计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (26): 1-3.

• 博士论坛 • 上一篇    下一篇

对抗条件下的计划生成过程建模及状态推理

武云鹏,黄金才,张维明,刘 忠,朱 承,修保新   

  1. 国防科学技术大学 信息系统与管理学院,长沙 410073
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-09-11 发布日期:2011-09-11

Planning modeling and state reasoning in competitive situation

WU Yunpeng,HUANG Jincai,ZHANG Weiming,LIU Zhong,ZHU Cheng,XIU Baoxin   

  1. Information System and Management,National University of Defense Technology,Changsha 410073,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-09-11 Published:2011-09-11

摘要: 计划生成是AI领域的一个重要的研究分支,其相关研究成果在越来越多的领域得到应用。研究对抗条件下的动态计划生成过程建模和相关推理方法;定义了对抗条件下的计划生成过程模型,并给出基于该模型的状态推理机制;动态环境的不确定性则以先验概率的形式给出。针对先验概率主观性较强的缺点,进一步设计了一种先验概率的修订策略。在分析计划生成问题复杂程度的基础上,设计了基于[A*]算法的启发式算法;实验结果验证了该算法具有良好的精确性和可扩展性。

关键词: 动态环境, 计划生成, 对抗条件下, 先验概率

Abstract: Planning is one of the most important branches in AI,the achievements of research have been applied in a lot of areas.The paper investigates the problem of planning modeling and related reasoning method in competitive situation.It defines a planning model and gives the state reasoning mechanism based on the model.The uncertainty in dynamic environment is given in the form of prior probability.To reduce the subjective affect of prior probability,this paper designs a revised strategy.After analyzing the complexity of the planning problem in competitive situation,the paper designs a heuristic algorithm based on [A*] algorithm,and the experimental results verify that the algorithm has good accuracy and scalability.

Key words: dynamic environment, planning, competitive situation, prior probability