自主虚拟人真实感行为与运动建模的研究

Modeling Realistic Behaviors and Movements of Autonomous Virtual Humans

提出一个构建具有高度自主性虚拟人的集成框架,在实时虚拟环境中创建具有类人的真实感行为特征与运动能力的虚拟人.在集成框架中,感知系统使虚拟人能够获取虚拟环境中视听觉信息,对虚拟环境进行自主探索;基于决策网络的行为决策系统模拟真实人类决策的复杂性与不确定性,根据所感知的周围虚拟环境信息,做出合理的行为决策;层次式运动控制系统实现虚拟人在虚拟环境中路径规划与Steering控制,实时合成出真实感的虚拟人运动动画.实验结果表明,该集成框架能够在实时虚拟环境中有效地构建出具有高度自主性、环境感知能力以及智能行为决策与运动控制功能的真实感虚拟人.

A comprehensive integrated framework for modeling virtual humans with high level autonomy is proposed,which aims to reproduce human-like believable behaviors and movements of virtual humans in virtual environment.In the integrated framework,the perception module enables virtual human to get virtual vision and audition information and explore virtual environment;the decision networks based behavioral decision-making module mimics the uncertainty and complexity in the way humans make decision,and enables virtual human arrive at rational decisions and react appropriately to the perceived surrounding environment;the hierarchical movement control module is designed to generate autonomous navigation,steering controls and realistic motion animation in virtual environment.Experimental results demonstrate the effectiveness of the integrated framework to create autonomous,perceptive and intelligent virtual human in real-time virtual environment.