Abstract
In this article, the authors propose a novel continuous projected kinky inference algorithm, which inherits the good properties of projected kinky inference in terms of prediction error bound and computational time while ensuring Lipschitz continuity. Based on this, a learning based MPC is presented which is demonstrated to be input-to-state stable by design. Illustrative examples are shown in a learning-based MPC framework.
International Journal of Robust and Nonlinear Control, Volume 35, Issue 7, Page 2521-2536, 10 May 2025. Read More
