US 12,275,146 B2
Simulation of tasks using neural networks
Ankur Handa, Seattle, WA (US); Viktor Makoviichuk, San Jose, CA (US); Miles Macklin, Auckland (NZ); Nathan Ratliff, Seattle, WA (US); Dieter Fox, Seattle, WA (US); Yevgen Chebotar, Los Angeles, CA (US); and Jan Issac, Seattle, WA (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Apr. 1, 2019, as Appl. No. 16/372,274.
Prior Publication US 2020/0306960 A1, Oct. 1, 2020
Int. Cl. G05B 13/04 (2006.01); B25J 9/16 (2006.01); G05B 13/02 (2006.01); G05D 1/00 (2006.01)
CPC B25J 9/163 (2013.01) [B25J 9/1605 (2013.01); G05B 13/0265 (2013.01); G05B 13/042 (2013.01); G05D 1/0088 (2013.01); G05B 2219/50391 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
performing one or more simulations at least by iteratively adjusting a range of one or more simulation parameters representing one or more physical characteristics of one or more autonomously controlled actions of an autonomous device based, at least in part, on a measured range of the one or more physical characteristics.