US 12,296,951 B2
Image space motion planning of an autonomous vehicle
Ryan David Kennedy, San Francisco, CA (US); Peter Benjamin Henry, San Francisco, CA (US); Hayk Martirosyan, San Francisco, CA (US); Jack Louis Zhu, San Mateo, CA (US); Abraham Galton Bachrach, Emerald Hills, CA (US); and Adam Parker Bry, Redwood City, CA (US)
Assigned to Skydio, Inc., San Mateo, CA (US)
Filed by Skydio, Inc., San Mateo, CA (US)
Filed on Sep. 8, 2023, as Appl. No. 18/463,928.
Application 17/513,179 is a division of application No. 16/789,176, filed on Feb. 12, 2020, granted, now 11,347,244, issued on May 31, 2022.
Application 18/463,928 is a continuation of application No. 18/162,227, filed on Jan. 31, 2023, granted, now 11,787,543.
Application 18/162,227 is a continuation of application No. 17/513,179, filed on Oct. 28, 2021, granted, now 11,592,845, issued on Feb. 28, 2023.
Application 16/789,176 is a continuation of application No. 15/671,743, filed on Aug. 8, 2017, granted, now 10,599,161, issued on Mar. 24, 2020.
Prior Publication US 2024/0067334 A1, Feb. 29, 2024
Int. Cl. G01C 21/34 (2006.01); B64C 39/02 (2023.01); B64U 10/14 (2023.01); G05D 1/00 (2006.01); G06T 7/246 (2017.01); G06T 7/277 (2017.01); G06T 7/593 (2017.01); G06T 17/05 (2011.01); G06V 20/13 (2022.01); G06V 20/17 (2022.01); G08G 5/00 (2006.01); G08G 5/04 (2006.01); B64U 101/32 (2023.01)
CPC B64C 39/024 (2013.01) [B64U 10/14 (2023.01); G01C 21/3453 (2013.01); G05D 1/106 (2019.05); G06T 7/246 (2017.01); G06T 7/277 (2017.01); G06T 7/593 (2017.01); G06T 17/05 (2013.01); G06V 20/13 (2022.01); G06V 20/17 (2022.01); G08G 5/0069 (2013.01); G08G 5/045 (2013.01); B64U 2101/32 (2023.01); B64U 2201/10 (2023.01); B64U 2201/20 (2023.01); G06T 2207/10021 (2013.01); G06T 2207/10032 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30188 (2013.01); G06T 2207/30241 (2013.01); G06T 2207/30252 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
a processing unit; and
a memory unit coupled to the processing unit, the memory unit including instructions stored thereon, which when executed by the processing unit, cause the system to:
process image of a physical environment to generate or modify a cost function map that associates a cost with each of multiple regions of a plurality of regions of the image,
wherein the cost comprises a value indicative of a measure of risk associated with navigating in an area of the physical environment corresponding to a corresponding region of the multiple regions of the plurality of regions of the image;
identify, based on the cost function map, a particular region of the multiple regions with an associated cost with a value that is greater than values associated with one or more other regions of the multiple regions of the plurality of regions of the image; and
optimize a trajectory for an autonomous vehicle to traverse through the physical environment trajectory by avoiding the particular region of the image and thereby reducing an overall cost of the trajectory.