Robot intelligent trajectory planning based on PCM guided reinforcement learning

Xiang Teng, Jian Fu, Cong Li, Zhaojie Ju

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

171 Downloads (Pure)

Abstract

Reinforcement Learning (RL) was successfully applied in multi-degree-of-freedoms robot to acquire motor skills, however, it hardly ever consider each joints’ relationship, or just think about the linear relationship between them. In order to find the nonlinear relationship between each degrees of freedom (DOFs), we propose a Pseudo Covariance Matrix (PCM) to guide reinforcement learning for motor skill acquisition. Specifically it combined Path Integral Policy Improvement (PI2) with Kernel Canonical Correlation Analysis (KCCA), where KCCA is used to obtain the PCM in high dimensional space and record it as the heuristic information to search an optimal/sub-optimal strategy. The experiments based on robots (SCARA and UR5) demonstrate the new method is feasible and effective.
Original languageEnglish
Title of host publicationIntelligent Robotics and Applications
Subtitle of host publication12th International Conference, ICIRA 2019, Shenyang, China, August 8–11, 2019, Proceedings, Part VI
EditorsHaibin Yu, Jinguo Liu, Lianqing Liu, Zhaojie Ju, Yuwang Liu, Dalin Zhou
PublisherSpringer
Chapter30
Pages342-355
Number of pages14
ISBN (Electronic)978-3-030-27529-7
ISBN (Print)978-3-030-27528-0
DOIs
Publication statusPublished - 6 Aug 2019
Event12th International Conference on Intelligent Robotics and Applications - Shenyang, China
Duration: 8 Aug 201911 Aug 2019

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume11745
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameLecture Notes in Artificial Intelligence
PublisherSpringer
Volume11745
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference12th International Conference on Intelligent Robotics and Applications
Abbreviated titleICIRA 2019
Country/TerritoryChina
CityShenyang
Period8/08/1911/08/19

Keywords

  • trajectory planning
  • learning from demonstration
  • Kernel canonical correlation analysis
  • path integral policy improvement
  • pseudo covariance matrix

Fingerprint

Dive into the research topics of 'Robot intelligent trajectory planning based on PCM guided reinforcement learning'. Together they form a unique fingerprint.

Cite this