This paper proposes an energy-efficient walking generation method utilizing limit cycles generated by nonlinear model predictive control (NMPC). Conventional limit cycle walking methods rely on strong feedback, such as output zeroing control, to attract the robot’s state toward a predefined periodic trajectory. However, we hypothesize that employing feedback control that better leverages the robot’s dynamics can improve energy efficiency during walking. Our previous work confirmed that using limit cycles generated by NMPC can produce energy-efficient walking patterns. This study builds upon this foundation and proposes a new method for generating walking in a general five-link bipedal robot. Through extensive numerical simulations, we demonstrate that the proposed method achieves highly energy-efficient walking while exhibiting excellent convergence to periodic trajectories.

Direct collocation (DC) methods are utilized for addressing trajectory optimization challenges in robotics due to their ability to generate dynamically consistent solutions. However, in the cable-driven robotic systems, where tension constraints impose kinodynamic restrictions, maintaining accuracy becomes significantly complex. This article addresses robot tensionability and proposes a method to overcome the limitations. A DC method is proposed to minimize the actuator force rate in a trajectory planning problem for a designed cable-driven parallel robot. The system comprises a 3-cable parallel mechanism with a central spine to counteract the end-effector’s weight and enhance tensionability. Integrating a pneumatic cylinder into the system that supports trajectory planning implementation is essential to minimize jerky motions. The DC method is applied through the proposed quadratic programming approach and benchmarked against existing packages to achieve and compare the resulting smoother trajectory. The numerical results demonstrate that the proposed method significantly reduces computation cost and enhances accuracy. Experimental data corroborate the simulation results, validating the method’s efficacy.

This study presents the control of an omnidirectional automated guided vehicle (AGV) with mecanum wheels using a hybrid optimization algorithm that combines a modified A* algorithm and the dynamic window approach (ADWA-HO). The method ensures efficient and precise navigation in both static and dynamic environments. The modified A* algorithm generates global paths, removes redundant nodes, and refines trajectories to improve efficiency and smoothness. At the same time, the dynamic window approach (DWA) enables real-time local path planning and obstacle avoidance. By evaluating the AGV’s motion commands in real time, ADWA-HO selects optimal velocity commands within a dynamically updated window, thereby reducing route conflicts and ensuring stable movement. Compared with benchmark methods including dynamic A* (D*), artificial potential field (APF), DWA, probabilistic roadmap (PRM) & rapidly exploring random tree (RRT) fusion, and PRM & DWA fusion, the proposed ADWA-HO achieves improvements in average path length of 28.10%, 22.95%, 21.16%, 17.35%, and 10.71% and in average motion time of 23.48%, 17.85%, 15.47%, 11.86%, and 7.53% on both Map 1 and Map 2, respectively. The difference between simulation and real-world experiments is limited to 5.35% in path length and 4.38% in motion time, confirming the method’s practical reliability. Furthermore, the algorithm achieves lower standard deviation in both metrics, indicating higher consistency of performance. This work also introduces a novel map-building strategy based on geometric and semantic data modules, which enhances the adaptability of real-world AGV deployment.

This paper presents an innovative hybrid approach that integrates traditional control strategies with deep reinforcement learning for robotic assembly. By fusing multimodal information from visual and force feedback, the method leverages admittance control to ensure safe force feedback while using deep reinforcement learning to process visual input, enabling precise control and real-time correction of assembly actions. This multi-sensor feedback mechanism not only enhances the stability and accuracy of the assembly process but also improves the robot’s robustness and adaptability in uncertain environments. Additionally, a twin-delay deep deterministic policy gradient algorithm based on residual reinforcement learning is proposed. The design of a task-specific reward function, which simultaneously considers visual goals, force compliance, and contact stability, effectively addresses challenges such as difficult state information acquisition and sparse rewards in assembly tasks. This improves the robot’s interaction capabilities and task execution efficiency in real-world environments. Experimental results demonstrate that the method designed in this paper effectively reduces the training time for reinforcement learning from 400 epochs to 100 epochs, significantly decreases the magnitude of contact forces during the assembly process, and shortens the contact time.

