New structured spectral gradient methods for nonlinear least squares with application in robotic motion control problems

Hybrid of representation learning and reinforcement learning for dynamic and complex robotic motion planning

Medical robots capable of autonomously performing interventional and surgical procedures are becoming a reality. Autonomous medical robots promise enhanced accuracy, reduced medical errors, improved accessibility to specialized care, and lower healthcare costs through efficient, minimally invasive procedures. This review examines motion planning as a fundamental building block enabling autonomous medical robots. Motion planning aims to compute high-quality and safe motions for robotic instruments to accomplish interventional and surgical procedures while considering anatomical constraints and physical limitations. We categorize medical robot motion planning into navigation planning (maneuvering instruments to targets via intratissue or endoluminal paths) and manipulation planning (tissue interaction through contact or contact-free approaches). We frame motion planning as a type of AI guidance that can enable eyes-on/hands-off automation. We review state-of-the-art methods in navigation and manipulation planning for medical robots, discuss challenges to clinical adoption, and explore future opportunities for autonomous medical robots.

As human-robot systems and autonomous robots become increasingly prevalent, the need for task-oriented datasets to study human behaviors in shared spaces has grown significantly. We present a novel dataset focusing on sequential human assembly and disassembly motions in human-robot coexisting environments. It contains over 10,000 samples recorded from multi-view camera setups, each comprising synchronized RGB videos and 2D and 3D human skeletons. Data were collected from 33 participants with diverse physical characteristics and behavior preferences. This dataset highlights practical challenges such as partial occlusions, similar repetitive motions, and varying human behaviors, which are often overlooked in existing datasets and research. Technical validation using benchmarking with state-of-the-art deep learning models reveals significant potential in using this dataset for practical applications. To support diverse research applications, this dataset provides raw and processed data with detailed annotations, including precise timestamps, procedure annotations, and Python codes for reproducibility. It aims to advance research in human motion prediction, task-oriented robotic sequential decision-making, motion and task planning of autonomous robots, and human-robot collaborative policies.

Abstract A concept for a 2-degree-of-freedom (DOF) mobile robot is proposed, and its design and experimental study are conducted. The robot achieves linear motion along the x-axis and rotational motion along the z-axis using only two serial inertial impact devices (SIID) vibrators driven by inertial impact forces. Flexible hinge mechanisms of the 2-DOF piezoelectric robot are simulated using ANSYS Workbench by varying structural parameters. Dynamic equations are established, and a dynamic simulation model is built using MATLAB/Simulink to output performance simulations. A prototype is produced, and the drive waveform, voltage amplitude, and frequency are adjusted in experiments to study the linear movement speed, rotational movement speed, and displacement accuracy of the linear and rotational movements of the piezoelectric robot. Its 2-DOF motion performance was verified, and the results are compared with the dynamic simulation results to analyze the rationality of the model. Based on a more compact and sophisticated structural design, this concept enables the 2-DOF motion of a piezoelectric robot, providing a new technical path for the design of piezoelectric-driven multi-DOF robots and verifying the feasibility and effectiveness of the inertial configuration in terms of motion accuracy and mechanism simplification. Experimental results show that the device maintains stable performance under drive voltages ranging from 10 to 140 Vp-p. Under drive conditions of 10 V and 1 Hz, the maximum linear movement accuracy of the drive device is 0.26 μm. At 100 V and within the test frequency range, the maximum movement speed is 16.223 mm/s. Under 9 Hz conditions, the maximum operating speed is 1.06 mm/s, demonstrating excellent motion speed performance. Under driving conditions of 100 V and 11 Hz, the maximum rotational movement speed of the drive device is 11.73 μrad/s.

