Advertisement

Exoskelette und künstliche Intelligenz in der klinischen Rehabilitation

  • Elsa A. KirchnerEmail author
  • Niels Will
  • Marc Simnofske
  • Peter Kampmann
  • Luis Manuel Vaca Benitez
  • José de Gea Fernández
  • Frank Kirchner
Chapter

Zusammenfassung

Das Tragen eines Roboters, also der direkte Kontakt eines potenziell sehr kraftvollen Systems mit dem menschlichen Körper, stellt enorme Anforderungen an die Ergonomie, Sicherheit durch Design und Steuerung sowie an das Zusammenspiel beider Partner – Mensch und Roboter. Letzteres erfordert Regelungsmechanismen, die ein transparentes Verhalten des Roboters für den Menschen ermöglichen (ohne den Menschen zu behindern) und das automatische Erkennen der Intention des Menschen, um ihn situationsgemäß zu unterstützen. Um diese Herausforderungen zu meistern, gilt es, nicht nur neue kinematische und mechanische Designs, Elektroniken und Regelungsansätze zu entwickeln, sondern auch Daten des Menschen, insbesondere psychophysiologische Daten, zu nutzen. Letzteres erfordert den Einsatz sehr fortschrittlicher Signalverarbeitungsverfahren und maschinellen Lernens in Echtzeit. Integriert in das System unter Nutzung von eingebetteter Elektronik und Einbindung in die Regelung des Exoskeletts ergibt sich eine Erweiterung der künstlichen Intelligenz, die den Menschen mit seinem Verhalten, Intentionen und Bedürfnissen einbezieht. Besondere Relevanz und Herausforderung stellt die Nutzung von Exoskeletten für die Neurorehabilitation dar, auf die im Kapitel besonders eingegangen wird.