Path planning, as a critical component of mobile robotic systems, significantly impacts operational efficiency and energy consumption ratios. State-of-the-art algorithms often suffer from inadequate real-time adjustment capability, insufficient dynamic environment adaptation, and suboptimal computational efficiency. To resolve these limitations, we propose a bidirectionally optimized path planning algorithm named Bidirectional Q-learning LPA* (BQ-LPA*), which incorporates three key innovations. Specifically, to enhance the global search capability of the LPA* framework, we replace fixed heuristic functions with a Q-learning-driven adaptive heuristic mechanism, which improves path quality through dynamic heuristic weighting and update strategies. Additionally, to improve the convergence rate and sample efficiency of Q-learning in complex environments, we propose integrating the LPA* framework to provide prior knowledge guidance, which can effectively minimize redundant exploration attempts by informed pathfinding initialization. Moreover, the Q-learning method inherently faces dimensionality challenges in high-dimensional continuous spaces, which manifest as action space congestion, storage bottlenecks, and computational inefficiency. To mitigate these risks, we devise an LPA*-based space discretization strategy that can reduce action space dimensionality and preserve the path feasibility. Experimental results show that, compared with mainstream path planning algorithms, BQ-LPA* achieves higher accuracy and faster convergence in mobile robot path planning.

The use of passive exoskeletons in industrial settings has gained growing interest as a means to reduce muscle fatigue and prevent work-related musculoskeletal disorders. However, translating laboratory methods into realistic occupational environments remains a challenge. This study presents a modular and wearable-sensor-based experimental protocol designed to bridge this gap by enabling the evaluation of exoskeletons in both static (STC) and dynamic (DYN) tasks while preserving natural movement variability. A total of 52 participants, including both men and women, completed tasks with and without two different passive exoskeletons, while their motor activity was assessed using surface electromyography (sEMG) and inertial motion sensors. The protocol incorporates key EMG-based metrics – Root Mean Square (RMS) and Hilbert Median Frequency (MDF) – that effectively quantify muscle activation and fatigue, along with subjective Perceived Fatigue Scores (PFS) and a task performance metric (Screwing Velocity, SV). The results confirm that the exoskeletons significantly reduce muscle activation and perceived fatigue without impairing task performance. The proposed methodology, combining rigorous metrics with wearable and non-invasive instrumentation, offers a robust framework for evaluating fatigue in both STC and DYN tasks and usability in both laboratory and field settings. This protocol represents a valuable tool for both research and industrial evaluation, facilitating the evidence-based integration of exoskeletons into real-world industrial workflows.

This endeavor encompasses establishing a dynamic model for a constrained joint module system in collaborative robots, predicated upon the Udwadia-Kalaba equation and constraint-following methodologies. Additionally, a leakage-type adaptive robust controller is developed to assuage uncertainties and disturbances. The structure of the dynamic model is methodically crafted, accommodating uncertain parameters to delineate the behavioral dynamics of the system. Furthermore, a meticulous derivation of a second-order representation of the constraint equations is undertaken to facilitate precise boundaries of the limitations imposed by the system. The proposed controller demonstrates adeptness in tailoring its strategies to the characteristics of both known and unknown attributes of the system, deftly navigating the intrinsic uncertainties of the system. Systematic simulations and empirical analyses have been performed to authenticate the efficacy of the advocated approach in regulating the joint module system. The research outcomes not only augment comprehension of robust control techniques for joint module systems but also furnish invaluable insights to propel future advancements within this specialized domain.

In view of the post-stroke finger contracture period, the patient’s muscle weakness causes the fingers to bend and not be extended, and the fingers are in a contracture state. A new hand rehabilitation exoskeleton with a cable and leaf spring hybrid drive is designed. The high-stiffness leaf spring helps the patient complete the extension movement, and the flexion and grasping movement is completed under the action of the cable. The exoskeleton combines the cable and the leaf spring in the driving form. It is flexible and can generate enough grasping force to meet daily activities. The workspace when wearing the exoskeleton is analyzed, and the simulation verifies that the exoskeleton has a high movement space. The stiffness of the finger module is analyzed to determine the appropriate size parameters of the leaf spring. The experimental prototype is built, and the structural performance test is carried out. A prosthetic hand model is made to simulate the hand of a patient without motor ability. The position control is carried out to complete the gesture experiment and grasping experiment, which verifies that the exoskeleton can meet the rehabilitation needs and daily grasping movements. Finally, a variety of performance parameters are designed to evaluate a variety of exoskeletons. The comparison shows that the exoskeleton in this paper has significant advantages, and the area coverage rate of the performance evaluation map can reach 70.4% of the ideal exoskeleton.

