University of Maryland Uses Reinforcement Learning to Train Autonomous Vehicles for Hazardous Situations

Xianfeng "Terry" Yang, associate professor in the Department of Civil and Environmental Engineering at the University of Maryland and director of the Maryland Transportation Institute, is using reinforcement learning to train autonomous "drivers" to handle various hazardous situations. His laboratory uses artificial intelligence to improve the operational efficiency of autonomous vehicles within road transportation systems and is working to address the lack of sufficient training for autonomous vehicles when facing decisions that require split-second choices.