Use of pattern classification algorithms to interpret acoustic echolocation data from a walking-speed robotic sensor platform

Abstract

An unresolved issue for autonomous walking-speed robots in unstructured outdoor environments is maintaining situational awareness. One strategy is combining information from different sensors so the robot can function in a variety of conditions and environments. The very low-cost Microsoft Kinect accessory incorporates active infrared and RGB video sensors to provide real-time depth information, as well as a 4-channel microphone array. We validate the Kinect sensors and investigate the combination of infrared (passive and active) and non-linear acoustic echolocation sensors on our mobile robotic sensor platform. By using an acoustic parametric array to generate the audible echolocation signal, a tightly-controlled beam of low-frequency sound can interrogate targets at long distances, while infrared imaging works well in the nearfield and in difficult weather conditions. Sophisticated signal processing techniques are required to combine and interpret the collected data; we present an example using pattern ...