Towards Multi-finger Dexterous Hand Mechanics Control and Tactile Feedback

Abstract：The ever-changing demands of industrial automation and space technology have promoted the rapid development of robotics. Traditional robotic end effectors are difficult to perform smart operations, so there is an urgent need for a robotic hand to perform complex operations instead of humans. In this article, we will focus our attention on mechanical control and haptic feedback. Mechanical control and haptic feedback are necessary conditions for the stable and accurate grasping of multi-finger dexterous hands. Tactile perception can provide stiffness and temperature to multi-finger dexterous hands. Important information makes the function of the dexterous hand more perfect. This article introduces the kinematics and dynamics of dexterous hand fingers, as well as the kinematics and dynamics solving equations, then reviews the current sensors and various control driving methods used in dexterous hands, discusses drive control, and compares each method Pros and cons. Finally, the future development of dexterous hands is predicted.

REVIEW ON DEEP LEARNING APPROACHES TO THE CONTROL OF PROSTHETIC HANDS WITH ELECTROMYOGRAPHY SIGNALS

Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. Several efforts have been carried out to enhance dexterous hand prosthesis control by impaired individuals. However, the control robustness offered by scientic research is still not sufcient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. This paper reviews various papers on deep learning approaches to the control of prosthetic hands with EMG signals and made a comparison on their accuracy.

The adaptive neural network sliding mode control for angle/force tracking of the dexterous hand

In order to achieve high precision control of the dexterous hand, an adaptive neural network sliding mode control algorithm based on the U-K (Udwadia-Kalaba) equation is proposed. Firstly, based on the U-K equation and considering the ideal and non-ideal constrained force at each link of the dexterous hand, the detailed dynamic equation is derived. Secondly, considering the uncertainty of the non-ideal constrained force (mainly the friction force on each link of the dexterous hand) and the chattering phenomenon when using sliding mode control alone, the adaptive neural network and the sliding mode control algorithm are combined to realize the high-precision tracking and estimation of each link angle trajectory and the non-ideal constrained force. Finally, in order to verify the correctness and rationality of the proposed algorithm, the 3-DOF spatial dexterous hand is taken as the simulated object. The simulation results show that the tracking and estimation errors of each link angle and the non-ideal constrained force are 10−2 order of magnitude.

Using Tactile Sensing to Improve the Sample Efficiency and Performance of Deep Deterministic Policy Gradients for Simulated In-Hand Manipulation Tasks

Deep Reinforcement Learning techniques demonstrate advances in the domain of robotics. One of the limiting factors is a large number of interaction samples usually required for training in simulated and real-world environments. In this work, we demonstrate for a set of simulated dexterous in-hand object manipulation tasks that tactile information can substantially increase sample efficiency for training (by up to more than threefold). We also observe an improvement in performance (up to 46%) after adding tactile information. To examine the role of tactile-sensor parameters in these improvements, we included experiments with varied sensor-measurement accuracy (ground truth continuous values, noisy continuous values, Boolean values), and varied spatial resolution of the tactile sensors (927 sensors, 92 sensors, and 16 pooled sensor areas in the hand). To facilitate further studies and comparisons, we make these touch-sensor extensions available as a part of the OpenAI Gym Shadow-Dexterous-Hand robotics environments.

Novel design method for multi-configuration dexterous hand based on a gesture primitives analysis

Purpose This paper aims to propose a novel method based on a gesture primitives analysis of human daily grasping tasks for designing dexterous hands with various grasping and in-hand manipulation abilities, which simplifies the complex and redundant humanoid five-finger hand system. Design/methodology/approach First, the authors developed the fingers and the joint configuration with a series of gesture primitives configurations and the modular virtual finger scheme, refined from the daily work gesture library by principal component analysis. Then, the authors optimized the joint degree-of-freedom configuration with the bionic design analysis of the anatomy, and the authors optimized the dexterity workspace. Furthermore, the adaptive fingertip and routing structure were designed based on the dexterous manipulation theory. Finally, the effectiveness of the design method was experimentally validated. Findings A novel lightweight three-finger and nine-degree-of-freedom dexterous hand with force/position perception was designed. The proposed routing structure was shown to have the capability of mapping the relationship between the joint space and actuator space. The adaptive fingertip with an embedded force sensor can effectively increase the robustness of the grasping operation. Moreover, the dexterous hand can grasp various objects in different configurations and perform in-hand manipulation dexterously. Originality/value The dexterous hand design developed in this study is less complex and performs better in dexterous manipulation than previous designs.