Attention-based Robot Learning of Haptic Interaction

Moringen A, Fleer S, Walck G, Ritter H (2020)
In: Haptics: Science, Technology, Applications. 12th International Conference, EuroHaptics 2020, Leiden, The Netherlands, September 6–9, 2020, Proceedings. Nisky I, Hartcher-O’Brien J, Wiertlewski M, Smeets J (Eds); Lecture Notes in Computer Science, 12272. Cham: Springer: 462-470.

Sammelwerksbeitrag | Veröffentlicht | Englisch
 
Download
OA 406.19 KB
Herausgeber*in
Nisky, Ilana; Hartcher-O’Brien, Jess; Wiertlewski, Michaël; Smeets, Jeroen
Abstract / Bemerkung
Haptic interaction involved in almost any physical interaction with the environment performed by humans is a highly sophisticated and to a large extent a computationally unmodelled process. Unlike humans, who seamlessly handle a complex mixture of haptic features and profit from their integration over space and time, even the most advanced robots are strongly constrained in performing contact-rich interaction tasks. In this work we approach the described problem by demonstrating the success of our online haptic interaction learning approach on an example task: haptic identification of four unknown objects. Building upon our previous work performed with a floating haptic sensor array, here we show functionality of our approach within a fully-fledged robot simulation. To this end, we utilize the haptic attention model (HAM), a meta-controller neural network architecture trained with reinforcement learning. HAM is able to learn to optimally parameterize a sequence of so-called haptic glances, primitive actions of haptic control derived from elementary human haptic interaction. By coupling a simulated KUKA robot arm with the haptic attention model, we pursue to mimic the functionality of a finger.

Our modeling strategy allowed us to arrive at a tactile reinforcement learning architecture and characterize some of its advantages. Owing to a rudimentary experimental setting and an easy acquisition of simulated data, we believe our approach to be particularly useful for both time-efficient robot training and a flexible algorithm prototyping.
Stichworte
Haptic interaction in 3D; Reinforcement learning; Haptic attention; Robot control
Erscheinungsjahr
2020
Buchtitel
Haptics: Science, Technology, Applications. 12th International Conference, EuroHaptics 2020, Leiden, The Netherlands, September 6–9, 2020, Proceedings
Serientitel
Lecture Notes in Computer Science
Band
12272
Seite(n)
462-470
Konferenz
Eurohaptics 2020
Konferenzort
Leiden, Netherlands
Konferenzdatum
2020-09-06 – 2020-09-09
ISBN
978-3-030-58146-6
eISBN
978-3-030-58147-3
Page URI
https://pub.uni-bielefeld.de/record/2943876

Zitieren

Moringen A, Fleer S, Walck G, Ritter H. Attention-based Robot Learning of Haptic Interaction. In: Nisky I, Hartcher-O’Brien J, Wiertlewski M, Smeets J, eds. Haptics: Science, Technology, Applications. 12th International Conference, EuroHaptics 2020, Leiden, The Netherlands, September 6–9, 2020, Proceedings. Lecture Notes in Computer Science. Vol 12272. Cham: Springer; 2020: 462-470.
Moringen, A., Fleer, S., Walck, G., & Ritter, H. (2020). Attention-based Robot Learning of Haptic Interaction. In I. Nisky, J. Hartcher-O’Brien, M. Wiertlewski, & J. Smeets (Eds.), Lecture Notes in Computer Science: Vol. 12272. Haptics: Science, Technology, Applications. 12th International Conference, EuroHaptics 2020, Leiden, The Netherlands, September 6–9, 2020, Proceedings (pp. 462-470). Cham: Springer. doi:10.1007/978-3-030-58147-3_51
Moringen, A., Fleer, S., Walck, G., and Ritter, H. (2020). “Attention-based Robot Learning of Haptic Interaction” in Haptics: Science, Technology, Applications. 12th International Conference, EuroHaptics 2020, Leiden, The Netherlands, September 6–9, 2020, Proceedings, Nisky, I., Hartcher-O’Brien, J., Wiertlewski, M., and Smeets, J. eds. Lecture Notes in Computer Science, vol. 12272, (Cham: Springer), 462-470.
Moringen, A., et al., 2020. Attention-based Robot Learning of Haptic Interaction. In I. Nisky, et al., eds. Haptics: Science, Technology, Applications. 12th International Conference, EuroHaptics 2020, Leiden, The Netherlands, September 6–9, 2020, Proceedings. Lecture Notes in Computer Science. no.12272 Cham: Springer, pp. 462-470.
A. Moringen, et al., “Attention-based Robot Learning of Haptic Interaction”, Haptics: Science, Technology, Applications. 12th International Conference, EuroHaptics 2020, Leiden, The Netherlands, September 6–9, 2020, Proceedings, I. Nisky, et al., eds., Lecture Notes in Computer Science, vol. 12272, Cham: Springer, 2020, pp.462-470.
Moringen, A., Fleer, S., Walck, G., Ritter, H.: Attention-based Robot Learning of Haptic Interaction. In: Nisky, I., Hartcher-O’Brien, J., Wiertlewski, M., and Smeets, J. (eds.) Haptics: Science, Technology, Applications. 12th International Conference, EuroHaptics 2020, Leiden, The Netherlands, September 6–9, 2020, Proceedings. Lecture Notes in Computer Science. 12272, p. 462-470. Springer, Cham (2020).
Moringen, Alexandra, Fleer, Sascha, Walck, Guillaume, and Ritter, Helge. “Attention-based Robot Learning of Haptic Interaction”. Haptics: Science, Technology, Applications. 12th International Conference, EuroHaptics 2020, Leiden, The Netherlands, September 6–9, 2020, Proceedings. Ed. Ilana Nisky, Jess Hartcher-O’Brien, Michaël Wiertlewski, and Jeroen Smeets. Cham: Springer, 2020.Vol. 12272. Lecture Notes in Computer Science. 462-470.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Creative Commons Namensnennung 4.0 International Public License (CC-BY 4.0):
Volltext(e)
Name
Access Level
OA Open Access
Zuletzt Hochgeladen
2020-06-12T12:47:18Z
MD5 Prüfsumme
5d0ffb1ab5493c238afbf68c43b9c036

Link(s) zu Volltext(en)
Access Level
OA Open Access

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar
ISBN Suche