做机器人数据增强和指令跟随的团队，TREAD用VLM低成本提升数据集质量，直接增强策略泛化，值得在LIBERO等基准上试试。
机器人学习中的大规模策略在操作任务上表现优异，但指令跟随能力不足，主要原因是现有数据集缺乏语言和动作序列多样性。TREAD提出一种可扩展框架，利用大型视觉语言模型（VLM）对现有机器人数据集进行重标注，无需额外数据采集。该方法通过三个步骤：从原始指令生成语义子任务、基于子任务分割演示视频、生成包含物体属性的多样化指令，将长演示分解为语言-动作对。实验表明，在LIBERO基准上，使用TREAD增强数据训练的策略在未见任务和目标上表现更好，提升了规划泛化和语言条件策略泛化能力。
Task Robustness via Re-Labelling Vision-Action Robot Data
The recent trend in scaling models for robot learning has resulted in impressive policies that can perform various manipulation tasks and generalize to novel scenarios. However, these policies continue to struggle with following instructions, likely due to the limited linguistic and action sequence diversity in existing robotics datasets. This paper introduces Task Robustness via Re-Labelling Vision-Action Robot Data (TREAD), a scalable framework that leverages large Vision-Language Models (VLMs) to augment existing robotics datasets without additional data collection, harnessing the transferable knowledge embedded in these models. Our approach leverages a pretrained VLM through three stages: generating semantic sub-tasks from original instruction labels and initial scenes, segmenting demonstration videos conditioned on these sub-tasks, and producing diverse instructions that incorporate object properties, effectively decomposing longer demonstrations into grounded language-action pairs. We further enhance robustness by augmenting the data with linguistically diverse versions of the text goals. Evaluations on LIBERO demonstrate that policies trained on our augmented datasets exhibit improved performance on novel, unseen tasks and goals. Our results show that TREAD enhances both planning generalization through trajectory decomposition and language-conditioned policy generalization through increased linguistic diversity.