Han Ding’s research while affiliated with Shanghai Jiao Tong University and other places

In nature, organisms have evolved diverse grasping mechanisms to perform vital functions such as hunting and self-defence. These time-tested biological structures, including the arms of octopuses and the trunks of elephants, offer valuable inspiration for designing multimodal soft grippers that can tackle diverse tasks in various environments. Similar to their biological counterparts, these grippers must adapt to dynamic working conditions to enhance their performance. This adaptation process involves multiple factors, including grasping mechanisms, structural design, materials, and application scenarios, with biomimetic strategies offering numerous innovative examples. Despite the significant potential of bio-inspired designs, it lacks comprehensive reviews that explore how these strategies can enhance the development of multimodal soft grippers. This review seeks to address this gap by providing a systematic review of how bioinspired approaches contribute to the advancement of multimodal grippers. It focuses on coupling strategies, integration methods, performance improvements, and application scenarios. Finally, the review explores how future biomimetic insights could address current challenges and further improve the functionality of multimodal grippers.

Multi‐target inverse design, which involves designing multiple targets with different optimization objectives, becomes a key focus in mechanical metamaterials (MMs) design. Specifically, many practical applications impose varying requirements for different sections. For instance, the heel of a sole demands to provide support, while the arch should be comfortable, adequately supportive, and lightweight. However, existing approaches, such as topology optimization, typically focus on optimizing MMs for specific objectives, e.g., high strength. Worse, these approaches are often inaccurate and time‐consuming, even just for a single target. In this work, based on graded triply periodic minimal surface (TPMS) architectures, a machine‐learning‐powered approach is proposed for rapid, accurate, and multi‐target MM inverse design by employing a six‐parallel pipeline network architecture and utilizing deep networks to map structural parameters to mechanical curves. The most suitable results are selected based on the target curves and other performance requirements, which can be derived from the structural parameters. The approach achieves a normalized root‐mean‐square error (NRMSE) of 2.49% on the test dataset and outputs corresponding design parameters within seconds, simultaneously meeting multiple targets. Finally, such an approach is demonstrated in designing soles suitable for various gait scenarios and foot deformity treatments.

Learning grinding skills from human craftsmen via imitation learning has become a key research topic in robotic machining. Due to their strong generalization and robustness to external disturbances, Dynamical Movement Primitives (DMPs) offer a promising approach for robotic grinding skill learning. However, directly applying DMPs to grinding tasks faces challenges, such as low orientation accuracy, unsynchronized position-orientation-force, and limited generalization for surface trajectories. To address these issues, this paper proposes a robotic grinding skill learning method based on geodesic length DMPs (Geo-DMPs). First, a normalized 2D weighted Gaussian kernel and intrinsic mean clustering algorithm are developed to extract geometric features from multiple demonstrations. Then, an orientation manifold distance metric removes the time dependency in traditional orientation DMPs, enabling accurate orientation learning via Geo-DMPs. A synchronization encoding framework is further proposed to jointly model position, orientation, and force using a geodesic length-based phase function. This framework enables robotic grinding actions to be generated between any two surface points. Experiments on robotic chamfer grinding and free-form surface grinding validate that the proposed method achieves high geometric accuracy and generalization in skill encoding and generation. To our knowledge, this is the first attempt to use DMPs for jointly learning and generating grinding skills in position, orientation, and force on model-free surfaces, offering a novel path for robotic grinding.

A neural interface translating human motor intentions into control commands for prosthetic hands helps amputees restore upper limb function. However, commercial neural interfaces with a few surface electromyography (sEMG) sensors are constrained by limitations such as low spatiotemporal resolution, limited number of recognizable hand gestures, and sensitivity to arm positions. Multimodal sensor fusion presents a viable approach to overcome these challenges, offering improved accuracy, versatility, and robustness in gesture recognition. In this study, we developed a wearable multi-sensor fusion system compact enough to be integrated into a prosthetic socket. The fusion probe had dimensions of 38.5×20.5×13.5 mm, and the signal acquisition/processing device measured 50×40×15 mm. The fusion system incorporated three types of sensors, capturing muscle movements from morphology (A-mode ultrasound), electrophysiology (sEMG), and kinematics (inertial measurement unit, IMU). Gesture recognition experiments were conducted with 20 subjects, including both healthy individuals and amputees, achieving classification accuracies of 94.8±1.1% and 96.9±1.3% for six common gestures, respectively. Furthermore, we proposed a new control strategy based on the characteristics of sensor fusion to enhance the stability of online gesture classification. Practical online testing with amputees wearing prostheses indicated that the designed fusion system had high classification accuracy and stability during gesture recognition. These results demonstrated that the wearable multi-sensor fusion system is well-suited for integration into prostheses, offering a robust solution for amputees’ practical use.

