Automated vehicle control during final assembly and dispatch
AssigneeFord Global Technologies, LLC
InventorsSmruti Panigrahi, Gregory P. Linkowski, Meghna Menon, Mario Anthony Santillo
Life of this patent
Estimating the term…
Abstract
A method of controlling an autonomously operated vehicle along a test track including the extraction of frequency characteristics of a vehicle, the determination of one or more driving profiles based on the frequency characteristics and a deep learning model, the causation of the vehicle to select at least one of the one or more driving profiles based on at least one of a plurality of track segments along the test track, and the control of the vehicle's movement along the test track based on the vehicle selecting the at least one of the one or more driving profiles and the at least one of the plurality of track segments.
Claims20
A method of controlling an autonomously operated vehicle along a test track, the method comprising:
- extracting frequency characteristics associated with the vehicle;
- determining, based on the frequency characteristics and a deep learning model trained based on the extracted frequency characteristics, one or more driving profiles;
- causing, based on at least one track segment of a plurality of track segments along the test track, the vehicle to select at least one of the one or more driving profiles;
- retrieving, from a calibration table stored in the vehicle, pre-calibrated values for control parameters associated with the at least one track segment;
- and
- controlling movement of the vehicle along the test track based on the at least one of the plurality of track segments, the pre-calibrated values for the control parameters, and the vehicle selecting the at least one of the one or more driving profiles.
A marshalling system for controlling an autonomously operated vehicle along a test track, the marshalling system comprising:
- a server configured to:
- extract frequency characteristics associated with the vehicle,
- determine, based on the frequency characteristics and a deep learning model trained based on the extracted frequency characteristics, one or more driving profiles,
- cause, based on at least one track segment of a plurality of track segments along the test track, the vehicle to select at least one of the one or more driving profiles,
- retrieve, from a calibration table stored in the vehicle, pre-calibrated values for control parameters associated with the at least one track segment;
- and
- control movement of the vehicle along the test track based on the at least one of the plurality of track segments, the pre-calibrated values for the control parameters, and the vehicle selecting the at least one of the one or more driving profiles;
- and
- the vehicle configured to automatically select the at least one of the one or more driving profiles.
One or more non-transitory computer-readable media storing processor-executable instructions that, when executed by at least one processor, cause the at least one processor to:
- extract frequency characteristics associated with a vehicle;
- determine, based on the frequency characteristics and a deep learning model trained based on the extracted frequency characteristics, one or more driving profiles;
- cause, based on at least one track segment of a plurality of track segments along a test track, the vehicle to select at least one of the one or more driving profiles;
- retrieve, from a calibration table stored in the vehicle, pre-calibrated values for control parameters associated with the at least one track segment;
- and
- control movement of the vehicle along the test track based on the at least one of the plurality of track segments, the pre-calibrated values for the control parameters, and the vehicle selecting the at least one of the one or more driving profiles.
Dependencies are inferred from the claim text.