Evaluation of feature representation and machine learning methods in grasp stability learning

Janne Laaksonen*, Ville Kyrki, Danica Kragic

*Corresponding author for this work

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

13 Citations (Scopus)

Abstract

This paper addresses the problem of sensor-based grasping under uncertainty, specifically, the on-line estimation of grasp stability. We show that machine learning approaches can to some extent detect grasp stability from haptic pressure and finger joint information. Using data from both simulations and two real robotic hands, the paper compares different feature representations and machine learning methods to evaluate their performance in determining the grasp stability. A boosting classifier was found to perform the best of the methods tested.

Original languageEnglish
Title of host publication2010 10th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2010
Pages112-117
Number of pages6
DOIs
Publication statusPublished - 2010
MoE publication typeA4 Article in a conference publication
EventIEEE-RAS International Conference on Humanoid Robots - Nashville, United States
Duration: 6 Dec 20108 Dec 2010
Conference number: 10

Conference

ConferenceIEEE-RAS International Conference on Humanoid Robots
Abbreviated titleHumanoids
CountryUnited States
CityNashville
Period06/12/201008/12/2010

Fingerprint Dive into the research topics of 'Evaluation of feature representation and machine learning methods in grasp stability learning'. Together they form a unique fingerprint.

  • Cite this

    Laaksonen, J., Kyrki, V., & Kragic, D. (2010). Evaluation of feature representation and machine learning methods in grasp stability learning. In 2010 10th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2010 (pp. 112-117). [5686310] https://doi.org/10.1109/ICHR.2010.5686310