AsianScientist (Jul. 5, 2019) – Scientists at the Center for Intelligent & Interactive Robotics of the Korea Institute of Science and Technology (KIST) have developed a method of teaching robots movements based on the muscle contractions of a human demonstrator.
Unlike traditional robots that are rigid, impedance-control robots or ‘soft’ robots are flexible and have a wider range of movements. However, programming the movements of these soft robots is complex and requires detailed coded instructions. Instead, a team of researchers led by Dr. Kim Kee-hoon used muscle signals from a human demonstrator to teach a robot how to trap a ball just like a soccer player.
Surface electromyograms (sEMGs) are electrical signals produced during muscle activation that can be picked up on the surface of the skin. The KIST research team first attached sEMG sensors to a man’s arm, allowing him to simultaneously control the location and flexibility of the robot’s rapid upward and downward movements. The man then ‘taught’ the robot how to trap a rapidly falling ball by giving a personal demonstration. After learning the movement, the robot was able to skillfully trap a dropped ball without any external assistance.
These results show that robots can be taught complex movements without the need for numerical calculations or programming. This study is expected to help advance the study of interactions between humans and robots, bringing us one step closer to a world in which robots are an integral part of our daily lives.
“The outcome of this research, which focuses on teaching human skills to robots, is an important achievement in the study of interactions between humans and robots,” Kim concluded.
———
Source: National Research Council of Science & Technology; Photo: Shutterstock.
Disclaimer: This article does not necessarily reflect the views of AsianScientist or its staff.
