Instantaneous trajectory planning is crucial for the autonomous navigation of mobile robots. Among existing methods, the Dynamic Window Approach (DWA) serves as a widely adopted benchmark. However, when applied to omnidirectional robots with high aspect ratios, conventional DWA suffers from limitations such as kinematic mismatches, overly conservative geometric approximations, and non-adaptive decision-making. To tackle these challenges, this paper first extends the conventional 2D velocity space to generalized planar velocity space to fully utilize the platform’s kinematics. Second, a precise rectangular footprint model is developed to replace the overly conservative circular envelope. Finally, a lightweight, real-time risk-based mechanism is developed for adaptive weight tuning. Extensive comparative simulations in various typical scenarios validate the significant advantages of the proposed improved DWA. The results show that in scenarios with narrow passages, the precise geometric model shortens the path length by 49.0

Humanoid robots operating in human-centered environments (e.g., homes, hospitals, and offices) must mitigate foot–ground impact transients, as impact-induced vibration and noise degrade user experience and repeated impacts accelerate hardware wear. However, existing low-noise locomotion training often relies on kinematic proxy objectives or fragile force sensors, and footwear-induced changes in contact dynamics introduce distribution shifts that hinder policy generalization.We present QuietWalk, a physics-informed reinforcement learning framework for ground-reaction-force-aware humanoid locomotion under diverse footwear conditions. QuietWalk employs an inverse-dynamics-constrained physics-informed neural network (PINN) to estimate per-foot vertical ground reaction forces (GRFs) from proprioceptive signals, and integrates the frozen predictor into the RL training loop to penalize predicted impact forces without requiring force sensors at deployment.On a held-out real-robot dataset, enforcing inverse-dynamics consistency reduces vertical GRF prediction errors by 82

Underwater vectored thrusters based on a parallel manipulator have shown a potential to improve the maneuverability of underwater equipment. Owing to the hazardous and remote working environment, it is necessary to promote the fault tolerance of underwater vectored thrusters. One effective method is to deploy redundant actuators. Under the prerequisite of achieving vectored thrust, the structure and the number of redundant actuators should be compact and minimum, respectively. Based on these considerations, the symmetrical tripod parallel manipulator with high stiffness is designed to vectorize the thrust and endow the thruster with fault-tolerant capability. This article delves into the fault-tolerant characteristics of the manipulator and presents the corresponding control methods. Firstly, to explicate the fault tolerance of the presented manipulator, the constraint screw theory is utilized to construct the mobility analysis procedure. The results demonstrate that the manipulator can naturally deal with arbitrary one actuator stuck. Thereafter, the fault-tolerant kinematics model of the manipulator is formulated. Furthermore, one fault-tolerant controller based on the constructed kinematics model is designed to cope with the stuck fault and inaccurate extension fault, which maximizes the structural advantages of the manipulator. Finally, experiments validate the proposed fault-tolerance analysis and the control method, respectively.

The hydrogel ionic diode is regarded as a promising self-powered sensor, capable of harvesting energy from low-frequency stimuli human motions and converting it into electrical signals. However, the sensitivity of the reported conventional bilayer hydrogel ionic diodes are relatively low, due to the single heterojunction interface and high interface resistance, making it challenging to meet the demands of high-precision sensing. Here, a universal method for fabricating dual-gradient hydrogel ionic diodes without bilayer structure through the induction of anionic and cationic polymer gradient distribution via a direct current electric field is developed. Due to the dual-gradient distribution, numerous heterogeneous microstructures (i.e., microdiodes) with low interface resistance are formed in the bulk phase of hydrogel, and these series-connected microdiodes demonstrate a significantly increase in open circuit voltage in response to mechanical pressure. The dual-gradient hydrogel ionic diode exhibits ultra-high sensitivity (1247.3 mV/MPa) and ultralow detection limit (0.8 Pa), enabling the smart prosthetic hand to non-destructive grasp ultrasoft tofu. This work is expected to pave the way for novel high-precision self-powered sensors in intelligent wearable electronics.

