Presented By: Industrial & Operations Engineering
IOE 899 - Jingwen Hu, University of Michigan
Safety for All in Motor Vehicle Crashes through an AI-Driven Digital Twin Framework

Dr. Hu is a Professor at IOE and a Research Professor at UMTRI. His research interests primarily focus on injury biomechanics and traffic injury prevention by a multidisciplinary approach using a combination of experimental, numerical, and epidemiological methods. Dr. Hu is an author of 150+ peer-reviewed journal and conference papers with four Best Paper Awards. His research has been funded by the National Highway Traffic Safety Administration, the National Science Foundation, the National Institute of Justice, the Department of Defense, and the Auto Industry.
Abstract:
Recent literature has shown that there is a growing concern of safety disparity in motor-vehicle crashes (MVCs), but technological tools for addressing this issue are limited. In particular, females, the elderly, and obese occupants are among the vulnerable populations who are often at increased risk of death and serious injury compared with mid-size young men in MVCs. This presentation will introduce the parametric finite element (FE) human and vehicle modeling work conducted in the past decade, along with recent machine-learning models and design optimizations. The results demonstrated the effectiveness of a population-based virtual testing framework on improving safety disparity among the diverse population.
Abstract:
Recent literature has shown that there is a growing concern of safety disparity in motor-vehicle crashes (MVCs), but technological tools for addressing this issue are limited. In particular, females, the elderly, and obese occupants are among the vulnerable populations who are often at increased risk of death and serious injury compared with mid-size young men in MVCs. This presentation will introduce the parametric finite element (FE) human and vehicle modeling work conducted in the past decade, along with recent machine-learning models and design optimizations. The results demonstrated the effectiveness of a population-based virtual testing framework on improving safety disparity among the diverse population.