An adaptive closed-loop ECoG decoder for long-term and stable bimanual control of an exoskeleton by a tetraplegic

TL;DR

This paper presents an adaptive, stable brain-computer interface for long-term control of a bimanual exoskeleton in a tetraplegic patient, using a novel tensor-based decoder that requires no recalibration over six months.

Contribution

The study introduces the REW-MSLM decoder, enabling robust, long-term, calibration-free control of a bimanual exoskeleton via epidural ECoG signals.

Findings

Stable 8-dimensional control over 6 months

No decoder recalibration needed during the period

Successful asynchronous control of exoskeleton and avatar

Abstract

Brain-computer interfaces (BCIs) still face many challenges to step out of laboratories to be used in real-life applications. A key one persists in the high performance control of diverse effectors for complex tasks, using chronic and safe recorders. This control must be robust over time and of high decoding performance without continuous recalibration of the decoders. In the article, asynchronous control of an exoskeleton by a tetraplegic patient using a chronically implanted epidural electrocorticography (EpiCoG) implant is demonstrated. For this purpose, an adaptive online tensor-based decoder: the Recursive Exponentially Weighted Markov-Switching multi-Linear Model (REW-MSLM) was developed. We demonstrated over a period of 6 months the stability of the 8-dimensional alternative bimanual control of the exoskeleton and its virtual avatar using REW-MSLM without recalibration of the decoder.