| CPC G06V 20/588 (2022.01) [B60W 60/001 (2020.02); G06V 10/774 (2022.01); B60W 2420/42 (2013.01); B60W 2556/40 (2020.02)] | 20 Claims |
|
1. A method comprising:
obtaining, by a processor of a vehicle, a machine-learning model that is trained to identify object locations within a high definition (HD) map, the machine-learning model being previously trained based at least in part on a machine-learning algorithm and a training data set comprising 1) HD map data corresponding to a respective HD map, the HD map data identifying locations for one or more objects on the respective HD map and 2) object detection data corresponding to a respective image that has been generated from the respective HD map to depict the one or more objects;
obtaining, by the processor from a camera of the vehicle, an image of an area in which the vehicle is located;
generating, by the processor from the image, corresponding object detection data identifying locations for one or more objects depicted within the image;
obtaining, by the processor, corresponding HD map data of an HD map of the area;
providing, by the processor to the machine-learning model as input, the corresponding HD map data and the corresponding object detection data that was generated from the image of the area obtained from the camera of the vehicle;
receiving, by the processor, output generated by the machine-learning model, the output identifying, on the HD map, 1) a first location of the vehicle and 2) one or more second locations within the HD map of the one or more objects depicted within the image obtained from the camera of the vehicle; and
executing, by the processor, one or more operations based at least in part on the output.
|