Multi-point turn decision making framework for human-like automated driving

This paper proposes a new methodology of achieving human-like automated driving, and presents a decision making framework and the minimum thresholds of the occupied widths of multi-point turn for autonomous vehicles. The concept of human-like automated driving and the multi-point turn decision making framework for autonomous vehicles are proposed at first. Then, the geometric characteristics that are provided by the reference paths of turn around manoeuvres are analysed. The minimum operation widths from U Turn to Five-Point Turn are investigated respectively, and the methodology and results are then generalized to solve the multi-point turn (i.e. N-Point Turn) scenario. Finally, by using the derived results and characteristics analysed above, the functions that are able to evaluate the most feasible turn around manoeuvre within the current situation are provided.