Skeletal muscles are essential parts of the human motor system and are mainly regulated by motor units (MUs) through the nervous system. As a widely used noninvasive measurement of MUs, surface EMG cannot obtain in-depth spatial information on MUs. Ultrafast ultrasound (UUS) can measure the mechanical response of MUs from muscle morphology with image sequences. This research proposed a blind source separation method with enhanced interpretability for decoding ultrasound image sequences to obtain the mechanical response of MUs. In particular, the spatiotemporal data were decomposed using non-negative matrix factorization (NMF). Then, the spatial components’ multiple probability density functions were obtained using a parametric self-fitting function. The proposed algorithm, called NMF-stICA, was validated on ten groups of computational simulation datasets. The accuracies of the obtained spatial and temporal components were 87.26% ± 2.18% and 85.13% ± 1.83%, respectively. Further, a dynamic ultrasound phantom experiment was performed, and all the potential spatial components were correctly decoded. Additionally, isometric contraction human experiments were conducted on the biceps muscle of eight subjects with simultaneous acquisition of UUS and intramuscular electromyography (iEMG). The results showed that the rate of agreement was 58.71%, comparing the decoded components with the firing pattern of iEMG. The proposed decoding method can get precise spatial position and the firing pattern of the MUs in the skeletal muscle. This might help to study the neuromechanical properties of MUs and localize disease in specific muscle regions.

This study presents a spiral-based complete coverage strategy for ball-end milling on freeform surfaces, utilizing conformal slit mapping to generate milling trajectories that are more compact, smoother, and evenly distributed when machining 2D cavities with islands. This approach, an upgrade from traditional methods, extends the original algorithm to effectively address 3D perforated surface milling. Unlike conventional algorithms, the method embeds a continuous spiral trajectory within perforated surfaces without requiring cellular decomposition or additional boundaries. The proposed method addresses three primary challenges, including modifying conformal slit mapping for mesh surfaces, maintaining uniform scallop height between adjacent spiral trajectories, and optimizing the mapped origin point to ensure uniform scallop height distribution. To overcome these challenges, surface flattening techniques are incorporated into the original approach to accommodate mesh surfaces effectively. Tool path spacing is then optimized using a binary search strategy to regulate scallop height. A functional energy metric associated with scallop height uniformity is introduced for rapid evaluation of points mapped to the origin, with the minimum functional energy determined through perturbation techniques. The optimal placement of this point is identified using a modified gradient descent approach applied to the energy function. Validation on intricate surfaces, including low-quality and high-genus meshes, verifies the robustness of the algorithm. Surface milling experiments comparing this method with conventional techniques indicate a 15.63% improvement in scallop height uniformity while reducing machining time, average spindle impact, and spindle impact variance by up to 7.36%, 27.79%, and 55.98%, respectively.

Multi-fingered dexterous hands hold significant potential for addressing manipulation tasks in intelligent manufacturing, owing to their inherent anthropomorphic flexibility and rich perceptual capabilities. However, the functionality of dexterous hands in intelligent manufacturing remains unclear due to current technological limitations. This paper provides a review of the current research status of dexterous hands for manipulation tasks, with a specific focus on key technologies related to structure, perception, grasping, and manipulation skills. Furthermore, this review also highlights potential applications of dexterous hands in intelligent manufacturing, including manufacturing in narrow spaces, bin-picking, and in-situ manufacturing. We also discuss the research challenges for the wide adoption of dexterous hands. This review offers a comprehensive analysis of dexterous hands from a manufacturing perspective, contributing to future technological breakthroughs and the advancement of new-generation intelligent manufacturing.