Denoising Diffusion-Based Control of Nonlinear Systems
- URL: http://arxiv.org/abs/2402.02297v1
- Date: Sat, 3 Feb 2024 23:19:26 GMT
- Title: Denoising Diffusion-Based Control of Nonlinear Systems
- Authors: Karthik Elamvazhuthi, Darshan Gadginmath, Fabio Pasqualetti
- Abstract summary: We propose a novel approach based on Denoising Diffusion Probabilistic Models (DDPMs) to control nonlinear dynamical systems.
DDPMs are the state-of-art of generative models that have achieved success in a wide variety of sampling tasks.
We numerically study our approach on various nonlinear systems and verify our theoretical results.
- Score: 3.4530027457862
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We propose a novel approach based on Denoising Diffusion Probabilistic Models
(DDPMs) to control nonlinear dynamical systems. DDPMs are the state-of-art of
generative models that have achieved success in a wide variety of sampling
tasks. In our framework, we pose the feedback control problem as a generative
task of drawing samples from a target set under control system constraints. The
forward process of DDPMs constructs trajectories originating from a target set
by adding noise. We learn to control a dynamical system in reverse such that
the terminal state belongs to the target set. For control-affine systems
without drift, we prove that the control system can exactly track the
trajectory of the forward process in reverse, whenever the the Lie bracket
based condition for controllability holds. We numerically study our approach on
various nonlinear systems and verify our theoretical results. We also conduct
numerical experiments for cases beyond our theoretical results on a
physics-engine.
Related papers
- A Deep Learning Technique to Control the Non-linear Dynamics of a
Gravitational-wave Interferometer [0.0]
We developed a deep learning technique that successfully solves a non-linear dynamic control problem.
We applied this technique to a crucial non-linear control problem that arises in the operation of the LIGO system.
We also developed a computationally efficient model that can run in real time at high sampling rate on a single modern CPU core.
arXiv Detail & Related papers (2023-02-15T19:47:56Z) - In-Distribution Barrier Functions: Self-Supervised Policy Filters that
Avoid Out-of-Distribution States [84.24300005271185]
We propose a control filter that wraps any reference policy and effectively encourages the system to stay in-distribution with respect to offline-collected safe demonstrations.
Our method is effective for two different visuomotor control tasks in simulation environments, including both top-down and egocentric view settings.
arXiv Detail & Related papers (2023-01-27T22:28:19Z) - An Offset-Free Nonlinear MPC scheme for systems learned by Neural NARX
models [0.803314610321292]
This paper deals with the design of nonlinear MPC controllers that provide offset-free setpoint tracking.
The proposed scheme attains remarkable performances even in presence of disturbances acting on the plant.
arXiv Detail & Related papers (2022-03-30T13:30:07Z) - Sparsity in Partially Controllable Linear Systems [56.142264865866636]
We study partially controllable linear dynamical systems specified by an underlying sparsity pattern.
Our results characterize those state variables which are irrelevant for optimal control.
arXiv Detail & Related papers (2021-10-12T16:41:47Z) - Deep Learning Explicit Differentiable Predictive Control Laws for
Buildings [1.4121977037543585]
We present a differentiable predictive control (DPC) methodology for learning constrained control laws for unknown nonlinear systems.
DPC poses an approximate solution to multiparametric programming problems emerging from explicit nonlinear model predictive control (MPC)
arXiv Detail & Related papers (2021-07-25T16:47:57Z) - Robust Data-Driven Predictive Control using Reachability Analysis [6.686241050151697]
We present a robust data-driven control scheme for unknown linear systems with a bounded process and measurement noise.
The data-driven reachable regions are computed based on only noisy input-output data of a trajectory of the system.
In the noise-free case, we prove that the presented purely data-driven control scheme results in an equivalent closed-loop behavior to a nominal model predictive control scheme.
arXiv Detail & Related papers (2021-03-25T19:55:15Z) - Controlling nonlinear dynamical systems into arbitrary states using
machine learning [77.34726150561087]
We propose a novel and fully data driven control scheme which relies on machine learning (ML)
Exploiting recently developed ML-based prediction capabilities of complex systems, we demonstrate that nonlinear systems can be forced to stay in arbitrary dynamical target states coming from any initial state.
Having this highly flexible control scheme with little demands on the amount of required data on hand, we briefly discuss possible applications that range from engineering to medicine.
arXiv Detail & Related papers (2021-02-23T16:58:26Z) - Data-Driven System Level Synthesis [2.335152769484957]
We show that optimization problems over system-responses can be posed using only libraries of past system trajectories.
We first consider the idealized setting of noise free trajectories, and show an exact equivalence between traditional and data-driven SLS.
We then show that in the case of a system driven by process noise, tools from robust SLS can be used to characterize the effects of noise on closed-loop performance.
arXiv Detail & Related papers (2020-11-20T22:52:29Z) - Gaussian Process-based Min-norm Stabilizing Controller for
Control-Affine Systems with Uncertain Input Effects and Dynamics [90.81186513537777]
We propose a novel compound kernel that captures the control-affine nature of the problem.
We show that this resulting optimization problem is convex, and we call it Gaussian Process-based Control Lyapunov Function Second-Order Cone Program (GP-CLF-SOCP)
arXiv Detail & Related papers (2020-11-14T01:27:32Z) - How Training Data Impacts Performance in Learning-based Control [67.7875109298865]
This paper derives an analytical relationship between the density of the training data and the control performance.
We formulate a quality measure for the data set, which we refer to as $rho$-gap.
We show how the $rho$-gap can be applied to a feedback linearizing control law.
arXiv Detail & Related papers (2020-05-25T12:13:49Z) - Adaptive Control and Regret Minimization in Linear Quadratic Gaussian
(LQG) Setting [91.43582419264763]
We propose LqgOpt, a novel reinforcement learning algorithm based on the principle of optimism in the face of uncertainty.
LqgOpt efficiently explores the system dynamics, estimates the model parameters up to their confidence interval, and deploys the controller of the most optimistic model.
arXiv Detail & Related papers (2020-03-12T19:56:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.