In this paper we present DALI, a distributed, collaborative multi-agent traffic signal timing system (TST) for highly dynamic traffic conditions. In DALI, intersection controllers are augmented with software agents which collaboratively adapt signal timings by considering the feedback of all controller agents that may be affected by a change. The model is based on a real-world TST and will be deployed with minimal changes to the infrastructure. DALI has been validated by traffic engineers as well as through extensive simulation of the City of Richardson’s traffic network, comprising 128 signalized intersections. The experimental results show that, in highly dynamic scenarios, DALI outperforms the conventional traffic system used by the city as well as a state-of-the-art reinforcement learning-based TST.

中文翻译：

---

基于协作代理的交通信号系统，用于高度动态的交通状况

在本文中，我们介绍了DALI，这是一种用于高度动态交通状况的分布式协作式多代理交通信号定时系统（TST）。在DALI中，交叉路口控制器增加了软件代理，可以通过考虑可能受更改影响的所有控制器代理的反馈来协作地调整信号时序。该模型基于真实的TST，将在对基础结构进行最小更改的情况下进行部署。DALI已通过交通工程师的验证，并已通过对包括128个信号交叉口的理查森市交通网络的广泛仿真进行了验证。实验结果表明，在高度动态的情况下，DALI的性能优于城市使用的常规交通系统以及最新的基于强化学习的TST。