Reach and grasp by people with tetraplegia using a neurally controlled robotic arm

Ilya Kuzovkin

11 April 2014, Tartu

Leigh R. Hochberg et al.

Nature, 17 May 2012

Paper overview

etc…

etc…

How it works?

2012 Reach and grasp by people with tetraplegia using a neurally controlled robotic arm

2011

Efficient Decoding With Steady-State Kalman Filter in Neural Interface Systems

Neural control of cursor trajectory and click by a human with tetraplegia 1000 days after implant of an intracortical microelectrode array

Point-and-Click Cursor Control With an Intracortical Neural Interface System by Humans With Tetraplegia

2010 Neural control of computer cursor velocity by decoding motor cortical spiking activity in humans with tetraplegia

2006

Neuronal ensemble control of prosthetic devices by a human with tetraplegia

Bayesian Population Decoding of Motor Cortical Activity using a Kalman Filter

2012 Reach and grasp by people with tetraplegia using a neurally controlled robotic arm

2011

Efficient Decoding With Steady-State Kalman Filter in Neural Interface Systems

Neural control of cursor trajectory and click by a human with tetraplegia 1000 days after implant of an intracortical microelectrode array

Point-and-Click Cursor Control With an Intracortical Neural Interface System by Humans With Tetraplegia

2010 Neural control of computer cursor velocity by decoding motor cortical spiking activity in humans with tetraplegia

2006

Neuronal ensemble control of prosthetic devices by a human with tetraplegia

Bayesian Population Decoding of Motor Cortical Activity using a Kalman Filter

“… uses Bayesian inference techniques to estimate hand motion from the firing rates of

multiple neurons.”

“Decoding was performed using a Kalman filter which gives an efficient recursive method for

Bayesian inference …”

“… uses Bayesian inference techniques to estimate hand motion from the firing rates of

multiple neurons.”

“… uses Bayesian inference techniques to estimate hand motion from the firing rates of

multiple neurons.”

“… uses Bayesian inference techniques to estimate hand motion from the firing rates of

multiple neurons.”

Hypothesis (hand motion)

Evidence (sequence of observed firing rates)

Posterior probability Prior probabilityLikelihood

Marginal likelihood (can be ignored since it is the same

for all hypothesis)

“… uses Bayesian inference techniques to estimate hand motion from the firing rates of

multiple neurons.”

“… uses Bayesian inference techniques to estimate hand motion from the firing rates of

multiple neurons.”

“Likelihood term models the probability of firing rates given a particular hand motion”

“… uses Bayesian inference techniques to estimate hand motion from the firing rates of

multiple neurons.”

“Likelihood term models the probability of firing rates given a particular hand motion”

“linear Gaussian model could be used to approximate this likelihood and could be readily learned from a small amount of training data”

“… uses Bayesian inference techniques to estimate hand motion from the firing rates of

multiple neurons.”

“Likelihood term models the probability of firing rates given a particular hand motion”

“linear Gaussian model could be used to approximate this likelihood and could be readily learned from a small amount of training data”

“The prior term defines a probabilistic model of hand

kinematics and was also taken to be a linear Gaussian model.”

Neural Coding

Neural Coding of Hand Kinematics

Neural Coding of Hand Kinematics

Neural Coding of Hand Kinematics

Neural Coding of Hand Kinematics

Experiment 1: 23/25 neurons are correctly described by equations (4) and (5) !Experiment 2: 39/42 neurons correctly described by (4) and (5)

Neural Coding of Hand Kinematics

Experiment 1: 23/25 neurons are correctly described by equations (4) and (5) !Experiment 2: 39/42 neurons correctly described by (4) and (5)

The relationship between the kinematics of the arm and the

behavior of the neurons is strong

Learning the model

Detour: Multivariate normal distribution

Detour: Multivariate normal distribution

Detour: Multivariate normal distribution

Why covariance matrix and not just a vector of variances?

Definitions

Definitions

Parameters of the model

Parameters of the model

H is the relation between the firing rates of each of the neurons and states of the arm

Q is covariance matrix of the noise

Parameters of the model

H is the relation between the firing rates of each of the neurons and states of the arm

Q is covariance matrix of the noise

A is the relation between the state at time k+1 and the state at time k

W is covariance matrix of the noise

Parameters of the model

H is the relation between the firing rates of each of the neurons and states of the arm

Q is covariance matrix of the noise

A is the relation between the state at time k+1 and the state at time k

W is covariance matrix of the noise

Matrices A, H, Q, W is what we want to learn from the training data

The Learning

Decoding

“Decoding was performed using a Kalman filter which gives an efficient recursive method for

Bayesian inference …”

Note that now x and z and everything else refer to the test data

“Decoding was performed using a Kalman filter which gives an efficient recursive method for

Bayesian inference …”

“Decoding was performed using a Kalman filter which gives an efficient recursive method for

Bayesian inference …”

The probability that the hand can move in

the way it did

“Decoding was performed using a Kalman filter which gives an efficient recursive method for

Bayesian inference …”

The probability that the hand can move in

the way it did

The probability that hand can end up in the state where it

was in time k-1

“… the Kalman filter operates recursively on streams of noisy input data to produce a statistically optimal estimate of the underlying system

state.” (Wikipedia)

“Decoding was performed using a Kalman filter which gives an efficient recursive method for

Bayesian inference …”

“Decoding was performed using a Kalman filter which gives an efficient recursive method for

Bayesian inference …”

“Decoding was performed using a Kalman filter which gives an efficient recursive method for

Bayesian inference …”

“Decoding was performed using a Kalman filter which gives an efficient recursive method for

Bayesian inference …”

Results

2012 Reach and grasp by people with tetraplegia using a neurally controlled robotic arm

2011

Efficient Decoding With Steady-State Kalman Filter in Neural Interface Systems

Neural control of cursor trajectory and click by a human with tetraplegia 1000 days after implant of an intracortical microelectrode array

Point-and-Click Cursor Control With an Intracortical Neural Interface System by Humans With Tetraplegia

2010 Neural control of computer cursor velocity by decoding motor cortical spiking activity in humans with tetraplegia

2006

Neuronal ensemble control of prosthetic devices by a human with tetraplegia

Bayesian Population Decoding of Motor Cortical Activity using a Kalman Filter

2006 2010

20112013

The steady-state Kalman filter significantly increases the computational efficiency for even relatively simple neural spiking data sets from a human NIS. <…> The decoding complexity is reduced dramatically by the SSKF, resulting in approximately seven-fold reduction in the execution time for decoding a typical neuronal firing rate signal.

Summary

http://braingate2.org/publications.asp