Metraipolis › archive › dc_dca6d856c905
Herding End-to-End Autonomous Driving via Neuro-Symbolic Safety Guards — arXiv:2608.11451
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11451
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:15:51.320Z
- SHA-256 of the archived text
7f4f01717f7c0e3fc7d8a0f3c0fa6057a06fe9f6db7ec4fcae130078334d9b6d- Stable URL of this page
https://metraipolis.com/documento/dc_dca6d856c905
How to cite
Herding End-to-End Autonomous Driving via Neuro-Symbolic Safety Guards — arXiv:2608.11451 — arXiv (en), https://arxiv.org/abs/2608.11451 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dca6d856c905 (Metraipolis archive dc_dca6d856c905, sha256 7f4f01717f7c0e3fc7d8a0f3c0fa6057a06fe9f6db7ec4fcae130078334d9b6d)
BibTeX
@misc{dcdca6d856c905,
title = {Herding End-to-End Autonomous Driving via Neuro-Symbolic Safety Guards — arXiv:2608.11451},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11451},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dca6d856c905; sha256 7f4f01717f7c0e3fc7d8a0f3c0fa6057a06fe9f6db7ec4fcae130078334d9b6d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11451. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern end-to-end driving agents can achieve high average performance yet still violate basic traffic rules that a human driver would never miss. The reason is structural: they learn statistical patterns rather than the physical conditions that guarantee safe driving, leaving their decision-making process opaque and safety constraints unenforced. We introduce a neuro-symbolic safety guard, a lightweight module that attaches to the final command interface of an already-trained agent. Immediately before a command reaches the vehicle, it checks the command against explicit safety rules and, only when necessary, replaces it with the nearest safe alternative. Each intervention is directly executable and traceable to the rule that triggered it, while the guard itself requires no retraining and adds no learned component. Evaluated on the long-tail benchmarks Fail2Drive and Bench2Drive using the state-of-the-art TransFuser v6 (TFv6) as a case study, the guard improves Success Rate by 15% and reduces safety-critical collisions by up to 53%, while preserving the original Driving Score. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2608.11451 — 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 2026-10-19T05:08:46.688Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).