Diff-DAgger：面向机器人操作的基于扩散策略的不确定性估计
Diff-DAgger: Uncertainty Estimation with Diffusion Policy for Robotic Manipulation
浏览论文内容
中文总结 AI 辅助
针对现有机器人门控DAgger方法易将多模态决策点的策略分歧误判为不确定性的问题，提出利用扩散策略训练目标的Diff-DAgger算法，显著提升任务预测与完成效率，推动高表达策略在交互式机器人学习中的应用。
中文摘要 AI 辅助
近年来，扩散策略在处理机器人操作中的多模态任务方面展现出令人瞩目的成果。然而，它在分布外失效问题上存在根本局限，这类失效会因误差累积以及有限的外推能力而持续存在。解决这些局限的一种方法是机器人门控DAgger（数据集聚合），这是一种带有机器人查询系统的交互式模仿学习方法，可在策略部署过程中主动寻求专家帮助。尽管机器人门控DAgger在大规模学习方面潜力巨大，但Ensemble-DAgger等现有方法在适配高表达性策略时存在困难：它们常常在多模态决策点将策略分歧误判为不确定性。为解决这一问题，我们提出了Diff-DAgger，这是一种高效的机器人门控DAgger算法，利用了扩散策略的训练目标。我们在堆叠、推动和插接等多种机器人任务上对Diff-DAgger进行了评估，结果表明Diff-DAgger将任务失效预测准确率提升了39.0%，任务完成率提升了20.6%，并将实际运行时间缩短了7.8倍。我们希望这项工作能为将高表达性但数据需求大的策略高效融入交互式机器人学习场景开辟道路。项目主页位于：https://diffdagger.github.io。
英文摘要
Recently, diffusion policy has shown impressive results in handling multi-modal tasks in robotic manipulation. However, it has fundamental limitations in out-of-distribution failures that persist due to compounding errors and its limited capability to extrapolate. One way to address these limitations is robot-gated DAgger, an interactive imitation learning with a robot query system to actively seek expert help during policy rollout. While robot-gated DAgger has high potential for learning at scale, existing methods like Ensemble-DAgger struggle with highly expressive policies: They often misinterpret policy disagreements as uncertainty at multi-modal decision points. To address this problem, we introduce Diff-DAgger, an efficient robot-gated DAgger algorithm that leverages the training objective of diffusion policy. We evaluate Diff-DAgger across different robot tasks including stacking, pushing, and plugging, and show that Diff-DAgger improves the task failure prediction by 39.0%, the task completion rate by 20.6%, and reduces the wall-clock time by a factor of 7.8. We hope that this work opens up a path for efficiently incorporating expressive yet data-hungry policies into interactive robot learning settings. The project website is available at: https://diffdagger.github.io.
发表机构
- University of Virginia（弗吉尼亚大学）
机构由 AI 辅助整理，请以论文原文为准。
