Control with Patterns: A D-learning Method

Quan Quan, Kai-Yuan Cai, Chenyu Wang
Proceedings of The 8th Conference on Robot Learning, PMLR 270:1384-1401, 2025.

Abstract

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 challenging 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 data sets of this kind, we introduce a new definition, namely exponential attraction on data sets, to describe nonlinear dynamical systems under consideration. The problem of exponential attraction on data sets is converted to a pattern classification one based on the data sets and parameterized Lyapunov functions. Furthermore, D-learning is proposed as a method for performing 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 only real-time images as feedback, which can be considered as an Image-Based Visual Servoing (IBVS) problem.

Cite this Paper


BibTeX
@InProceedings{pmlr-v270-quan25a, title = {Control with Patterns: A D-learning Method}, author = {Quan, Quan and Cai, Kai-Yuan and Wang, Chenyu}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {1384--1401}, year = {2025}, editor = {Agrawal, Pulkit and Kroemer, Oliver and Burgard, Wolfram}, volume = {270}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v270/main/assets/quan25a/quan25a.pdf}, url = {https://proceedings.mlr.press/v270/quan25a.html}, abstract = {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 challenging 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 data sets of this kind, we introduce a new definition, namely exponential attraction on data sets, to describe nonlinear dynamical systems under consideration. The problem of exponential attraction on data sets is converted to a pattern classification one based on the data sets and parameterized Lyapunov functions. Furthermore, D-learning is proposed as a method for performing 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 only real-time images as feedback, which can be considered as an Image-Based Visual Servoing (IBVS) problem.} }
Endnote
%0 Conference Paper %T Control with Patterns: A D-learning Method %A Quan Quan %A Kai-Yuan Cai %A Chenyu Wang %B Proceedings of The 8th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Pulkit Agrawal %E Oliver Kroemer %E Wolfram Burgard %F pmlr-v270-quan25a %I PMLR %P 1384--1401 %U https://proceedings.mlr.press/v270/quan25a.html %V 270 %X 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 challenging 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 data sets of this kind, we introduce a new definition, namely exponential attraction on data sets, to describe nonlinear dynamical systems under consideration. The problem of exponential attraction on data sets is converted to a pattern classification one based on the data sets and parameterized Lyapunov functions. Furthermore, D-learning is proposed as a method for performing 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 only real-time images as feedback, which can be considered as an Image-Based Visual Servoing (IBVS) problem.
APA
Quan, Q., Cai, K. & Wang, C.. (2025). Control with Patterns: A D-learning Method. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:1384-1401 Available from https://proceedings.mlr.press/v270/quan25a.html.

Related Material