EMG-based Robot Control Interfaces: Past, Present and Future

Robots are now more than ever capable of performing a plethora of demanding tasks. However, as the presence of robotic technologies in everyday life grows rapidly, the role of humans in controlling the robots becomes of utmost importance. An efficient human-robot control interface is, therefore, required. In particular, an interface that would allow the user to control a robot in a continuous way by performing natural motions with his/her arm would be very effective. Neural interfaces and especially surface electromyographic (EMG) signals were proposed more than 30 years ago for actuating prosthetic limbs. Since then, a wide-range of algorithms and hardware solutions have been proposed. Multi-fingered prosthetic hands and agile arms are now capable of mimicking the function that the human counterparts provide. However, advances in the EMG-based control of prosthetics did not proceed at the same speed. This article will give an overview of the research done on the EMG-based human-robot control interfaces, focusing on the main advantages and disadvantages of this technology. Finally, future directions of the field will be discussed.