注意力特征聚合：如何让政策学会不担心鲁棒性，专注于任务相关的视觉线索
机器人学
2026-03-02 v2 计算机视觉与模式识别
摘要
采用预训练视觉表征（PVR）作为训练视觉运动策略的流行范式，这些强大的表征可能编码广泛的任务无关场景信息，使训练后的策略在扰动场景中脆弱。本文通过注意力特征聚合（AFA）解决视觉运动策略特征池化中缺乏鲁棒性的问题。我们通过一种轻量级可训练池化机制实现，该机制自然学习注意力聚焦于任务相关的视觉线索，忽略甚至富含语义的场景干扰项。通过在仿真和真实世界中进行大量实验，我们展示了使用 AFA 训练的策略在视觉扰动存在时显著优于标准池化方法，无需昂贵的数据增强或对 PVR 进行微调。我们的发现表明，忽略多余视觉信息是部署稳健且可泛化视觉运动策略的关键步骤。项目页面: tsagkas.github.io/afa
引用
@article{arxiv.2511.10762,
title = {Attentive Feature Aggregation or: How Policies Learn to Stop Worrying about Robustness and Attend to Task-Relevant Visual Cues},
author = {Nikolaos Tsagkas and Andreas Sochopoulos and Duolikun Danier and Sethu Vijayakumar and Alexandros Kouris and Oisin Mac Aodha and Chris Xiaoxuan Lu},
journal= {arXiv preprint arXiv:2511.10762},
year = {2026}
}
备注
This paper stems from a split of our earlier work "When Pre-trained Visual Representations Fall Short: Limitations in Visuo-Motor Robot Learning." While "The Temporal Trap" replaces the original and focuses on temporal entanglement, this companion study examines policy robustness and task-relevant visual cue selection. arXiv admin note: text overlap with arXiv:2502.03270