US 11,798,122 B2
Vision architecture
Sarah Tariq, Palo Alto, CA (US); and Zejia Zheng, Palo Alto, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Aug. 15, 2022, as Appl. No. 17/887,925.
Application 17/887,925 is a continuation of application No. 16/786,288, filed on Feb. 10, 2020, granted, now 11,416,959.
Prior Publication US 2022/0392013 A1, Dec. 8, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 1/20 (2006.01); G06T 1/60 (2006.01); G05D 1/02 (2020.01); G05D 1/00 (2006.01)
CPC G06T 1/20 (2013.01) [G05D 1/0088 (2013.01); G05D 1/0246 (2013.01); G06T 1/60 (2013.01); G05D 2201/0213 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30252 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A method performed by one or more processors of an autonomous operation system of an autonomous vehicle, the method comprising:
determining, in response to an invocation of vision processing on first vision data stored in a first memory range in a first memory associated with a central processing unit (CPU) of the one or more processors, that second vision data stored in a second memory range in a second memory associated with a graphic processing unit (GPU) of the one or more processors is a modified copy of the first vision data;
replacing, using a non-blocking operation, the first vision data stored in the first memory range with the second vision data from the second memory range;
performing, by the CPU, the vision processing using the second vision data stored in the first memory range;
detecting an object based at least in part on an output of the vision processing, by the CPU, using the second vision data stored in the first memory range;
generating control information for the autonomous vehicle based on the object; and
controlling the autonomous vehicle based on the control information.