{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T09:02:58Z","timestamp":1760346178009,"version":"3.38.0"},"reference-count":47,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2010,10,11]],"date-time":"2010-10-11T00:00:00Z","timestamp":1286755200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of Robotics Research"],"published-print":{"date-parts":[[2011,3]]},"abstract":"<jats:p> We discuss vision as a sensory modality for systems that interact flexibly with uncontrolled environments. Instead of trying to build a generic vision system that produces task-independent representations, we argue in favor of task-specific, learn-able representations. This concept is illustrated by two examples of our own work. First, our RLVC algorithm performs reinforcement learning directly on the visual input space. To make this very large space manageable, RLVC interleaves the reinforcement learner with a supervised classification algorithm that seeks to split perceptual states so as to reduce perceptual aliasing. This results in an adaptive discretization of the perceptual space based on the presence or absence of visual features. Its extension, RLJC, additionally handles continuous action spaces. In contrast to the minimalistic visual representations produced by RLVC and RLJC, our second method learns structural object models for robust object detection and pose estimation by probabilistic inference. To these models, the method associates grasp experiences autonomously learned by trial and error. These experiences form a non-parametric representation of grasp success likelihoods over gripper poses, which we call a grasp density . Thus, object detection in a novel scene simultaneously produces suitable grasping options. <\/jats:p>","DOI":"10.1177\/0278364910382464","type":"journal-article","created":{"date-parts":[[2010,10,12]],"date-time":"2010-10-12T00:31:37Z","timestamp":1286843497000},"page":"294-307","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":12,"title":["Learning visual representations for perception-action systems"],"prefix":"10.1177","volume":"30","author":[{"given":"Justus","family":"Piater","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Grande Traverse, University of Li\u00e8ge, Li\u00e8ge - Sart Tilman Belgium,"}]},{"given":"S\u00e9bastien","family":"Jodogne","sequence":"additional","affiliation":[{"name":"EURESYS s.a., Angleur, Belgium"}]},{"given":"Renaud","family":"Detry","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Grande Traverse, University of Li\u00e8ge, Li\u00e8ge - Sart Tilman Belgium"}]},{"given":"Dirk","family":"Kraft","sequence":"additional","affiliation":[{"name":"The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense M, Denmark"}]},{"given":"Norbert","family":"Kr\u00fcger","sequence":"additional","affiliation":[{"name":"The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense M, Denmark"}]},{"given":"Oliver","family":"Kroemer","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Biological Cybernetics, T\u00fcbingen, Germany"}]},{"given":"Jan","family":"Peters","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Biological Cybernetics, T\u00fcbingen, Germany"}]}],"member":"179","published-online":{"date-parts":[[2010,10,11]]},"reference":[{"volume-title":"International Conference on Robotics and Automation","author":"Bagnell, J.","key":"atypb1"},{"volume-title":"Neuroscience: Exploring the Brain","year":"2006","author":"Bear M.","key":"atypb2"},{"volume-title":"Dynamic Programming","year":"1957","author":"Bellman, R.","key":"atypb3"},{"volume-title":"Neuro-Dynamic Programming","year":"1996","author":"Bertsekas, D.","key":"atypb4"},{"volume-title":"Vehicles: Experiments in synthetic psychology","year":"1984","author":"Braitenberg, V.","key":"atypb5"},{"volume-title":"Classification and Regression Trees","year":"1984","author":"Breiman, L.","key":"atypb6"},{"key":"atypb7","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(91)90053-M"},{"key":"atypb8","doi-asserted-by":"publisher","DOI":"10.1145\/136035.136043"},{"volume-title":"International Conference on Development and Learning","author":"Detry, R.","key":"atypb9"},{"volume-title":"International Conference on Robotics and Automation","author":"Detry, R.","key":"atypb10"},{"key":"atypb11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.64"},{"key":"atypb12","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1638022"},{"volume-title":"14th