DriveLaW：在潜空间驾驶世界中统一规划与视频生成
DriveLaW: Unifying Planning and Video Generation in a Latent Driving World
把视频生成器的潜变量直接接入扩散规划器，让未来预测与轨迹规划共享同一表征，为自动驾驶端到端规划提供了一种「生成即规划」的可复用范式；其潜变量注入与三阶段渐进训练策略也可迁移到其他需要预测-决策耦合的视觉任务。
原文依据 By directly injecting the latent representation from its video generator into the planner
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论世界模型对自动驾驶至关重要，因为它们能够学习场景随时间演化的方式，从而应对真实世界中的长尾挑战。然而，现有方法将世界模型局限于有限的作用：它们在表面上统一的架构中运行，却仍将世界预测与运动规划视为解耦的过程。为弥合这一鸿沟，我们提出 DriveLaW，一种统一视频生成与运动规划的新范式。通过将视频生成器的潜变量表示直接注入规划器，DriveLaW 确保了高保真未来生成与可靠轨迹规划之间的内在一致性。具体而言，DriveLaW 由两个核心组件构成：DriveLaW-Video，即我们强大的世界模型，能够以富有表现力的潜变量表示生成高保真预测；以及 DriveLaW-Act，即一个扩散规划器，从 DriveLaW-Video 的潜变量中生成一致且可靠的轨迹，两个组件均通过三阶段渐进式训练策略进行优化。两项任务上取得的最优新结果证明了我们统一范式的强大能力。DriveLaW 不仅显著推进了视频预测，在弗雷歇初始距离上超越此前表现最佳的工作 33.3%、在 FVD 上超越 1.8%，还在 NAVSIM 规划基准上创下新纪录。
英文原文摘要 1340 字符
World models have become crucial for autonomous driving, as they learn how scenarios evolve over time to address the long-tail challenges of the real world. However, current approaches relegate world models to limited roles: they operate within ostensibly unified architectures that still keep world prediction and motion planning as decoupled processes. To bridge this gap, we propose DriveLaW, a novel paradigm that unifies video generation and motion planning. By directly injecting the latent representation from its video generator into the planner, DriveLaW ensures inherent consistency between high-fidelity future generation and reliable trajectory planning. Specifically, DriveLaW consists of two core components: DriveLaW-Video, our powerful world model that generates high-fidelity forecasting with expressive latent representations, and DriveLaW-Act, a diffusion planner that generates consistent and reliable trajectories from the latent of DriveLaW-Video, with both components optimized by a three-stage progressive training strategy. New state-of-the-art results across both tasks demonstrate the power of our unified paradigm. DriveLaW not only significantly advances video prediction, surpassing the previous best-performing work by 33.3% in FID and 1.8% in FVD, but also sets a new record on the NAVSIM planning benchmark.