Artificial intelligence system for modeling and evaluating robotic success at task performance
US10766136B1 · kind B1 · utility
22Cited by
0References
15Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Nov 3, 2017 |
| Grant date | Sep 8, 2020 |
| Priority date | — |
| Expiry date | Dec 21, 2037 |
Classification
- Technology area (CPC Y)Emerging Cross-Sectional Technologies
- CPC primaryY10S901/47
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A machine learning system builds and uses computer models for identifying how to evaluate the level of success reflected in a recorded observation of a task. Such computer models may be used to generate a policy for controlling a robotic system performing the task. The computer models can also be used to evaluate robotic task performance and provide feedback for recalibrating the robotic control policy.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.