Learn from Incomplete Tactile Data: Tactile Representation Learning with Masked Autoencoders
Learn from Incomplete Tactile Data: Tactile Representation Learning with Masked Autoencoders
复制标题
DOI：
10.1109/iros55552.2023.10341788
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
G. Cao;Jiaqi Jiang;D. Bollegala;Shan Luo
中科院分区：
文献类型：
--
作者：
G. Cao;Jiaqi Jiang;D. Bollegala;Shan Luo
由于物体被遮挡或传感器不稳定而导致信号丢失是数据收集过程中的常见挑战。这种丢失的信号将对从数据中获得的结果产生不利影响，并且这个问题在机器人触觉感知中更常见。在触觉感知中，由于有限的工作空间和动态环境，触觉传感器与物体的接触经常不充分且不稳定，导致信号部分丢失，从而导致触觉数据不完整。因此，触觉数据将包含较少的触觉线索，且信息密度较低。在本文中，我们提出了一种基于Masked Autoencoder的触觉表示学习方法，名为TacMAE，以解决触觉感知中触觉数据不完整的问题。在我们的框架中，触觉图像的一部分被遮盖以模拟缺失的接触区域。通过重建触觉图像中缺失的信号，经过训练的模型可以从有限的触觉线索中实现对表面几何形状和触觉特性的高级理解。触觉纹理识别的实验结果表明，TacMAE在零镜头迁移时可以达到71.4%的高识别准确率，微调后可以达到85.8%的识别准确率，比不使用掩模建模的结果分别提高了15.2%和8.2%。对 YCB 对象的广泛实验证明了我们提出的方法的知识可转移性以及提高触觉探索效率的潜力。
The missing signal caused by the objects being occluded or an unstable sensor is a common challenge during data collection. Such missing signals will adversely affect the results obtained from the data, and this issue is observed more frequently in robotic tactile perception. In tactile perception, due to the limited working space and the dynamic environment, the contact between the tactile sensor and the object is frequently insufficient and unstable, which causes the partial loss of signals, thus leading to incomplete tactile data. The tactile data will therefore contain fewer tactile cues with low information density. In this paper, we propose a tactile representation learning method, named TacMAE, based on Masked Autoencoder to address the problem of incomplete tactile data in tactile perception. In our framework, a portion of the tactile image is masked out to simulate the missing contact regions. By reconstructing the missing signals in the tactile image, the trained model can achieve a high-level understanding of surface geometry and tactile properties from limited tactile cues. The experimental results of tactile texture recognition show that TacMAE can achieve a high recognition accuracy of 71.4% in the zero-shot transfer and 85.8% after fine-tuning, which are 15.2% and 8.2% higher than the results without using masked modeling. The extensive experiments on YCB objects demonstrate the knowledge transferability of our proposed method and the potential to improve efficiency in tactile exploration.