Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Sensor design and model-based tactile feature recognition

: Müller, Veit; Lam, Thang-Long; Elkmann, Norbert

Postprint urn:nbn:de:0011-n-5024285 (608 KByte PDF)
MD5 Fingerprint: 16947a7b6896843d259662f28d1488b2
© IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Erstellt am: 16.11.2018

Institute of Electrical and Electronics Engineers -IEEE-:
IEEE Sensors 2017. Conference Proceedings : October 29 - November 1, 2017, Glasgow, Scotland, UK
Piscataway, NJ: IEEE, 2017
ISBN: 978-1-5090-1012-7
ISBN: 978-1-5090-1013-4
ISBN: 978-1-5386-4056-2
Sensors Conference <2017, Glasgow>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IFF ()

This paper1 presents the design of a flexible tactile sensor and a model-based approach for the pose estimation and surface reconstruction of objects in a gripper. We show that the proposed sensor composite can be easily attached to almost all object shapes, while still achieving a high spatial sensor resolution and a high force sensitivity. Since machine learning algorithms require a large data base and do not offer the scalability of training data, the approach that we prefer here uses model-based feature classification. In order to improve the accuracy of our approach, we investigated fundamental sensor properties and applied sustainable correction methods to the data processing. Finally, the sensor's operability and the evaluation results have been verified in a pick-and-place application for two different grippers.