Metraipolis › archive › dc_66e08249f91c

Mechanistic Interpretability for End-to-End Self-Driving — arXiv:2610.41185

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41185
License (as archived): CC0-1.0
Archived: 2026-11-02T07:51:15.611Z
SHA-256 of the archived text: f63525a7e9813c955ea380a98e368cb131641301f5db64ac6565adc9deda4f6b
Stable URL of this page: https://metraipolis.com/documento/dc_66e08249f91c

How to cite

Mechanistic Interpretability for End-to-End Self-Driving — arXiv:2610.41185 — arXiv (en), https://arxiv.org/abs/2610.41185 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_66e08249f91c (Metraipolis archive dc_66e08249f91c, sha256 f63525a7e9813c955ea380a98e368cb131641301f5db64ac6565adc9deda4f6b)

BibTeX

@misc{dc66e08249f91c,
  title = {Mechanistic Interpretability for End-to-End Self-Driving — arXiv:2610.41185},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41185},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_66e08249f91c; sha256 f63525a7e9813c955ea380a98e368cb131641301f5db64ac6565adc9deda4f6b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41185. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

End-to-end (E2E) autonomous driving models achieve strong planning performance but remain largely opaque, limiting observability and trust. We apply mechanistic interpretability to E2E driving by training Sparse Autoencoders (SAEs) on the internal activations of a simple, single-camera end-to-end path planning model. Unsupervised clustering of SAE latents reveals interpretable structure aligned with route intent, vehicle speed, and braking behavior, recovering route intent with 98.3% accuracy without supervision. Through paired counterfactual image edits, we further show that specific SAE features are visually grounded and systematically respond to scene changes such as traffic light state and stop sign presence. Steering individual SAE latents produces predictable, monotonic changes in planner outputs including lateral displacement, curvature, and braking. Finally, we demonstrate a practical application of these representations: we build a lightweight adapter trained on SAE latents that reduces trajectory selection error by 3.44%, outperforming an equivalent adapter that omits SAE latents, confirming that the sparse representation captures useful information for interpretability. Code and visualizations are available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.41185 — 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 2026-11-02T07:40:00.248Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).