Learning Grasp Configuration Through Object-Specific Hand Primitives for Posture Planning of Anthropomorphic Hands

The proposal of postural synergy theory has provided a new approach to solve the problem of controlling anthropomorphic hands with multiple degrees of freedom. However, generating the grasp configuration for new tasks in this context remains challenging. This study proposes a method to learn grasp configuration according to the shape of the object by using postural synergy theory. By referring to past research, an experimental paradigm is first designed that enables the grasping of 50 typical objects in grasping and operational tasks. The angles of the finger joints of 10 subjects were then recorded when performing these tasks. Following this, four hand primitives were extracted by using principal component analysis, and a low-dimensional synergy subspace was established. The problem of planning the trajectories of the joints was thus transformed into that of determining the synergy input for trajectory planning in low-dimensional space. The average synergy inputs for the trajectories of each task were obtained through the Gaussian mixture regression, and several Gaussian processes were trained to infer the inputs trajectories of a given shape descriptor for similar tasks. Finally, the feasibility of the proposed method was verified by simulations involving the generation of grasp configurations for a prosthetic hand control. The error in the reconstructed posture was compared with those obtained by using postural synergies in past work. The results show that the proposed method can realize movements similar to those of the human hand during grasping actions, and its range of use can be extended from simple grasping tasks to complex operational tasks.

Adaptive SNN for Anthropomorphic Finger Control

Anthropomorphic hands that mimic the smoothness of human hand motions should be controlled by artificial units of high biological plausibility. Adaptability is among the characteristics of such control units, which provides the anthropomorphic hand with the ability to learn motions. This paper presents a simple structure of an adaptive spiking neural network implemented in analogue hardware that can be trained using Hebbian learning mechanisms to rotate the metacarpophalangeal joint of a robotic finger towards targeted angle intervals. Being bioinspired, the spiking neural network drives actuators made of shape memory alloy and receives feedback from neuromorphic sensors that convert the joint rotation angle and compression force into the spiking frequency. The adaptive SNN activates independent neural paths that correspond to angle intervals and learns in which of these intervals the rotation the finger rotation is stopped by an external force. Learning occurs when angle-specific neural paths are stimulated concurrently with the supraliminar stimulus that activates all the neurons that inhibit the SNN output stopping the finger. The results showed that after learning, the finger stopped in the angle interval in which the angle-specific neural path was active, without the activation of the supraliminar stimulus. The proposed concept can be used to implement control units for anthropomorphic robots that are able to learn motions unsupervised, based on principles of high biological plausibility.

A Workspace-Analysis-Based Genetic Algorithm for Solving Inverse Kinematics of a Multi-Fingered Anthropomorphic Hand

Although the solution of inverse kinematics for a serial redundant manipulator has been widely researched, many algorithms still seem limited in dealing with complex geometries, including multi-finger anthropomorphic hands. In this paper, the inverse kinematic problems of multiple fingers are an aggregate problem when the target points of fingers are given. The fingers are concatenated to the same wrist and the objective is to find a solution for the wrist and two fingers simultaneously. To achieve this goal, a modified immigration genetic algorithm based on workspace analysis is developed and validated. To reduce unnecessary computation of the immigration genetic algorithm, which arises from an inappropriate inverse kinematic request, a database of the two fingers’ workspace is generated using the Monte Carlo method to examine the feasibility of inverse kinematic request. Furthermore, the estimation algorithm provides an optimal set of wrist angles for the immigration genetic algorithm to complete the remaining computation. The results reveal that the algorithm can be terminated immediately even when the inverse kinematic request is out of the workspace. In addition, a distribution of population in each generation illustrates that the optimized wrist angles provide a better initial condition, which significantly improves the convergence of the immigration genetic algorithm.

Anthropomorphism Indexes of the Kinematic Chain for Artificial Hands

Anthropomorphic hands have received increasing research interest in the fields of robotics and prosthetics. But it is not yet clear how to evaluate their anthropomorphism. Similarity in the kinematic chain is essential to achieve both functionality and cosmesis. A few previous works have addressed the definition of anthropomorphism indexes, although they have some limitations in its definition. In this study, three different anthropomorphism indexes have been defined to compare the kinematic chain of artificial hands with that of the human hand. These indexes are based on the comparison of: (1) the parameters of the kinematic chain (dimensions, type of joints, orientations and ranges of motion), (2) the reachable workspace, and (3) common grasping postures. Five artificial hands with different degrees of anthropomorphism have been compared using the three Anthropomorphism Indexes of the Kinematic Chain (AIKC). The results show a high correlation between the first and third AIKC for the hands compared. The second AIKC presents much lower values than the other two, although they are higher for hands that combine abduction/adduction and flexion/extension movements in the kinematic chain of each finger. These indexes can be useful during the initial stage of designing artificial hands or evaluating their anthropomorphism.

Human-Inspired Representation of Object-Specific Grasps for Anthropomorphic Hands

The human hand is a complex, highly-articulated system, which has been the source of inspiration in designing humanoid robotic and prosthetic hands. Understanding the functionality of the human hand is crucial for the design, efficient control and transfer of human versatility and dexterity to such anthropomorphic robotic hands. Although research in this area has made significant advances, the synthesis of grasp configurations, based on observed human grasping data, is still an unsolved and challenging task. In this work we derive a novel, constrained autoencoder model, that encodes human grasping data in a compact representation. This representation encodes both the grasp type in a three-dimensional latent space and the object size as an explicit parameter constraint allowing the direct synthesis of object-specific grasps. We train the model on 2250 grasps generated by 15 subjects using 35 diverse objects from the KIT and YCB object sets. In the evaluation we show that the synthesized grasp configurations are human-like and have a high probability of success under pose uncertainty.

Vision-based grasp learning of an anthropomorphic hand-arm system in a synergy-based control framework

In this work, the problem of grasping novel objects with an anthropomorphic hand-arm robotic system is considered. In particular, an algorithm for learning stable grasps of unknown objects has been developed based on an object shape classification and on the extraction of some associated geometric features. Different concepts, coming from fields such as machine learning, computer vision, and robot control, have been integrated together in a modular framework to achieve a flexible solution suitable for different applications. The results presented in this work confirm that the combination of learning from demonstration and reinforcement learning can be an interesting solution for complex tasks, such as grasping with anthropomorphic hands. The imitation learning provides the robot with a good base to start the learning process that improves its abilities through trial and error. The learning process occurs in a reduced dimension subspace learned upstream from human observation during typical grasping tasks. Furthermore, the integration of a synergy-based control module allows reducing the number of trials owing to the synergistic approach.