Abstract: The thermo-mechanical behavior of masonry materials is investigated through an in-tegrated experimental testing and numerical modelling approach. The study focuses on the characterization of masonry under fire exposure, where coupled thermal and mechanical effects govern material response and failure mechanisms. A multi-scale framework is proposed to link physico-chemical transformations, material-level prop-erties, and structural-scale behavior. The experimental component includes full-scale fire-resistance tests on load-bearing masonry walls, providing temperature evolution, deformation histories, and observed damage patterns. These results enable the identi-fication of key mechanisms such as stiffness degradation, cracking, and the influence of thermal gradients on structural response. The experimental observations are used to support the development and calibration of numerical models capable of representing temperature-dependent behavior and strain-rate effects. In addition, non-destructive testing techniques are incorporated to relate internal damage to measurable diagnostic signals, enhancing material characterization and structural assessment. Although the present study is limited to structural-scale validation, the proposed approach demon-strates how combined experimental and numerical strategies can be used to develop consistent constitutive descriptions of masonry materials. The results contribute to improved understanding and modelling of engineering materials subjected to coupled thermo-mechanical loading.

Abstract: Polymer composites used in structural applications are frequently exposed to combined thermal and moisture environments, which gradually degrade their mechanical performance over time. Predicting this behavior remains challenging due to the complex interaction between moisture diffusion, thermally activated degradation, and evolving mechanical response. In this study, a physics-based digital twin framework is developed to model the coupled hygro–thermo–mechanical degradation of fiber-reinforced polymer composites. The approach integrates moisture diffusion based on Fickian principles, temperature-dependent degradation described using Arrhenius kinetics, and a coupled modulus evolution model to represent time-dependent material behavior. The results capture key physical trends, including moisture saturation behavior, gradual stiffness reduction, and stable damage evolution under moderate environmental conditions. In addition, the influence of fiber volume fraction and temperature is systematically examined, highlighting their important roles in governing degradation resistance and long-term durability. Rather than relying on data-driven methods, the proposed framework is grounded in physically interpretable mechanisms, providing a transparent and computationally efficient tool for durability assessment. The model is presented as a qualitative benchmarking framework in the absence of system-specific calibration, with clear potential for future experimental validation and probabilistic extensions.

Abstract: To address the issues of manual operation dependency and low efficiency in tunnel fire research combining computational fluid dynamics (CFD)with deep learning, this paper proposes a multi-agent collaborative framework based on large language models to automate the entire process of inverting fire source characteristics. The framework decomposes the traditional workflow into four specialized agents, namely physical modeling, data governance, model training, and evaluation analysis, which collaboratively execute end-to-end tasks from CFD scenario generation to model deployment. The results demonstrate that the CNN-LSTM model performs optimally. Under a 6 second observation window and 10 meter sensor spacing, the average R² reaches 0.942, representing a 2% improvement over the baseline LSTM model, while the RMSE is reduced by 28.8%. Under sparse deployment with 30 meter spacing, the average R² remains as high as 0.917, validating the effectiveness of integrating spatial feature extraction with temporal modeling. This work provides an efficient technological pathway for intelligent tunnel fire identification and advances the research paradigm from manual optimization to multi-agent system optimization.

Abstract: Plastic packaging waste has emerged as a critical environmental challenge due to its persistence, low degradation rates, and increasing accumulation in terrestrial and marine ecosystems. Conventional petroleum-based plastics dominate packaging applications because of their durability and low cost; however, their environmental impacts have prompted urgent demand for sustainable alternatives. Bio-based and compostable packaging materials offer promising solutions by utilizing renewable resources and enabling environmentally benign end-of-life pathways. This paper examines the development of bio-based and compostable packaging alternatives aimed at reducing plastic waste. Through a systematic review of material innovations, processing technologies, and life-cycle considerations, the study evaluates the performance, environmental benefits, and limitations of emerging bio-based packaging solutions. The findings indicate that materials such as polylactic acid, polyhydroxyalkanoates, starch-based composites, and cellulose-derived packaging can significantly reduce fossil resource dependency and plastic pollution when supported by appropriate infrastructure. The paper concludes that while bio-based and compostable packaging presents strong environmental potential, successful large-scale adoption requires integrated design strategies, composting infrastructure, and supportive policy frameworks.

