用户认知驱动的VR自然交互认知负荷研究.PDF

37 7 Vol. 37 No. 7 第 卷第 期 计算机应用研究 录用定稿 Application Research of Computers Accepted Paper 用户认知驱动的VR 自然交互认知负荷研究 * † 徐小萍，吕 健 ，金昱潼，姬文渊 (贵州大学 现代制造技术教育部重点实验室, 贵阳 550003) 摘 要：针对目前虚拟现实自然交互系统中用户认知负荷难以量化问题，以量化认知负荷为目的，提出一种基于概 率神经网络的多通道信息融合模型。首先根据认知理论建立“认知—行为—环境”框架，并在此基础上研究用户认 知的数学表征 （方法，过程，机理），构建多通道认知模型；然后将多通道信息融合方法引入虚拟现实自然交互系 统，建立一种面向虚拟现实自然交互系统的认知负荷模型；最后通过VR 隧道应急救援系统实验，对系统中用户认 知进行验证。验证结果表明，具体提出的认知负荷模型具有一定的可行性。 关键词：虚拟现实系统；多通道融合；认知表达；认知负荷 中图分类号：TP391 doi: 10.19734/j.issn.1001-3695.2018.12.0936 Research on natural interactive cognitive load of virtual reality driven by user cognition † Xu Xiaoping, Lyu Jian , Jin Yutong, Ji Wenyuan (Key Laboratory of Advanced Manufacturing Technology, Ministry of Education , Guizhou University, Guiyang 550003, China) Abstract: Aiming at the problem that it is difficult to quantify the cognitive load of users in virtual reality natural interactive system, a multi-channel information fusion model based on probabilistic neural network is proposes to quantify the cognitive load. Firstly, the framework of cognition-behavior-environment is establishes based on cognitive theory, and then the mathematical representation (method, process, mechanism) of user cognition is studies, and a multi-modal cognitive model is constructes. Then the multi-modal information fusion method is introduced into the virtual reality natural interaction system