ExtremeDrive: A Real-World Dataset and Benchmark for Critical Driving
Existing autonomous driving datasets and benchmarks provide extensive resources for routine driving, yet real-world data covering safety-critical scenarios and extreme environmental conditions remain limited. To address this gap, we present ExtremeDrive, a real-world dataset and benchmark covering emergency maneuvers, complex traffic interactions, and adverse conditions such as slippery or snow-covered roads, alongside routine driving. The dataset comprises 589 driving scenes curated from a larger pool of real-world driving recordings, with calibrated and aligned multisensor data and reviewed annotations of road structure and traffic participants. We further establish a benchmark to evaluate planned trajectories through simulated vehicle execution, measuring safety-related metrics and driving performance. Experiments at equal training set sizes show that incorporating critical driving data reduces trajectory prediction errors and improves mean critical-success rates in critical scenarios. ExtremeDrive provides a unified resource for learning and evaluating autonomous driving in safety-critical scenarios and extreme environmental conditions.
Authors
- Ruihai Ma (ORCID: https://orcid.org/0009-0007-0062-0858)
- Jinbo Lv
- Shiyue Zhao (ORCID: https://orcid.org/0000-0001-6742-2767)
- Yuhong Jiang (ORCID: https://orcid.org/0009-0007-1734-7210)
- Xinhan Li
- Wenxuan Cheng
- Tao Liu
- Shijie Zhao
- Junzhi Zhang
- Chengkun He
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-16
- DOI
- https://doi.org/10.48550/arxiv.2611.20574
- Primary Topic
- Autonomous Vehicle Technology and Safety
- Type
- preprint