Distributed safe reinforcement learning for multi-robot motion planning

Yang Lu, Yaohua Guo, Guoxiang Zhao, Minghui Zhu

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

2 Scopus citations

Abstract

This paper studies optimal motion planning of multiple mobile robots with collision avoidance. We develop a distributed reinforcement learning algorithm which ensures suboptimal goal reaching and anytime collision avoidance simultaneously. Theoretical results on the convergence of neural network weights, the uniform and ultimate boundedness of system states of the closed-loop system, and anytime collision avoidance are established. Numerical simulations for single integrator and unicycle robots illustrate the effectiveness of our theoretical results.

Original languageEnglish (US)
Title of host publication2021 29th Mediterranean Conference on Control and Automation, MED 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1209-1214
Number of pages6
ISBN (Electronic)9781665422581
DOIs
StatePublished - Jun 22 2021
Event29th Mediterranean Conference on Control and Automation, MED 2021 - Bari, Puglia, Italy
Duration: Jun 22 2021Jun 25 2021

Publication series

Name2021 29th Mediterranean Conference on Control and Automation, MED 2021

Conference

Conference29th Mediterranean Conference on Control and Automation, MED 2021
Country/TerritoryItaly
CityBari, Puglia
Period6/22/216/25/21

All Science Journal Classification (ASJC) codes

  • Decision Sciences (miscellaneous)
  • Engineering (miscellaneous)
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Distributed safe reinforcement learning for multi-robot motion planning'. Together they form a unique fingerprint.

Cite this