Metraipolis › archive › dc_a248a3fa465a

Driving on Registers, Reasoning on Risk: Risk-Aware Occupancy for Register-Based End-to-End Autonomous Driving — arXiv:2609.21486

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21486
License (as archived)
CC0-1.0
Archived
2026-10-10T01:05:21.154Z
SHA-256 of the archived text
73ca1c23b4ce3366f8807c5572dc3d42768ed5d5dc6ff0c0b5f7a0a5a9455e56
Stable URL of this page
https://metraipolis.com/documento/dc_a248a3fa465a

How to cite

Driving on Registers, Reasoning on Risk: Risk-Aware Occupancy for Register-Based End-to-End Autonomous Driving — arXiv:2609.21486 — arXiv (en), https://arxiv.org/abs/2609.21486 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a248a3fa465a (Metraipolis archive dc_a248a3fa465a, sha256 73ca1c23b4ce3366f8807c5572dc3d42768ed5d5dc6ff0c0b5f7a0a5a9455e56)
BibTeX
@misc{dca248a3fa465a,
  title = {Driving on Registers, Reasoning on Risk: Risk-Aware Occupancy for Register-Based End-to-End Autonomous Driving — arXiv:2609.21486},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21486},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a248a3fa465a; sha256 73ca1c23b4ce3366f8807c5572dc3d42768ed5d5dc6ff0c0b5f7a0a5a9455e56},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21486. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal trajectory prediction improves behavioral coverage in end-to-end autonomous driving, but existing methods remain limited by sparse scene representations. Incomplete evidence leads to low-quality candidate generation and unreliable ranking among geometrically similar trajectories. On a register-based baseline, bad and poor candidates constitute 19.74% of the candidate set, while the oracle-best candidate ranks only 33.9th on average. We propose RRDrive, which introduces risk-aware occupancy as a dense, temporally aligned, and trajectory-queryable representation. Its global structure guides high-quality multimodal generation, while candidate-conditioned risk queries support fine-grained selection. We further construct RiskOcc4D-NAVSIM with automatic risk annotations. RRDrive achieves a selected-trajectory PDMS of 0.951, representing a 1.5% relative improvement over the baseline (0.937), and improves the average candidate PDMS by 7.7%. In challenging scenes, it improves candidate PDMS by 30.2% and increases the Spearman correlation among good candidates by 0.41, from 0.26 to 0.67. To move beyond this oracle setting, we further develop an external RiskOcc predictor, a perception module that estimates risk-aware occupancy directly from sensor inputs. The competitive performance validates the representation's feasibility.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.21486 — 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 2026-10-10T00:23:42.455Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).