Most bioinspired cable-driven continuum robots (CDCRs) usually employ a flexible backbone to realize the continuous deflection. For the CDCR to merely produce bending motions, its flexible backbone has to be designed with low bending stiffness but high tensile and torsion stiffness. In this article, a pattern-based design approach is employed for the flexible backbone, which adopts rectangle-shaped patterns inspired by elastic couplings. As it is rather difficult to derive accurate analytical stiffness models for such a pattern-based backbone structure with large nonlinear deflections, a novel data-driven stiffness modeling approach is proposed. The Gaussian process regression method is employed to train the stiffness model with respect to structure parameters of the backbone, while the dataset is generated through a commercial finite element analysis software package. To narrow the distribution of the training data and make the predicated stiffness values always positive, the natural logarithm transformation is utilized for data preprocessing, which significantly increases the accuracy of prediction results. The average errors of the bending, tensile, and torsion stiffness between simulation results and predicted results converge to 1.88%, 2.33%, and 2.11%, respectively. The particle swarm optimization algorithm is employed for the structure parameter optimization based on the data-driven stiffness model. The stiffness errors of the optimized flexible backbone between simulation results and experimental results are 5.19%, 19.09%, and 5.38%, respectively. Experimental results show that the average position repeatability and orientation repeatability of a CDCR are 0.8822 mm and 0.0046 rad and the CDCR can carry the 500 g payload.

This paper investigates a novel omnidirectional mobile robot (OMR) equipped with four decoupled active casters (DACs). A real-time calculation model for position contour error based on an orthogonal global task coordinate frame is established for OMR trajectory tracking. To address the non-monotonicity of the parametric equations of the trajectory along the x and y directions within each time interval, the model is extended to derive the Jacobian matrix for the transformation from the contour task space to the Cartesian space when inverse functions exist for x and y separately. This approach accommodates both the practical scenarios where the robot is stationary in either the x or y direction during trajectory tracking and when both directions are in motion simultaneously. The positive direction of motion for the vehicle body and casters is defined, and the orthogonal decomposition method is applied to analyze the motion constraints of the casters, leading to the derivation of the caster kinematic model. This results in a kinematic model based on the contour task space. Combined with a model predictive control algorithm, experimental verification demonstrates its capability to achieve precise trajectory tracking.

This paper proposes an innovative virtual chain-based kinematic calibration for the 4PPa-2PaR parallel manipulators with subchain architectures. Conventional calibration methods for such architectures suffer from inherent limitations due to coupled parameter constraints and restricted solution spaces caused by joint displacement and structural parameter dependencies. The presented methodology introduces three fundamental advancements: (1) a novel parameter assignment strategy enabling independent joint/link parameter definition across different kinematic chains, (2) systematic transformation of constrained optimization into an unconstrained one, and (3) significant expansion of error parameter solution space through virtual chain modeling. Comparative experiment on the physical prototype demonstrate improvements in both orientation and position accuracy compared to existing methods.

In recent years, three-degree-of-freedom (3-DOF) parallel robots have attracted significant attention within underwater vector thruster. Nevertheless, existing research exhibits certain shortcomings, posing challenges in meeting both the workspace and stiffness requirements concurrently. This paper addresses these issues through the design of a 3-RPUR ( $P$ is the prismatic joint, R is the revolute joint, U is the universal joint) underwater parallel robot. The design incorporates U+R pairs to replace spherical pair, enlarging the workspace of the moving platform. Additionally, a redundant static platform serves as auxiliary support to ensure stiffness. This paper begins with an analysis of the inverse kinematics of the parallel robot, deriving its solution. Subsequently, the velocity mapping relationship is examined. The mechanical model of the parallel robot is then integrated into the MATLAB/SIMULINK environment, combining the inverse kinematics solution. A controller is introduced to each moving branch chain to regulate the error, facilitating precise motion control. Simulation results demonstrate that each joint of the parallel robot effectively follows the reference trajectory, with a maximum error of less than 0.006mm. These findings validate the correctness of the mechanism design and the closed-loop control system.

Flexible capacitive stretchable sensors have a promising prospect in humanoid and soft robots. However, the flexible sensors are difficult to be extensively deployed due to their low accuracy caused by intrinsic nonlinearity. The nonlinearity is mainly from the hysteresis of the material of the sensors. In this paper, a piecewise power-law model is proposed to improve the perception accuracy of a flexible capacitive stretchable sensor. The kernel of the model is the hysteretic operator generated from the piecewise power-law function. Benefiting from the design, the proposed model can better describe the asymmetric dynamic behavior of the flexible sensor than some hysteresis models. Its capability to characterize hysteresis in the flexible sensor is demonstrated by comparing the predicted data of the model and the real captured data from the flexible sensor. Then the proposed model is used to compensate for the hysteresis of the sensor to promote its perception accuracy. The accuracy performance of the proposed method is also compared with the other three different methods. The flexible sensor is deployed in a homemade humanoid knee and a tensile test platform to be tested involving the bending motion and the linear motion, respectively. The experimental results demonstrate that the maximum absolute error of the proposed method is significantly smaller than other methods.

