US 12,248,319 B2
Regression-based line detection for autonomous driving machines
Minwoo Park, Saratoga, WA (US); Xiaolin Lin, Sunnyvale, CA (US); Hae-Jong Seo, San Jose, CA (US); David Nister, Bellevue, WA (US); and Neda Cvijetic, East Palo Alto, CA (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Jun. 23, 2023, as Appl. No. 18/340,255.
Application 18/340,255 is a continuation of application No. 18/151,012, filed on Jan. 6, 2023, granted, now 11,921,502.
Application 18/151,012 is a continuation of application No. 16/514,230, filed on Jul. 17, 2019, granted, now 11,604,944, issued on Mar. 14, 2023.
Claims priority of provisional application 62/699,669, filed on Jul. 17, 2018.
Prior Publication US 2023/0333553 A1, Oct. 19, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G05D 1/00 (2024.01); G05D 1/228 (2024.01); G06F 18/214 (2023.01); G06F 18/23 (2023.01); G06F 18/2411 (2023.01); G06N 3/04 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06V 10/14 (2022.01); G06V 10/44 (2022.01); G06V 10/48 (2022.01); G06V 10/75 (2022.01); G06V 10/764 (2022.01); G06V 10/766 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); G06V 10/94 (2022.01); G06V 20/56 (2022.01)
CPC G05D 1/0077 (2013.01) [G05D 1/0088 (2013.01); G05D 1/228 (2024.01); G06F 18/2155 (2023.01); G06F 18/23 (2023.01); G06F 18/2411 (2023.01); G06N 3/0418 (2013.01); G06V 10/457 (2022.01); G06V 10/48 (2022.01); G06V 10/751 (2022.01); G06V 10/764 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); G06V 10/955 (2022.01); G06V 20/588 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
determining, using one or more neural networks and based at least on sensor data corresponding to one or more sensor data representations:
a first output indicative of one or more distances to one or more points within the one or more sensor data representations; and
a second output indicative of a classification associated with a line;
determining, based at least on the one or more distances, a subset of points from the one or more points within the one or more sensor data representations corresponding to the line; and
causing a machine to perform one or more operations based at least on the subset of the points and the classification.