We present an autonomous spatial voice localization crawling robot, namely Spidey, demonstrating the potential of assistive technology for people with visual impairment to ask for help whenever they are in a spatial area without physical assistance. The sound source localization is implemented using Generalized Cross-Correlation Phase Transform (GCC-PHAT) and Voice Activity Detection. The robot could hear where the sound source (human voice) comes from in space, simultaneously adjust itself to the angle of arrival of sound, and go towards the sound source location.
For more details, please refer my post at 2022 HackMIT and the video demo on my YouTube channel.
