arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.12813cs.CVcs.AI
收藏

从演示中进行对比学习

Contrastive Learning from Demonstrations

NOVA LINCS;Universidade da Beira Interior(贝拉 interior 大学)

André Correia, Luís A. Alexandre

摘要:

本文提出了一个框架,学习视觉表示从未标记的视频演示捕获从多个视点。我们表明,这些表示是适用于模仿几个机器人的任务,包括拾取和放置。我们优化了最近提出的自监督学习算法,通过应用对比学习,以提高任务相关的信息,同时抑制不相关的信息的特征嵌入。我们验证了所提出的方法上公开可用的多视图浇注和自定义拾取和放置数据集,并将其与TCN三重基线。我们使用三个指标来评估学习的表示:视点对齐,阶段分类和强化学习,并且在所有情况下,与最先进的方法相比,结果都有所改善,并且增加了减少训练迭代次数的好处。

英文摘要:

This paper presents a framework for learning visual representations from unlabeled video demonstrations captured from multiple viewpoints. We show that these representations are applicable for imitating several robotic tasks, including pick and place. We optimize a recently proposed self-supervised learning algorithm by applying contrastive learning to enhance task-relevant information while suppressing irrelevant information in the feature embeddings. We validate the proposed method on the publicly available Multi-View Pouring and a custom Pick and Place data sets and compare it with the TCN triplet baseline. We evaluate the learned representations using three metrics: viewpoint alignment, stage classification and reinforcement learning, and in all cases the results improve when compared to state-of-the-art approaches, with the added benefit of reduced number of training iterations.

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。

↑