Abstract: A new multi-robot path planning algorithm (MRPPA) for 2D static environments is developed and evaluated. It combines a roadmap method, utilising the visibility graph (VG), with the algebraic connectivity (second smallest eigenvalue (λ2)) of the graph’s Laplacian and Dijkstra's algorithm. The paths depend on the planning order, i.e., they are in sequence path-by-path, based on the measured values of algebraic connectivity of the graph’s Laplacian and the determined weights functions. Algebraic connectivity maintains robust communication between the robots during their movements while avoiding collision. The algorithm efficiently balanced connectivity maintenance and path length minimisation thus improving the performance of path finding. It produced solutions with optimal paths, i.e., the shortest and safest route. The devised MRPPA significantly improved path length efficiency across different configurations. The results demonstrated a highly efficient and robust solution for multi-robot systems requiring both optimal path planning and reliable connectivity, making it well-suited in scenarios where communication between robots is necessary. Simulation results demonstrated the performance of the proposed algorithm in balancing the path optimality and network connectivity across multiple static environments with varying complexities. The algorithm is suitable for identifying optimal and complete collision-free paths. The results illustrated the algorithm's effectiveness, computational efficiency, and adaptability.

Abstract: To achieve shorter path length and lower repetition rate for robotic complete coverage path planning, a complete-coverage path-planning algorithm based on transition probability and learning perturbation operator (CCPP-TPLP) is proposed. Firstly, according to the adjacency information between nodes, the distance matrix and transition probability matrix of the accessible grid are established, and the optimal initialization path is generated by applying greedy strategy on the transition probability matrix. Secondly, the population is divided into four subgroups, and different degrees of learning perturbation operations are carried out on subgroups to update each path in the population. CCPP-TPLP was tested against five algorithms in different map environments and in the working map environment of electric tractors with height information The results show that CCPP-TPLP can optimize the selection of path nodes, reduce the total length and repetition rate of the path, and significantly improve the planning efficiency and quality of complete coverage path planning.

Abstract: This paper addresses the following problem of information extraction using an AI-powered chatbot. An AI chatbot processes a natural language conversation with a human user using semantic search and human-chatbot interaction to extract the most relevant and contextually appropriate information from available databases. During a natural language conversation between a human and an AI, the human user can modify and refine queries until he/she is satisfied with the chatbot’s output. The reliability of an AI chatbot is defined as its ability to understand user queries and provide correct answers; in the current study, it is measured by the frequency (probability) of correct answers. The search efficiency of a chatbot indicates how accurate and relevant the information returned by the chatbot is; in this work, it is measured by the satisfaction level that the human user receives for a correct answer. We uncover a counterintuitive relationship between AI chatbot reliability and search efficiency: we demonstrate that, under fairly general conditions, a less reliable AI chatbot can have a higher expected search efficiency than a more reliable chatbot. This phenomenon aligns with a family of “more-for-less” paradoxes observed in various complex systems. Finally, we discuss the underlying mechanism of this paradox.

Abstract: The Mentes Robóticas project, implemented at João Batista de Carvalho State School in Bambuí-MG, aimed to integrate robotics and programming into the high school curriculum, focusing on developing computational thinking and the practical application of interdisciplinary concepts. This preprint presents the project’s final results, highlighting the impact of robotics on learning mathematics and physics. Through theoretical and practical lessons, students were introduced to concepts in electronics, programming, and robotics, using Arduino kits and digital tools such as TinkerCAD. Feedback from teachers indicates that robotics sparked students’ interest in technology, potentially extending to related fields such as mathematics, physics, and chemistry. This contributes to an interdisciplinary and contextualized learning approach, making education more engaging and meaningful. The project also demonstrated the potential of robotics as an inclusive educational tool, with students with Autism Spectrum Disorder (ASD) actively participating and showing interest in the activities. Initial findings suggest that robotics can be an effective way to enhance mathematics and physics education by connecting theoretical concepts to practical applications and fostering a deeper understanding of STEM disciplines.

