A Survey of Large Foundation Models for Trajectory Planning in Autonomous Driving
Expert Systems · 2026-12 · 43 (12)
DOI: 10.1111/exsy.70482 ↗Kurz gefasst
Fachartikel in der Zeitschrift Expert Systems, online erschienen am 13.11.2026. Verfasst von Rufan Bai und 13 weiteren Autor:innen. Die Arbeit nennt 125 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Key Laboratory of Computer Network and Information Integration, Ministry of Education.
Abstract (Originalsprache)
Trajectory planning converts scene understanding, motion prediction, navigation objectives and traffic constraints into safe and executable ego motion. Its scope has expanded from geometric search and constrained optimization to representation learning oriented toward planning, end‐to‐end driving, semantic reasoning, generative trajectory modelling and action‐conditioned future prediction. This expansion has also blurred several distinct concepts: a planning paradigm describes how the driving stack is organized, whereas a planning method describes how trajectories are generated, evaluated, refined or verified. This survey develops a unified framework for organizing the field around the planning problem in the foundation model era. We first formulate trajectory planning as constrained decision making under uncertainty and distinguish open‐loop from closed‐loop operation and one‐stage from multi‐stage planning. We then connect structured, unstructured and open‐world scenarios to the data formats used to encode geometry, semantics, interaction, intent and future evolution. At the architectural level, we analyse modular, learning‐enhanced modular, planning‐oriented end‐to‐end and hybrid paradigms as overlapping rather than mutually exclusive research streams. At the methodological level, we organize the literature into classical autonomous driving trajectory planning algorithms, planning based on large language models and vision‐language models and planning based on world models, with detailed subcategories reflecting the functional role of each method. We further compare datasets, simulators and evaluation protocols across safety, task completion, comfort, rule compliance, planning quality, robustness, semantic grounding, world model utility and efficiency. Finally, we identify physical and semantic grounding, uncertainty propagation, closed‐loop generalization, real‐time generative inference, long‐tail robustness and verifiable hybrid integration as central challenges. The resulting taxonomy clarifies how established planning principles and foundation model capabilities can be combined without sacrificing executability or safety.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Jiangsu Province
- Key Laboratory of Computer Network and Information Integration, Ministry of Education
Zitieren
APA
Bai, R., Xue, T., Zhou, T., Chen, Y., Chen, Q., Han, H., Li, J., Yang, J., Song, B., Chen, T., Fu, C., Wu, W., Wang, W., & Lu, Y. (2026). A Survey of Large Foundation Models for Trajectory Planning in Autonomous Driving. Expert Systems, 43(12). https://doi.org/10.1111/exsy.70482
Vancouver
Bai R, Xue T, Zhou T, Chen Y, Chen Q, Han H, et al. A Survey of Large Foundation Models for Trajectory Planning in Autonomous Driving. Expert Systems. 2026;43(12). doi:10.1111/exsy.70482
BibTeX
@article{Bai2026,
author = {Bai, Rufan and Xue, Tianyi and Zhou, Tiantian and Chen, Yixian and Chen, Qiqi and Han, Hui and Li, Jiaqi and Yang, Jingjing and Song, Binbin and Chen, Tiantian and Fu, Chenchen and Wu, Weiwei and Wang, Wei and Lu, Yuhuan},
title = {A Survey of Large Foundation Models for Trajectory Planning in Autonomous Driving},
journal = {Expert Systems},
year = {2026},
volume = {43},
number = {12},
doi = {10.1111/exsy.70482}
}
EUVIMED