Learning grasp stability based on tactile data and HMMs

Yasemin Bekiroglu*, Danica Kragic, Ville Kyrki

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

38 Citations (Scopus)

Abstract

In this paper, the problem of learning grasp stability in robotic object grasping based on tactile measurements is studied. Although grasp stability modeling and estimation has been studied for a long time, there are few robots today able of demonstrating extensive grasping skills. The main contribution of the work presented here is an investigation of probabilistic modeling for inferring grasp stability based on learning from examples. The main objective is classification of a grasp as stable or unstable before applying further actions on it, e.g. lifting. The problem cannot be solved by visual sensing which is typically used to execute an initial robot hand positioning with respect to the object. The output of the classification system can trigger a regrasping step if an unstable grasp is identified. An off-line learning process is implemented and used for reasoning about grasp stability for a three-fingered robotic hand using Hidden Markov models. To evaluate the proposed method, experiments are performed both in simulation and on a real robot system.

Original languageEnglish
Title of host publicationProceedings - IEEE International Workshop on Robot and Human Interactive Communication
Pages132-137
Number of pages6
DOIs
Publication statusPublished - 2010
MoE publication typeA4 Article in a conference publication
EventIEEE International Symposium on Robot and Human Interactive Communication - Viareggio, Italy
Duration: 12 Sep 201015 Sep 2010
Conference number: 19

Conference

ConferenceIEEE International Symposium on Robot and Human Interactive Communication
Abbreviated titleRO-MAN
Country/TerritoryItaly
CityViareggio
Period12/09/201015/09/2010

Fingerprint

Dive into the research topics of 'Learning grasp stability based on tactile data and HMMs'. Together they form a unique fingerprint.

Cite this