{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T10:53:59Z","timestamp":1775732039568,"version":"3.50.1"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10161374","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"10181-10188","source":"Crossref","is-referenced-by-count":8,"title":["Hierarchical Policy Blending as Inference for Reactive Robot Control"],"prefix":"10.1109","author":[{"given":"Kay","family":"Hansel","sequence":"first","affiliation":[{"name":"Technische Universität Darmstadt,Computer Science Department,Germany"}]},{"given":"Julen","family":"Urain","sequence":"additional","affiliation":[{"name":"Technische Universität Darmstadt,Computer Science Department,Germany"}]},{"given":"Jan","family":"Peters","sequence":"additional","affiliation":[{"name":"Technische Universität Darmstadt,Computer Science Department,Germany"}]},{"given":"Georgia","family":"Chalvatzaki","sequence":"additional","affiliation":[{"name":"Technische Universität Darmstadt,Computer Science Department,Germany"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561543"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211040561"},{"key":"ref12","article-title":"Geometric fabrics for the acceleration-based design of robotic motion","author":"xie","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184003"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/70.508439"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2012.VIII.045"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143311"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2012.08.006"},{"key":"ref53","first-page":"1481","article-title":"Distributed gaussian processes","volume":"37","author":"deisenroth","year":"2015","journal-title":"Proceedings of The 32nd International Conference on Machine Learning"},{"key":"ref52","article-title":"Transductive log opinion pool of gaussian process experts","author":"cao","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref11","first-page":"441","article-title":"Rmpflow: A computational graph for automatic motion policy generation","author":"cheng","year":"2018","journal-title":"International Workshop on the Algorithmic Foundations of Robotics"},{"key":"ref55","first-page":"2068","article-title":"Healing products of Gaussian process experts","volume":"119","author":"cohen","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2159412"},{"key":"ref54","first-page":"3131","article-title":"Generalized robust Bayesian committee machine for large-scale Gaussian process regression","volume":"80","author":"liu","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref16","article-title":"Rapidly-exploring random trees: A new tool for path planning","volume":"98","author":"lavalle","year":"1998","journal-title":"Computer Science Dept Oct"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918790369"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.058"},{"key":"ref51","article-title":"Generalized product of experts for automatic and principled fusion of gaussian process predictions","author":"cao","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793786"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1177\/0278364908091463"},{"key":"ref45","first-page":"204","article-title":"Riemannian motion policy fusion through learnable lyapunov function reshaping","author":"mukadam","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907339"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-05181-4_11"},{"key":"ref42","first-page":"25 867","article-title":"Actor-critic based improper reinforcement learning","volume":"162","author":"zaki","year":"2022","journal-title":"Proceedings of the 39th International Conference on Machine Learning"},{"key":"ref41","article-title":"Continuous action reinforcement learning from a mixture of interpretable experts","author":"akrour","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref44","article-title":"Rmp2: A structured composable policy class for robot learning","author":"li","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.052"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385651"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980280"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913488805"},{"key":"ref9","article-title":"Learning implicit priors for motion optimization","author":"lambert","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-012-0527-1"},{"key":"ref6","article-title":"Riemannian motion policies","author":"ratliff","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9648-7"},{"key":"ref40","first-page":"1423","article-title":"Specializing versatile skill libraries using local mixture of experts","author":"celik","year":"2022","journal-title":"Conference on Robot Learning"},{"key":"ref35","first-page":"5058","article-title":"Neural dynamic policies for end-to-end sensorimotor learning","volume":"33","author":"bahl","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref34","first-page":"17 321","article-title":"Long-horizon visual planning with goal-conditioned hierarchical predictors","volume":"33","author":"pertsch","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref37","first-page":"273","article-title":"Hierarchical relative entropy policy search","author":"daniel","year":"2012","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.023"},{"key":"ref31","article-title":"Hierarchical planning in the now","author":"kaelbling","year":"0","journal-title":"Workshops at the Twenty-Fourth AAAI Conference on Artificial Intelligence"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3188109"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906922"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1109\/ICHR.2008.4755937","article-title":"Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields","author":"park","year":"2008","journal-title":"IEEE-RAS International Conference on Humanoid Robots HUMANOIDS 2008"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989761"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139389"},{"key":"ref24","article-title":"Stein variational model predictive control","author":"lambert","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1714","DOI":"10.1109\/ICRA.2017.7989202","article-title":"Information theoretic mpc for model-based reinforcement learning","author":"williams","year":"2017","journal-title":"2017 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-60916-4_7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-8997-2_29"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912444543"},{"key":"ref64","author":"ellenberger","year":"2018","journal-title":"PyBullet Gymperium"},{"key":"ref63","author":"minka","year":"2000","journal-title":"Estimating a Dirichlet Distribution"},{"key":"ref22","first-page":"750","article-title":"Storm: An integrated framework for fast joint-space model-predictive control for reactive manipulation","volume":"164","author":"bhardwaj","year":"2022","journal-title":"Proceedings of the 5th Conference on Robot Learning"},{"key":"ref21","first-page":"1049","article-title":"Sample-efficient cross-entropy method for real-time planning","volume":"155","author":"pinneri","year":"2021","journal-title":"Proceedings of the 2020 Conference on Robot Learning"},{"key":"ref28","article-title":"Reinforcement learning and control as probabilistic inference: Tutorial and review","author":"levine","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553508"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300014908"},{"key":"ref60","author":"beal","year":"2003","journal-title":"Variational algorithms for approximate Bayesian inference"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7727"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.929620"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10161374.pdf?arnumber=10161374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:34:56Z","timestamp":1690220096000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10161374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10161374","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}