Physics-Augmented Data-Enabled Predictive Control for Eco-driving of Mixed Traffic Considering Diverse Human Behaviors

Feb 1, 2024·
Dongjun Li
,
Kaixiang Zhang
,
Haoxuan Dong
,
Qun Wang
,
Zhaojian Li
,
Ziyou Song
· 0 min read
Abstract
This paper develops a physics-augmented Data-EnablEd Predictive Control (DeePC) framework for eco-driving of connected and automated vehicles in mixed traffic. By embedding vehicle dynamics priors into the data-driven representation, the controller attains high sample efficiency while remaining robust to diverse human driving behaviors. The framework outperforms both purely data-driven DeePC and model-based MPC baselines in energy consumption and tracking accuracy.
Type
Publication
IEEE Transactions on Control Systems Technology
publications
Data-Enabled Predictive Control Eco-Driving Human Behavior Modeling
Authors
Qun Wang
Postdoctoral Fellow
Qun Wang is a Postdoctoral Fellow at the AIMS Lab, Hong Kong Polytechnic University, working with Assistant Professor Hailong Huang. His research focuses on energy-saving optimization and safety-guaranteed control of autonomous electrified vehicles, with emphasis on reinforcement learning for eco-driving, human driving behavior modeling, and multi-agent car-following control. He has published over 10 papers in leading journals including IEEE Transactions on ITS, TTE, TCST and Energy.