PRISM helps robots move better by learning how forces and motion interact

Researchers at University of Michigan Engineering have developed a new neural network component called PRISM, which challenges a common assumption in robot learning: that general-purpose networks used for image recognition are equally suited to controlling physical movement. The component is intended to help robots move better.

Headlines are indexed or machine translated, not independent verification of scientific results. Medical news is not clinical advice. Distinguish interstellar concepts from demonstrated space technology using the original source.