{"id":"https://openalex.org/W4283694278","doi":"https://doi.org/10.1109/ismr48347.2022.9807609","title":"AMBF-RL: A real-time simulation based Reinforcement Learning toolkit for Medical Robotics","display_name":"AMBF-RL: A real-time simulation based Reinforcement Learning toolkit for Medical Robotics","publication_year":2022,"publication_date":"2022-04-13","ids":{"openalex":"https://openalex.org/W4283694278","doi":"https://doi.org/10.1109/ismr48347.2022.9807609"},"language":"en","primary_location":{"id":"doi:10.1109/ismr48347.2022.9807609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ismr48347.2022.9807609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Symposium on Medical Robotics (ISMR)","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/A5037165457","display_name":"Vignesh Manoj Varier","orcid":null},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vignesh Manoj Varier","raw_affiliation_strings":["Worcester Polytechnic Institute, WPI, 100 Institute Road,Robotics Engineering Department,MA,USA,01609"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, WPI, 100 Institute Road,Robotics Engineering Department,MA,USA,01609","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081829323","display_name":"Dhruv Kool Rajamani","orcid":null},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruv Kool Rajamani","raw_affiliation_strings":["Worcester Polytechnic Institute, WPI, 100 Institute Road,Robotics Engineering Department,MA,USA,01609"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, WPI, 100 Institute Road,Robotics Engineering Department,MA,USA,01609","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002628893","display_name":"Farid Tavakkolmoghaddam","orcid":"https://orcid.org/0000-0001-6703-7260"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farid Tavakkolmoghaddam","raw_affiliation_strings":["Worcester Polytechnic Institute, WPI, 100 Institute Road,Robotics Engineering Department,MA,USA,01609"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, WPI, 100 Institute Road,Robotics Engineering Department,MA,USA,01609","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036968620","display_name":"Adnan Munawar","orcid":"https://orcid.org/0000-0002-3400-4558"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adnan Munawar","raw_affiliation_strings":["Johns Hopkins University,Laboratory for Computational Sensing and Robotics,Baltimore,Maryland,USA,21218"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Laboratory for Computational Sensing and Robotics,Baltimore,Maryland,USA,21218","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057001205","display_name":"Gregory S. Fischer","orcid":"https://orcid.org/0000-0001-6723-6614"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory S Fischer","raw_affiliation_strings":["Worcester Polytechnic Institute, WPI, 100 Institute Road,Robotics Engineering Department,MA,USA,01609"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, WPI, 100 Institute Road,Robotics Engineering Department,MA,USA,01609","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037165457"],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":2.082,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88736498,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9939000010490417,"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":0.9939000010490417,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9580000042915344,"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"}},{"id":"https://openalex.org/T10933","display_name":"Real-Time Systems Scheduling","score":0.942799985408783,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8416818380355835},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.795306384563446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7639293670654297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7366505861282349},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6526408195495605},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6335218548774719},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.6169806718826294},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5553021430969238},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4488900601863861},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4042871594429016},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.32284826040267944},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3212538957595825},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3209250271320343},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.14326491951942444},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11222255229949951}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8416818380355835},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.795306384563446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7639293670654297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7366505861282349},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6526408195495605},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6335218548774719},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.6169806718826294},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5553021430969238},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4488900601863861},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4042871594429016},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.32284826040267944},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3212538957595825},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3209250271320343},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.14326491951942444},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11222255229949951},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ismr48347.2022.9807609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ismr48347.2022.9807609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Symposium