{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T19:22:14Z","timestamp":1773775334633,"version":"3.50.1"},"reference-count":132,"publisher":"SAGE Publications","issue":"13-14","license":[{"start":{"date-parts":[[2019,7,12]],"date-time":"2019-07-12T00:00:00Z","timestamp":1562889600000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.sagepub.com\/licence-information-for-chorus"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N000141310821"],"award-info":[{"award-number":["N000141310821"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000104","name":"National Aeronautics and Space Administration","doi-asserted-by":"publisher","award":["NNX17CS56C"],"award-info":[{"award-number":["NNX17CS56C"]}],"id":[{"id":"10.13039\/100000104","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of Robotics Research"],"published-print":{"date-parts":[[2018,12]]},"abstract":"<jats:p> Robot planning is the process of selecting a sequence of actions that optimize for a task=specific objective. For instance, the objective for a navigation task would be to find collision-free paths, whereas the objective for an exploration task would be to map unknown areas. The optimal solutions to such tasks are heavily influenced by the implicit structure in the environment, i.e. the configuration of objects in the world. State-of-the-art planning approaches, however, do not exploit this structure, thereby expending valuable effort searching the action space instead of focusing on potentially good actions. In this paper, we address the problem of enabling planners to adapt their search strategies by inferring such good actions in an efficient manner using only the information uncovered by the search up until that time. We formulate this as a problem of sequential decision making under uncertainty where at a given iteration a planning policy must map the state of the search to a planning action. Unfortunately, the training process for such partial-information-based policies is slow to converge and susceptible to poor local minima. Our key insight is that if we could fully observe the underlying world map, we would easily be able to disambiguate between good and bad actions. We hence present a novel data-driven imitation learning framework to efficiently train planning policies by imitating a clairvoyant oracle: an oracle that at train time has full knowledge about the world map and can compute optimal decisions. We leverage the fact that for planning problems, such oracles can be efficiently computed and derive performance guarantees for the learnt policy. We examine two important domains that rely on partial-information-based policies: informative path planning and search-based motion planning. We validate the approach on a spectrum of environments for both problem domains, including experiments on a real UAV, and show that the learnt policy consistently outperforms state-of-the-art algorithms. Our framework is able to train policies that achieve up to [Formula: see text] more reward than state-of-the art information-gathering heuristics and a [Formula: see text] speedup as compared with A* on search-based planning problems. Our approach paves the way forward for applying data-driven techniques to other such problem domains under the umbrella of robot planning. <\/jats:p>","DOI":"10.1177\/0278364918781001","type":"journal-article","created":{"date-parts":[[2018,7,12]],"date-time":"2018-07-12T12:48:58Z","timestamp":1531399738000},"page":"1632-1672","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":42,"title":["Data-driven planning via imitation learning"],"prefix":"10.1177","volume":"37","author":[{"given":"Sanjiban","family":"Choudhury","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Mohak","family":"Bhardwaj","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Sankalp","family":"Arora","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Ashish","family":"Kapoor","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}]},{"given":"Gireeja","family":"Ranade","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}]},{"given":"Sebastian","family":"Scherer","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Debadeepta","family":"Dey","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}]}],"member":"179","published-online":{"date-parts":[[2018,7,12]]},"reference":[{"key":"bibr1-0278364918781001","author":"Abadi M","year":"2016","journal-title":"CoRR"},{"key":"bibr2-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"bibr3-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915594029"},{"key":"bibr4-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2011.08.001"},{"key":"bibr5-0278364918781001","author":"Arora S","year":"2017","journal-title":"Proceedings of ICRA"},{"key":"bibr6-0278364918781001","author":"Arulkumaran K","year":"2017","journal-title":"Preprint arXiv:1708.05866"},{"key":"bibr7-0278364918781001","volume-title":"Proceedings 