL Experiment
Pantoja-Garcia et al. [235] 2022 Serial NS AC-based AC, NN RL Simulation
Pan et al. [236] 2025 Serial Multiple DRL-based TD3 RL Simulation
Pan et al. [237] 2023 Serial NS DRL-based DRL RL Simulation
Park et al. [238] 2024 Serial NS DRL-based PPO RL Both
Pavlichenko et al. [239] 2022 Redundant Serial NS DRL-based Soft AC, Beta policy RL Both
Pedersen et al. [240] 2020 Serial NS DRL-based PPO, CycleGAN RL, Unsupervised Experiment
Perrusquia et al. [241] 2021 Serial NS RL-based optimal tracking NN, RL, Experience replay RL Simulation
Perrusquía et al. [242] 2019 Pan and tilt NS RL-based impedance RL, Q-learning, TD-learning, NRBF, K-means RL Experiment
Pham et al. [243] 2025 Parallel NS RL-based adaptive AC RL, NN RL Experiment
Polydoros et al. [244] 2015 Serial Manufacturing Learning-based PC-ESN, Echo State Network, Generalized Hebbian Learning, Bayesian linear regression Supervised Experiment
Popov et al. [245] 2017 Serial NS DRL-based DDPG RL Both
Qiao et al. [246] 2021 Serial NS MPC-guided DRL-based DQN RL Simulation
Qin et al. [247] 2022 Dexterous Hand NS DRL-based PPO, PointNet RL Both
Qi et al. [248] 2021 Serial NS DRL-based improved DDPG RL Simulation
Quillen et al. [249] 2018 Hybrid NS Vision-guided DRL-based DQN, DDPG, Path consistency learning, Monte Carlo policy evaluation, Corrected Monte Carlo RL, Supervised Simulation
Rajeswaran et al. [250] 2018 Anthropomorphic Gripper NS DRL-based DRL, DAPG, Behavior cloning, NPG RL, IL, Hybrid Simulation
Ramirez et al. [251] 2022 Redundant Serial NS DRL-based TD3, Supervised learning RL, IL, Supervised Simulation
Ramirez et al. [252] 2023 Redundant Serial NS RLED-based TD3, Supervised learning RL, IL, Hybrid Simulation
Ren et al. [253] 2020 Serial NS Learning-based RBFNN Supervised Simulation
Ren et al. [254] 2020 Serial NS GAN-based inverse modeling CGAN, LSGAN, BiGAN, DualGAN Supervised Experiment
Rizzardo et al. [255] 2023 Serial NS DRL-based Soft AC, Variational Autoencoder RL, Unsupervised Both
Rubagotti et al. [256] 2023 Serial NS DRL-based DRL, Q-learning, NAF RL Both
Saeed et al. [257] 2021 Dexterous Hand NS DRL-based DDPG, DDPG+HER, PPO RL Simulation
Sahu et al. [258] 2021 Serial NS DRL-based DDPG, AC RL Simulation
Saidi et al. [259] 2023 Serial NS GA-optimized backstepping GA - Simulation
Said et al. [260] 2019 Serial NS ABC-optimized PID ABC, PSO - Simulation
Sajadi et al. [261] 2022 Serial Healthcare DRL-based DDPG RL Both
Sangiovanni et al. [262] 2021 Redundant Serial Manufacturing DRL-based DRL, NAF RL Simulation
Sangiovanni et al. [263] 2018 Anthropomorphic Manufacturing DRL-based DRL, NAF RL Simulation
Sangiovanni et al. [264] 2018 Serial Manufacturing DRL-based DRL, NAF RL Simulation
Scheikl et al. [265] 2023 Serial Healthcare Vision-guided learning-based PPO, Contrastive GAN, DCL RL Both
Sekkat et al. [266] 2021 Serial NS DRL-based DDPG, YOLOv5 RL Simulation
Shahid et al. [267] 2022 Redundant Serial Manufacturing RL-based PPO, Soft AC RL Both
Shahna et al. [268] 2024 Serial NS DRL-based Soft AC RL Simulation
Shao et al. [269] 2025 Serial NS DRL-based impedance DDPG, Behavior cloning RL, IL, Hybrid Simulation
