Journal of South China University of Technology (Natural Science Edition) ›› 2006, Vol. 34 ›› Issue (1): 96-100.

• Computer Science & Technology • Previous Articles     Next Articles

Layered Model and Task Planning for Multi-Agent Cooperation

Zhao Long-wen   

  1. College of Electronic Business,South China Univ.of Tech.,Guangzhou 510006,Guangdong,China
  • Received:2005-07-12 Online:2006-01-25 Published:2006-01-25
  • Contact: 赵龙文(1964-)，男，博士，高级工程师，主要从事智能软件理论、电子商务和信息化工程等方面的研究． E-mail:lwzhao@scut.edu.cn
  • About author:赵龙文(1964-)，男，博士，高级工程师，主要从事智能软件理论、电子商务和信息化工程等方面的研究．

PDF

257

Abstract:

In a multi-agent environment,multiple agents should be united to realize some complex tasks that are dificult to solve depending only on one agent because of being lacking in the capability or precondition of the sys-tem.Aiming at the cooperation of multiple agents,this paper proposes a layered model,in which the partners join hands to form a layered cooperation sequence via the joint capability.A large joint capability is then taken as the
plan unit and the layered cooperation target is taken as the plan target.Thus,the task plan and management be-come simple and clear.Moreover,the methods of determ ining the partners and form ing the dynamic teams are also presented,with the task planning being finally discussed.

Key words: multi-agent system, collaboration, capability matching, task planning, joint capability