Cell Transmission Model-Based Multiagent Q-Learning for Network-Scale Signal Control With Transit Priority

摘要

This paper addresses the development of a new framework to control traffic signal lights for a road network with a recently introduced bus rapid transit (BRT) system. By applying automated goal-directed learning and decision-making called reinforcement learning, the best possible traffic signal actions can be sought upon changes of network states as modelled by the signalized cell transmission model (CTM). An extension to a network of cascading interactions with a BRT system has been proposed with simple uni-directional flows without turning movements. Motivated by the BRT system in Thailand, the conventional signalized CTM has been generalized to cope with the preplanned space-usage priority of a BRT over other non-priority vehicles. A BRT physical lane separator as well as the location of BRT stations have been explicitly modelled. The delay function of both carried passengers on BRT and on other non-priority vehicles as well as waiting passengers at stations has been introduced. The deployment of BRT system with one lane deducted by the lane separator cannot reduce the total passenger delay in comparison with the same road and traffic condition before the installation of the BRT system. Moreover, our proposed method outperforms preemptive and differential priority control methods because of the improved awareness of the signal switching cost.