Search Results (526)

Soft exoskeletons have attracted increasing attention as wearable robotic devices for lower limb rehabilitation and assistive mobility. This study presents an integrated modelling, control, and mechanical design framework for a cable-driven soft exoskeleton operating in the sagittal plane, targeting elderly users with reduced mobility. Lower limb swing-phase dynamics were derived using the Euler–Lagrange formulation and subsequently recast via a Legendre transformation into a Hamiltonian representation of the coupled hip–knee system under tendon-driven actuation. Building upon this model, a hierarchical control architecture combining Quasi-Sliding Mode Control (QSMC) for angular regulation with Sliding Mode Control (SMC) for conjugate-momentum dynamics is developed. A Lyapunov-based stability analysis formally establishes the asymptotic stability of the closed-loop system and derives explicit gain conditions for robust tracking in the presence of bounded disturbance. In parallel, a compact winch-based actuation module was designed and geometrically optimized using a genetic algorithm to minimize the distal mass while preserving mechanical robustness and ergonomic wearability. The framework was validated through numerical simulations in MATLAB–Simulink^® and physics-based simulations in a MuJoCo–ROS2 environment, in which gravity, contact interactions, and cable compliance were considered. A modular mechanical prototype was developed and worn by users with different anthropometric characteristics for a static qualitative assessment of its fit and structural feasibility. These results establish a rigorous foundation for the future integration of embedded sensing and actuation hardware into experimental rehabilitation assessment. Full article

This paper presents a wearable soft strain sensor based on a commercially available conductive thermoplastic polyurethane (cTPU) 3D-printed as an auxetic soft metamaterial for human activity recognition. The growing demand for flexible and wearable electronics, driven by advances in artificial intelligence, highlights the importance of such sensors in healthcare, medical rehabilitation, soft robotics, and human–machine interfaces. The auxetic cTPU sensor was mechanically and electrically characterized through empirical measurements and validated against numerical simulations. A single sensor mounted on a knee brace was used to collect gait signals across four activities: running, walking, standing, and sitting. Two classification approaches were investigated. A Long Short-Term Memory (LSTM) network was trained directly on the raw time-series signal, with the best configuration achieving 96% accuracy using Relative Standard Deviation Normalization with 50 hidden units. Traditional machine learning models, namely Random Forest and XGBoost, were trained on 30 extracted time-domain and frequency-domain features per motion cycle, achieving 100% and 97.33% accuracy, respectively, under five-fold cross-validation. To enhance model transparency, explainability analysis using SHAP identified power spectral density and the first harmonic frequency as the most consistently influential features across both models, with dynamic activities driven by frequency characteristics and stationary activities distinguished by signal mean amplitude. The results demonstrate that auxetic cTPU soft strain sensors combined with machine learning and explainable artificial intelligence provide an accurate and interpretable solution for wearable human activity recognition, highlighting their potential for applications in robotics, healthcare, and human–robot interfaces. Full article

Soft continuum robots exhibit highly nonlinear and configuration-dependent dynamics, making accurate trajectory tracking challenging under model uncertainty and external disturbances. This paper presents an adaptive Koopman-based model predictive control (MPC) framework for a tendon-driven soft continuum robot and evaluates its performance through comprehensive closed-loop simulations. A lifted linear Koopman model is identified from experimentally collected robot data and incorporated into an MPC formulation to provide computationally efficient prediction while capturing dominant nonlinear behavior. To compensate for plant–model mismatch and time-varying uncertainties, an online Recursive Least Squares (RLS) adaptation mechanism is integrated into the Koopman–MPC framework, enabling continuous model refinement during closed-loop operation without repeated offline retraining. The proposed controller is evaluated through comprehensive closed-loop simulations on circular, triangular, helical, and figure-eight trajectories under stochastic disturbances and structured parametric bias conditions using a Koopman model identified from experimentally collected robot data. Results demonstrate consistent improvements in tracking performance compared with fixed Koopman MPC while maintaining real-time computational feasibility. Under structured parametric bias, the proposed controller reduces the mean tracking error from 9.30 mm to 1.36 mm during circular trajectory tracking and achieves sub-millimeter accuracy in several operating conditions. These findings highlight the potential of online Koopman model adaptation for predictive control of soft continuum robots operating under uncertainty. Full article

