中文摘要：

本文提出了一种基于改进学习分类器的多机器人混合分层体系结构。体系协作规划层中的人工势场栅格法、协调规划层的学习分类器广播操作及行为控制层的多机器人DSP控制系统，易于实现多机器人间的通信联络及系统的扩充，提高了整个多机器人系统的实用性、实时性和可靠性。

英文摘要：

The paper proposes a hybrid hierarchical architecture in multiple robot system based on improved learning classifier system. In the system cooperation-planning layer, Artificial Potential Field Grid Method,learning classifier broadcast operation of coordinationplanning layer and Mobile Control Platform in multiple robot system of behavior-control layer, easy to realize the multiple robot signal communication and system＇ s expansion, enhanced the entire multi-robot assembly system＇ s Practicality, Real-time and Reliability.