on Medical Robotics (ISMR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320317074","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W1996863251","https://openalex.org/W2061417916","https://openalex.org/W2081725020","https://openalex.org/W2088392499","https://openalex.org/W2613958746","https://openalex.org/W2623491082","https://openalex.org/W2735048916","https://openalex.org/W2736750746","https://openalex.org/W2767050701","https://openalex.org/W2771434468","https://openalex.org/W2784465508","https://openalex.org/W2785542505","https://openalex.org/W2787938642","https://openalex.org/W2888546857","https://openalex.org/W2901136733","https://openalex.org/W2910913210","https://openalex.org/W2911024029","https://openalex.org/W2920854799","https://openalex.org/W2921119768","https://openalex.org/W2923090615","https://openalex.org/W2962899390","https://openalex.org/W2963099939","https://openalex.org/W2963277051","https://openalex.org/W2963864421","https://openalex.org/W2964174623","https://openalex.org/W2982887926","https://openalex.org/W2985533531","https://openalex.org/W2989598077","https://openalex.org/W3004322459","https://openalex.org/W3089594962","https://openalex.org/W3089664991","https://openalex.org/W3094103188","https://openalex.org/W3100789280","https://openalex.org/W3101442004","https://openalex.org/W3103266692","https://openalex.org/W3196757288","https://openalex.org/W4206833234","https://openalex.org/W4300799055","https://openalex.org/W6638134809","https://openalex.org/W6649416506","https://openalex.org/W6684921986","https://openalex.org/W6718092244","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6740578593","https://openalex.org/W6740801417","https://openalex.org/W6747790125","https://openalex.org/W6748398410","https://openalex.org/W6748839928","https://openalex.org/W6756486208","https://openalex.org/W6760114309","https://openalex.org/W6760425463","https://openalex.org/W6770246895","https://openalex.org/W6770407973","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W3140454661","https://openalex.org/W4245029315","https://openalex.org/W1492315459","https://openalex.org/W1512434910","https://openalex.org/W2540910169","https://openalex.org/W3148904318","https://openalex.org/W2139970489","https://openalex.org/W2022803902","https://openalex.org/W2105474389"],"abstract_inverted_index":{"Recently,":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"techniques":[4],"have":[5],"seen":[6],"significant":[7],"progress":[8],"in":[9,72,115],"the":[10,47,99,105,119,143,155,162],"robotics":[11,60],"domain.":[12],"This":[13],"can":[14],"be":[15],"attributed":[16],"to":[17,25,40,70,84,96],"robust":[18],"simulation":[19,116],"frameworks":[20],"that":[21,37],"offer":[22,35],"realistic":[23],"environments":[24,36],"train.":[26],"However,":[27],"there":[28],"is":[29],"a":[30,53,82,152],"lack":[31],"of":[32,101,161],"platforms":[33],"which":[34],"are":[38,139],"conducive":[39],"medical":[41,59],"robotic":[42],"tasks.":[43],"Having":[44],"earlier":[45],"designed":[46],"Asynchronous":[48],"Multibody":[49],"Framework":[50],"(AMBF)":[51],"-":[52],"real-time":[54],"dynamics":[55],"simulator":[56],"well-suited":[57],"for":[58,76],"tasks,":[61],"we":[62,150],"propose":[63],"an":[64],"open":[65],"source":[66],"AMBF-RL":[67],"(ARL)":[68],"toolkit":[69],"assist":[71],"designing":[73],"control":[74],"algorithms":[75],"these":[77],"robots,":[78],"as":[79,81],"well":[80],"module":[83],"collect":[85],"and":[86,129,147,157],"parse":[87],"expert":[88],"demonstration":[89],"data.":[90],"We":[91],"validate":[92],"ARL":[93],"by":[94,117],"attempting":[95],"partially":[97],"automate":[98],"task":[100],"debris":[102],"removal":[103],"on":[104],"da":[106],"Vinci":[107],"Research":[108],"Kit":[109],"(dVRK)":[110],"Patient":[111],"Side":[112],"Manipulator":[113],"(PSM)":[114],"calculating":[118],"optimal":[120],"policy":[121],"using":[122],"both":[123],"Deep":[124],"Deterministic":[125],"Policy":[126],"Gradient":[127],"(DDPG)":[128],"Hindsight":[130],"Experience":[131],"Replay":[132],"(HER)":[133],"with":[134],"DDPG.":[135],"The":[136],"trained":[137],"policies":[138],"successfully":[140],"transferred":[141],"onto":[142],"physical":[144],"dVRK":[145],"PSM":[146],"tested.":[148],"Finally,":[149],"draw":[151],"conclusion":[153],"from":[154],"results":[156],"discuss":[158],"our":[159],"observations":[160],"experiments":[163],"conducted.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-14T08:36:36.166977","created_date":"2025-10-10T00:00:00"}