US 12,189,033 B2
Modeling foliage in a synthetic environment
Richard Stenson, San Mateo, CO (US); Jacqueline Chu, San Francisco, CA (US); and Leftheris Kaleas, San Francisco, CA (US)
Assigned to GM Cruise Holdings LLC, San Francisco, CA (US)
Filed by GM Cruise Holdings LLC, San Francisco, CA (US)
Filed on Mar. 31, 2021, as Appl. No. 17/219,315.
Prior Publication US 2022/0317301 A1, Oct. 6, 2022
Int. Cl. G01S 17/89 (2020.01); G01S 17/931 (2020.01); G06F 18/214 (2023.01); G06F 18/2413 (2023.01); G06N 20/00 (2019.01); G06V 10/60 (2022.01); G06V 20/64 (2022.01)
CPC G01S 17/89 (2013.01) [G01S 17/931 (2020.01); G06F 18/214 (2023.01); G06F 18/2413 (2023.01); G06N 20/00 (2019.01); G06V 10/60 (2022.01); G06V 20/64 (2022.01)] 17 Claims
OG exemplary drawing
 
1. A method for integrating synthetic plants into a virtual scene, the method comprising:
receiving a digital asset comprising synthetic foliage;
processing the digital asset to modify at least one parameter associated with the synthetic foliage to generate a modified digital asset;
acquiring synthetic sensor data corresponding with the modified digital asset by virtually scanning the virtual scene, including the modified digital asset, using a virtual Light Detection and Ranging (LiDAR) sensor to produce the synthetic sensor data, wherein the modified digital asset and the synthetic sensor data are separate data structures;
calculating a classification score for the modified digital asset based on the synthetic sensor data; and
navigating, by an autonomous vehicle, based on the synthetic sensor data, the classification score, and a semantic label identifying an object type with the modified digital asset.