Shetty et al. [270] 2021 Serial NS DRL-based DDPG RL Simulation
Shiferaw et al. [271] 2024 Serial Multiple DRL-based DQN, DenseNet-121 RL, Self-supervised Simulation
Shin et al. [272] 2019 Cable-driven Healthcare Learning-based model predictiv RL, Learning from demonstration, NN RL, IL Both
Siddique et al. [273] 2024 Serial Rehabilitation DRL-based DDPG RL Simulation
Simon et al. [274] 2024 Serial Multiple DRL-based DQN, DMP RL, IL Both
Sivertsvik et al. [275] 2024 Hybrid Multiple DRL-based PPO, PPG RL Both
Song et al. [276] 2024 Serial Manufacturing RL-based Q-learning RL Both
Song et al. [277] 2024 Serial NS RL-based consensus RL, AC, NN RL Simulation
Staley et al. [278] 2018 Serial NS DRL-based DQN, DRL RL Simulation
Sun et al. [279] 2021 Redundant Serial Manufacturing Learning-based Fully connected NN Supervised Simulation
Sun et al. [280] 2023 Redundant Serial NS Hybrid LfD-RL DMP, RL, Policy network, Q-network RL, IL, Hybrid Experiment
Sun et al. [281] 2020 Serial NS DRL-based DRL, Soft AC RL Both
Su et al. [282] 2024 Serial NS RL-based PPO RL Both
Su et al. [283] 2025 Serial NS RL-based backstepping AC NN, RL RL Simulation
Su et al. [284] 2020 Anthropomorphic Healthcare Learning-based DCNN Supervised Both
Tajdari et al. [285] 2017 Serial Manufacturing Adaptive sliding-mode Model reference adaptive control, Adaptive sliding mode - Experiment
Takeda et al. [286] 2025 Serial NS Hierarchical RL-based Soft AC, Goal-conditioned RL RL Simulation
Tang et al. [287] 2022 Serial Rehabilitation DRL-based PPO, DRL RL Simulation
Uchibe et al. [288] 2021 Humanoid NS IL-based ERIL, Soft AC, IRL RL, IL Both
Valencia et al. [289] 2023 Serial NS RL-based TD3, Probabilistic NN, Gaussian mixture RL Simulation
Vijay et al. [290] 2018 Serial Power Transmission Learning-based RBFNN Supervised, Hybrid Simulation
Vu et al. [291] 2021 Serial NS ARL-based AC NN, ADP RL Simulation
V et al. [292] 2025 Flexible Joint NS DRL-based CPPO, PPO, CNN RL Experiment
Wang et al. [293] 2020 Mobile NS DRL-based PPO, DRL RL Both
Wang et al. [294] 2025 Serial NS DRL-based Soft AC, LSTM, Random Network Distillation, attention mechanism RL Simulation
Wang, et al. [295] 2024 Serial NS DRL-based DDPG RL Both
Wang et al. [296] 2025 Serial Multiple DRL-based HTSK Fuzzy system, GABC, Rainbow-DDPG, CPL RL, IL, Hybrid Both
Wang et al. [297] 2024 Serial NS RL-based RL, NN RL Simulation
Wang, et al. [298] 2017 Serial NS Learning-based RBFNN - Simulation
Wang et al. [299] 2023 Dexterous NS DRL-based DDPG, HER, Knowledge Transfer RL Both
Wang et al. [300] 2020 Serial NS Learning-based LSTM, Attention mechanism Supervised Experiment
Wang et al. [301] 2024 Serial NS MBRL-based Model-based RL, Curiosity-driven RL, Soft AC RL, Self-supervised Simulation
Wang et al. [302] 2025 Redundant Serial NS Neuro-fuzzy-based Fuzzy Logic System, AC-Identify, ADP RL, Hybrid Experiment
Wang et al. [303] 2025 Serial Multiple Learning-based optimal Multilayer FNN, RL RL Simulation
Wang et al. [304] 2023 Redundant Serial NS Hierarchical multi-agent RL-based Multi-agent PPO, hierarchical RL, PPO RL Simulation
