{"id":"https://openalex.org/W4417251985","doi":"https://doi.org/10.1109/lra.2025.3643304","title":"An Intention-Guided Reinforcement Learning Approach With Dirichlet Energy Constraint for Heterogeneous Multi-Robot Cooperation","display_name":"An Intention-Guided Reinforcement Learning Approach With Dirichlet Energy Constraint for Heterogeneous Multi-Robot Cooperation","publication_year":2025,"publication_date":"2025-12-11","ids":{"openalex":"https://openalex.org/W4417251985","doi":"https://doi.org/10.1109/lra.2025.3643304"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2025.3643304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3643304","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","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/A5102753306","display_name":"Heteng Zhang","orcid":"https://orcid.org/0000-0002-4602-3836"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Heteng Zhang","raw_affiliation_strings":["School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002615112","display_name":"Yunjie Jia","orcid":"https://orcid.org/0000-0001-5967-2125"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yunjie Jia","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Hong Kong, SAR, China","Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057493831","display_name":"Zihao Sun","orcid":"https://orcid.org/0000-0001-6337-1712"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Sun","raw_affiliation_strings":["School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651809","display_name":"Yong Song","orcid":"https://orcid.org/0000-0003-2505-2766"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Song","raw_affiliation_strings":["School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101552069","display_name":"Bao Pang","orcid":"https://orcid.org/0000-0002-3483-9352"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bao Pang","raw_affiliation_strings":["School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035287663","display_name":"Xianfeng Yuan","orcid":"https://orcid.org/0000-0002-6217-6429"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianfeng Yuan","raw_affiliation_strings":["School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101645277","display_name":"Rui Song","orcid":"https://orcid.org/0000-0002-4119-4433"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Song","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029827598","display_name":"Simon X. Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Simon X. Yang","raw_affiliation_strings":["Advanced Robotics and Intelligent Systems Laboratory, University of Guelph, Guelph, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Advanced Robotics and Intelligent Systems Laboratory, University of Guelph, Guelph, ON, Canada","institution_ids":["https://openalex.org/I79817857"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5102753306"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22110204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"2","first_page":"1450","last_page":"1457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6324999928474426,"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":0.6324999928474426,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.13809999823570251,"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"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.04320000112056732,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7005000114440918},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.5160999894142151},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.508400022983551},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.49140000343322754},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4496999979019165},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.41269999742507935},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.3736000061035156},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.35899999737739563},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3255000114440918}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7005000114440918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6234999895095825},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4496999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42719998955726624},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40380001068115234},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.3005000054836273},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C199622910","wikidata":"https://www.wikidata.org/wiki/Q1128326","display_name":"Constraint satisfaction problem","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C149946192","wikidata":"https://www.wikidata.org/wiki/Q3235733","display_name":"Cognitive radio","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C173404611","wikidata":"https://www.wikidata.org/wiki/Q528588","display_name":"Constraint programming","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3643304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3643304","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2775110590","https://openalex.org/W2936516903","https://openalex.org/W2951360122","https://openalex.org/W3043763914","https://openalex.org/W4308365139","https://openalex.org/W4319302559","https://openalex.org/W4388017433","https://openalex.org/W4389665335","https://openalex.org/W4390224158","https://openalex.org/W4400877128","https://openalex.org/W4405137273","https://openalex.org/W4405779056","https://openalex.org/W4405785484","https://openalex.org/W4406755395","https://openalex.org/W4413513049","https://openalex.org/W4413847202"],"related_works":[],"abstract_inverted_index":{"Multi-robot":[0],"systems":[1],"have":[2],"demonstrated":[3],"significant":[4],"potential":[5],"in":[6,34,57],"accomplishing":[7],"complex":[8],"tasks,":[9],"such":[10],"as":[11],"cooperative":[12,136],"pursuit,":[13],"search-and-rescue":[14],"operations.":[15],"The":[16],"emergence":[17],"of":[18,116,122,144,159],"heterogeneous":[19,58],"robots":[20,125],"with":[21,30,47,73],"diverse":[22],"capabilities":[23],"and":[24,42,50,147,153],"characteristics":[25],"shows":[26],"superior":[27],"adaptability":[28],"compared":[29],"homogeneous":[31],"teams.":[32],"However,":[33],"practical":[35],"applications,":[36],"global":[37],"information":[38],"is":[39,86,106,166],"typically":[40],"inaccessible,":[41],"composite":[43],"teams":[44],"must":[45],"contend":[46],"partial":[48],"observability":[49],"coordination":[51],"difficulties.":[52],"To":[53],"address":[54],"the":[55,109,114,142,157,160,170],"issue":[56],"multi-robot":[59],"systems,":[60],"we":[61],"propose":[62],"a":[63,102],"novel":[64],"<italic":[65,74,77],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[66,68,75,78],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">I</i>ntention-<italic":[67],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">G</i>uided":[69],"reinforcement":[70],"learning":[71],"approach":[72,140],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">D</i>irichlet":[76],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">E</i>nergy":[79],"constraint":[80,105],"(IGDE).":[81],"Specifically,":[82],"an":[83],"intention-guided":[84],"module":[85],"designed":[87],"to":[88,112,168],"derive":[89],"long-horizon":[90],"strategies":[91],"based":[92],"solely":[93],"on":[94],"local":[95],"observations,":[96],"enabling":[97],"foresighted":[98],"decision-making.":[99],"In":[100],"addition,":[101],"Dirichlet":[103],"energy":[104],"incorporated":[107],"into":[108],"communication":[110],"process":[111],"enhance":[113],"diversity":[115],"environmental":[117],"cognition":[118],"among":[119],"different":[120],"classes":[121],"robots.":[123],"Heterogeneous":[124],"perform":[126],"class-aware":[127],"actions":[128],"driven":[129],"by":[130],"distinct":[131],"cognitive":[132],"representations,":[133],"thereby":[134],"enhancing":[135],"efficiency.":[137],"Notably,":[138],"our":[139],"alleviates":[141],"need":[143],"prior":[145],"knowledge":[146],"heterogeneity":[148],"modeling.":[149],"Extensive":[150],"comparative":[151],"experiments":[152],"ablation":[154],"studies":[155],"verify":[156],"effectiveness":[158],"proposed":[161],"framework.":[162],"Additionally,":[163],"real-world":[164],"deployment":[165],"conducted":[167],"demonstrate":[169],"practicality.":[171]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-11T00:00:00"}
