Path Selection in Disaster Response Management Based on Q-learning  

作　　者：Zhao-Pin Su Jian-Guo Jiang Chang-Yong Liang2＇ 3 Guo-Fu Zhang Guo-Fu Zhang 

机构地区：[1]Key Laboratory of Special Display Technology （Hefei University of Technology）, Ministry of Education, Hefei 230009, PRC [2]School of Computer and Information, Hefei University of Technology, Hefei 230009, PRC [3]Postdoctoral Research Station for Management Science and Engineering, Hefei University of Technology, Hefei 230009, PRC [4]Engineering Research Center of Safety Critical Industrial Measurement and Control Technology, Ministry of Education, Hefei 230009, PRC

出　　处：《International Journal of Automation and computing》2011年第1期100-106,共7页国际自动化与计算杂志（英文版）

基　　金：supported by National Basic Research Program of China (973 Program) (No. 2009CB326203);National Natural Science Foundation of China (No. 61004103);the National Research Foundation for the Doctoral Program of Higher Education of China (No. 20100111110005);China Postdoctoral Science Foundation (No. 20090460742);National Engineering Research Center of Special Display Technology (No. 2008HGXJ0350);Natural Science Foundation of Anhui Province (No. 090412058, No. 070412035);Natural Science Foundation of Anhui Province of China (No. 11040606Q44, No. 090412058);Specialized Research Fund for Doctoral Scholars of Hefei University of Technology (No. GDBJ2009-003, No. GDBJ2009-067)

摘　　要：Suitable rescue path selection is very important to rescue lives and reduce the loss of disasters, and has been a key issue in the field of disaster response management. In this paper, we present a path selection algorithm based on Q-learning for disaster response applications. We assume that a rescue team is an agent, which is operating in a dynamic and dangerous environment and needs to find a safe and short path in the least time. We first propose a path selection model for disaster response management, and deduce that path selection based on our model is a Markov decision process. Then, we introduce Q-learning and design strategies for action selection and to avoid cyclic path. Finally, experimental results show that our algorithm can find a safe and short path in the dynamic and dangerous environment, which can provide a specific and significant reference for practical management in disaster response applications.Suitable rescue path selection is very important to rescue lives and reduce the loss of disasters, and has been a key issue in the field of disaster response management. In this paper, we present a path selection algorithm based on Q-learning for disaster response applications. We assume that a rescue team is an agent, which is operating in a dynamic and dangerous environment and needs to find a safe and short path in the least time. We first propose a path selection model for disaster response management, and deduce that path selection based on our model is a Markov decision process. Then, we introduce Q-learning and design strategies for action selection and to avoid cyclic path. Finally, experimental results show that our algorithm can find a safe and short path in the dynamic and dangerous environment, which can provide a specific and significant reference for practical management in disaster response applications.

关 键 词：Disaster response management path selection AGENT SELF-ORGANIZING Markov decision process Q-learning. 

分 类 号：TP[自动化与计算机技术]