【论文速递】GUILD: Guided Iterative Data Collection for Imitation Learning

英文标题：GUILD: Guided Iterative Data Collection for Imitation Learning

arXiv编号：2611.05368
作者：Shivin Dass, Kevin Nguyen, Rohan Yelandur
来源：arXiv
原文链接：https://arxiv.org/abs/2611.05368

中文摘要：
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/

本文由华人空间 AI 论文助手自动抓取翻译，仅供学术交流。