Pneumatic soft actuators have been drawing considerable attention in the field of soft robotics, thanks to their inherent flexibility, high power density, and safe interaction. However, the strong, intricate coupling between the material’s hyperelastic behavior and the reinforcement of anisotropic fibers creates significant challenges for both analytical modeling and numerical characterization of these actuators. In this paper, we design and fabricate a fiber-reinforced pneumatic soft actuator using Ecoflex 00-30 silicone rubber as the base material and helically wound fibers as the reinforcing layer. We set up a theoretical framework that combines the Neo-Hookean model for isotropic silicone rubber with a strain energy-based formulation for anisotropic wound fibers. This framework describes how the actuator is stretched, expanded, twisted, and bent. Finite element simulations are then carried out, focusing on three key design parameters: winding fiber density (three levels: high, medium, low), air cavity offset distance from the central axis (1, 2, 3, and 4 mm), and air cavity cross-sectional geometry (cube vs. cylindrical). The simulations reveal that a higher winding fiber density promotes more uniform stress distribution across both the strain and confinement layers. In contrast, a low fiber density can lead to local bulging and large stress variations, which ultimately compromises the bending performance. The offset distance of the air cavity from the neutral axis is directly linked to the bending curvature: a larger offset produces greater air cavity deformation and higher actuation efficiency. Furthermore, the cuboid air cavity yields a larger bending angle (experimentally validated up to 90° at 0.045 MPa) and better efficiency, while the cylindrical air cavity distributes stress more evenly across the outer surface of the strain layer and reduces stress concentration at the edges. These findings provide useful quantitative guidance for optimizing the structure of fiber-reinforced soft actuators and establish a framework for hybrid analytical–numerical prediction of their mechanical behavior. Full article

Terrain types significantly affect the dynamics and locomotion performance of hexapod robots during walking. Terrain classification is a key solution to modify gait patterns in different terrains and recognize hazardous conditions. Perceiving the terrain with proprioceptive sensing is a robust and reliable approach in extreme conditions. In this paper, an efficient terrain classification approach for a hexapod robot is proposed. The proposed method combines a deep classification framework including the long short-term memory (LSTM) network and an effective statistical feature extraction. Proprioceptive inertial measurement unit (IMU) data is only used as the sensing system for the robot–terrain interaction. In the feature extraction process, four meaningful characteristic features, namely, the mean, median, Lomb–Scargle periodogram power spectral density (LPSD), and Welch’s power spectral density (WPSD), are extracted from the body orientation data using a sliding-window method. These features are combined and fed into the network to perform the training and testing processes. In the experiments, the proposed method is evaluated with commonly used soft computing and deep learning models. The classification performance for the concrete, pebble, and waxed tile terrains reaches 100% with the proposed method. The overall accuracy, precision, sensitivity, specificity, F1-score, and Matthew correlation coefficient are recorded as 95.45%, 96.36%, 95.28%, 98.86%, 95.49%, and 94.61%, respectively. These results demonstrate that the proposed approach delivers reliable classification performance with a low-cost and easy-to-implement solution. Full article

Soft deformable materials such as elastomers, biological tissues, and polymeric membranes are widely used in modern engineering applications including biomechanics, soft robotics, and flexible electronics. Accurate identification of their constitutive parameters is therefore essential for reliable mechanical modeling and design. Membrane inflation or bulge tests are commonly used for this purpose, where material parameters are typically identified from pressure–deflection measurements. However, such measurements generally require optical systems to capture membrane deformation, which increases experimental complexity. In this work, we propose a surrogate-assisted inverse identification framework for determining hyperelastic material parameters using pressure–volume data obtained from membrane inflation tests, thereby eliminating the need for optical deformation measurements. To reduce the computational cost associated with repeated forward simulations, an Artificial Neural Network (ANN) surrogate model is trained using numerically generated pressure–volume data from finite-element simulations. The trained ANN efficiently predicts the pressure response of the membrane for different material parameters and volume influx values. A Genetic Algorithm (GA) is then employed to identify the optimal parameters by minimizing the discrepancy between measured and predicted responses. The proposed GA–ANN framework is demonstrated for the Mooney–Rivlin hyperelastic model and accurately recovers material parameters for both noise-free and noisy datasets, providing a computationally efficient and robust methodology for the characterization of soft membranes. Full article