Abstract: As SLAM technology has evolved from the geometric level to the object level, Active SLAM (ASLAM) has also adopted a new goal: improving the ability to observe objects. However, current ASLAM mostly focuses on low-dimensional environmental features such as points, lines, and planes, while ignores the impact of motion process on SLAM. This paper proposes a new observation pose optimization method based on the ellipsoid model and the camera field of view to enhance the robot’s ability to observe objects. We integrate view planning and motion planning into a unified observation pose optimization module and construct an optimized factor graph based on probabilistic inference. Our method ensures the observation poses are globally optimal and can directly generate robot control variables. Leveraging the camera’s field of view and the ellipsoid model abstracted from object SDF model, we introduce three key factors into the factor graph: object completeness observation factor, self-observation prevention factor, camera motion smoothness factor. Finally, we develop the object ASLAM system with our observation pose optimization method, and evaluate it in multiple simulation environments. Experimental results demonstrate that our method significantly improves object modeling accuracy, mapping efficiency, and localization precision. The code for this work are open-sourced at https://github.com/TINY-KE/OPO_ASLAM.git.

Abstract: Engaging with social robots has been identified as possibly advantageous for children with social communication challenges, particularly in practicing social skills like shared attention. This study included systematic review on articles from 2018 describing the robotic applications and technologies used in improving children’s cognitive develop-ment. By reporting on contemporary study types, modes of cognition, and the role of children, important factors and key considering for social robot’s design also discussed. This review aims to give a broad picture of the state of "cognitive development" research especially in recent years. It investigates the use of robotic technology based on the ed-ucational attainment of children at various ages. The review includes articles including experimental, non-experimental, article type, research field, robots, context of use, target audience and results or conclusions. The results indicate the increasing potential of social robots to support kids' cognitive development, especially by providing them with in-teresting and engaging learning opportunities. This review offers valuable insight for researchers, and designers looking to further enhance robotic therapies and modify them to fit a variety of developmental requirements and educational environments.

Abstract: Multi-agent pathfinding (MAPF) holds significant utility within autonomous systems, however, the calculation and memory space required for multi-agent path finding (MAPF) grows exponentially as the number of agents increases. This often results in some MAPF instances being unsolvable under limited computational resources and memory space, thereby limiting the application of MAPF in complex scenarios. Hence, we propose a decomposition approach for MAPF instances, which breaks down instances involving a large number of agents into multiple isolated subproblems involving fewer agents. Moreover, we present a framework to enable general MAPF algorithms to solve each subproblem independently and merge their solutions into one conflict-free final solution, and avoid loss of solvability as much as possible. Unlike existing works that propose isolated methods aimed at reducing the time cost of MAPF, our method is applicable to all MAPF methods. In our results, we apply decomposition to multiple state-of-the-art MAPF methods using a classic MAPF benchmark\footnote{https://movingai.com/benchmarks/mapf.html}. The decomposition of MAPF instances is completed on average within 1s, and its application to seven MAPF methods reduces the memory usage or time cost significantly, particularly for serial methods. Based on massive experiments, we speculate the possibilty about loss of solvability caused by our method is $<$ 1\%. To facilitate further research within the community, we have made the source code of the proposed algorithm publicly available\footnote{https://github.com/JoeYao-bit/LayeredMAPF/tree/minimize\_dependence}.

Abstract:

The Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm offers a robust solution for the coverage path planning problem, where a robot must effectively and efficiently cover a designated area, ensuring minimal redundancy and maximum coverage. Traditional methods for path planning often lack the adaptability required for dynamic and unstructured environments. In contrast, TD3 utilizes twin Q-networks to reduce overestimation bias, delayed policy updates for increased stability, and target policy smoothing to maintain smooth transitions in the robot's path. These features allow the robot to learn an optimal path strategy in real-time, effectively balancing exploration and exploitation. This paper explores the application of TD3 to coverage path planning, demonstrating that it enables a robot to adaptively and efficiently navigate complex coverage tasks, showing significant advantages over conventional methods in terms of coverage rate, total length, and adaptability.

