Independent Mobility Achieved through a Wireless Brain-Machine Interface

Abstract

Individuals with tetraplegia lack independent mobility, making them highly dependent on others to move from one place to another. Here, we describe how two macaques were able to use a wireless integrated system to control a robotic platform, over which they were sitting, to achieve independent mobility using the neuronal activity in their motor cortices. The activity of populations of single neurons was recorded using multiple electrode arrays implanted in the arm region of primary motor cortex, and decoded to achieve brain control of the platform. We found that free-running brain control of the platform (which was not equipped with any machine intelligence) was fast and accurate, resembling the performance achieved using joystick control. The decoding algorithms can be trained in the absence of joystick movements, as would be required for use by tetraplegic individuals, demonstrating that the non-human primate model is a good pre-clinical model for developing such a cortically-controlled movement prosthetic. Interestingly, we found that the response properties of some neurons differed greatly depending on the mode of control (joystick or brain control), suggesting different roles for these neurons in encoding movement intention and movement execution. These results demonstrate that independent mobility can be achieved without first training on prescribed motor movements, opening the door for the implementation of this technology in persons with tetraplegia.

Towards Autonomous Intra-cortical Brain Machine Interfaces: Applying Bandit Algorithms for Online Reinforcement Learning

“…iBMIs literally transform thought into action. The input to this system is neural signals recorded from the surface of the motor cortex to drive effectors such as cursors [2], prosthetic limbs [3], wheelchairs [4] and so on.…”

Sparse Ensemble Machine Learning to improve robustness of long-term decoding in iBMIs

“…Joystick movement was restricted to right, left and forward directions only. In the top portion, a multi-electrode array is shown to be implanted in the hand and arm regions of primary motor cortex [19], (b) Experiment 1 setup: NHP A was seated in a robotic wheelchair. The wheelchair translated in the forward, left or right directions in discrete time steps of 100 ms depending on the position of the joystick [19], (c) Experiment 2 setup: NHP B is trained to drive a virtual wheelchair using a joystick in a manner similar to experiment 1.…”

“…In the top portion, a multi-electrode array is shown to be implanted in the hand and arm regions of primary motor cortex [19], (b) Experiment 1 setup: NHP A was seated in a robotic wheelchair. The wheelchair translated in the forward, left or right directions in discrete time steps of 100 ms depending on the position of the joystick [19], (c) Experiment 2 setup: NHP B is trained to drive a virtual wheelchair using a joystick in a manner similar to experiment 1. Figures (a), (b) are adapted from [19] (CC-BY license) and Figure (c) is adapted from [20] (CC-BY license) Authors in [14], [27] have presented a decoder being updated in a retrospective fashion after every block of trials in a human subject based point and click cursor experiment.…”

“…The wheelchair translated in the forward, left or right directions in discrete time steps of 100 ms depending on the position of the joystick [19], (c) Experiment 2 setup: NHP B is trained to drive a virtual wheelchair using a joystick in a manner similar to experiment 1. Figures (a), (b) are adapted from [19] (CC-BY license) and Figure (c) is adapted from [20] (CC-BY license) Authors in [14], [27] have presented a decoder being updated in a retrospective fashion after every block of trials in a human subject based point and click cursor experiment. Sustained performance has been reported employing this approach in a closed loop study involving 11 sessions spanning 29 days [27] and 6 sessions spanning 42 days [14] in two human subjects.…”

Experimental Comparison of Hardware-Amenable Spike Detection Algorithms for iBMIs

“…Intra-cortical Brain Machine Interfaces (iBMIs) have enabled patients suffering from debilitating spinal cord afflictions to regain a sense of control through demonstrations such as [1], [2] where the subjects are successfully able to feed themselves and [3] where record communication speeds have been achieved among other things [4], [5]. Spikes serve as an input to these systems, where instantaneous firing rates are computed on every recorded electrode and subsequently mapped to a behavioral co-variate to drive an effector or stimulate a paralysed limb.…”