[论文] GUILD: Guided Iterative Data Collection for Imitation Learning

论文概要

研究领域: ML 作者: Shivin Dass, Kevin Nguyen, Rohan Yelandur, Junhong Xu, Roberto Martín-Martín 发布时间: 2026-11-03 arXiv: 2611.05368

中文摘要

机器人模仿学习策略依靠昂贵的真机遥操作数据训练，而数据采集往往是无引导的，依赖遥操作员直觉，导致许多数据对策略性能贡献甚微。近期工作表明，策划这样的数据集能显著提升策略表现，但它们是事后过滤，无法在源头避免无信息量数据的采集。我们提出 GUILD——一种引导式数据采集（GDC）方法，主动推理应该采集哪些数据以最大化下游策略性能。该框架在「任务提议与数据采集」和「数据评估」之间迭代闭环：任务提议利用视觉-语言模型的语义先验识别相关环境、物体配置与目标；但语义相关并不必然带来策略提升，因此我们借助预测性数据归因来近似所采轨迹对目标部署性能的影响，并以此信号反馈引导下一轮采集。仿真与真机实验表明，相比被动采集策略、多个基线乃至经验丰富的机器人专家，引导式数据采集都能显著提升样本效率与部署性能。

原文摘要

Imitation learning policies in robotics are trained on datasets collected through costly real-world teleoperation. Often, the data-collection process is unguided, relying on the teleoperator's intuition, resulting in data that contributes little to overall policy performance. Recent work has shown that curating such unguided datasets can substantially improve policy performance, but these approaches operate by filtering existing datasets after collection and therefore do not prevent the acquisition of uninformative data. In this work, we propose GUILD, a novel Guided Data Collection (GDC) method that actively reasons about which data should be collected to maximize downstream policy performance. We introduce an iterative framework that alternates between 1) task proposal and data collection and 2) data evaluation to close the loop. For task proposal, we leverage semantic priors from vision-language models to identify relevant environments, object configurations, and goals for data collection. However, since semantic relevance does not imply policy improvement, we perform data evaluation. By leveraging predictive data attribution we approximate how the collected trajectories influence policy performance on a target deployment setting. This signal is then used as feedback to guide subsequent data collection, closing the data collection loop. We evaluate our approach in simulation and real robot settings, demonstrating that guided data collection substantially improves sample efficiency and deployment performance compared to passive data collection strategies, multiple baselines and experienced roboticists. More information at https://robin-lab.cs.utexas.edu/guild2026/

---

*自动采集于 2026-11-05*

#论文 #arXiv #AI #小凯