Flow: A Modular Learning Framework for Mixed Autonomy Traffic

TL;DR

This paper introduces a modular deep reinforcement learning framework for mixed autonomy traffic, demonstrating significant improvements in traffic flow and congestion reduction with limited autonomous vehicle adoption.

Contribution

It presents a novel modular RL framework that captures complex traffic phenomena and outperforms existing controllers, even with partial AV adoption.

Findings

Control laws improve system velocity by up to 57% with 4-7% AV adoption.

A small neural network eliminates stop-and-go traffic in single-lane scenarios.

The framework generalizes well to different traffic densities.

Abstract

The rapid development of autonomous vehicles (AVs) holds vast potential for transportation systems through improved safety, efficiency, and access to mobility. However, the progression of these impacts, as AVs are adopted, is not well understood. Numerous technical challenges arise from the goal of analyzing the partial adoption of autonomy: partial control and observation, multi-vehicle interactions, and the sheer variety of scenarios represented by real-world networks. To shed light into near-term AV impacts, this article studies the suitability of deep reinforcement learning (RL) for overcoming these challenges in a low AV-adoption regime. A modular learning framework is presented, which leverages deep RL to address complex traffic dynamics. Modules are composed to capture common traffic phenomena (stop-and-go traffic jams, lane changing, intersections). Learned control laws are found to improve upon human driving performance, in terms of system-level velocity, by up to 57% with only 4-7% adoption of AVs. Furthermore, in single-lane traffic, a small neural network control law with only local observation is found to eliminate stop-and-go traffic - surpassing all known model-based controllers to achieve near-optimal performance - and generalize to out-of-distribution traffic densities.