The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.
The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.
Patent No.:
Date of Patent:
Apr. 16, 2024
Filed:
Aug. 20, 2020
Applicant:
Nvidia Corporation, Santa Clara, CA (US);
Inventors:
Ajay Uday Mandlekar, Cupertino, CA (US);
Fabio Tozeto Ramos, Seattle, WA (US);
Byron Boots, Seattle, WA (US);
Animesh Garg, Berkeley, CA (US);
Dieter Fox, Seattle, WA (US);
Assignee:
NVIDIA CORPORATION, Santa Clara, CA (US);
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
B62D 15/02 (2006.01); B25J 1/02 (2006.01); B60W 30/06 (2006.01); B60W 60/00 (2020.01); G05B 13/02 (2006.01); G06N 3/04 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01);
U.S. Cl.
CPC ...
B62D 15/0285 (2013.01); B25J 1/02 (2013.01); B60W 30/06 (2013.01); B60W 60/0025 (2020.02); G05B 13/027 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01);
Abstract
A framework for offline learning from a set of diverse and suboptimal demonstrations operates by selectively imitating local sequences from the dataset. At least one embodiment recovers performant policies from large manipulation datasets by decomposing the problem into a goal-conditioned imitation and a high-level goal selection mechanism.