Rapid and accurate detection of the power battery pole area before welding is the prerequisite for accurately locating the welding starting point, and its performance determines the assembly efficiency and quality of the battery module. In view of the complex welding environment, low color contrast, and small area ratio, an improved model based on YOLOX is proposed. A multi-scale mixed attention module is introduced after the backbone feature to infer attention from different scales and enhance the key features of the target. A complex bidirectional fusion strategy that is conducive to small target detection is introduced at the neck of the model. The feature gradient flow is enriched through deep separable convolutions of multiple kernel sizes, and the original features are effectively utilized with the help of residual structures and multi-scale information is integrated. Experiments have shown that the optimized model is more stable to various environmental interferences while maintaining lightweight. The detection accuracy of the model is improved by 4.13% compared with the baseline model, the parameters are 6.27M, and the detection speed is 93 FPS. The overall performance is better than other models, providing an effective solution to the problem of welding initial point detection in power battery assembly.

Compound Twisted and Coiled Actuators (CTCAs) are promising candidates for artificial muscles due to their outstanding competences in producing large output forces and long strokes. However, as their thermal actuation performance depends on not only the driving temperature, but also the spandex deformation caused by the payload, it is rather difficult to obtain accurate actuation models for the conventional CTCAs and thus seriously restricts their control performance and application development. To tackle such difficulties, a CTCA with a novel strategic fabrication method is proposed in this work. Motivated by the kinetostatic performance of a stiffening spring with a high preload, the fiber draw ratio of the CTCA is significantly increased through pre-stretching the fiber during the fabrication process, which makes the thermal actuation performance of the CTCA insensitive to the external payload. The effectiveness of the proposed payload-insensitive characteristics of the CTCA is validated through experimental results, which shows that the CTCA has almost the same untwisting strain-temperature curves under different payloads. Consequently, a simplified yet accurate actuation model is obtained such that the displacement of the CTCA is mainly determined by the driving temperature within a meaningful range of payloads. Experiments are conducted to evaluate the accuracy of the actuation model and the model error is less than 7.6%. Such a simplified actuation model is implemented for the pose control of a 2-DOF CTCA-driven continuum robot joint module, in which the average steady-state error of the bending angle is less than 1.0∘.

Aiming at problems of the limited accuracy of the model and poor control precision caused by the complex deformation of Cable-Driven Continuum Robot(CDCR), a shape sensing and feedback control approach for CDCR is proposed based on the elastic magnetoelectric strain sensor. The kinematic model of CDCR was established based on the product of the exponential (POE) formula. Based on the sensor's physical characteristics, the robot's shape-sensing model was proposed and Qualisys Track System was used for calibration. A module prototype was built to verify the effect of the perceptual feedback control algorithm. The experiment proved that the flexible perception method used in this paper is universal and accurate, and provides a valuable framework for real-time sensing control.

Aiming to address the issues of moving speed and overall machining efficiency of a robot arm in path planning for laser flying welding, a method is proposed. This method involves using the non-central point of the trajectory to be welded as the welding position point and is further extended to the generalized traveling salesman problem. Through the analysis of the optimization model, the two-chromosome genetic algorithm is utilized to solve the path planning. Based on this, path intersection elimination and neighbor node replacement are carried out for every iteration in order to enhance the quality of the best solution. Finally, the path planning based on the general genetic algorithm for central welding position points, and the path planning based on the two-chromosome genetic algorithm and the improved two-chromosome genetic algorithm for non-central welding position points are simulated. The results show that the improved two-chromosome genetic algorithm can calculate the optimal solution of higher quality and a more reasonable machining path for non-central point welding positions.

The unit dual quaternion (UDQ)-based product-of-exponential (POE) formula has achieved efficient kinematic calibration for serial manipulators. However, due to the presence of unknown passive joint displacements, it is difficult to directly establish explicit forward kinematic models for parallel manipulators (PMs). This forms a barrier to subsequent error modeling and compensation. This work establishes a novel UDQ-based forward kinematic model for a PM by utilizing constraints on the identical pose of the moving platform across all its chains. Furthermore, the adjoint transformation of UDQ's twist is derived for PM's error modeling. Notably, an index matrix is introduced to achieve a unified representation of active or passive joint displacement. Thereby, this UDQ-based kinematic error modeling method is applicable to general PMs. In addition, an error compensation method is proposed for a PM using the UDQ-based local POE formula, which incorporates the developed forward kinematic model to adjust active joint displacements. The proposed method offers significant runtime savings compared to the traditional homogeneous-transformation-matrix-based POE formula due to the compact data structure and reduced arithmetic operations.

