Introduction To Intelligent Control

Slides:



Advertisements
Similar presentations
Artificial Intelligence 12. Two Layer ANNs
Advertisements

ARCHITECTURES FOR ARTIFICIAL INTELLIGENCE SYSTEMS
Rule extraction in neural networks. A survey. Krzysztof Mossakowski Faculty of Mathematics and Information Science Warsaw University of Technology.
Multilayer Perceptrons 1. Overview  Recap of neural network theory  The multi-layered perceptron  Back-propagation  Introduction to training  Uses.
Computer Science Department FMIPA IPB 2003 Neural Computing Yeni Herdiyeni Computer Science Dept. FMIPA IPB.
Computer Intelligence and Soft Computing
Class Discussion Chapter 2 Neural Networks. Top Down vs Bottom Up What are the differences between the approaches to AI in chapter one and chapter two?
Fuzzy Logic Based on a system of non-digital (continuous & fuzzy without crisp boundaries) set theory and rules. Developed by Lotfi Zadeh in 1965 Its advantage.
AI – CS364 Hybrid Intelligent Systems Overview of Hybrid Intelligent Systems 07 th November 2005 Dr Bogdan L. Vrusias
Intelligent Systems Group Emmanuel Fernandez Larry Mazlack Ali Minai (coordinator) Carla Purdy William Wee.
Soft Computing 1 Neuro-Fuzzy and Soft Computing chapter 1 J.-S.R. Jang Bill Cheetham Kai Goebel.
WELCOME TO THE WORLD OF FUZZY SYSTEMS. DEFINITION Fuzzy logic is a superset of conventional (Boolean) logic that has been extended to handle the concept.
The Equivalence between fuzzy logic controllers and PD controllers for single input systems Professor: Chi-Jo Wang Student: Nguyen Thi Hoai Nam Student.
A FUZZY LOGIC BASED MULTIPLE REFERENCE MODEL ADAPTIVE CONTROL (MRMAC) By Sukumar Kamalasadan, Adel A Ghandakly Khalid S Al-Olimat Dept. of Electrical Eng.
CHAPTER 12 ADVANCED INTELLIGENT SYSTEMS © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang.
Management in complexity The exploration of a new paradigm Complexity in computing and AI Walter Baets, PhD, HDR Associate Dean for Innovation and Social.
Artificial Neural Nets and AI Connectionism Sub symbolic reasoning.
An Introduction to Artificial Intelligence and Knowledge Engineering N. Kasabov, Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering,
 The most intelligent device - “Human Brain”.  The machine that revolutionized the whole world – “computer”.  Inefficiencies of the computer has lead.
Artificial Neural Networks An Overview and Analysis.
10/6/2015 1Intelligent Systems and Soft Computing Lecture 0 What is Soft Computing.
5. Alternative Approaches. Strategic Bahavior in Business and Econ 1. Introduction 2. Individual Decision Making 3. Basic Topics in Game Theory 4. The.
LINEAR CLASSIFICATION. Biological inspirations  Some numbers…  The human brain contains about 10 billion nerve cells ( neurons )  Each neuron is connected.
Artificial Intelligence Lecture No. 29 Dr. Asad Ali Safi ​ Assistant Professor, Department of Computer Science, COMSATS Institute of Information Technology.
Artificial Intelligence Techniques Multilayer Perceptrons.
TUSTP 2003 by Vasudevan Sampath by Vasudevan Sampath May 20, 2003 Intelligent Control of Compact Separation System Intelligent Control of Compact Separation.
Intelligent vs Classical Control Bax Smith EN9940.
I Robot.
Features of Biological Neural Networks 1)Robustness and Fault Tolerance. 2)Flexibility. 3)Ability to deal with variety of Data situations. 4)Collective.
Features of Biological Neural Networks 1)Robustness and Fault Tolerance. 2)Flexibility. 3)Ability to deal with variety of Data situations. 4)Collective.
Intelligent System Ming-Feng Yeh Department of Electrical Engineering Lunghwa University of Science and Technology Website:
LI Aijun. Introduce yourself   Where you from   Major   supervisor.
CSE & CSE6002E - Soft Computing Winter Semester, 2011 Course Review.
Chapter 1: Introduction to Neuro-Fuzzy (NF) and Soft Computing (SC)
NEURAL NETWORKS LECTURE 1 dr Zoran Ševarac FON, 2015.
Neural Networks Si Wu Dept. of Informatics PEV III 5c7 Spring 2008.
A field of study that encompasses computational techniques for performing tasks that require intelligence when performed by humans. Simulation of human.
A Presentation on Adaptive Neuro-Fuzzy Inference System using Particle Swarm Optimization and it’s Application By Sumanta Kundu (En.R.No.
1 Neural Networks MUMT 611 Philippe Zaborowski April 2005.
Information Processing
Fundamental ARTIFICIAL NEURAL NETWORK Session 1st
Soft Computing Introduction.
SOFT COMPUTING.
CSE 473 Introduction to Artificial Intelligence Neural Networks
Neural Networks Dr. Peter Phillips.
Introduction to Soft Computing
Artificial Intelligence ppt
Build Intelligence from the bottom up!
Build Intelligence from the bottom up!
with Daniel L. Silver, Ph.D. Christian Frey, BBA April 11-12, 2017
Dr. Unnikrishnan P.C. Professor, EEE
Intelligent Leaning -- A Brief Introduction to Artificial Neural Networks Chiung-Yao Fang.
Artificial Intelligence Methods
Intelligent Leaning -- A Brief Introduction to Artificial Neural Networks Chiung-Yao Fang.
Case Study on Robotic Systems Using Intelligent Approach
Intelligent Systems and
CSE 573 Introduction to Artificial Intelligence Neural Networks
Build Intelligence from the bottom up!
Fuzzy Logic Colter McClure.
Artificial Intelligence Chapter 3 Neural Networks
Intelligent Control, Its evolution, Recent Technology on Robotics
Dr. Unnikrishnan P.C. Professor, EEE
Dept. of Mechanical and Control Systems Eng.
Artificial Intelligence 12. Two Layer ANNs
Masoud Nikravesh EECS Department, CS Division BISC Program
Fuzzy Logic Bai Xiao.
The Network Approach: Mind as a Web
Fuzzy Logic Based on a system of non-digital (continuous & fuzzy without crisp boundaries) set theory and rules. Developed by Lotfi Zadeh in 1965 Its advantage.
Behavior Based Systems
Outline Announcement Neural networks Perceptrons - continued
Presentation transcript:

