User: Guest  Login
Title:

S2R-DAD: Sim-to-Real Distribution-Aligned Dataset

Document type:
Forschungsdaten
Publication date:
27.01.2023
Responsible:
Huch, Sebastian
Authors:
Huch, Sebastian; Scalerandi, Luca; Rivera, Esteban; Lienkamp, Markus
Author affiliation:
TUM
Publisher:
TUM
Identifier:
doi:10.14459/2023mp1695833
End date of data production:
28.02.2022
Subject area:
DAT Datenverarbeitung, Informatik; VER Technik der Verkehrsmittel
Resource type:
Experimente und Beobachtungen / experiments and observations; Simulationen / simulations
Data type:
Texte / texts; Datenbanken / data bases
Other data type:
Point clouds and text files
Description:
Sim-to-Real Distribution-Aligned Dataset (S2R-DAD) for Domain Shift and Domain Adaptation Analysis. Includes 12000 labeled point clouds in total, whereas 6000 are captured during the Indy Autonomous Challenge in Las Vegas in 2022. The other subset of 6000 samples is generated in simulation and includes the same scenarios, objects, and environment as the real counterpart. Each point cloud file contains the fused point clouds of three LiDAR sensors, covering 360deg horizontally in total. The lab...     »
Method of data assessment:
Real-world data generation using real-world LiDAR and GPS sensors. Simulated data generation using Unity Game Engine.
Links:
This dataset relates to the publication: 10.1109/TIV.2023.3251650
Key words:
Sim-to-Real; LiDAR; Point Cloud; Domain Shift; Domain Adaptation
Technical remarks:
View and download (11,8 GB total, 24007 Files)
The data server also offers downloads with FTP
The data server also offers downloads with rsync (password m1695833):
rsync rsync://m1695833@dataserv.ub.tum.de/m1695833/
Language:
en
Rights:
by, http://creativecommons.org/licenses/by/4.0
 BibTeX