FairLight: Fairness-Aware Autonomous Traffic Signal Control With Hierarchical Action Space

Although reinforcement learning (RL) approaches are promising in autonomous traffic signal control (TSC), they often suffer from the unfairness problem that causes extremely long waiting time at intersections for partial vehicles. This is mainly because the traditional RL methods focus on optimizing the overall traffic performance, while the fairness of individual vehicles is neglected. To address this problem, we propose a novel RL-based method named FairLight for the fair and efficient control of traffic with variable phase duration. Inspired by the concept of user satisfaction index (USI) proposed in the transportation field, we introduce a fairness index in the design of key RL elements, which specially considers the travel quality (e.g., fairness). Based on our proposed hierarchical action space method, FairLight can accurately allocate the duration of traffic lights for selected phases. Experimental results obtained from various well-known traffic benchmarks show that, compared with the state-of-the-art RL-based TSC methods, FairLight can not only achieve better fairness performance but also improve the control quality from the perspectives of the average travel time of vehicles and RL convergence speed.

I. Introduction

Along with the dramatic growth of global urbanization and accelerated economy, we are witnessing more and more traffic congestion scenarios accompanied by an increase in traffic costs [1]. Traffic congestion not only causes environmental pollution issues such as carbon emissions but also results in a tremendous loss in economic and time costs [2]. According to the 2021 Global Traffic Scorecard reported by the world leader in transportation analytics INRIX, Inc., drivers in the United States lost 28 h and 564 on average in 2021. In the most congested city of the United States, i.e., New York, commuters lost 102 h and 1594.75 on average in 2021 [3]. Therefore, improving traffic conditions and relieving traffic congestion is the key to speeding up urban and economic development and improving the quality of people’s daily lives.