A Study on Solutions to Finite-Time Optimal Control Problems by Numerical Gaussian Processes

This paper proposes solutions to finite-time optimal control problems based on numerical Gaussian processes. In the proposed method, Hamilton-Jacobi-Bellman (HJB) equations are formulated using Euler method to be solved by numerical Gaussian processes. In order to incorporate information of systems...

Full description

Saved in:
Bibliographic Details
Published in2019 12th Asian Control Conference (ASCC) pp. 399 - 404
Main Authors Beppu, Hirofumi, Maruta, Ichiro, Fujitmoto, Kenji
Format Conference Proceeding
LanguageEnglish
Published JSME 01.06.2019
Subjects
Differential equations
Dynamic programming
Gaussian distribution
Gaussian processes
Gradient methods
Mathematical model
Optimal control
Online AccessGet full text

Cover

More Information
Summary:This paper proposes solutions to finite-time optimal control problems based on numerical Gaussian processes. In the proposed method, Hamilton-Jacobi-Bellman (HJB) equations are formulated using Euler method to be solved by numerical Gaussian processes. In order to incorporate information of systems into Gaussian processes, the covariance functions are structured explicitly by HJB equations.