CogDriver：融合认知惯性实现自动驾驶中的时序连贯规划
CogDriver: Integrating Cognitive Inertia for Temporally Coherent Planning in Autonomous Driving
对做自动驾驶端到端规划的人，这篇给出了用稀疏时序记忆维持稳定内部状态、并用时空知识蒸馏显式监督决策连贯性的做法，可直接迁移到基于 VLM 的闭环规划器中抑制决策抖动。
原文依据 a sparse temporal memory to maintain a stable internal state, the foundation of a world model
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论当前视觉语言模型（VLM）存在一个根本缺陷：它们缺乏认知惯性，这阻碍了具备预测性认知世界模型的自主智能体的实现。这些模型仅在孤立快照上运行，无法形成时序连贯的世界观，从而导致决策抖动，并且无法执行复杂的多步操作。为解决这一问题，我们提出了 CogDriver，一个通过注入这一关键认知属性来构建连贯世界模型的框架。我们的工作有两项关键贡献：（1）我们提出了 CogDriver-Data，一个大规模视觉-语言-动作数据集，其叙事标注为学习世界模型的时序动态提供了监督信号。（2）我们开发了 CogDriver-Agent，一种具有稀疏时序记忆以维持稳定内部状态的架构，这是世界模型的基础。这一能力由时空知识蒸馏方法实现，该方法显式地教会模型决策连贯性。大量实验验证了我们的范式：CogDriver-Agent 在 Bench2Drive 上的闭环驾驶得分提升了 22%，在 nuScenes 上的平均 L2 误差降低了 21%，达到了新的最先进水平。这些在长期决策和模仿精度上的显著提升，有力地证明了我们的智能体正在形成更稳定的内部世界模型。
英文原文摘要 1387 字符
The pursuit of autonomous agents with predictive cognitive world models is hindered by a fundamental flaw in current vision-language models (VLMs): they lack cognitive inertia. Operating on isolated snapshots, these models cannot form a temporally coherent world view, leading to erratic decision jitter and a failure to execute complex, multi-step maneuvers. To remedy this, we introduce CogDriver, a framework designed to build a coherent world model by instilling this crucial cognitive property. Our work makes two key contributions: (1) We present CogDriver-Data, a large-scale vision-language-action dataset whose narrative annotations provide the supervisory signal for learning the temporal dynamics of a world model. (2) We develop the CogDriver-Agent, an architecture featuring a sparse temporalmemory to maintain a stable internal state, the foundation of a world model. This is enabled by a spatiotemporal knowledge distillation approach that explicitly teaches decision coherence. Comprehensive experiments validate our paradigm: CogDriver-Agent achieves a 22% increase in the closed-loop Driving Score on Bench2Drive and a 21% reduction in mean L2 error on nuScenes, establishing a new state-of-the-art. These significant gains in both long-term decision-making and imitation accuracy provide strong evidence that our agent is developing a more stable internal world model.