US 12,293,538 B2
Computer vision classifier defined path planning for unmanned aerial vehicles
William S. Bowman, Melbourne, FL (US); Mark B. Moffett, Grant, FL (US); Andrew D. Falendysz, Grant, FL (US); Michael E. Bowman, Satellite Beach, FL (US); Michael W. Holt, Smyrna, GA (US); Timothy M. Williams, Indialantic, FL (US); Matthew R. Danko, Melbourne, FL (US); and Matthew D. Summer, Melbourne, FL (US)
Assigned to Tomahawk Robotics, Inc., Melbourne, FL (US)
Filed by Tomahawk Robotics, Inc., Melbourne, FL (US)
Filed on Aug. 8, 2023, as Appl. No. 18/446,450.
Prior Publication US 2025/0054175 A1, Feb. 13, 2025
Int. Cl. G06T 7/70 (2017.01); G06T 7/50 (2017.01); G06T 7/90 (2017.01)
CPC G06T 7/70 (2017.01) [G06T 7/50 (2017.01); G06T 7/90 (2017.01); G06T 2207/10024 (2013.01); G06T 2207/10028 (2013.01); G06T 2207/10032 (2013.01); G06T 2207/20081 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A system for adjusting flight paths using terrain guidance, the system comprising:
one or more processors; and
one or more non-transitory, computer-readable storage media storing instructions, which, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving, at an aerial vehicle, an image recorded by a camera on board the aerial vehicle, wherein the camera is configured to record images of terrain below the aerial vehicle;
inputting the image into a machine learning model to detect a first plurality of objects with the image, wherein the machine learning model is trained to detect objects within received images, and wherein the machine learning model outputs a corresponding shape representing each object and one or more colors representing pixels of each object;
retrieving an electronic map comprising a second plurality of objects, wherein each object within the second plurality of objects is associated with a location comprising a latitude and a longitude, and wherein each object of the second plurality of objects is represented by a corresponding stored shape and a corresponding stored one or more colors;
determining, based on each corresponding color and each corresponding shape, whether one or more objects within the first plurality of objects match the one or more objects within the second plurality of objects;
in response to determining that the one or more objects within the first plurality of objects match the one or more objects within the second plurality of objects, retrieving object locations for the one or more objects;
determining, based on the object locations for the one or more objects, a vehicle location for the aerial vehicle, wherein the vehicle location is calculated based on a horizontal distance to each object and a corresponding latitude and a corresponding longitude of each object; and
generating a flight instruction based on the vehicle location and a target location.