Literatur

  1. Alfven H, Kleinwächter H (1970) Syntelmann – und die möglichen Konsequenzen, Bild der Wissenschaft, Heft 7. Deutsche Verlags-Anstalt, MünchenGoogle Scholar
  2. Anam K, Al-Jumaily AA (2012) Active exoskeleton control systems: state of the art. Proc Eng 41:988–994. ISSN 1877-7058CrossRefGoogle Scholar
  3. Cobb G (1934) Walking motion. Patent US 2010482 A. United States Patent Office, United States of America (USA)Google Scholar
  4. Clark M, Smith D (1999) Psychological correlates of outcome following rehabilitation from stroke. Clin Rehabil 13(2):129–140CrossRefGoogle Scholar
  5. Dettmers C, Hömberg V, Koenig E (2009) S2e-Leitlinien zur motorischen Rehabilitation des Schlaganfalls. Neurol Rehabil 15(2):71–73Google Scholar
  6. Folgheraiter M, Jordan M, Straube S, Seeland A, Kim S-K, Kirchner EA (2012) Measuring the improvement of the interaction comfort of a wearable exoskeleton. Int J Soc Robot 4(3):285–302. Springer, NetherlandsCrossRefGoogle Scholar
  7. Fowers J, Brown G, Cooke P, Stitt G (2012) A performance and energy comparison of FPGAs, GPUs, and multicores for sliding-window applications. In: Association for Computing Machinery (ACM) (Hrsg) Proceedings of the ACM/SIGDA international symposium on field programmable gate arrays (FPGA ’12), 22–24 Feb, New York, S 47–56.  https://doi.org/10.1145/2145694.2145704
  8. Gancet J, Ilzkovitz M, Cheron G, Ivanenko Y, van der Kooij H, van der Helm F, Zanow F, Thorsteinsson F (2011) MINDWALKER: a brain controlled lower limbs exoskeleton for rehabilitation. Potential applications to space. In: 11th Symposium on advanced space technologies in robotics and automation, 12–15 Apr, European Space Agency (ESA), Noordwijk, S 12–14Google Scholar
  9. Golem (Hrsg) (2018) Exoskelett ermöglicht Sitzen ohne Stuhl, Golem. https://www.golem.de/news/noonee-exoskelett-ermoeglicht-sitzen-ohne-stuhl-1704-127527.html. Zugegriffen am 11.02.2018
  10. Guizzo E, Goldstein H (2005) The rise of the body bots [robotic exoskeletons]. IEEE Spectr 42(10):50–56CrossRefGoogle Scholar
  11. Gunasekara JMP, Gopura RARC, Jayawardane TSS, Lalitharathne SWHMTD (2012) Control methodologies for upper limb exoskeleton robots. In: 2012 IEEE/SICE international symposium on system integration (SII), Institute of Electrical and Electronics Engineers/The Society of Instrument and Control Engineers (IEEE, SICE), 16–18 Dec 2012, Fukuoka, S 19–24Google Scholar
  12. Heuschmann PU, Busse O, Wagner M, Endres M, Villringer A, Röther J, Kolominsky-Rabas PL, Berge K (2010) Schlaganfallhäufigkeit und Versorgung von Schlaganfallpatienten in Deutschland. Akt Neurol 37(7):333–340CrossRefGoogle Scholar
  13. Hogan N (1987) Stable execution of contact tasks using impedance control. In: Proceedings of IEEE international conference on robotics and automation (ICRA), 31 March–3 April 1987, Raleigh (NC), S 1047–1054Google Scholar
  14. Jo I, Park Y, Bae J (2013) A teleoperation system with an exoskeleton interface. In: Institute of Electrical and Electronics Engineers/American Society of Mechanical Engineers (IEEE, ASME) (Hrsg) IEEE/ASME international conference on advanced intelligent mechatronics, 9–12 July, Wollongong, S 1649–1654.  https://doi.org/10.1109/AIM.2013.6584333
  15. Johansson BB (2000) Brain plasticity and stroke rehabilitation: the Willis lecture. Stroke 31(1):223–230CrossRefGoogle Scholar
  16. Kirchner EA, Drechsler R (2013) A formal model for embedded brain reading. Ind Robot 40(6):530–540. Emerald Group Publishing LimitedCrossRefGoogle Scholar
  17. Kirchner EA, Albiez J, Seeland A, Jordan M, Kirchner F (2013a) Towards assistive robotics for home rehabilitation. In: Proceedings of the 6th international conference on biomedical electronics and devices, BIODEVICES-13, Institute for Systems and Technologies of Information, Control and Communication (INSTICC), 11–14 Feb 2013, BarcelonaGoogle Scholar
  18. Kirchner EA, Kim S-K, Straube S, Seeland A, Wöhrle H, Krell MM, Tabie M, Fahle M (2013b) On the applicability of brain reading for predictive human-machine interfaces in robotics. PLoS ONE 8(12):e81732CrossRefGoogle Scholar
  19. Kirchner EA, Seeland A, Tabie T (2014) Multimodal movement prediction – towards an individual assistance of patients. PLoS ONE 9(1):e85060CrossRefGoogle Scholar
  20. Kirchner EA, Kim S-K, Wöhrle H, Tabie M, Maurus M, Kirchner F (2016a) An intelligent man-machine interface – multi-robot control adapted for task engagement based on single-trial detectability of P300. Front Hum Neurosci 10:291CrossRefGoogle Scholar
