{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T18:20:53Z","timestamp":1772302853149,"version":"3.50.1"},"reference-count":46,"publisher":"SAGE Publications","issue":"12","license":[{"start":{"date-parts":[[2015,8,5]],"date-time":"2015-08-05T00:00:00Z","timestamp":1438732800000},"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":[[2015,10]]},"abstract":"<jats:p> Robotic sampling is attractive in many field robotics applications that require persistent collection of physical samples for ex-situ analysis. Examples abound in the earth sciences in studies involving the collection of rock, soil, and water samples for laboratory analysis. In our test domain, marine ecosystem monitoring, detailed understanding of plankton ecology requires laboratory analysis of water samples, but predictions using physical and chemical properties measured in real-time by sensors aboard an autonomous underwater vehicle (AUV) can guide sample collection decisions. In this paper, we present a data-driven and opportunistic sampling strategy to minimize cumulative regret for batches of plankton samples acquired by an AUV over multiple surveys. Samples are labeled at the end of each survey, and used to update a probabilistic model that guides sampling during subsequent surveys. During a survey, the AUV makes irrevocable sample collection decisions online for a sequential stream of candidates, with no knowledge of the quality of future samples. In addition to extensive simulations using historical field data, we present results from a one-day field trial where beginning with a prior model learned from data collected and labeled in an earlier campaign, the AUV collected water samples with a high abundance of a pre-specified planktonic target. This is the first time such a field experiment has been carried out in its entirety in a data-driven fashion, in effect \u201cclosing the loop\u201d on a significant and relevant ecosystem monitoring problem while allowing domain experts (marine ecologists) to specify the mission at a relatively high level. <\/jats:p>","DOI":"10.1177\/0278364915587723","type":"journal-article","created":{"date-parts":[[2015,8,6]],"date-time":"2015-08-06T01:20:29Z","timestamp":1438824029000},"page":"1435-1452","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":96,"title":["Data-driven robotic sampling for marine ecosystem monitoring"],"prefix":"10.1177","volume":"34","author":[{"given":"Jnaneshwar","family":"Das","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Southern California, USA"}]},{"given":"Fr\u00e9d\u00e9ric","family":"Py","sequence":"additional","affiliation":[{"name":"Monterey Bay Aquarium Research Institute, Moss Landing, USA"}]},{"given":"Julio B.J.","family":"Harvey","sequence":"additional","affiliation":[{"name":"Monterey Bay Aquarium Research Institute, Moss Landing, USA"}]},{"given":"John P.","family":"Ryan","sequence":"additional","affiliation":[{"name":"Monterey Bay Aquarium Research Institute, Moss Landing, USA"}]},{"given":"Alyssa","family":"Gellene","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, University of Southern California, USA"}]},{"given":"Rishi","family":"Graham","sequence":"additional","affiliation":[{"name":"Monterey Bay Aquarium Research Institute, Moss Landing, USA"}]},{"given":"David A.","family":"Caron","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, University of Southern California, USA"}]},{"given":"Kanna","family":"Rajan","sequence":"additional","affiliation":[{"name":"Monterey Bay Aquarium Research Institute, Moss Landing, USA"}]},{"given":"Gaurav S.","family":"Sukhatme","sequence":"additional","affiliation":[{"name":"Monterey Bay Aquarium Research Institute, Moss Landing, USA"}]}],"member":"179","published-online":{"date-parts":[[2015,8,5]]},"reference":[{"issue":"3","key":"bibr1-0278364915587723","first-page":"12","volume":"83","author":"Anderson CR","year":"2010","journal-title":"Journal of Marine Systems"},{"key":"bibr2-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943245"},{"key":"bibr3-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2009.01.016"},{"key":"bibr4-0278364915587723","first-page":"1215","volume-title":"Proceedings of the 29th international conference on machine learning (ICML)","author":"Azimi J","year":"2012"},{"key":"bibr5-0278364915587723","unstructured":"Bach F (2011) Learning with submodular functions: A convex optimization perspective. Report, arXiv: abs\/1111.6453."