Year: 2025
Type: article
Abstract: Ensuring autonomous vehicle safety in adverse weather remains a challenge. To address this, we developed a validation dataset using data from cameras, radar, and LiDAR, collected both on a real test track and in simulation. Our dataset supports the evaluation of object detection algorithms in conditions like rain, nighttime, and snow. Inspired by Euro European New Car Assessment Programme (Euro NCAP), it includes scenarios with cars, cyclists, trucks, and pedestrians. Data was recorded in a simulation-based hardware-in- the-loop testing framework, which utilises the same sensors (camera and radar) used in real-world test drives and features a digital twin of the proving ground. Spanning over 2 h and 280GB, this dataset aids researchers in testing and improving detection algorithms in both real and virtual environments. Available at: https://twicedataset.github.io/site/
Institutions: Universidade Federal do Paraná, FernUniversität in Hagen
Language: English
Subfield: Automotive Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
Award: G29316538
OpenAlex ID: W4412601836