Thermal drawing is a prominent, scalable method for transforming preforms with complex macroscopic morphologies into multifunctional microscopic fibers. With the intent to develop fibers with complex cross-sections for potential integration in soft robotics, smart textile and fabric applications, we explore the potential of polyamide-6 (PA6) as a base material for thermal drawing. By implementing Fused Deposition Modeling (FDM), we additively manufactured PA6 preforms with solid circular and three-channel cross-sectional architectures. These preforms were then utilized in a series of thermal drawing experiments to identify the best-performing printing layer thickness and channel aspect ratio (AR) that consistently yielded scalable, microscopic fiber diameters over extended durations. Our results demonstrate that a printing layer thickness of 0.3 mm yielded the most consistent drawn fiber diameters for extended durations among the tested values. Additionally, AR experiments indicate that the intermediate ARs of 0.4 and 0.5 between the inner channel diameter and the outer diameter produce the most promising results within the investigated range, based on dimensional trends and qualitative observations of internal channel integrity. Full article

In complex and unstructured orchard environments, accurate fruit detection is essential for yield estimation and robotic harvesting in precision agriculture. However, single-model detectors often suffer from reduced robustness and high miss rates under drastic illumination changes, severe occlusions, and dense fruit overlap. To address these challenges, this study proposes a multi-model fusion framework for robust mango detection in complex orchard environments. The proposed method employs YOLOv8n, YOLOv8s, and YOLOv8m as base detectors and applies multi-scale test-time augmentation (TTA) to obtain predictions from different augmented views. After mapping the predicted bounding boxes back to the original image coordinate system, predictions corresponding to the same target across different TTA views of each base detector are matched based on the intersection over union (IoU), yielding model-specific prediction results. Weighted Box Fusion (WBF) is then applied to determine the fused bounding-box coordinates. For candidate targets jointly detected by multiple base detectors, the confidence scores provided by the individual models are combined using Noisy-OR to obtain the fused confidence score. Finally, Gaussian Soft-NMS is applied to decay the scores of overlapping candidate boxes, thereby reducing the risk of incorrectly suppressing adjacent mangoes in densely clustered scenes. Experiments on two complementary datasets under within-dataset evaluation protocols demonstrate the effectiveness of the proposed method. On the standard dataset (Data1), Recall and mAP@0.5 reach 95.52% and 98.60%, respectively. Across five repeated random holdout splits of Data2, the proposed framework increased the mean Recall from 82.79% to 84.90% and the mean mAP@0.5 from 90.27% to 91.23%. These results indicate that the proposed framework improves detection robustness and completeness compared with single-model detectors in complex orchard environments, demonstrating its potential for offline yield estimation and orchard phenotyping. Full article

Modeling large shape changes efficiently is an important challenge in deformable kinematics, soft robotics, compliant mechanisms, geometric modeling, and deformation-based path planning. This paper presents Projective Estimation with Per-Point Scales (PEPS), a family of linear estimation methodologies for obtaining a compact global approximation of the deformation between two configurations of a body from corresponding points. The deformation is represented by a single projective deformation matrix, 3 by 3 in two dimensions and 4 by 4 in three dimensions, which provides a unified representation of translation, rotation, scaling, shearing, and projective effects. Three related formulations are developed and compared. PEPS-1 explicitly introduces an independent homogeneous scale for each point correspondence. PEPS-2 eliminates these additional variables by enforcing projective collinearity and has an algebraic structure closely related to the classical Direct Linear Transform. PEPS-3 augments the collinearity formulation with equivalent constraints derived in a translated coordinate frame to investigate improvements in numerical conditioning. Isotropic coordinate normalization is applied to all three formulations to reduce sensitivity to coordinate magnitude, reference-frame placement, and point distribution. The resulting systems are estimated efficiently using singular value decomposition. The methodologies are evaluated on representative nonlinear shape transformations, including square-to-circle, cube-to-sphere, and cube-to-ellipsoid mappings. Reconstruction accuracy is assessed both at the correspondences used for estimation and at additional points, allowing fitting performance to be distinguished from generalization over the complete shape. The results show that a single projective deformation matrix can effectively capture the dominant global characteristics of nonlinear shape changes. PEPS-2 and PEPS-3 generally provide smaller linear systems, improved numerical conditioning, and lower computational cost than PEPS-1, while PEPS-1 can offer greater fitting flexibility for certain redundant or geometrically dependent correspondence sets. Comparisons with iterative nonlinear optimization demonstrate that the proposed linear formulations achieve comparable global approximations at substantially lower computational cost. These characteristics make the PEPS framework particularly suitable for fast deformation representation, deformation-aware kinematics, soft and continuum robotics, compliant mechanisms, and geometry-based path planning and control. Full article