Weber et al. [305] 2021 Serial NS DRL-based DDPG RL Both
Wu et al. [306] 2025 Serial Manufacturing RL-based Soft AC, DDPG, gated feature extractor RL Both
Wu et al. [307] 2022 Serial NS Adversarial RL-based Adversarial RL RL Both
Wu et al. [308] 2023 Serial NS Learning-based RBFNN - Both
Wu et al. [309] 2024 Serial NS RL-based output feedback RL, RBFNN RL Simulation
Wu et al. [310] 2025 Serial NS DRL-based Soft AC, Soft ACwB RL Both
Xhin et al. [311] 2024 Serial NS DRL-based DDPG RL Both
Xiao et al. [312] 2024 Serial Manufacturing Learning-based PPO, IL RL, IL Both
Xie et al. [313] 2019 Serial NS DRL-based DDPG, A3C, DPPO RL Simulation
Xu et al. [314] 2023 Serial NS Learning-based CURL, Soft AC, U-Net RL, Self-supervised, Unsupervised Both
Xu et al. [315] 2024 Serial NS Learning-based Hybrid NN, RBFNN, DiffNEA Supervised Experiment
Yagi et al. [12] 2025 Serial NS Hierarchical RL-based Hierarchical RL, PPO RL Experiment
Yang et al. [316] 2025 Serial Mining DRL-based IM-DQN, Prioritized experience replay, ICM RL Both
Yang et al. [317] 2023 Serial NS Hybrid model-based model-free RL, broader industrial applications Soft AC, PETS, CEM RL Both
Yang et al. [318] 2025 Serial NS Learning-based fault-tolerant AC RL, RBFNN RL Both
Yang et al. [319] 2025 Serial NS Learning-based Deterministic learning, RBFNN, Knowledge fusion - Simulation
Yang et al. [320] 2022 Serial NS RL-based impedance Off-policy reinforcement RL Both
Yuan et al. [321] 2025 Dexterous Hand NS Vision-guided learning-based PPO, DrM, DAgger RL, IL Both
Zhang et al. [322] 2015 Serial NS DRL-based DQN RL Both
Zhang et al. [323] 2023 Dexterous Hand NS DRL-based Soft AC, GAN RL Both
Zhang [324] 2025 Serial Manufacturing Learning-based MLP, CNN, LSTM, Q-learning, AC RL, Supervised, Hybrid Both
Zhang et al. [325] 2023 Redundant Serial NS DRL-based DQN, Soft AC RL Simulation
Zhang et al. [326] 2023 Serial NS DRL-based trajectory PPO, DRL RL Both
Zhang et al. [327] 2022 Serial NS DRL-based Mask R-CNN, Soft AC RL Both
Zhang et al. [328] 2023 Serial NS symbolic regression-based Symbolic regression, Genetic programming Supervised Simulation
Zhang et al. [329] 2022 Serial NS DRL-based PPO, CNN RL Simulation
Zhan et al. [330] 2022 Serial NS Vision-guided learning-based Soft AC, Contrastive learning, Data augmentation RL, IL, Self-supervised Both
Zhao et al. [331] 2024 Serial Manufacturing DRL-based MAPPO, PPO RL Both
Zhao et al. [332] 2020 Serial NS DRL-based PPO, DRL RL Simulation
Zheng et al. [333] 2023 Serial NS DRL-based trajectory DDPG, TD3, Soft AC RL Simulation
Zhou et al. [334] 2021 Serial NS DRL-based DDPG RL Simulation
Zhu et al. [335] 2022 Serial Aerospace Fuzzy RL-based Fuzzy wavelet network, RL RL Simulation
Zhu et al. [336] 2019 Dexterous Hand NS DRL-based DRL, DAPG, natural policy gradient RL, IL, Hybrid Both
Zhu et al. [337] 2025 Serial Multiple RL-based optimal tracking AC-identifier NN, RL RL Simulation
Zong et al. [338] 2025 Dexterous Hand Manufacturing DRL-based TD3, D2SR, pruning RL Simulation
Modares et al. [339] 2016 Serial NS Learning-based Integral RL, NN RL Both