},{"key":"bibr6-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1145\/1031495.1031499"},{"key":"bibr7-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15369-3_4"},{"key":"bibr8-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913488427"},{"key":"bibr9-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20343"},{"key":"bibr10-0278364915587723","first-page":"160","volume-title":"International conference on machine learning (ICML)","volume":"28","author":"Chen Y","year":"2013"},{"key":"bibr11-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912440736"},{"key":"bibr12-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509930"},{"issue":"1","key":"bibr13-0278364915587723","first-page":"3873","volume":"15","author":"Desautels T","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"bibr14-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1111\/j.1472-4642.2010.00725.x"},{"key":"bibr15-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1177012493"},{"key":"bibr16-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANSE.2007.4302447"},{"key":"bibr17-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2012.2183934"},{"key":"bibr18-0278364915587723","volume-title":"26th conference on artificial intelligence (AAAI), special track on computational sustainability and AI","author":"Garg S","year":"2012"},{"key":"bibr19-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2009.30"},{"key":"bibr20-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-62703-974-1_18"},{"key":"bibr21-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1016\/j.jembe.2011.11.022"},{"key":"bibr22-0278364915587723","unstructured":"Harvey JBJ, Zhang Y, Ryan JP (2012b) AUVs for ecological studies of marine plankton communities: Intelligent algorithms on Dorado and Tethys AUVs enable precise water sampling for plankton research. Sea Technology, September."},{"key":"bibr23-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2011.2181771"},{"key":"bibr24-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912452675"},{"key":"bibr25-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-00065-7_51"},{"key":"bibr26-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273553"},{"key":"bibr27-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1145\/1127777.1127782"},{"key":"bibr28-0278364915587723","volume-title":"Proceedings of the 19th international conference on automated planning and scheduling (ICAPS-09)","author":"Low KH","year":"2009"},{"key":"bibr29-0278364915587723","volume-title":"version 8.1.0.604, R2013a","author":"MATLAB","year":"2013"},{"key":"bibr30-0278364915587723","volume-title":"Gaussian Processes for Machine Learning","author":"Rasmussen CE","year":"2006"},{"key":"bibr31-0278364915587723","unstructured":"Rasmussen CE, Nickisch H (2013) GPML Gaussian Processes for Machine Learning Toolbox. http:\/\/mloss.org\/software\/view\/263\/."},{"key":"bibr32-0278364915587723","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2013.IX.025"},{"key":"bibr33-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1016\/j.jembe.2014.05.017"},{"key":"bibr34-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsr2.2013.01.017"},{"key":"bibr35-0278364915587723","doi-asserted-by":"publisher","DOI":"10.4319\/lom.2010.8.394"},{"key":"bibr36-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385685"},{"key":"bibr37-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2674"},{"key":"bibr38-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509934"},{"key":"bibr39-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2182033"},{"key":"bibr40-0278364915587723","unstructured":"Srinivas N, Krause A, Kakade SM, (2009) Gaussian process optimization in the bandit setting: no regret and experimental design. In: Proceedings of the 27th international conference on machine learning (ICML), Haifa, Israel, 21\u201324 June, pp. 1015\u20131022. Madison: Omnipress."},{"key":"bibr41-0278364915587723","first-page":"621","author":"Stealey MJ","year":"2008","journal-title":"IEEE international conference on robotics and automation (ICRA)"},{"key":"bibr42-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20364"},{"key":"bibr43-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6697126"},{"key":"bibr44-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.364041"},{"key":"bibr45-0278364915587723","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2010.2081031"},{"key":"bibr46-0278364915587723","doi-asserted-by":"publisher","DOI":"10.4319\/lom.2012.10.934"}],"container-title":["The International Journal of Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0278364915587723","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/0278364915587723","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0278364915587723","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T12:39:06Z","timestamp":1740832746000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/0278364915587723"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,8,5]]},"references-count":46,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2015,10]]}},"alternative-id":["10.1177\/0278364915587723"],"URL":"https:\/\/doi.org\/10.1177\/0278364915587723","relation":{},"ISSN":["0278-3649","1741-3176"],"issn-type":[{"value":"0278-3649","type":"print"},{"value":"1741-3176","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,8,5]]}}}