Fused filament fabrication (FFF) is one of the most widely adopted additive manufacturing methods for thermoplastic polyurethane (TPU)-based soft pneumatic actuators, enabling low-cost fabrication, geometric customization, embedded pneumatic architectures, and rapid prototyping for soft robotic systems. However, despite these advantages, achieving reliable airtightness remains a major challenge due to process-induced anisotropy, interlayer voids, incomplete filament fusion, residual porosity, seam discontinuities, material permeability, and interface-related leakage. These defects can significantly reduce pressure retention, actuation efficiency, deformation repeatability, and long-term pneumatic reliability. This review systematically examines the dominant leakage mechanisms affecting FFF-printed soft pneumatic actuators and comparatively analyzes fabrication approaches, TPU material systems, geometric design factors, post-processing methods, sealing strategies, and leakage characterization techniques. Representative experimental observations, including pressure-decay testing, submerged-bubble visualization, microscopy, and localized thermal surface treatment, are also discussed to connect the findings reported in the literature with experimentally observed leakage behavior. Emerging analytical leakage models, sensing technologies, AI-assisted predictive monitoring, and digital-twin-enabled manufacturing frameworks are reviewed as promising approaches for developing leakage-aware soft robotic systems. The review highlights current limitations related to standardized leakage testing, cyclic durability evaluation, scalable sealing strategies, and intelligent manufacturing integration. Overall, airtightness is identified as a coupled material-process-geometry challenge that must be systematically addressed to improve the reliability, scalability, and long-term operational stability of next-generation TPU-based soft pneumatic actuators. The review was conducted following the PRISMA-ScR framework and includes 248 studies published between 2017 and 2026. Full article

Accurate modeling of deformable object dynamics is critical for robotic manipulation but remains challenging due to complex physics and strict physical constraints. In this paper, PhysCon-Deform is introduced, which is a mixed framework for specific tasks, combining residual neurodynamics learning and a differential augmented Lagrangian projection layer. Using a grid-based graph representation, PhysCon-Deform integrates a physics-based neurodynamics operator (PINDO) and a differentiable constraint projection module to achieve the deployment of residual correction, grid-based neurodynamics and model predictive control (MPC). Based on standard simulation benchmarks (Cloth3D, SoftGym and SoftMAC), our framework is always superior to the existing baselines in clean and disturbed environments. Specifically, it reduces long-term constraint violations by over 50%, demonstrates high robustness to end-effector trajectory noise, and enables efficient real-time trajectory optimization within an MPC pipeline. Extensive ablation and bias studies reveal that removing PINDO increases the prediction mean squared error (MSE) from 0.28 cm² to 0.68 cm² (a 143% increase), while omitting the constraint projection layer leads to a fourfold increase in violation rates. Furthermore, the robustness analysis of a colored noise and random walk drift model verifies its elasticity to non-ideal sensing. Although the deformation mechanism with a moderate rate-dependent effect in the simulation environment is optimized at present, PhysCon-Deform provides a very practical method to balance the precision-constraint trade-off in the control of deformable objects with physical constraints. Full article

Accurate perception of occluded apples in tree canopies is important for precision orchard management and robotic harvesting, but RGB-only vision is sensitive to leaf occlusion, fruit overlap, and unstable illumination. This study presents OAFBC-Net, a lightweight RGB-depth network for joint localization and occlusion-level recognition of apples classified as non-occluded (NO), soft-occluded (SO), or hard-occluded (HO). OAFBC-Net integrates three components: a Fourier amplitude-phase enhancement fusion module (FAPEF) for cross-modal frequency-domain fusion, a weighted bidirectional feature pyramid (BiFPN) for multi-scale interaction, and a Triple Context Guided Block (TCG) for local-to-global semantic compensation. Using an orchard RGB-depth dataset with 3000 image pairs and 134,999 annotated instances acquired with an Intel RealSense D455 camera, OAFBC-Net achieves AP50 values of 72.1%, 87.3%, and 57.9% for SO, NO, and HO, respectively. Under the same split, it outperforms the self-implemented RGB-depth baselines. With FAPEF, BiFPN, and TCG enabled, the macro-average mAP50 and mAP50–95 reach 72.4% and 55.2%, respectively. The model has 3.6 M parameters. On a single image, the total latency is 11.3 ms, corresponding to an inference speed of 88.5 FPS. Three random seeds and five-fold cross-validation with a fixed independent test set show consistent gains over the dual-modal baseline. These findings support OAFBC-Net as a promising visual perception method for occluded-fruit detection in orchards, while cross-site and field-robot validation remain necessary for deployment-oriented claims. Full article

