Learning Sampling Distribution and Safety Filter for Autonomous Driving with VQ-VAE and Differentiable Optimization

Sampling trajectories from a distribution followed by ranking them based on a specified cost function is a common approach in autonomous driving. Typically, the sampling distribution is hand-crafted (e.g a Gaussian, or a grid). Recently, there have been efforts towards learning the sampling distribu...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the ... IEEE/RSJ International Conference on Intelligent Robots and Systems s. 3260 - 3267
Hlavní autoři: Idoko, Simon, Sharma, Basant, Singh, Arun Kumar
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 14.10.2024
Témata:
ISSN:2153-0866
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Sampling trajectories from a distribution followed by ranking them based on a specified cost function is a common approach in autonomous driving. Typically, the sampling distribution is hand-crafted (e.g a Gaussian, or a grid). Recently, there have been efforts towards learning the sampling distribution through generative models such as Conditional Variational Autoencoder (CVAE). However, these approaches fail to capture the multi-modality of the driving behaviour due to the Gaussian latent prior of the CVAE. Thus, in this paper, we re-imagine the distribution learning through vector quantized variational autoencoder (VQ-VAE), whose discrete latent-space is well equipped to capture multi-modal sampling distribution. The VQ-VAE is trained with demonstration data of optimal trajectories. We further propose a differentiable optimization based safety filter to minimally correct the VQ-VAE sampled trajectories to ensure collision avoidance. We use backpropagation through the optimization layers in a self-supervised learning set-up to learn good initialization and optimal parameters of the safety filter. We perform extensive comparisons with state-of-the-art CVAE-based baseline in dense and aggressive traffic scenarios and show a reduction of up to 12 times in collision-rate while being competitive in driving speeds.
AbstractList Sampling trajectories from a distribution followed by ranking them based on a specified cost function is a common approach in autonomous driving. Typically, the sampling distribution is hand-crafted (e.g a Gaussian, or a grid). Recently, there have been efforts towards learning the sampling distribution through generative models such as Conditional Variational Autoencoder (CVAE). However, these approaches fail to capture the multi-modality of the driving behaviour due to the Gaussian latent prior of the CVAE. Thus, in this paper, we re-imagine the distribution learning through vector quantized variational autoencoder (VQ-VAE), whose discrete latent-space is well equipped to capture multi-modal sampling distribution. The VQ-VAE is trained with demonstration data of optimal trajectories. We further propose a differentiable optimization based safety filter to minimally correct the VQ-VAE sampled trajectories to ensure collision avoidance. We use backpropagation through the optimization layers in a self-supervised learning set-up to learn good initialization and optimal parameters of the safety filter. We perform extensive comparisons with state-of-the-art CVAE-based baseline in dense and aggressive traffic scenarios and show a reduction of up to 12 times in collision-rate while being competitive in driving speeds.
Author Sharma, Basant
Idoko, Simon
Singh, Arun Kumar
Author_xml – sequence: 1
  givenname: Simon
  surname: Idoko
  fullname: Idoko, Simon
  email: cisimon7@gmail.com
  organization: University of Tartu
– sequence: 2
  givenname: Basant
  surname: Sharma
  fullname: Sharma, Basant
  organization: University of Tartu
– sequence: 3
  givenname: Arun Kumar
  surname: Singh
  fullname: Singh, Arun Kumar
  email: aks1812@gmail.com
  organization: University of Tartu
BookMark eNo1UNtKAzEUjKJgrf0DwfzA1pOkm8tj6UWFQtFqX0t2N9Eju9mSTZX69bZenmZgLjBzSc5CGxwhNwyGjIG5fXharnKdGz7kwEdDBhqYZHBCBkYZLXIQSinIT0mPs1xkoKW8IIOuewcABgeLkT3SLZyNAcMrXdlmWx_JFLsUsdglbAO1oToo3qU9nWOdXKS-jXS8S21om3bX0WnEj2PqE9MbXT9m6_HsJzRF7110IaEtakeX24QNftlj6RU597bu3OAP--RlPnue3GeL5d3DZLzIkCmZMukqMJxXUgoxEioXRnlTSFsWzCrNdAH5yLLS6qoqNXNeicP8SjvudaFLC6JPrn970Tm32UZsbNxv_n8S3wdPYB8
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/IROS58592.2024.10801610
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 Engineering
EISBN 9798350377705
EISSN 2153-0866
EndPage 3267
ExternalDocumentID 10801610
Genre orig-research
GrantInformation_xml – fundername: European Social Fund
  funderid: 10.13039/501100004895
GroupedDBID 6IE
6IF
6IH
6IL
6IN
AAJGR
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
M43
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i176t-6ed0922d66334375397f9b6acb1a7818b054a1ca8ddc81ef73161d8e2f8b8ca03
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001411890000351&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 02:29:53 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i176t-6ed0922d66334375397f9b6acb1a7818b054a1ca8ddc81ef73161d8e2f8b8ca03
PageCount 8
ParticipantIDs ieee_primary_10801610
PublicationCentury 2000
PublicationDate 2024-Oct.-14
PublicationDateYYYYMMDD 2024-10-14
PublicationDate_xml – month: 10
  year: 2024
  text: 2024-Oct.-14
  day: 14
PublicationDecade 2020
PublicationTitle Proceedings of the ... IEEE/RSJ International Conference on Intelligent Robots and Systems
PublicationTitleAbbrev IROS
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001079896
Score 2.270663
Snippet Sampling trajectories from a distribution followed by ranking them based on a specified cost function is a common approach in autonomous driving. Typically,...
