自动化学报2012，Vol.38Issue(4)：518-524,7.DOI:10.3724/SP.J.1004.2012.00518
模仿学习:一种新人工生命动画方法
Imitation Learning: A New Approach in Artificial Life Animation
摘要
Abstract
This paper proposes a new artificial life animation approach — imitation learning. Imitation is a highly effective learning method for acquiring motion skill which can be regarded as a set of numerous motion sequences. Imitating representative motion sequences to acquire the local motion skill and generalizing them can achieve the entire motion skill. The cores of imitation learning are motion similarity and simple-compose behavior methodology, and evolutionary computation is used as an optimization method. Imitation learning decreases the dependence of evolutionary computation on traditional fitness function and the time spent on designing a suitable fitness function. It also increases the ability of optimizing complex goal. So it increases the efficiency of producing animation. We verify our method by training an artificial cat robot to learn landing behavior based on PhysX simulation framework, which achieves a good result.关键词
模仿学习/简单-复杂行为方法论/运动相似度匹配/进化计算/人工生命动画Key words
Imitation learning, simple-compose behavior, motion similarity matching, evolutionary computation, artificial life animation引用本文复制引用
班晓娟,徐卓然,刘浩..模仿学习:一种新人工生命动画方法[J].自动化学报,2012,38(4):518-524,7.基金项目
国家自然科学基金(60973063),北京自然科学基金(4092028),中央高校基本科研业务费专项资金(FRF-TP-09-016B),教育部新世纪人才支持计划(NCET-10-0221)资助 （60973063）
