US 12,014,553 B2
Predicting three-dimensional features for autonomous driving
Ashok Kumar Elluswamy, Sunnyvale, CA (US); Matthew Bauch, San Francisco, CA (US); Christopher Payne, San Francisco, CA (US); Andrej Karpathy, San Francisco, CA (US); Dhaval Shroff, San Francisco, CA (US); Arvind Ramanandan, Sunnyvale, CA (US); and James Robert Howard Hakewill, Los Gatos, CA (US)
Assigned to TESLA, INC., Austin, TX (US)
Filed by Tesla, Inc., Palo Alto, CA (US)
Filed on Oct. 14, 2021, as Appl. No. 17/450,914.
Application 17/450,914 is a continuation of application No. 16/265,720, filed on Feb. 1, 2019, granted, now 11,150,664.
Prior Publication US 2022/0107651 A1, Apr. 7, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 20/56 (2022.01); G05D 1/00 (2006.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06T 7/20 (2017.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)
CPC G06V 20/588 (2022.01) [G05D 1/0214 (2013.01); G05D 1/0221 (2013.01); G05D 1/0223 (2013.01); G05D 1/0231 (2013.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06T 7/20 (2013.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06T 2207/20076 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30241 (2013.01); G06T 2207/30256 (2013.01); G06V 2201/10 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A system, comprising:
non-transitory computer storage media storing instructions that when executed by one or more processors, cause the one or more processors to:
obtain sensor data via one or more sensors of a vehicle;
determine, based on a machine learning model, a three-dimensional feature associated with the sensor data,
wherein the machine learning model is trained using a training dataset comprising a determined ground truth and corresponding sensor data captured within a period of time, the corresponding sensor data comprising a plurality of time series elements,
wherein the machine learning model is trained to output the determined ground truth based on an input of at least a portion of the corresponding sensor data comprising a particular time series element of the plurality of time series elements, and
wherein the determined ground truth is indicative of a three-dimensional feature associated with the corresponding sensor data; and
adjust operation of the vehicle based on the three-dimensional feature.