{"id":"https://openalex.org/W4405785366","doi":"https://doi.org/10.1109/iros58592.2024.10802681","title":"Waypoint-Based Reinforcement Learning for Robot Manipulation Tasks","display_name":"Waypoint-Based Reinforcement Learning for Robot Manipulation Tasks","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785366","doi":"https://doi.org/10.1109/iros58592.2024.10802681"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5014071264","display_name":"Shaunak A. Mehta","orcid":"https://orcid.org/0000-0002-3160-6879"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaunak A. Mehta","raw_affiliation_strings":["Virginia Tech,Collaborative Robotics Lab (Collab),Dept. of Mechanical Engineering,Blacksburg,VA,24061"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech,Collaborative Robotics Lab (Collab),Dept. of Mechanical Engineering,Blacksburg,VA,24061","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071429330","display_name":"Soheil Habibian","orcid":"https://orcid.org/0000-0003-4103-4664"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soheil Habibian","raw_affiliation_strings":["Virginia Tech,Collaborative Robotics Lab (Collab),Dept. of Mechanical Engineering,Blacksburg,VA,24061"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech,Collaborative Robotics Lab (Collab),Dept. of Mechanical Engineering,Blacksburg,VA,24061","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063608480","display_name":"Dylan P. Losey","orcid":"https://orcid.org/0000-0002-8787-5293"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dylan P. Losey","raw_affiliation_strings":["Virginia Tech,Collaborative Robotics Lab (Collab),Dept. of Mechanical Engineering,Blacksburg,VA,24061"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech,Collaborative Robotics Lab (Collab),Dept. of Mechanical Engineering,Blacksburg,VA,24061","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":2.3485,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91069345,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"541","last_page":"548"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9667999744415283,"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":0.9667999744415283,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9247999787330627,"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/waypoint","display_name":"Waypoint","score":0.9107380509376526},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7184423804283142},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6893750429153442},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5656718015670776},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.48809942603111267},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4517485499382019},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4364296793937683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.377103328704834},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3603406548500061},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14640897512435913},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.10931959748268127},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05112224817276001}],"concepts":[{"id":"https://openalex.org/C2781271823","wikidata":"https://www.wikidata.org/wiki/Q138081","display_name":"Waypoint","level":2,"score":0.9107380509376526},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7184423804283142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6893750429153442},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5656718015670776},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.48809942603111267},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4517485499382019},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4364296793937683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.377103328704834},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3603406548500061},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14640897512435913},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.10931959748268127},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05112224817276001}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":26,"referenced_works":["https://openalex.org/W187005120","https://openalex.org/W2109910161","https://openalex.org/W2732475570","https://openalex.org/W2950929549","https://openalex.org/W2963007936","https://openalex.org/W2964227312","https://openalex.org/W3128894241","https://openalex.org/W3133533407","https://openalex.org/W3146696145","https://openalex.org/W3204657926","https://openalex.org/W3206530605","https://openalex.org/W4362672763","https://openalex.org/W6720331669","https://openalex.org/W6726187413","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6752089545","https://openalex.org/W6764173040","https://openalex.org/W6780571964","https://openalex.org/W6782766965","https://openalex.org/W6784521679","https://openalex.org/W6784748513","https://openalex.org/W6788646031","https://openalex.org/W6810887335","https://openalex.org/W6854348952","https://openalex.org/W6854474332"],"related_works":["https://openalex.org/W2688471429","https://openalex.org/W4360939124","https://openalex.org/W2077345734","https://openalex.org/W2899287767","https://openalex.org/W2275928629","https://openalex.org/W4387126713","https://openalex.org/W2624524574","https://openalex.org/W3032985159","https://openalex.org/W2122871747","https://openalex.org/W3114279067"],"abstract_inverted_index":{"Robot":[0],"arms":[1],"should":[2],"be":[3,104],"able":[4],"to":[5,33,39,60,77,82,100,176,190],"learn":[6,52],"new":[7,232],"tasks.":[8],"One":[9],"framework":[10],"here":[11],"is":[12,18,161],"reinforcement":[13,40,133],"learning,":[14],"where":[15],"the":[16,25,28,62,73,83,87,93,141,180,210],"robot":[17,29,74,142],"given":[19],"a":[20,47,53,56,89,108,120,128,138,145,167,216],"reward":[21],"function":[22],"that":[23,72,96,186,208,227],"encodes":[24],"task,":[26],"and":[27,51,149,222],"autonomously":[30],"learns":[31,144,231],"actions":[32,71],"maximize":[34],"its":[35],"reward.":[36],"Existing":[37],"approaches":[38],"learning":[41,137],"often":[42,103],"frame":[43],"this":[44,123,163,191,228],"problem":[45,174],"as":[46,166],"Markov":[48],"decision":[49],"process,":[50],"policy":[54],"(or":[55],"hierarchy":[57],"of":[58,69,111,136,147,169],"policies)":[59],"complete":[61],"task.":[63],"These":[64],"policies":[65],"reason":[66],"over":[67],"hundreds":[68],"fine-grained":[70],"arm":[75],"needs":[76],"take:":[78],"e.g.,":[79,114],"moving":[80],"slightly":[81],"right":[84],"or":[85,118],"rotating":[86],"end-effector":[88],"few":[90],"degrees.":[91],"But":[92],"manipulation":[94],"tasks":[95,233],"we":[97,125],"want":[98],"robots":[99],"perform":[101],"can":[102],"broken":[105],"down":[106],"into":[107],"small":[109],"number":[110],"high-level":[112],"motions:":[113],"reaching":[115],"an":[116,187,203],"object":[117],"turning":[119],"handle.":[121],"In":[122],"paper":[124],"therefore":[126],"propose":[127],"waypoint-based":[129,164],"approach":[130,230],"for":[131],"model-free":[132],"learning.":[134],"Instead":[135],"low-level":[139],"policy,":[140],"now":[143],"trajectory":[146],"waypoints,":[148],"then":[150],"interpolates":[151],"between":[152],"those":[153],"waypoints":[154],"using":[155],"existing":[156],"controllers.":[157],"Our":[158],"key":[159],"novelty":[160],"framing":[162],"setting":[165],"sequence":[168],"multi-armed":[170],"bandits:":[171],"each":[172],"bandit":[173],"corresponds":[175],"one":[177,213],"waypoint":[178,214],"along":[179],"robot\u2019s":[181,211],"motion.":[182],"We":[183,200],"theoretically":[184],"show":[185],"ideal":[188],"solution":[189,207],"reformulation":[192],"has":[193],"lower":[194],"regret":[195],"bounds":[196],"than":[197,236],"standard":[198],"frameworks.":[199],"also":[201],"introduce":[202],"approximate":[204],"posterior":[205],"sampling":[206],"builds":[209],"motion":[212],"at":[215],"time.":[217],"Results":[218],"across":[219],"benchmark":[220],"simulations":[221],"two":[223],"real-world":[224],"experiments":[225],"suggest":[226],"proposed":[229],"more":[234],"quickly":[235],"state-of-the-art":[237],"baselines.":[238],"See":[239],"our":[240],"website":[241],"here:":[242],"https://collab.me.vt.edu/rl-waypoints/":[243]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}