skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Concurrent Learning and Lyapunov-Based Updates of Deep Neural Networks for Euler-Lagrange Dynamic Systems
This paper presents a deep neural network (DNN)-and concurrent learning (CL)-based adaptive control architecture for an Euler-Lagrange dynamic system that guarantees system performance for the first time. The developed controller includes two DNNs with the same output-layer weights to ensure feasibility of the control system. In this work, a Lyapunov-and CL-based update law is developed to update the output-layer DNN weights in real-time; whereas, the inner-layer DNN weights are updated offline using data that is collected in real-time. A Lyapunov-like analysis is performed to prove that the proposed controller yields semi-global exponential convergence to an ultimate bound for the output-layer weight estimation errors and for the trajectory tracking errors.  more » « less
Award ID(s):
2230971
PAR ID:
10562221
Author(s) / Creator(s):
; ; ;
Publisher / Repository:
IEEE
Date Published:
ISBN:
979-8-3503-8265-5
Page Range / eLocation ID:
15 to 20
Subject(s) / Keyword(s):
Deep Neural Networks (DNNs) Concurrent Learning (CL) Euler-Lagrange dynamics Lyapunov methods
Format(s):
Medium: X
Location:
Toronto, ON, Canada
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, IEEE)
    A deep neural network (DNN)-based adaptive controller with a real-time and concurrent learning (CL)-based adaptive update law is developed for a class of uncertain, nonlinear dynamic systems. The DNN in the control law is used to approximate the uncertain nonlinear dynamic model. The inner-layer weights of the DNN are updated offline using data collected in real-time; whereas, the output-layer DNN weights are updated online (i.e., in real-time) using the Lyapunov- and CL-based adaptation law. Specifically, the inner-layer weights of the DNN are trained offline (concurrent to real-time execution) after a sufficient amount of data is collected in real-time to improve the performance of the system, and after training is completed the inner-layer DNN weights are updated in batch-updates. The key development in this work is that the output-layer DNN update law is augmented with CL-based terms to ensure that the output-layer DNN weight estimates converge to within a ball of their optimal values. A Lyapunov-based stability analysis is performed to ensure semi-global exponential convergence to an ultimate bound for the trajectory tracking errors and the output-layer DNN weight estimation errors. 
    more » « less
  2. ; ; (, American Society of Mechanical Engineers)
    Hybrid exoskeletons are used to blend the rehabilitative efficacy and mitigate the shortcomings of functional electrical stimulation (FES) and exoskeleton-based rehabilitative solutions. This paper introduces a novel nonlinear controller that may potentially improve the rehabilitative efficiency of a lower limb hybrid exoskeleton by implementing four key features into the FES and exoskeleton controllers. First, the FES input to the user’s muscles is saturated based on user preference to ensure user comfort. Second, rather than discarding the excess control effort from the saturated FES input, it is redirected into the exoskeleton’s motor controller. Third, a safe deep neural network (DNN) is designed to estimate the unknown dynamics of the hybrid exoskeleton and the DNN is implemented in the FES controller to improve the control efficiency and tracking performance. Fourth, an adaptive update law is designed to estimate the unknown muscle control effectiveness to facilitate the implementation of the DNN. Lyapunov stability-based methods are used to generate real-time adaptive update laws that will train the adaptive estimate of the muscle effectiveness and the output layer weights of the DNN in real-time, ensure the effectiveness and safety of the controllers, and prove global asymptotic tracking of the desired trajectory. 
    more » « less
  3. ; ; (, International Journal of Control)
    This paper addresses the problem of hybrid control for a class of switched uncertain systems. The switched system under consideration is subject to structured uncertain dynamics in a linear fractional transformation (LFT) form and time-varying input delays. A novel hybrid controller is proposed, which consists of three major components: the integral quadratic constraint (IQC) dynamics, the continuous dynamics, and the jump dynamics. The IQC dynamics are developed by leveraging methodologies from robust control theory and are utilised to address the effects of time-varying input delays. The continuous dynamics are structured by feeding back not only measurement outputs but also some system's internal signals. The jump dynamics enforce a jump (update/reset) at every switching time instant for the states of both IQC dynamics and continuous dynamics. Based on this, robust stability of the overall hybrid closed-loop system is established under the average dwell time framework with multiple Lyapunov functions. Moreover, the associated control synthesis conditions are fully characterised as linear matrix inequalities, which can be solved efficiently. An application example on regulation of a nonlinear switched electronic circuit system has been used to demonstrate effectiveness and usefulness of the proposed approach. 
    more » « less
  4. (, UTD Theses and Dissertations)
    Tweezers-based nanorobots, optical tweezers in particular, are renowned for their exceptional precision, and among their biomedical applications are cellular manipulation, unzipping DNAs, and elongating polypeptide chains. This thesis introduces a series of Lyapunov-based feedback control frameworks that address both stability and controlled instability for biological manipulation, applied within the context of optical tweezers. At the core of this work are novel controllers that stabilize or destabilize specific molecular configurations, enabling fine manipulation of particles like polystyrene beads and tethered polymers under focused laser beams. Chapter 1 covers the foundational principles and surveys existing literature on the modeling and control of optical tweezers, emphasizing gaps in the stability and instability control of molecular systems. Chapter 2 presents a robust Control Lyapunov Function (CLF) approach, designed to stabilize spherical particles under optical trapping. By formulating a smooth, norm-bounded feedback controller, we achieve lateral stabilization despite external disturbances, using a real-time, static nonlinear programming (NLP) solution. Simulations verify the effectiveness of this CLF framework, even with significant initial displacements from the laser focus and under thermal forces modeled as a white Gaussian noise. Chapter 3 addresses controlled instability through a Control Chetaev Function (CCF) framework, specifically targeting protein unfolding applications. Linearization with respect to the control input facilitates the application of destabilizing universal controls for affine- in-control system dynamics. The resulting CCF-based norm-bounded feedback controller induces system instability by laterally extending the trapped DNA handle, thereby increasing the molecular extension and providing insights into protein denaturation and unfolding pathways. This controller is robust to stochastic thermal forces and optimized for real-time computational efficiency. These Lyapunov and Chetaev-based control designs collectively expand the capabilities of optical tweezers, advancing single-molecule manipulation under both stable and unstable conditions. These findings advance precision nanomanipulation, opening new avenues for exploring the molecular mechanics of protein unfolding and DNA elasticity. 
    more » « less
  5. ; ; (, American Control Conference (ACC))
    We present an analytical design and experimental verification of trajectory tracking control of a 7-DOF robot manipulator, which achieves convergence of all tracking errors to the origin within a finite terminal time. A key feature of this control strategy is that this terminal convergence time is explicitly prescribed by the control designer, and is thus independent of the initial conditions of the tracking errors. In order to achieve this beneficial property of the proposed controller, a scaling of the state by a function of time that grows unbounded towards the terminal time is employed. Through Lyapunov analysis, we first demonstrate that the proposed controller achieves regulation of all tracking errors within the prescribed time as well as the uniform boundedness of the joint torques, even in the presence of a matched, non-vanishing disturbance. Then, through both simulation and experiment, we demonstrate that the proposed controller is capable of converging to the desired trajectory within the prescribed time, despite large initial conditions of the tracking errors and a sinusoidal disturbance being applied in each joint. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email