US 12,271,194 B2
Using neural networks to perform fault detection in autonomous driving applications
Richard Bramley, Santa Clara, CA (US); Philip Payman Shirvani, San Mateo, CA (US); and Nirmal Saxena, Los Altos Hills, CA (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Jan. 20, 2023, as Appl. No. 18/157,365.
Application 18/157,365 is a continuation of application No. 16/745,238, filed on Jan. 16, 2020, granted, now 11,592,828.
Prior Publication US 2023/0152805 A1, May 18, 2023
Int. Cl. G05D 1/00 (2024.01); G06F 18/2431 (2023.01); G06N 3/04 (2023.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/98 (2022.01); G06V 20/56 (2022.01)
CPC G05D 1/0088 (2013.01) [G05D 1/0221 (2013.01); G05D 1/0246 (2013.01); G06F 18/2431 (2023.01); G06N 3/04 (2013.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/98 (2022.01); G06V 20/56 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
applying, to one or more machine learning models (MLMs), input data including (i) first data representing a frame of sensor data generated using one or more sensors of a machine and (ii) second data representing one or more patterns incorporated into a portion of the input data that is separate from the frame of the sensor data based at least on the one or more MLMs being trained to perform one or more tasks corresponding to the one or more patterns;
determining, based at least on the applying, one or more predictions corresponding to the input data;
performing an evaluation of the one or more predictions with respect to the one or more patterns; and
performing one or more operations associated with the machine based at least on the evaluation.