Abstract: Accurate tomato yield estimation and ripeness monitoring are critical for optimizing greenhouse management. While manual counting remains labor-intensive and error-prone, this study introduces a novel vision-based framework for automated tomato counting in standardized greenhouse environments. The proposed method integrates YOLOv8-based detection, depth filtering, and an inter-frame prediction algorithm to address key challenges such as background interference, occlusion, and double-counting. Our approach achieves 97.09% accuracy in tomato cluster detection, with mature and immature single-fruit recognition accuracies of 92.03% and 91.79%, respectively. The multi-target tracking algorithm demonstrates a MOTA (Multiple Object Tracking Accuracy) of 0.954, outperforming conventional methods like YOLOv8+DeepSORT. By fusing odometry data from an inspection robot, this lightweight solution enables real-time yield estimation and maturity classification, offering practical value for precision agriculture.

Abstract: Dyscalculia is a specific learning disorder that affects numerical comprehension, arithmetic reasoning, and problem-solving skills, significantly impacting academic performance and daily life activities. Traditional teaching methods often fail to address the unique cognitive challenges faced by students with dyscalculia, highlighting the need for innovative educational approaches. Recent studies suggest that educational robotics and game-based learning can provide engaging and adaptive learning environments, enhancing numerical cognition and motivation in students with mathematical difficulties. The intervention was designed to improve calculation skills, problem-solving strategies, and overall engagement in mathematics. The study involved 73 secondary students, divided into three classes, among whom only a specific group had been diagnosed with dyscalculia. Data were collected through pre- and post-intervention assessment- evaluating improvements in numerical accuracy, processing speed, and support motivation. Preliminary findings indicate that robotics and gamification create an interactive, less anxiety-inducing learning experience, facilitating conceptual understanding and retention of mathematical concepts. The results suggest that these tools hold promise as supplementary interventions for children with dyscalculia. Future research should explore long-term effects, optimal implementation strategies, and their integration within formal educational settings.

Abstract: Rotation motion in a three-dimensional physical world refers to an angular displacement of an object around a specific axis in $\mathbb{R}^3$. It is typically formulated as a non-linear and non-convex motion due to the nonlinearity and nonconvexity of $\mathbb{SO}(3)$. However, this paper proposes a new perspective that the 3D rotation motion can be expressed by a linear system without dropping any constraints and increasing any singularities. Moreover, two frequent cases, i.e., $\angle\left(\mathbf{R}\boldsymbol{x},\boldsymbol{y}\right)=0$ and $\angle\left(\mathbf{R}\boldsymbol{x},\boldsymbol{y}\right)=\frac{\pi}{2}$, in computer vision and robotics that can be expressed linearly are deeply discussed in this paper.

Abstract: This study aims to enhance the maneuverability and monitoring capabilities of biomimetic robotic fish in aquatic environments. A three joint biomimetic fish with forked tail fins was designed based on the body and tail fin (BCF) model to optimize propulsion efficiency and mimic natural fish swimming. The mechanical structure uses servo modules connected in series to simulate spinal joints, and precise control is achieved through PWM signals and Arduino based systems. The tail fin design follows the principles of fluid dynamics, especially the anti Karman vortex street effect, while the ballast mechanism is used to adjust the pitch angle to achieve vertical motion. The robotic fish integrates temperature, pH, and turbidity sensors for real-time water quality monitoring and data transmission through WiFi. The experimental results show that the swimming speed of the bionic fish is 0.018 m/s, the turning angular velocity is 15 °/s, and the maximum pitch angle is 5.69 °, verifying its good maneuverability. The water quality monitoring experiment shows that compared with traditional methods, the deviations of water temperature, pH value, and turbidity are 0.67%, 0.05%, and 0.23%, respectively, which meet the accuracy requirements of water quality parameter detection. This design successfully combines biomimetic motion with embedded sensing technology, providing a compact solution for dynamic aquatic monitoring. Although the system has shown potential in environmental applications, improvements in speed, maneuverability, and sensor accuracy are still needed in the future to enhance its operational capabilities in complex underwater environments.

