6th JOINT SESSION CIMATEC & DFKI: Exoskeleton-supported stroke rehabilitation using embedded brain reading

Stroke rehabilitation has to address many brain and body function that are impaired by brain lesion caused by brain hemorrhage. Patients show diverse symptoms reaching from movement disorders, impaired sensation and cognitive deficits, which must be addressed by therapy. To compensate movement disorders, exoskeletons can be applied (1-4). They can sense movements and support them to enable a patient with smallest remaining muscular activity to regain control over a disabled limb (Fig. 1). Electromyogram and force measurements can be used to adapt the support to the patients need (5). In case that no control of the limb is left, brain activity can be analyzed by embedded brain reading (eBR) to infer on the intention of the patient and to trigger movements implicitly (6,7). For a successful therapy not only “assist as needed” is required but further, patients must be able to follow instructions - mental stress must be avoided to assure optimal therapy conditions. Again, eBR can be used to detect task load on a patient while he or she is performing an ongoing action, e.g., performing a specific arm movement to infer whether a patient (while performing the movement) is still able to understand instructions by the therapist or a serious game (8).
Further, EEG signals can be used to adapt the behavior of the system to the subjective preferences of the patient. This talk will show new therapy approaches for upper limb rehabilitation made possible by means of an active exoskeleton with highly adaptive embedded control combined with movement intention recognition based on EEG, EMG and eye tracking data. In future our approach will be supported by task-load detection based on P300-related activity and ErrP-related activity evoked by subjective misbehavior of the system (9).

References:
(1) Platz T, Roschka S (2009) Rehabilitative Therapie bei Armparese nach Schlaganfall. Neurol Rehabil 15(2):81–106
(2) Platz T (2011) Rehabilitative Therapie bei Armlähmungen nach einem Schlaganfall. S2-Leitlinie der Deutschen Gesellschaft für Neurorehabilitation. NeuroGeriatrie 3(4):104–116 (3) Nitschke J., Kuhn D, Fischer K, Röhl K (2014) Comparison of the usability of the ReWalk, Ekso and HAL. OrthOpädietechnik 9(14):22
(4) Kirchner, E. A., Will. N., Simnofske, M., Vaca Benitez, L. M., de Gea Fernández, J., Kampmann, P., Kirchner, F. (2019) Exoskelette und künstliche Intelligenz in der klinischen Rehabilitation. Editors: Mario A. Pfannstiel, Patrick Da-Cruz, Harald Mehlich. In: Digitale Transformation von Dienstleistungen im Gesundheitswesen V, Springer Nature, chapter 21, pages 413-435, Aug/2019. ISBN: 978-3-658-23986-2.
(5) Kirchner, Elsa and Bütefür, Judith (2022) Towards Bidirectional and Coadaptive Robotic Exoskeletons for Neuromotor Rehabilitation and Assisted Daily Living: A Review. In: Current Robotics Reports Jg. 3 (2022) Nr. 2, S. 21 – 32, ISSN: 2662-4087.
(6) Kirchner, E. A., Fairclough, S., Kirchner, F. (2019) Embedded Multimodal Interfaces in Robotics: Applications, Future Trends, and Societal Implications. Editors: S. Oviatt, B. Schuller, P. Cohen, D. Sonntag, G. Potamianos, A. Krueger. In: The Handbook of Multimodal-Multisensor Interfaces, Morgan & Claypool Publishers, volume 3,
chapter 13, pages 523-576, 2019. ISBN: e-book: 978-1-97000-173-0, hardcover: 978-1-97000-175-4, paperback: 978-1-97000-172-3, ePub: 978-1-97000-174-7.
(7) Kirchner, E. A., Kim, S.-K., Straube, S., Seeland, A., Wöhrle, H., Krell, M.M., Tabie, M., Fahle M. (2013) On the Applicability of Brain Reading for Predictive Human-Machine Interfaces in Robotics. In PLoS ONE, Public Library of Science, volume 8, number 12, pages e81732, Dec/2013.
(8) Kirchner, E. A., Kim S.-K. (2018), Multi-Tasking and Choice of Training Data Influencing Parietal ERP Expression and Single-Trial Detection—Relevance for Neuroscience and Clinical Applications, In: Frontiers in Neuroscience, volume 12, pages 188, DOI: 10.3389/fnins.2018.00188
(9) Kim, S.-K., Kirchner, E. A., Stefes, A., Kirchner F. (2017). Intrinsic interactive reinforcement learning - Using error-related potentials for real world human-robot interaction. In Scientific Reports, Nature, volume 7: 17562, pages n.a., Dec/2017.