Metraipolis › archive › dc_8d70f376db83

RiskWorld: Object-Centric Latent World Modeling for Autonomous Driving Risk Identification — arXiv:2608.21414

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.21414
License (as archived)
CC0-1.0
Archived
2026-10-18T09:01:42.734Z
SHA-256 of the archived text
21d5d46742bd86602181b1cc46010954ba5c1bab0daef15ccec4e4e4c1ce475d
Stable URL of this page
https://metraipolis.com/documento/dc_8d70f376db83

How to cite

RiskWorld: Object-Centric Latent World Modeling for Autonomous Driving Risk Identification — arXiv:2608.21414 — arXiv (en), https://arxiv.org/abs/2608.21414 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8d70f376db83 (Metraipolis archive dc_8d70f376db83, sha256 21d5d46742bd86602181b1cc46010954ba5c1bab0daef15ccec4e4e4c1ce475d)
BibTeX
@misc{dc8d70f376db83,
  title = {RiskWorld: Object-Centric Latent World Modeling for Autonomous Driving Risk Identification — arXiv:2608.21414},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21414},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8d70f376db83; sha256 21d5d46742bd86602181b1cc46010954ba5c1bab0daef15ccec4e4e4c1ce475d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21414. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autonomous driving risk identification aims to determine which observed object is likely to become safety-critical to the ego vehicle. Existing approaches typically predict scene-level accidents, infer risk objects indirectly from ego behavior, or apply geometric checks after trajectory forecasting, without directly using predicted ego--object relations for risk-source localization. We propose RiskWorld, an object-centric latent world model that identifies risk from the imagined evolution of each candidate relative to the ego vehicle. RiskWorld combines pretrained predictive video representations with structured ego--object histories, contextualizes observed interactions, and rolls relation-aware object states into the future using RSSM-style latent dynamics. It decodes the rollout into object-level risk scores, supported by auxiliary future-relation and temporal-risk predictions. Inference uses only observations up to the current time, while logged futures provide training supervision. On RiskBench, RiskWorld achieves the best overall F1 of 63.0\% and the lowest false-alarm rate of 2.1\%. Further analyses show that the learned rollout captures the evolution of object-level risk before critical events, while RiskWorld's selections preserve planning-critical information under filtered observation.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-25 in cs.RO).
Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.21414 — 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 2026-10-18T08:57:47.827Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).