Transition State Clustering for Interaction Segmentation and Learning

Fabian Hahne, Vignesh Prasad, Alap Kshirsagar, Dorothea Koert, Ruth Stock-Homburg, Jan Peters and Georgia Chalvatzaki

Publications of Darmstadt Technical University, Institute for Business Studies (BWL) from Darmstadt Technical University, Department of Business Administration, Economics and Law, Institute for Business Studies (BWL)

Abstract: Hidden Markov Models with an underlying Mixture of Gaussian structure have proven efective in learning Human-Robot Interactions from demonstrations for various interactive tasks via Gaussian Mixture Regression. However, a mismatch occurs when segmenting the interaction using only the observed state of the human compared to the joint state of the human and the robot. To enhance this underlying segmentation and subsequently the predictive abilities of such Gaussian Mixture-based approaches, we take a hierarchical approach by learning an additional mixture distribution on the states at the transition boundary. This helps prevent misclassifcations that usually occur in such states. We fnd that our framework improves the performance of the underlying Gaussian Mixture-based approach, which we evaluate on various interactive tasks such as handshaking and fistbumps.

Date: 2024
Note: for complete metadata visit http://tubiblio.ulb.tu-darmstadt.de/143736/
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:dar:wpaper:143736

Access Statistics for this paper

More papers in Publications of Darmstadt Technical University, Institute for Business Studies (BWL) from Darmstadt Technical University, Department of Business Administration, Economics and Law, Institute for Business Studies (BWL) Contact information at EDIRC.
Bibliographic data for series maintained by Dekanatssekretariat ().