Abstract: We introduce the Australian Supermarket Object Set, a dataset comprising 50 readily available supermarket items with high-quality 3D textured meshes. Designed for both real-world and simulated environments, this dataset supports benchmarking in robotic manipulation and computer vision tasks. This paper details the dataset’s construction process, object categorization, and its potential to enhance reproducibility and advance research in robotics and computer vision.

Abstract: Introduction: Medical simulation manikins have evolved to include advanced sensor networks, actuators, and physiological modeling capabilities. However, their potential applications in robotics remain underexplored, and there is a lack of comprehensive analysis of opportunities and implementation challenges. Methods: This scoping review examined research from the IEEE Xplore, PubMed, ACM Digital Library, SpringerLink, and Elsevier databases (1969-2024). Out of 156 initial studies, 64 met the inclusion criteria, focusing on adapting medical manikins for robotics. The analysis investigated hardware modifications, software integrations, and hybrid implementation strategies. Results: Analysis revealed three main development paths: hardware adaptation evolving from basic sensor integration to intricate musculoskeletal framework (15 studies); software integration progressing from rule-based responses to biomimetic control architectures (22 studies); and hybrid approaches that combine physical manikins with mixed reality interfaces (18 studies). Nine additional studies investigated convergent applications in humanoid robotics and dynamic tactile systems. Discussion: Findings indicate significant potential for cross-disciplinary innovation in biomimetic control systems and human-robot interaction. Major challenges include achieving seamless hardware-software integration while upholding anatomical accuracy. Future development should emphasize standardized integration frameworks and modular architectures supporting simulation and robotics applications. Conclusion: Repurposing medical manikins for robotics presents transformative potential for human-robot interaction and biomedical engineering. Achieving success requires tackling integration challenges through interdisciplinary collaboration and standardized frameworks.

Abstract: The primary challenge in robotic navigation lies in enabling robots to adapt effectively to new, unseen environments. Addressing this gap, this paper enhances the Twin Delayed Deep Deterministic Policy Gradient (TD3) model's adaptability by introducing randomized start and goal points. This approach aims to overcome the limitations of fixed goal points used in prior research, allowing the robot to navigate more effectively through unpredictable scenarios. This proposed extension was evaluated in unseen environments to validate the enhanced adaptability and performance of the TD3 model. The experimental results highlight improved flexibility and robustness in the robot's navigation capabilities, demonstrating the model's ability to generalize effectively to unseen environments. In addition, In addition, this paper presents a streamlined overview of the TD3 algorithm, focusing on its core mechanisms and improvements, to clarify its application in achieving enhanced adaptability and performance.

Abstract: Service robots commonly deliver objects through direct handovers, assuming users are fully attentive. However, in real-world scenarios, users are often occupied with other tasks. This paper investigates how user attentiveness affects preferences between direct handovers and placing objects on a table. A user study was conducted (n=15) to evaluate these strategies in scenarios where participants were either occupied (simulated via a typing task) or unoccupied. Results show that placing objects on the table significantly enhances user experience when users were occupied, with higher ratings for satisfaction, perceived safety, confidence in robot's ability and intuitiveness of interaction. While direct handovers performed better with unoccupied users compared to occupied users, table placement maintained consistently high performance regardless of user state. All participants preferred table placement when occupied, and the majority preferred it even when unoccupied. These findings suggest table placement should be the default object delivery strategy for service robots, particularly in environments where user attention may vary. We also discuss implications for robot design and propose future directions for adaptive delivery behaviors.

