Research Article
Networked Multi-robot Collaboration in Cooperative–Competitive Scenarios Under Communication Interference
@INPROCEEDINGS{10.1007/978-3-030-67537-0_36, author={Yaowen Zhang and Dianxi Shi and Yunlong Wu and Yongjun Zhang and Liujing Wang and Fujiang She}, title={Networked Multi-robot Collaboration in Cooperative--Competitive Scenarios Under Communication Interference}, proceedings={Collaborative Computing: Networking, Applications and Worksharing. 16th EAI International Conference, CollaborateCom 2020, Shanghai, China, October 16--18, 2020, Proceedings, Part I}, proceedings_a={COLLABORATECOM}, year={2021}, month={1}, keywords={Electromagnetic and geographic domains Multi-agent reinforcement learning Scenario curriculum learning}, doi={10.1007/978-3-030-67537-0_36} }- Yaowen Zhang
Dianxi Shi
Yunlong Wu
Yongjun Zhang
Liujing Wang
Fujiang She
Year: 2021
Networked Multi-robot Collaboration in Cooperative–Competitive Scenarios Under Communication Interference
COLLABORATECOM
Springer
DOI: 10.1007/978-3-030-67537-0_36
Abstract
In this paper, we consider a scenario where a team of predator robots collaboratively survey an area for preventing the invasion from opponent robots. In this scenario, the predator robots can share the sensing information of the prey robots through wireless communication. In order to constrain the surveillance performance of the predator robots, besides the prey robots, some interfering robots are added to break the communication connectivity between the predator robots. This is a typical “cooperative–competitive” decision problem involving multiple optimization variables from electromagnetic and geographic domains, which makes it challenging to solve. For this problem, we first propose the perception and communication models of the robots. Then, with these models, we formulate the problem and adopt multi-agent reinforcement learning (MARL) to solve it. Furthermore, considering the long training-time cost of traditional MARL, we propose a scenario curriculum learning (SCL) training strategy, which can reduce the computation time and improve the performance by evolving the scenarios from simplicity to complexity. The effectiveness of the proposed method is verified by the analysis and simulation results. The results show that the SCL strategy can reduce the training time by 13%.