Permanent magnet synchronous motors (PMSMs) are the preferred choice for robot joint drives. Non-singular fast terminal sliding mode control (NFTSMC) can significantly enhance the robustness and control performance of PMSMs. Nevertheless, it requires the manual tuning of up to ten control parameters, and traditional tuning methods struggle to identify the optimal settings. Therefore, this paper proposes an NFTSMC optimization scheme for PMSM based on an improved gray wolf optimization (IGWO) algorithm. To ensure the GWO finds the optimal solution quickly in this application scenario, two enhancement strategies have been selected. In addition, a comprehensive evaluation indicator is proposed, which combines performance indicators such as response time and overshoot to guide the algorithm in achieving the desired control performance. Finally, an algorithm deployment scheme is proposed to achieve online performance optimization. The proposed approach has been experimentally validated using a fast-prototyping framework. The experimental results demonstrate that the proposed solution can quickly identify control parameters that meet the requirements under the guidance of the proposed evaluation indicator. Comparative experiments also confirm the superiority of the IGWO algorithm in this application.

Tendon-driven Continuum Robots (TDCRs) excel at operating in confined and complex environments due to their inherent flexibility and high degrees of freedom. Despite these advantages, achieving precise control in multi-section TDCRs remains challenging because of their infinite degrees of freedom, nonlinear behaviour, and coupled tendon actuation. This paper introduces a generalised virtual actuation space framework that significantly simplifies kinematic modelling and control of multi-section TDCRs. By formulating a novel concept of virtual actuation space that converts each bending section of the TDCR two-input actuation system, the proposed method reduces the complexity of TDCR modelling and control, enabling unique and simplified representations of each section. Furthermore, the formulation decouples each section via a generalised tendon mapping matrix that handles coupling effects. Experimental validation on a two-section TDCR demonstrates tracking performance with a root mean square error below 3 mm, corresponding to approximately 1% of the robot’s length. These results confirm the method’s efficacy in improving TDCR precision for minimally invasive surgery, industrial applications, and other constrained environments.

Non-spherical wrist manipulators are widely used in industrial settings, yet they lack effective inverse kinematics solutions. Current methods primarily rely on numerical iteration, which suffers from limitations such as sensitivity to initial values and convergence issues. Meanwhile, algebraic elimination methods require complex elimination techniques to obtain analytical solutions, restricting their practical engineering application. To address the limitations of these existing approaches, this paper innovatively proposes a novel analytical method based on conformal geometric algebra theory. The core of this method lies in utilizing the geometric characteristics of the manipulator to establish a polynomial equation for one of the joint variables, after which the remaining joint angles are solved according to the joint angle solution methodology. The correctness of the proposed method was verified using three sets of joint angles. Additionally, a comparative analysis with the Dixon elimination method was conducted using 100 sets of arbitrary initial joint angles. Example validation demonstrates that the proposed method exhibits significant advantages in computation time, solution completeness, and numerical accuracy, thereby providing a new theoretical tool and practical framework for the inverse kinematics analysis of robotic manipulators.

Robot grippers have drawn a lot of attention due to their various applications in the fields of manufacturing, agriculture, etc. The shape and mass of the workable objects have been considerable issues. For effective gripping, many studies have sought to control gripping forces; however, force control often requires complex external control structures. Here, it is aimed to develop a gripper of simple structure that resists moments, grasps object edges in the absence of complete object envelopment, and does not tilt the object. Moment resistance and edge grasping are key capabilities in ensuring stable object gripping. To ensure an energy-efficient, simple structure, a mechanical trigger and a variable torque joint link the output torque to the finger actuation angle without electrical sensing. The variable torque joint creates different torques for each finger, thus ensuring the sufficient reactive moments required for stable gripping without tilting the object. To implement the output torque profile, a mechanical cam was designed and utilized in the torque joint. The developed gripper effectively resists moments and grasps object edges without the need for electrical components such as sensors, wires, or batteries. This study shows that form-sensing data can be used in various scenarios to ensure successful gripping.

