| CPC G06N 7/01 (2023.01) [G06F 18/2148 (2023.01); G06F 18/22 (2023.01); G06F 30/27 (2020.01); G06F 30/20 (2020.01)] | 11 Claims |
|
1. A method for updating an autonomous vehicle, the method comprising the following steps:
providing a simulation probability distribution including a number x of simulation time series, and providing a reference probability distribution including a number y of reference time series;
determining a first Gaussian random process for the simulation probability distribution, and determining a second Gaussian random process for the reference probability distribution, each of the first and second Gaussian random processes being assigned a respective mean and a respective covariance matrix;
calculating, by a processor system that includes at least one processor, a model form error using a 2-Wasserstein distance between the first Gaussian random process and the second Gaussian random process based on a Euclidean distance of the respective means of the first and second Gaussian random processes and based on a trace of the respective covariance matrices of the first and second Gaussian random processes;
determining, by the processor system, a family of simulation probability distributions by integrating the model form error into an updated version of the first Gaussian random process;
modifying, by the processor system, a simulation model based on the family of simulation probability distributions;
running, by the processor system, a hardware in the loop (HiL) or a software in the loop (SiL) simulation of a controller of the autonomous motor vehicle with the simulation model; and
based on results of the simulation modifying, by the processor system, the controller of the autonomous motor vehicle, thereby modifying an operability of the autonomous motor vehicle.
|