System and method for brain machine interface (BMI) control using reinforcement learning
US9050200B2 · kind B2 · utility
6Cited by
6References
28Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Apr 25, 2008 |
| Grant date | Jun 9, 2015 |
| Priority date | — |
| Expiry date | Dec 24, 2030 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/092
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A Brain Machine Interface (BMI) agent (110) is provided, that when operatively coupled to a subject during a mental task by the subject to control a prosthetic device (130), monitors one or more states (125) of neural activity of the subject, receives feedback associated with a behavior of the prosthetic device responsive to the control, learns a functional mapping between the mental task and the behavior in view of the feedback, and applies at least one control action (115) to the prosthetic device in accordance with the learning to control the prosthetic device for a targeted behavior.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.