Design of intelligent multirobot teams control architecture and its performance analysis
Xingce Wang, Meiping Song · Harbin Gongcheng Daxue Xuebao/Journal of Harbin Engineering University · 2005
AbstrcatA layered control architecture was designed for the formation of intelligent multirobot team. There were three levels:the cooperation task level, the coordination behavior level and the action planning level.The cooperation task level used a potential grid method to improve the safety of the path and reduce calculation complexity. The coordination behavior level used reinforcement learning to strengthen the robots' intelligence. The action planning level used fuzzy planning methods to realize the action matching.A communication model transfers messages between levels. This architecture not only shows the independence and the intelligence of a single robot but also the cooperation and the coordination among robots. In each level, the task was distributed reasonably and clearly. At last, the feasibility of the architecture was verified further through simulation.The expandibility of the architecture is good and the architecture can be used in similar systems.