SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Control
SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Control
复制标题
DOI：
10.48550/arxiv.2211.10871
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Wenlu Du;J. Ye;Jingyi Gu;Jing Li;Hua Wei;Gui-Liu Wang
中科院分区：
文献类型：
--
作者：
Wenlu Du;J. Ye;Jingyi Gu;Jing Li;Hua Wei;Gui-Liu Wang
交通信号控制对我们的日常生活安全至关重要。在美国，大约四分之一的交通事故发生在交叉口，这是由于信号配时问题，这促使了以安全为导向的交叉口控制的发展。然而，现有的基于强化学习技术的自适应交通信号控制的研究主要集中在最大限度地减少交通延误，但忽略了潜在的不安全条件。我们首次将道路安全标准纳入执法范围，以确保现有强化学习方法的安全性，旨在实现零碰撞的交叉路口运营。我们提出了一种安全增强的残差强化学习方法（SafeLight），并采用了多种优化技术，如多目标损失函数和奖励整形，以更好地进行知识集成。使用合成和真实世界的基准数据集进行了广泛的实验。结果表明，我们的方法可以显着减少碰撞，同时增加流量的流动性。
Traffic signal control is safety-critical for our daily life. Roughly one-quarter of road accidents in the U.S. happen at intersections due to problematic signal timing, urging the development of safety-oriented intersection control. However, existing studies on adaptive traffic signal control using reinforcement learning technologies have focused mainly on minimizing traffic delay but neglecting the potential exposure to unsafe conditions. We, for the first time, incorporate road safety standards as enforcement to ensure the safety of existing reinforcement learning methods, aiming toward operating intersections with zero collisions. We have proposed a safety-enhanced residual reinforcement learning method (SafeLight) and employed multiple optimization techniques, such as multi-objective loss function and reward shaping for better knowledge integration. Extensive experiments are conducted using both synthetic and real-world benchmark datasets. Results show that our method can significantly reduce collisions while increasing traffic mobility.