Mapping the relationship between neural activity and motor behavior is a central aim of sensorimotor neuroscience and neurotechnology. While most progress to this end has relied on restricting complexity, the advent of foundation models instead proposes integrating a breadth of data as an alternate avenue for broadly advancing downstream modeling. We quantify this premise for motor decoding from intracortical microelectrode data, pretraining an autoregressive Transformer on 2000 hours of neural population spiking activity paired with diverse motor covariates from over 30 monkeys and humans. The resulting model is broadly useful, benefiting decoding on 8 downstream decoding tasks and generalizing to a variety of neural distribution shifts. However, we also highlight that scaling autoregressive Transformers seems unlikely to resolve limitations stemming from sensor variability and output stereotypy in neural datasets.

This paper demonstrates a synergy-based brain-machine interface that uses low-dimensional command signals to control a high dimensional virtual hand. First, temporal postural synergies were extracted from the angular velocities of finger joints of five healthy subjects when they performed hand movements that were similar to activities of daily living. Two synergies inspired from the extracted synergies, namely, two-finger pinch and whole-hand grasp, were used in real-time brain control, where a virtual hand with 10 degrees of freedom was controlled to grasp or pinch virtual objects. These two synergies were controlled by electrocorticographic (ECoG) signals recorded from two electrodes of an electrode array that spanned motor and speech areas of an individual with intractable epilepsy, thus demonstrating closed loop control of a synergy-based brain-machine interface.

The potential of modern telecommunications and computing technologies as tools in the delivery and evaluation of assistive technology (AT) has been discussed and has been termed telerehabilitation. The problems of providing AT in rural areas parallels the delivery of health care to rural areas where the proportion of people with chronic illnesses is higher and the means to pay for them is reduced. Large distances mean long travel times, increasing costs associated with any service delivery, and consuming valuable time skilled professionals could be using to provide services elsewhere. The technology available for practising telerehabilitation is significant and expanding at a rapid rate. Currently, plain old telephone systems (POTS) and broad-band videoconferencing equipment, Internet and World Wide Web, and embedded processor systems are most widely available. These technologies continue to evolve as well as emerging technologies such as wearable sensors that will have telehabilitation applications. Issues of payment, safety liability, and licensure need to be resolved, as legislation lags the development of new technologies.