Vehicle trajectory prediction and collision warning for lane change conditions

Abstract

With the gradual increase in the number of vehicles on the road, the number of traffic accidents has also increased. Inappropriate lane changing is an important cause of traffic accidents. Based on the above problems, it is of great significance to study vehicle trajectory prediction and collision warning under lane changing conditions. Therefore, this paper proposes a collision warning algorithm based on S-shaped conditions for vehicle trajectory prediction and collision warning. The method can provide collision warnings so that vehicle collisions can be avoided. In this study, the trajectories of the surrounding vehicles in the constructed scenario are predicted by long- and short-term neural networks. At the same time, a B-spline curve is used to plan the lane change path of the vehicle when it encounters an obstacle. Next, a linear quadratic regulator trajectory tracking control algorithm is used to track the planned path. Finally, the predicted trajectories of the surrounding vehicles and the planned trajectories of the experimental vehicles are simulated and analyzed to provide collision warning. The simulation results show that the method can provide a 2s warning of whether a vehicle can change lanes or not. The study combines trajectory prediction and path planning, which is an important reference for collision warning research in autonomous driving.

Keywords:

• model construction
• lane change path planning
• trajectory prediction
• collision warning

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

The project is supported partly by the National Natural Science Foundation of China (No. 52107220), Postdoctoral Research Fund Project of China (No. 2021M690353), Foundation of State Key Laboratory of Automotive Simulation and Control (No. 20210211), Scientific and Technological Innovation Foundation of Foshan (No. BK21BE012), Postdoctor Research Foundation of Shunde Graduate innovation School of University of Science and Technology Beijing (No. 2021BH007), Fundamental Research Funds for the Central Universities (No. FRF-BD-20-08A, NO.FRF-IDRY-21-013).