Lane Departure Risk Assessment for Hands-free Driving Functions

Hands-free driving has become increasingly appealing and popular as an advanced form of SAE Level 2 automation, especially in premium brands. Such kind of advanced driver assistance system must ensure safety via a risk assessment module to initiate human take-over request if necessary. In lane keeping scenario, accurate trajectory prediction of the ego vehicle is vital to lane departure risk assessment. Thanks to automated driving, the actual control laws are known or can be learnt, which can support more precise prediction. Here we propose a Kalman predictor with actual control laws for future ego vehicle trajectory prediction. With a simulated scenario with varying velocity and road curvature, the algorithm is proved effective and outperforms traditional physics-based trajectory prediction benchmarks. Comparison between algorithms considering only lateral control law is also carried out, and results show that the algorithm considering both longitudinal and lateral control laws has better prediction accuracy. The proposed algorithm is promising to be applied in risk assessment module of hands-free driving functions.