Josie Hughes from the 2014 cohort has developed a robotic hand which mimics the movements of a human hand to play piano. Using soft and rigid parts the robotic hand helps to understand the complex movements of the human hand.
This robotic hand was developed by Josie Hughes, Perla Maiolino and Fumiya Iida from the Biologically Inspired Robotics Group at the Engineering Department, University of Cambridge.
While the bones and ligaments have been replicated in the robotic hand it cannot move its fingers independently. Still, by just changing the hands position and rotating it around its wrist it can play simple tunes on the piano.
Please allow social and marketing cookies to show embedded content.
The aim of the research is to understand the role of physical design in the development of robots without relying on active control.
Josie comments that the research can be extended to investigate how even more complex manipulation tasks we can be achieved, e.g. developing robots which can perform medical procedures or handle fragile objects. She says: “This approach also reduces the amount of machine learning required to control the hand; by developing mechanical systems with intelligence built in, it makes control much easier for robots to learn.”
Read more here.
J.A.E. Hughes, P. Maiolino, F. Iida. ‘An Anthropomorphic Soft Skeleton Hand Exploiting Conditional Models for Piano Playing.’ Science Robotics (2018). DOI: 10.1126/scirobotics.aau3098