Abstract: This paper presents a certification-oriented, system-level analysis of using Linux in safety-critical airborne avionics, with emphasis on Design Assurance Level (DAL) A/B systems. Linux is a feature-rich general-purpose OS whose open and dynamic execution semantics can be difficult to finitely bound and operationally “freeze” at integration time. We analyze how key architectural characteristics of Linux—including a large trusted computing base (TCB), asynchronous kernel activity, mutable memory mappings, monolithic privilege domains, and a rapidly evolving toolchain—interact with assurance objectives commonly expected under DO-178C and DO-330. The analysis identifies eight independently sufficient certification-relevant risk factors affecting temporal determinism, spatial isolation, fault containment, configuration stability, and lifecycle assurance feasibility. To avoid fragmented observations, these factors are consolidated into a unified causal framework that traces certification challenges back to two consequence categories: airworthiness feasibility constraints and semantic complexity. The framework also evaluates commonly proposed mitigations (e.g., PREEMPT_RT, containers, and static configuration) and explains why these measures may not address the underlying system-level issues. The contribution of this work is a structured argumentation framework that makes architectural implications explicit and supports operating-system selection and safety governance decisions in integrated modular avionics.

Abstract: This paper presents the simulation of the Asynchronous Machine Module, making use of the LabView tool to make the graphical presentation of it, simulating its real behavior at the time of performing the practices, thus allowing the prediction of the state of the Variables of the induction motor according to its operation. With the data obtained from the simulation carried out in Simulink it was possible to observe the ideal behavior of the machine and the realization of the simulation in LabVIEW in order to later take data in a practical way and being able to compare by error percentage having low results.

Abstract: In hybrid Wire Arc Additive Manufacturing with interlayer Friction Stir Processing (UAMFSP), refined microstructures are produced in aluminum alloy builds; however, the thermal parameters governing layer-resolved defect evolution remain poorly understood. In this study, a first mechanistic framework is presented, identifying post-peak cooling rate as a governing parameter for porosity evolution in UAMFSP Al 4043 three-layer walls. In this study, a comprehensive multi-scale characterization of three-layer Al 4043 UAMFSP walls is presented, employing infrared thermography, quantitative optical grain morphology analysis (N = 10,346 grains, Layers 1–3), scanning electron microscopy from 250× to 35,000×, and image-based porosity quantification from calibrated SEM fields. A counterintuitive layer-dependent porosity gradient is reported, wherein the upper layer (L3) exhibited 80% higher porosity (2.90 ± 1.18%) and 107% higher pore density (4,283 ± 900 pores/mm²) than the bottom layer (L1), despite recording a 26% lower peak FSP surface temperature (195.1 vs. 263.2°C) (n = 3 fields per layer; Cohen’s d ≈1.7). Based on these results, the post-peak cooling rate, rather than peak temperature, is identified as a dominant controlling parameter for void consolidation quality, as evidenced by the observation that L3 cools at −12.3 °C/s versus −16.2 °C/s for L1, which is consistent with prolonged high-temperature dwell and reduced plastic-flow-assisted pore closure in the upper layer. It should be noted that the anomalously rapid cooling of L2 (−46.9 °C/s), attributed to a bilateral thermal gradient between the substrate and the air-cooled free surface, places it in a thermally distinct regime; accordingly, L2 is utilized exclusively for high-magnification SEM characterization in this study. High-magnification SEM imaging (12,000×–35,000×) revealed a frequent spatial co-location of sub-micron pores with fragmented Al–Si eutectic particles, which is consistent with preferential void persistence near particle–matrix interfaces. Furthermore, grain morphology exhibited evolve non-monotonically with build height, with mean circularity following the order L3 (0.645) > L1 (0.621) > L2 (0.569), and the equiaxed grain fraction ranging from 25.5% (L2) to 36.1% (L3) (ANOVA: F = 56.2, p = 5.15 × 10⁻²⁵), while the mean equivalent grain diameter remained below 3.4 μm across all layers. In summary, the outcomes of this study establish post-peak cooling rate, rather than peak temperature, as a governing parameter for void consolidation quality in UAMFSP builds. These outcomes are presented as a first mechanistic framework for this class of hybrid process, and are intended to motivate targeted controlled experiments, subsurface thermal characterization, and expanded porosity sampling in future investigations of multi-layer additive–deformation manufacturing of Al-based alloys.

