{"id":"https://openalex.org/W4413925386","doi":"https://doi.org/10.1109/icra55743.2025.11127719","title":"RM-Planner: Integrating Reinforcement Learning with Whole-Body Model Predictive Control for Mobile Manipulation","display_name":"RM-Planner: Integrating Reinforcement Learning with Whole-Body Model Predictive Control for Mobile Manipulation","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925386","doi":"https://doi.org/10.1109/icra55743.2025.11127719"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5104226051","display_name":"Zixuan Zhuang","orcid":"https://orcid.org/0009-0004-8675-2883"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zixuan Zhuang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103871674","display_name":"Le Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Zheng","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102531361","display_name":"Wanyue Li","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wanyue Li","raw_affiliation_strings":["The University of Hong Kong,Department of Mechanical Engineering,Hong Kong SAR,China"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,Department of Mechanical Engineering,Hong Kong SAR,China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018019304","display_name":"Renming Liu","orcid":"https://orcid.org/0000-0002-0088-7583"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renming Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063274899","display_name":"Peng L\u00fc","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Peng Lu","raw_affiliation_strings":["The University of Hong Kong,Department of Mechanical Engineering,Hong Kong SAR,China"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,Department of Mechanical Engineering,Hong Kong SAR,China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101409148","display_name":"Hui Cheng","orcid":"https://orcid.org/0000-0003-2579-7004"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Cheng","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5104226051"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35153781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7263","last_page":"7269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9794999957084656,"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":0.9794999957084656,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9398999810218811,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.8162363767623901},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7984398603439331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6634547710418701},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5649964213371277},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5371765494346619},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5012495517730713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38699033856391907},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3796570897102356},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2213873565196991},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2028990387916565}],"concepts":[{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.8162363767623901},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7984398603439331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6634547710418701},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5649964213371277},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5371765494346619},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5012495517730713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38699033856391907},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3796570897102356},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2213873565196991},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2028990387916565}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1531755431","https://openalex.org/W2012320692","https://openalex.org/W2141664020","https://openalex.org/W2162991084","https://openalex.org/W2194775991","https://openalex.org/W2288650507","https://openalex.org/W2842089854","https://openalex.org/W2904246096","https://openalex.org/W2962787639","https://openalex.org/W2962887844","https://openalex.org/W2963092423","https://openalex.org/W2967464230","https://openalex.org/W2970228732","https://openalex.org/W2982095652","https://openalex.org/W2998903229","https://openalex.org/W3033227010","https://openalex.org/W3046709980","https://openalex.org/W3130930520","https://openalex.org/W3206530605","https://openalex.org/W3207537403","https://openalex.org/W4200630212","https://openalex.org/W4285102174","https://openalex.org/W4385430747","https://openalex.org/W4385607490","https://openalex.org/W4388936652","https://openalex.org/W4401413720","https://openalex.org/W4401416030","https://openalex.org/W4401416917","https://openalex.org/W4401417276","https://openalex.org/W4405785337","https://openalex.org/W4405788108"],"related_works":["https://openalex.org/W1568779110","https://openalex.org/W804484174","https://openalex.org/W4244698559","https://openalex.org/W4246538999","https://openalex.org/W56933075","https://openalex.org/W4399598005","https://openalex.org/W2002361198","https://openalex.org/W2168364913","https://openalex.org/W1548568597","https://openalex.org/W2482749251"],"abstract_inverted_index":{"Mobile":[0],"manipulation":[1,42,77,101],"is":[2],"a":[3,37,50,56,80],"crucial":[4],"problem":[5],"in":[6,44],"various":[7],"real-world":[8,116],"applications.":[9],"However,":[10],"existing":[11],"methods":[12],"have":[13],"demonstrated":[14],"unsatisfactory":[15],"training":[16],"efficiency":[17],"and":[18,29,67,107,115],"sparse":[19],"rewards,":[20],"requiring":[21],"complex":[22,46],"coordination":[23],"strategies":[24],"between":[25],"the":[26,75,93,96],"mobile":[27,41],"base":[28],"arm.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,54],"propose":[35],"RM-Planner,":[36],"planning":[38],"method":[39],"for":[40],"tasks":[43],"unknown":[45],"environments.":[47],"By":[48],"adopting":[49],"two-layer":[51],"hierarchical":[52],"framework,":[53],"utilize":[55],"whole-body":[57],"Model":[58],"Predictive":[59],"Control":[60],"(MPC)-based":[61],"low-level":[62],"planner":[63],"to":[64,98],"track":[65],"subgoals":[66],"generate":[68],"aggressive":[69],"but":[70],"safe":[71],"joint":[72],"commands":[73],"throughout":[74],"entire":[76],"process,":[78],"while":[79],"Reinforcement":[81],"Learning":[82],"(RL)based":[83],"high-level":[84],"policy":[85],"directly":[86],"uses":[87],"3D":[88],"point":[89],"cloud":[90],"representations":[91],"of":[92],"environment,":[94],"guiding":[95],"robot":[97],"achieve":[99],"optimal":[100],"postures":[102],"based":[103],"on":[104],"current":[105],"observations":[106],"specific":[108],"task":[109],"objectives.":[110],"We":[111],"conduct":[112],"extensive":[113],"simulations":[114],"experiments,":[117],"where":[118],"RM-planner":[119],"significantly":[120],"outperforms":[121],"state-of-the-art":[122],"methods.":[123],"Our":[124],"code":[125],"will":[126],"be":[127],"released":[128],"at":[129],"https://github.com/SYSU-RoboticsLab/RM-Planner.git.":[130]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}