Bioinspired tactile sensor for surface roughness discrimination
Bioinspired tactile sensor for surface roughness discrimination
复制标题
DOI：
10.1016/j.sna.2016.12.021
复制
发表时间：
2017-03-01
影响因子：
4.6
通讯作者：
Peters, Jan
中科院分区：
文献类型：
--
作者：
Yi, Zhengkun;Zhang, Yilei;Peters, Jan
使用人工触觉传感器进行表面纹理辨别在过去十年中引起了越来越多的关注，因为它可以赋予机器人系统关键缺失的能力。然而，作为纹理的主要组成部分，粗糙度却很少被探索。本文提出了一种触觉表面粗糙度辨别方法，包括两个部分：（1）仿生人工指尖的设计和制造，以及（2）用于触觉表面粗糙度辨别的触觉信号处理。仿生指尖由两个聚二甲基硅氧烷（PDMS）层、一个聚甲基丙烯酸甲酯（PMMA）棒和两个垂直的聚偏二氟乙烯（PVDF）薄膜传感器组成。这种人造指尖在三个方面模仿了人类指尖：(1) 具有不同刚度的两个 PDMS 层复制了人类皮肤表皮和真皮的弹性特性，(2) PMMA 棒的作用类似于骨骼，(3) PVDF 薄膜传感器在位置和对振动刺激的响应方面模拟迈斯纳小体。检查各种提取的特征和分类算法，包括支持向量机 (SVM) 和 k 最近邻 (kNN)，以进行触觉表面粗糙度辨别。探索了粗糙度值（Ra）为50μm、25μm、12.5μm、6.3μm、3.2μm、1.6μm、0.8μm和0.4μm的八种标准粗糙表面。通过简单地将传感器在没有任何负载和速度控制器的情况下在表面上滑动，我们发现仅使用一个具有 kNN (k = 9) 分类器和标准差特征的 PVDF 薄膜传感器就可以实现 (82.6 +/- 10.8) % 的最高分类精度，即，所开发的方法非常经济实惠、稳健且适合实时表面粗糙度评估。 (C) 2017 Elsevier B.V. 保留所有权利。
Surface texture discrimination using artificial tactile sensors has attracted increasing attentions in the past decade as it can endow robot systems with a key missing ability. However, as a major component of texture, roughness has rarely been explored. This paper presents an approach for tactile surface roughness discrimination, which includes two parts: (1) design and fabrication of a bioinspired artificial fingertip, and (2) tactile signal processing for tactile surface roughness discrimination. The bioinspired fingertip is comprised of two polydimethylsiloxane (PDMS) layers, a polymethyl methacrylate (PMMA) bar, and two perpendicular polyvinylidene difluoride (PVDF) film sensors. This artificial fingertip mimics human fingertips in three aspects: (1) Elastic properties of epidermis and dermis in human skin are replicated by the two PDMS layers with different stiffness, (2) The PMMA bar serves the role analogous to that of a bone, and (3) PVDF film sensors emulate Meissner's corpuscles in terms of both location and response to the vibratory stimuli. Various extracted features and classification algorithms including support vector machines (SVM) and k-nearest neighbors (kNN) are examined for tactile surface roughness discrimination. Eight standard rough surfaces with roughness values (Ra) of 50 mu m, 25 mu m,12.5 mu m, 6.3 mu m, 3.2 mu m, 1.6 mu m, 0.8 mu m, and 0.4 mu m are explored. By simply sliding the sensor on the surfaces without any load and speed controller, we found that the highest classification accuracy of (82.6 +/- 10.8) % can be achieved using solely one PVDF film sensor with kNN (k = 9) classifier and the standard deviation feature, i.e., the developed approach is very affordable, robust and suitable for real time surface roughness evaluation. (C) 2017 Elsevier B.V. All rights reserved.