Interaction and Safety Perrusquía et al. [340] 2019 Serial NS Learning-based position/force Q-learning, Sarsa RL Both
Sasaki et al. [341] 2022 Serial NS DRL-based DDQN, CNN RL, Supervised Both
Wang et al. [342] 2024 Serial Multiple Learning-based teleoperation 1D CNN, Multiview multitask Supervised Experiment
AlAttar et al. [343] 2022 Serial NS Learning-based predictive Local linear models, Least squares regression Self-supervised Both
Learning and Adaptation Baselizadeh, et al. [344] 2022 Serial NS Learning-based Q-Learning, RL RL Simulation
Ding et al. [345] 2021 Serial NS NS Model-based off-policy RL RL Simulation
Elsisi et al. [13] 2021 Serial NS NS Modified NN Algorithm, polynomial mutation - Simulation
Haddad et al. [346] 2021 Serial NS Swarm-optimized PSO, SSO - Simulation
Jeong et al. [347] 2020 Serial NS Vision-guided learning-based MPO, behavioral cloning, Contrastive Forward Dynamics RL, IL, Self-supervised Both
Jhan et al. [348] 2015 Serial NS Fuzzy neural-based adaptive impedance force fuzzy NN, FNS Hybrid Simulation
Kallel et al. [349] 2025 Serial NS Learning-based MLP Regressor, Random Forest Regressor, PINNs Hybrid, Supervised Simulation
Kuang et al. [350] 2025 Serial NS DRL-based DRL, Soft AC RL Both
Li et al. [351] 2022 Serial NS Learning-based adaptive Concurrent learning - Both
Li et al. [352] 2023 Serial NS RL-tuned MPC visual servoing DDPG RL Simulation
Li et al. [353] 2017 Exoskeleton Rehabilitation RL-based adaptive impedance Integral RL RL Experiment
Lu et al. [354] 2024 Serial NS Learning-based SARSA, RL RL Simulation
Pradhan et al. [355] 2020 Serial NS Nonlinear self-tuning PID NARMAX, RLS - Both
Sacchi et al. [356] 2023 Serial NS DRL-assisted ISM DNN, TD3, DRL RL Simulation
Shcherbakov et al. [357] 2020 Serial Manufacturing Digital-twin based adaptive Kalman filtering, System identification, Predictive modeling - Simulation
Wu et al. [358] 2025 Serial Multiple DRL-based admittance DRL, NAF RL Both
Xie et al. [359] 2020 Serial Aerospace RL-based fuzzy sliding mode Fuzzy logic, RL, Q-learning RL Simulation
Yousef et al. [360] 2024 Serial NS DRL-based DDPG RL Simulation
Zhang et al. [361] 2024 Serial NS Deep MPC-based Deep MPC, NN RL, Adaptive Learning Simulation
* ACO: Ant Colony Optimization; ADP: Adaptive Dynamic Programming; ANN: Artificial Neural Network; ARL: Adoption Readiness Levels; BBO: Biogeography-based Optimization; BCI: Brain-Computer Interface; Both: Simulation and Experiment; CNN: Convolutional Neural Network; CNN-LSTM: Convolutional Neural Network-Long Short-Term Memory; DDPG: Deep Deterministic Policy Gradient; DDQN: Double Deep Q-Network; DMP: Dynamic movement primitives; DNN: Deep Neural Network; DQN: Deep Q-Network; DRL: Deep Reinforcement Learning; dDRL: Distributed Deep Reinforcement Learning; DT: Decision Tree; FL: Fuzzy Logic; GA: Genetic Algorithm; GAN: Generative Adversarial Networks; GP: Gaussian Process; GPR: Gaussian Process Regression; HER: Hindsight Experience Replay; HGCIL: Hierarchical goal-conditioned imitation learning.; ID: Inverse Dynamics; IK: Inverse Kinematics; IL: Imitation