This paper proposed a mixed traffic control algorithm for connected and autonomous vehicles (CAV) trajectory scheduling problem in a one-lane roadway with signalized intersection control. The Monte Carlo Tree Search (MCTS) model under mixed traffic flow (MCTS-MTF), was proposed for optimize the CAV movement in a mixed traffic flow of Human-Driven Vehicles (HDV) and CAV. Previous researches often simplified the problem with certain assumptions to reduce computational burden, such as dividing a vehicle trajectory into several segments with constant speed or linear acceleration/deceleration, which was rather unrealistic. Minimum constraints on CAV trajectory control were required in this manuscript, other than some basic rules such as safety consideration and vehicular performance limit. Modeling efforts were made to improve the algorithm solution quality and the runtime efficiency over naïve MCTS (n-MCTS) algorithm. This was achieved by an exploration-exploitation balance calibration module, and a tree expansion determination module to more effectively expand the tree along the desired direction. The proposed algorithm was implemented and tested in a one-lane roadway with signalized intersection control. The results found that compared with the benchmark scenario, the proposed algorithm was able to achieve a travel time saving of 3.5% and a fuel consumption of 6.5%. The proposed algorithm was also demonstrated to run 8 times the speed of a naïve MCTS model, suggesting a promising potential for real-time application for CAV trajectory control.

CICTP