Leveraging autonomous vehicles in mixed-autonomy traffic networks with reinforcement learning-controlled intersections
Leveraging autonomous vehicles in mixed-autonomy traffic networks with reinforcement learning-controlled intersections
复制标题
DOI：
10.1080/19427867.2022.2146302
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Sahand Mosharafian;Shirin Afzali;Javad Mohammadpour Velni
中科院分区：
文献类型：
--
作者：
Sahand Mosharafian;Shirin Afzali;Javad Mohammadpour Velni
摘要 自适应交通信号控制新方法的开发受到了广泛关注。强化学习 (RL) 就是一个例子，其中 RL 代理的训练和实施可以考虑代理过去的经验，实现实时自适应信号控制。此外，自动驾驶汽车（AV）技术已显示出增强高速公路和十字路口交通流动性的前景。本文针对具有信号交叉口的车辆网络开发了延迟动作深度 Q 学习来控制信号相位。提出了模型预测控制（MPC）方案，以允许自动驾驶汽车适应其速度。研究了几个考虑混合自动驾驶的案例研究，旨在减少具有多个交叉口的交通网络中的网络流量和燃料消耗。模拟研究表明，即使网络中只有少量自动驾驶汽车，等待时间、燃油消耗和走走停停的次数也会显着减少，而出行时间却会增加。
ABSTRACT Development of new approaches to adaptive traffic signal control has received significant attention; an example is the reinforcement learning (RL), where training and implementation of an RL agent can allow adaptive signal control in real time, considering the agent’s past experiences. Furthermore, autonomous vehicle (AV) technology has shown promise to enhancing the traffic mobility at highways and intersections. In this paper, delayed action deep Q-learning is developed for a vehicle network with signalized intersections to control the signal phase. A model predictive control (MPC) scheme is proposed to allow AVs to adapt their speed. Several case studies that consider mixed autonomy are examined aiming at reducing network traffic and fuel consumption in the traffic network with multiple intersections. Simulation studies reveal that even with a few AVs in the network, the waiting time, fuel consumption, and the number of stop-and-go movements are significantly reduced, while the travel time is increased.