Existing signalized intersection control methods allocate intersection resources to each phase from the time dimension based on traffic conflict. Solving the traffic control issues caused by the unbalanced traffic demands at intersections is always a challenge. Recently developed connected and automated vehicle (CAV) technologies render it possible to collect detailed real-time traffic information from vehicles for the optimal control and management of time-space resources at signalized intersections. In this paper, we propose a mixed integer quadratic programming to jointly optimize signal timings and variable guide lane settings for a typical four-arm intersection in the CAV environment. From the time dimension, restrictions of the conventional concept of the signal cycle are overcome.Phase sequences, green start, and duration are freely assigned for each CAV platoon based on the movement-based signal timing. From the space dimension, lane resources can be reasonably allocated in consideration of the dynamic traffic demand distribution. In this study, a demand-response control is realized for the signalized intersection through time-space resources cooperated optimization. Furthermore, vehicle trajectory control is integrated into the collaborative control framework to reduce or eliminate wasted green time. At last, we propose the dynamic control process using the collaborative control framework. Numerical simulation results show that the collaborative control method outperforms over fixed-time and signal optimization control modes in terms of travel time with both under-saturated and over-saturated conditions.

No abstract

No abstract

Observability and controllability are two critical requirements for a partially observable transportation system. This paper proposes a stepwise signal optimization framework with connected vehicle (CV) data as input to solve both challenges. First, a Bayesian deduction method based on low‐penetration CV data is established to estimate the traffic volume. Thereafter, an offline signal optimization model is constructed to simultaneously optimize the flexible lane settings and signal timings, which are set as the prior information for the third step. In the third step, an online deep recurrent Q‐learning (DRQN) signal optimization model dynamically adjusts signal settings based on real‐time traffic information. Numerical experiments demonstrate that the model outperforms the actuated control, the online DQRN model without offline filter, and the back‐pressure model by 9%–66% and 7%–29% in two networks. This study innovatively combines traffic state estimation and traffic signal control as an integrated process. It contributes to an improved understanding of traffic control in a CV environment and lays a solid foundation for future traffic control strategies.