Improving energy efficiency with safety guarantee: A practical framework in transportation

Transportation system accounts for approximately a quarter of U.S. annual energy usage. Designing smart and efficient control algorithms for vehicles in the transportation systems therefore would help reduce energy usage greatly. However, traditional approaches require high computational power to solve holistic optimization constraints. Moreover, potential boundaries between different sub-components are likely ignored. Such end-to-end solutions may not be practical. In this talk, I will introduce a different framework based on the control safety function theory to achieve maximum efficiency with a safety guarantee. A data-driven approach that focuses on efficiency is presented to leverage rich data gathered from vehicle-to-vehicle communication. Wrapped around is a safety filter that monitors the action and applies minimum intervention and coordinates different sub-components. The proposed framework has been implemented in class 8 heavy-duty vehicles and demonstrates its effectiveness.

Dr. Chaozhe He received his B.S. degree in Applied Mathematics from the Beijing University of Aeronautics and Astronautics in 2012, and his M.S. and Ph.D. degrees in Mechanical Engineering from the University of Michigan, Ann Arbor in 2015 and 2018, respectively. Dr. He was a research engineer at Navistar, where he contributed to powertrain fuel efficiency feature development and autonomous platform developments for heavy-duty vehicles. He was also a key member of the Navistar team on the U.S. Department of Energy Super Truck II program. Dr. He is now a staff research engineer at Plus.ai, focusing on planning and control algorithm development for automated trucks. His research interests include optimal and nonlinear control theory, as well as data-driven and learning-based control.