{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:40:21Z","timestamp":1775076021964,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981661","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T14:38:15Z","timestamp":1672065495000},"page":"4112-4119","source":"Crossref","is-referenced-by-count":15,"title":["Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Andrej","family":"Orsula","sequence":"first","affiliation":[{"name":"University of Luxembourg,Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT),Luxembourg"}]},{"given":"Simon","family":"B\u00f8gh","sequence":"additional","affiliation":[{"name":"Robotics & Automation Group, Aalborg University,Department of Materials and Production,Denmark"}]},{"given":"Miguel","family":"Olivares-Mendez","sequence":"additional","affiliation":[{"name":"University of Luxembourg,Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT),Luxembourg"}]},{"given":"Carol","family":"Martinez","sequence":"additional","affiliation":[{"name":"University of Luxembourg,Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT),Luxembourg"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/s21248418"},{"key":"ref35","article-title":"Open Robotics","year":"0","journal-title":"Gazebo"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/s21238161"},{"key":"ref34","article-title":"OpenAI Gym","author":"brockman","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref15","article-title":"Data-efficient Deep Reinforcement Learning for Dexterous Manipulation","author":"popov","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm6074"},{"key":"ref14","first-page":"1395","article-title":"A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms","volume":"22","author":"kroemer","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SII46433.2020.9025951"},{"key":"ref31","author":"sucan","year":"0","journal-title":"MoveIt 2"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844730"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363472"},{"key":"ref2","author":"moses","year":"2016","journal-title":"Frontier In-Situ Resource Utilization for Enabling Sustained Human Presence on Mars ser NASA technical memorandum NASA Langley Research Center"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41550-019-0804-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref38","article-title":"Blender 3.0","year":"0","journal-title":"Blender Development Team"},{"key":"ref19","article-title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","author":"kalashnikov","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460553"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560889"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/s21113606"},{"key":"ref26","first-page":"5556","article-title":"Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics","volume":"119","author":"kuznetsov","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070300"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"key":"ref42","first-page":"1162","article-title":"Active Domain Randomization","volume":"100","author":"mehta","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref41","article-title":"Building a Piece of the Moon: Construction of Two Indoor Lunar Analogue Environments","author":"ludivig","year":"2020","journal-title":"International Astronautical Congress"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.701"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073608"},{"key":"ref28","first-page":"1","article-title":"Stable-Baselines3: Reliable Reinforcement Learning Implementations","volume":"22","author":"raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref27","article-title":"Soft Actor-Critic Algorithms and Applications","author":"haarnoja","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICARSC.2016.62"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2009.07.029"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/AERO.2018.8396726"},{"key":"ref4","article-title":"NASA Selects Companies to Collect Lunar Resources for Artemis","author":"schierholz","year":"2020","journal-title":"NASA"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11214-020-00781-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11214-012-9892-2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/AERO.2019.8742215"},{"key":"ref40","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"0","journal-title":"International Conference on Learning Representations"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Kyoto, Japan","start":{"date-parts":[[2022,10,23]]},"end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981661.pdf?arnumber=9981661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T17:40:11Z","timestamp":1701279611000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981661\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981661","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}