Abstract: This study addresses the need for reliable calibration of finite element (FE) models of historical masonry structures, whose dynamic behavior is often poorly represented without experimental validation. The objective is to calibrate a numerical model of the San Pedro Apóstol Church (Uchumayo, Peru) using ambient vibration data. An experimental campaign was conducted using a TROMINO® seismograph, and modal parameters were identified through signal processing techniques. A parametric grid-based calibration approach was implemented to systematically adjust the mechanical properties and reduce discrepancies between numerical and experimental responses. The results show that calibration required a significant reduction of the elastic modulus depending on the structural component, ranging from 60%–80% in concrete rings, 60%–80% in the nave vault, 60%–70% in masonry walls, and 20% in the tower. The comparison between numerical and experimental modal periods indicates a satisfactory agreement for the first modes, while higher modes exhibit larger discrepancies, consistent with the expected sensitivity to local effects and modeling assumptions. The study demonstrates that systematic model updating based on ambient vibration testing provides a practical and reliable approach for representing the dynamic behavior of heritage structures and supports their seismic assessment and conservation.

Abstract: Hard ceramic coatings are essential for extending the operational limits of metal components in the extreme thermal and mechanical conditions of the aerospace and defense sectors. While considerable research exists on individual synthesis and characterization methods, a critical knowledge gap persists in bridging experimental fabrication with predictive computational modeling, a gap that limits the rational design of next-generation coating systems. This review addresses this gap by critically synthesizing the lifecycle of aerospace coatings from atomic-scale design to industrial deployment. Unlike prior reviews that focus on either fabrication or individual coating chemistries in isolation, this work uniquely integrates Integrated Computational Materials Engineering (ICME) with emerging machine learning (ML) strategies to provide a unified design-to-deployment framework. The principal ceramic material systems, Tungsten Carbide (WC), Boron Nitride (BN), Boron Carbide (B₄C), Silicon Carbide (SiC), Alumina (Al₂O₃), and Zirconia (ZrO₂) are discussed within the context of their specific roles in protecting aerospace-grade alloys. A central contribution is the multiscale computational framework, spanning Density Functional Theory (DFT), Molecular Dynamics (MD), mesoscale modelling, Finite Element Analysis (FEA), and ML-driven inverse design, which collectively accelerate the prediction of thermal breakdown, multi-axial stress responses, and coating lifetime. By relating these advances to gas turbine engines, airframes, and supersonic and hypersonic aviation systems, this review offers a clear research roadmap. Future research should prioritize the development of ultra-high-temperature ceramics (UHTCs), multifunctional self-healing coatings, and data-driven approaches to surface engineering. The goal is to move the field beyond traditional trial-and-error methods toward a more predictive framework based on fundamental physics and accelerated by machine learning techniques.

Abstract: This observational study evaluated changes in selected performance parameters of 15 new high-speed dental handpieces after eight months of routine clinical use in a routine educational undergraduate environment (two 4h daily clinical shifts, five days per week, with repeated sterilization cycles). All handpieces underwent routine cleaning, lubrication, and autoclave sterilization as instructed. The turbine components from the handpieces were disassembled and examined by stereomicroscopy before and after use, while free-running speed and bur-tube friction grip force were assessed at the same intervals. Two handpieces were no longer operational at follow-up due to ball bearing failure. Among the remaining handpieces, statistically significant reductions were observed in both free-running speed and friction grip force (p < 0.01). Microscopic examination of the rotors revealed surface alterations consistent with corrosion and wear. Within the limitations of this study, routine clinical use over an eight month period was associated with measurable changes in key performance characteristics of high-speed dental handpieces in educational clinical settings.

Abstract: Unmanned aerial vehicles (UAVs) are increasingly recognized as a viable option for urban parcel delivery. However, their energy performance under varying environmental and mission conditions remains underexplored. This paper presents a simulation-based analysis of multirotor UAV energy consumption using the PX4-Gazebo platform, calibrated with real-world telemetry from a publicly available DJI Matrice 100 dataset [12]. Three UAV models—Iris, Typhoon H480, and Octocopter—were evaluated across a range of payloads (0.1–5 kg), cruise speeds (2–16 m/s), and environmental factors, including wind, temperature, and humidity. Results revealed consistent U-shaped energy speed curves, with optimal cruise speeds ranging from 8 to 10 m/s, depending on the payload and platform. Headwinds alone increased energy consumption by up to 25% and combined cold–dry and headwind conditions resulted in increases of up to 53% for lightweight platforms. Validation against field telemetry showed mean absolute percentage errors below 11%. These findings offer a simulation-grounded framework for UAV mission planning, platform selection, and integration into energy-efficient logistics networks, and development of data-driven optimization frameworks. The three platforms span a 10-fold mass range (1.4–14 kg), enabling systematic analysis of how energy scaling behavior varies across lightweight, mid-range, and heavy-lift delivery configurations.

