{"id":"https://openalex.org/W7125975985","doi":"https://doi.org/10.2514/6.2026-0131","title":"Multi-Agent Reinforcement Learning for Swarm Planetary Exploration","display_name":"Multi-Agent Reinforcement Learning for Swarm Planetary Exploration","publication_year":2026,"publication_date":"2026-01-08","ids":{"openalex":"https://openalex.org/W7125975985","doi":"https://doi.org/10.2514/6.2026-0131"},"language":"en","primary_location":{"id":"doi:10.2514/6.2026-0131","doi":"https://doi.org/10.2514/6.2026-0131","is_oa":false,"landing_page_url":"https://doi.org/10.2514/6.2026-0131","pdf_url":null,"source":{"id":"https://openalex.org/S4363604158","display_name":"AIAA SciTech Forum","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"AIAA SCITECH 2026 Forum","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124075716","display_name":"Adri\u00e1n Menor de O\u00f1ate","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Adri\u00e1n Menor de O\u00f1ate","raw_affiliation_strings":["Technische Universiteit Delft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universiteit Delft","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084079105","display_name":"Erik-Jan Van Kampen","orcid":"https://orcid.org/0000-0002-5593-4471","observed_orcids":["https://orcid.org/0000-0002-5593-4471"]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Erik-Jan Van Kampen","raw_affiliation_strings":["Technische Universiteit Delft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universiteit Delft","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06267038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.008299999870359898,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9100000262260437},{"id":"https://openalex.org/keywords/planetary-exploration","display_name":"planetary exploration","score":0.6660000085830688},{"id":"https://openalex.org/keywords/swarm-robotics","display_name":"swarm robotics","score":0.9909999966621399},{"id":"https://openalex.org/keywords/mappo","display_name":"MAPPO","score":0.8370000123977661},{"id":"https://openalex.org/keywords/decentralized-control","display_name":"decentralized control","score":0.7129999995231628},{"id":"https://openalex.org/keywords/lidar-perception","display_name":"LiDAR perception","score":0.8389999866485596},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.6159999966621399},{"id":"https://openalex.org/keywords/technology-readiness-level","display_name":"technology readiness level","score":0.6340000033378601},{"id":"https://openalex.org/keywords/planetary-rovers","display_name":"planetary rovers","score":0.4480000138282776}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7939000129699707},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.659600019454956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6025999784469604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5289000272750854},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.48399999737739563},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C169337768","wikidata":"https://www.wikidata.org/wiki/Q2446723","display_name":"Swarm robotics","level":3,"score":0.47699999809265137},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4699000120162964},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3203999996185303},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C119487961","wikidata":"https://www.wikidata.org/wiki/Q863960","display_name":"Swarm intelligence","level":3,"score":0.29179999232292175},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2547999918460846},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C2989189746","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Function optimization","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2514/6.2026-0131","doi":"https://doi.org/10.2514/6.2026-0131","is_oa":false,"landing_page_url":"https://doi.org/10.2514/6.2026-0131","pdf_url":null,"source":{"id":"https://openalex.org/S4363604158","display_name":"AIAA SciTech Forum","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"AIAA SCITECH 2026 Forum","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W2056746635","https://openalex.org/W2747213132","https://openalex.org/W2996134258","https://openalex.org/W2997312297","https://openalex.org/W3033770108","https://openalex.org/W3215870290"],"related_works":["https://openalex.org/W3033770108","https://openalex.org/W4410087040","https://openalex.org/W7163425368","https://openalex.org/W7206157038","https://openalex.org/W4417509091","https://openalex.org/W4388116576","https://openalex.org/W6893084799","https://openalex.org/W4388430290","https://openalex.org/W2997312297","https://openalex.org/W7124160873"],"abstract_inverted_index":{"Exploring":[0],"planetary":[1,36],"bodies":[2],"using":[3],"robot":[4],"swarms":[5,37,54],"can":[6],"potentially":[7],"increase":[8],"the":[9,12,16,31,66,70,85,92,95],"value":[10,96,133],"of":[11,18,35,69,94,130],"exploration":[13],"missions;":[14],"enabling":[15],"execution":[17],"novel":[19],"measurements":[20],"and":[21,91,100,113,119,135],"explorations":[22],"previously":[23],"deemed":[24],"impractical":[25],"or":[26],"unattainable.":[27],"Despite":[28],"its":[29],"potential,":[30],"technology":[32,67],"readiness":[33,68],"level":[34],"is":[38,79],"not":[39],"very":[40],"mature.":[41],"This":[42],"work":[43],"uses":[44,87],"multi-agent":[45,73],"reinforcement":[46],"learning":[47,121],"to":[48,55,115],"find":[49],"control":[50,107],"policies":[51,108],"that":[52,109],"allow":[53],"autonomously":[56],"explore":[57],"unknown":[58],"areas":[59],"in":[60],"a":[61],"decentralized":[62],"manner,":[63],"contributing":[64],"towards":[65],"field.":[71],"A":[72],"proximal":[74],"policy":[75,86],"optimization":[76],"(MAPPO)":[77],"algorithm":[78,105],"proposed":[80],"for":[81],"this":[82],"end,":[83],"where":[84],"LIDAR":[88],"perception":[89],"information,":[90],"input":[93],"function":[97],"contains":[98],"local":[99],"global":[101],"environment":[102,136],"information.":[103],"The":[104],"finds":[106],"achieve":[110],"cooperation":[111],"behaviors":[112],"generalize":[114],"unseen":[116],"swarm":[117],"sizes":[118],"environments":[120],"with":[122],"simple,":[123],"sparse":[124],"reward":[125,131],"functions.":[126],"Moreover,":[127],"different":[128],"types":[129],"functions,":[132],"inputs,":[134],"configurations":[137],"are":[138],"investigated.":[139]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-01-29T00:00:00"}