AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understanding
For autonomous driving researchers, it provides a standardized benchmark to evaluate safety-aware reasoning in vision-language models, addressing a gap in existing evaluations.
The paper introduces AUTOPILOT-VQA, a benchmark for evaluating vision-language models on incident-centric dashcam video understanding, covering diverse safety-relevant categories. It aims to assess models' ability to reason about safety-critical incidents beyond object recognition.
Recent advances in Vision-Language Models, Large Language Models, and Multimodal Large Language Models have improved autonomous driving tasks such as scene understanding, decision making, trajectory prediction, and visual question answering. However, evaluating whether these models can reliably reason about safety-critical incidents remains challenging. To address this gap, we present AUTOPILOT-VQA, an incident-centric visual question answering benchmark for dashcam video understanding. The dataset evaluates different systems through structured questions designed around real-world driving incidents and near-incidents. The benchmark covers diverse safety-relevant categories, including weather and lighting conditions, traffic environment, road layout, road surface state, signage, involved entities, accident occurrence, impact location, and avoidability-related reasoning. By requiring models to answer grounded questions about both contextual scene properties and event-level incident details, AUTOPILOT-VQA moves beyond object recognition toward temporally grounded, safety-aware reasoning. The dataset is released as part of the AUTOPILOT CVPR 2026 competition and provides a standardized benchmark for assessing the reliability of autonomous driving systems in different scenarios. Our benchmark support developments for more interpretable, robust, and safety-conscious vision-language systems for real-world autonomous driving.