AI 中文总结
本文提出4D-WAM模型，通过几何基础模型的训练时监督与面向决策的时间步长采样策略，提升自动驾驶中世界-动作模型的4D场景一致性，在NAVSIM-v1、NAVSIM-v2基准上实现最优性能。
AI 中文摘要
新兴的世界-动作模型（World-Action Models, WAMs）通过联合建模未来驾驶场景演化与轨迹规划，在自动驾驶中展现出良好性能。然而，现有WAMs通常以视频数据训练，而视频仅为底层4D驾驶场景的2D投影，导致WAMs无法理解和捕捉4D场景结构，进而生成视觉上合理但4D不一致的未来预测，误导下游规划。为缓解该问题，本文提出4D-WAM模型，利用几何基础模型提供训练时监督，实现4D一致的世界建模。具体而言，将WAM预测的未来帧输入几何基础模型，基于其4D感知响应定义4D一致性损失，该损失鼓励模型在训练中理解、表示和预测物理一致的4D场景，且无额外推理成本。此外，本文发现WAMs存在早期决策现象，提出面向决策的时间步长采样策略，重点监督驾驶决策主要形成的早期高噪声阶段，通过将4D监督传播至该关键决策形成阶段，进一步提升轨迹规划性能。大量实验表明，4D-WAM可有效建模4D一致的场景演化，在具有挑战性的NAVSIM-v1和NAVSIM-v2基准上实现了最优性能。
英文摘要
Emerging World-Action Models (WAMs) have demonstrated promising performance in autonomous driving by jointly modeling future driving scene evolution and trajectory planning. However, existing WAMs are typically trained with video data, which is only 2D projections of the underlying 4D driving scene. Consequently, WAMs fail to understand and capture the structure of 4D scenes and thus generate visually plausible yet 4D inconsistent future predictions that mislead downstream planning. To alleviate this issue, we present 4D-WAM, a model that leverages geometric foundation models for training-time supervision to enable 4D consistent world modeling. Specifically, we feed WAM-predicted future frames into a geometric foundation model, and use 4D-aware responses to define a 4D consistency loss. This loss encourages the model to understand, represent, and predict physically consistent 4D scenes during training, without additional inference cost. Moreover, we identify an early-decision phenomenon in WAMs and propose a decision-oriented timestep sampling strategy that emphasizes supervision at early, high-noise stages, where driving decisions are primarily formed. By propagating 4D supervision to this critical decision-formation phase, the proposed strategy further improves trajectory planning. Extensive experiments demonstrate that 4D-WAM effectively models 4D consistent scene evolution and achieves state-of-the-art performance on challenging NAVSIM-v1 and NAVSIM-v2 benchmarks.