Coordination algorithms are required to minimise congestion when every robot in a robotic swarm has a common target area to visit. Some of these algorithms use artificial potential fields to enable path planning to become distributed and local. An efficiency measure for comparing them is the time to complete a task in relation to the number of individuals in the swarm. To compare distinct solutions as the swarm grows, experiments with different numbers of robots must be simulated to form a plot of the function of the task completion time versus the number of robots or other parameters. Nevertheless, plotting it for many robots through simulation is time-consuming. Additionally, the inference of a global swarm behaviour as the task completion time from the local individual robot motion controller based on potential fields and other dynamical variables is intractable and requires experimental analysis. Based on that, equations are presented and compared with simulation data for estimating the expected task completion time of state-of-the-art algorithms, robots using only attractive and repulsive force fields and mixed teams for the common target area problem in robotic swarms with not only the number of robots as input but also environment- and algorithm-related global variables, such as the size of the common target area and the working area, average speed and average distance between the robots. This paper is a fundamental first step to start a discussion on how better approximations can be achieved and which mathematical theories about local-to-global analysis are better suited to this problem.

With the rapid advancements in automation and soft robotics, the exploration of mobile robots for applications in complex environments is increasingly deepening. This paper presents a novel dual soft arm mobile robot (DSAMR), whose design integrates advanced soft robotics technologies with biomimetic design inspired by human arms, aiming to achieve efficient obstacle avoidance and object manipulation. The robot employs Bubble Artificial Muscle Arms (BAMAs) for locomotion, enabling flexible movements such as forward, backward, and turning motions; it also integrates TacTip (tactile fingertip), a biomimetic sensor that mimics the tactile structure of human fingertips, to achieve real-time perception. BAMAs and TacTip collaborate to achieve the integration of perception and operation like a human hand, enabling the system to accurately detect obstacles and manipulate objects, including typical delicate items such as a paper towel roll and a pen, with the maximum capacity to grasp objects weighing up to 148.8 g. Experiments have demonstrated that a single inflation-deflation cycle of the BAMAs enables the DSAMR to turn right by 35.5° and left by 28.3°, and successfully allows the DSAMR to recognize obstacles and turn to avoid them. The experimental results indicate that the DSAMR can operate effectively in dynamic environments, with excellent stability and obstacle avoidance capabilities. This paper discusses the design details of BAMA actuators, steering engines, and TacTip, as well as their integration into the robot's motion and sensing systems. The findings emphasize the DSAMR's potential applications in industrial automation, particularly in the context of Industry 4.0. Finally, the study summarizes optimization strategies and future improvement directions to enhance the robot's operational efficiency, including onboard power integration and advanced obstacle recognition technologies.

A Planning and Control Scheme for the Run-and-Jump Motion of a Wheeled Bipedal Robot Considering Dynamic Constraints

A system for docking robotic wheelchair to partially visible table of unknown pose using human input and robotic wheelchair motion

Understanding the effects of humanlike robot motions on unfocused human–robot interaction

To quantify the contributions of specific ligaments to overall joint biomechanics, the principle of superposition has been used for nearly 30 years. This principle relies on a robotic test system to move a biological joint to the same pose before and after transecting a ligament. The difference in joint forces before and after transecting the ligament is assumed to be the transected ligament's tension. However, the robotic test system's ability to accurately return the joint to the commanded pose is dependent on the compliance of the system's various components, which is often neglected. An alternative approach to superposition testing is to use additional sensors attached directly to the joint to inform robot motion. Accordingly, there are two objectives: (1) describe a testing methodology with 6DOF position sensors to correct for system compliance and (2) demonstrate the effectiveness of this methodology to reduce uncertainty of in situ forces determined using superposition. A Sensor Fusion algorithm fuses 6DOF position sensors with robot pose measurements to compensate for system compliance. For the equipment, loading condition, and surrogate knee joint used in this study, the Traditional control method underestimated ligament tension by 23% while the Sensor Fusion control method brought that error down to 3%. Thus, this Sensor Fusion algorithm is a promising approach to minimize errors in superposition testing caused by compliance in a robotic test system.

