GPLight+: A Genetic Programming Method for Learning Symmetric Traffic Signal Control Policy

TL;DR

This paper introduces GPLight+, a genetic programming approach that evolves symmetric phase urgency functions for traffic signal control, improving policy performance and interpretability in real-world scenarios.

Contribution

It proposes a novel symmetric phase urgency function representation and a GP method to evolve it, addressing inconsistency issues in traffic feature treatment.

Findings

Significant performance improvement over traditional GP methods.

Evolved policies are human-understandable and easily deployable.

Effective across multiple real-world traffic scenarios.

Abstract

Recently, learning-based approaches, have achieved significant success in automatically devising effective traffic signal control strategies. In particular, as a powerful evolutionary machine learning approach, Genetic Programming (GP) is utilized to evolve human-understandable phase urgency functions to measure the urgency of activating a green light for a specific phase. However, current GP-based methods are unable to treat the common traffic features of different traffic signal phases consistently. To address this issue, we propose to use a symmetric phase urgency function to calculate the phase urgency for a specific phase based on the current road conditions. This is represented as an aggregation of two shared subtrees, each representing the urgency of a turn movement in the phase. We then propose a GP method to evolve the symmetric phase urgency function. We evaluate our proposed method on the well-known cityflow traffic simulator, based on multiple public real-world datasets. The experimental results show that the proposed symmetric urgency function representation can significantly improve the performance of the learned traffic signal control policies over the traditional GP representation on a wide range of scenarios. Further analysis shows that the proposed method can evolve effective, human-understandable and easily deployable traffic signal control policies.