Virtual-Reality-Based Training System for the Improvement of the Driver’s Ability to Predict Dangers in Driving Situations  

作　　者：Hiroto Suto Xingguo Zhang Xun Shen Pongsathorn Raksincharoensak Norimichi Tsumura 

机构地区：[1]Department of Imaging Science,Chiba University,Chiba 263-8522,Japan [2]Department of Mechanical Systems Engineering,Tokyo University of Agriculture and Technology,Tokyo 183-8538,Japan [3]Graduate School of Engineering,Chiba University,Chiba 263-8522,Japan

出　　处：《Journal of Electrical Engineering》2020年第1期8-16,共9页电气工程（英文版）

摘　　要：Improving the danger prediction during driving can significantly reduce the risk of accidents.However,previous danger prediction training systems had not been sufficiently effective owing to the lack of realism.In this study,we propose an immersive training system for danger prediction training using virtual reality(VR)technology.This system provides drivers with a highly realistic training environment with 360°videos viewed with VR goggles.Users can practice various dangerous scenarios in an environment that simulates a real-driving situation.In addition,we introduced a system to select dangerous spots with a controller and implement training schemes on a voluntary basis.This setup enables them to train in a highly interactive state.In addition,we proposed a method to express multiple indices numerically so that users can understand the training effect.We tested the effect of the system on the danger prediction abilities of various users with two experiments by using this approach.These results show that our system was more effective in improving the driver’s danger prediction ability than previous systems.

关 键 词：VR VR goggle traffic accident danger prediction 360°video interaction 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]