Synthesis of Stabilizing Recurrent Equilibrium Network Controllers

03/31/2022
by   Neelay Junnarkar, et al.
0

We propose a parameterization of a nonlinear dynamic controller based on the recurrent equilibrium network, a generalization of the recurrent neural network. We derive constraints on the parameterization under which the controller guarantees exponential stability of a partially observed dynamical system with sector-bounded nonlinearities. Finally, we present a method to synthesize this controller using projected policy gradient methods to maximize a reward function with arbitrary structure. The projection step involves the solution of convex optimization problems. We demonstrate the proposed method with simulated examples of controlling nonlinear plants, including plants modeled with neural networks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/08/2021

Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems

Neural network controllers have become popular in control tasks thanks t...
research
04/28/2021

Communication Topology Co-Design in Graph Recurrent Neural Network Based Distributed Control

When designing large-scale distributed controllers, the information-shar...
research
12/08/2021

Learning over All Stabilizing Nonlinear Controllers for a Partially-Observed Linear System

We propose a parameterization of nonlinear output feedback controllers f...
research
12/02/2021

Youla-REN: Learning Nonlinear Feedback Policies with Robust Stability Guarantees

This paper presents a parameterization of nonlinear controllers for unce...
research
02/09/2021

Orbital Stabilization of Point-to-Point Maneuvers in Underactuated Mechanical Systems

The task of inducing, via continuous static state-feedback, an asymptoti...
research
03/22/2022

Neural System Level Synthesis: Learning over All Stabilizing Policies for Nonlinear Systems

We address the problem of designing stabilizing control policies for non...
research
06/01/2018

Learning convex bounds for linear quadratic control policy synthesis

Learning to make decisions from observed data in dynamic environments re...

Please sign up or login with your details

Forgot password? Click here to reset