arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.22041cs.RO
收藏

规划不等于执行:将冻结的世界模型规划器适配至控制器诱导的执行偏移

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

School of Vehicle and Mobility, Tsinghua University(清华大学车辆与出行学院);Shanghai Technical Center, DENSO (China) Investment Co., Ltd.(电装(中国)投资有限公司上海技术中心);DENSO (China) Investment Co., Ltd.(电装(中国)投资有限公司)

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

AI总结:

针对冻结世界模型规划器与下游控制器间的规划-执行差距,提出ExecutionBridge适配方法,在NAVSIM数据集上显著提升了规划性能。

摘要:

世界模型规划器通过预测候选轨迹的未来结果来评估它们,隐含依赖训练期间学习到的规划到运动的关系。在部署阶段,不同的下游控制器可能会以不同方式执行相同的规划轨迹,从而在冻结模型的想象未来与实际执行之间产生规划-执行差距。一种自然的补救方法是用预测或观察到的执行轨迹替代规划轨迹。然而,我们发现更好的执行保真度并不一定能带来更好的决策:直接替换预测的执行轨迹在10个未见过的控制器配置上仅带来0.048的PDMS提升,远小于我们提出的适配方法带来的增益。这表明作为下游控制参考的规划轨迹,与已经描述控制器后运动的执行轨迹之间存在语义不匹配。我们引入ExecutionBridge,它从规划-执行轨迹对中推断特定于控制器的执行特征,并利用这些特征适配原生自我智能体的潜在滚动,同时保持原始规划轨迹不变。规划器、世界模型和奖励头均保持冻结状态。在NAVSIM上,ExecutionBridge在未见过的控制器配置和多个冻结世界模型规划器上持续提升规划性能,在执行不匹配对候选评估影响更大的具有挑战性的驾驶场景中,增益显著更大。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