Learning; IRL: Inverse Reinforcement Learning; ISM: Interpretive Structural Modeling; KNN: k-Nearest Neighbor; LSTM: Long Short-Term Memory network; MBRL: Model-based Reinforcement Learning; MDGPS: Mirror-descent Guided Policy Search; MLP: Multilayer Perceptron; MP: Movement primitives; MPC: Model Predictive Control; MS-CLSTM: Multi-Scale CNN-LSTM (MS Block-ResCBAM-Bi-LSTM hybrid); MSBO: Modified Smell Bee Optimizatio (for EMG); NAF: Normalized Advantage Function; NN: Neural Network; NS: Not Specified; PG: Policy Gradient; PPG: Phasic Policy Gradient; PPO: Proximal Policy Optimization; PSO: Particle Swarm Optimization; R-CNN: Region-based CNN; RBFNN: Radial Basis Function Neural Network; RL: Reinforcement Learning; RLED: Reinforcement Learning from Expert Demonstration; RNN: Recurrent Neural Network; RT: Regression tree; SNN: Spiking Neural Network; SVM: Suport Vector Machine; SVR: Support Vector Regression; sEMG: Surface Electromyography; TAC-CA: Tsallis Actor-Critic with Clipped Automatic; TD3: Twin Delayed Deep Deterministic Policy Gradien; TSK: Takagi–Sugeno–Kang.
Table 4. Frequency and percentage of use in robot types.
Table 4. Frequency and percentage of use in robot types.
Robot Type Frequency of Use Percentage
Serial 255 74.3%
Robotic Hand 32 9.3%
Others 18 5.2%
Flexible Joint 15 4.4%
Anthropomorphic 6 1.7%
Parallel 5 1.5%
Magnetic 5 1.5%
Mobile 3 0.9%
Hybrid 3 0.9%
Not Specified 1 0.3%
Table 5. Frequency and percentage of use in applications.
Table 5. Frequency and percentage of use in applications.
Application Frequency of Use Percentage
Not Specified 207 60.3%
Manufacturing 64 18.7%
Multiple 21 6.1%
Rehabilitation 16 4.7%
Healthcare 10 2.9%
Service 7 2.0%
Aerospace 5 1.5%
Logistics 4 1.2%
Industrial 3 0.9%
Others 6 1.7%
Table 6. Frequency and percentage of use in control technique.
Table 6. Frequency and percentage of use in control technique.
Control Technical Family Frequency of Use Percentage
Learning-based 311 90.7%
Fuzzy-based 8 2.3%
Optimization-based 6 1.7%
Adaptive / Robust classical control 6 1.7%
MPC-based / Hybrid MPC 3 0.9%
Perception / Estimation-guided 6 1.7%
Assistive / Copilot-based 1 0.3%
Not Specified 2 0.6%
*MPC: Model Predictive Control.
Table 7. Frequency and percentage of use in control technique.
Table 7. Frequency and percentage of use in control technique.
Learning Paradigm Frequency of Use Percentage
Reinforcement Learning 202 58.9%
Supervised 42 12.2%
Self-supervised 2 0.6%
Unsupervised 1 0.3%
Hybrid 48 14.0%
Multi-paradigm 29 8.5%
Not Specified 19 5.5%
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
Copyright: This open access article is published under a Creative Commons CC BY 4.0 license, which permit the free download, distribution, and reuse, provided that the author and preprint are cited in any reuse.
Prerpints.org logo

Preprints.org is a free preprint server supported by MDPI in Basel, Switzerland.

facebook logotwitter logolinkedin logo
bsky
MDPI Initiatives
Important Links
Subscribe

Disclaimer

Terms of Use

Privacy Policy

Privacy Settings

© 2026 MDPI (Basel, Switzerland) unless otherwise stated