在模仿学习中数据质量测量的高效指标
An Efficient Metric for Data Quality Measurement in Imitation Learning
AI总结：
本文提出基于功率谱密度的高效自动演示排序指标，用于筛选高质量演示数据，提升模仿学习性能。
摘要：
模仿学习（IL）虽取得显著进展，但机器人在实际部署中仍受分布外（OOD）场景限制。通过微调预训练策略以利用部署环境中的用户演示可缓解此问题。然而，用户演示质量通常较差，包含过多修正动作、振荡和突变，影响学习和微调策略性能。现有自动演示数据筛选方法需环境交互，计算成本高且不适用于实际部署。本文提出基于演示轨迹功率谱密度（PSD）的快速、高效、全自动演示排序指标，无需策略学习、环境交互或专家标注，适用于大规模现场数据筛选。较低的PSD值对应更平滑、高质量的演示，而较高的PSD值表明不规则、含噪声的轨迹。我们在两个基准模仿学习数据集上评估该指标，并通过养老机构老年人用户研究，利用收集的演示数据微调π0.5策略以完成日常任务。结果表明，PSD筛选数据产生的策略在任务成功率和轨迹平滑度上优于未筛选基线和两种竞争性数据排序方法。
英文摘要：
Imitation learning (IL) has seen remarkable progress, yet field deployment of IL-powered robots remains hindered by the challenge of out-of-distribution (OOD) scenarios. Fine-tuning pre-trained policies with end-user demonstrations collected in deployment environments is a promising strategy to address this challenge. However, end-user demonstrations are frequently of poor quality, characterized by excessive corrective motions, oscillations, and abrupt adjustments that degrade both learned and fine-tuned policy performance. Existing automated approaches for curating demonstration data require policy rollouts in the environment, making them computationally expensive and impractical for real-world deployment. In this paper, we propose a fast, efficient, and fully automated demonstration ranking metric based on the power spectral density (PSD) of demonstration trajectories. The PSD metric requires no policy learning, environment interaction, or expert labeling, making it well-suited for scalable, in-the-field data curation. Lower PSD values correspond to smoother, higher-quality demonstrations, while higher PSD values indicate erratic, artifact-laden trajectories. We evaluate the proposed metric on two benchmark imitation learning datasets comprising expert and lay-user demonstrations, and through a user study with older adults at a retirement facility, where collected demonstrations are used to fine-tune $\pi0.5$ \cite{intelligence2025pi_} for a daily living task. Results demonstrate that PSD-curated data yields policies with higher task success rates and smoother execution trajectories compared to uncurated baselines and two competitive data-ranking methods.
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。
