A partitioning-based task allocation strategy for Police Multi-Agents

Author

Liang Zhiwei ; Yang Xiang ; Deng Yao

Author_Institution

Coll. of Autom., Nanjing Univ. of Posts & Telecommun., Nanjing, China

fYear

2014

fDate

May 31 2014-June 2 2014

Firstpage

2124

Lastpage

2128

Abstract

RCRSS (RoboCup Rescue Simulation System, RCRSS) is a typical multi-agent system. In order to solve the task allocation problem for police multi-agents of this system, this paper presents a novel partitioning-based task allocation strategy. It is carried out through the use of clustering, namely the K-means clustering algorithm, to divide the map into several regions. Then the dynamic adjustment system with static assignment was adopted synthetically for the implementation. The experimental results show that the new task allocation strategy for the police can adapt to a variety of disaster environments and improve the efficiency of multi-agent collaboration.

Keywords

multi-agent systems; multi-robot systems; pattern clustering; rescue robots; K-means clustering algorithm; RCRSS; RoboCup rescue simulation system; disaster environment; dynamic adjustment system; multiagent collaboration; partitioning-based task allocation; police multiagents; static assignment; Buildings; Clustering algorithms; Collaboration; Fires; Resource management; Roads; Robots; Cluster; Multi-agent; RoboCup rescue; Task allocation;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Decision Conference (2014 CCDC), The 26th Chinese

Conference_Location

Changsha

Print_ISBN

978-1-4799-3707-3

Type

conf

DOI

10.1109/CCDC.2014.6852518

Filename

6852518