Unmanned aerial vehicle (UAV) plays an increasingly important role both in civil and military fields. As a typical mission, area coverage search is a primary measure for reconnaissance and surveillance of unknown areas. Due to the limited information about the mission area, UAV needs adaptiveness to the dynamic changes of the area and makes decisions based on local observation. It puts higher demands on the response speed of UAV, and traditional planning methods are tough to be directly applied. The problem becomes more noticeable for multiple UAV because of the heterogeneous function and large scale, and new solutions are urgently required. In this paper, the feasibility of reinforcement learning (RL) for performing area coverage search is explored, and an environment is designed for RL training and evaluation. Simulation results show that multiple UAV can cooperate and perform the mission with pretty high coverage.
Design of Reinforcement Learning Environment for Multiple UAV Area Coverage Search
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Kapitel : 265 ; 2700-2711
18.03.2022
12 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Design of Reinforcement Learning Environment for Multiple UAV Area Coverage Search
British Library Conference Proceedings | 2022
|