Metraipolis › archive › dc_579376a8bbcd

ForeDrive: Foresight-Guided End-to-End Autonomous Driving with a Planning-Relevant Latent World Model — arXiv:2609.26299

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.26299
License (as archived): CC0-1.0
Archived: 2026-10-08T16:39:37.675Z
SHA-256 of the archived text: 1428a510db55d47d3c24d418b3a471012fc44fb3e00b48fb3f47cdbeb2605c3d
Stable URL of this page: https://metraipolis.com/documento/dc_579376a8bbcd

How to cite

ForeDrive: Foresight-Guided End-to-End Autonomous Driving with a Planning-Relevant Latent World Model — arXiv:2609.26299 — arXiv (en), https://arxiv.org/abs/2609.26299 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_579376a8bbcd (Metraipolis archive dc_579376a8bbcd, sha256 1428a510db55d47d3c24d418b3a471012fc44fb3e00b48fb3f47cdbeb2605c3d)

BibTeX

@misc{dc579376a8bbcd,
  title = {ForeDrive: Foresight-Guided End-to-End Autonomous Driving with a Planning-Relevant Latent World Model — arXiv:2609.26299},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26299},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_579376a8bbcd; sha256 1428a510db55d47d3c24d418b3a471012fc44fb3e00b48fb3f47cdbeb2605c3d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26299. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing latent world models are typically optimized for future predictability, yet the resulting representations are not necessarily useful for planning in autonomous driving. Predictions are commonly used for pretraining or auxiliary supervision rather than as direct conditioning signals for trajectory generation. We propose ForeDrive, which learns a planning-relevant latent representation and couples it asymmetrically to a Diffusion Transformer (DiT) planner. The planner consumes multi-horizon latent future representations learned with a JEPA-style world model; planning gradients update the shared online encoder, while stop-gradient routing trains the latent predictor with forecasting losses only. Because predicted futures have varying reliability across horizons and BEV trajectories are misaligned with image tokens, we use gated visual fusion, future-status injection, and Trajectory-Adaptive Bias (TAB) to inject future latents as guidance without overriding the current observation. Trained with pure imitation learning and using only the current front-view image as visual input at inference, ForeDrive attains 89.9 PDMS on NAVSIM v1 and 90.0 one-stage EPDMS on NAVSIM v2, without reinforcement learning or an external trajectory scorer.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.26299 — 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 2026-10-08T15:56:18.193Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).