Abstract: Conductive intracardiac communication (CIC) is one of the most innovative and promising communication technologies in multi-point cardiac pacing schemes that utilize the heart as the transmission channel in recent years. Current research predominantly focuses on the static channel characteristics, with only limited investigations into the dynamic responses of amplitude-frequency and amplitude-time behaviors. Designing CIC systems solely on the basis of static properties can result in inaccurate channel estimation, distorted channel state information (CSI), elevated bit error rate (BER), and overall degradation of system communication performance. To solve the problems of dynamic channel measurement and modeling of the heart, this paper for the first time proposes a dynamic channel modeling method for CIC based on sinusoidal response and impulse response. Firstly, we develop a physical simulation and miniaturized measurement setup to measure dynamic cardiac channel, and analyze the amplitude-frequency characteristics and amplitude-time characteristics. The influence of factors such as instrument differences, heart rate, flow rate and comparative experiments of free electrodes and fixed electrodes on the channel characteristics are also discussed. Secondly, we systematically analyze the path loss, shadowing effect, multipath effect and Doppler effect of the CIC channel. Combined with the dynamic channel characteristics and parameters, we propose a composite fading dynamic channel model and analyze the BER performance of baseband signals transmission and On-Off Keying (OOK) modulation systems. We can conclude that (1) The CIC channel exhibits capacitive characteristics. The fluctuation of the channel gain of the free electrode is mainly caused by motion artifacts. The fixed electrode can effectively suppress this interference. (2) The dynamic channel gain of CIC varies periodically with the heartbeat, and the fluctuation range of the signal is less than 1-2 dB. This is due to the length change of the myocardial tissue. (3) The CIC channel still presents extremely weak shadow fading, no significant multipath, and no measurable Doppler characteristics under dynamic conditions, belonging to an extremely slow fading channel. This work provides effective dynamic channel measurements approach and parameter basis for the transceiver design of CIC and a reliable model for the simulation for CIC systems.

Abstract: Vegetative restoration in degraded landscapes requires deployment strategies that can scale while adapting to heterogeneous terrain conditions. Conventional aerial seeding is typically performed in an open-loop manner, where seeds are distributed uniformly without accounting for local suitability for plant establishment. This paper describes a modular, unmanned aerial vehicle (UAV)-independent system for vision-guided aerial seeding, integrating onboard sensing, embedded processing, and real-time actuation within a closed-loop framework. The system combines a downward-facing visible-spectrum camera, a lightweight embedded computing unit, and a custom seed-dispensing mechanism organized in a perception–decision–actuation pipeline. Terrain suitability is evaluated in real time using three convolutional neural network (CNN) models and a conventional color-based greenness ratio method, enabling classification of sowable and non-sowable areas based on soil exposure, vegetation density, and obstacle presence. A confidence-based decision strategy, combined with temporal filtering, reduces noisy measurements, while an altitude-adaptive pulse-width modulation (PWM) controller regulates seed release to maintain a target seed density across varying flight heights. Field experiments conducted under semi-arid conditions show that terrain classification accuracy exceeds 85%, with inference latency below 100 ms per frame on an embedded Jetson Nano platform. In addition, the proposed control strategy maintains consistent seed density across different altitudes. These results indicate that onboard perception can be effectively coupled with adaptive aerial actuation, enabling more selective and efficient UAV-based vegetative restoration.