This paper proposes a trajectory planning method for a four-degree-of-freedom (4-DOF) spraying robotic arm based on a digital twin platform and an improved soft actor–critic (SAC) algorithm. The method addresses the complex environment of underground shotcrete spraying operations, the high cost and risk of physical robotic arm training, and the difficulty of incorporating spraying process constraints into traditional path planning methods. To enable unified modeling of the virtual prototype, operating scenario, reference trajectory, joint constraints, and spraying process proxy indicators, a digital twin platform for the spraying robotic arm was built using Unity Editor 2022.3.14f1c1.A composite reward function was designed to incorporate trajectory tracking, spray distance, nozzle normal, spraying speed, safety, and motion smoothness, and a prioritized experience replay (PER) mechanism based on double-critic temporal difference (TD) error was introduced to the conventional SAC algorithm. Simulation results show that, under the current digital twin environment and two-dimensional S-shaped reference trajectory, the Improved SAC algorithm reduces trajectory tracking root mean square error (RMSE) from 24.0 ± 2.0 mm to 8.0 ± 0.7 mm, corresponding to a 66.7% reduction compared with standard SAC. In addition, the spray distance error, nozzle normal error, spraying speed error, and motion smoothness index are reduced by 43.5%, 49.1%, 47.3%, and 48.7%, respectively. Full article

Line-driven soft robots possess inherent advantages in terms of cushioning and terrain adaptability, but the controllable deformation design of line-driven structures and its coordination mechanism with the overall robot motion remain insufficiently studied. To fill this gap, this paper designs a line-driven hexapod soft robot that achieves directional bending of flexible legs through unilateral line traction, combined with triangular gait co-motion and ROS-based multi-sensor perception. Integrating leg deformation as part of the motion mechanism enables the robot to achieve straight-line and turning movements while maintaining structural compliance. This paper establishes the mapping relationship between the leg actuation space, configuration space, and task space, constructs a kinematic model, and uses the finite element method to analyze leg deformation and stress distribution. Based on this, a robot prototype is built, and a ROS-based distributed control and perception system is constructed, utilizing LiDAR, camera, and attitude sensor data to achieve SLAM and state monitoring. Experimental results show that the robot can achieve continuous motion with an average speed of 15.32 mm/s and a turning angle of 4.75° in a single gait cycle. The feasibility of line-driven structure control based on unilateral traction was verified, and a reference was provided for the design of soft robots oriented towards environmental perception. Full article

Achieving rapid and accurate obstacle avoidance in complex and dynamic environments remains a significant challenge for robots. To enhance the adaptability and flexibility of humanoid arms for obstacle avoidance, a brain-inspired multi-pathway motion decision-making method is proposed to modulate rational planning and habitual actions of humanoid arms. Firstly, a novel framework integrating both a slow and a fast pathway is designed for motion decision-making tasks. Imitating the rational planning function of the prefrontal cortex, the slow pathway employs an improved planning approach based on Real-Time Rapidly exploring Random Tree Star (RT-RRT^*) to execute deliberate decisions, along with an improvement in planning via the Smart technique and the high-efficiency neighbor searching method. Meanwhile, mimicking the habitual responses governed by the striatum, the fast pathway utilizes an action model trained by Soft Actor-Critic to make quick and habitual motions. The model in the fast pathway is also used to guide the sampling strategy in the slow pathway. Moreover, to facilitate the integration and smooth transition between the two pathways, an emotional neural network is designed as the modulation module with inspiration from the structure and function of the amygdala. Based on body and obstacle information, the network generates emotional signals to modulate the involvement degree of the two pathways before each decision-making process. Experimental results demonstrate that the proposed multi-pathway framework achieves a higher obstacle-avoidance success rate than existing methods while generating motion characteristics that are consistent with certain aspects of human obstacle-avoidance behavior. Full article