Learning Grasp Affordance Densities
We address the issue of learning and representing object grasp affordance models. We model grasp affordances with continuous probability density functions (grasp densities) which link object-relative grasp poses to their success probability. The underlying function representation is nonparametric an...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2011-03-01
|
| Series: | Paladyn |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/s13230-011-0012-x |
| _version_ | 1797423626879762432 |
|---|---|
| author | Detry R. Kraft D. Kroemer O. Bodenhagen L. Peters J. Krüger N. Piater J. |
| author_facet | Detry R. Kraft D. Kroemer O. Bodenhagen L. Peters J. Krüger N. Piater J. |
| author_sort | Detry R. |
| collection | DOAJ |
| description | We address the issue of learning and representing object grasp affordance models. We model grasp affordances with continuous probability density functions (grasp densities) which link object-relative grasp poses to their success probability. The underlying function representation is nonparametric and relies on kernel density estimation to provide a continuous model. Grasp densities are learned and refined from exploration, by letting a robot “play” with an object in a sequence of grasp-and-drop actions: the robot uses visual cues to generate a set of grasp hypotheses, which it then executes and records their outcomes. When a satisfactory amount of grasp data is available, an importance-sampling algorithm turns it into a grasp density. We evaluate our method in a largely autonomous learning experiment, run on three objects with distinct shapes. The experiment shows how learning increases success rates. It also measures the success rate of grasps chosen to maximize the probability of success, given reaching constraints. |
| first_indexed | 2024-03-09T07:49:40Z |
| format | Article |
| id | doaj.art-61b93311a93e46c2837422535efc18ae |
| institution | Directory Open Access Journal |
| issn | 2081-4836 |
| language | English |
| last_indexed | 2024-03-09T07:49:40Z |
| publishDate | 2011-03-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Paladyn |
| spelling | doaj.art-61b93311a93e46c2837422535efc18ae2023-12-03T02:05:30ZengDe GruyterPaladyn2081-48362011-03-012111710.2478/s13230-011-0012-xLearning Grasp Affordance DensitiesDetry R.0Kraft D.1Kroemer O.2Bodenhagen L.3Peters J.4Krüger N.5Piater J.6 Centre for Autonomous Systems, Kungliga Tekniska högskolan (KTH), Stockholm, Sweden Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Denmark MPI for Biological Cybernetics, Tübingen, Germany Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Denmark MPI for Biological Cybernetics, Tübingen, Germany Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Denmark University of Innsbruck, Austria.We address the issue of learning and representing object grasp affordance models. We model grasp affordances with continuous probability density functions (grasp densities) which link object-relative grasp poses to their success probability. The underlying function representation is nonparametric and relies on kernel density estimation to provide a continuous model. Grasp densities are learned and refined from exploration, by letting a robot “play” with an object in a sequence of grasp-and-drop actions: the robot uses visual cues to generate a set of grasp hypotheses, which it then executes and records their outcomes. When a satisfactory amount of grasp data is available, an importance-sampling algorithm turns it into a grasp density. We evaluate our method in a largely autonomous learning experiment, run on three objects with distinct shapes. The experiment shows how learning increases success rates. It also measures the success rate of grasps chosen to maximize the probability of success, given reaching constraints.https://doi.org/10.2478/s13230-011-0012-xrobot learninggraspingprobabilistic modelscognitive robotics |
| spellingShingle | Detry R. Kraft D. Kroemer O. Bodenhagen L. Peters J. Krüger N. Piater J. Learning Grasp Affordance Densities Paladyn robot learning grasping probabilistic models cognitive robotics |
| title | Learning Grasp Affordance Densities |
| title_full | Learning Grasp Affordance Densities |
| title_fullStr | Learning Grasp Affordance Densities |
| title_full_unstemmed | Learning Grasp Affordance Densities |
| title_short | Learning Grasp Affordance Densities |
| title_sort | learning grasp affordance densities |
| topic | robot learning grasping probabilistic models cognitive robotics |
| url | https://doi.org/10.2478/s13230-011-0012-x |
| work_keys_str_mv | AT detryr learninggraspaffordancedensities AT kraftd learninggraspaffordancedensities AT kroemero learninggraspaffordancedensities AT bodenhagenl learninggraspaffordancedensities AT petersj learninggraspaffordancedensities AT krugern learninggraspaffordancedensities AT piaterj learninggraspaffordancedensities |