Enhanced vehicle operation
AssigneeFord Global Technologies, LLC
InventorsYan Wang, Kai Wu, Dimitar Petrov Filev, Brandon M. Dawson
Life of this patent
Estimating the term…
Abstract
Operation data from one or more vehicle subsystems are input to a vehicle dynamics model. Predicted operation data of the one or more vehicle subsystems are output from the vehicle dynamics model. The operation data and the predicted operation data are input to an optimization program that is programmed to output control directives for the one or more vehicle subsystems. One or more vehicle subsystems are operated according to the output control directives.
Claims19
A system, comprising a computer including a processor and a memory, the memory storing instructions executable by the processor to:
- input operation data from one or more vehicle subsystems to a vehicle dynamics model, wherein the vehicle dynamics model is trained to model nonlinear vehicle dynamics in the operation data to output predicted operation data of the one or more vehicle subsystems;
- output predicted operation data of the one or more vehicle subsystems from the vehicle dynamics model;
- input the operation data from the one or more vehicle subsystems and the predicted operation data output from the vehicle dynamics model that models the nonlinear vehicle dynamics to an optimization program that is programmed to output control directives for the one or more vehicle subsystems;
- and
- operate the one or more vehicle subsystems according to the output control directives;
- wherein the vehicle dynamics model includes a clustering program that assigns the operation data to one of a plurality of clusters, wherein respective clusters represent localized models of operation of the one or more vehicle subsystems, and are configured to output at least some of the predicted operation data of the one or more vehicle subsystems.
A method, comprising:
- inputting operation data from one or more vehicle subsystems to a vehicle dynamics model, wherein the vehicle dynamics model is trained to model nonlinear vehicle dynamics in the operation data to output predicted operation data of the one or more vehicle subsystems;
- outputting predicted operation data of the one or more vehicle subsystems from the vehicle dynamics model;
- inputting the operation data from the one or more vehicle subsystems and the predicted operation data output from the vehicle dynamics model that models the nonlinear vehicle dynamics to an optimization program that is programmed to output control directives for the one or more vehicle subsystems;
- and
- operating the one or more vehicle subsystems according to the output control directives;
- wherein the vehicle dynamics model includes a clustering program that assigns the operation data to one of a plurality of clusters, wherein respective clusters represent localized models of operation of the one or more vehicle subsystems, and are configured to output at least some of the predicted operation data of the one or more vehicle subsystems.
Dependencies are inferred from the claim text.