TU Darmstadt / ULB / TUprints

Building a Library of Tactile Skills Based on FingerVision

Belousov, Boris ; Sadybakasov, Alymbek ; Wibranek, Bastian ; Veiga, Filipe ; Tessmann, Oliver ; Peters, Jan (2022)
Building a Library of Tactile Skills Based on FingerVision.
19th International Conference on Humanoid Robots (Humanoids). Toronto, ON, Canada (15.-17.10.2019)
doi: 10.26083/tuprints-00020548
Conference or Workshop Item, Secondary publication, Postprint

[img] Text
Copyright Information: In Copyright.

Download (3MB)
Item Type: Conference or Workshop Item
Type of entry: Secondary publication
Title: Building a Library of Tactile Skills Based on FingerVision
Language: English
Date: 2022
Place of Publication: Darmstadt
Year of primary publication: 2022
Publisher: IEEE
Book Title: 2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids)
Collation: 6 Seiten
Event Title: 19th International Conference on Humanoid Robots (Humanoids)
Event Location: Toronto, ON, Canada
Event Dates: 15.-17.10.2019
DOI: 10.26083/tuprints-00020548
Corresponding Links:
Origin: Secondary publication service

Camera-based tactile sensors are emerging as a promising inexpensive solution for tactile-enhanced manipulation tasks. A recently introduced Finger Vision sensor was shown capable of generating reliable signals for force estimation, object pose estimation, and slip detection. In this paper, we build upon the Finger Vision design, improving already existing control algorithms, and, more importantly, expanding its range of applicability to more challenging tasks by utilizing raw skin deformation data for control. In contrast to previous approaches that rely on the average deformation of the whole sensor surface, we directly employ local deviations of each spherical marker immersed in the silicone body of the sensor for feedback control and as input to learning tasks. We show that with such input, substances of varying texture and viscosity can be distinguished on the basis of tactile sensations evoked while stirring them. As another application, we learn a mapping between skin deformation and force applied to an object. To demonstrate the full range of capabilities of the proposed controllers, we deploy them in a challenging architectural assembly task that involves inserting a load-bearing element underneath a bendable plate at the point of maximum load.

Status: Postprint
URN: urn:nbn:de:tuda-tuprints-205484
Classification DDC: 000 Generalities, computers, information > 004 Computer science
Divisions: 15 Department of Architecture > Fachgruppe B: Gestalten und Darstellen > Digital Design
20 Department of Computer Science > Intelligent Autonomous Systems
TU-Projects: EC/H2020|640554|SKILLS4ROBOTS
Date Deposited: 18 Nov 2022 14:07
Last Modified: 24 Mar 2023 07:40
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/20548
PPN: 502453869
Actions (login required)
View Item View Item