21st International Conference on Automated Planning and Scheduling","author":"Asmuth J","year":"2011"},{"key":"bibr8-0278364918781001","author":"Bhardwaj M","year":"2017","journal-title":"Proceedings of CoRL"},{"key":"bibr9-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911404092"},{"key":"bibr10-0278364918781001","first-page":"213","volume":"3","author":"Brafman RI","year":"2002","journal-title":"Journal of Machine Learning Research"},{"key":"bibr11-0278364918781001","volume-title":"The Complexity of Robot Motion Planning","author":"Canny J","year":"1988"},{"key":"bibr12-0278364918781001","author":"Chang KW","year":"2015","journal-title":"Proceedings of ICML"},{"key":"bibr13-0278364918781001","author":"Charrow B","year":"2015","journal-title":"Proceedings of RSS"},{"key":"bibr14-0278364918781001","author":"Chekuri C","year":"2005","journal-title":"Proceedings of FOCS"},{"key":"bibr15-0278364918781001","author":"Chen M","year":"2016","journal-title":"Preprint arXiv:1602.04875"},{"key":"bibr16-0278364918781001","author":"Chen Y","year":"2016","journal-title":"CoRR"},{"key":"bibr17-0278364918781001","author":"Chen Y","year":"2015","journal-title":"Proceedings of AAAI"},{"key":"bibr18-0278364918781001","author":"Choudhury S","year":"2014","journal-title":"AHS 70th Annual Forum"},{"key":"bibr19-0278364918781001","author":"Choudhury S","year":"2016","journal-title":"Proceedings of IROS"},{"key":"bibr20-0278364918781001","author":"Choudhury S","year":"2017","journal-title":"Proceedings of NIPS"},{"key":"bibr21-0278364918781001","author":"Choudhury S","year":"2017","journal-title":"Proceedings of RSS"},{"key":"bibr22-0278364918781001","author":"Choudhury S","year":"2017","journal-title":"Proceedings of ICRA"},{"key":"bibr23-0278364918781001","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence","author":"Cohen WW","year":"2005"},{"key":"bibr24-0278364918781001","author":"Cover H","year":"2013","journal-title":"Proceedings of ICRA"},{"key":"bibr25-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5106-x"},{"key":"bibr26-0278364918781001","author":"Dellin CM","year":"2016","journal-title":"Proceedings of ICAPS"},{"key":"bibr27-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23778-7_11"},{"key":"bibr28-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399557"},{"key":"bibr29-0278364918781001","author":"Dolgov D","year":"2008","journal-title":"Proceedings of AAAI"},{"key":"bibr30-0278364918781001","first-page":"1329","volume-title":"Proceedings of International Conference on Machine Learning","author":"Duan Y","year":"2016"},{"key":"bibr31-0278364918781001","doi-asserted-by":"publisher","DOI":"10.2307\/2372560"},{"key":"bibr32-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989017"},{"key":"bibr33-0278364918781001","volume":"1","author":"Dugar V","year":"2017","journal-title":"AHS International 73rd Annual Forum"},{"key":"bibr34-0278364918781001","first-page":"49","volume-title":"International Conference on Machine Learning","author":"Finn C","year":"2016"},{"key":"bibr35-0278364918781001","first-page":"3089","volume-title":"Proceedings of the 25th International Joint Conference on Artificial Intelligence","author":"Garrett CR","year":"2016"},{"key":"bibr36-0278364918781001","first-page":"427","volume":"42","author":"Golovin D","year":"2011","journal-title":"Journal of Artificial Intelligence Research"},{"key":"bibr37-0278364918781001","author":"Golovin D","year":"2010","journal-title":"Proceedings of NIPS"},{"key":"bibr38-0278364918781001","volume-title":"Deep Learning","author":"Goodfellow I","year":"2016"},{"key":"bibr39-0278364918781001","author":"Gupta A","year":"2010","journal-title":"International Colloquium on Automata, Languages, and Programming"},{"key":"bibr40-0278364918781001","author":"Gupta S","year":"2017","journal-title":"Proceedings of CVPR"},{"key":"bibr41-0278364918781001","author":"Hansen N","year":"2016","journal-title":"Preprint arXiv:1604.00772"},{"key":"bibr42-0278364918781001","volume-title":"2015 AAAI Fall Symposium Series","author":"Hausknecht M","year":"2015"},{"key":"bibr43-0278364918781001","author":"Heng L","year":"2015","journal-title":"Proceedings of ICRA"},{"key":"bibr44-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1613\/jair.855"},{"key":"bibr45-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912467485"},{"key":"bibr46-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-29363-9_6"},{"key":"bibr47-0278364918781001","author":"Hollinger GA","year":"2013","journal-title":"Proceedings of RSS"},{"key":"bibr48-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1109\/ISATP.1999.782972"},{"key":"bibr49-0278364918781001","author":"Ichter B","year":"2017","journal-title":"Preprint arXiv:1709.05448"},{"key":"bibr50-0278364918781001","author":"Isler S","year":"2016","journal-title":"Proceedings of ICRA"},{"key":"bibr51-0278364918781001","author":"Iyer