SourceID ieee
SourceType Publisher
StartPage 3260
SubjectTerms Autoencoders
Autonomous vehicles
Collision avoidance
Cost function
Driver behavior
Intelligent robots
Safety
Self-supervised learning
Trajectory
Vectors
Title Learning Sampling Distribution and Safety Filter for Autonomous Driving with VQ-VAE and Differentiable Optimization
URI https://ieeexplore.ieee.org/document/10801610
WOSCitedRecordID wos001411890000351&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/eLvHCXMwlV1LTwIxEG6UeNCLL4zv9OC1sF1KH0ciEL0AihJupO3OGhJdDCwm_ns7yyJ68OCt6SNp2qTzzXS--Qi58bbpXDOyTKexY8I7yZwVwNANU6nl2ti0EJtQvZ4ej82gJKsXXBgAKJLPoIbN4i8_mfklhsrqmA8XEErw0LeVkiuy1iagEimjjSxzuHhk6veP_WFAwwb5VrGorVf_0lEpzEh3_58bOCDVDSGPDr5NzSHZguyI7P2oJXhMFmWl1Bc6tJglHhptLIpb6llRmyVhJIX8k3an-EVOA1ylrWWOrIbg_tP2fIrBBYqRWTp6YKNWp1jULiVUwlPgXoH2wxvzVpI3q-S523m6vWOlogKbciVzJiGJTBwnAWY0RCN4KkalxknrHbcqmG4XAJzl3uok8ZpDirJWPNEQp9ppb6PGCalkswxOCVUgQIb5UhstvOA6kk45qZWyOBHOSBXPb_K-KpoxWR_d-R_9F2QXbwnNAheXpJLPl3BFdvxHPl3Mr4ur_gKPmauL
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG4MmqgXXxjf9uB1YbuUPo5EIBgRUJBwI2131myii4FdE_-97bKIHjx4a_pImjbpfDOdbz6Eboyqa133lSeiQHvUaOZpRcFzbhiPFBFSRbnYBO_1xGQiBwVZPefCAECefAYV18z_8sOZyVyorOry4SxCsR76Zp3SwF_StdYhFZ9LIVmRxUV8Wb176g8tHpaOcRXQymr9LyWV3JC09_65hX1UXlPy8ODb2BygDUgO0e6PaoJHaFHUSn3BQ-XyxG2j6criFopWWCWhHYkg_cTt2H2SYwtYcSNLHa9hli1wcx678AJ2sVk8fvTGjVa-qFmIqNjHQL8C7ttX5q2gb5bRc7s1uu14haaCFxPOUo9B6MsgCC3QqNGa9VUkj6RmymiiuDXe2kI4RYwSYWgEgcgJW5FQQBAJLYzya8eolMwSOEGYAwVm5zMhBTWUCJ9prpngXLmJcIrK7vym78uyGdPV0Z390X-Ntjujh-60e9e7P0c77sackSD0ApXSeQaXaMt8pPFifpVf-xeo4a7S
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=Proceedings+of+the+...+IEEE%2FRSJ+International+Conference+on+Intelligent+Robots+and+Systems&rft.atitle=Learning+Sampling+Distribution+and+Safety+Filter+for+Autonomous+Driving+with+VQ-VAE+and+Differentiable+Optimization&rft.au=Idoko%2C+Simon&rft.au=Sharma%2C+Basant&rft.au=Singh%2C+Arun+Kumar&rft.date=2024-10-14&rft.pub=IEEE&rft.eissn=2153-0866&rft.spage=3260&rft.epage=3267&rft_id=info:doi/10.1109%2FIROS58592.2024.10801610&rft.externalDocID=10801610