{"id":"https://openalex.org/W7223676819","doi":"https://doi.org/10.48550/arxiv.2610.32034","title":"PPO vs. SAC: A Comparative Study for Cooperative Motion Control of Dual-Arm Space Robots","display_name":"PPO vs. SAC: A Comparative Study for Cooperative Motion Control of Dual-Arm Space Robots","publication_year":2026,"publication_date":"2026-10-23","ids":{"openalex":"https://openalex.org/W7223676819","doi":"https://doi.org/10.48550/arxiv.2610.32034"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.32034","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.32034","pdf_url":"https://arxiv.org/pdf/2610.32034","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.32034","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117395127","display_name":"Nasim Fallahiarezoodar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]},{"id":"https://openalex.org/I4210112962","display_name":"York University","ror":"https://ror.org/022jz8688","country_code":"US","type":"education","lineage":["https://openalex.org/I4210112962"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Fallahiarezoodar, Nasim","raw_affiliation_strings":["Department of Earth and Space Science and Engineering , York University , M3J1P3 , Student Member of AIAA \u2020 Professor &"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Earth and Space Science and Engineering , York University , M3J1P3 , Student Member of AIAA \u2020 Professor &","institution_ids":["https://openalex.org/I192455969","https://openalex.org/I4210112962"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159585893","display_name":"Zheng H. Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]},{"id":"https://openalex.org/I4210112962","display_name":"York University","ror":"https://ror.org/022jz8688","country_code":"US","type":"education","lineage":["https://openalex.org/I4210112962"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Zhu, Zheng H.","raw_affiliation_strings":["Department of Earth and Space Science and Engineering , York University , M3J1P3 , Student Member of AIAA \u2020 Professor &"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Earth and Space Science and Engineering , York University , M3J1P3 , Student Member of AIAA \u2020 Professor &","institution_ids":["https://openalex.org/I192455969","https://openalex.org/I4210112962"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8949999809265137,"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":0.8949999809265137,"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/T11701","display_name":"Space Satellite Systems and Control","score":0.10040000081062317,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10653","display_name":"Robot Manipulation and Learning","score":0.0026000000070780516,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cooperative-motion-planning","display_name":"cooperative motion planning","score":0.7639999985694885},{"id":"https://openalex.org/keywords/on-orbit-servicing","display_name":"on-orbit servicing","score":0.8029999732971191},{"id":"https://openalex.org/keywords/active-debris-removal","display_name":"active debris removal","score":0.9869999885559082},{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.8610000014305115},{"id":"https://openalex.org/keywords/soft-actor-critic","display_name":"soft actor-critic","score":0.9990000128746033},{"id":"https://openalex.org/keywords/orientation-alignment","display_name":"orientation alignment","score":0.7059999704360962},{"id":"https://openalex.org/keywords/policy-generalization","display_name":"policy generalization","score":0.5429999828338623}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.642799973487854},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6312000155448914},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6154999732971191},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.5978000164031982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5863000154495239},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5584999918937683},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5529000163078308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5526999831199646},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.54830002784729},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.49079999327659607},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.4740000069141388},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.42649999260902405},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.33059999346733093},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3246000111103058},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2822999954223633},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27379998564720154},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C18949120","wikidata":"https://www.wikidata.org/wiki/Q275450","display_name":"Space