Authors:
Elsa Andrea Kirchner
1
;
Jan Christian Albiez
2
;
Anett Seeland
2
;
Mathias Jordan
2
and
Frank Kirchner
1
Affiliations:
1
German Research Center for Artificial Intelligence (DFKI) and University of Bremen, Germany
;
2
German Research Center for Artificial Intelligence (DFKI), Germany
Keyword(s):
Cognitive Human-robot Interaction, Rehabilitation Robotics, Virtual Reality and Interfaces, Exoskeleton, Psychophysiological Data.
Related
Ontology
Subjects/Areas/Topics:
Biomechanical Devices
;
Biomedical Engineering
;
Biomedical Instruments and Devices
;
Biorobotics
;
Brain-Computer Interfaces
;
Devices
;
Embedded Signal Processing
;
Emerging Technologies
;
Human-Computer Interaction
;
Physiological Computing Systems
;
Telecommunications
;
Wireless and Mobile Technologies
;
Wireless Information Networks and Systems
Abstract:
In this paper, we want to point out the possibilities that arise from the latest advances in robotic exoskeleton design and control. We show that approaches of artificial intelligence research and robotics that integrate psychophysiological data analysis offer the possibility to assist disabled people in their everyday lives. Thus, continuous long term rehabilitation training and daily support can be provided in the future to help them to regain motor functions. We outline a possible scenario for fully embedded home rehabilitation and its components. The presented work further investigates two challenges of the application of such a system in more detail: (i) improvement of the interaction between the patient and the supporting interface and (ii) enhancement of reliability of predictions made about the patients intention. In the experimental part we demonstrate that the exoskeleton control can compensate for gravitational loads, imposed by the device itself. Further, we present resul
ts that show that movement onset prediction can be made based on different psychophysiological measures, and can be improved with respect to their reliability.
(More)