Výsledky vyhledávání - "Fahimi Farbod"

Akademický článek

Variable sampling time discrete sliding mode control for a flapping wing micro air vehicle using flapping frequency as the control input

Autor: Hill Joshua, Fahimi Farbod

Publikováno v: Nonlinear Engineering, Vol 13, Iss 1, Pp 200-5 (2024)

In this article, two main assumptions commonly used in the reported literature are relaxed. First, instead of a continuous time controller, a discrete time controller is proposed. Second, the controller uses the flapping frequency as opposed to flapp

Externí odkaz: https://doaj.org/article/d2b9f93f65794245bdf3a7673b89999c

Zobrazit plný text záznamu

Akademický článek

Nonlinear adaptive sliding mode control with application to quadcopters

Autor: Mathewson Ryan, Fahimi Farbod

Publikováno v: Nonlinear Engineering, Vol 12, Iss 1, Pp p. 115-25 (2023)

Nonlinear adaptive sliding mode control (NASMC) has the capability to adequately control a system whose parameters are unknown to the controller designer. Conventional model-based controllers require a mathematical dynamic model of the system with kn

Externí odkaz: https://doaj.org/article/94eefd2e28484819903850aa373a9db3

Zobrazit plný text záznamu

Akademický článek

Vision-Based CubeSat Closed-Loop Formation Control in Close Proximities

Autor: Fahimi Farbod

Publikováno v: Nonlinear Engineering, Vol 8, Iss 1, Pp 609-618 (2019)

A vision based formation and attitude controller has been derived and simulated for the formation keeping of two 3U CubeSats. Four markers are installed on the leader CubeSat. Two cameras are installed on the follower CubeSat. An efficient vision bas

Externí odkaz: https://doaj.org/article/79e0f9e04cf543d7bb69b056dce2dbc7

Zobrazit plný text záznamu

Report

Control-Theoretic Techniques for Online Adaptation of Deep Neural Networks in Dynamical Systems

Autor: Elkins, Jacob G., Fahimi, Farbod

Deep neural networks (DNNs), trained with gradient-based optimization and backpropagation, are currently the primary tool in modern artificial intelligence, machine learning, and data science. In many applications, DNNs are trained offline, through s

Externí odkaz: http://arxiv.org/abs/2402.00761