This paper designed a continuum robot and its control system based on ROS. Firstly, the structure of the continuum robot is described, and the relationship between the posture of the continuum robot and the length of the drive rope is obtained by using the constant curvature model. Then, the continuous robot control system based on ROS is described, including master hand and slave hand, and a master-slave control strategy is proposed. In addition, the human-computer interface is developed based on QT. Finally, the control experiment is carried out and the control precision is analyzed, and the effectiveness of the designed continuum robot control system is verified.

This paper presents a self-adaptive software for efficiently generating personalized lower-limb rehabilitation mechanisms, which based on patients’ parameters such as height, thigh length, shank length and gender. The proposed system utilizes clustering method and the GA-SVM classifier to predict the optimal standard gait trajectory for patients, combined with a GA-BFGS hybrid optimization algorithm to determine the geometric parameters of a 1-degree-of-freedom (DOF) six-bar mechanisms which can best similarize the target trajectory. The innovation of this paper is in its use of clustering method to map a vast amount of disordered user trajectories to a limited set of standardized trajectories, thereby enabling user-to-institution matching. Featuring an intuitive interface, the software integrates trajectory recommendation, mechanism synthesis and motion visualization into a unified workflow, thereby enabling the generation of patient-specific rehabilitation mechanisms for diverse anthropometric characteristics. Experimental validation demonstrates that the synthesized mechanisms achieve an average trajectory deviation of 8.2 mm, confirming the software’s clinical applicability in personalized rehabilitation.

Abstract Automated handling of flexible and breathable fabric samples remains a major challenge in intelligent garment manufacturing. To address this issue, a non-contact vortex gripper was developed and optimized for stable fabric grasping. A steady-state mathematical model was established to describe the relationship among suction force, inlet flow rate, and gap height. Computational fluid dynamics simulations were conducted to investigate the effects of key structural parameters on the internal flow field and pressure distribution. Based on the simulation results, the influences of swirl chamber inclination angle, upper chamber height ratio, and flow deflector diameter on suction performance were analyzed. An orthogonal experimental design was further employed to determine the optimal structural configuration. In addition, grasping experiments were performed on nine fabric samples with different physical properties to evaluate the applicability of the optimized gripper. The results show that suction force increases with inlet flow rate and exhibits a non-monotonic relationship with gap height. The optimal structural parameters were identified as a swirl chamber inclination angle of 60°, an upper chamber height ratio of 0.500, and a flow deflector diameter of 12 mm. Experimental results agree well with theoretical and simulation predictions. Furthermore, fabric air permeability was found to be the primary factor affecting grasping performance, whereas fabric thickness and grammage had limited influence. The proposed vortex gripper provides an effective solution for non-contact handling of breathable garment pieces in automated textile manufacturing.

To prevent subsequent injuries, minimize the risk of overtraining, and optimize rehabilitation training programs, fatigue assessment is essential. Current approaches have serious drawbacks: single-modality detection techniques like electroencephalogram (EEG), galvanic skin response (GSR), and photoplethysmography (PPG) only cover one physiological dimension, leading to low accuracy and insufficient robustness; subjective scales are heavily influenced by individual differences and cannot provide real-time monitoring. This paper proposes a multimodal fatigue assessment approach that integrates EEG, GSR, and PPG features. After feature selection using the random forest algorithm, we construct classification models based on K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Decision Trees (DT) to achieve four fatigue levels: no fatigue, mild fatigue, moderate fatigue, and severe fatigue. The results show that the tri-modal combination of PPG+GSR+EEG performs best in the KNN model with 5-second signal segments, achieving an overall classification accuracy of 79.77%, which is a 10% to 26% improvement over single-modality techniques. This multimodal fusion approach overcomes the limitations of traditional assessments and single-modality detection, enabling accurate dynamic monitoring of rehabilitation fatigue and providing reliable, objective data for real-time adjustments of rehabilitation training.

Robotic grippers with integrated sensing capabilities exhibit significant potential in interactive manipulation tasks. However, existing studies typically concentrate tactile sensors at the fingertips, overlooking the critical role of the palm during grasping, and thus the design of sensor-integrated palms remains insufficiently explored. To address this issue, this article proposes a robotic gripper based on a multi-spherical-joints self-adaptive palm structure. By strategically combining multiple levels of spherical joints, the palm passively conforms to the object during grasping and readily accommodates embedded orientation sensors. Using the measured joint pose angles in combination with a surface-fitting algorithm, the gripper can rapidly reconstruct the surface model of the object. Experimental results demonstrate that the proposed perception method is accurate and reliable, and that the palm structure exhibits excellent compliance with objects of various shapes, providing a solid reference for future designs of sensor-integrated robotic palms.

