{"id":"https://openalex.org/W4413917765","doi":"https://doi.org/10.1109/icra55743.2025.11128042","title":"Vision Transformers for End-to-End Vision-Based Quadrotor Obstacle Avoidance","display_name":"Vision Transformers for End-to-End Vision-Based Quadrotor Obstacle Avoidance","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917765","doi":"https://doi.org/10.1109/icra55743.2025.11128042"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128042","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":"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/A5047097027","display_name":"Anish Bhattacharya","orcid":"https://orcid.org/0000-0002-2752-4416"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anish Bhattacharya","raw_affiliation_strings":["The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110339402","display_name":"N.J. Rao","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nishanth Rao","raw_affiliation_strings":["The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060605073","display_name":"Dhruv Parikh","orcid":"https://orcid.org/0009-0003-9767-2275"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruv Parikh","raw_affiliation_strings":["The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055220072","display_name":"Pratik Kunapuli","orcid":"https://orcid.org/0000-0002-0601-9787"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pratik Kunapuli","raw_affiliation_strings":["The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458048","display_name":"Yuwei Wu","orcid":"https://orcid.org/0000-0003-4926-2530"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuwei Wu","raw_affiliation_strings":["The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060751452","display_name":"Yuezhan Tao","orcid":"https://orcid.org/0000-0002-7448-8411"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuezhan Tao","raw_affiliation_strings":["The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052941508","display_name":"Nikolai Matni","orcid":"https://orcid.org/0000-0003-4936-3921"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolai Matni","raw_affiliation_strings":["The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113696439","display_name":"Vijay Kumar","orcid":"https://orcid.org/0000-0002-3460-6989"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Kumar","raw_affiliation_strings":["The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":4.2246,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.94311746,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9965000152587891,"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"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9846000075340271,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7253099679946899},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6605509519577026},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.6298844218254089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6087430715560913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5717262029647827},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.4523889720439911},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45131823420524597},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.30043724179267883},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.238613098859787},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.1961638331413269},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12832722067832947},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08016940951347351}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7253099679946899},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6605509519577026},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.6298844218254089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6087430715560913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5717262029647827},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.4523889720439911},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45131823420524597},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.30043724179267883},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.238613098859787},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.1961638331413269},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12832722067832947},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08016940951347351},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128042","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":[{"id":"https://openalex.org/G7251536512","display_name":null,"funder_award_id":"SLES-2331880,CAREER2045834","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1578294898","https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2476548250","https://openalex.org/W2788239209","https://openalex.org/W2913365477","https://openalex.org/W2962787639","https://openalex.org/W3017661315","https://openalex.org/W3023767264","https://openalex.org/W3135218110","https://openalex.org/W3138516171","https://openalex.org/W3202883604","https://openalex.org/W3206969010","https://openalex.org/W4200338404","https://openalex.org/W4210247145","https://openalex.org/W4286267382","https://openalex.org/W4319990398","https://openalex.org/W4383066575","https://openalex.org/W4383108733","https://openalex.org/W4383108878","https://openalex.org/W4385245566","https://openalex.org/W4413917765"],"related_works":["https://openalex.org/W2930076404","https://openalex.org/W4253519380","https://openalex.org/W2071957557","https://openalex.org/W2596413128","https://openalex.org/W4391249562","https://openalex.org/W2356867392","https://openalex.org/W2782776446","https://openalex.org/W3043170174","https://openalex.org/W2155948905","https://openalex.org/W2906946336"],"abstract_inverted_index":{"We":[0,89,146],"demonstrate":[1],"the":[2,129,160,167],"capabilities":[3],"of":[4,82,131,151,162],"an":[5],"attentionbased":[6],"end-to-end":[7,70,175],"approach":[8],"for":[9,79,103,174],"high-speed":[10],"vision-based":[11,176],"quadrotor":[12,119,138,177],"obstacle":[13],"avoidance":[14],"in":[15,106,123,155],"dense,":[16],"cluttered":[17,87],"environments,":[18,127],"with":[19],"comparison":[20],"to":[21,45,58,75,125,153,170],"various":[22],"state-of-the-art":[23],"learning":[24],"architectures.":[25],"Quadrotor":[26],"unmanned":[27],"aerial":[28],"vehicles":[29],"(UAVs)":[30],"have":[31,73,76],"tremendous":[32],"maneuverability":[33],"when":[34],"flown":[35],"fast;":[36],"however,":[37],"as":[38,118],"flight":[39,144],"speed":[40],"increases,":[41],"traditional":[42],"model-based":[43],"approaches":[44],"navigation":[46],"via":[47],"independent":[48],"perception,":[49],"mapping,":[50],"planning,":[51],"and":[52,64,91,95,122,157],"control":[53,81],"modules":[54],"breaks":[55],"down":[56],"due":[57],"increased":[59,65],"sensor":[60],"noise,":[61],"compounding":[62],"errors,":[63],"processing":[66],"latency.":[67],"Thus,":[68],"learning-based,":[69],"vision-to-control":[71],"networks":[72],"shown":[74],"great":[77],"potential":[78],"online":[80],"these":[83],"fast":[84],"robots":[85],"through":[86],"environments.":[88],"train":[90],"compare":[92],"convolutional,":[93],"U-Net,":[94],"recurrent":[96],"architectures":[97],"against":[98],"vision":[99,172],"transformer":[100],"(ViT)":[101],"models":[102,112],"depth":[104],"image-to-control":[105],"high-fidelity":[107],"simulation,":[108],"observing":[109],"that":[110],"ViT":[111],"are":[113],"more":[114],"effective":[115],"than":[116],"others":[117],"speeds":[120,150],"increase":[121],"generalization":[124],"unseen":[126],"while":[128,136],"addition":[130],"recurrence":[132],"further":[133],"improves":[134],"performance":[135,148],"reducing":[137],"energy":[139],"cost":[140],"across":[141],"all":[142],"tested":[143],"speeds.":[145],"assess":[147],"at":[149],"up":[152],"7m/s":[154],"simulation":[156],"hardware.":[158],"To":[159],"best":[161],"our":[163],"knowledge,":[164],"this":[165],"is":[166],"first":[168],"work":[169],"utilize":[171],"transformers":[173],"control.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}