کنفرانس مهندسی برق ایران

صفحه اصلی / سی و یکمین کنفرانس بین المللی مهندسی برق

A reinforcement learning-based control approach for tracking problem of a class of nonlinear systems: Applied to a Single-Link Manipulator

نویسندگان :

Farshad Rahimi¹ Sepideh Ziaei² Reza Mahboobi Esfanjani³

1- دانشگاه صنعتی سهند تبریز 2- دانشگاه صنعتی سهند تبریز 3- دانشگاه صنعتی سهند تبریز

کلمات کلیدی :

neural networks،adaptive control،nonlinear system،adversarial attacks

چکیده :

This paper introduces a reinforcement learning-based tracking control approach for a class of nonlinear systems using neural networks in the presence of adversarial attacks. This approach incorporates a simultaneous tracking and optimization process. It is necessary to be able to solve the Hamilton-Jacobi-Bellman equation (HJB) in order to obtain optimal control input, but this is difficult due to the strong nonlinearity terms in the equation. In order to find the solution to the HJB equation, we used a reinforcement learning approach. In this online adaptive learning approach, three neural networks are simultaneously adapted: the critic neural network, the actor neural network, and the adversary neural network. Ultimately, simulation results are presented to demonstrate the effectiveness of the introduced method on a manipulator.

لیست مقالات

لیست مقالات بایگانی شده

Computational Insights into the Superior Performance of ψ-Graphene in Li-S Batteries: A DFT Study

Donna Rashidi - Maryam Abbasi - Leila Sadeghbeigy - Matin Bakhtavari - Ebrahim Nadimi

A Novel Method to Estimate Thevenin Equivalent Circuit Using Local Measurements

Pouria Akbarzadeh Aghdam - Hamid Khoshkhoo

Robust Object Detection Against Adversarial Perturbations with Gabor Filter

Mohammad Parsa Karimi - Abdollah Amirkhani - Shahriar B. Shokouhi

طراحی قانون رویداد-تحریک دینامیکی برای سیستم های سینگولار خطی به منظور کاهش تعداد بروزرسانی

سیدمحمدرضا احمدانجوی - طاهره بینازاده

A High Linearity Wideband Low-Noise Amplifier Using Capacitor Cross-Coupled Common-Gate Structure

Abolfazl Rajaiyan - Fahimeh Rahimi - Mehdi Saberi

Transfer Learning Based Method for Human Activity Recognition

Saeedeh Zebhi - Smt Almodarresi - Vahid Abootalebi

شناسایی گره‌های مهم سیستم قدرت با استفاده از ابزار شبکه‌های پیچیده و مرکزیت‌های مبتنی بر تشخیص جامعه

سپهر مردانی - علی کریمی - مهران معماری

MoS2 Grating on a Grounded Periodic SiO2 as a Wideband THz Absorber

Mohammad Amin Zolghadr - Mahmood Rafaei Booket

Classifying Human Spatial Navigation Anxiety Using Electrooculography Signals and Machine Learning Techniques

Saeed Mousavi - Sara Ashrafi - Mehdi Delrobaei

Incentive-based Demand Response Economic Model for Peak Shaving Considering Load Serving Entity Profit Maximization

Nasim EslamiNia - Habib RajabiMashhdi

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.3