2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This paper introduces Projection-Regularized Predictive Control (PRPC), retaining the fundamental-lemma weight vector via a regularized projection analytically condensed into an efficient, fixed-dimension covariance update.
This paper presents a Kernelized Data-Driven Predictive Control (KDPC) scheme for robust, offset-free tracking of nonlinear systems. To overcome the computational burden of direct data-driven methods, we employ a hybrid framework that learns the nonlinear dynamics in a Reproducing Kernel Hilbert Space (RKHS) via joint ridge regression. A key contribution is the derivation of an analytical linearization of the kernel map, which renders the control problem a strictly convex Quadratic Program (QP) for efficient real-time implementation. We provide rigorous guarantees for recursive feasibility using terminal ingredients and establish Input-to-State Stability (ISS) with respect to the kernel approximation error. Finally, a simulation study on a Van der Pol oscillator is provided to illustrate the disturbance rejection and offset-free tracking capabilities of the proposed KDPC.