Learning of Object Manipulation Operations from Continuous Multimodal Input

Großekathöfer U, Barchunova A, Haschke R, Hermann T, Franzius M, Ritter H (2011)
In: IEEE/RAS International Conference on Humanoid Robots 2011.

Download
Campus/VPN Humanoids2011-Barchunova.pdf
Konferenzbeitrag | Veröffentlicht | Englisch
Abstract / Bemerkung
In this paper we propose an approach for identification of high-level object manipulation operations within a continuous multimodal time-series. We focus on a multimodal approach for robust recognition of action primitive data. Our procedure combines an unsupervised Bayesian multimodal segmentation with a supervised machine learning approach. We briefly outline (1) the unsupervised segmentation and selection of uni- and bi-manual manipulation primitives developed in our previous work. We show (2) an application of the ordered means models to classification of estimated segments. To assess the performance of our approach, we compare the computed labels to the ground truth acquired during the data recording. In our experiments we examined the robustness of the procedure on two different sets of segments: full length (≈ 95% overlap with the ground truth on average), partial length (≈ 10% overlap with ground truth on average). We have achieved a cross validation rate of ≈ 0.95 and recognition accuracy of ≈ 0.97 for full length and ≈ 0.84 for partial length test sets.
Erscheinungsjahr
Titel des Konferenzbandes
IEEE/RAS International Conference on Humanoid Robots 2011
Konferenz
Humanoids 2011
Konferenzort
Bled, Slovenia
Konferenzdatum
2011-10-26
PUB-ID

Zitieren

Großekathöfer U, Barchunova A, Haschke R, Hermann T, Franzius M, Ritter H. Learning of Object Manipulation Operations from Continuous Multimodal Input. In: IEEE/RAS International Conference on Humanoid Robots 2011. 2011.
Großekathöfer, U., Barchunova, A., Haschke, R., Hermann, T., Franzius, M., & Ritter, H. (2011). Learning of Object Manipulation Operations from Continuous Multimodal Input. IEEE/RAS International Conference on Humanoid Robots 2011. doi:10.1109/Humanoids.2011.6100880
Großekathöfer, U., Barchunova, A., Haschke, R., Hermann, T., Franzius, M., and Ritter, H. (2011). “Learning of Object Manipulation Operations from Continuous Multimodal Input” in IEEE/RAS International Conference on Humanoid Robots 2011.
Großekathöfer, U., et al., 2011. Learning of Object Manipulation Operations from Continuous Multimodal Input. In IEEE/RAS International Conference on Humanoid Robots 2011.
U. Großekathöfer, et al., “Learning of Object Manipulation Operations from Continuous Multimodal Input”, IEEE/RAS International Conference on Humanoid Robots 2011, 2011.
Großekathöfer, U., Barchunova, A., Haschke, R., Hermann, T., Franzius, M., Ritter, H.: Learning of Object Manipulation Operations from Continuous Multimodal Input. IEEE/RAS International Conference on Humanoid Robots 2011. (2011).
Großekathöfer, Ulf, Barchunova, Alexandra, Haschke, Robert, Hermann, Thomas, Franzius, Mathias, and Ritter, Helge. “Learning of Object Manipulation Operations from Continuous Multimodal Input”. IEEE/RAS International Conference on Humanoid Robots 2011. 2011.
Volltext(e)
Name
Humanoids2011-Barchunova.pdf
Access Level
Campus/VPN UniBi Only
Zuletzt Hochgeladen
2011-10-09T17:20:07Z

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar
ISBN Suche