Optimizing Efficiency of Mixed Traffic through Reinforcement Learning: A Topology-Independent Approach and Benchmark

TL;DR

This paper introduces a reinforcement learning-based traffic control policy that is topology-independent and demonstrates its effectiveness through a new real-world benchmark with diverse scenarios, outperforming existing methods.

Contribution

It develops a model-free RL approach for mixed traffic management and releases the first comprehensive real-world mixed traffic benchmark covering diverse scenarios and topologies.

Findings

The proposed method outperforms existing traffic control techniques.

It demonstrates high adaptability across various road topologies.

The benchmark enables realistic evaluation of mixed traffic policies.

Abstract

This paper presents a mixed traffic control policy designed to optimize traffic efficiency across diverse road topologies, addressing issues of congestion prevalent in urban environments. A model-free reinforcement learning (RL) approach is developed to manage large-scale traffic flow, using data collected by autonomous vehicles to influence human-driven vehicles. A real-world mixed traffic control benchmark is also released, which includes 444 scenarios from 20 countries, representing a wide geographic distribution and covering a variety of scenarios and road topologies. This benchmark serves as a foundation for future research, providing a realistic simulation environment for the development of effective policies. Comprehensive experiments demonstrate the effectiveness and adaptability of the proposed method, achieving better performance than existing traffic control methods in both intersection and roundabout scenarios. To the best of our knowledge, this is the first project to introduce a real-world complex scenarios mixed traffic control benchmark. Videos and code of our work are available at https://sites.google.com/berkeley.edu/mixedtrafficplus/home