	US 12,260,332 B2
	Data pipeline and deep learning system for autonomous driving
Timofey Uvarov, San Carlos, CA (US); Brijesh Tripathi, Los Altos, CA (US); and Evgene Fainstain, San Jose, CA (US)
Assigned to Tesla, Inc., Austin, TX (US)
Filed by Tesla, Inc., Austin, TX (US)
Filed on Jul. 17, 2023, as Appl. No. 18/353,821.
Application 18/353,821 is a continuation of application No. 17/644,748, filed on Dec. 16, 2021, granted, now 11,734,562.
Application 17/644,748 is a continuation of application No. 16/013,817, filed on Jun. 20, 2018, granted, now 11,215,999, issued on Jan. 4, 2022.
Prior Publication US 2023/0359897 A1, Nov. 9, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 3/08 (2023.01); B60W 60/00 (2020.01); G05D 1/00 (2024.01); G06N 3/04 (2023.01); G06V 10/10 (2022.01); G06V 10/20 (2022.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01)

CPC G06N 3/08 (2013.01) [B60W 60/001 (2020.02); G05D 1/0088 (2013.01); G05D 1/0221 (2013.01); G05D 1/0246 (2013.01); G06N 3/04 (2013.01); G06V 10/17 (2022.01); G06V 10/20 (2022.01); G06V 10/44 (2022.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01)]

20 Claims

1. A method, comprising:

receiving sensor data using one or more sensors of a vehicle;

extracting a global data component and a feature data component from the sensor data to form input data, wherein the global data component is associated with global illumination data and the feature data component is associated with edge data;

providing at least a first portion and at least a second portion of the input data to a respective first layer and second layer of a convolutional neural network comprising a plurality of layers, wherein the plurality of layers are sequential and form respective portions of the convolutional neural network; and

obtaining, based on a result of the convolutional neural network, information indicating a vehicle control result which informs autonomous operation of the vehicle.