The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset
Summary
KITScenes Multimodal is a high-fidelity European autonomous driving dataset with synchronized sensors, complete 3D HD maps, and four benchmarks for spatial learning and embodied AI research.
View Cached Full Text
Cached at: 06/05/26, 10:10 PM
Paper page - The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset
Source: https://huggingface.co/papers/2606.02956
Abstract
KITScenes Multimodal dataset provides high-fidelity European driving data with comprehensive 3D maps and diverse urban environments for embodied AI research.
Existingautonomous driving datasetshave enabled major progress, but fall short in sensor fidelity, map completeness, or geographic diversity. We present KITScenes Multimodal, a European dataset built aroundhigh-fidelity sensorsand maps. Our fully synchronized sensor suite combines high-resolution global-shutter cameras, long-range lidar beyond 400m,4D imaging radar, and redundantGNSS/INS localization. OurHD mapsare, 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 street layouts and mixed traffic modes, our dataset complements existing datasets by broadening the available geographic diversity. We also introduce four benchmarks, each advancingspatial learningforembodied AI:online HD map construction,long-range depth estimation,novel view synthesis, andend-to-end driving. Project page: https://kitscenes.com/
View arXiv pageView PDFProject pageAdd to collection
Get this paper in your agent:
hf papers read 2606\.02956
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2606.02956 in a model README.md to link it from this page.
Datasets citing this paper1
#### KIT-MRT/KITScenes-Multimodal Updated2 days ago • 632 • 11
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2606.02956 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
DriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style Identification
Introduces DriveDNA, a large-scale multimodal naturalistic driving dataset with 4,121 drives from 465 drivers across 115 vehicle models, and a benchmark for driving style identification through tasks like few-shot driver re-identification and personalized behavior prediction.
Learning A Unified Risk Map for Autonomous Driving in Partially Observable Environments
Proposes a unified risk map modeling framework for autonomous driving that integrates traffic flow and collision risks in partially observable environments, using spatiotemporal modeling and diffusion-based scenario generation. Outperforms state-of-the-art occlusion-aware baselines on the Waymo Open Motion Dataset.
ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving
ScenePilot proposes a feasibility-guided, boundary-driven framework for generating safety-critical scenarios for autonomous driving, using constrained multi-objective reinforcement learning to produce physically valid yet failure-inducing scenarios.
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
A comprehensive survey of methods, datasets, and benchmarks for multimodal unlearning across vision, language, video, and audio, providing a taxonomy and highlighting open problems.
Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving
Chat2Scenic is an iterative RAG-based framework that generates executable scenario scripts in Domain Specific Language from regulatory descriptions for autonomous driving testing, achieving 76.42% compilation success rate and outperforming existing methods.