Learning energy-efficient driving behaviors by imitating experts

TL;DR

This paper explores how imitation learning can enable automated vehicles to adopt energy-efficient driving behaviors using only local observations, potentially reducing energy consumption in dense traffic by 15% with minimal vehicle adoption.

Contribution

It demonstrates that imitation learning can derive effective energy-efficient driving policies from expert controllers, even under realistic sensing and communication constraints.

Findings

Imitation learning can improve energy efficiency by 15% in dense traffic.

Effective policies can be learned with only 5% vehicle adoption.

Results are validated with real-world traffic scenarios.

Abstract

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.