Distance Estimation and Material Classification of a Compliant Tactile Sensor Using Vibration Modes and Support Vector Machine

Abstract

Many animals possess actively movable tactile sensors in their heads, to explore the near-range space. During locomotion, an antenna is used in near range orientation, for example, in detecting, localizing, probing, and negotiating obstacles. A bionic tactile sensor used in the present work was inspired by the antenna of the stick insects. The sensor is able to detect an obstacle and its location in 3D (Three dimensional) space. The vibration signals are analyzed in the frequency domain using Fast Fourier Transform (FFT) to estimate the distances. Signal processing algorithms, Artificial Neural Network (ANN) and Support Vector Machine (SVM) are used for the analysis and prediction processes. These three prediction techniques are compared for both distance estimation and material classification processes. When estimating the distances, the accuracy of estimation is deteriorated towards the tip of the probe due to the change in the vibration modes. Since the vibration data within that region have high a variance, the accuracy in distance estimation and material classification are lower towards the tip. The change in vibration mode is mathematically analyzed and a solution is proposed to estimate the distance along the full range of the probe.