{"id":"https://openalex.org/W7153985619","doi":"https://doi.org/10.1109/lra.2026.3682979","title":"Dynamic Legged Ball Manipulation on Rugged Terrains With Hierarchical Reinforcement Learning","display_name":"Dynamic Legged Ball Manipulation on Rugged Terrains With Hierarchical Reinforcement Learning","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7153985619","doi":"https://doi.org/10.1109/lra.2026.3682979"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3682979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3682979","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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/A5133542930","display_name":"Dongjie Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongjie Zhu","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-2290-4725","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhuo Yang","orcid":"https://orcid.org/0009-0001-5572-1679"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Yang","raw_affiliation_strings":["School of Computer Science, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-5572-1679","affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuesong Li","orcid":"https://orcid.org/0000-0003-1570-277X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesong Li","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","School of Computer Science, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1570-277X","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Computer Science, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133494524","display_name":"Wenjun Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Xu","raw_affiliation_strings":["Research Institute of Multiple Agents and Embodied Intelligence, Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0053-0752","affiliations":[{"raw_affiliation_string":"Research Institute of Multiple Agents and Embodied Intelligence, Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-7485-6344"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":["The Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0001-7485-6344","affiliations":[{"raw_affiliation_string":"The Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-0699-1904"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","School of Computer Science, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0699-1904","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Computer Science, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39928277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"6","first_page":"6815","last_page":"6822"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.4194999933242798,"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":0.4194999933242798,"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":0.21799999475479126,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.0997999981045723,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/terrain","display_name":"Terrain","score":0.5626000165939331},{"id":"https://openalex.org/keywords/ball","display_name":"Ball (mathematics)","score":0.5289999842643738},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4772000014781952},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.31610000133514404},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.29269999265670776}],"concepts":[{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.5626000165939331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5605000257492065},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.5289999842643738},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4772000014781952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46399998664855957},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3765000104904175},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3158000111579895},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.27000001072883606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3682979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3682979","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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":[{"id":"https://openalex.org/G3702059814","display_name":null,"funder_award_id":"62461160307","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Achieving":[0],"reliable":[1],"object":[2],"manipulation":[3,29,133],"while":[4],"traversing":[5],"complex":[6],"terrains":[7],"is":[8,39,54],"the":[9],"missing":[10],"link":[11],"between":[12,88],"agile":[13],"quadruped":[14],"locomotion":[15],"and":[16,48,83,96,113,120],"practical":[17],"autonomy.":[18],"Specifically,":[19],"using":[20],"traditional":[21],"end-to-end":[22,59],"reinforcement":[23],"learning":[24],"(RL)":[25],"for":[26],"dynamic":[27,131],"ball":[28,49,84,94,132],"in":[30,58,130,140],"rugged":[31,135],"environments":[32],"presents":[33],"two":[34],"key":[35],"challenges.":[36],"The":[37,52],"first":[38],"coordinating":[40],"distinct":[41],"motion":[42],"modalities":[43],"to":[44,107],"integrate":[45],"terrain":[46,98],"traversal":[47],"control":[50],"seamlessly.":[51],"second":[53],"overcoming":[55],"sparse":[56],"rewards":[57],"RL,":[60],"which":[61],"impedes":[62],"efficient":[63],"policy":[64],"convergence.":[65],"To":[66],"address":[67],"these":[68],"challenges,":[69],"we":[70],"propose":[71,102],"a":[72],"hierarchical":[73],"RL":[74],"framework.":[75],"A":[76],"high-level":[77],"policy,":[78],"informed":[79],"by":[80],"proprioceptive":[81],"data":[82],"position,":[85],"adaptively":[86],"switches":[87],"pre-trained":[89],"low-level":[90],"skills":[91,112],"such":[92],"as":[93],"dribbling":[95],"rough":[97],"navigation.":[99],"We":[100],"further":[101],"Dynamic":[103],"Skill-Focused":[104],"Policy":[105],"Optimization":[106],"suppress":[108],"gradients":[109],"from":[110],"inactive":[111],"enhance":[114],"critical":[115],"skill":[116],"learning.":[117],"Both":[118],"simulation":[119],"realworld":[121],"experiments":[122],"validate":[123],"that":[124],"our":[125],"method":[126],"outperforms":[127],"baseline":[128],"approaches":[129],"across":[134],"terrains,":[136],"highlighting":[137],"its":[138],"effectiveness":[139],"challenging":[141],"environments.":[142]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-04-14T00:00:00"}