Industrial robots and collaborative robots are widely employed in industry and are progressively being utilized to assist individuals in their daily routines. To improve their absolute accuracy, self-calibration methods using portable local measurement devices are cost-effective solutions. However, compared with the conventional external calibration methods, self-calibration methods employing two configurations as a calibration sample introduce more non-kinematic errors to the robot. Therefore, noise reduction is significantly necessary in self-calibration. A novel Piecewise-weighted Random Sample Consensus (RANSAC) method is proposed in this paper. Instead of choosing an optimal model with all inliers, the proposed method employs a general weight considering both the sample and hypothesis model qualities to generate a new model with Weighted Least Square (WLS) method. Besides, the proposed method turns the target of finding an uncontaminated set of inliers into the training of the proper weight coefficient for WLS, which not only improves the accuracy but also greatly enhances the speed. The self-calibration experiment on a 6 degree-of-freedom(DOF) robot CR10 shows that the accuracy of the proposed Piecewise-weighted RANSAC method makes a 27.7% accuracy improvement from that employing Least Square method, a 20.0% accuracy improvement from that employing standard RANSAC method, and a 5.5% accuracy improvement from that employing LO-RANSAC method. Besides, the proposed method is also over 10.9 times faster than the standard RANSAC method and 18.6 times faster than the LO-RANSAC method.

Rigid robots have found wide-ranging applications in manufacturing automation, owing to their high loading capacity, high speed, and high precision. Nevertheless, these robots typically feature joint-based drive mechanisms, possessing limited degrees of freedom (DOF), bulky structures, and low manipulability in confined spaces. In contrast, continuum robots, drawing inspiration from biological structures, exhibit characteristics such as high compliance, lightweight designs, and high adaptability to various environments. Among them, cable-driven continuum robots (CDCRs) driven by multiple cables offer advantages like higher dynamic response compared to pneumatic systems and increased working space and higher loading capacity compared to shape memory alloy (SMA) drives. However, CDCRs also exhibit some shortcomings, including complex motion, drive redundancy, challenging modeling, and control difficulties. This study presents a comprehensive analysis and summary of CDCR research progress across four key dimensions: configuration design, kinematics and dynamics modeling, motion planning, and motion control. The objective of this study is to identify common challenges, propose solutions, and unlock the full potential of CDCRs for a broader range of applications.

Many studies on the object detection emphasizes the accuracy of the algorithms themselves, while the requirement of real-time processing can be addressed by the usage of "you only look once" (YOLO) model. However, the reliably of machine vision is still a problem since some practical issues are not addressed properly, such as variation of light intensity, reflection of light on the surface and interference of shooting background. In this paper, we address above problems by developing a vision system with YOLO algorithm for object detection, segmentation and localization. A segmentation approach is adopted on the model outputs to extract the object to be detected from the background, under the premise of enhancing the adaptability of the YOLO model to environmental changes. Thus, the influence of background and light-sensitive factors on localization is removed even in extreme lighting conditions. An experimental platform is built based on a pair of low-cost cameras, which verifies the effectiveness of proposed method.

The accuracy of the kinematic model is affected by the error of geometric parameters caused by the machining and assembly of the robot, causing decline of the accuracy of the motion control and the odometry. In order to improve the motion accuracy of the omnidirectional mobile robot（OMR）, a step-by-step calibration method is proposed for an omnidirectional mobile robot based on decoupled powered caster wheels（DPCW）.This method simplifies the kinematic matrix by limiting the input of motion in joint space. Then the least squares method is used to obtain actual values of kinematic parameters. As a result, the precision of the kinematic model is improved. The experimental platform for the OMR based on DPCW is built, and the calibration algorithm is verified by simulation and experiment. The results show that the accuracies of both velocity control and odometry are significantly improved in three degrees of freedom in the plane, which proves the effectiveness of the calibration algorithm.

In recent years, intelligent omnidirectional robots for indoor environment have received wide attention. To improve the accuracy of indoor localization of intelligent omnidirectional robots, this paper proposes a fusion localization method based on graph optimization for UWB(Ultra-wideband) and the odometry of robot. The proposed method first uses the distance between the anchor and the tag measured by UWB to perform least-squares solving to obtain the initial localization value. Then the graph optimization model is constructed based on the UWB range information and odometry displacement information as UWB and odometry constraints, respectively. Then the modified Gaussian Newton method is used to solve all robot positions. The experimental results is carried out, the experiment data show that the localization error is reduced by 30% compared to using only UWB for localization. Compare to the odometry track projection only, the presented method have no significant cumulative error. In addition, the experiment show that the present method has a good robust in positioning predict.