{"id":"https://openalex.org/W4312335729","doi":"https://doi.org/10.1109/iros47612.2022.9981661","title":"Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning","display_name":"Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312335729","doi":"https://doi.org/10.1109/iros47612.2022.9981661"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981661","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbilu.uni.lu/handle/10993/51908","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086236975","display_name":"Andrej Orsula","orcid":"https://orcid.org/0000-0003-0706-1191"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Andrej Orsula","raw_affiliation_strings":["University of Luxembourg,Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT),Luxembourg","Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg,Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT),Luxembourg","institution_ids":["https://openalex.org/I186903577"]},{"raw_affiliation_string":"Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048839097","display_name":"Simon B\u00f8gh","orcid":"https://orcid.org/0000-0002-5960-4365"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Simon B\u00f8gh","raw_affiliation_strings":["Robotics & Automation Group, Aalborg University,Department of Materials and Production,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics & Automation Group, Aalborg University,Department of Materials and Production,Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085280731","display_name":"Miguel A. Olivares-M\u00e9ndez","orcid":"https://orcid.org/0000-0001-8824-3231"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Miguel Olivares-Mendez","raw_affiliation_strings":["University of Luxembourg,Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT),Luxembourg","Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg,Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT),Luxembourg","institution_ids":["https://openalex.org/I186903577"]},{"raw_affiliation_string":"Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059979207","display_name":"Carol Mart\u00ednez","orcid":"https://orcid.org/0000-0003-3040-6119"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Carol Martinez","raw_affiliation_strings":["University of Luxembourg,Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT),Luxembourg","Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg,Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT),Luxembourg","institution_ids":["https://openalex.org/I186903577"]},{"raw_affiliation_string":"Space Robotics Research Group (SpaceR), Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9085,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.97303009,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4112","last_page":"4119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.8227134346961975},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7687618732452393},{"id":"https://openalex.org/keywords/octree","display_name":"Octree","score":0.714128315448761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6653107404708862},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4652930498123169},{"id":"https://openalex.org/keywords/astrobiology","display_name":"Astrobiology","score":0.43477320671081543},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.420726478099823}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.8227134346961975},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7687618732452393},{"id":"https://openalex.org/C141297171","wikidata":"https://www.wikidata.org/wiki/Q1143237","display_name":"Octree","level":2,"score":0.714128315448761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6653107404708862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4652930498123169},{"id":"https://openalex.org/C87355193","wikidata":"https://www.wikidata.org/wiki/Q411","display_name":"Astrobiology","level":1,"score":0.43477320671081543},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.420726478099823},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros47612.2022.9981661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981661","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:orbilu.uni.lu:10993/51908","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/51908","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2022-10-23); 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan [JP], 23/10/2022 \u2192 27/10/2022","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":{"id":"pmh:oai:orbilu.uni.lu:10993/51908","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/51908","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2022-10-23); 