Automated Fiber Placement (AFP) significantly improves production rates by minimizing interruptions and enhancing consistency, while also reducing part count, lead time, and production costs. Compared to traditional hand layup (HLU), AFP offers increased material efficiency. However, it also produces scrap due to leftover material in the creel and encounters difficulties when laying up highly contoured or small, complex parts. Fiber steering around intricate geometries often results in defects such as puckers (wrinkles on the inner radius of the tow) and overlaps. To address these limitations, Fiber Patch Placement (FPP)—a hybrid of additive manufacturing and fiber placement—is introduced. FPP enables the production of geometrically complex composites and curvilinear reinforcements by depositing small prepreg patches using a multi-robotic system. This approach offers greater flexibility in fiber deposition, allowing for the fabrication of intricate shapes at higher production rates than both AFP and HLU. First, the continuous-fiber part design is imported into patch design software to define the initial patch placement architecture, aligning reinforcement patches with expected load paths. A structural analysis is then performed, followed by iterative optimization to enhance performance and material efficiency. The optimized design is subsequently transferred to specialized software that generates the corresponding toolpaths and numerical control (NC) codes for robotic motion. Offline programming and simulation are used to virtually validate the layup process before physical production begins. By leveraging advanced robotics and digital manufacturing tools, FPP bridges the gap in producing complex composite geometries. This study outlines methodologies for the design and optimized manufacturing of FPP parts, including standard practices for patch modeling, integration of FPP-specific properties into finite element models, and established structural analysis workflows. Additionally, it details the performance of FPP composites through static and fatigue testing at the coupon level. Flat panels with varying patch overlap lengths were tested to evaluate strength reductions caused by fiber discontinuities and to support design optimization strategies. Building on prior findings from coupon-level tests and simulations, the validation was extended to a part-scale cylindrical specimen with a variable-radius compression profile. In both cases, test results closely aligned with analytical predictions, demonstrating the robustness of proposed design and analysis tools in supporting complex FPP design.

Challenges: Strong impact operation robots—motion analysis, transient measurement, and vibration suppression strategy

With the continuous advancement of industrial automation, robotic arms have been widely adopted across various fields, making performance optimization a key research focus. As a critical component for enhancing robotic arm performance, kinematic analysis plays a vital role in achieving precise control. This study utilizes the MatlabRobotics toolbox to conduct kinematic analysis on the SNR3-C30 robotic arm. By establishing a mathematical model of the robotic arm and solving forward/reverse kinematic equations, we implemented a fifth-order polynomial interpolation algorithm for trajectory planning in the joint space. The research demonstrates that the established model accurately describes the robotic arm's motion characteristics, while the forward/reverse kinematic solution method proves effective and reliable. These findings provide crucial theoretical foundations for optimizing design and developing control strategies for the SNR3-C30 robotic arm, significantly improving operational precision and efficiency in real-world applications. This work holds great significance for advancing robotic arm technology development.

This paper presents the design and performance of Table ASSIST-EW, a portable adaptable user-friendly cable-driven device that can be used on a table to support elbow and wrist exercises. This device is intended for older adults who experience arm weakness due to aging. Table ASSIST-EW has been developed based on results from testing and practical insights from biomechanics and robotics to address challenges in human–robot interaction that limit the use of assistive technologies. Table ASSIST-EW is designed to assist natural arm movements during motion exercise and rehabilitation, making the motion assistance easy and easily engaged for users. The design process is explained starting from identifying user needs up to the creation of a prototype. A key feature of Table ASSIST-EW is its cable-driven actuation system. The design is inspired by a previous device, L-CADEL, which went through several design revisions. The lessons learned from L-CADEL’s development and test experiences suggested design solutions for Table ASSIST-EW’s structure, function, and use. This paper discusses the background, design requirements, system development, and performance evaluation. The results show that the Table ASSIST-EW device meets important goals in usability and functionality, making it a promising solution for robotic rehabilitation and motion exercise for the elderly.

This study explores the use of construction robots with collaborative path planning and coordination in complex building construction tasks. Current construction processes involving robots are often fragmented due to their single-task focus, with limited research focused on employing multiple construction robots to collaboratively perform tasks. To address such a challenge, this research proposes an improved A* algorithm for global path planning and obstacle avoidance, combined with the development of a BIM-based grid map of the construction site. The leader–follower method is utilized to guide the robot group in maintaining an optimal formation, ensuring smooth collaboration during construction. The methodology includes formalizing building construction site environments into BIM-based grid maps, path planning, and obstacle avoidance, which allows robot groups to autonomously navigate and complete specific tasks such as concrete, masonry, and decoration construction. The results of this study show that the proposed approach achieves significant reductions in pathlength and operational time of approximately 9% and 10%, respectively, while maintaining safety and efficiency compared with traditional manual methods. This research demonstrates the potential of collaborative construction robot groups to enhance productivity, reduce labor costs, and provide a scalable solution for the intelligent transformation of the construction industry; extends the classical A* algorithm by incorporating obstacle density into the heuristic function; and proposes a new node simplification strategy, contributing to the literature on robot motion planning in semi-structured environments.

