We introduce a newly developed robotic musician designed to play an acoustic guitar in a rich and expressive manner. Unlike previous robotic guitarists, our Expressive Robotic Guitarist (ERG) is designed to play a commercial acoustic guitar while controlling a wide dynamic range, millisecond-level note generation, and a variety of playing techniques such as strumming, picking, overtones, and hammer-ons. To allow for these functionalities, we recorded and modeled human guitarists and implemented our findings in hardware and software design. The ERG's final construction includes a robotic co-bot arm for strumming and plucking, as well as a 12-motor fret-shifting module that can move across the guitar bridge. We evaluated the ERG dynamic range, speed, microtiming control, and guitar techniques using both objective and subjective methods. The objective benchmarks and subjective ratings demonstrate that the ERG can perform with human-level expressivity.Authors: Ning Yang, Amit Rogel, and Gil WeinbergInstitution: Georgia Tech
