Bionic Hand Motion Control Method Based on Imitation of Human Hand Movements and Reinforcement Learning

扫码查看

原文链接

NETL
NSTL
万方数据

外文摘要：Bionic hands are promising devices for assisting individuals with hand disabilities in rehabilitation robotics.Controlled primarily by bioelectrical signals such as myoelectricity and EEG,these hands can compensate for lost hand functions.However,developing model-based controllers for bionic hands is challenging and time-consuming due to varying control parameters and unknown application environments.To address these challenges,we propose a model-free approach using reinforcement learning(RL)for designing bionic hand controllers.Our method involves mimicking real human hand motion with the bionic hand and employing a human hand motion decomposition technique to learn complex motions from simpler ones.This approach significantly reduces the training time required.By utilizing real human hand motion data,we design a multidimensional sampling proximal policy optimization(PPO)algorithm that enables efficient motion control of the bionic hand.To validate the effectiveness of our approach,we compare it against advanced baseline methods.The results demonstrate the quick learning capabilities and high control success rate of our method.

外文关键词：

Bionic handReinforcement learningMotion decompositionMultidimensional sampling PPO algorithm

作者：

Jibo Bai、Baojiang Li、Xichao Wang、Haiyan Wang、Yuting Guo

展开 >

作者单位：

The School of Electrical Engineering,Shanghai DianJi University,Shanghai 201306,China

基金：

Su Yan YuanShanghai DianJi Universitysci-entific research start-up fund project of Shanghai DianJi Universitysci-entific research start-up fund project of Shanghai DianJi University

项目编号：

Su Yan Yuan[2019]107Sciencetechnology[2020]79of Shanghai DianJi University

出版年：

2024

DOI：

10.1007/s42235-023-00472-5

仿生工程学报(英文版)

吉林大学

仿生工程学报(英文版)

CSTPCDEI

影响因子：0.837

ISSN：1672-6529

年,卷(期)：2024.21(2)

参考文献量46