{"id":"https://openalex.org/W2765395072","doi":"https://doi.org/10.1145/3132734.3132737","title":"Learning End-to-End Autonomous Steering Model from Spatial and Temporal Visual Cues","display_name":"Learning End-to-End Autonomous Steering Model from Spatial and Temporal Visual Cues","publication_year":2017,"publication_date":"2017-10-20","ids":{"openalex":"https://openalex.org/W2765395072","doi":"https://doi.org/10.1145/3132734.3132737","mag":"2765395072"},"language":"en","primary_location":{"id":"doi:10.1145/3132734.3132737","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132734.3132737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Visual Analysis in Smart and Connected Communities","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/A5100543665","display_name":"Lu Chi","orcid":"https://orcid.org/0009-0004-2274-6142"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Chi","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028877572","display_name":"Yadong Mu","orcid":"https://orcid.org/0000-0001-7815-3750"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Mu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998999834060669,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9998000264167786,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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/robustness","display_name":"Robustness (evolution)","score":0.7785297632217407},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7651638388633728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6232478618621826},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5831326246261597},{"id":"https://openalex.org/keywords/stateful-firewall","display_name":"Stateful firewall","score":0.54916912317276},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5251243710517883},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49954748153686523},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4708409309387207},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45450833439826965},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.42708539962768555}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7785297632217407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7651638388633728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6232478618621826},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5831326246261597},{"id":"https://openalex.org/C22927095","wikidata":"https://www.wikidata.org/wiki/Q1784206","display_name":"Stateful firewall","level":3,"score":0.54916912317276},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5251243710517883},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49954748153686523},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4708409309387207},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45450833439826965},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.42708539962768555},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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:10.1145/3132734.3132737","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132734.3132737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Visual Analysis in Smart and Connected Communities","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1485009520","https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W2038794597","https://openalex.org/W2117287331","https://openalex.org/W2119112357","https://openalex.org/W2133233905","https://openalex.org/W2155893237","https://openalex.org/W2167224731","https://openalex.org/W2194775991","https://openalex.org/W2218433086","https://openalex.org/W2342840547","https://openalex.org/W2395611524","https://openalex.org/W2407521645","https://openalex.org/W2550446853","https://openalex.org/W2552465644","https://openalex.org/W2557283755","https://openalex.org/W2559767995","https://openalex.org/W2611430843","https://openalex.org/W2618530766","https://openalex.org/W2950094539"],"related_works":["https://openalex.org/W2541791370","https://openalex.org/W2035976912","https://openalex.org/W3094187672","https://openalex.org/W1999222583","https://openalex.org/W2921707373","https://openalex.org/W2990667865","https://openalex.org/W2891108385","https://openalex.org/W2080322084","https://openalex.org/W1967456564","https://openalex.org/W4312095940"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"autonomous":[3],"driving":[4,83,126,182],"algorithms":[5],"using":[6,53],"low-cost":[7],"vehicle-mounted":[8],"cameras":[9],"have":[10],"attracted":[11],"increasing":[12],"endeavors":[13],"from":[14,94,99],"both":[15],"academia":[16],"and":[17,78,140,149,165,193,205],"industry.":[18],"There":[19],"are":[20,71,86],"multiple":[21],"fronts":[22],"to":[23,50],"these":[24],"endeavors,":[25],"including":[26],"object":[27],"detection":[28],"on":[29,40,80,117,176],"roads,":[30],"3-D":[31],"reconstruction":[32],"etc.,":[33],"but":[34],"in":[35,62,102,155,219],"this":[36,69],"work":[37,70],"we":[38],"focus":[39],"a":[41,58,128,136,226],"vision-based":[42],"model":[43,75,134],"that":[44,85],"directly":[45],"maps":[46],"raw":[47],"input":[48],"images":[49],"steering":[51],"angles":[52,115],"deep":[54],"networks.":[55],"This":[56,92,153],"represents":[57],"nascent":[59],"research":[60],"topic":[61],"computer":[63],"vision.":[64],"The":[65,208],"technical":[66],"contributions":[67],"of":[68,125,138,180,195],"two-fold.":[72],"First,":[73],"the":[74,113,191,221],"is":[76,154,174],"learned":[77],"evaluated":[79],"real":[81],"human":[82,181],"videos":[84],"time-synchronized":[87],"with":[88,210],"other":[89,211],"vehicle":[90],"sensors.":[91],"differs":[93],"many":[95],"prior":[96],"models":[97,213],"trained":[98],"synthetic":[100],"data":[101,183],"racing":[103],"games.":[104],"Second,":[105],"state-of-the-art":[106,212],"models,":[107],"such":[108],"as":[109,127],"PilotNet,":[110],"mostly":[111],"predict":[112],"wheel":[114,223],"independently":[116],"each":[118],"video":[119],"frame,":[120],"which":[121],"contradicts":[122],"common":[123],"understanding":[124],"stateful":[129],"process.":[130],"Instead,":[131],"our":[132,196],"proposed":[133],"strikes":[135],"combination":[137],"spatial":[139],"temporal":[141],"cues,":[142],"jointly":[143],"investigating":[144],"instantaneous":[145],"monocular":[146],"camera":[147],"observations":[148],"vehicle\u00bbs":[150],"historical":[151],"states.":[152],"practice":[156],"accomplished":[157],"by":[158,185],"inserting":[159],"carefully-designed":[160],"recurrent":[161],"units":[162],"(e.g.,":[163],"LSTM":[164],"Conv-LSTM)":[166],"at":[167],"proper":[168],"network":[169],"layers.":[170],"Our":[171],"experimental":[172],"study":[173],"based":[175],"about":[177],"6":[178],"hours":[179],"provided":[184],"Udacity.":[186],"Comprehensive":[187],"quantitative":[188],"evaluations":[189],"demonstrate":[190],"effectiveness":[192],"robustness":[194],"model,":[197],"even":[198],"under":[199],"scenarios":[200],"like":[201],"drastic":[202],"lighting":[203],"changes":[204],"abrupt":[206],"turning.":[207],"comparison":[209],"clearly":[214],"reveals":[215],"its":[216],"superior":[217],"performance":[218],"predicting":[220],"due":[222],"angle":[224],"for":[225],"self-driving":[227],"car.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}