CPC G06F 9/50 (2013.01) [B64D 43/00 (2013.01); B64D 45/04 (2013.01); G06F 3/14 (2013.01); G06F 9/4881 (2013.01); G06F 18/2113 (2023.01); G06F 18/24 (2023.01); G06T 11/001 (2013.01); G06V 10/40 (2022.01); G06V 20/13 (2022.01); G06F 2209/509 (2013.01)] | 18 Claims |
1. A method for offline task-based feature processing for aerial vehicles, comprising:
extracting, by one or more processors coupled to memory of an aerial vehicle, a plurality of features from a world model generated based on a task associated with the aerial vehicle and sensor information captured by one or more sensors mounted on the aerial vehicle;
generating, by the one or more processors, a label for each of the plurality of features extracted from the world model;
identifying, by the one or more processors, a plurality of processing levels based on the plurality of features, wherein the plurality of processing levels each utilize a different amount of computing resources;
selecting, by the one or more processors, from the plurality of processing levels, a processing level for each feature of a subset of the plurality of features based on i) the task and the label associated with the feature, and ii) a distance in the world model from the aerial vehicle to each of the subset of the plurality of features;
generating, by the one or more processors, one or more processed features by applying the processing level to a respective feature of the subset of the plurality of features; and
presenting, by the one or more processors, the one or more processed features on a display device of the aerial vehicle.
|