Temporally Decoupled Diffusion Planning for Autonomous Driving
Proceedings of the International Conference on Automated Planning and Scheduling · 08.06.2026 · 36 (1) · 719-728
DOI: 10.1609/icaps.v36i1.42892 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the International Conference on Automated Planning and Scheduling, online erschienen am 08.06.2026. Verfasst von Xiang Li und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Motion planning in dynamic urban environments requires balancing immediate safety with long-term goals. While diffusion models effectively capture multi-modal decision-making, existing approaches treat trajectories as monolithic entities, overlooking heterogeneous temporal dependencies where near-term plans are constrained by instantaneous dynamics and far-term plans by navigational goals. To address this, we propose Temporally Decoupled Diffusion Model (TDDM), which reformulates trajectory generation via a noise-as-mask paradigm. By partitioning trajectories into segments with independent noise levels, we implicitly treat high noise as information voids and weak noise as contextual cues. This compels the model to reconstruct corrupted near-term states by leveraging internal correlations with better-preserved temporal contexts. Architecturally, we introduce a Temporally Decoupled Adaptive Layer Normalization (TD-AdaLN) to inject segment-specific timesteps. During inference, our Asymmetric Temporal Classifier-Free Guidance utilizes weakly noised far-term priors to guide immediate path generation. Evaluations on the nuPlan benchmark show TDDM approaches or exceeds state-of-the-art baselines, particularly excelling in the challenging Test14-hard subset.
Zitieren
APA
Li, X., Wang, B., Zhang, J., & Wang, J. (2026). Temporally Decoupled Diffusion Planning for Autonomous Driving. Proceedings of the International Conference on Automated Planning and Scheduling, 36(1), 719-728. https://doi.org/10.1609/icaps.v36i1.42892
Vancouver
Li X, Wang B, Zhang J, Wang J. Temporally Decoupled Diffusion Planning for Autonomous Driving. Proceedings of the International Conference on Automated Planning and Scheduling. 2026;36(1):719-728. doi:10.1609/icaps.v36i1.42892
BibTeX
@article{Li2026,
author = {Li, Xiang and Wang, Bikun and Zhang, John and Wang, Jianjun},
title = {Temporally Decoupled Diffusion Planning for Autonomous Driving},
journal = {Proceedings of the International Conference on Automated Planning and Scheduling},
year = {2026},
volume = {36},
number = {1},
pages = {719--728},
doi = {10.1609/icaps.v36i1.42892}
}
EUVIMED