Saved in:
Bibliographic Details
Main Authors: Quan, Quan, Cai, Kai-Yuan, Wang, Chenyu
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2206.03809
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915753592094720
author Quan, Quan
Cai, Kai-Yuan
Wang, Chenyu
author_facet Quan, Quan
Cai, Kai-Yuan
Wang, Chenyu
contents Learning-based control policies are widely used in various tasks in the field of robotics and control. However, formal (Lyapunov) stability guarantees for learning-based controllers with nonlinear dynamical systems are difficult to obtain. We propose a novel control approach, namely Control with Patterns (CWP), to address the stability issue over data sets corresponding to nonlinear dynamical systems. For such data sets, we introduce a new definition, namely exponential attraction on data sets, to describe the nonlinear dynamical systems under consideration. The problem of exponential attraction on data sets is transformed into a problem of pattern classification one based on the data sets and parameterized Lyapunov functions. Furthermore, D-learning is proposed as a method to perform CWP without knowledge of the system dynamics. Finally, the effectiveness of CWP based on D-learning is demonstrated through simulations and real flight experiments. In these experiments, the position of the multicopter is stabilized using real-time images as feedback, which can be considered as an Image-Based Visual Servoing (IBVS) problem.
format Preprint
id arxiv_https___arxiv_org_abs_2206_03809
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Control with Patterns: A D-learning Method
Quan, Quan
Cai, Kai-Yuan
Wang, Chenyu
Robotics
Learning-based control policies are widely used in various tasks in the field of robotics and control. However, formal (Lyapunov) stability guarantees for learning-based controllers with nonlinear dynamical systems are difficult to obtain. We propose a novel control approach, namely Control with Patterns (CWP), to address the stability issue over data sets corresponding to nonlinear dynamical systems. For such data sets, we introduce a new definition, namely exponential attraction on data sets, to describe the nonlinear dynamical systems under consideration. The problem of exponential attraction on data sets is transformed into a problem of pattern classification one based on the data sets and parameterized Lyapunov functions. Furthermore, D-learning is proposed as a method to perform CWP without knowledge of the system dynamics. Finally, the effectiveness of CWP based on D-learning is demonstrated through simulations and real flight experiments. In these experiments, the position of the multicopter is stabilized using real-time images as feedback, which can be considered as an Image-Based Visual Servoing (IBVS) problem.
title Control with Patterns: A D-learning Method
topic Robotics
url https://arxiv.org/abs/2206.03809