Temporally Decoupled Diffusion Planning for Autonomous Driving

arXiv cs.RO / 3/27/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

この論文は、都市部の動的環境での自動運転向けモーション計画において、既存拡散モデルが軌道を「単一の存在」として扱いがちで、近未来と遠未来で異なる時間依存関係を捉えられていない点を指摘しています。
提案手法TDDMは「noise-as-mask」発想により軌道を時間的セグメントに分け、セグメントごとに異なるノイズ水準を与えて再構成させることで、近未来は瞬間的ダイナミクス、遠未来はナビゲーション目標という異質な制約を自然に学習・分離します。
専用アーキテクチャとして、セグメント固有のタイムステップを注入するTemporally Decoupled Adaptive Layer Normalization（TD-AdaLN）を導入し、さらに推論ではAsymmetric Temporal Classifier-Free Guidanceで遠未来の弱ノイズ事前を即時の経路生成に誘導します。
nuPlanベンチマークで評価した結果、TDDMは既存SOTAに並ぶか上回り、とくにTest14-hardサブセットの難所で優れた性能を示したと報告しています。

Abstract

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.