Multi-agent system (MAS) has become a distributed artificial intelligence (DAI) research hotspot, and has gained wide-ranging research in robotics, artificial intelligence, and knowledge acquisition. The RoboCup Rescue Simulation (RCRS) system is a typical MAS platform for studying multi-agent coordination. In the RCRS, the rescue agent faces an unknown disaster environment, real-time dynamic changes, and limited resources for communication. This paper focuses on the cooperative task planning problem of multiple fire protection agents based on reinforcement learning, and uses the simulation platform to conduct experiments using the Proximal Policy Optimization (PPO) algorithm. Multiple fire-fighting agents can learn cooperative fire-fighting strategy well after training for certain episodes.
Multi-agent Task Coordination Method Based on RCRS
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 : 254 ; 2582-2593
2022-03-18
12 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Task-oriented control and coordination of multi-agent systems under varying constraints
BASE | 2021
|