RDD：面向长时程任务中规划器对齐的基于检索的演示分解器
RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks
AI总结：
针对长时程任务中启发式子任务分解与低层策略不匹配的问题，提出基于检索的演示分解器RDD，通过对齐视觉特征自动分解演示，在仿真和真实任务上超越现有方法。
摘要：
为应对长时程任务，近期分层视觉-语言-动作（VLA）框架采用基于视觉-语言模型（VLM）的规划器，将复杂操作任务分解为低层视觉运动策略易于处理的较简单子任务。通常，VLM规划器通过微调来学习分解目标任务，此微调需要目标任务的演示，这些演示需通过人工标注或启发式规则分割成子任务。然而，启发式子任务可能与视觉运动策略的训练数据存在显著偏差，从而降低任务性能。为解决这些问题，我们提出一种基于检索的演示分解器（RDD），它通过将分解后的子任务区间的视觉特征与低层视觉运动策略训练数据中的视觉特征进行对齐，自动将演示分解为子任务。我们的方法在仿真和真实世界任务上均优于最先进的子任务分解器，展现出在不同设置下的鲁棒性。代码和更多结果可在 rdd-neurips.github.io 获取。
英文摘要：
To tackle long-horizon tasks, recent hierarchical vision-language-action (VLAs) frameworks employ vision-language model (VLM)-based planners to decompose complex manipulation tasks into simpler sub-tasks that low-level visuomotor policies can easily handle. Typically, the VLM planner is finetuned to learn to decompose a target task. This finetuning requires target task demonstrations segmented into sub-tasks by either human annotation or heuristic rules. However, the heuristic subtasks can deviate significantly from the training data of the visuomotor policy, which degrades task performance. To address these issues, we propose a Retrieval-based Demonstration Decomposer (RDD) that automatically decomposes demonstrations into sub-tasks by aligning the visual features of the decomposed sub-task intervals with those from the training data of the low-level visuomotor policies. Our method outperforms the state-of-the-art sub-task decomposer on both simulation and real-world tasks, demonstrating robustness across diverse settings. Code and more results are available at rdd-neurips.github.io.
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。
