Citation

Zhang L, Gao J, Lan L, Li B, Sun H. Int. J. Veh. Des. 2021; 87(1/2/3/4): 95-119.

Copyright

(Copyright © 2021, Inderscience Publishers)

DOI

10.1504/IJVD.2021.122690

PMID

unavailable

Abstract

A novel cooperative collision warning system (CCWS) based on trajectory prediction and conflict risk evaluation is proposed to guarantee driving safety at intersections. First, a vehicle kinematics model is introduced based on the constant acceleration model, turn rate and acceleration model respectively. The extended Kalman filtering (EKF) is applied to integrate the signal of global position system (GPS) and on-board vehicle sensors and filter the noise data of both to realise the real-time estimation of vehicle position. Then, based on the intersection's road geometry information, a cubic parabola model is established to simulate the driver's future manoeuvres. Considering the prediction uncertainty, the Gaussian process regression (GPR) is used to fit the vehicle's trajectory within 0-2 s in the future and further deduce the vehicle trajectory of the next 2-2.5 s. Simulation results show that the proposed algorithm has a higher precision of trajectory prediction.

Language: en