论文/arXiv 2610.22041·13 天前

计划不是执行：使冻结世界模型规划器适应控制器引起的执行偏移

针对冻结世界模型规划器的规划-执行差距，ExecutionBridge利用规划-执行轨迹对适配自车潜变量，在NAVSIM验证。

AI 整理

• 本体 SDK 与控制
• 具身模型
• 端侧部署

原文链接：Plans Are Not Executions: Adapting Frozen World-Model Planners to Controller-Induced Execution Shift（arXiv 2610.22041 · 发布日期：2026-10-15）

Plans Are Not Executions: Adapting Frozen World-Model Planners to Controller-Induced Execution Shift

针对冻结世界模型规划器的规划-执行差距，ExecutionBridge利用规划-执行轨迹对适配自车潜变量，在NAVSIM验证。

核心要点

• 部署时不同下游控制器会改变同一规划轨迹的执行，造成规划-执行差距。
• 直接替换预测执行轨迹仅带来0.048 PDMS提升，显示存在语义不匹配。
• ExecutionBridge从规划-执行轨迹对推断控制器特性，适配自车潜变量滚动预测。
• 在NAVSIM上跨未见控制器配置和多个冻结世界模型规划器持续提升。

验证范围与局限：验证范围限于NAVSIM上的未见控制器配置和多个冻结世界模型规划器。

英文摘要 (Abstract)

World-model planners evaluate candidate trajectories by predicting their future consequences, implicitly relying on the plan-to-motion relationship learned during training. At deployment, a different downstream controller may execute the same planned trajectory differently, creating a planning-execution gap between the frozen model's imagined future and actual execution. A natural remedy is to replace the planned trajectory with its predicted or observed execution. However, we find that better execution fidelity does not necessarily yield better decisions: directly substituting predicted execution trajectories yields only a 0.048 PDMS improvement across 10 unseen controller configurations, far smaller than the gain from our proposed adaptation. This suggests a semantic mismatch between a planned trajectory, which serves as a reference for downstream control, and an executed trajectory, which already describes the resulting post-controller motion. We introduce ExecutionBridge, which infers controller-specific execution characteristics from planned-executed trajectory pairs and uses them to adapt the native ego latent rollout while keeping the original planned trajectory unchanged. The planner, world model, and reward head remain frozen. On NAVSIM, ExecutionBridge consistently improves planning across unseen controller configurations and multiple frozen world-model planners, with substantially larger gains in challenging driving scenes where execution mismatch more strongly affects candidate evaluation.

作者：Danqi Zhao, Keyu Chen, Wenchao Sun, Minglei Huang, Jianhe Zhang, Yan Zhu, Hao Cheng, Zifan Cao, Sifa Zheng

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.22041：Plans Are Not Executions: Adapting Frozen World-Model Planners to Controller-Induced Execution Shift访问 2026-10-21