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...
Gespeichert in:
| Veröffentlicht in: | Proceedings of the ... IEEE/RSJ International Conference on Intelligent Robots and Systems S. 3260 - 3267 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Tagungsbericht |
| Sprache: | Englisch |
| Veröffentlicht: |
IEEE
14.10.2024
|
| Schlagworte: | |
| ISSN: | 2153-0866 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| 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/eLvHCXMwlV1LSwMxEA5aPOjFV8U3OXjddl_mcSy2RUHaarX0VvJaWdCttFvBf-9MurV68OAt7BIIGZj5ZjLffIRccRurUGcqiG1iIEERKoCoqAPwl-AMjQxD7S19z3s9MR7LQUVW91wY55xvPnMNXPq3fDs1CyyVNbEfDhAKZOibnLMlWWtdUAm5FJJVPVxRKJt3j_0hoGGJfKs4bax2_9JR8WGku_vPA-yR-pqQRwffoWafbLjigOz8mCV4SObVpNQXOlTYJQ6LNg7FrfSsqCos_Mlc-Um7OT6RU4CrtLUokdUA6T9tz3IsLlCszNLRQzBqdfymdiWhAq5AvzraBx_zVpE36-S523m6uQ0qRYUgjzgrA-ZsKOPYAsxI0gQyFckzqZkyOlIcQrcGAKcio4S1RkQuQ1mryAoXZ0ILo8LkiNSKaeGOCb02gA1jLXUCiMqPiBHSWJTycaljTJ6QOt7f5H05NGOyurrTP76fkW20EoaFKD0ntXK2cBdky3yU-Xx26U39BTfLqhQ |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEF6kCurFV8W3e_CaNi-T3WOxLRVrW20tvZV9RQKaSpsI_ntn1tTqwYO3JWFh2YGZb2bnm4-Qq1j7wpWJcHwdKEhQmHAgKkoH_CU4Q8VdV1pLd-Nej00mfFCS1S0Xxhhjm89MDZf2LV_PVIGlsjr2wwFCgQx9HaWzSrrWqqTixpzxqOzi8lxev33sDwEPc2Rc-WFtuf-XkooNJO2dfx5hl1RXlDw6-A42e2TNZPtk-8c0wQOyKGelPtOhwD5xWDRxLG6paEVFpuFPYvIP2k7xkZwCYKWNIkdew6xY0OY8xfICxdosHT8440bLbmqWIirgDOSLoX3wMq8lfbNKntqt0U3HKTUVnNSLo9yJjHa572sAGkEYQK7C44TLSCjpiRiCtwQIJzwlmNaKeSZBYStPM-MnTDIl3OCQVLJZZo4IvVaADn3JZQCYyg6JYVxpFPMxoYkifkyqeH_Tt6-xGdPl1Z388f2SbHZG991p97Z3d0q20GIYJLzwjFTyeWHOyYZ6z9PF_MKa_RNBkq1d |
| 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 |