Metraipolis › archive › dc_8fbc79e86c1f

Driving on Memory — arXiv:2608.31029

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.31029
License (as archived)
CC0-1.0
Archived
2026-10-17T08:40:04.073Z
SHA-256 of the archived text
118bb303248845f3b3e00a8f97abd5a49cd4f9dff9e582f1b5fc56eaf0f2dd7d
Stable URL of this page
https://metraipolis.com/documento/dc_8fbc79e86c1f

How to cite

Driving on Memory — arXiv:2608.31029 — arXiv (en), https://arxiv.org/abs/2608.31029 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8fbc79e86c1f (Metraipolis archive dc_8fbc79e86c1f, sha256 118bb303248845f3b3e00a8f97abd5a49cd4f9dff9e582f1b5fc56eaf0f2dd7d)
BibTeX
@misc{dc8fbc79e86c1f,
  title = {Driving on Memory — arXiv:2608.31029},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.31029},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8fbc79e86c1f; sha256 118bb303248845f3b3e00a8f97abd5a49cd4f9dff9e582f1b5fc56eaf0f2dd7d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.31029. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

End-to-end autonomous driving models plan future trajectories from raw sensor input. While earlier driving benchmarks often measured deviation from the human trajectory, current benchmarks such as NAVSIM and Bench2Drive evaluate models with richer simulation-based metrics intended to capture safe and compliant driving. A high benchmark score should reflect that a model can understand the scene in front of it and act accordingly. But how much of that score specifically comes from reacting to the dynamic part of that scene? To probe this, we remove a model's camera input and replace it with memories from prior drives at the same location. The retrieved memories can provide persistent scene information, including road layout and location-conditioned regularities, but not the current traffic state. Surprisingly, memory is nearly sufficient on NAVSIM, reaching or even exceeding the performance of leading end-to-end methods without actually observing the evaluated scene. Our results suggest that a high NAVSIM score does not require a planner to react to the current traffic scene and should be treated with caution. This effect is benchmark-dependent: driving from memory causes substantially larger performance drops on Bench2Drive and RealEngine. We provide our code at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.31029 — 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 2026-10-17T08:13:26.954Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).