Skip to main navigation Skip to search Skip to main content

Multi-UAV Automatic Dynamic Obstacle Avoidance with Experience-shared A2C

  • Harbin Institute of Technology Shenzhen

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

Abstract

With the increasing usage of UAV in reconnaissance, agriculture, logistics and entertainment, it's necessary for multi-UAV to automatically avoid the dynamic obstacles in order to ensure the safety of drones and livings in environment. The automatic obstacle avoidance is a classic multiple agent decision-making problem. Traditional algorithms, limited in the method of state classification and policy selection, are not applicable in such a complex scene including randomly dynamic scene and cooperative decision-making. In this paper, Advantaged Actor-Critic Algorithm is introduced to train multi-UAVs to automatically avoid obstacles and optimize avoidance decision-making model. Deep Q Learning, Actor-Critic (AC) and Advantaged Actor-Critic (A2C) algorithm are compared. And to further maximize the performance, we specifically improved A2C algorithm towards the multi-UAV scene by sharing experiences between UAVs to expedite the training process. Our experimental result shows our Experience-shared A2C (ES-A2C) algorithm leads to a higher performance and a shorter training period.

Original languageEnglish
Title of host publication2019 International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2019
PublisherIEEE Computer Society
Pages330-335
Number of pages6
ISBN (Electronic)9781728133164
DOIs
StatePublished - Oct 2019
Externally publishedYes
Event15th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2019 - Barcelona, Spain
Duration: 21 Oct 201923 Oct 2019

Publication series

NameInternational Conference on Wireless and Mobile Computing, Networking and Communications
Volume2019-October
ISSN (Print)2161-9646
ISSN (Electronic)2161-9654

Conference

Conference15th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2019
Country/TerritorySpain
CityBarcelona
Period21/10/1923/10/19

Keywords

  • advantage actor-critic
  • moving obstacles avoidance
  • multi-Agent decision
  • multi-UAV
  • shared experience

Fingerprint

Dive into the research topics of 'Multi-UAV Automatic Dynamic Obstacle Avoidance with Experience-shared A2C'. Together they form a unique fingerprint.

Cite this