debris","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.32034","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.32034","pdf_url":"https://arxiv.org/pdf/2610.32034","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.32034","doi":"https://doi.org/10.48550/arxiv.2610.32034","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.32034","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.32034","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.32034","pdf_url":"https://arxiv.org/pdf/2610.32034","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223676819.pdf","grobid_xml":"https://content.openalex.org/works/W7223676819.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387652939","https://openalex.org/W7204083838","https://openalex.org/W3191709555","https://openalex.org/W7130322989","https://openalex.org/W4405746964","https://openalex.org/W4284879263","https://openalex.org/W7162445183","https://openalex.org/W4408157794","https://openalex.org/W4416788423","https://openalex.org/W7213243320"],"abstract_inverted_index":{"The":[0,208],"growing":[1],"population":[2],"of":[3,59,202,215,243],"orbital":[4],"debris":[5,11],"has":[6],"intensified":[7],"interest":[8],"in":[9,64,153],"active":[10],"removal":[12],"and":[13,25,42,79,97,107,116,119,170,184,187],"on-orbit":[14],"servicing,":[15],"for":[16,55,126],"which":[17],"dual-arm":[18,61],"space":[19,62],"manipulators":[20,35],"offer":[21],"improved":[22],"grasping":[23],"stability":[24],"load":[26],"distribution":[27],"relative":[28],"to":[29,128,224,226,234,246],"single-arm":[30],"systems.":[31],"However,":[32],"coordinating":[33],"two":[34],"under":[36,217],"inter-arm":[37,69],"collision":[38,98],"avoidance,":[39],"orientation":[40,90,185],"alignment,":[41,91],"sensing":[43],"uncertainty":[44],"remains":[45],"challenging.":[46],"This":[47,238],"paper":[48],"develops":[49],"a":[50,60,65,83,167,173,212,227],"coordinated":[51],"reinforcement":[52],"learning":[53,245],"framework":[54],"cooperative":[56],"motion":[57,92],"planning":[58],"manipulator":[63],"target-reaching":[66,88],"task":[67,95],"with":[68,181],"collision-avoidance":[70],"constraints.":[71],"A":[72],"centralized":[73],"state":[74],"representation":[75],"combines":[76],"joint-space,":[77],"end-effector,":[78],"target-relative":[80],"information,":[81],"while":[82,205],"multi-objective":[84],"reward":[85,247],"function":[86],"promotes":[87],"accuracy,":[89],"smoothness,":[93],"synchronized":[94],"completion,":[96],"avoidance.":[99],"Within":[100],"this":[101],"framework,":[102],"Proximal":[103],"Policy":[104],"Optimization":[105],"(PPO)":[106],"Soft":[108],"Actor-Critic":[109],"(SAC)":[110],"are":[111,123],"compared":[112],"as":[113],"representative":[114],"on-policy":[115,244],"off-policy":[117],"algorithms,":[118],"the":[120,142,218,235,241],"learned":[121],"policies":[122],"further":[124],"evaluated":[125],"generalization":[127],"previously":[129],"unseen":[130,195],"target":[131],"configurations.":[132],"Across":[133],"five":[134],"random":[135],"seeds,":[136],"SAC":[137,199],"substantially":[138],"outperforms":[139],"PPO":[140,161],"within":[141,166],"considered":[143],"fixed-base":[144],"simulation":[145],"scenarios:":[146],"it":[147,165,171,222],"reaches":[148],"an":[149],"80%":[150],"success":[151,176],"threshold":[152],"every":[154],"seed":[155],"(median":[156],"1.6M":[157],"environment":[158],"steps)":[159],"whereas":[160],"does":[162],"not":[163],"reach":[164],"4M-step":[168],"budget,":[169],"attains":[172],"higher":[174],"mean":[175],"rate":[177],"(78.6%":[178],"versus":[179],"7.4%)":[180],"lower":[182],"position":[183],"errors":[186],"tighter":[188],"bimanual":[189],"synchronization.":[190],"Both":[191],"algorithms":[192],"degrade":[193],"on":[194],"boundary":[196],"targets,":[197],"but":[198],"retains":[200],"most":[201],"its":[203],"performance":[204],"PPO's":[206],"collapses.":[207],"results":[209],"also":[210],"expose":[211],"failure":[213],"mode":[214],"PPO:":[216],"two-phase":[219],"shaped":[220],"reward,":[221],"tends":[223],"converge":[225],"reward-loitering":[228],"local":[229],"optimum":[230],"rather":[231],"than":[232],"committing":[233],"precision":[236],"task.":[237],"behavior":[239],"highlights":[240],"sensitivity":[242],"shaping.":[248]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-10-27T00:00:00"}