Surrounding Vehicles Motion Prediction for Risk Assessment and Motion Planning of Autonomous Vehicle in Highway Scenarios

Abstract

Safety is the cornerstone of autonomous driving vehicles. For autonomously controlled vehicles driving safely in complex and dynamic traffic scenarios, it is essential to precisely predict the evolution of the current traffic situation in the near future and make an accurate situational risk assessment. The precise motion prediction of surrounding vehicles is an essential prerequisite for risk assessment and motion planning of autonomous vehicles. In this paper, we propose a risk assessment and motion planning method for autonomously controlled vehicles based on motion prediction of surrounding vehicles. Firstly, surrounding vehicles' trajectories are predicted based on fusing constant turn rate and acceleration-based motion prediction model and maneuver-based motion prediction model with interactive multiple models. Then, considering both the probability of collision event and collision severity, the collision risk assessment between autonomously controlled vehicle and surrounding vehicles is conducted with a collision risk index. After that, the motion planning of the autonomously controlled vehicle is formulated as a multi-objectives and multi-constraints optimization problem with a model predictive control framework. Finally, the proposed method is applied to several traffic scenarios to validate its feasibility and effectiveness.