RK","year":"2013","journal-title":"Proceedings of NIPS"},{"key":"bibr52-0278364918781001","author":"Javdani S","year":"2014","journal-title":"Proceedings of AISTATS"},{"key":"bibr53-0278364918781001","author":"Javdani S","year":"2013","journal-title":"Proceedings of ICRA"},{"key":"bibr54-0278364918781001","author":"Javdani S","year":"2015","journal-title":"Proceedings of RSS"},{"key":"bibr55-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1017\/S026988891200001X"},{"key":"bibr56-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"bibr57-0278364918781001","author":"Kahn G","year":"2017","journal-title":"Proceedings of ICRA"},{"key":"bibr58-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"bibr59-0278364918781001","author":"Karkus P","year":"2017","journal-title":"Preprint arXiv:1703.06692"},{"key":"bibr60-0278364918781001","first-page":"1001","author":"Kearns MJ","year":"2000","journal-title":"Advances in Neural Information Processing Systems"},{"key":"bibr61-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1177\/02783649030227008"},{"key":"bibr62-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"bibr63-0278364918781001","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.034"},{"key":"bibr64-0278364918781001","first-page":"71","volume-title":"Tractability: Practical Approaches to Hard Problems","author":"Krause A","year":"2012"},{"key":"bibr65-0278364918781001","author":"Krause A","year":"2007","journal-title":"Proceedings of AAAI"},{"key":"bibr66-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733-9496(2008)134:6(516)"},{"key":"bibr67-0278364918781001","author":"Kuffner JJ","year":"2000","journal-title":"Proceedings of ICRA"},{"key":"bibr68-0278364918781001","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2008.IV.009"},{"key":"bibr69-0278364918781001","first-page":"158","volume":"3559","author":"Langford J","year":"2005","journal-title":"COLT 2005: Learning Theory"},{"key":"bibr70-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0036070"},{"key":"bibr71-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"bibr72-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1177\/02783640122067453"},{"key":"bibr73-0278364918781001","author":"Levine S","year":"2013","journal-title":"Proceedings of ICML"},{"key":"bibr74-0278364918781001","first-page":"1131","volume":"10","author":"Li H","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"bibr75-0278364918781001","author":"Li J","year":"2016","journal-title":"Preprint arXiv:1606.01541"},{"issue":"3","key":"bibr76-0278364918781001","first-page":"18","volume":"2","author":"Liaw A","year":"2002","journal-title":"R News"},{"key":"bibr77-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1177\/0278364909340445"},{"key":"bibr78-0278364918781001","author":"Lim ZW","year":"2015","journal-title":"Proceedings of NIPS"},{"key":"bibr79-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915596378"},{"key":"bibr80-0278364918781001","author":"Littman ML","year":"1995","journal-title":"Proceedings of ICML"},{"key":"bibr81-0278364918781001","first-page":"1555","author":"Littman ML","year":"2002","journal-title":"Advances in Neural Information Processing Systems"},{"key":"bibr82-0278364918781001","author":"Liu M","year":"2013","journal-title":"Proceedings of IJCAI"},{"key":"bibr83-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00378-8"},{"key":"bibr84-0278364918781001","first-page":"409","volume-title":"Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence","author":"McAllester DA","year":"1999"},{"key":"bibr85-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"bibr86-0278364918781001","volume-title":"Eighth Annual Symposium on Combinatorial Search","author":"Narayanan V","year":"2015"},{"key":"bibr87-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354077"},{"key":"bibr88-0278364918781001","first-page":"406","volume-title":"Proceedings of the Sixteenth conference on Uncertainty in artificial intelligence","author":"Ng AY","year":"2000"},{"key":"bibr89-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2651157"},{"key":"bibr90-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1287\/moor.12.3.441"},{"key":"bibr91-0278364918781001","volume-title":"Heuristics: Intelligent Search Strategies for Computer Problem Solving","author":"Pearl J","year":"1984"},{"key":"bibr92-0278364918781001","author":"Peters J","year":"2006","journal-title":"Proceedings of IROS"},{"key":"bibr93-0278364918781001","author":"Phillips M","year":"2012","journal-title":"Proceedings of Robotics: Science and Systems"},{"key":"bibr94-0278364918781001","author":"Phillips M","year":"2015","journal-title":"Proceedings of IJCAI"},{"key":"bibr95-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20285"},{"key":"bibr96-0278364918781001","first-page":"219","volume":"5","author":"Pohl I","year":"1970","journal-title":"Machine