The cable-driven parallel robot combines the high rigidity of parallel mechanisms with the lightweight characteristics of cable-driven systems. However, due to the existence of various sources of error, it is unavoidable to bring uncertainty of cable lengths and lead to pose errors of the end effector. In this article, the inverse kinematic model of a cable-driven parallel lumbar rehabilitation robot (CDPLRR) is established by considering the geometric structure of fixed pulleys. The influence of fixed pulley radius on errors of cable lengths is explored. The error transfer model of the CDPLRR is constructed to analyze the effects of cable length errors, pulley installation errors, and the sagging effect of cables on the robotic system. In addition, an evidence theory and reliability analysis-based uncertainty method (ETRAM) is presented. Based on the error transfer model, the performance function for structural kinematic response is derived, and the belief and plausibility measures of the joint focal elements are calculated at the given threshold. Compared with the vertex method and the Monte Carlo method (MCM), it is verified that the ETRAM exhibits higher precision and computational efficiency in the kinematic uncertainty analysis of the CDPLRR. Additionally, by comparing the experimental results with numerical examples, the effectiveness and accuracy of the ETRAM in kinematic uncertainty analysis are further demonstrated.

The components of a fusion reactor would be ruined by high radiation and temperature whileconducting the fusion experiments to ensure the mankind safety, so it’s necessary to find a non-manual way to repair, such as remote handling maintenance in the hot cell. As for blanket modulerepairment of a fusion reactor, a 12-degree-of-freedom (DOF) serial–parallel hybrid robot, consistingof a Stewart parallel platform and a robotic arm, is designed for high-precision operations. Becauseof its ultra-high degrees of freedom and complicated kinematic coupling of the serial–parallel hybridrobot, this paper proposes an inverse kinematics algorithm based on multi-objective particle swarmoptimization (MOPSO) and a segmented trajectory control strategy, including the following parts:(i) The kinematics model of the hybrid robot: established by serially composing the moving platformcenter pose, the fixed base offset, and end pose of the robotic arm; (ii) The inverse kinematics analysis:using MOPSO to decouple the end-effector pose via the Stewart platform center pose and solving thejoint variables of both subsystems. (iii) The segmented trajectory control: Firstly, MOPSO is usedto determine feasible joint configurations that enable a smooth transition from the initial posture tothe starting pose. Secondly, a Jacobian-based incremental correction updates the Stewart platform leglengths and robotic arm joints to achieve high-precision continuous tracking of the desired trajectory.The simulation and experiment results validate the intelligent algorithms application’s correctness forthe complicated-structural robot in kinematics and segmented trajectory control problems.

Planar single-degree-of-freedom (DOF) mechanisms are widely used in human rehabilitation devices, yet research on spatial single-DOF mechanisms remains limited. Given the complex spatial nature of human motion, this study proposes a multi-mode spatial RSCR mechanism for gait rehabilitation. Multi-mode mechanisms incorporate adjustable parameters, enabling structural adaptation to different task trajectories. A kinematic model is established, followed by a circuit analysis to ensure trajectory synthesis accuracy. Using Gaussian mixture model clustering, a dataset of human gait trajectories is divided into three clusters, with one representative trajectory regressed from each cluster. A two-stage optimization strategy is implemented: an adaptive reference point-based non-dominated sorting genetic algorithm performs multi-objective optimization to determine optimal adjustable parameters ( y A and y( F )(c) ), while GA-BFGS refines these and additional parameters via single-objective optimization. Simulation results show that the mechanism can accurately reproduce the three representative trajectories by adjusting y A and y F c , with fitting errors of 9.76 & times; 10 (- 3 )m, 3.35 & times; 10 (- 2) m, and 1.09 & times; 10 (- 2) m, respectively. These results confirm the feasibility of using distributed optimization for the multi-mode design of RSCR mechanisms. The proposed dual-parameter adjustment method significantly enhances trajectory adaptability, achieving subcentimeter precision in some cases. This work explores a viable path for the development of spatial rehabilitation mechanisms and highlights potential advancements in the multi-mode design of gait rehabilitation systems.

