Reliable extraction of line segments from complex scenes has been enabled by the line segment detector (LSD) algorithm, which provides accurate geometric information for various visual perception applications. However, LSD often extracts line segments that are either excessively short or overly long, increasing computational complexity and degrading feature matching accuracy. Although many methods focus on eliminating redundant short lines, the challenges of overly long line segments remain largely unexplored. To address these issues, this paper proposes an enhanced LSD-based method that integrates short-segment elimination and long-segment truncation strategies. The resulting line segments are constrained within a reasonable length range, effectively balancing geometric information with feature matching robustness. In addition, a collinearity-based matching method is introduced to maintain the geometric continuity of truncated segments and improve inter-frame feature consistency. Furthermore, the proposed method is integrated into a point-line visual-inertial odometry system by fusing data from an inertial measurement unit, significantly improving system robustness and accuracy, especially in low-texture environments. Extensive experiments on public datasets and real-world scenarios show that the proposed method achieves competitive overall performance, particularly in structured and low-texture environments.

The state-of-charge (SOC) estimation of lithium-ion batteries is essential for the performance, safety, and longevity of electric vehicles. While traditional physics-based models face difficulties in predicting SOC under complex conditions, data-driven methods demand large volumes of labeled data, limiting their practical applicability. This paper introduces a Transformer-based SOC estimation method that incorporates a self-supervised learning framework. By combining a masking recovery mechanism with a self-attention mechanism, the approach effectively captures SOC’s long-term dependencies and identifies global patterns under complex operating conditions. Experimental results on the Nissan Leaf and University of Maryland datasets demonstrate significant performance improvements. Compared to traditional deep learning methods, this approach delivers higher prediction accuracy and robustness, offering an innovative solution for efficient SOC estimation in complicated environments.

To address uncertainty-induced kinematic response fluctuations in passive ankle exoskeletons, a bioinspired passive compliant ankle-exoskeleton structural concept is proposed. The design integrates four biomechanical subsystems: (I) a soleus muscle-inspired elastic-damping energy storage assistance mechanism, (II) an ankle soft tissue-mimetic elastic load-bearing structure, (III) a foot–ankle complex motion-inspired buffering-propulsion unit, and (IV) an ankle-joint motion-inspired passive compliant support, collectively forming an integrated shank-ankle–foot composite bioinspired system. Based on prescribed sagittal-plane human input and simplified foot–ground boundary constraints, a human–exoskeleton–environment equivalence kinematic model is established. The Chebyshev polynomial response-interval method is applied to quantify the destabilizing effects of wearing-position uncertainty on human–exoskeleton coordination. A bioinspired kinematic response containment-smoothness (BKRCS) index is proposed for human–exoskeleton optimization. Structural parameters are optimized via an enhanced particle swarm optimization-genetic algorithm (PSO-GA) hybrid strategy using multi-objective formulation. Simulation results show that the optimized configuration reduces the selected comprehensive kinematic metric, while different key response variables exhibit mixed trends: the objective-function value converges to 0.2276, the BKRCS decreases to 0.1902, the fluctuations in displacement, velocity, and acceleration of $L^{\text{45e}}$ and $\theta ^{\text{13re}}$ all exhibit a downward trend; although the displacement and velocity responses of $L^{\text{78e}}$ increase slightly, its acceleration fluctuations are effectively suppressed. Numerical results indicate that the optimized mechanism exhibits smoother kinematic responses and reduced sensitivity to wearing-position uncertainty. Thus, this study provides a theoretical framework and methodological basis for the biomimetic structural design, uncertainty kinematic evaluation, and multi-objective kinematic dimensional synthesis of passive ankle exoskeletons.

Connecting multiple destinations with the shortest overall path in an obstacle-rich indoor environment is a classic problem in robotic path planning. Established solutions, such as A*, ARA*, and RRT*, execute faster when given smaller input maps that exclude extraneous paths. However, removing such paths without losing the ground truth solution is challenging because runtime-efficient approximations can yield detours. This work proposes a deep learning-based search-space reduction pipeline (SRP) that integrates a module called MazeNet to solve indoor navigation tasks with fast runtimes while maintaining accuracy. We transform the indoor environment into a graph representation, reducing the planning task into a graph-based optimization problem known as the Obstacle-Avoiding Rectilinear Steiner Minimum Tree. MazeNet takes compressed images derived from graph abstractions as inputs and uses a recurrent convolutional neural network trained to predict the shortest feasible path connecting all destinations. Within SRP, MazeNet’s output restricts the search space for classical planners. MazeNet solves more complex instances than those seen during training via recurrence with an integrated termination condition. We evaluate MazeNet’s runtime and path-length performance using a variety of planning methods against both exact and approximate graph algorithms in simulations and, after fine-tuning, in real-life floor plans. MazeNet solves all these specific test cases with improved runtimes and no increase in path length. Physics simulation further supports SRP’s feasibility across the tested floor plans, with no collisions recorded during navigation tasks.

