arXiv 2605.168712026-08-18cs.RO

SADP：基于基础模型生成示范的子目标感知扩散策略用于可解释机器人

SADP: Subgoal-Aware Diffusion Policy for Long-Horizon Manipulation Learned from Foundation Model Generated Demonstrations

Department of Systems Innovation, Graduate School of Engineering Science, Osaka University（系统创新系，工学研究科，大阪大学）

Site Hu, Takato Horii

备注：: Revised manuscript with an updated title, evaluation protocol, and simulation results

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出SADP，一种基于基础模型生成示范的子目标感知扩散策略，用于可解释机器人，通过自主生成子目标标注的示范数据，训练扩散策略，使机器人能够通过子目标结构和执行进度向用户解释决策过程，从而在长周期操作中实现更高的任务成功率和故障诊断能力。

摘要：

可解释机器人不仅需要成功执行任务，还需要以用户友好的方式暴露内部决策过程。然而，大多数模仿学习方法仅在任务层面的示范上训练，没有显式建模子目标结构或执行进度。这种限制在标准机器人学习数据集中子目标级监督稀缺的情况下进一步加剧，限制了能够传达其执行子任务的机器人发展。为了解决这个问题，本文提出了Subgoal-Aware Diffusion Policy (SADP)，一种利用基础模型自主生成子目标标注的示范数据，并在这些数据集上训练扩散策略的框架。SADP通过将动作生成条件化在任务层面和子目标层面的描述上，围绕人类可解释的子目标结构构建策略执行。一个轻量级的辅助头进一步预测子目标完成状态，使机器人能够暴露其当前执行阶段并监控子目标进展。在RLBench模拟和实际UR5e机器人上的实验表明，SADP在任务成功率方面优于强大的任务条件扩散基线，同时提供子目标级执行信号用于监控进度和故障诊断。这些结果表明，内置而非事后解释性可以与高任务性能共存。

英文摘要：

Long-horizon robot manipulation requires policies to coordinate multiple intermediate subgoals and determine when to advance between them. However, most imitation learning methods are trained solely on task-level demonstrations, without explicitly modeling the active subgoal or its execution progress. This limitation is further exacerbated by the scarcity of subgoal-level supervision in standard robot learning datasets, which makes explicit subgoal-conditioned control and online transition modeling difficult to learn. To address this issue, this paper proposes Subgoal-Aware Diffusion Policy (SADP), a framework that leverages foundation models to autonomously generate subgoal-annotated demonstrations and trains diffusion policies on these datasets. SADP structures policy execution around explicit natural-language subgoals by conditioning action generation on both task-level and subgoal-level descriptions. A lightweight auxiliary head further predicts a continuation score that drives online subgoal switching and supports stage-level progress monitoring. Experiments in RLBench simulations and real-world evaluations on a UR5e robot demonstrate that SADP maintains competitive task performance while exposing temporally aligned subgoal-level execution signals for progress monitoring. These results show that explicit subgoal progression can be incorporated into a diffusion policy without degrading task-level performance.

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。