Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Generating Scenarios with Diverse Pedestrian Behaviors for Autonomous Vehicle Testing
Lund University, Sweden.
RISE Research Institutes of Sweden, Digitala system, Datavetenskap.ORCID-id: 0000-0002-5299-142X
University of Bucharest, Romania; Institute of Mathematics of the Romanian Academy, Romania.
Lund University, Sweden; Google Research, USA.
2021 (engelsk)Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

There exist several datasets for developing self-driving car methodologies. Manually collected datasets impose inherent limitations on the variability of test cases and it is particularly difficult to acquire challenging scenarios, e.g. ones involving collisions with pedestrians. A way to alleviate this is to consider automatic generation of safety-critical scenarios for autonomous vehicle (AV) testing. Existing approaches for scenario generation use heuristic pedestrian behavior models. We instead propose a framework that can use state-of-the-art pedestrian motion models, which is achieved by reformulating the problem as learning where to place pedestrians such that the induced scenarios are collision prone for a given AV. Our pedestrian initial location model can be used in conjunction with any goal driven pedestrian model which makes it possible to challenge an AV with a wide range of pedestrian behaviors – this ensures that the AV can avoid collisions with any pedestrian it encounters. We show that it is possible to learn a collision seeking scenario generation model when both the pedestrian and AV are collision avoiding. The initial location model is conditioned on scene semantics and occlusions to ensure semantic and visual plausibility, which increases the realism of generated scenarios. Our model can be used to test any AV model given sufficient constraints.

sted, utgiver, år, opplag, sider
2021.
Emneord [en]
Autonomous Vehicles, AV Testing, Reinforcement Learning
HSV kategori
Identifikatorer
URN: urn:nbn:se:ri:diva-62527OAI: oai:DiVA.org:ri-62527DiVA, id: diva2:1726541
Konferanse
5th Conference on Robot Learning (CoRL 2021), London, UK.
Tilgjengelig fra: 2023-01-13 Laget: 2023-01-13 Sist oppdatert: 2025-09-23bibliografisk kontrollert

Open Access i DiVA

fulltext(1459 kB)87 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 1459 kBChecksum SHA-512
e55500ff1822adef6a4d7fdcb0936f709183bbe85190190e5e10f143c6918df7a2d70f22d92dcbcea0e54b011f93a620e932858c77a4f4a23b13fd94cbbe91c3
Type fulltextMimetype application/pdf

Person

Pirinen, Aleksis

Søk i DiVA

Av forfatter/redaktør
Pirinen, Aleksis
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 89 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 413 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
v. 2.50.0