(a) Structured neural network architecture with explicit inertia matrix representation. Physics-based domain knowledge is introduced into the design of neural network architecture for modeling target dynamics. (b) Two-stage dynamics modeling method for contact-rich tasks. We investigated the control performance of real-time, model-based control methods on a trackball-manipulation task using a real 3-DoF finger robot.
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.