Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Sensor glove for an intuitive human-machine interface for exoskeletons as manual load handling assistance

 
: Stelzer, Patrick; Kraus, Werner; Pott, Andreas

:
Postprint urn:nbn:de:0011-n-4024323 (7.7 MByte PDF)
MD5 Fingerprint: a2d3fb069b8bdbeda1275b5a213a9025
Erstellt am: 15.7.2016


Verl, Alexander (Chairman, Tagungspräsident); Dragan, Mihai (Programmkomitee); Hägele, Martin (Programmkomitee) ; International Federation of Robotics; Deutsche Gesellschaft für Robotik -DGR-; Informationstechnische Gesellschaft -ITG-; Verband Deutscher Maschinen- und Anlagenbau e.V. -VDMA-, Fachverband Robotik und Automation, Frankfurt/Main; Fraunhofer-Institut für Produktionstechnik und Automatisierung -IPA-, Stuttgart:
47th International Symposium on Robotics 2016 : Robotics in the Era of Digitalization. June 21-22, 2016, Munich, Germany
Berlin: VDE-Verlag, 2016
ISBN: 978-3-8007-4231-8
S.265-270
International Symposium on Robotics (ISR) <47, 2016, München>
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IPA ()
Exoskelett; Mensch-Roboter-Kooperation (MRK); Mensch Maschine Schnittstelle; Sensor; Handschuh; Handhaben

Abstract
Wearable assistive robots, also called exoskeletons, require an intuitive human-machine interface to reproduce human flexibility and to ensure user acceptance. In this paper, a concept for such an intuitive interface for assistance in manual handling of loads in industry is presented. The concept is based on the measurement of the interaction force between the human and the robot, on an impedance-based control approach and, in contrast to existing solutions, on an intelligent sensor glove. Suitable sensor types and sensor locations on the hand are selected. To show the feasibility of the concept a prototype of a sensor glove equipped with six piezoresistive force is developed and the force signals are recorded for two different grasp types. The resulting characteristic signal patterns could be recognized using a feed forward neural networks. Further, an outlook on future research is given.

: http://publica.fraunhofer.de/dokumente/N-402432.html