First applications of sound-based control on a mobile robot equipped with two microphones

This paper validates experimentally a novel approach to robot audition, sound-based control, which consists in introducing auditory features directly as inputs of a closed-loop control scheme, that is, without any explicit localization process. The applications we present rely on the implicit bearings of the sound sources computed from the time difference of arrival (TDOA) between two microphones. By linking the motion of the robot to the aural perception of the environment, this approach has the benefit of being more robust to reverberation and noise. Therefore neither complex tracking method such as Kalman filtering nor TDOA enhancement with denoising or dereverberation methods are needed to track the correct TDOA measurements. The experiments conducted on a mobile robot instrumented with a pair of microphones show the validity of our approach. In a reverberating and noisy room, this approach is able to orient the robot to a mobile sound source in real time. A positioning task with respect to two sound sources is also performed while the robot perception is disturbed by altered and spurious TDOA measurements.