With the continuous increase in the global aging population, stroke has become one of the major diseases affecting the health of the elderly, and the upper limb motor dysfunction it causes often requires long-term rehabilitation. To improve rehabilitation outcomes for hemiplegic patients and alleviate the shortage of rehabilitation physicians, upper limb rehabilitation robots have shown great potential in enhancing motor function and improving stroke patients’ rehabilitation outcomes in clinical research. This paper first classifies rehabilitation robots based on their driving mechanisms and interaction modes, describing the application of their structural features in various scenarios. It then analyzes the optimization methods used in the trajectory planning process of rehabilitation robots at different stages. Finally, based on existing shortcomings, the paper summarizes the future development directions of upper limb rehabilitation robots, providing prospects for the development of upper limb rehabilitation robots in the areas of artificial intelligence and compliant control, multi-sensory feedback and interactive training, ergonomics and new driving technologies, modular and customizable designs, and multi-modal brain stimulation techniques.

Surface electromyographic (sEMG) signal-driven joint-angle estimation plays a critical role in intelligent rehabilitation systems, as its accuracy directly affects both control performance and rehabilitation efficacy. This study proposes a continuous elbow joint angle estimation method based on time–frequency domain analysis. Raw sEMG signals were processed using the Short-Time Fourier Transform (STFT) to extract time–frequency features. A Scale Temporal–Channel Cross-Encoder (STCCE) network was developed, integrating temporal and channel attention mechanisms to enhance feature representation and establish the mapping from sEMG signals to elbow joint angles. The model was trained and evaluated on a dataset comprising approximately 103,000 samples collected from seven subjects. In the single-subject test set, the proposed STCCE model achieved an average Mean Absolute Error (MAE) of 2.96±0.24∘, Root Mean Square Error (RMSE) of 4.41±0.45∘, Coefficient of Determination (R2) of 0.9924±0.0020, and Correlation Coefficient (CC) of 0.9963±0.0010. It achieved a MAE of 3.30∘, RMSE of 4.75∘, R2 of 0.9915, and CC of 0.9962 on the multi-subject test set, and an average MAE of 15.53±1.80∘, RMSE of 21.72±2.85∘, R2 of 0.8141±0.0540, and CC of 0.9100±0.0306 on the inter-subject test set. These results demonstrated that the STCCE model enabled accurate joint-angle estimation in the time–frequency domain, contributing to a better motion intent perception for upper-limb rehabilitation.

This finger rehabilitation device can perform grasping rehabilitation movements by driving all fingers through the mechanism. Based on measured finger grasping motions, the flexion-extension trajectory of the index finger is used as an example. MSOPS-II algorithm was employed to conduct a comparative analysis of a single-DOF four-bar mechanism, a Watt-type six-bar mechanism, and a Stephenson-type six-bar mechanism to achieve flexion-extension movements for the four fingers excluding the thumb. This study compares the optimization results of PSO, GA-BFGS, and MSOPS-II algorithms for mechanism synthesis and design. Since the four fingers (excluding the thumb) exhibit simple motion patterns, strong synergy, and primarily planar movement, adaptive designs, such as strap-on modules and adjustment modules, can meet rehabilitation requirements. In contrast, the thumb’s opposition function and individualized motion demands necessitate precise control through link-length adjustments in its rehabilitation mechanism. To address this, we adopted a multi-mode single-DOF (MMSD) mechanism design to achieve thumb grasping motions. The SolidWorks modeling and simulation verified the feasibility of using a Watt-type six-bar mechanism and an MMSD four-bar mechanism to drive fingertip motion for grasping. The development of this wearable exoskeletal finger re-habilitation device can assist stroke patients and individuals with hand dysfunction in restoring grasping function, thereby improving their quality of life.

Kinematic analysis and synthesis are two key topics for the study of mechanisms, and they are also important foundations of the practical application of mechanical design and control. Machine learning (ML), as a data-driven approach, enables the kinematic analysis and synthesis of different types of mechanisms while avoiding complex analytical and numerical methods. In this review, we summarize the various applications of ML algorithms and different types of data representations in the kinematic analysis and synthesis of mechanisms. A comprehensive literature review and brief analysis of current advances in ML-based approaches for the kinematic analysis of serial and parallel mechanisms, as well as their kinematic synthesis, are presented. The advantages of applying single, modular, and hybrid neural networks in the kinematics of mechanisms are discussed and compared. The future integration of ML and the kinematics of mechanisms is proposed, and the potential challenges involved are addressed.