Abstract: This systematic literature review (SLR) investigates the use of physics-informed neural networks (PINNs) in electromagnetics by examining peer-reviewed journal articles and conference papers. By integrating governing physical laws into the loss function of a neural network (NN), PINNs offer a promising mesh-free method in scientific computing. The reviewed records were retrieved from the databases Scopus, Web of Science, and IEEE Xplore, published between 2020 and 2025. The initial dataset comprised 500 records of which 292 unique publications were identified. These were screened, yielding a final set of 139 publications that met predefined inclusion criteria. The analysis reveals a growth in research activity, with a pronounced increase from 2022 onward. The reviewed literature predominantly addresses electrodynamic problems, employs feedforward neural network architectures and adopts unsupervised, physics-driven training paradigms. Two-dimensional problem formulations are considerably more prevalent than three-dimensional formulations, and advanced architectures remain limited. A contingency table analysis reveals the associations between the extracted characteristics. The choice of medium is strongly dependent on the physics regime, and architectural diversity increases with spatial dimensionality. The review’s conclusions identify potential priorities for future work: extending three-dimensional formulations to the static and quasistatic electromagnetic regimes, broader architectural experimentation particularly in lower-dimensional settings, and increased use of semi-supervised learning in static electromagnetic applications.

Abstract: This paper presents a fast adaptive power control with implicit predictive behavior for an onboard power converter operating in support with a 400 Hz aircraft electrical network. Accurate control of active and reactive power in such high-frequency networks requires precise estimation of the network voltage phase, frequency, and amplitude. To achieve this, a novel adaptive phase-locked loop (PLL) algorithm is integrated with a proportion-al–resonant (PR) current controller. The adaptive PLL continuously estimates the instan-taneous phase, frequency, and amplitude of the fundamental voltage component, ena-bling fast synchronization and dynamic adjustment of the PR controller resonant fre-quency. This combination familiarizes predictive characteristics into the control loop without the need for computationally intensive model predictive control algorithms. Sim-ulation results demonstrate that the proposed method significantly reduces synchroniza-tion time, maintains high accuracy under frequency variations and harmonic distortion, and exhibits robustness against measurement noise. Furthermore, the algorithm’s modu-lar and computationally efficient structure makes it suitable for real-time FPGA imple-mentation. The proposed approach provides an effective solution for high-performance power management in aircraft electrical systems, ensuring precise power control under hard dynamic conditions.

Abstract: This paper reports thermophysical-property data for binary dielectric mixtures of hy-drofluoroether (HFE) fluids and ethyl acetate (EA) and applies a correlation-based workflow to compare their single-phase forced-convection performance in rectangular minichannels. Density, viscosity, thermal conductivity, and isobaric heat capacity were measured at three temperature levels (293.1, 313.1, and 328.1 K) for selected compositions of HFE-7100/EA, HFE-7300/EA, and HFE-73DE/EA. Using these meas-ured properties, Reynolds and Prandtl numbers were evaluated and a laminar ther-mally developing correlation was employed to obtain Nusselt numbers and corre-sponding heat transfer coefficients. The assessment was performed for two geometries representing a long reference minichannel module and a short multi-minichannel module. A validation dataset for pure HFE-7100 in the short module, derived from IR thermography and an energy-balance data reduction, indicates a systematic deviation between correlation-based estimates and experimental values, which should be con-sidered when interpreting absolute predictions. The presented dataset and workflow support transparent down-selection of candidate mixtures prior to extended experi-mental campaigns.

Abstract: As cities worldwide face challenges of rapid urbanization and declining public transit ridership, traditional fixed-route systems often fail to meet evolving mobility needs. Urban planning issues, such as suburban sprawl and fragmented land use, exacerbate these limitations, leading to underutilized services, higher operational costs, and accessibility gaps, particularly for underserved communities. Demand-Responsive Transit (DRT) systems have emerged as an effective solution, offering flexible, on-demand services that dynamically adjust routes based on user demand. This review synthesizes insights from 65 studies, including 20 real-world implementations, examining DRT's potential to enhance accessibility, cost efficiency, and environmental sustainability. Key findings demonstrate that DRT systems reduce operational costs by 25-35% while increasing ridership up to 300%. Integration of AI-driven routing algorithms improves service reliability by 90-98% and reduces travel times by 35-50%. Multiple booking interfaces increase adoption by 40-60%, while multimodal integration expands service coverage by 100-150%. However, significant barriers persist, with 58% of DRT system models requiring subsidies and 51% facing equity challenges. The study proposes hybrid funding models, integrated multimodal platforms, and inclusive design approaches to address these challenges. By aligning with urban design principles and leveraging advanced technologies, DRT systems can enhance urban resilience while promoting sustainable development.

