A Large-Scale Dataset for Simulated Car-Pedestrian Collisions to Advance Safety Research

dc.contributor.authorMedina, Edgar
dc.contributor.authorLoh, Leyong
dc.contributor.editorSkala, Václav
dc.date.accessioned2025-07-30T10:04:31Z
dc.date.available2025-07-30T10:04:31Z
dc.date.issued2025
dc.description.abstract-translatedCar-pedestrian collisions are a daily occurrence worldwide, yet there is a notable absence of public datasets in this domain. Research in this area is crucial, as it directly impacts pedestrian safety and serves as a basis for validating autonomous driving systems. Although finite element simulations are used, they are computationally intensive and yield insufficient data for deep learning applications. In this work, we present the PeDesCar dataset for safe autonomous driving, which spans around 15 days of simulated time and encompasses over 1 million collision events, each constrained within a temporal window of up to 2 seconds per event. The dataset is generated using MuJoCo as a physics simulator, proving its effectiveness in sim2real robotics research. We use PeDesCar to train and assess state-of-the-art models in human motion prediction and validate the realism of the simulation against realistic high-fidelity finite element simulations. Our results validate that PeDesCar is sufficient for preliminary car-pedestrian collision research. The visualization code and dataset are accessible on the project website https: //github.com/QualityMinds/PeDesCar.en
dc.description.sponsorshipThe research leading to these results is funded by the German Federal Ministry for Economic Affairs and Climate Action within the project “ATTENTION – Artificial Intelligence for realtime injury prediction”. The authors appreciate the consortium’s successful collaboration and extend special thanks to Niels Heller for his contributions to data management.
dc.format14 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.doihttp://www.doi.org/10.24132/CSRN.2025-21
dc.identifier.issn2464-4617 (Print)
dc.identifier.issn2464-4625 (online)
dc.identifier.urihttp://hdl.handle.net/11025/62227
dc.language.isoenen
dc.publisherVaclav Skala - UNION Agencyen
dc.rights© Vaclav Skala - UNION Agencyen
dc.rights.accessopenAccessen
dc.subjectPeDesCarcs
dc.subjectpredikce lidského pohybucs
dc.subjectsimulacecs
dc.subject.translatedPeDesCaren
dc.subject.translatedhuman motion predictionen
dc.subject.translatedsimulationen
dc.titleA Large-Scale Dataset for Simulated Car-Pedestrian Collisions to Advance Safety Researchen
dc.typekonferenční příspěvekcs
dc.typeconferenceObjecten
dc.type.statusPeer revieweden
dc.type.versionpublishedVersionen
local.files.count1*
local.files.size4128521*
local.has.filesyes*

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
C47.pdf
Size:
3.94 MB
Format:
Adobe Portable Document Format
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: