PATH PLANNING OF VIRTUAL HUMAN BY USING REINFORCEMENT LEARNING

摘要：

Virtual Human can hold the possibility of performing a variety of assistive and analysis tasks in 3D virtual environments. However, widespread use of avatars assistants in these environments requires ease of use by individuals who are generally not skilled on designing operators. In this paper we present a method of training virtual human that bridges the gap between designing and building of a virtual humans action as well as its autonomous learning ability to adapt a certain task. With our approach, we integrate reinforcement learning to the action of virtual humans path planning to achieve fast policy acquisition. The result of the approach is illustrated in the case of successfully instructing virtual human to cross a terrain with pyramid and a number of obstacles to reach a certain target.

关键词： Virtual Human Character animation Reinforcement learning Behavioral model Intelligent animation Machine learning Path plan

作者: YUE-SHENG HE YUAN-YAN TANG

作者单位: Computer Science Department, Hong Kong Baptist University, Kowloon Tong, Hong Kong

会议类型: 国际会议

会议名称: 2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

会议地点: 昆明

会议语种:英文

页码: 987-992

在线出版日期: 2008-07-12（万方平台首次上网日期，不代表论文的发表时间）