Emergence of Motor Synergy in Multi-directional Reaching with Deep Reinforcement Learning

Jihui Han, Jiazheng Chai, Mitsuhiro Hayashibe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this study, we apply Deep Reinforcement Learning for handling full-dimensional 7 degrees of freedom arm reaching, and demonstrate the relations among motion error, energy, and synergy emergence during the learning process, to reveal the mechanism of employing motor synergy. Although synergy information has never been encoded into the reward function, the synergy effect naturally emerges, leading to a similar situation as human motion learning. To the best of our knowledge, this is a pioneer study verifying a concurrent relation between the error-energy index and synergy development in DRL for multi-directional reaching tasks. In addition, our proposed feedback-augmented DRL controller shows better capability over DRL only in terms of error-energy index.

Original languageEnglish
Title of host publication2021 IEEE/SICE International Symposium on System Integration, SII 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages78-82
Number of pages5
ISBN (Electronic)9781728176581
DOIs
Publication statusPublished - 2021 Jan 11
Event2021 IEEE/SICE International Symposium on System Integration, SII 2021 - Virtual, Iwaki, Fukushima, Japan
Duration: 2021 Jan 112021 Jan 14

Publication series

Name2021 IEEE/SICE International Symposium on System Integration, SII 2021

Conference

Conference2021 IEEE/SICE International Symposium on System Integration, SII 2021
Country/TerritoryJapan
CityVirtual, Iwaki, Fukushima
Period21/1/1121/1/14

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems
  • Information Systems and Management
  • Control and Systems Engineering
  • Industrial and Manufacturing Engineering
  • Mechanical Engineering

Fingerprint

Dive into the research topics of 'Emergence of Motor Synergy in Multi-directional Reaching with Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this