Terrain Classification for Autonomous Vehicles Using Bat-Inspired Echolocation

Abstract

Many types of bats use echolocation to sense their environment. Despite often have little or no visual acuity, they are able to acquire very detailed views of their surroundings through emission, receipt, and analysis of acoustic pulses. In this study autonomous navigation was examined with respect to classification of nearby terrain. The goal of this effort was to demonstrate that a bat-inspired acoustic sensor could be built, and when trained using advanced signal filtering and machine learning techniques, could be used to accurately classify terrain types for a small mobile robot. A dual channel in-air sonar was constructed using two common piezoelectric transmitter elements with 25 kHz and 32 kHz nominal center frequencies, and echo data was collected from grass, concrete, sand, and gravel terrain substrates. Higher dimension time, frequency, and time-frequency PCA scores were used to discriminate between terrain substrates. These features were used to train a support vector machine (SVM) to classify the terrain types. The SVM-based classifier was able to classify terrain types at a greater than 97% success rate using the constructed bat-inspired echolocation sensor.