Title :
The architecture design of the multirobot team formation
Author :
Xing-Ce, Wang ; Guo-chang, Gu ; Ru-Bo, Zhang ; Song Mei-ping
Author_Institution :
Coll. of Comput. Sci. & Technol., Harbin Eng. Univ.
Abstract :
The layered control architecture is designed for the need of the multirobot intelligent team formation. There are three levels: the cooperation task level, the coordination behavior level and the action planning level. The cooperation task level is using the potential grid method, which improves the safety of the path and reduces the calculation complexity. The coordination behavior level is using the reinforcement learning which strengthen the robots´ intelligence. The action planning level is using the fuzzy planning methods to realize the action matching. The communication model transfer the message in different level. This architecture shows not only the independence and the intelligence of the single robot but also the cooperation and the coordination among the robots. In each level, the task is distributed reasonably and clearly. At last the feasibility of the architecture is verified further in the simulation of the experiment. The expansibility of the architecture is good and the architecture can be used in the similar system
Keywords :
fuzzy systems; intelligent robots; learning (artificial intelligence); multi-robot systems; planning (artificial intelligence); action matching; action planning level; control architecture design; cooperation task level; coordination behavior level; fuzzy planning; intelligent robot; multiagent system; multirobot intelligent team formation; potential grid method; reinforcement learning; Computer architecture; Computer science; Design automation; Design engineering; Educational institutions; Intelligent robots; Laboratories; Multirobot systems; Robot kinematics; Robotics and automation; architecture; multiagent system; multirobot; plan;
Conference_Titel :
Robotics and Biomimetics, 2004. ROBIO 2004. IEEE International Conference on
Conference_Location :
Shenyang
Print_ISBN :
0-7803-8614-8
DOI :
10.1109/ROBIO.2004.1521857