POINT: Partially Observable Imitation Network for Traffic Signal Control

Abstract

Listen

Translate article

• This is the first study in the area of traffic signal control that combines the optimization-based signal control algorithm with imitation learning network to generate optimal signal plans in real time. • The proposed model does not need 100% penetration rate of CVs or necessity of complete traffic information in online system. Instead, only partial observable traffic information collected in real time are required for the POINT model. • The proposed model accounts for the stochastic features of traffic flows and diversities of driving behaviors in offline expert signal plan collection. • The proposed model has largely reduced the online computational burden and ready to be implemented in real world. Smart traffic signals bring together transportation infrastructure and advance technologies to improve the mobility and efficiency of urban transportation network. Adaptive traffic signal control studies can be categorized into modeling-based approaches and learning-based approaches. In order to take advantages of these two systems, this study developed an offline-online combined Partial Observable Imitation Network for Traffic signal control (POINT). In the offline system, the traffic signal timing optimization problem was formulated as a Mixed Integer Nonlinear Programming (MINLP) given complete traffic information, i.e., second-by-second speeds and locations of all vehicles. The objective of MINLP is to minimize total travel delays considering individual vehicle trajectories under Connected Vehicle (CV) environment. The calculated optimal solutions under various traffic conditions were considered as the ”expert” decisions. In the online system, an imitation neural network model was developed to learn the ”expert” signal plans generated from offline system. Given partial observable traffic conditions in real time, e.g., the aggregate-level of traffic volume, the POINT model can compute the signal timing parameters in the online system. The numerical results demonstrated that the proposed method outperformed other state-of-the-art signal control method under high and unbalanced traffic demand levels in terms of reducing travel delays and queue length.