Abstract: Currently operating commercial photovoltaics (PV) systems integrated with agricultural production (Agrivoltaics) offer immense potential for the dual harvest of renewable energy and agro-products. Within controlled-environment agriculture (CEA), the use of semi-transparent photovoltaics (ST-PV) and the ability to control the microclimate and shading are beneficial for the production of high-value crops such as cucumbers. The objective of this research was to commence the cultivation of cucumbers under evolving CEA-PV systems by combining greenhouse experiments with computer vision (CV) based driven phenotyping to create an analytical framework and system control framework for the cultivation of cucumbers in an evolving CEA-PV system. The method involved using the monitored plant vigor to control in real time the irrigation and shading of the cucumber plants. The control of irrigation and shading was based on the monitored plant vigor as determined by a U-Net++ implementation for canopy segmentation, an EfficientNet-B3 implementation for stress detection, and a CNN regressor for growth trait estimation. Within the greenhouse, uniform environmental and fertigation conditions were established to evaluate the effect of four shading regimes (0%, 20%, 40%, 60%) on the cucumbers. Simulated, yet representative results predicted cucumber yields to be stable (within ±4% of full yield) with a 20% shading and a 15-20% reduction in water use compared to full sun. Yield was also observed to drop by 10-14% under higher shading of 40 to 60% due to insufficient photosynthetic activity for fruiting. The CNN based models were robust, (segmentation IoU 0.91, stress-class F1 0.92, LAI regression R²≈0.93), allowing for precise and comprehensive monitoring in an annual non-invasive fashion. The greenhouse's annual photovoltaic (PV) output was estimated to be 1,550 to 1,750 kWh/kWp which is able to exceed the energy demand resulting to a net energy surplus. The outcome demonstrates that the cucumber crop can be successfully combined with controlled environment agrovoltaic systems with moderate shading for optimum cucumber yield. Moreover, informed supervision through Artificial Intelligence (AI) helps to navigate closed-loop systems and enhance the water-use efficiency and yield stability.

Abstract: The rapid and accurate assessment of residual ultimate strength after ship damage is crucial for rescue decision-making and navigation safety, while traditional methods struggle to meet the demands of complex random damage scenarios in terms of efficiency or accuracy. This study proposes a hybrid framework that integrates high-fidelity nonlinear finite element simulation (FEM) and a Bayesian-regularized backpropagation neural network (BPNN). FEM is used to accurately simulate a large number of random damage scenarios, generating a physically credible benchmark dataset. BPNN serves as an efficient surrogate prediction model, with its key parameters—the number of hidden layers and the training algorithm—systematically optimized to enhance generalization capability. The results show that: 1) The FEM simulation results deviate by less than 5% compared to the Smith method, validating the reliability of the dataset. 2) The prediction performance of BPNN is highly dependent on the number of hidden layers and the training algorithm, exhibiting non-monotonic variation, with an optimal parameter combination identified as 8 hidden layers paired with the Bayesian algorithm, achieving a prediction regression value R of 0.91662. 3) Deep networks are prone to overfitting, while shallow networks suffer from insufficient feature capture. 4) The Bayesian algorithm performs best in terms of overfitting resistance and stability. This study not only provides a high-precision and efficient intelligent solution for residual strength assessment of damaged hulls, but its systematic neural network parameter optimization strategy, particularly the approach of identifying optimal depth and selecting anti-overfitting algorithms, also offers important reference for the design of intelligent damage assessment models for similar engineering structures.

Abstract: Vision-Language-Action (VLA) models unify visual perception, natural-language understanding, and action generation within a single foundation model, allowing a robot to follow instructions such as “fold the towel” or “fly to the red building” directly from camera images. Because VLAs inherit world knowledge from internet-scale pre-training, they have become the dominant framework for learning-based manipulation, with bimanual coordination serving as the most demanding testbed: two arms with 7+ degrees of freedom each must move in concert to fold, assemble, and reorient objects. Unmanned aerial robotics faces a structurally similar challenge: a drone must coordinate thrust, attitude, and increasingly gripper commands from visual observations under strict latency and payload constraints. This review covers 186 contributions spanning 2017–2026 and organized along seven dimensions: VLA architectures, training recipes, action representations, bimanual coordination (2022–2026), unmanned aerial vehicle (UAV) navigation and control (2017–2026), language grounding, and cross-cutting concerns including memory and world models. We show that the coordination strategies, training recipes, and action representations developed for bimanual VLAs transfer to unmanned aerial systems, and identify fourteen research directions across both domains.