EUVIMEDEUVIMED entdecken
Crossref

Latent World Models for Autonomous Driving: A Taxonomy and Survey

Changjie Liu, Zhuolin Liu, Dantong He, Xun Gong, Nan Li, Hong Chen

IEEE Transactions on Systems, Man, and Cybernetics: Systems · 2026-11 · 56 (11) · 6277-6293

DOI: 10.1109/tsmc.2026.3736451 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2026-11. Verfasst von Changjie Liu und 5 weiteren Autor:innen. Die Arbeit nennt 155 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Autonomous driving is evolving from fragmented modular pipelines toward more integrated system-level architectures for perception–prediction–planning–control coordination. Latent world models (LWMs) provide a compact systems-oriented modeling paradigm for connecting perception, prediction, and decision-making by compressing high-dimensional sensory inputs into latent states that support downstream prediction and planning. This survey reviews LWMs in autonomous driving and establishes a taxonomy based on dominant alignment objectives: feature alignment, value alignment, and behavior alignment. We discuss their applications in latent dynamics, anticipatory driving, predictive control, and safety verification, with particular attention to their integration with model predictive control (MPC) for closed-loop autonomous-driving systems. Furthermore, we summarize benchmark datasets and multidimensional evaluation metrics required by latent architectures, covering latent quality, open-loop accuracy, closed-loop robustness, and reasoning-oriented assessment. Finally, we identify key challenges, including latent physical reliability, latent drift and misalignment, and compositional generalization, and outline future directions such as physics-constrained dynamics, drift-aware representations, and compositional closed-loop training.

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities of China

Zitieren

APA

Liu, C., Liu, Z., He, D., Gong, X., Li, N., & Chen, H. (2026). Latent World Models for Autonomous Driving: A Taxonomy and Survey. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 56(11), 6277-6293. https://doi.org/10.1109/tsmc.2026.3736451

Vancouver

Liu C, Liu Z, He D, Gong X, Li N, Chen H. Latent World Models for Autonomous Driving: A Taxonomy and Survey. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2026;56(11):6277-6293. doi:10.1109/tsmc.2026.3736451

BibTeX
@article{Liu2026,
  author = {Liu, Changjie and Liu, Zhuolin and He, Dantong and Gong, Xun and Li, Nan and Chen, Hong},
  title = {Latent World Models for Autonomous Driving: A Taxonomy and Survey},
  journal = {IEEE Transactions on Systems, Man, and Cybernetics: Systems},
  year = {2026},
  volume = {56},
  number = {11},
  pages = {6277--6293},
  doi = {10.1109/tsmc.2026.3736451}
}
Kostenlos starten →