摘要
本文从模仿机制的再现环节入手，采用知识使用和行动预见为主的拟人化推理策略，来实现有效的行为模仿.具体地，以模糊集合间的Hausdorff距离作为知识使用的尺度，导入知识半径到距离型模糊推理方法当中实现知识的选择使用；以预见控制的基本思想为指导，设计行动预见模型作为知识使用的高层决策，优化知识使用策略的参数.并以驾驶行为模仿为例，验证了拟人化推理策略对于动态知识使用的有效性，实现了即学即仿的模仿效果.
This paper focuses on the recurrence component of imitation mechanism and presents humanoid reasoning slrate- gies such as knowledge use and action preview to implement effective behavior imitation. Concretely, by defining the Hausdorff dis- tance between fuzzy sets as the metric of knowledge use, we combined knowledge radius into the distance-type fuzzy reasoning method for the implementation of selective knowledge use; according to the main idea of preview control, we designed the action preview model as high level decision of knowledge use to optimize the parameters of knowledge use strategy. Finally we presented the results of driving behavior imitation, demonstrated the validity of humanoid reasoning strategies in dynamic knowledge use, and realized quick learning-and-imitating performance.
出处
《电子学报》
EI
CAS
CSCD
北大核心
2010年第B02期83-88,共6页
Acta Electronica Sinica
基金
32批教育部留学回国人员科研启动基金
高等学校博士学科点专项科研基金(No.2008000600018)
中国博士后科学基金(No.20080430303)
国家自然科学基金(No.60672102)
关键词
模仿
模糊推理
知识使用
行动预见
imitation
fuzzy reasoning
knowledge use
action preview
