Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks
Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments. This is challenging because human motion is inherently multimodal: given a history of human motion paths, there are many soci...
Uloženo v:
| Vydáno v: | 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition s. 2255 - 2264 |
|---|---|
| Hlavní autoři: | , , , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
01.06.2018
|
| Témata: | |
| ISSN: | 1063-6919 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments. This is challenging because human motion is inherently multimodal: given a history of human motion paths, there are many socially plausible ways that people could move in the future. We tackle this problem by combining tools from sequence prediction and generative adversarial networks: a recurrent sequence-to-sequence model observes motion histories and predicts future behavior, using a novel pooling mechanism to aggregate information across people. We predict socially plausible futures by training adversarially against a recurrent discriminator, and encourage diverse predictions with a novel variety loss. Through experiments on several datasets we demonstrate that our approach outperforms prior work in terms of accuracy, variety, collision avoidance, and computational complexity. |
|---|---|
| AbstractList | Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments. This is challenging because human motion is inherently multimodal: given a history of human motion paths, there are many socially plausible ways that people could move in the future. We tackle this problem by combining tools from sequence prediction and generative adversarial networks: a recurrent sequence-to-sequence model observes motion histories and predicts future behavior, using a novel pooling mechanism to aggregate information across people. We predict socially plausible futures by training adversarially against a recurrent discriminator, and encourage diverse predictions with a novel variety loss. Through experiments on several datasets we demonstrate that our approach outperforms prior work in terms of accuracy, variety, collision avoidance, and computational complexity. |
| Author | Savarese, Silvio Fei-Fei, Li Alahi, Alexandre Johnson, Justin Gupta, Agrim |
| Author_xml | – sequence: 1 givenname: Agrim surname: Gupta fullname: Gupta, Agrim – sequence: 2 givenname: Justin surname: Johnson fullname: Johnson, Justin – sequence: 3 givenname: Li surname: Fei-Fei fullname: Fei-Fei, Li – sequence: 4 givenname: Silvio surname: Savarese fullname: Savarese, Silvio – sequence: 5 givenname: Alexandre surname: Alahi fullname: Alahi, Alexandre |
| BookMark | eNotjL1OwzAYAA0CiVIyM7D4BRLsOHZstiiiBakqf4W1-ux8ES4hqeyoVd8eUJnuhtNdkrN-6JGQa84yzpm5rT-eX7OccZ0xlhfshCSm1FwKrVSRM3NKJpwpkSrDzQVJYtyw305poQs5IS9vg_PQ0Xm1vKNH7w60cg63I9gO6SrABt04BI-R7v34SefYY4DR75BWzQ5DhPB3WOK4H8JXvCLnLXQRk39OyfvsflU_pIun-WNdLVKfczWmtjSmbJSwOWh0hShKi4praZpWWSa4lY1yCqwGx1vROtsw2XKQLZi8RGBiSm6OX4-I623w3xAOay1LLYQWP_9RUos |
| CODEN | IEEPAD |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/CVPR.2018.00240 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences |
| EISBN | 9781538664209 1538664208 |
| EISSN | 1063-6919 |
| EndPage | 2264 |
| ExternalDocumentID | 8578338 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IH 6IL 6IN AAWTH ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP OCL RIE RIL RIO |
| ID | FETCH-LOGICAL-i216t-b7997d63b2a8ec4347be61859df6b031b5d6c6ab8ac1f3fcbd05f1a5fa927ea03 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 1685 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000457843602040&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Aug 27 02:52:16 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i216t-b7997d63b2a8ec4347be61859df6b031b5d6c6ab8ac1f3fcbd05f1a5fa927ea03 |
| OpenAccessLink | https://infoscience.epfl.ch/handle/20.500.14299/146393 |
| PageCount | 10 |
| ParticipantIDs | ieee_primary_8578338 |
| PublicationCentury | 2000 |
| PublicationDate | 2018-Jun |
| PublicationDateYYYYMMDD | 2018-06-01 |
| PublicationDate_xml | – month: 06 year: 2018 text: 2018-Jun |
| PublicationDecade | 2010 |
| PublicationTitle | 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition |
| PublicationTitleAbbrev | CVPR |
| PublicationYear | 2018 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0002683845 ssj0003211698 |
| Score | 2.6396172 |
| Snippet | Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 2255 |
| SubjectTerms | Computational modeling Decoding Gallium nitride Generators History Predictive models Trajectory |
| Title | Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks |
| URI | https://ieeexplore.ieee.org/document/8578338 |
| WOSCitedRecordID | wos000457843602040&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4A8eAJFYzv9ODRyj66fXgjRPS0QaOGG-kzwRggLJj47227G_TgxVvbU9Np-3Wm3zcDcO0MNU6wBBNpHCbEZlhpJTGxLneSJERLFYtNsLLk06mYtOBmp4Wx1kbymb0NzfiXb5Z6G0JlA-63l3ep2tBmjNVarV08JaM8580PWejn3rOhgjfZfNJEDEZvk-fA5YrkyRDs-FVOJaLJuPu_eRxA_0eWhyY7wDmEll0cQbd5R6LmlFY9eKo1t-hhWN6huv3xhYY6MFiCUgp5gHqP0XrvJqMQiUV19ulw9aFYormSYWOisiaJV314Hd-_jB5xUzoBz7OUbrBiQjBDc5VJbjXJCVOWemgWxlHlz7EqDNVUKi516o2ilUkKl8rCSZExK5P8GDqL5cKeANKEE5No75jlhnjA4_5G9K-wwkrrstS4U-iFFZqt6uwYs2Zxzv4ePof9YIKabHUBnc16ay9hT39u5tX6Kpr0G7vSo8c |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4gmugJFYxve_Doyj663dYbISJG3KBBw430mWAMGBZM_Pe23Q168OKt7anptP060--bAbg0iijDsjDAXJkAYx0HQgoeYG0Sw3GIJRe-2ESW53Q8ZsMaXK21MFprTz7T167p__LVXK5cqKxN7fayLtUGbKYYx1Gp1lpHVGJCE1r9kbl-Yn0bwmiVzycKWbv7Onx2bC5Pn3Thjl8FVTye9Br_m8kutH6EeWi4hpw9qOnZPjSqlySqzmnRhKdSdYvuOvkNKtvvX6gjHYfFaaWQhag3H6-3jjJysVhU5p92lx_yRZoL7rYmykuaeNGCl97tqNsPquIJwTSOyDIQGWOZIomIOdUSJzgTmlhwZsoQYU-ySBWRhAvKZWTNIoUKUxPx1HAWZ5qHyQHUZ_OZPgQkMcUqlNY1SxS2kEftnWjfYanm2sSRMkfQdCs0-SjzY0yqxTn-e_gCtvujx8FkcJ8_nMCOM0dJvTqF-nKx0mewJT-X02Jx7s37DW_4pw4 |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2018+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.atitle=Social+GAN%3A+Socially+Acceptable+Trajectories+with+Generative+Adversarial+Networks&rft.au=Gupta%2C+Agrim&rft.au=Johnson%2C+Justin&rft.au=Fei-Fei%2C+Li&rft.au=Savarese%2C+Silvio&rft.date=2018-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=2255&rft.epage=2264&rft_id=info:doi/10.1109%2FCVPR.2018.00240&rft.externalDocID=8578338 |