Clustering analysis of long-term robot motion patterns generated by cat motion trained gMLP

Abstract Legged robots face significant challenges in navigating complex terrains. The Virtual Model Control (VMC) method, which utilizes virtual forces to govern robot motion, is a promising approach. However, traditional VMC suffers from computational complexity. While the Decoupled Virtual Model Control (DVMC) mitigates this issue to some extent, existing research on DVMC has primarily focused on quadruped robots, with no prior applications for hexapod systems.To address this gap, this paper proposes a DVMC framework specifically designed for hexapod robots, accompanied by a complete theoretical derivation.The paper first derives the mathematical equations required for the hexapod robot to use DVMC, then deduces the complete mathematical model of DVMC for the hexapod robot. Secondly, a dynamics-based feedforward compensation strategy is adopted to address the trajectory errors of the swing phase, and an optimized foot-end trajectory is proposed to adapt to complex terrain, along with a control strategy for omnidirectional movement of the hexapod robot. Finally, multiple simulations of the hexapod robot based on DVMC are conducted in the Webots-Matlab co-simulation.The simulation results show that the hexapod robot based on DVMC has good passability on uneven surfaces such as slopes and rough roads, and the effectiveness of the omnidirectional movement strategy for the hexapod robot is also verified, providing a reference for subsequent research on the motion control of hexapod robots.

Abstract Robot motion control is challenging due to the ever- demanding requirements on precision and agility under highly nonlinear dynamics, large uncertainties, and unknown disturbance. Sliding mode control (SMC) is well-known for its good robustness, but suffers from chattering. Thus, many chattering-reduced SMCs were explored at a price of compromised tracking performance. However, they are either not accurate enough or too complicated. To enhance tracking performance of robot manipulators, this paper proposes a modified SMC that establishes the sliding surface in the joint state space of the plant and the controller to filter the switching term and achieve high tracking accuracy. Furthermore, by analyzing the equivalent systems in the sliding mode of various SMCs, we point out that dynamic SMCs contain a feedback loop around the input gain matrix uncertainty in the sliding mode. Therefore, closed-loop stability of the whole system requires not only convergence of the sliding variable but stability of the equivalent system in the sliding mode. Then experimental comparisons among the first-order SMC with sliding layers (FOSMC), two types of second-order SMC (SOSMC), and the proposed SMC on a 6-axis industrial robot show that the proposed one effectively reduces chattering and outperforms the others.

Hydraulic actuated quadruped robot has strong load capacity, good flexibility, and strong adaptability to complex environments. Pointing at the multi coupling and multi variable characteristics of hydraulic quadruped robot, this paper proposes a decomposed trajectory tracking control strategy based on model prediction for hydraulic quadruped robot. The tracking model is derived by the structure of the hydraulic quadruped robot. The inequality constraints of the quadruped robot motion are built. And the trajectory tracking control problem of the robot is transformed into a quadratic programing problem. The error model of the robot is built. Combining the minimization goals of robot motion speed and acceleration error, the stability and continuity constraints for robot motion are planned. The decomposed trajectory tracking controller with trajectory constraints is designed. The performance of proposed control method is verified by simulation and prototype experiment. The simulation and prototype comparative experiments of classical control strategy and the proposed control strategy are conducted on the hydraulic robot. The results show that compared with the traditional method, the motion trajectory error of the hydraulic robot is relatively small by the proposed optimal trajectory tracking control strategy. The rolling angle accuracy is ±0.066 rad, and the pitching angle accuracy is −0.073 to 0.044 rad. The effectiveness of the proposed control algorithm is verified by the simulation and experimental results. The accuracy of the hydraulic robot model in the control algorithm is improved, the impact during hydraulic robot motion is reduced, and the service life of the robot was increased, as well as the stability of robot motion is enhanced.