A Fairness-Oriented Multi-Objective Reinforcement Learning approach for Autonomous Intersection Management

TL;DR

This paper presents a multi-objective reinforcement learning method for autonomous intersection management that balances traffic efficiency, emissions reduction, and fairness among vehicle types, demonstrated through simulation results.

Contribution

It introduces a novel MORL approach with a fairness criterion for equitable and sustainable intersection control, advancing urban mobility management.

Findings

Effective optimization of traffic flow and emissions in simulations

Demonstrated fairness across electric and combustion vehicles

Potential foundation for equitable smart mobility systems

Abstract

This study introduces a novel multi-objective reinforcement learning (MORL) approach for autonomous intersection management, aiming to balance traffic efficiency and environmental sustainability across electric and internal combustion vehicles. The proposed method utilizes MORL to identify Pareto-optimal policies, with a post-hoc fairness criterion guiding the selection of the final policy. Simulation results in a complex intersection scenario demonstrate the approach's effectiveness in optimizing traffic efficiency and emissions reduction while ensuring fairness across vehicle categories. We believe that this criterion can lay the foundation for ensuring equitable service, while fostering safe, efficient, and sustainable practices in smart urban mobility.