Single degree-of-freedom (DOF) mechanisms have been widely used for their simple structure and easy to control, but it can only lead through one specific motion trajectory. This article proposes an approach to design multi-mode single-DOF (MMSD) four-bar mechanisms, which could realize multiple motion trajectories using only one driving motor via an optimized structure with a selected adjustable parameter, which is applied in the design of upper limb rehabilitation mechanism. Firstly, three target trajectories are established for the upper limb rehab of three different groups of population. Then a source mechanism for multi-mode four bar linkage with five candidate adjustable parameters is designed, which can fit multiple different motion trajectories by selecting one specific parameter to be adjustable. Next, multi-objective optimization algorithm MSOPS-II is adopted to analyze the Pareto boundary, and HV value is evaluated to determine the optimal adjustable parameter, while the rest fixed parameters are also obtained through optimization. Finally, the multi-trajectory fitting results with the MMSD four-bar mechanism are presented and a comparison of various multi-objective optimization algorithms is con-ducted to assess the fitting errors under three different modes. The prototype of the multi-mode upper limb rehabilitation device is also designed.

This paper focuses on investigating the dynamic target tracking problem based on local observation. Target tracking faces the dual challenges of real-time observation and efficient tracking strategies in industrial grasping, human-robot interaction, and other scenarios. Traditional methods typically handle target state estimation and robot tracking strategies independently, neglecting their coupling correlation. This paper first presents and analyzes the dynamic target tracking problem, and then proposes a local observation-based non-adversarial dynamic target adaptive tracking strategy, which combines local polynomial fitting of target motion trends with robot dynamic tracking control to realize the joint optimization of target position estimation and tracking strategy. When the target is far, the strategy emphasizes long-term motion trend prediction, while for close-range tracking, short-term precise prediction is prioritized. The simulation experiments are conducted using 100 randomly generated trajectories with varying noise levels. An error distribution analysis is performed on the experimental results, which demonstrated that, compared to traditional methods. The proposed approach significantly reduces tracking errors with a new solution for dynamic target tracking problems.

For injured and after-stroke patients who temporarily lose their hand’s grasping abilities, assisting them in regaining their index finger mobility is very important in the rehabilitation process. In this paper, a finger rehabilitation device based on one degree-of-freedom (DOF) linkage mechanism is designed, aiming to lead the index finger through the flexion–extension trajectory during grasping tasks. Two types of one-DOF mechanisms, a four-bar linkage and a Watt-I six-bar linkage, are synthesized for the task trajectory. Various algorithms such as PSO, GA, and GA–BFGS are adopted and compared for the synthesis of these two types of mechanisms, among which the Watt-I six-bar linkage obtained with GA–BFGS shows the optimal performance in accuracy. Clinical biomechanical data are utilized to perform static analyses of the mechanisms, and the feasibility of the Watt-I six-bar linkage models is tested, compared, and demonstrated. Finally, the prototype of the six-bar linkage as well as a wearable exoskeleton finger rehabilitation device are designed to show how they are applied in the finger rehabilitation scenario.

Gesture recognition plays an increasingly important role in fields such as human-computer inter-action and rehabilitation robots and therapy. However, most current gesture recognition systems are based on a single type of sensor, which limits the feature sources for gesture recognition. Therefore, this paper proposes a time-frequency and visual feature fusion multimodal recognition framework (TFVF -CNN). It combines the deep features extracted from a small amount of image data with the time-frequency fea-tures of surface electromyogram (sEMG) signals to improve the accuracy of gesture recognition based on sEMG. Additionally, this paper introduces a multi-modal dataset (MEVD) containing raw sEMG signal data, sEMG signal time-frequency data, and image data, providing a reliable data source for experiments. Finally, the experimental results show that gesture recognition accuracy with multimodal fusion features and time-frequency features based on sEMG signals is 93.88 % and 95.9 %, respectively. Furthermore, we verified the performance of gesture recognition under partial image occlusion and found that TFVF -CNN still exhibits superior performance.

