BCI Award 2021 Nomination – Auto adaptive ECoG based Brain Machine Interface
The use of BCIs out of laboratory is a challenging task. One of the major drawbacks of BCIs is the necessity of training the decoders that transform brain signals into external effector commands (control decoders).The novelty of the ECoG-based project presented here is twofold: finding such a continuous in time motor task performance (cMTP) neural correlate, and proving that it can be used to perform adaptation of BCI decoders in
real time. The cases of BCIs with multiple discrete outputs and BCIs with continuous outputs with more than one degree of freedom are studied.
Vincent Rouanne1*, Thomas Costecalde1, Félix Martel1, Serpil Karakas1, Alim Louis Benabid1,2, Tetiana Aksenova1*
1 Univ. Grenoble Alpes, CEA, LETI, Clinatec, Grenoble, France
2 CHU Grenoble Alpes, Grenoble, France
The use of BCIs out of laboratory is a challenging task. One of the major drawbacks of BCIs is the necessity of training the decoders that transform brain signals into external effector commands (control decoders).The novelty of the ECoG-based project presented here is twofold: finding such a continuous in time motor task performance (cMTP) neural correlate, and proving that it can be used to perform adaptation of BCI decoders in
real time. The cases of BCIs with multiple discrete outputs and BCIs with continuous outputs with more than one degree of freedom are studied.
Vincent Rouanne1*, Thomas Costecalde1, Félix Martel1, Serpil Karakas1, Alim Louis Benabid1,2, Tetiana Aksenova1*
1 Univ. Grenoble Alpes, CEA, LETI, Clinatec, Grenoble, France
2 CHU Grenoble Alpes, Grenoble, France
