Multi-vehicle Flocking Control with Deep Deterministic Policy Gradient Method

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

37 Scopus citations

Abstract

Flocking control has been studied extensively along with the wide application of multi-vehicle systems. In this paper the Multi-vehicles System (MVS) flocking control with collision avoidance and communication preserving is considered based on the deep reinforcement learning framework. Specifically the deep deterministic policy gradient (DDPG) with centralized training and distributed execution process is implemented to obtain the flocking control policy. First, to avoid the dynamically changed observation of state, a three layers tensor based representation of the observation is used so that the state remains constant although the observation dimension is changing. A reward function is designed to guide the way-points tracking, collision avoidance and communication preserving. The reward function is augmented by introducing the local reward function of neighbors. Finally, a centralized training process which trains the shared policy based on common training set among all agents. The proposed method is tested under simulated scenarios with different setup.

Original languageEnglish
Title of host publication2018 IEEE 14th International Conference on Control and Automation, ICCA 2018
PublisherIEEE Computer Society
Pages306-311
Number of pages6
ISBN (Print)9781538660898
DOIs
StatePublished - 21 Aug 2018
Event14th IEEE International Conference on Control and Automation, ICCA 2018 - Anchorage, United States
Duration: 12 Jun 201815 Jun 2018

Publication series

NameIEEE International Conference on Control and Automation, ICCA
Volume2018-June
ISSN (Print)1948-3449
ISSN (Electronic)1948-3457

Conference

Conference14th IEEE International Conference on Control and Automation, ICCA 2018
Country/TerritoryUnited States
CityAnchorage
Period12/06/1815/06/18

Fingerprint

Dive into the research topics of 'Multi-vehicle Flocking Control with Deep Deterministic Policy Gradient Method'. Together they form a unique fingerprint.

Cite this