CaltechAUTHORS
  A Caltech Library Service

Neural Contraction Metrics for Robust Estimation and Control: A Convex Optimization Approach

Tsukamoto, Hiroyasu and Chung, Soon-Jo (2021) Neural Contraction Metrics for Robust Estimation and Control: A Convex Optimization Approach. IEEE Control Systems Letters, 5 (1). pp. 211-216. ISSN 2475-1456. https://resolver.caltech.edu/CaltechAUTHORS:20200624-155134352

[img] PDF - Published Version
Creative Commons Attribution.

1264Kb
[img] PDF - Submitted Version
See Usage Policy.

1362Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200624-155134352

Abstract

This letter presents a new deep learning-based framework for robust nonlinear estimation and control using the concept of a Neural Contraction Metric (NCM). The NCM uses a deep long short-term memory recurrent neural network for a global approximation of an optimal contraction metric, the existence of which is a necessary and sufficient condition for exponential stability of nonlinear systems. The optimality stems from the fact that the contraction metrics sampled offline are the solutions of a convex optimization problem to minimize an upper bound of the steady-state Euclidean distance between perturbed and unperturbed system trajectories. We demonstrate how to exploit NCMs to design an online optimal estimator and controller for nonlinear systems with bounded disturbances utilizing their duality. The performance of our framework is illustrated through Lorenz oscillator state estimation and spacecraft optimal motion planning problems.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/lcsys.2020.3001646DOIArticle
https://arxiv.org/abs/2006.04361arXivDiscussion Paper
ORCID:
AuthorORCID
Chung, Soon-Jo0000-0002-6657-3907
Additional Information:© 2020 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 License. Manuscript received March 17, 2020; revised May 15, 2020; accepted June 4, 2020. Date of publication June 11, 2020; date of current version June 24, 2020. This work was supported in part by the Jet Propulsion Laboratory, California Institute of Technology and in part by the Raytheon Company. Recommended by Senior Editor G. Cherubini.
Group:GALCIT, Center for Autonomous Systems and Technologies (CAST)
Funders:
Funding AgencyGrant Number
JPL/CaltechUNSPECIFIED
Raytheon CompanyUNSPECIFIED
Subject Keywords:Machine learning, Observers for nonlinear systems, Optimal control
Issue or Number:1
Record Number:CaltechAUTHORS:20200624-155134352
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200624-155134352
Official Citation:H. Tsukamoto and S. Chung, "Neural Contraction Metrics for Robust Estimation and Control: A Convex Optimization Approach," in IEEE Control Systems Letters, vol. 5, no. 1, pp. 211-216, Jan. 2021, doi: 10.1109/LCSYS.2020.3001646
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:104021
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:25 Jun 2020 14:33
Last Modified:06 Jul 2020 21:00

Repository Staff Only: item control page