European Conference on Machine Learning","author":"Ernst, D.","key":"atypb13"},{"key":"atypb14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.1.1"},{"volume-title":"The Ecological Approach to Visual Perception","year":"1979","author":"Gibson, J.","key":"atypb15"},{"key":"atypb16","doi-asserted-by":"publisher","DOI":"10.1109\/IVL.2001.990853"},{"volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems","author":"H\u00fcbner, K.","key":"atypb17"},{"volume-title":"22nd International Conference on Machine Lea-rning","author":"Jodogne, S.","key":"atypb18"},{"volume-title":"7th European Workshop on Reinforcement Learning","author":"Jodogne, S.","key":"atypb19"},{"key":"atypb20","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_24"},{"key":"atypb21","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2110"},{"journal-title":"Proceedings of the IEEE Workshop on Learning in Computer Vision and Pattern Recognition","year":"2005","author":"Jodogne, S.","key":"atypb22"},{"key":"atypb23","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"volume-title":"The Cradle of Knowledge","year":"1998","author":"Kellman, P.","key":"atypb24"},{"key":"atypb25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2009.V.027"},{"volume-title":"Computer Vision Systems: Seventh International Conference (Lecture Notes in Computer Science)","author":"Kraft, D.","key":"atypb26"},{"key":"atypb27","doi-asserted-by":"publisher","DOI":"10.1142\/S021984360800139X"},{"issue":"5","key":"atypb28","first-page":"417","volume":"1","author":"Kr\u00fcger, N.","year":"2004","journal-title":"Interdisciplinary Journal of Artificial Intelligence and the Simulation of Behaviour"},{"volume-title":"IEEE International Conference on Robotics and Automation","author":"Miller, A.","key":"atypb29"},{"volume-title":"The Visual Brain in Action","year":"1995","author":"Milner, A.","key":"atypb30"},{"key":"atypb31","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2007.914848"},{"key":"atypb32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993591"},{"volume-title":"Columbia Object Image Library (COIL-100). Technical Report CUCS-006-96","year":"1996","author":"Nene, S.","key":"atypb33"},{"key":"atypb34","doi-asserted-by":"publisher","DOI":"10.1177\/105971239300100403"},{"key":"atypb35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"atypb36","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.01.003"},{"volume-title":"British Machine Vision Conference","author":"Pugeault, N.","key":"atypb37"},{"key":"atypb38","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843610002209"},{"key":"atypb39","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9120-4"},{"key":"atypb40","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907087172"},{"volume-title":"Learning from demonstration. Advances in Neural Information Processing Systems, volume 9","year":"1997","author":"Schaal, S.","key":"atypb41"},{"key":"atypb42","doi-asserted-by":"publisher","DOI":"10.1177\/027836499601500302"},{"key":"atypb43","first-page":"605","author":"Sudderth, E.","year":"2003","journal-title":"Computer Vision and Pattern Recognition"},{"volume-title":"Reinforcement Learning: An Introduction","year":"1998","author":"Sutton, R.","key":"atypb44"},{"volume-title":"Probabilistic Robotics","year":"2005","author":"Thrun, S.","key":"atypb45"},{"key":"atypb46","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(84)90023-4"},{"volume-title":"Learning From Delayed Rewards","year":"1989","author":"Watkins, Christopher","key":"atypb47"}],"container-title":["The International Journal of Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0278364910382464","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0278364910382464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T12:57:16Z","timestamp":1740833836000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/0278364910382464"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,10,11]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2011,3]]}},"alternative-id":["10.1177\/0278364910382464"],"URL":"https:\/\/doi.org\/10.1177\/0278364910382464","relation":{},"ISSN":["0278-3649","1741-3176"],"issn-type":[{"type":"print","value":"0278-3649"},{"type":"electronic","value":"1741-3176"}],"subject":[],"published":{"date-parts":[[2010,10,11]]}}}