  21. Kirchner EA, Will N, Simnofske M, Vaca Benitez LM, Bongardt B, Krell MM, Kumar S, Mallwitz M, Seeland A, Tabie M, Wöhrle H, Yüksel M, Heß A, Buschfort R, Kirchner F (2016b) Recupera-Reha: exoskeleton technology with integrated biosignal analysis for sensorimotor rehabilitation. In: 2. Transdisziplinäre Konferenz Technische Unterstützungssysteme, die die Menschen wirklich wollen, 12–13 Dec 2016, Elsevier, Hamburg, S 504–517Google Scholar
  22. Kõiva R, Riedenklau E, Viegas C, Castellini C (2015) Shape conformable high spatial resolution tactile bracelet for detecting hand and wrist activity. In: Institute of Electrical and Electronics Engineers (IEEE) (Hrsg) IEEE international conference on rehabilitation robotics (ICORR), 11–14 Aug, Singapore, S 157–162.  https://doi.org/10.1109/ICORR.2015.7281192
  23. Krell MM, Straube S, Seeland A, Wöhrle H, Teiwes J, Metzen JH, Kirchner EA, Kirchner F (2013) pySPACE – a signal processing and classification environment in Python. Front Neuroinform 7(40):1–11Google Scholar
  24. Kumar S, Simnofske M, Bongardt B, Mueller A, Kirchner F (2017) Integrating mimic joints into dynamics algorithms – exemplified by the hybrid recupera exoskeleton. In: Proceedings of the 2017 conference on advances in robotics, AIR-2017, Association for Computing Machinery 28 June–2 July 2017, ACM-ICPS, New Delhi, S 27:1–27:6Google Scholar
  25. Lee G, Kim J, Panizzolo FA, Zouh YM, Baker LM, Galiana I, Malcom P, Walsh CJ (2017) Reducing the metabolic cost of running with a tethered soft exosuit. Sci Robot 2(6):eaan6708CrossRefGoogle Scholar
  26. Lenzi T, De Rossi S, Vitiello N, Carrozza M (2012) Intention-based EMG control for powered exoskeletons. IEEE Trans Biomed Eng 59(8):2180–2190CrossRefGoogle Scholar
  27. Lew E, Chavarriaga R, Silvoni S, Millan J d R (2012) Detection of self-paced reaching movement intention from EEG signals. Front Neuroeng 5(13):13.  https://doi.org/10.3389/fneng.2012.00013CrossRefGoogle Scholar
  28. Lowes innovation lab (Hrsg) (2018) Exosuit, Lowes innovation. http://www.lowesinnovationlabs.com/exosuits. Zugegriffen am 11.02.2018
  29. Mallwitz M, Will N, Teiwes J, Kirchner EA (2015) The CAPIO active upper body exoskeleton and its application for teleoperation. In: European Space Agency (ESA) (Hrsg) Proceedings of the 13th symposium on advanced space technologies in robotics and automation, ASTRA-2015, NoordwijkGoogle Scholar
  30. Neumann J v (1928) Zur Theorie der Gesellschaftsspiele. Math Ann 100:295–320CrossRefGoogle Scholar
  31. New Atlas (Hrsg) (2018) Exoskeleton helps Ford workers reach up, New Atlas. https://newatlas.com/ford-eksovest/52166/. Zugegriffen am 11.02.2018
  32. Nitschke J, Kuhn D, Fischer K, Röhl K (2014) Comparison of the usability of the ReWalk, Ekso and HAL. OrthOpädietechnik 9(14):22Google Scholar
  33. noonee (Hrsg) (2018) chairless chair, noonee. https://www.noonee.com/. Zugegriffen am 11.02.2018
  34. Planthaber S, Maurus M, Bongardt B, Mallwitz M, Vaca Benitez LM, Christensen L, Cordes F, Sonsalla R, Stark T, Roehr TM (2017) Controlling a semi-autonomous robot team from a virtual environment. In: Association for Computing Machinery/Institute of Electrical and Electronics Engineers (ACM, IEEE) (Hrsg) Proceedings of the HRI conference. ACM/IEEE international conference on human-robot interaction (HRI), 6–9 Mar, Vienna, S 417Google Scholar
  35. Platz T (2011) Rehabilitative Therapie bei Armlähmungen nach einem Schlaganfall. S2-Leitlinie der Deutschen Gesellschaft für Neurorehabilitation. NeuroGeriatrie 3(4):104–116Google Scholar
  36. Platz T, Roschka S (2009) Rehabilitative Therapie bei Armparese nach Schlaganfall. Neurol Rehabil 15(2):81–106Google Scholar
  37. Proietti T, Crocher V, Roby-Brami A, Jarrasse N (2016) Upper-limb robotic exoskeletons for neurorehabilitation: a review on control strategies. IEEE Rev Biomed Eng 9:4–14CrossRefGoogle Scholar
  38. RKI und DESTATIS (Hrsg) (2015) Gesundheitsberichterstattung des Bundes gemeinsam getragen von RKI und DESTATIS Gesundheit in Deutschland. Robert-Koch Institut, Berlin, S 43Google Scholar
  39. Russell S, Norvig P (1995) Artificial intelligence: a modern approach (PDF). Simon & Schuster, Upper Saddle River, S 22–23Google Scholar
  40. Sankai Y (2010) HAL: hybrid assistive limb based on cybernics. In: Kaneko M, Nakamura Y (Hrsg) Robotics research. Springer tracts in advanced robotics, Bd 66. Springer, Berlin, S 25–34Google Scholar
  41. Simnofske M, Kumar S, Bongardt B, Kirchner F (2016) Active ankle – an almost-spherical parallel mechanism. In: 47th international symposium on robotics (ISR 2016), international symposium on robotics (ISR), 21–22 June, VDE, München, S 37–42.Google Scholar
