Probabilistic consolidation of grasp experience

Yasemin Bekiroglu, Andreas Damianou, Renaud Detry, Johannes A Stork, Danica Kragic, Carl Henrik Ek

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

6 Citations (Scopus)
342 Downloads (Pure)

Abstract

We present a probabilistic model for joint representation of several sensory modalities and action parameters in a robotic grasping scenario. Our non-linear probabilistic latent variable model encodes relationships between grasp-related parameters, learns the importance of features, and expresses confidence in estimates. The model learns associations between stable and unstable grasps that it experiences during an exploration phase. We demonstrate the applicability of the model for estimating grasp stability, correcting grasps, identifying objects based on tactile imprints and predicting tactile imprints from object-relative gripper poses. We performed experiments on a real platform with both known and novel objects, i.e., objects the robot trained with, and previously unseen objects. Grasp correction had a 75% success rate on known objects, and 73% on new objects. We compared our model to a traditional regression model that succeeded in correcting grasps in only 38% of cases.
Original languageEnglish
Title of host publication2016 IEEE International Conference on Robotics and Automation (ICRA 2016)
Subtitle of host publicationProceedings of a meeting held 16-21 May 2016, Stockholm, Sweden
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages193-200
Number of pages8
ISBN (Electronic)9781467380263
ISBN (Print)9781467380270
DOIs
Publication statusPublished - Aug 2016

Fingerprint Dive into the research topics of 'Probabilistic consolidation of grasp experience'. Together they form a unique fingerprint.

Cite this