A Hysteretic Q-learning Coordination Framework for Emerging Mobility Systems in Smart Cities
This work addresses traffic congestion and efficiency problems for smart city mobility systems, but it is incremental as it builds on existing Q-learning with added coordination mechanisms.
The paper tackles decentralized coordination of connected and automated vehicles at signal-free intersections to minimize travel time and improve fuel efficiency, demonstrating efficacy through simulation with comparisons to classical optimal control methods.
Connected and automated vehicles (CAVs) can alleviate traffic congestion, air pollution, and improve safety. In this paper, we provide a decentralized coordination framework for CAVs at a signal-free intersection to minimize travel time and improve fuel efficiency. We employ a simple yet powerful reinforcement learning approach, an off-policy temporal difference learning called Q-learning, enhanced with a coordination mechanism to address this problem. Then, we integrate a first-in-first-out queuing policy to improve the performance of our system. We demonstrate the efficacy of our proposed approach through simulation and comparison with the classical optimal control method based on Pontryagin's minimum principle.