Kernel-Based Hamilton–Jacobi Equations for Data-Driven Optimal and H-Infinity Control

Abstract

This paper presents a data-driven method for designing optimal controllers and robust controllers for unknown nonlinear systems. Mathematical models for the realization of the control are difficult to develop owing to a lack of knowledge regarding such systems. The proposed multidisciplinary method, based on optimal control theory and machine learning with kernel functions, facilitates designing appropriate controllers using a data set. Kernel-based system models are useful for representing nonlinear systems. An optimal and an H-infinity controller can be designed by solving Hamilton-Jacobi (HJ) equations, which unfortunately, are difficult to solve owing to the nonlinearity and complexity of the kernelbased models. The objective of this study consists of overcoming two challenges. The first challenge is to derive exact solutions to the HJ equations for a class of kernel-based system models. A key technique in overcoming this challenge is to reduce the HJ equations to easily solvable algebraic matrix equations, from which optimal and H-infinity controllers are designed. The second challenge is to control an unknown system using the obtained controllers, wherein the system is identified as a kernel-based model. Additionally, this study analyzes probabilistic stability of the feedback system with the proposed controllers. Numerical simulations demonstrate control performances of both the derived optimal and Hinfinity controllers and stability of the feedback system.

On First Integrals of Hamiltonian System with Holonomic Hamiltonian

“…However, for nonlinear systems, the HJE is formulated as a nonlinear partial differential equation (PDE), which is difficult to solve analytically. Numerical solution methods for the HJE have been studied based on various mathematical techniques, such as series expansion [5], expansion with basis functions [6], and data-driven approximation [7].…”

“…, with any fixed ¯ ∈ . The inverse −1 B ( ) can be defined as the first component of ; −1 ¯ ( ¯ ) can be defined as the unique solution of (7) with boundary condition ( ¯ ) = ¯ . When = P 1 , .…”

Cooperative Target Tracking by Multiagent Camera Sensor Networks via Gaussian Process

“…The authors in [13] considered a PD-plus-feedforward control approach to establish uniform ultimate boundedness of tracking errors of robot manipulators. The approaches by sliding mode control [14], [15] and H ∞ control [16], [17] have also been widely investigated.…”

Gaussian process-based visual pursuit control with unknown target motion learning in three dimensions

“…In Ref. [11][12][13][14], a GP model is utilized to learn the unknown dynamics and to analyse control performance and stability. By using the mean function of a GP model in a feed-forward manner, Beckers et al [13] aims to eliminate unmodelled dynamics and further provide a method to adjust the error feedback gains based on the GP variance.…”