Balancing Efficiency and Fairness in Traffic Light Control through Deep Reinforcement Learning

2026-05-11

AI Summary

Traditional traffic signal control struggles to adapt to dynamic traffic flows and often overlooks fairness between pedestrians and vehicles, resulting in inefficiency and imbalanced service. This work proposes an adaptive signal control method based on deep reinforcement learning that, for the first time, explicitly models and jointly optimizes both traffic efficiency and vehicle-pedestrian fairness within a deep reinforcement learning framework. By integrating real-time traffic state perception with multi-agent collaborative decision-making, the approach dynamically adjusts signal timing to respond to evolving traffic conditions. Experimental results demonstrate that the proposed method significantly alleviates congestion while delivering more balanced and equitable passage opportunities for both pedestrians and vehicles.

Abstract

Urban traffic congestion presents a significant challenge for modern cities, which impacts mobility and sustainability. Traditional traffic light control systems often fail to adapt to dynamic conditions, leading to inefficiencies. This paper proposes a novel deep reinforcement learning agent for traffic light control that addresses this limitation by explicitly integrating fairness considerations for both vehicular and pedestrian traffic. Unlike prior work, our approach dynamically balances these flows based on real-time demand, moving beyond systems focused solely on vehicles. Experimental results demonstrate that our agent effectively reduces congestion while ensuring equitable service for both the categories of road users. This research contributes to a practical and adaptable solution for intelligent traffic management within the framework of smart cities, paving the way for more efficient and inclusive urban mobility.

Problem

• traffic light control
• efficiency
• fairness
• urban mobility
• smart cities

Innovation

• deep reinforcement learning
• traffic light control
• fairness
• urban mobility
• smart cities