{"id":"https://openalex.org/W4413917587","doi":"https://doi.org/10.1109/icra55743.2025.11128428","title":"SARO: Space-Aware Robot System for Terrain Crossing via Vision-Language Model","display_name":"SARO: Space-Aware Robot System for Terrain Crossing via Vision-Language Model","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917587","doi":"https://doi.org/10.1109/icra55743.2025.11128428"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5040608113","display_name":"Shaoting Zhu","orcid":"https://orcid.org/0009-0000-9294-6212"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoting Zhu","raw_affiliation_strings":["Tsinghua University,IIIS,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,IIIS,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102738329","display_name":"Derun Li","orcid":"https://orcid.org/0000-0003-0512-6684"},"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":"Derun Li","raw_affiliation_strings":["Shanghai Jiao Tong University,SEIEE,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,SEIEE,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031959594","display_name":"Linzhan Mou","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]},{"id":"https://openalex.org/I922845939","display_name":"Philadelphia University","ror":"https://ror.org/03zzmyz63","country_code":"US","type":"education","lineage":["https://openalex.org/I922845939"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linzhan Mou","raw_affiliation_strings":["University of Pennsylvania,GRASP Lab,Philadelphia,PA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,GRASP Lab,Philadelphia,PA,USA","institution_ids":["https://openalex.org/I79576946","https://openalex.org/I922845939"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100988742","display_name":"Yong Liu","orcid":"https://orcid.org/0009-0000-8133-5686"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Zhejiang University,CSE,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,CSE,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100833305","display_name":"Ningyi Xu","orcid":null},"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":"Ningyi Xu","raw_affiliation_strings":["Shanghai Jiao Tong University,SEIEE,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,SEIEE,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418988","display_name":"Hang Zhao","orcid":"https://orcid.org/0009-0008-7252-3827"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Zhao","raw_affiliation_strings":["Tsinghua University,IIIS,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,IIIS,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14820","last_page":"14827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9666000008583069,"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"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9666000008583069,"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/terrain","display_name":"Terrain","score":0.8048821687698364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7577933073043823},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6692485213279724},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6332868933677673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6126562356948853},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.49359428882598877},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.4536905884742737},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4501703083515167},{"id":"https://openalex.org/keywords/raised-relief-map","display_name":"Raised-relief map","score":0.43609195947647095},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.104339599609375},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06588423252105713}],"concepts":[{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.8048821687698364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577933073043823},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6692485213279724},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6332868933677673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6126562356948853},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.49359428882598877},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.4536905884742737},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4501703083515167},{"id":"https://openalex.org/C99695388","wikidata":"https://www.wikidata.org/wiki/Q350514","display_name":"Raised-relief map","level":3,"score":0.43609195947647095},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.104339599609375},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06588423252105713},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2149606028","https://openalex.org/W2150317946","https://openalex.org/W2156355884","https://openalex.org/W2909331752","https://openalex.org/W2909553221","https://openalex.org/W2911087563","https://openalex.org/W3093922502","https://openalex.org/W3142410314","https://openalex.org/W3175254947","https://openalex.org/W3203184215","https://openalex.org/W4205430897","https://openalex.org/W4226143977","https://openalex.org/W4362722144","https://openalex.org/W4378696928","https://openalex.org/W4382365373","https://openalex.org/W4383097638","https://openalex.org/W4383108274","https://openalex.org/W4383108457","https://openalex.org/W4383108895","https://openalex.org/W4385245566","https://openalex.org/W4386083015","https://openalex.org/W4390494915","https://openalex.org/W4392646028","https://openalex.org/W4401415110","https://openalex.org/W4401417061","https://openalex.org/W4402449733","https://openalex.org/W4402727730","https://openalex.org/W4405786295","https://openalex.org/W4405786528"],"related_works":["https://openalex.org/W3213331859","https://openalex.org/W4226458444","https://openalex.org/W4390637946","https://openalex.org/W2113164274","https://openalex.org/W2132444301","https://openalex.org/W2378911484","https://openalex.org/W2122871747","https://openalex.org/W2466038652","https://openalex.org/W3114279067","https://openalex.org/W2348432434"],"abstract_inverted_index":{"The":[0],"application":[1],"of":[2,45,87,93],"vision-language":[3],"models":[4,21],"(VLMs)":[5],"has":[6],"achieved":[7],"impressive":[8],"success":[9],"in":[10,23,29,146,160],"various":[11],"robotics":[12],"tasks.":[13],"However,":[14],"there":[15],"are":[16],"few":[17],"explorations":[18],"for":[19,38],"foundation":[20],"used":[22],"quadruped":[24],"robot":[25,63],"navigation":[26],"through":[27],"terrains":[28,68],"3D":[30,67,137],"environments.":[31],"We":[32],"introduce":[33],"SARO":[34],"(Space-Aware":[35],"Robot":[36],"System":[37],"Terrain":[39],"Crossing),":[40],"an":[41],"innovative":[42],"system":[43,84,129],"composed":[44],"a":[46,50,56,81,88,91,97,117],"high-level":[47,75],"reasoning":[48,76],"module,":[49,54],"closed-loop":[51,98],"sub-task":[52,99],"execution":[53,100],"and":[55,69,77,96,132,139,149,152,155],"low-level":[57,103],"control":[58,118],"policy.":[59],"It":[60],"enables":[61],"the":[62,71,108,144],"to":[64,114],"navigate":[65,134],"across":[66,135],"reach":[70],"goal":[72],"position.":[73],"For":[74,102],"execution,":[78],"we":[79,106],"propose":[80],"novel":[82],"algorithmic":[83],"taking":[85],"advantage":[86],"VLM,":[89],"with":[90],"design":[92],"task":[94],"decomposition":[95],"mechanism.":[101],"locomotion":[104],"control,":[105],"utilize":[107],"Probability":[109],"Annealing":[110],"Selection":[111],"(PAS)":[112],"method":[113],"effectively":[115],"train":[116],"policy":[119],"by":[120],"reinforcement":[121],"learning.":[122],"Numerous":[123],"experiments":[124],"show":[125],"that":[126],"our":[127],"whole":[128],"can":[130,157],"accurately":[131],"robustly":[133],"several":[136],"terrains,":[138],"its":[140],"generalization":[141],"ability":[142],"ensures":[143],"applications":[145],"diverse":[147],"indoor":[148],"outdoor":[150],"scenarios":[151],"terrains.":[153],"Appendix":[154],"Videos":[156],"be":[158],"found":[159],"project":[161],"page:":[162],"https://saro-vlm.github.io/.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}