智能规划器StepByStep的研究和开发  

Research and Development of StepByStep AI Planner

作　　者：吴向军[1] 姜云飞[2] 凌应标[3] 

机构地区：[1]中山大学软件学院,广东广州510275 [2]中山大学信息科学与技术学院软件研究所,广东广州510275 [3]中山大学信息科学与技术学院计算机科学系,广东广州510275

出　　处：《软件学报》2008年第9期2243-2264,共22页Journal of Software

基　　金：国家自然科学基金;中山大学985工程专项资金~~

摘　　要：智能规划器是智能规划研究成果的重要表现形式,规划器的求解效率和规划质量是智能规划理论研究的直接反映.首先介绍智能规划器的一般结构和StepByStep规划器的总体结构,然后详细阐述StepByStep规划器各组成部分所采用的方法和策略,定义谓词知识树来提取领域知识.在谓词知识树的基础上定义谓词规划树,并用各种策略来提高规划树的生成效率.在谓词规划树的基础上设计StepByStep的规划策略,最后用8个规划器对3个具有代表性的基准规划领域及其规划问题进行实际的求解实验,分析了StepByStep规划器在求解效率和规划质量上的具体表现.实验数据表明,StepByStep规划器的规划策略对3个不同规划领域都具有很好的指导作用,验证了领域知识在规划求解过程中的实际价值.AI planner is one of the important representations of AI planning study, the performances of planner, the efficiency and quality of plan, represent the researches of AI planning directly. This paper introduces the architectures of AI planner and StepByStep planner in brief, then describes the methods and strategies adopted by SteByStep in detail, defines the knowledge tree of predicate for extracting domain knowledge. Based on knowledge tree of predicate, the planning tree of predicate is defined and some strategies are applied for constructing the planning tree fast. StepByStep adopts some planning strategies according to the planning trees. Finally, some experiments are taken for eight planners with three representative benchmark domains and their problems, the performances of StepByStep, the efficiency and quality of plan, are analyzed in detail. Experiments show that the strategies of StepByStep controls the process of planning the problems of the three domains well, and validate the guide effect of the domain knowledge in planning process.

关 键 词：人工智能 智能规划 智能规划器 规划领域 知识树 规划树 规划策略 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]