US 12,122,053 B2
Generating computer simulations of manipulations of materials based on machine learning from measured statistics of observed manipulations
Carolyn Linjon Chen, El Cerrito, CA (US); Yashraj Shyam Narang, Seattle, WA (US); Fabio Tozeto Ramos, Seattle, WA (US); and Dieter Fox, Seattle, WA (US)
Assigned to NVIDIA CORPORATION, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Jun. 29, 2020, as Appl. No. 16/916,017.
Claims priority of provisional application 62/913,688, filed on Oct. 10, 2019.
Prior Publication US 2021/0110089 A1, Apr. 15, 2021
Int. Cl. B25J 9/16 (2006.01); B25J 11/00 (2006.01); G01N 15/00 (2024.01); G06F 17/18 (2006.01); G06F 18/214 (2023.01); G06F 30/27 (2020.01); G06N 3/08 (2023.01); G06N 7/01 (2023.01); G06T 7/00 (2017.01); G06T 7/77 (2017.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01); G06V 20/64 (2022.01)
CPC B25J 9/1671 (2013.01) [B25J 9/163 (2013.01); B25J 11/008 (2013.01); G06F 17/18 (2013.01); G06F 18/214 (2023.01); G06F 30/27 (2020.01); G06N 3/08 (2013.01); G06N 7/01 (2023.01); G06T 7/0004 (2013.01); G06T 7/77 (2017.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01); G06V 20/64 (2022.01); G01N 15/00 (2013.01); G06T 2207/10028 (2013.01)] 27 Claims
OG exemplary drawing
 
1. A method of simulating a granular material, using a processor comprising one or more arithmetic logic units (ALUs), the method comprising:
deriving, from at least one recorded observation of an aggregation of the granular material, a derived set of summary statistics corresponding to motion of one or more grains of the granular material;
providing the derived set of summary statistics to an inference engine implemented using the one or more ALUs, the inference engine to infer a first posterior probability distribution corresponding to at least one physical characteristic of the one or more grains of the granular material;
applying the first posterior probability distribution to a simulation process that outputs a simulated set of summary statistics;
comparing the derived set of summary statistics to the simulated set of summary statistics to determine a comparison;
using the comparison to determine a revised posterior probability distribution based on the first posterior probability distribution, wherein the revised posterior probability distribution is over a space of possible physical characteristics of the one or more grains of the granular material; and
simulating the motion of the one or more grains of the granular material with the at least one physical characteristic based at least on the revised posterior probability distribution.