Faults serve as oil and gas storage space and transportation channels, so fault identification is significant to oil and gas exploration. Fault extraction methods based on manual identification or seismic body attributes are prone to recognition errors due to human factors or poor data quality. With the development of deep learning, researchers have proposed different network models to extract 3D faults. However, the traditional models still have room for improvement in fine-grained segmentation results and model robustness. Therefore, this study proposes a new multi-scale feature fusion network architecture named MAR-UNet. In order to solve the defect of insufficient fine granularity of traditional model segmentation results, this paper designs a local feature extraction module named Residual Sampling Convolution block (RSC block) and deploys it to MAR-UNet; at the same time, in order to improve the defect that the existing 3D model cannot effectively deal with complex spatial relationship features, this study designs a plug-and-play attention module named Mix Attention Mechanism (MAM) in the model. Finally, this paper proposes a compound loss function named Weight Focal-Dice loss for the model's weak robustness caused by sample imbalance. The results of ablation and cross-experiments show that the loss function proposed in this paper is suitable for accomplishing the fault segmentation task under the influence of sample imbalance, and the model proposed in this paper still shows good reliability and robustness when deploying the model to the actual workspace data.

Single degree-of-freedom (DOF) mechanisms have been widely used as motion executers for their compact structure and simple control. However, a single-DOF device can only lead through one specific motion trajectory. This article proposes an approach to design multimode single-DOF (MMSD) six-bar devices, which could realize multiple task trajectories using only one driving motor via an optimized structure with a selected adjustable parameter (A-Parameter). First, a source mechanism for multimode Watt-I six bar linkage is designed with nine candidate adjustable parameters, which enables the same mechanism to fit multiple different trajectories by selecting one specific parameter to be adjustable. Next, to determine the optimal A-Parameter, a multiobjective optimization algorithm nondominated sorting genetic algorithm II (NSGA-II)-adaptive rotation-based simulated binary crossover (ARSBX) is used to demonstrate and analyze the Pareto frontier optimization under different A-Parameters. Then, we take a family of gait trajectories from three different groups of volunteers as the task to illustrate the design of the MMSD six bar device. It shows that the optimal result appears when selecting $l_{1}$ as the A-parameter with the optimization window width $m=1$ . Finally, a prototype of the multimode source mechanism is built, and an application on the design of the MMSD gait rehabilitation device is configured and tested on the prototype, in which kinematic and dynamic analysis results both show a good realization of the tasks.

In the automation process of the garment industry, a notable challenge arises from the presence of flexible materials characterized by irregular shapes, posing difficulties for robotic grasping. This article addresses this challenge by proposing a gripper manipulator centered around the 4 P-RRP quadrilateral cone folding mechanism as the core driving mode, with the angled four-bar linkage mechanism serving as the extension arm. Utilizing screw theory, the developability of the 4 P-RRP four-pyramid mechanism with one degree of freedom is verified, forming the basis for its adoption as the central driving mechanism. Furthermore, an in-depth analysis of the geometric properties of the robot's extension arm leads to the derivation of an optimal folding ratio structure, which is seamlessly integrated into the robot design. Kinematic equations for the mechanism are formulated and solved using the D-H parameter method to obtain the kinematic solution. The investigation demonstrates that the manipulator utilizing the quadrilateral cone folding mechanism significantly enhances adaptability to irregular shapes. By incorporating this proposed mechanism, robots can efficiently manipulate flexible materials across various garment manufacturing applications.

This paper presents a low-cost, light-weight, six-degree-of-freedom force feedback manipulator, aiming to conduct the master-slave control of a surgical robot system with continuum structure. Firstly, considering the practical workspace requirements of the continuum minimally invasive surgical robot, a basic series configuration is proposed that can provide three degrees of freedom for force feedback and achieve gravity balance through mechanical counterweighting. Secondly, a force feedback bidirectional master-slave control system based on a dynamic model is constructed, which can realize incremental master-slave control, variable ratio control, and force feedback functions. In the end, experiments are conducted to verify the position accuracy, gravity balance effect, and force feedback performance of the master manipulator. The experimental results show that the presented force feedback master manipulator has a position resolution of less than 0.4mm and can provide a maximum feedback force of 75.7N. The overall cost of the system is less than 60 US dollars.