In this research, a hierarchical dynamic and kinematic modeling framework is proposed for a wheeled-legged manipulator (WLM), explicitly incorporating wheel slip and skid effects through the Gibbs–Appell formulation. Unlike traditional Lagrangian methods that depend on constraint multipliers, the proposed approach unifies the platform and manipulator dynamics while substantially reducing computational complexity. This integration enables efficient handling of nonholonomic constraints without compromising physical fidelity and offers a clear separation between subsystems, allowing the effects of wheel-ground interactions to be analyzed independently from manipulator motions. The proposed formulation is validated through a combination of MATLAB/Webots simulations and laboratory experiments conducted under both dry and wet (soapy ceramic) surface conditions. Experimental results indicate end-effector position deviations of 8–10.5% primarily due to wheel slip and initial joint torque discrepancies of 6.5–20% that progressively diminish as steady-state motion is reached. Comparative evaluation against a conventional Lagrangian model highlights the computational advantage of the Gibbs–Appell formulation, demonstrating reduced assembly time and fewer symbolic differentiation operations. Furthermore, a sensitivity analysis on friction coefficients and slip ratios confirms the robustness of the model to variations in surface conditions. Beyond accurate dynamic prediction, the hierarchical structure enables modular real-time implementation, supporting controller design, trajectory planning, and fault detection. Overall, the results demonstrate that the Gibbs–Appell-based hierarchical modeling framework combines analytical rigor with computational efficiency, providing a robust foundation for control and optimization in advanced wheeled-legged robotic manipulators.

With the rapid development of artificial intelligence technology, robotics, as its core branch, has attracted extensive attention from researchers. This paper designs and develops a robotic arm learning system based on multi-source sensor information fusion, which investigates the autonomous learning capability of robotic arms by closely integrating deep reinforcement learning (DRL) as the core framework for skill acquisition. By incorporating imitation learning as a source of expert prior and leveraging DRL’s intrinsic ability for policy optimization through environmental exploration, the proposed system achieves both rapid learning and robust generalization. Specifically, we introduce the gradient penalty mechanism from Wasserstein generative adversarial networks (WGANs), a technique that improves the stability of adversarial training by penalizing gradients that deviate from a specified norm. This mechanism is incorporated into the soft actor-critic (SAC) algorithm, a widely used off-policy DRL method known for its sample efficiency and robust performance in continuous control tasks. The resulting SAC-GP (SAC-gradient penalty) algorithm benefits from both SAC’s stable policy learning and WGAN’s improved training regularization, leading to superior convergence speed and system stability. Furthermore, this paper proposes a hybrid learning framework by combining generative adversarial imitation learning (GAIL) with SAC-GP, enabling the agent to benefit from both demonstration-based policy initialization and continuous self-improvement via reinforcement learning. Finally, a door-opening experiment is designed to verify the learning and execution capabilities of the system in both virtual and real environments. Experimental results demonstrate that the proposed learning system possesses excellent learning and motion execution abilities in practical applications. This achievement not only provides new insights for research in robot learning but also lays a solid foundation for the future development of robotic technology.

This paper proposes an indoor LiDAR-visual fusion framework based on dynamic elimination. The framework effectively suppresses transient dynamic interferences. It integrates multi-view geometric constraints with semantic priors, which is achieved through a prior model-guided dynamic feature elimination strategy. Moreover, an adaptive gamma correction (AGC) algorithm enhances the image quality under uneven illumination. Meanwhile, an improved quadtree algorithm homogenizes feature point distribution. These two measures achieve more robust ORB feature extraction while ensuring image quality. For map fusion, we focus on combining the processed visual map with the LiDAR map. The visual map, with dynamic feature points eliminated, is first aligned with the LiDAR map via Harris corner detection. We then integrate them using Bayesian inference-based grid information fusion to generate the final integrated map. Extensive evaluations were carried out on six dynamic sequence datasets, and practical dynamic corridor mapping experiments were also conducted. These evaluations and experiments demonstrate the superiority of the proposed system.

Constant-force mechanisms (CFMs) are attractive for mechanical energy storage owing to their distinctive force–displacement characteristics, particularly under conditions with limited external load capacity and restricted space. However, conventional CFMs often suffer from short constant-force strokes and inefficient space utilization, which hinder their broader application. To address these limitations, this study exploits the buckling of compliant beams and increases the structural degrees of freedom by adopting a less constrained configuration, which extends the constant-force stroke and space utilization while reducing the required external load, thus improving energy storage efficiency for the same stored elastic energy. A novel catapult was developed through NSGA-II multi-objective optimization, achieving a high energy-to-cost ratio and an extended constant-force stroke. This work presents an effective design approach for motion mechanisms that demand high energy-storage efficiency and high-power output.