US 12,346,117 B2
Guiding vehicles through vehicle maneuvers using machine learning models
Chenyi Chen, Fremont, CA (US); Artem Provodin, Highlands, NJ (US); and Urs Muller, Keyport, NJ (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Jun. 11, 2024, as Appl. No. 18/740,131.
Application 18/740,131 is a continuation of application No. 18/355,148, filed on Jul. 19, 2023, granted, now 12,032,380.
Application 18/355,148 is a continuation of application No. 18/153,072, filed on Jan. 11, 2023, granted, now 11,755,025, issued on Sep. 12, 2023.
Application 18/153,072 is a continuation of application No. 17/322,365, filed on May 17, 2021, granted, now 11,609,572, issued on Mar. 21, 2023.
Application 17/322,365 is a continuation of application No. 16/241,005, filed on Jan. 7, 2019, granted, now 11,042,163, issued on Jun. 22, 2021.
Claims priority of provisional application 62/614,466, filed on Jan. 7, 2018.
Prior Publication US 2024/0329639 A1, Oct. 3, 2024
Int. Cl. G06N 3/08 (2023.01); B60W 30/00 (2006.01); B60W 30/18 (2012.01); B62D 15/02 (2006.01); G05D 1/00 (2006.01); G05D 1/81 (2024.01); G06N 3/045 (2023.01); G06N 20/00 (2019.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01)
CPC G05D 1/0221 (2013.01) [B60W 30/00 (2013.01); B60W 30/18154 (2013.01); B62D 15/02 (2013.01); B62D 15/025 (2013.01); B62D 15/0255 (2013.01); G05D 1/0088 (2013.01); G05D 1/81 (2024.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/588 (2022.01); B60W 2420/403 (2013.01); B60W 2420/408 (2024.01)] 20 Claims
OG exemplary drawing
 
1. A system on a chip (SoC) comprising:
one or more central processing units (CPUs);
one or more graphics processing units (GPUs);
one or more image signal processors (ISPs);
one or more vision accelerators;
one or more processor subsystems for safety management,
wherein the SoC, at least in part, causes performance of one or more maneuvers corresponding to a vehicle based at least on control data determined using one or more learning models and based at least on map data from one or more maps and sensor data from one or more sensors of the vehicle.