The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset
The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset
This paper introduces KITScenes Multimodal, a European autonomous driving dataset built around high-fidelity sensors and maps.
The authors present KITScenes Multimodal, a European autonomous driving dataset featuring high-fidelity sensors including long-range lidar beyond 400 m and HD maps with 3D traffic elements validated through trials on open-source software; four benchmarks for spatial learning are introduced alongside claims of improved geographic diversity and sensor synchronization.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Dataset details reported by the source
- Modalities
- high-resolution global-shutter cameras Open source S2long-range lidar beyond 400 m Open source S2aging radar Open source S3redundant GNSS/INS localization Open source S3
- Tasks
- online HD map construction Open source S4long-range depth estimation Open source S4novel view synthesis Open source S4end-to-end driving Open source S4
- Embodiments
- European dataset built around high-fidelity sensors and maps Open source S2
- paper: not_reported
What remains unknown
Dataset licensing and commercial-use rights are not established here.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2606.02956v2 Announce Type: replace-cross Abstract: Existing autonomous driving datasets have enabled major progress, but fall short in sensor fidelity, map completeness, or geographic diversity. We present KITScenes Multimodal, a European dataset built around high-fidelity sensors and maps. Our fully synchronized sensor suite combines high-resolution global-shutter cameras, long-range lidar beyond 400 m, 4D im
Open source S2
aging radar, and redundant GNSS/INS localization. Our HD maps are, to our knowledge, the most complete of any sensor dataset, validated through autonomous driving trials on open-source software. For the first time in a public dataset, all driving-relevant traffic elements, such as traffic lights, are mapped in 3D to a reprojection-accurate level with full topological connectivity. Recorded in cities with irregular st
Open source S3
reet layouts and mixed traffic modes, our dataset complements existing datasets by broadening the available geographic diversity. We also introduce four benchmarks, each advancing spatial learning for embodied AI: online HD map construction, long-range depth estimation, novel view synthesis, and end-to-end driving. Project page: https://kitscenes.com/multimodal/
Open source S4
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
- Check the exact dataset version, license, modalities and task coverage against the intended use.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：arXiv Robotics — research abstracts · arxiv.org