Driving Performance
Research on driving performance focuses on improving both human and autonomous driving capabilities. Current efforts involve developing AI-based coaching systems using multi-task imitation learning and other machine learning techniques to enhance driver skills and provide effective feedback, alongside creating robust benchmarks for evaluating end-to-end autonomous driving systems under diverse conditions. These advancements aim to improve road safety by addressing driver error, enhancing autonomous vehicle reliability, and ultimately reducing accidents through better driver training and more dependable self-driving technology.
Papers
Vision-based Analysis of Driver Activity and Driving Performance Under the Influence of Alcohol
Ross Greer, Akshay Gopalkrishnan, Sumega Mandadi, Pujitha Gunaratne, Mohan M. Trivedi, Thomas D. Marcotte
What Matters to Enhance Traffic Rule Compliance of Imitation Learning for End-to-End Autonomous Driving
Hongkuan Zhou, Wei Cao, Aifen Sui, Zhenshan Bing