进化行为树方法研究综述  

Survey of Evolutionary Behavior Tree Algorithm

作　　者：杨杰[1] 张琪 曾俊杰 尹全军[1] Yang Jie;Zhang Qi;Zeng Junjie;Yin Quanjun(College of Systems Engineering,National University of Defense Technology,Changsha 410073,China)

机构地区：[1]国防科技大学系统工程学院,湖南长沙410073

出　　处：《系统仿真学报》2021年第10期2315-2322,共8页Journal of System Simulation

基　　金：国家社科基金军事学项目(2020-SKJJ-O-C-005)。

摘　　要：进化行为树方法是一种利用进化算法自主生成和优化行为树模型的智能体行为建模方法。从介绍行为树、进化算法相关背景知识入手,阐述了基于遗传编程、语法演化、混合算法三类进化行为树算法以及相应改进算法,分析比较不同算法的优劣;梳理总结了进化行为树方法在作战仿真、游戏人工智能、机器人等领域的具体应用;从搜索能力、泛化能力、行为树优化、多智能体应用方面提出并探讨了未来的发展趋势。Evolutionary behavior tree method is an agent behavior modeling method which uses evolutionary algorithm to generate and optimize behavior tree model. Based on the background knowledge of behavior tree and evolutionary algorithm, three kinds of evolutionary behavior tree algorithms based on genetic programming, grammar evolution and hybrid algorithm as well as corresponding improved algorithms are described, and the advantages and disadvantages of different algorithms are analyzed and compared. The specific applications of evolutionary behavior tree in combat simulation, game artificial intelligence, robotics and other fields are summarized. The future development trends of evolutionary behavior tree are proposed and discussed from the perspectives of search ability, generalization ability, behavior tree optimization and multi-agent application.

关 键 词：进化行为树 行为树 遗传编程 语法演化 混合算法 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]