{"id":"https://openalex.org/W4403129459","doi":"https://doi.org/10.1177/02783649241284653","title":"SAM-RL: Sensing-aware model-based reinforcement learning via differentiable physics-based simulation and rendering","display_name":"SAM-RL: Sensing-aware model-based reinforcement learning via differentiable physics-based simulation and rendering","publication_year":2024,"publication_date":"2024-10-03","ids":{"openalex":"https://openalex.org/W4403129459","doi":"https://doi.org/10.1177/02783649241284653"},"language":"en","primary_location":{"id":"doi:10.1177/02783649241284653","is_oa":false,"landing_page_url":"https://doi.org/10.1177/02783649241284653","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","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/A5100308848","display_name":"Jun Lv","orcid":"https://orcid.org/0000-0003-4328-0420"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Lv","raw_affiliation_strings":["Shanghai Jiao Tong University","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4328-0420","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100934095","display_name":"Yunhai Feng","orcid":"https://orcid.org/0009-0006-3041-9816"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunhai Feng","raw_affiliation_strings":["University of California San Diego","University of California San Diego, La Jolla, CA, USA"],"raw_orcid":"https://orcid.org/0009-0006-3041-9816","affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"University of California San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047670873","display_name":"Cheng Zhang","orcid":"https://orcid.org/0000-0002-4790-9188"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng Zhang","raw_affiliation_strings":["University of Irvine","University of Irvine, Irvine, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Irvine","institution_ids":[]},{"raw_affiliation_string":"University of Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031061480","display_name":"Shuang Zhao","orcid":"https://orcid.org/0000-0001-7081-6177"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuang Zhao","raw_affiliation_strings":["University of Irvine","University of Irvine, Irvine, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Irvine","institution_ids":[]},{"raw_affiliation_string":"University of Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100566831","display_name":"Lin Shao","orcid":"https://orcid.org/0000-0002-3412-5755"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lin Shao","raw_affiliation_strings":["National University of Singapore","National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-3412-5755","affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010726528","display_name":"Cewu Lu","orcid":"https://orcid.org/0000-0002-4023-9257"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cewu Lu","raw_affiliation_strings":["Shanghai Jiao Tong University","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010726528"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.5557,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72265532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"44","issue":"10-11","first_page":"1767","last_page":"1783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11195","display_name":"Simulation Techniques and Applications","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7668644189834595},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.7551059722900391},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.6577438712120056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5244134664535522},{"id":"https://openalex.org/keywords/dynamical-simulation","display_name":"Dynamical simulation","score":0.4993605613708496},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4381347894668579},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40153059363365173},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.212362140417099},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20261046290397644},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15075504779815674},{"id":"https://openalex.org/keywords/classical-mechanics","display_name":"Classical mechanics","score":0.11382186412811279},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.08392304182052612},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.07869145274162292}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7668644189834595},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7551059722900391},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6577438712120056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5244134664535522},{"id":"https://openalex.org/C81587630","wikidata":"https://www.wikidata.org/wiki/Q5319044","display_name":"Dynamical simulation","level":2,"score":0.4993605613708496},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4381347894668579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40153059363365173},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.212362140417099},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20261046290397644},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15075504779815674},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.11382186412811279},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08392304182052612},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.07869145274162292}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/02783649241284653","is_oa":false,"landing_page_url":"https://doi.org/10.1177/02783649241284653","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5465080215","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G7968867161","display_name":null,"funder_award_id":"21511101200","funder_id":"https://openalex.org/F4320336652","funder_display_name":"Science and Technology Innovation Plan Of Shanghai Science and Technology Commission"},{"id":"https://openalex.org/G88417457","display_name":null,"funder_award_id":"2021ZD0110700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336652","display_name":"Science and Technology Innovation Plan Of Shanghai Science and Technology Commission","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1979709633","https://openalex.org/W2055647814","https://openalex.org/W2071888022","https://openalex.org/W2093550895","https://openalex.org/W2099940712","https://openalex.org/W2101024363","https://openalex.org/W2145339207","https://openalex.org/W2146405081","https://openalex.org/W2155370467","https://openalex.org/W2167061621","https://openalex.org/W2205727652","https://openalex.org/W2257979135","https://openalex.org/W2292964075","https://openalex.org/W2409009991","https://openalex.org/W2560722161","https://openalex.org/W2902812770","https://openalex.org/W2938807566","https://openalex.org/W2953708620","https://openalex.org/W2963150697","https://openalex.org/W2964333597","https://openalex.org/W2968095426","https://openalex.org/W2968268581","https://openalex.org/W2990138404","https://openalex.org/W2990173985","https://openalex.org/W2995298643","https://openalex.org/W3037265641","https://openalex.org/W3038570409","https://openalex.org/W3048916779","https://openalex.org/W3049755554","https://openalex.org/W3091444023","https://openalex.org/W3106721722","https://openalex.org/W3122690883","https://openalex.org/W3128000279","https://openalex.org/W3128478003","https://openalex.org/W3168575721","https://openalex.org/W3173446233","https://openalex.org/W3205139037","https://openalex.org/W3206194865","https://openalex.org/W3214811308","https://openalex.org/W3216834690","https://openalex.org/W4224903718","https://openalex.org/W4283311220","https://openalex.org/W4285102395","https://openalex.org/W4289115845","https://openalex.org/W4312891659"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4327738859","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2348722996"],"abstract_inverted_index":{"Model-based":[0],"reinforcement":[1,16,52,66],"learning":[2,53,67,99],"is":[3,41],"recognized":[4],"with":[5,87],"the":[6,47,55,72,81,93,97,112,138],"potential":[7],"to":[8,105,110,119],"be":[9,23],"significantly":[10],"more":[11],"sample":[12],"efficient":[13],"than":[14],"model-free":[15],"learning.":[17],"How":[18],"an":[19,107],"accurate":[20],"model":[21,82],"can":[22],"developed":[24],"automatically":[25,79],"and":[26,39,76,91,132],"efficiently":[27],"from":[28],"raw":[29,89],"sensory":[30],"inputs":[31],"(such":[32],"as":[33],"images),":[34],"especially":[35],"for":[36,123],"complex":[37],"environments":[38],"tasks,":[40],"a":[42,63,103],"challenging":[43],"problem":[44],"that":[45],"hinders":[46],"broad":[48],"application":[49],"of":[50,140],"model-based":[51,65],"in":[54],"real":[56,88,120],"world.":[57],"In":[58],"this":[59],"work,":[60],"we":[61],"propose":[62],"sensing-aware":[64,98],"system":[68],"called":[69],"SAM-RL.":[70],"Leveraging":[71],"differentiable":[73],"physics-based":[74],"simulation":[75],"rendering,":[77],"SAM-RL":[78,101,141],"updates":[80],"by":[83],"comparing":[84],"rendered":[85],"images":[86,90],"produces":[92],"policy":[94],"efficiently.":[95],"With":[96],"pipeline,":[100],"allows":[102],"robot":[104],"select":[106],"informative":[108],"viewpoint":[109],"monitor":[111],"task":[113],"process.":[114],"We":[115,136],"apply":[116],"our":[117,149],"framework":[118],"world":[121],"experiments":[122],"accomplishing":[124],"three":[125],"manipulation":[126],"tasks:":[127],"robotic":[128],"assembly,":[129],"tool":[130],"manipulation,":[131],"deformable":[133],"object":[134],"manipulation.":[135],"demonstrate":[137],"effectiveness":[139],"via":[142],"extensive":[143],"experiments.":[144],"Videos":[145],"are":[146],"available":[147],"on":[148],"project":[150],"webpage.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