Abstract: Aiming at global path planning of mobile robot in unknown environment and how to avoid random dynamic and static obstacles in unknown environment, A path planning algorithm combining improved A* algorithm and optimized dynamic window method is proposed. The A* algorithm has a more comprehensive global path planning ability, and has a good computational speed, but also is currently the most widely used algorithm for global path planning. But the traditional A* algorithm also has many drawbacks, low search efficiency in complex environments, the existence of a large number of redundant nodes, the path is not smooth and other problems. Therefore, this paper proposes an improved A* algorithm first, which reduces the search direction, removes redundant turning points and covariance nodes, and obtains a smooth optimal planning path after Bessel curve optimization; secondly, it is optimized for the single motion state of the dynamic window method, and the safety distance is set to cope with obstacles that have a similar motion state to the robot, and the improved A* algorithm is integrated with the optimized dynamic window method, so as to meet the global planning The improved A* algorithm is integrated with the optimized dynamic window method, so as to realize obstacle avoidance in the face of random obstacles at the local position while satisfying the optimal curve in the global planning path. After simulation experiments with the traditional A* algorithm in several groups of different environments, the experimental results are obtained, the improved A* algorithm has obvious advantages in global path planning, the computation time is reduced by 40%, the search nodes are reduced by 50%, and the cost of global path search is reduced by 75%, and the fusion with the optimized dynamic window method can solve the local obstacle avoidance problem very well.

Abstract: Large Language Models (LLMs) provide cognitive capabilities that enable robots to interpret and reason about their workspace, especially when paired with semantically rich representations like semantic maps. However, these models are prone to generating inaccurate or invented responses, known as hallucinations, that can produce an erratic robotic operation. This can be addressed by employing agentic workflows, structured processes that guide and refine the model’s output to improve response quality. This work formally defines and qualitatively analyzes the impact of three agentic workflows (LLM Ensemble, Self-Reflection, and Multi-Agent Reflection) on enhancing the reasoning capabilities of an LLM guiding a robotic system to perform object-centered planning. In this context, the LLM is provided with a pre-built semantic map of the environment and a query, to which it must respond by determining the most relevant objects for the query. This response can be used in a multitude of downstream tasks. Extensive experiments were carried out employing state-of-the-art LLMs and semantic maps generated from the widely-used datasets ScanNet and SceneNN. Results show that agentic workflows significantly enhance object retrieval performance, especially in scenarios requiring complex reasoning, with improvements averaging up to 10% over the baseline.

Abstract: This survey extends and refines the existing definitions of integrity and protection level in localization systems (localization as a broad term, i.e., not limited to GNSS-based localization). In our definition, we study integrity from two aspects: quality and quantity. Unlike existing reviews, this survey examines integrity methods covering various localization techniques and sensors. We classify localization techniques as optimization-based, fusion-based, and SLAM-based. A new classification of integrity methods is introduced, evaluating their applications, effectiveness, and limitations. Comparative tables summarize strengths and gaps across key criteria. The survey presents a general probabilistic model addressing diverse error types in localization systems. Findings reveal a significant research imbalance: 73.3% of surveyed papers focus on GNSS-based methods, while only 26.7% explore non-GNSS approaches like fusion, optimization, or SLAM, with few addressing protection level calculations. Robust modeling is highlighted as a promising integrity method, combining quantification and qualification to address critical gaps. This approach offers a unified framework for improving localization system reliability and safety. This survey provides key insights for developing more robust localization systems, contributing to safer and more efficient autonomous operations.

Abstract: Aiming at the problems of six-degree-of-freedom robotic arm in three-dimensional multi-obstacle space, such as low sampling efficiency and path search failure, an improved fast extended random tree (RRT*) algorithm for robotic arm path planning method (abbreviated as HP-APF-RRT*) is proposed. The algorithm generates multiple candidate points per iteration, selecting a sampling point probabilistically based on heuristic values, thereby optimizing sampling efficiency and reducing unnecessary nodes. To mitigate increased search times in obstacle-dense areas, an Artificial Potential Field (APF) approach is integrated, establishing gravitational and repulsive fields to guide sampling points around obstacles toward the target. This method enhances path search in complex environments, yielding near-optimal paths. Furthermore, the path is simplified using the triangle inequality, and redundant intermediate nodes are utilized to further refine the path. Finally, the simulation experiment of the improved HP-APF-RRT* is executed on the Matlab and ROS, and the physical experiment is done on the NZ500-500 robotic arm. The effectiveness and superiority of the improved algorithm are deter-mined by comparing it with the existing algorithms.