Intelligence"},{"key":"bibr97-0278364918781001","author":"Ranzato M","year":"2015","journal-title":"Preprint arXiv:1511.06732"},{"key":"bibr98-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9121-3"},{"key":"bibr99-0278364918781001","author":"Ross S","year":"2014","journal-title":"Prepring arXiv:1406.5979"},{"key":"bibr100-0278364918781001","first-page":"6","volume":"1","author":"Ross S","year":"2011","journal-title":"AISTATS"},{"key":"bibr101-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2567"},{"key":"bibr102-0278364918781001","author":"Ruml W","year":"2007","journal-title":"Proceedings of IJCAI"},{"key":"bibr103-0278364918781001","author":"Schaul T","year":"2015","journal-title":"CoRR"},{"key":"bibr104-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"bibr105-0278364918781001","author":"Silver D","year":"2010","journal-title":"Proceedings of NIPS"},{"key":"bibr106-0278364918781001","author":"Singh A","year":"2007","journal-title":"Proceedings of IJCAI"},{"key":"bibr107-0278364918781001","author":"Singh A","year":"2009","journal-title":"Proceedings of IJCAI"},{"key":"bibr108-0278364918781001","author":"Smith T","year":"2012","journal-title":"Preprint arXiv:1207.1412"},{"key":"bibr109-0278364918781001","author":"Somani A","year":"2013","journal-title":"Proceedings of NIPS"},{"key":"bibr110-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1659"},{"key":"bibr111-0278364918781001","author":"Sturm J","year":"2012","journal-title":"Proceedings of IROS"},{"key":"bibr112-0278364918781001","author":"Sun W","year":"2017","journal-title":"Proceedings of ICML"},{"key":"bibr113-0278364918781001","volume-title":"Reinforcement learning: An introduction","volume":"1","author":"Sutton RS","year":"1998"},{"key":"bibr114-0278364918781001","author":"Tamar A","year":"2016","journal-title":"Preprint arXiv:1609.09001"},{"key":"bibr115-0278364918781001","author":"Thayer JT","year":"2011","journal-title":"Proceedings of ICAPS"},{"key":"bibr116-0278364918781001","author":"Theano Development Team","year":"2016","journal-title":"arXiv e-prints"},{"key":"bibr117-0278364918781001","volume-title":"Probabilistic robotics","author":"Thrun S","year":"2005"},{"key":"bibr118-0278364918781001","author":"Tielman T","year":"2012","journal-title":"COURSERA: Neural Networks for Machine Learning"},{"key":"bibr119-0278364918781001","volume-title":"Preprints of the ICAPS\u201913 PAL Workshop on Planning and Learning","author":"Virseda J","year":"2013"},{"key":"bibr120-0278364918781001","author":"van Hasselt H","year":"2015","journal-title":"CoRR"},{"key":"bibr121-0278364918781001","volume-title":"ALR Workshop, NIPS","author":"Venkatraman A","year":"2014"},{"key":"bibr122-0278364918781001","author":"Wang Z","year":"2016","journal-title":"Proceedings of ICML"},{"key":"bibr123-0278364918781001","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"bibr124-0278364918781001","volume-title":"Proceedings of the Eighth Annual Symposium on Combinatorial Search","author":"Wilt CM","year":"2015"},{"key":"bibr125-0278364918781001","first-page":"1571","volume":"10","author":"Xu Y","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"bibr126-0278364918781001","author":"Xu Y","year":"2007","journal-title":"Proceedings of IJCAI"},{"key":"bibr127-0278364918781001","author":"Xu Y","year":"2010","journal-title":"Proceedings of ICAPS"},{"key":"bibr128-0278364918781001","author":"Yoon SW","year":"2006","journal-title":"Proceedings of ICAPS"},{"key":"bibr129-0278364918781001","author":"Yu J","year":"2014","journal-title":"Proceedings of IROS"},{"key":"bibr130-0278364918781001","first-page":"819","volume-title":"AAAI\u201916 Proceedings of the 30th AAAI Conference on Artificial Intelligence","author":"Zhang H","year":"2016"},{"key":"bibr131-0278364918781001","author":"Zhang T","year":"2016","journal-title":"Proceedings of ICRA"},{"key":"bibr132-0278364918781001","first-page":"1433","volume-title":"Proceedings of AAAI","volume":"8","author":"Ziebart BD","year":"2008"}],"container-title":["The International Journal of Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0278364918781001","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/0278364918781001","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0278364918781001","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0278364918781001","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T17:03:11Z","timestamp":1740762191000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/0278364918781001"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,12]]},"references-count":132,"journal-issue":{"issue":"13-14","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["10.1177\/0278364918781001"],"URL":"https:\/\/doi.org\/10.1177\/0278364918781001","relation":{},"ISSN":["0278-3649","1741-3176"],"issn-type":[{"value":"0278-3649","type":"print"},{"value":"1741-3176","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7,12]]}}}