The Importance of Online Error Correction and Feed-Forward Adjustments in Brain-Machine Interfaces for Restoration of Movement

Abstract

Intended movement can now be decoded in real time from neural activity recorded via intracortical microelectrodes implanted in motor areas of the brain. This opens up the possibility that severely paralyzed individuals may be able to use their extracted movement commands to control various assistive devices directly. Even direct control of one's own paralyzed limbs may be possible by combining brain recording and decoding technologies with functional electrical stimulation systems that generate movement in paralyzed limbs by applying low levels of current to the peripheral nerves. However, the microelectrode arrays can record only a small fraction of the neurons that normally are used to control movement, and we are unable to decode the user's desired movement without errors. This chapter discusses experiments in which a monkey used its cortical signals to control the movements of a 3D cursor and a robotic arm in real time. Both consistent errors and random errors were seen when decoding intended movement. However, the animal learned to compensate for consistent decoding errors by making feed-forward adjustments to its motor plan. The animal also learned to compensate for random decoding errors by using visual feedback to make online error corrections to the evolving movement trajectories. This ability to compensate for imperfect decoding suggests intracortical signals may be quite useful for assistive device control even if the current technology does not perfectly extract the users native movement commands.