Authors:
Michele Folgheraiter
1
;
Elsa Andrea Kirchner
2
;
Anett Seeland
1
;
Su Kyoung Kim
2
;
Mathias Jordan
1
;
Hendrik Wöhrle
1
;
Bertold Bongardt
1
;
Steffen Schmidt
1
;
Jan Christian Albiez
1
and
Frank Kirchner
2
Affiliations:
1
German Research Center for Artificial Intelligence (DFKI), Germany
;
2
German Research Center for Artificial Intelligence (DFKI) and University of Bremen, Germany
Keyword(s):
Haptic Interface, Bio-Inspired Design, Brain-Computer Interface, Wearable Exoskeleton, Support Vector Machine, Adaptive Brain Reading Interface, Electroencephalogram, Lateralized Readiness Potential, Bereitschaftspotential.
Related
Ontology
Subjects/Areas/Topics:
Biomechanical Devices
;
Biomedical Engineering
;
Biomedical Instruments and Devices
;
Biorobotics
;
Brain-Computer Interfaces
;
Devices
;
Human-Computer Interaction
;
Physiological Computing Systems
Abstract:
This work introduces the architecture of a novel brain-arm haptic interface usable to improve the operation of complex robotic systems, or to deliver a fine rehabilitation therapy to the human upper limb. The proposed control scheme combines different approaches from the areas of robotics, neuroscience and human-machine interaction in order to overcome the limitations of each single field. Via the adaptive Brain Reading Interface (aBRI) user movements are anticipated by classification of surface electroencephalographic data in a millisecond range. This information is afterwards integrated into the control strategy of a wearable exoskeleton in order to finely modulate its impedance and therefore to comply with the motion preparation of the user. Results showing the efficacy of the proposed control approach are presented for the single joint case.