Learning energy-efficient driving behaviors by imitating experts
This work addresses energy efficiency in automated vehicle networks for traffic management, but it is incremental as it applies imitation learning to an existing control strategy.
The paper tackles the challenge of adapting automated vehicle control strategies to real-world limitations in communication and sensing by using imitation learning to derive policies from an expert controller. It demonstrates that adopting these policies in 5% of vehicles can boost energy efficiency by 15% in networks with varying traffic conditions using only local observations.
The rise of vehicle automation has generated significant interest in the potential role of future automated vehicles (AVs). In particular, in highly dense traffic settings, AVs are expected to serve as congestion-dampeners, mitigating the presence of instabilities that arise from various sources. However, in many applications, such maneuvers rely heavily on non-local sensing or coordination by interacting AVs, thereby rendering their adaptation to real-world settings a particularly difficult challenge. To address this challenge, this paper examines the role of imitation learning in bridging the gap between such control strategies and realistic limitations in communication and sensing. Treating one such controller as an "expert", we demonstrate that imitation learning can succeed in deriving policies that, if adopted by 5% of vehicles, may boost the energy-efficiency of networks with varying traffic conditions by 15% using only local observations. Results and code are available online at https://sites.google.com/view/il-traffic/home.