Soft robotic hands face trade-offs between flexibility and load capacity, with rigid-palm designs limiting grasping conformity and fully soft structures struggling under payloads. Existing pneumatic systems suffer from tubing interference and poor sealing. This study presents a bioinspired modular hand combining rigid supports and soft actuators to enhance stability and payload (2 N fingertip force at 300 kPa; 1.97 kg maximum grasping payload). A biomimetic thenar joint and rigid linkages optimize thumb-mediated grasping, while built-in pneumatic channels eliminate external tubing, improving reliability. Integrated with RGB-D vision and robotic arm coordination, the system achieved autonomous grasping with 87.22% and 83.33% success rates in single- and multi-object tasks, respectively. This hybrid rigid-flexible approach advances dexterous robotic manipulation by synergizing structural adaptability, modular maintenance, and intelligent perception for practical robotic applications.

This paper presents the design, analysis, dynamic dimensional synthesis, and prototype development of a novel 2-degree-of-freedom (2-DOF) parallel robot actuated by prismatic pairs. First, the proposed robot, designated as “TGU-SV2”, is introduced; it features prismatic actuation and spatial V-shaped passive limbs. This mechanism is designed to be modular, allowing integration with auxiliary modules to expand its DOFs. The forward and inverse kinematics, along with velocity and acceleration models, are derived to establish the Jacobian mapping relationships among the moving components. Based on these kinematic formulations, both simplified and exact rigid-body dynamic models are developed. The validity of these models is rigorously verified through co-simulations using SolidWorks and MATLAB/Simscape. Furthermore, three dynamic performance indices characterizing inertial forces, centrifugal/Coriolis forces, and gravitational terms are systematically formulated, subject to geometric and motion constraints. Monotonicity analysis and a genetic algorithm are then employed to determine the optimal dimensional parameters. Finally, a physical prototype is fabricated based on the optimized design, and preliminary performance tests are conducted. The test results show that the prototype can basically complete trajectory tracking, demonstrating its potential for applications in logistics sorting and industrial production, as well as laying a foundation for more refined prototype control in subsequent research.

To address the difficulty of simultaneously achieving motion bionics, active driving capability, and structural compactness in prosthetic knee joints, a structurally compact magnetorheological prosthetic knee joint (SCMRPK) with obstacle-crossing function is proposed in this paper. The SCMRPK combines a four-bar linkage mechanism and a linear magnetorheological actuator (LMRA). By integrating a micro linear motor into the piston rod of an MR damper, the LMRA combines the active and semi-active modes, enabling it to output driving force in the active mode and controllable damping force in the semi-active mode. The four-bar linkage mechanism is used to mimic the variation of the instantaneous center of rotation of the human knee. The structure and working principle of the SCMRPK are presented. A key dimensional design method for the LMRA magnetic circuit is proposed, and simulation and experimental tests are conducted to verify the effectiveness of the designed magnetic circuit. A control method for the SCMRPK is developed, and a prototype is fabricated. Under a locking current of 1.5 A, the LMRA prototype achieves stable displacement tracking in active mode. At a walking speed of 1.2 m/s, the semi-active mode of the SCMRPK prototype yields a root mean square error of 1.54° between the measured and ideal knee angles. In active mode, the SCMRPK-based lower-limb prosthesis successfully crosses an obstacle 0.3 m high. These results demonstrate that the proposed SCMRPK is compact and capable of achieving a relatively natural gait and obstacle crossing.

For a four-limb 2R1T parallel mechanism consisting of three coplanar limbs and one spatial limb, determining its exact position often involves complex elimination and cumbersome calculations. This paper introduces a conformal geometric algebra framework, integrating rigid-body motion operators with intersection operations of geometric elements, and proposes a differentiated forward kinematics solution strategy based on geometric feature classification. Based on the geometric perpendicular relationship between the line connecting the moving-platform articulation points of the passive coplanar limb and the spatial limb, and the common plane of the three coplanar limbs, this class of mechanisms is divided into two subclasses, namely mechanisms without perpendicular constraints and mechanisms with perpendicular constraints. For mechanisms without perpendicular constraints, a direct analytical solution method that does not require elimination has been developed. For mechanisms with perpendicular constraints, a low-order matrix can be constructed via resultant elimination to solve the problem, which also significantly reduces the scale of the elimination process and the difficulty of the solution. A comparative analysis under identical conditions shows that the proposed method, which combines rigid-body motion operators, is more efficient than the geometric intersection operations method alone. Taking the two spatial configurations 2UPU-2SPR as examples, the eight sets of real-number solutions obtained from the numerical examples are in close agreement with the 3D simulation results, thereby validating the correctness and reliability of the method. This work also provides a new approach that can be applied to the efficient solution of forward kinematics for other complex parallel mechanisms.

The reachable velocity of a serial robot within its workspace is crucial for planning complex robotic tasks. Traditional methods often struggle to accurately assess the maximum reachable velocity of both redundant and nonredundant serial robots in directions involving coupled translational and rotational motion. This paper proposes a method for evaluating the maximum oriented velocity of serial robots. The approach separates the motion into pure translational and pure rotational components. It converts the summation of joint velocities that satisfy only translational and rotational velocity constraints into an objective function. Consequently, solving the robot’s maximum oriented velocity is transformed into a numerical optimization problem using linear programming. The proposed method is applicable to both nonredundant and redundant serial robots. A comparative experiment demonstrates that the proposed method exhibits high accuracy. Especially in the redundant serial robots, the proposed method has an average error of 0.67%, while the existing decomposed twist feasibility method has an average error of 12.56%.