{"id":"https://openalex.org/W4417099698","doi":"https://doi.org/10.48550/arxiv.2508.01539","title":"HALO: Human Preference Aligned Offline Reward Learning for Robot Navigation","display_name":"HALO: Human Preference Aligned Offline Reward Learning for Robot Navigation","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4417099698","doi":"https://doi.org/10.48550/arxiv.2508.01539"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.01539","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01539","pdf_url":"https://arxiv.org/pdf/2508.01539","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.01539","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108716741","display_name":"Gershom Seneviratne","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seneviratne, Gershom","raw_affiliation_strings":["University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":null,"display_name":"An, Jianyu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"An, Jianyu","raw_affiliation_strings":["University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120717808","display_name":"Sahire Ellahy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ellahy, Sahire","raw_affiliation_strings":["University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080472165","display_name":"Kasun Weerakoon","orcid":"https://orcid.org/0000-0002-6526-8652","observed_orcids":["https://orcid.org/0000-0002-6526-8652"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weerakoon, Kasun","raw_affiliation_strings":["University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092506235","display_name":"Mohamed Elnoor","orcid":"https://orcid.org/0009-0000-2326-6184","observed_orcids":["https://orcid.org/0009-0000-2326-6184"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elnoor, Mohamed Bashir","raw_affiliation_strings":["University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120697547","display_name":"Jonathan Deepak Kannan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kannan, Jonathan Deepak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109793073","display_name":"Amogha Thalihalla Sunil","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunil, Amogha Thalihalla","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801","observed_orcids":["https://orcid.org/0000-0001-7047-9801"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manocha, Dinesh","raw_affiliation_strings":["University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"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":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/human-preference-alignment","display_name":"human preference alignment","score":0.7269999980926514},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.972000002861023},{"id":"https://openalex.org/keywords/visual-navigation","display_name":"visual navigation","score":0.9559999704360962},{"id":"https://openalex.org/keywords/expert-trajectories","display_name":"expert trajectories","score":0.5090000033378601},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"model predictive control","score":0.7760000228881836},{"id":"https://openalex.org/keywords/generalization-to-unseen-environments","display_name":"generalization to unseen environments","score":0.7110000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6948999762535095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6330999732017517},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.5227000117301941},{"id":"https://openalex.org/C184665706","wikidata":"https://www.wikidata.org/wiki/Q186310","display_name":"Halo","level":3,"score":0.5045999884605408},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4514999985694885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4440000057220459},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3249000012874603},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.2858000099658966},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.2687999904155731},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.2515999972820282},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2508.01539","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01539","pdf_url":"https://arxiv.org/pdf/2508.01539","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.01539","doi":"https://doi.org/10.48550/arxiv.2508.01539","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.01539","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.01539","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01539","pdf_url":"https://arxiv.org/pdf/2508.01539","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/W4417099698.pdf","grobid_xml":"https://content.openalex.org/works/W4417099698.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W3016404858","https://openalex.org/W3022566517","https://openalex.org/W3089356304","https://openalex.org/W3167658443","https://openalex.org/W3205794883","https://openalex.org/W4311992093","https://openalex.org/W4382334278","https://openalex.org/W4385571689","https://openalex.org/W4386302222","https://openalex.org/W4393934511","https://openalex.org/W4401415435","https://openalex.org/W4402670989","https://openalex.org/W4405785489","https://openalex.org/W4411155478","https://openalex.org/W4413917771","https://openalex.org/W4413924978","https://openalex.org/W4416749176","https://openalex.org/W4416749536","https://openalex.org/W6966354681"],"related_works":["https://openalex.org/W4311992093","https://openalex.org/W4298112294","https://openalex.org/W4416748544","https://openalex.org/W2407933","https://openalex.org/W7161013377","https://openalex.org/W4310386505","https://openalex.org/W3120831418","https://openalex.org/W4386634158","https://openalex.org/W4312480554","https://openalex.org/W2415177987"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,98],"introduce":[4],"HALO,":[5,97],"a":[6,19,28,48,58,120,152,187,193,201],"novel":[7],"Offline":[8],"Reward":[9],"Learning":[10],"algorithm":[11],"that":[12,125,159],"quantifies":[13],"human":[14,209],"intuition":[15],"in":[16,103,174,190,196,204],"navigation":[17,75,146,182],"into":[18],"vision-based":[20,181],"reward":[21,29,78,101,129],"function":[22],"for":[23],"robot":[24],"navigation.":[25],"HALO":[26,128,140,163,178],"learns":[27],"model":[30,79,102],"from":[31,38,57],"offline":[32,109],"data,":[33],"leveraging":[34],"expert":[35,210],"trajectories":[36],"collected":[37],"mobile":[39],"robots.":[40],"During":[41],"training,":[42],"actions":[43],"are":[44],"uniformly":[45],"sampled":[46],"around":[47],"reference":[49],"action":[50],"and":[51,66,118,144,169,200],"ranked":[52,90],"using":[53],"preference":[54],"scores":[55],"derived":[56],"Boltzmann":[59],"distribution":[60],"centered":[61],"on":[62,69,114,151],"the":[63,83,94,115,127,137,175],"preferred":[64],"action,":[65],"shaped":[67],"based":[68,123],"binary":[70],"user":[71],"feedback":[72],"to":[73,86,166,208],"intuitive":[74],"queries.":[76],"The":[77],"is":[80],"trained":[81,112,161],"via":[82],"Plackett-Luce":[84],"loss":[85],"align":[87],"with":[88,162],"these":[89],"preferences.":[91],"To":[92],"demonstrate":[93,158],"effectiveness":[95],"of":[96,139],"deploy":[99],"its":[100],"two":[104],"downstream":[105],"applications:":[106],"(i)":[107],"an":[108,131],"learned":[110],"policy":[111],"directly":[113],"HALO-derived":[116],"rewards,":[117],"(ii)":[119],"model-predictive-control":[121],"(MPC)":[122],"planner":[124],"incorporates":[126],"as":[130],"additional":[132],"cost":[133],"term.":[134],"This":[135],"showcases":[136],"versatility":[138],"across":[141,155],"both":[142],"learning-based":[143],"classical":[145],"frameworks.":[147],"Our":[148],"real-world":[149],"deployments":[150],"Clearpath":[153],"Husky":[154],"diverse":[156],"scenarios":[157],"policies":[160],"generalize":[164],"effectively":[165],"unseen":[167],"environments":[168],"hardware":[170],"setups":[171],"not":[172],"present":[173],"training":[176],"data.":[177],"outperforms":[179],"state-of-the-art":[180],"methods,":[183],"achieving":[184],"at":[185],"least":[186],"33.3%":[188],"improvement":[189],"success":[191],"rate,":[192],"12.9%":[194],"reduction":[195,203],"normalized":[197],"trajectory":[198],"length,":[199],"26.6%":[202],"Frechet":[205],"distance":[206],"compared":[207],"trajectories.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":6}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-10T00:00:00"}