Use this URL to cite or link to this record in EThOS:
Title: Monte Carlo approaches to nonlinear optimal and model predictive control
Author: de Villiers, J. P.
Awarding Body: University of Cambridge
Current Institution: University of Cambridge
Date of Award: 2008
Availability of Full Text:
Full text unavailable from EThOS.
Please contact the current institution’s library for further details.
This work explores the novel use of advanced Monte Carlo techniques in the disciplines of nonlinear optimal and model predictive control. The interrelation between the subjects of estimation, random sampling and optimisation is exploited to expand the application of advanced numerical. Bayesian inference techniques to the control setting. Firstly, the deterministic optimal control problem is considered. Sophisticated inter-dimensional population Markov Chain Monte Carlo (MCMC) techniques are proposed to solve the nonlinear optimal control problem. The linear quadratic and Acrobot example problems are used as demonstration of the relevant techniques. Secondly, these methods are extended to the Nonlinear Model Predictive Control (NMPC) setting with uncertain state observations. In this case, two variants of the novel Particle Predictive Controller (PPC) are developed. These PPC algorithms are successfully applied to an F-16 aircraft terrain following problem.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available