Method of receiving current scenario sensor data 120, determining a distance 124, 126 between the current scenario and a closest known scenario 76, if the distance is below a first threshold, manoeuvring the autonomous vehicle within a manoeuvring constraint 130 associated with the closest scenario; if the distance is above a second threshold, performing a minimal risk manoeuvre 132; and if the distance is between the first and second threshold, interpolating the manoeuvring constraint 130 associated with the closest known scenario 76. Second aspect: running known scenario as a simulation, iteratively applying dynamic parameters, and identifying a maximum dynamic parameter (e.g. speed, acceleration, jerk). Current and known scenarios may be a descriptor of multivariate distribution. Manoeuvring constraint may be a travel envelope. Minimum risk manoeuvre may be an emergency stop or pulling over. Distance may be calculated by multiple weighted machers including time wrapping, Euclidian distance, cosine distance and a learned matcher.
Controlling an autonomous vehicle
2023-11-08
Patent
Electronic Resource
English
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion |
AUTONOMOUS VEHICLE AND METHOD FOR CONTROLLING AUTONOMOUS VEHICLE
European Patent Office | 2022
|METHOD FOR CONTROLLING AUTONOMOUS VEHICLE, AND AUTONOMOUS VEHICLE
European Patent Office | 2022
|