用少样本快速识别触觉形状与材质，自动优化特征空间。
Tactile Recognition of Both Shapes and Materials with Automatic Feature Optimization-Enabled Meta Learning
- 基于触觉信号构建元学习框架，自动寻找最优特征表示。
- 5路1样本场景下准确率达96.08%，36路1样本仍保持88.7%。
- 适用于新形状、新材料及力速扰动下的泛化识别任务。
触觉感知对机器人在高接触场景中实现灵巧操作至关重要。然而，深度学习发展的同时，实际应用中面临训练数据稀缺和学习过程耗时的问题，因大量触觉数据采集成本高甚至不可行。为此，本文提出一种自动特征优化的原型网络元学习框架（AFOP-ML）。该框架作为“学会学习”的模型，不仅能以极少样本快速适应新类别，还能自动学习最优特征空间。基于四通道触觉手指信号，同时识别物体形状与材质。在36类基准上，5路1样本场景下准确率达到96.08%，极端36路1样本场景下仍达88.7%。通过三组实验验证其在未见形状、材料及力/速度扰动下的泛化能力。研究还为触觉识别任务理解与传感器设计优化提供了新思路。
原文摘要 · Abstract (English)
Tactile perception is indispensable for robots to implement various manipulations dexterously, especially in contact-rich scenarios. However, alongside the development of deep learning techniques, it meanwhile suffers from training data scarcity and a time-consuming learning process in practical applications since the collection of a large amount of tactile data is costly and sometimes even impossible. Hence, we propose an automatic feature optimization-enabled prototypical network to realize meta-learning, i.e., AFOP-ML framework. As a ``learn to learn" network, it not only adapts to new unseen classes rapidly with few-shot, but also learns how to determine the optimal feature space automatically. Based on the four-channel signals acquired from a tactile finger, both shapes and materials are recognized. On a 36-category benchmark, it outperforms several existing approaches by attaining an accuracy of 96.08% in 5-way-1-shot scenario, where only 1 example is available for training. It still remains 88.7% in the extreme 36-way-1-shot case. The generalization ability is further validated through three groups of experiment involving unseen shapes, materials and force/speed perturbations. More insights are additionally provided by this work for the interpretation of recognition tasks and improved design of tactile sensors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。