Model-Based Learning Controller Design for a Furuta Pendulum

We present a method for designing and tuning controllers for the problem of swing-up and stabilization of a Furuta pendulum. The method is based on suitable parameterization of a family of controllers and the application of Bayesian optimization to their tuning with minimal interaction with the phys...

Full description

Saved in:
Bibliographic Details
Main Authors: Nikovski, Daniel, Yerazunis, William, Goldsmith, Abraham
Format: Conference Proceeding
Language:English
Subjects:
Bayes methods
Complexity theory
Control systems
Design methodology
Information technology
Optimization methods
Reinforcement learning
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a method for designing and tuning controllers for the problem of swing-up and stabilization of a Furuta pendulum. The method is based on suitable parameterization of a family of controllers and the application of Bayesian optimization to their tuning with minimal interaction with the physical system. Unlike traditional controller design methodologies, the method does not require the derivation of an exact physical model of the controlled plant, thus saving significant design time and effort. Furthermore, the method has much more favorable sample complexity than most policy optimization methods proposed in the field of reinforcement learning.
ISSN:2576-3555
DOI:10.1109/CoDIT58514.2023.10284465