US 11,769,052 B2
Distance estimation to objects and free-space boundaries in autonomous machine applications
Junghyun Kwon, San Jose, CA (US); Yilin Yang, Santa Clara, CA (US); Bala Siva Sashank Jujjavarapu, Sunnyvale, CA (US); Zhaoting Ye, Santa Clara, CA (US); Sangmin Oh, San Jose, CA (US); Minwoo Park, Saratoga, CA (US); and David Nister, Belleview, WA (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Sep. 29, 2021, as Appl. No. 17/449,310.
Application 17/449,310 is a continuation of application No. 16/813,306, filed on Mar. 9, 2020, granted, now 11,170,299.
Application 16/813,306 is a continuation in part of application No. 16/728,595, filed on Dec. 27, 2019, granted, now 11,308,338.
Claims priority of provisional application 62/786,188, filed on Dec. 28, 2018.
Prior Publication US 2022/0019893 A1, Jan. 20, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/00 (2022.01); G06N 3/08 (2023.01); B60W 30/14 (2006.01); B60W 60/00 (2020.01); G06V 20/56 (2022.01); G06F 18/214 (2023.01); G06V 10/762 (2022.01)
CPC G06N 3/08 (2013.01) [B60W 30/14 (2013.01); B60W 60/0011 (2020.02); G06F 18/2155 (2023.01); G06V 10/763 (2022.01); G06V 20/56 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A processor comprising:
processing circuitry to:
compute, using a deep neural network (DNN) and based at least in part on sensor data generated using one or more sensors of an ego-machine, first data representative of first depth values corresponding to one or more objects and second data representative of second depth values corresponding to one or more free-space boundaries; and
perform one or more operations for controlling the ego-machine based at least in part on the first depth values and the second depth values.