MalLight: Influence-Aware Coordinated Traffic Signal Control for Traffic Signal Malfunctions

TL;DR

MalLight tackles the challenge of traffic signal malfunction by enabling influence-aware coordination among intersections through two novel diffusion-based modules: ISAM for state aggregation and IRAM for reward aggregation. By modeling spatial and temporal influence with masked diffusion convolution and diffusion-based reward shaping, each well-functioning intersection learns policies that alleviate congestion at malfunctioning neighbors. Empirical results on real-world (Hangzhou, NYC) and synthetic (Grid4*4) datasets show MalLight reduces throughput loss by up to 48.6% compared with strong baselines, while preserving performance in normal conditions. The work demonstrates the practical value of inter-intersection cooperation and diffusion-based information flow for resilient traffic signal control under malfunction.

Abstract

Urban traffic is subject to disruptions that cause extended waiting time and safety issues at signalized intersections. While numerous studies have addressed the issue of intelligent traffic systems in the context of various disturbances, traffic signal malfunction, a common real-world occurrence with significant repercussions, has received comparatively limited attention. The primary objective of this research is to mitigate the adverse effects of traffic signal malfunction, such as traffic congestion and collision, by optimizing the control of neighboring functioning signals. To achieve this goal, this paper presents a novel traffic signal control framework (MalLight), which leverages an Influence-aware State Aggregation Module (ISAM) and an Influence-aware Reward Aggregation Module (IRAM) to achieve coordinated control of surrounding traffic signals. To the best of our knowledge, this study pioneers the application of a Reinforcement Learning(RL)-based approach to address the challenges posed by traffic signal malfunction. Empirical investigations conducted on real-world datasets substantiate the superior performance of our proposed methodology over conventional and deep learning-based alternatives in the presence of signal malfunction, with reduction of throughput alleviated by as much as 48.6$\%$.

Figures (9)

• Figure 1: Throughput reduction at intersections around malfunctioning traffic signal
• Figure 2: Locations of complaints about traffic signal malfunction
• Figure 3: Intersection, incoming lanes(blue), outgoing lanes(red). Phase 3 is set.
• Figure 4: Eight phases (actions).
• Figure 5: MalLight framework and modules.