Metraipolis › archive › dc_df88b68e4842

ExceptionDrive: A Planning-Oriented Counterfactual Corner-Case Benchmark for Autonomous Driving — arXiv:2609.37871

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37871
License (as archived)
CC0-1.0
Archived
2026-10-07T16:27:51.162Z
SHA-256 of the archived text
7668189c401daa8e76f4a65c627bcb065681cd95d1bf2f06d54831864b008a67
Stable URL of this page
https://metraipolis.com/documento/dc_df88b68e4842

How to cite

ExceptionDrive: A Planning-Oriented Counterfactual Corner-Case Benchmark for Autonomous Driving — arXiv:2609.37871 — arXiv (en), https://arxiv.org/abs/2609.37871 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df88b68e4842 (Metraipolis archive dc_df88b68e4842, sha256 7668189c401daa8e76f4a65c627bcb065681cd95d1bf2f06d54831864b008a67)
BibTeX
@misc{dcdf88b68e4842,
  title = {ExceptionDrive: A Planning-Oriented Counterfactual Corner-Case Benchmark for Autonomous Driving — arXiv:2609.37871},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37871},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df88b68e4842; sha256 7668189c401daa8e76f4a65c627bcb065681cd95d1bf2f06d54831864b008a67},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37871. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Average performance on routine driving benchmarks does not establish planner reliability under rare, safety-critical hazards. We proposed ExceptionDrive, a counterfactual planning benchmark that uses VLM-assisted screening, localized multi-view editing, and quality auditing to insert hazards into real nuScenes scenes while preserving their context. Its 21 tasks span six safety families and define hazard or conflict regions, local safety constraints, and acceptable responses. Because hazard insertion can invalidate the recorded human trajectory, our reference-free protocol evaluates edited predictions using Unsafe Rate (UR), Hazard Clearance Compliance (HCC), Hazard Proximity Response (HPR), and Counterfactual Trajectory Shift (CTS), which measure core-region intrusion, clearance compliance, clearance relative to a prescribed margin, and counterfactual trajectory change. Seven representative planners frequently intrude into hazard regions or provide insufficient clearance. We also develop a Reminder Agent that, without sample-specific task labels, converts visual evidence and the shared taxonomy into structured records of hazard presence, type, and a recommended high-level strategy. The agent neither predicts trajectories nor controls the vehicle; its records guide a VLM-based decision agent. In zero-shot experiments, the reminders improve strategy accuracy and reduce under-warning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.37871 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T15:54:54.043Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).