  42. Spada S, Ghibaudo L, Gilotta S, Gastaldi L, Cavatorta MP (2017) Investigation into the applicability of a passive upper-limb exoskeleton in automotive industry. Proc Manuf 11:1255–1262Google Scholar
  43. Spada S, Ghibaudo L, Gilotta S, Gastaldi L, Cavatorta MP (2018) Advances in physical ergonomics and human factors. In: Goonetilleke RS, Karwowski W (Hrsg) Analysis of exoskeleton introduction in industrial reality: main issues and EAWS risk assessment. Springer, Berlin, S 236–245Google Scholar
  44. Takahashi CD, Der-Yeghiaian L, Le V, Motiwala RR, Cramer SC (2008) Robot-based hand motor therapy after stroke. Brain 131(2):425–437CrossRefGoogle Scholar
  45. Teich J, Henkel J, Herkersdorf A, Schmitt-Landsiedel D, Schröder-Preikschat W, Snelting G (2011) Invasive computing – an overview. In: Hübner M, Becker J (Hrsg) Multiprocessor system-on-chip – hardware design and tool integration. Springer, Berlin, S 241–268Google Scholar
  46. Turing AM (1937) On computable numbers, with an application to the Entscheidungsproblem. Proc Lond Math Soc 42:230–265.  https://doi.org/10.1112/plms/s2-42.1.230CrossRefGoogle Scholar
  47. Turing AM (1950) Computing machinery and intelligence. Mind LIX(236):433–460.  https://doi.org/10.1093/mind/LIX.236.433CrossRefGoogle Scholar
  48. Vaca Benitez LM, Will N, Schmidt S, Jordan M, Kirchner EA (2013) Exoskeleton technology in rehabilitation: towards an EMG-based orthosis system for upper limb neuromotor rehabilitation. J Rob 2013:13. Hindawi Publishing CorporationGoogle Scholar
  49. Volpe B, Krebs H, Hogan N, Edelstein O, Diels C, Aisen M (2000) A novel approach to stroke rehabilitation: robot-aided sensorimotor stimulation. Neurology 54(10):1938–1944CrossRefGoogle Scholar
  50. Waddington DG, Changhui L (2016) A fast lightweight time-series store for IoT data. Cornell UniversityGoogle Scholar
  51. Wöhrle H, Kirchner EA (2014) Online classifier adaptation for the detection of P300 target recognition processes in a complex teleoperation scenario. In: Physiological computing systems. Lecture notes in computer science (LCNS). Springer, Heidelberg, S 105–119Google Scholar
  52. Wöhrle H, Kirchner EA (2017) Eingebettete Biosignalverarbeitung und integrierte Regelung eines Ganzkörper-Exoskelettes für die Neurorehabilitation. In: Proceedings of the 2. VDI Fachkonferenz Humanoide Roboter, 5–6 Dec 2017, VDI Fachkonferenz Humanoide Roboter, MünchenGoogle Scholar
  53. Wöhrle H, Tabie T, Kim S-K, Kirchner F, Kirchner EA (2017) A hybrid FPGA-based system for EEG- and EMG-based online movement prediction. Sensors 17(7):15–52. MDPICrossRefGoogle Scholar
  54. Wolpaw J, Wolpaw EW (2012) Brain-computer interfaces: principles and practice. Oxford University Press, OxfordCrossRefGoogle Scholar
  55. Yagn N (1890) Apparatus for facilitating walking. Patent US 440684 A. United States Patent and Trademark Office, AlexandriaGoogle Scholar
  56. Yang C-J, Zhang J-F, Chen Y, Dong Y-M, Zhang Y (2008) A review of exoskeleton-type systems and their key technologies. Proc Inst Mech Eng C J Mech Eng Sci 222(8):1599–1612.  https://doi.org/10.1243/09544062JMES936CrossRefGoogle Scholar
  57. Yeung JHC, Tsang CC, Tsoi KH, Kwan BSH, Cheung CCC, Chan APC, Leong Philip HW (2008) Map-reduce as a programming model for custom computing machines. In: Institute of Electrical and Electronics Engineers (IEEE) (Hrsg) Proceedings of the 2008 16th international symposium on field-programmable custom computing machines (FCCM ’08), 13–15 Apr, IEEE Computer Society, Washington, DC, S 149–159.  https://doi.org/10.1109/FCCM.2008.19
  58. Zoss A, Kazerooni H, Chu A (2005) On the mechanical design of the Berkeley Lower Extremity Exoskeleton (BLEEX). In: Institute of Electrical and Electronics Engineers/Robotics Society of Japan (IEEE, RSJ) (Hrsg) IEEE/RSJ international conference on intelligent robots and systems (2005), 2–6 Aug, Edmonton, S 3465–3472Google Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2019

Authors and Affiliations

  • Elsa A. Kirchner
    • 1
    • 2
    Email author
  • Niels Will
    • 3
  • Marc Simnofske
    • 3
  • Peter Kampmann
    • 3
  • Luis Manuel Vaca Benitez
    • 3
  • José de Gea Fernández
    • 3
  • Frank Kirchner
    • 1
    • 2
  1. 1.Robotics Innovation CenterDeutsches Forschungszentrum für Künstliche Intelligenz GmbH (DFKI)BremenDeutschland
  2. 2.Fachbereich 3, AG RobotikUniversität BremenBremenDeutschland
  3. 3.Robotics Innovation Center (RIC)Deutsches Forschungszentrum für Künstliche Intelligenz GmbH (DFKI)BremenDeutschland

Personalised recommendations