Neural Identification for Control
Priyabrata Saha,Magnus Egerstedt,Saibal Mukhopadhyay +2 more
- Vol. 6, Iss: 3, pp 4648-4655
Reads0
Chats0
TLDR
A new method for learning control law that stabilizes an unknown nonlinear dynamical system at an equilibrium point and relies on the Lyapunov stability theory to generate a stable closed-loop dynamics hypothesis and corresponding control law is presented.Abstract:
We present a new method for learning control law that stabilizes an unknown nonlinear dynamical system at an equilibrium point. We formulate a system identification task in a self-supervised learning setting that jointly learns a controller and corresponding stable closed-loop dynamics hypothesis. The input-output behavior of the unknown dynamical system under random control inputs is used as the supervising signal to train the neural network-based system model and the controller. The proposed method relies on the Lyapunov stability theory to generate a stable closed-loop dynamics hypothesis and corresponding control law. We demonstrate our method on various nonlinear control problems such as n-link pendulum balancing and trajectory tracking, pendulum on cart balancing, and wheeled vehicle path following.read more
Citations
More filters
Proceedings ArticleDOI
Neural Lyapunov Differentiable Predictive Control
TL;DR: In this paper , a learning-based predictive control methodology using the differentiable programming framework with probabilistic Lyapunov-based stability guarantees is presented, where the policy is learned by constructing a computational graph encompassing the system dynamics, state and input constraints, and the necessary LyAPunov certification constraints.
Proceedings ArticleDOI
Neural Lyapunov Differentiable Predictive Control
TL;DR: This work presents a learning-based predictive control methodology using the differentiable programming framework with probabilistic Lyapunov-based stability guarantees, and provides a sampling-based statistical guarantee for the training of NLDPC from the distribution of initial conditions.
Journal ArticleDOI
Learning Deep Neural Network Controller for Path Following of Unicycle Robots
TL;DR: In this paper , a DNN-based controller is trained to follow paths with arbitrary curvature in two-dimensional space, and the training process does not require initialization or supervision from any other known expert controller.
Journal ArticleDOI
Learning Deep Neural Network Controller for Path Following of Unicycle Robots
TL;DR: In this paper , a DNN-based controller is trained to follow paths with arbitrary curvature in two-dimensional space, and the training process does not require initialization or supervision from any other known expert controller.
Proceedings ArticleDOI
Identification and Optimal Control of a Dynamical System via ANN-based Approaches
TL;DR: In this article, a modification of particle swarm optimization (gradient-free) method has been applied to train a neurocontroller to obtain the weights and biases of neurocontroller, the initial problem has been reduced to the unconstrained optimization problem.
References
More filters
Book
Reinforcement Learning: An Introduction
TL;DR: This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
Book
Applied Nonlinear Control
TL;DR: Covers in a progressive fashion a number of analysis tools and design techniques directly applicable to nonlinear control problems in high performance systems (in aerospace, robotics and automotive areas).
Posted Content
Proximal Policy Optimization Algorithms
TL;DR: A new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent, are proposed.
Book
Linear Optimal Control Systems
Huibert Kwakernaak,Raphael Sivan +1 more
TL;DR: In this article, the authors provide an excellent introduction to feedback control system design, including a theoretical approach that captures the essential issues and can be applied to a wide range of practical problems.
Posted Content
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision
Alex Kendall,Yarin Gal +1 more
TL;DR: A Bayesian deep learning framework combining input-dependent aleatoric uncertainty together with epistemic uncertainty is presented, which makes the loss more robust to noisy data, also giving new state-of-the-art results on segmentation and depth regression benchmarks.
Related Papers (5)
Direct-reinforcement-adaptive-learning neural network control for nonlinear systems
Y.H. Kim,F.L. Lewis +1 more