Brain Machine Interface utilizing a Discrete Action State Decoder in Parallel with a Continuous Decoder for a Neural Prosthetic Device

• US 20140081454A1
• Filed: 09/12/2013
• Published: 03/20/2014
• Est. Priority Date: 09/17/2012
• Status: Active Grant

• Current Assignee: Board of Trustees of the Leland Stanford Junior University (Stanford University)
• Original Assignee: Board of Trustees of the Leland Stanford Junior University (Stanford University)
• Inventors: Nuyujukian, Paul, Shenoy, Krishna V., Kao, Jonathan C.
• Granted Patent: US 9,373,088 B2
• Time in Patent Office: Days
• US Class Current: 700/246
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/00 Computing arrangements based on biological models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: Y10S 901/03 Teaching system
• CPC Class Codes: Y10S 901/27 Arm part

Abstract

A brain machine interface for control of prosthetic devices is provided. In its control, the interface utilizes parallel control of a continuous decoder and a discrete action state decoder. In the discrete decoding, we not only learn states affiliated with the task, but also states related to the velocity of the prosthetic device and the engagement of the user. Moreover, we not only learn the distributions of the neural signals in these states, but we also learn the interactions/transitions between the states, which is crucial to enabling a relatively higher level of performance of the prosthetic device. Embodiments according to this parallel control system enable us to reliably decode not just task-related states, but any “discrete action state,” in parallel with a neural prosthetic “continuous decoder,” to achieve new state-of-the-art levels of performance in brain-machine interfaces.

Claims

1. A method of controlling a prosthetic device, comprising:

a brain machine interface for controlling said prosthetic device based on neural brain signals, wherein said brain machine interface in said control executes in parallel a continuous decoder and a discrete action state decoder,

wherein said continuous decoder controls kinematics of said prosthetic device based on said neural brain signals as input to said continuous decoder,

wherein said discrete action state decoder controls discrete action states of said prosthetic device based on said neural brain signals as input to said discrete action state decoder, wherein said discrete action states comprise;

(i) discrete velocity states of said prosthetic device,

(ii) discrete idle states; and

(iii) discrete task states of said prosthetic device,

wherein said discrete action state decoder is based on learning models, wherein said learning comprises;

(j) learning distribution models of neural data for each of said states (i), (ii) and (iii); and

(jj) learning probability transition models between said states (i), (ii) and (iii).