In EDS ansehen

Evaluation of adaptive sampling methods in scenario generation for virtual safety impact assessment of pre-crash safety systems

Gespeichert in:
Bibliographische Detailangaben
Titel: Evaluation of adaptive sampling methods in scenario generation for virtual safety impact assessment of pre-crash safety systems
Autoren: Yang, Xiaomi, 1994, Imberg, Henrik, 1991, Flannagan, Carol Ann Cook, 1962, Bärgman, Jonas, 1972
Quelle: Supporting the interaction of Humans and Automated vehicles: Preparing for the Environment of Tomorrow (Shape-IT).
Schlagwörter: machine learning, virtual safety impact assessment, active sampling, domain knowledge, crash-causation model, importance sampling, glance behavior
Beschreibung: Virtual safety assessment plays a vital role in evaluating the safety impact of pre-crash safety systems such as advanced driver assistance systems (ADAS) and automated driving systems (ADS). However, as the number of parameters in simulation- based scenario generation increases, the number of crash scenarios to simulate grows exponentially, making complete enumeration computationally infeasible. Efficient sampling methods, such as importance sampling and active sampling, have been proposed to address this challenge. However, a comprehensive evaluation of how domain knowledge, stratification, and batch sampling affect their efficiency remains limited. This study evaluates the performance of importance sampling and active sampling in scenario generation, incorporating two domain-knowledge-driven features: adaptive sample space reduction (ASSR) and stratification. Additionally, we assess the effects of a third feature, batch sampling, on computational efficiency in terms of both CPU and wall-clock time. Based on our findings, we provide practical recommendations for applying ASSR, stratification, and batch sampling to optimize sampling performance. Our results demonstrate that ASSR substantially improves sampling efficiency for both importance sampling and active sampling. When integrated into active sampling, ASSR reduces the root mean squared estimation error (RMSE) of the estimates by up to 90%. Stratification further improves sampling performance for both methods, regardless of ASSR implementation. When ASSR and/or stratification are applied, importance sampling performs on par with active sampling, whereas when neither feature is used, active sampling is more efficient. Larger batch sizes reduce wall-clock time but increase the number of simulations required to achieve the same estimation accuracy. In conclusion, applying ASSR and stratification in importance sampling and active sampling, where applicable, significantly improves efficiency, enabling the reallocation of computational resources to other safety initiatives.
Dateibeschreibung: electronic
Zugangs-URL: https://research.chalmers.se/publication/545464
https://research.chalmers.se/publication/545464/file/545464_Fulltext.pdf
Datenbank: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://research.chalmers.se/publication/545464#
    Name: EDS - SwePub (s4221598)
    Category: fullText
    Text: View record in SwePub
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Yang%20X
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsswe
DbLabel: SwePub
An: edsswe.oai.research.chalmers.se.1e79b15a.b5bc.493e.a779.ac82e9516298
RelevancyScore: 1065
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1064.736328125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Evaluation of adaptive sampling methods in scenario generation for virtual safety impact assessment of pre-crash safety systems
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Yang%2C+Xiaomi%22">Yang, Xiaomi</searchLink>, 1994<br /><searchLink fieldCode="AR" term="%22Imberg%2C+Henrik%22">Imberg, Henrik</searchLink>, 1991<br /><searchLink fieldCode="AR" term="%22Flannagan%2C+Carol+Ann+Cook%22">Flannagan, Carol Ann Cook</searchLink>, 1962<br /><searchLink fieldCode="AR" term="%22Bärgman%2C+Jonas%22">Bärgman, Jonas</searchLink>, 1972
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>Supporting the interaction of Humans and Automated vehicles: Preparing for the Environment of Tomorrow (Shape-IT)</i>.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22machine+learning%22">machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22virtual+safety+impact+assessment%22">virtual safety impact assessment</searchLink><br /><searchLink fieldCode="DE" term="%22active+sampling%22">active sampling</searchLink><br /><searchLink fieldCode="DE" term="%22domain+knowledge%22">domain knowledge</searchLink><br /><searchLink fieldCode="DE" term="%22crash-causation+model%22">crash-causation model</searchLink><br /><searchLink fieldCode="DE" term="%22importance+sampling%22">importance sampling</searchLink><br /><searchLink fieldCode="DE" term="%22glance+behavior%22">glance behavior</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Virtual safety assessment plays a vital role in evaluating the safety impact of pre-crash safety systems such as advanced driver assistance systems (ADAS) and automated driving systems (ADS). However, as the number of parameters in simulation- based scenario generation increases, the number of crash scenarios to simulate grows exponentially, making complete enumeration computationally infeasible. Efficient sampling methods, such as importance sampling and active sampling, have been proposed to address this challenge. However, a comprehensive evaluation of how domain knowledge, stratification, and batch sampling affect their efficiency remains limited. This study evaluates the performance of importance sampling and active sampling in scenario generation, incorporating two domain-knowledge-driven features: adaptive sample space reduction (ASSR) and stratification. Additionally, we assess the effects of a third feature, batch sampling, on computational efficiency in terms of both CPU and wall-clock time. Based on our findings, we provide practical recommendations for applying ASSR, stratification, and batch sampling to optimize sampling performance. Our results demonstrate that ASSR substantially improves sampling efficiency for both importance sampling and active sampling. When integrated into active sampling, ASSR reduces the root mean squared estimation error (RMSE) of the estimates by up to 90%. Stratification further improves sampling performance for both methods, regardless of ASSR implementation. When ASSR and/or stratification are applied, importance sampling performs on par with active sampling, whereas when neither feature is used, active sampling is more efficient. Larger batch sizes reduce wall-clock time but increase the number of simulations required to achieve the same estimation accuracy. In conclusion, applying ASSR and stratification in importance sampling and active sampling, where applicable, significantly improves efficiency, enabling the reallocation of computational resources to other safety initiatives.
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/545464" linkWindow="_blank">https://research.chalmers.se/publication/545464</link><br /><link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/545464/file/545464_Fulltext.pdf" linkWindow="_blank">https://research.chalmers.se/publication/545464/file/545464_Fulltext.pdf</link>
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.research.chalmers.se.1e79b15a.b5bc.493e.a779.ac82e9516298
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.48550/arXiv.2503.00815
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: machine learning
        Type: general
      – SubjectFull: virtual safety impact assessment
        Type: general
      – SubjectFull: active sampling
        Type: general
      – SubjectFull: domain knowledge
        Type: general
      – SubjectFull: crash-causation model
        Type: general
      – SubjectFull: importance sampling
        Type: general
      – SubjectFull: glance behavior
        Type: general
    Titles:
      – TitleFull: Evaluation of adaptive sampling methods in scenario generation for virtual safety impact assessment of pre-crash safety systems
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Yang, Xiaomi
      – PersonEntity:
          Name:
            NameFull: Imberg, Henrik
      – PersonEntity:
          Name:
            NameFull: Flannagan, Carol Ann Cook
      – PersonEntity:
          Name:
            NameFull: Bärgman, Jonas
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-locals
              Value: SWEPUB_FREE
            – Type: issn-locals
              Value: CTH_SWEPUB
          Titles:
            – TitleFull: Supporting the interaction of Humans and Automated vehicles: Preparing for the Environment of Tomorrow (Shape-IT)
              Type: main
ResultId 1