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan [JP], 23/10/2022 \u2192 27/10/2022","raw_type":"http://purl.org/coar/resource_type/c_5794"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2005824379","https://openalex.org/W2087153461","https://openalex.org/W2107469655","https://openalex.org/W2141664020","https://openalex.org/W2145339207","https://openalex.org/W2205340216","https://openalex.org/W2443711627","https://openalex.org/W2482417697","https://openalex.org/W2556802233","https://openalex.org/W2600030077","https://openalex.org/W2605102758","https://openalex.org/W2737234477","https://openalex.org/W2810785043","https://openalex.org/W2811462648","https://openalex.org/W2904246096","https://openalex.org/W2948894702","https://openalex.org/W2949676527","https://openalex.org/W2949924544","https://openalex.org/W2952988163","https://openalex.org/W2962793652","https://openalex.org/W2963166883","https://openalex.org/W3011706575","https://openalex.org/W3021619395","https://openalex.org/W3104141662","https://openalex.org/W3104734738","https://openalex.org/W3109891913","https://openalex.org/W3113399439","https://openalex.org/W3127352841","https://openalex.org/W3152021768","https://openalex.org/W3158652289","https://openalex.org/W3164788650","https://openalex.org/W3207351740","https://openalex.org/W3216772467","https://openalex.org/W4200235977","https://openalex.org/W4200453945","https://openalex.org/W4280571816","https://openalex.org/W4288374418","https://openalex.org/W4293864724","https://openalex.org/W6631190155","https://openalex.org/W6737327832","https://openalex.org/W6753243525","https://openalex.org/W6757592117","https://openalex.org/W6761443123","https://openalex.org/W6764969207","https://openalex.org/W6776730770","https://openalex.org/W6780559895","https://openalex.org/W6794526071","https://openalex.org/W6804601995"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W165915117","https://openalex.org/W2059402478","https://openalex.org/W2123347777","https://openalex.org/W4387804363","https://openalex.org/W2477150073","https://openalex.org/W2019547100","https://openalex.org/W2515493494"],"abstract_inverted_index":{"Extraterrestrial":[0],"rovers":[1,28],"with":[2,59,73,137],"a":[3,91,158,162],"general-purpose":[4],"robotic":[5,48],"arm":[6],"have":[7],"many":[8],"potential":[9],"applications":[10],"in":[11,70,102,161],"lunar":[12],"and":[13,34,76,141,168],"planetary":[14],"exploration.":[15],"Introducing":[16],"autonomy":[17],"into":[18],"such":[19],"systems":[20],"is":[21,62,84],"desirable":[22],"for":[23,46,87],"increasing":[24],"the":[25,40,53,129],"time":[26],"that":[27,93,108],"can":[29],"spend":[30],"gathering":[31],"scientific":[32],"data":[33,110],"collecting":[35],"samples.":[36],"This":[37],"work":[38],"investigates":[39],"applicability":[41],"of":[42,50,90,116,131],"deep":[43],"reinforcement":[44],"learning":[45,89,115],"vision-based":[47],"grasping":[49],"objects":[51,140],"on":[52,157],"Moon.":[54],"A":[55,79],"novel":[56,135],"simulation":[57],"environment":[58],"procedurally-generated":[60],"datasets":[61,169],"created":[63],"to":[64,99,121,134],"train":[65],"agents":[66,156],"under":[67],"challenging":[68],"conditions":[69],"unstructured":[71],"scenes":[72,136],"uneven":[74],"terrain":[75],"harsh":[77],"illumination.":[78],"model-free":[80],"off-policy":[81],"actor-critic":[82],"algorithm":[83],"then":[85],"employed":[86],"end-to-end":[88],"policy":[92],"directly":[94],"maps":[95],"compact":[96],"octree":[97],"observations":[98],"continuous":[100],"actions":[101],"Cartesian":[103],"space.":[104],"Experimental":[105],"evaluation":[106],"indicates":[107],"3D":[109],"representations":[111],"enable":[112],"more":[113],"effective":[114],"manipulation":[117],"skills":[118],"when":[119],"compared":[120],"traditionally":[122],"used":[123],"image-based":[124],"observations.":[125],"Domain":[126],"randomization":[127],"improves":[128],"generalization":[130],"learned":[132],"policies":[133],"previously":[138],"unseen":[139],"different":[142],"illumination":[143],"conditions.":[144],"To":[145],"this":[146],"end,":[147],"we":[148],"demonstrate":[149],"zero-shot":[150],"sim-to-real":[151],"transfer":[152],"by":[153],"evaluating":[154],"trained":[155],"real":[159],"robot":[160],"Moon-analogue":[163],"facility.":[164],"The":[165],"source":[166],"code":[167],"are":[170],"available":[171],"at":[172],"https://github.com/AndrejOrsula/drl_grasping.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-08T08:33:18.762332","created_date":"2025-10-10T00:00:00"}