Search Results for author: Peter Seiler

Found 21 papers, 7 papers with code

Synthesizing Neural Network Controllers with Closed-Loop Dissipativity Guarantees

no code implementations10 Apr 2024 Neelay Junnarkar, Murat Arcak, Peter Seiler

Finally, this convex condition is used in a projection-based training method to synthesize neural network controllers with dissipativity guarantees.

Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra

no code implementations4 Apr 2024 Darioush Kevian, Usman Syed, Xingang Guo, Aaron Havens, Geir Dullerud, Peter Seiler, Lianhui Qin, Bin Hu

In this paper, we explore the capabilities of state-of-the-art large language models (LLMs) such as GPT-4, Claude 3 Opus, and Gemini 1. 0 Ultra in solving undergraduate-level control problems.

Model-Free $μ$-Synthesis: A Nonsmooth Optimization Perspective

no code implementations18 Feb 2024 Darioush Keivan, Xingang Guo, Peter Seiler, Geir Dullerud, Bin Hu

Built upon such a policy optimization persepctive, our paper extends these subgradient-based search methods to a model-free setting.

Frequency-domain Gaussian Process Models for $H_\infty$ Uncertainties

no code implementations15 Dec 2023 Alex Devonport, Peter Seiler, Murat Arcak

We then establish how an $H_\infty$ Gaussian process can serve as a prior for Bayesian system identification and as a probabilistic uncertainty model for probabilistic robust control.

Gaussian Processes

Learning Reduced-Order Linear Parameter-Varying Models of Nonlinear Systems

1 code implementation11 Dec 2023 Patrick J. W. Koelewijn, Rajiv Sing, Peter Seiler, Roland Tóth

In this paper, we consider the learning of a Reduced-Order Linear Parameter-Varying Model (ROLPVM) of a nonlinear dynamical system based on data.

On the convexity of static output feedback control synthesis for systems with lossless nonlinearities

no code implementations6 Jul 2023 Talha Mushtaq, Peter Seiler, Maziar S. Hemati

Computing a stabilizing static output-feedback (SOF) controller is an NP-hard problem, in general.

Trajectory-based Robustness Analysis for Nonlinear Systems

no code implementations11 Feb 2023 Peter Seiler, Raghu Venkataraman

This paper considers the robustness of an uncertain nonlinear system along a finite-horizon trajectory.

Frequency Domain Gaussian Process Models for $H^\infty$ Uncertainties

no code implementations29 Nov 2022 Alex Devonport, Peter Seiler, Murat Arcak

Complex-valued Gaussian processes are used in Bayesian frequency-domain system identification as prior models for regression.

Gaussian Processes regression

Structured Singular Value of a Repeated Complex Full-Block Uncertainty

no code implementations11 Nov 2022 Talha Mushtaq, Diganta Bhattacharjee, Peter Seiler, Maziar S. Hemati

Existing algorithms compute upper and lower bounds on the SSV for structured uncertainties that contain repeated (real or complex) scalars and/or non-repeated complex full blocks.

Computational Efficiency

Synthesis of Stabilizing Recurrent Equilibrium Network Controllers

1 code implementation31 Mar 2022 Neelay Junnarkar, He Yin, Fangda Gu, Murat Arcak, Peter Seiler

We propose a parameterization of a nonlinear dynamic controller based on the recurrent equilibrium network, a generalization of the recurrent neural network.

Policy Gradient Methods

Revisiting PGD Attacks for Stability Analysis of Large-Scale Nonlinear Systems and Perception-Based Control

no code implementations3 Jan 2022 Aaron Havens, Darioush Keivan, Peter Seiler, Geir Dullerud, Bin Hu

We show that the ROA analysis can be approximated as a constrained maximization problem whose goal is to find the worst-case initial condition which shifts the terminal state the most.

On the Necessity and Sufficiency of Discrete-Time O'Shea-Zames-Falb Multipliers

no code implementations14 Dec 2021 Lanlan Su, Peter Seiler, Joaquin Carrasco, Sei Zhen Khong

Roughly speaking, a successful proof of the conjecture would require: (a) a conic parameterization of a set of multipliers that describes exactly the set of nonlinearities, (b) a lossless S-procedure to show that the non-existence of a multiplier implies that the Lurye system is not uniformly robustly stable over the set of nonlinearities, and (c) the existence of a multiplier in the set of multipliers used in (a) implies the existence of an LTI multiplier.

Model-Free $μ$ Synthesis via Adversarial Reinforcement Learning

no code implementations30 Nov 2021 Darioush Keivan, Aaron Havens, Peter Seiler, Geir Dullerud, Bin Hu

We build a connection between robust adversarial RL and $\mu$ synthesis, and develop a model-free version of the well-known $DK$-iteration for solving state-feedback $\mu$ synthesis with static $D$-scaling.

reinforcement-learning Reinforcement Learning (RL)

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

1 code implementation8 Sep 2021 Fangda Gu, He Yin, Laurent El Ghaoui, Murat Arcak, Peter Seiler, Ming Jin

Neural network controllers have become popular in control tasks thanks to their flexibility and expressivity.


Estimating Regions of Attraction for Transitional Flows using Quadratic Constraints

no code implementations9 Mar 2021 Aniketh Kalur, Talha Mushtaq, Peter Seiler, Maziar S. Hemati

This approach reduces conservatism and improves estimates for regions of attraction and bounds on permissible perturbation amplitudes over related methods that employ quadratic constraints on spherical sets.

Fluid Dynamics

Imitation Learning with Stability and Safety Guarantees

1 code implementation16 Dec 2020 He Yin, Peter Seiler, Ming Jin, Murat Arcak

A method is presented to learn neural network (NN) controllers with stability and safety guarantees through imitation learning (IL).

Imitation Learning

Finite Horizon Robust Synthesis Using Integral Quadratic Constraints

1 code implementation2 Jun 2020 Jyot Buch, Peter Seiler

We present a robust synthesis algorithm for uncertain linear time-varying (LTV) systems on finite horizons.

Analysis of Biased Stochastic Gradient Descent Using Sequential Semidefinite Programs

no code implementations3 Nov 2017 Bin Hu, Peter Seiler, Laurent Lessard

We present a convergence rate analysis for biased stochastic gradient descent (SGD), where individual gradient updates are corrupted by computation errors.

Cannot find the paper you are looking for? You can Submit a new open access paper.