Dexterous prosthetic hand is an essential rehabilitation assistant device to improve the life quality of amputee patients. Despite the continuous emergence of commercial prostheses and laboratory prototypes, the rejection rate remains high caused by the poor neural interaction performance and excessive cognitive burden, especially for the usage of upper-arm prostheses controlled by above-the-elbow amputation stump. The progress in artificial perception, bidirectional neural interface and share control indicates a great potential to improve the manipulation efficiency of upper-limb prostheses. In this review, a comprehensive analysis of human-in-the-loop shared control studies is presented to provide researchers with a systematic technical route in upper-limb prostheses control. The latest avenues of research concerning myoelectric control, sensory feedback, perception, autonomous motion planning of multiple degree of freedom elbow-wrist, and share control are overviewed and discussed. The comprehensive assessments show that there remains inadequate technologies to achieve an anthropomorphic and efficient unified elbow-wrist-hand prostheses manipulation. By delineating the current shortcomings, the outcomes of this work highlight future investigation in the field of intuitive motion control, feedback of proprioception/touch and the natural interaction between human intent and machine autonomy.

Anthropomorphic robotic hands have been widely investigated to dexterously manipulate objects because of their anatomical similarity to the human hand. However, the large dimension of configuration space challenges the real-time performance of existing grasp planning methods and drastically limits the application of anthropomorphic hands. In this letter, we propose a fast force-closure grasp synthesis (FFCGS) method for the anthropomorphic hand to efficiently grasp unknown objects. The FFCGS is implemented by using a signed distance field (SDF) as input. Firstly, a network that samples feasible 6D wrist poses is trained in an end-to-end fashion to reduce the dimension of search space. Furthermore, a fast optimization algorithm is presented to find finger configurations for force-closure precision grasp based on the differentiable Q-distance metric. We validate our method in both a simulated and a real-world environment. Experiment results show that the proposed FFCGS achieves a significantly improved performance in terms of time efficiency (5 times faster), grasp quality metrics, and success rate (5%–10% improvement) over benchmark methods. The outcomes of this study have great significance in promoting the motion planning of robot hand-arm systems and upper-limb prostheses.

Grasping multiple affordance parts and from arbitrary directions for complex shaped objects still remains a challenging problem for prosthetic hand with wrist. We propose a semi-autonomous control method that uses only an integrated in-hand camera to predict the final grasping part on an object as the hand approaches it and obtain the appropriate wrist joint angles and preshape type. We collect approach-grasp motion sequences from human experts to construct a motion prior field (MPF) and derive the prediction model MPFNet by behavior cloning. With noise augmentation and a hybrid regression-categorization policy training, our prediction model gets less than 2 cm predicting deviation under a small number (15) of demonstrations for each object. We apply our control method to a prosthetic hand with a 2 $^{\circ }$ -of-freedom (DoF) wrist, enabling it to grasp multiple parts of complex shaped objects and remain robust under the position and orientation variation. Compared to state-of-the-art myoelectric control and semi-autonomous control methods, respectively, our method improves 65.4%/26.3% in grasp success rate, 40.4%/26.3% in control time, and 35.6%/27.8% in error distance. Furthermore, our method is adaptable to different objects in the same category.

Shared control of bionic robot hands has recently attracted much research attention. However, few studies have performed predictive analysis for grasp pose, which is vital for the pre-shape planning of robotic wrists and hands. Aiming at shared control of dexterous hand grasp planning, this paper proposes a framework for grasp pose prediction based on the motion prior field. To map the hand–object pose to the final grasp pose, an object-centered motion prior field is established to learn the prediction model. The results of motion capture reconstruction show that, with the input of a 7-dimensional pose and cluster manifolds of dimension 100, the model performs best in terms of prediction accuracy (90.2%) and error distance (1.27 cm) in the sequence. The model makes correct predictions in the first 50% of the sequence during hand approach to the object. The outcomes of this study enable prediction of the grasp pose in advance as the hand approaches the object, which is very important for enabling the shared control of bionic and prosthetic hands.

In this work, we tackle the challenge of generating human-like grasp motions on humanoid robots—a task that remains difficult for traditional methods due to the complexity of modeling human arm joint preferences and synthesizing dexterous grasps for novel objects. Our approach, termed anthropomorphic grasp motion planning (AGMP), integrates deep learning models by leveraging on human demonstrations and annotated grasps. Specifically, we learn a Riemannian metric in the joint space from human data to capture the directional preferences of upper limb movements, and formulate a quadratic Riemannian distance function as the optimization objective. To assess the grasp quality, we propose a dexterous grasp evaluator that accepts candidate grasps and object as inputs, returning scalar costs. By exploiting the differentiable nature of these networks, we iteratively solve the problem through approximations to both the learned Riemannian distance and the grasp constraint. Simulation results demonstrate that our approach reduces trajectory errors by up to 40% compared to the minimum-jerk model. Moreover, our approach improves the success rate by 11% and significantly reduces planning time relative to existing methods. We further validate our method on a humanoid robot prototype in realworld experiments, achieving a 73.3% success rate.

In humanoid robot manipulation imitation learning, arm and tool synergies are required to accomplish tasks. However, the existence of arm and tool shape variations within the demonstrators and between the demonstrator-robot impacts the generalization performance. This paper models the arm and tool as an extended kinematic chain, taking the elbow, wrist, tool end, and tool orientation as keypoints. We propose a humanoid arm manipulation generalization method based on keypoints synergetic guidance, including Postural and Movement Synergy. Using principal component dimensionality reduction and feature space optimization, Postural Synergy obtains the task's start and end positions corresponding to the new target under the new kinematic chain shape. Movement Synergy generates keypoints' trajectories adapted to the new kinematic chain through a dynamical system with coupling terms, and then obtains robot joint trajectories by optimization-based inverse kinematics. Experiments are conducted under shape variations of both the arms and tools. The results indicate that our method significantly reduces keypoints' errors in Postural Synergy compared to Tool-Centric, Motion Retargeting and Cartesian space optimization methods. In Movement Synergy, our method generates dynamically similar motions using coupling terms. Real robot generalization results show that our method is able to improve the task success rate remarkably while mimicking human motion at the same time.