Learning a Robust Multiagent Driving Policy for Traffic Congestion Reduction
This work addresses traffic congestion for urban societies by proposing a robust policy that could enable practical deployment of autonomous vehicles, though it is incremental in extending existing methods to new conditions.
The paper tackles the problem of traffic congestion by developing a robust multiagent driving policy for autonomous vehicles that generalizes to various traffic conditions, achieving significant improvements in traffic flow as demonstrated in high-fidelity simulations.
In most modern cities, traffic congestion is one of the most salient societal challenges. Past research has shown that inserting a limited number of autonomous vehicles (AVs) within the traffic flow, with driving policies learned specifically for the purpose of reducing congestion, can significantly improve traffic conditions. However, to date these AV policies have generally been evaluated under the same limited conditions under which they were trained. On the other hand, to be considered for practical deployment, they must be robust to a wide variety of traffic conditions. This article establishes for the first time that a multiagent driving policy can be trained in such a way that it generalizes to different traffic flows, AV penetration, and road geometries, including on multi-lane roads. Inspired by our successful results in a high-fidelity microsimulation, this article further contributes a novel extension of the well-known Cell Transmission Model (CTM) that, unlike past CTMs, is suitable for modeling congestion in traffic networks, and is thus suitable for studying congestion-reduction policies such as those considered in this article.