Cooperative Comfortable-Driving at Signalized Intersections for Connected and Automated Vehicles

Abstract

This letter proposes a control framework for Connected and Automated Vehicles(CAVs) to approach the signalized intersections with good driving-comfortability. Both the velocity plan and longitudinal dynamics control are concerned in this study. Regarding the velocity plan problem, a two-layer framework is designed. First, a scenario identifier method is proposed to identify which scenario the target velocity profile should be according to the current vehicle speed, distance to the intersection, and traffic signal information. Then, an assigned-time velocity planning problem with velocity and acceleration constraints is formulated and solved to obtain a smooth velocity profile with the minimal jerk. For the longitudinal dynamics control, a predictive controller with Online Sequential Extreme Learning Machine(OSELM) is applied to realize the smooth velocity profile tracking. CarMaker-Simulink co-simulation has been conducted to validate the proposed method. The validation results show that the proposed method can identify the scenario in 100% of the time according to the validation results. On the other hand, the OSELM-based predictive control has improved MSE $e_v,e_a,e_{jerk}$ of 33.85%, 27.66%, and 38.03% respectively than PID control.