US 11,734,885 B2
Systems and methods for generating synthetic light detection and ranging data via machine learning
Sivabalan Manivasagam, Toronto (CA); Shenlong Wang, Toronto (CA); Wei-Chiu Ma, Toronto (CA); and Raquel Urtasun, Toronto (CA)
Assigned to UATC, LLC, Mountain View, CA (US)
Filed by UATC, LLC, Mountain View, CA (US)
Filed on Oct. 3, 2022, as Appl. No. 17/958,797.
Application 17/958,797 is a continuation of application No. 16/567,607, filed on Sep. 11, 2019, granted, now 11,461,963.
Claims priority of provisional application 62/834,596, filed on Apr. 16, 2019.
Claims priority of provisional application 62/768,850, filed on Nov. 16, 2018.
Prior Publication US 2023/0044625 A1, Feb. 9, 2023
Int. Cl. G06T 15/00 (2011.01); G06T 17/05 (2011.01); G06T 15/06 (2011.01); G06N 20/00 (2019.01); G05D 1/02 (2020.01); G07C 5/02 (2006.01); G01S 17/89 (2020.01); G01S 17/931 (2020.01)
CPC G06T 17/05 (2013.01) [G01S 17/89 (2013.01); G01S 17/931 (2020.01); G05D 1/0231 (2013.01); G06N 20/00 (2019.01); G06T 15/06 (2013.01); G07C 5/02 (2013.01); G05D 2201/0213 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method to generate synthetic light detection and ranging (LiDAR) data, the method comprising:
generating, using a physics-based simulation engine and based at least in part on an object in an environment, an initial point cloud that comprises a plurality of points descriptive of the object; and
generating, using a machine-learned geometry network and based at least in part on the initial point cloud, an adjusted point cloud,
wherein the machine-learned geometry network was trained by evaluating a loss over synthetic point clouds generated using the machine-learned geometry network and ground truth point clouds collected by a physical LiDAR system, the loss configured to correspond to a perceptual similarity between the synthetic point clouds and the ground truth point clouds.