{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:10:50Z","timestamp":1784301050333,"version":"3.55.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["2070 - 390732324"],"award-info":[{"award-number":["2070 - 390732324"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9812025","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"4473-4479","source":"Crossref","is-referenced-by-count":66,"title":["Adaptive Informative Path Planning Using Deep Reinforcement Learning for UAV-based Active Sensing"],"prefix":"10.1109","author":[{"given":"Julius","family":"Ruckin","sequence":"first","affiliation":[{"name":"University of Bonn,Cluster of Excellence PhenoRob, Institute of Geodesy and Geoinformation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liren","family":"Jin","sequence":"additional","affiliation":[{"name":"University of Bonn,Cluster of Excellence PhenoRob, Institute of Geodesy and Geoinformation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marija","family":"Popovic","sequence":"additional","affiliation":[{"name":"University of Bonn,Cluster of Excellence PhenoRob, Institute of Geodesy and Geoinformation"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","article-title":"Accelerating Self-Play Learning in Go","author":"wu","year":"2019","journal-title":"ArXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2018.8636075"},{"key":"ref30","article-title":"A disciplined approach to neural network hyper-parameters: Part 1– rate, batch size, momentum, and weight decay","author":"smith","year":"2018","journal-title":"ArXiv"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1609\/icaps.v30i1.6645","article-title":"Adaptive Informative Path Planning with Multimodal Sensing","volume":"30","author":"choudhury","year":"2020","journal-title":"International Conference on Automated Planning and Scheduling"},{"key":"ref11","article-title":"Informative Path Planning for Active Field Mapping under Localization Uncertainty","author":"popovi?","year":"2020","journal-title":"IEEE International Conference on Robotics and Automation"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2924839"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341657"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of Go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1287\/opre.43.4.684"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224902"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17432-2_31"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891991"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2011.2181683"},{"key":"ref27","first-page":"1344","article-title":"Active Learning for Level Set Estimation","author":"gotovos","year":"2013","journal-title":"International Joint Conference on Artificial Intelligence"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914533443"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76928-6_1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2750080"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/s8053557"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9790-x"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2013.09.004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21722"},{"key":"ref9","article-title":"Informative path planning for anomaly detection in environment exploration and eonitoring","author":"blanchard","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-020-09903-2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1609\/icaps.v28i1.13882","article-title":"Online algorithms for POMDPs with continuous state, action, and observation spaces","author":"sunberg","year":"2018","journal-title":"International Conference on Automated Planning and Scheduling"},{"key":"ref21","first-page":"216","article-title":"Monte-Carlo Tree Search: A New Framework for Game AI","volume":"8","author":"chaslot","year":"0","journal-title":"AAAI Artificial Intelligence and Interactive Digital Entertainment"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref23","article-title":"Monte-Carlo planning in large POMDPs","author":"silver","year":"2010","journal-title":"Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570193"},{"key":"ref25","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09812025.pdf?arnumber=9812025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T13:53:28Z","timestamp":1700834008000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9812025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9812025","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}