Introduction To Intelligent Control M.Yamakita Dept. of Mechanical and Control Systems Eng. Tokyo Inst. Of Tech. 2018/9/21

Controlled system becomes more and more complex. It is almost impossible to represent mathematical differential and difference equation representation of the systems. Emergent technology is needed ! Intelligent Control 2018/9/21

Trends from ’60 Artificial Intelligence (AI) Crisp Logic Fuzzy Logic Symbolic Representation Non-Symbolic Representation (ANN) Control Theory Classical Control Theory (PID) Modern Control Theory Robust Control Theory Adaptive Control Theory Hybrid System Control 2018/9/21

What’s Intelligent Control ? (G.Saridis,1979) Information Processing Formal Language Planning Scheduling Management Dyn. Feedback Optimization Memory Dynamics Coordination AI CONTROL OR Intelligent Control Intelligent Control ≠ Fuzzy Control ( 2018/9/21

Structure Of Intelligent Control 1. Hierarchical Intelligent Control (Albus, Saridis) 2. Reactive Intelligent Control (Brooks) (Subsumption Architecture) 2018/9/21

Hierarchical Intelligent Control (Saridis) INTELLIGENCE PRECISION Organization Level Coordination Execution MOTION COORDINATOR VISION COMMUNICATION CONTROLLER ACTUATORS HARDWARE NETWORK … ORGANIZER DISPACHER PLANNING 2018/9/21

Reactive Intelligent Control (Brooks) Modify the World BEHAVIORAL MODULE I R S RESET INPUT OUTPUT Suppressor Inhibitor Create Maps Discover New Area Avoid Collisions Move Around 2018/9/21

Supporting Technologies 1. Extensions of conventional control technologies Robust optimal control Adaptive control Learning control 2. New technologies FAN(Fuzzy, AI, and Neural network) technology (Fukuda) Soft computing (Zadeh) 2018/9/21

Dynamical System Representation (State Space Representation) 2018/9/21

Robust Optimal Control Set of uncertain systems A nominal system Model set of uncertain systems 2018/9/21

Adaptive Control 2018/9/21

Symbolic System Representation (Rule Based Representation) Area3 Area2 ? Area1 Classical AI, Automaton etc. 2018/9/21

Crisp Logic vs. Fuzzy Logic Tall Mr.A 180cm 170cm ? Mrs.B ( 170cm 160cm Mr.C Short 2018/9/21

When we describe real world symbolically, there always exist ‘gray zone’ state. It is very difficult to describe the gray zone property by conventional crisp logic. Or, we must define undesirably many categories. Fuzzy Logic 2018/9/21

Introduction of membership functions Degree of property 100% 50% ) x 160 170 180 Height Short Tall 2018/9/21

Perceptron O1 O2 B B A C A C D A--B B--C C--D A--B (A is connected to B) B--C C--A Triangle NOT Triangle Human easily recognize O2 as triangle ! 2018/9/21

Mimic the brain function ! D Mimic the brain function ! 2018/9/21

No Hidden Layer Adjustable Weights Activation Function (Rosenbratto Type Perceptron) 2018/9/21

Multi Layered Neural Network Adjustable Weights Activation Function . Generalized delta rule, Back-propagation algorithm (Amari, Rumelhalt) 2018/9/21

References 1.M.M.Gupta,N.k.Sinha:Intelligent Control Systems, IEEE Press. (1996) 2. K.Furuta et.:Intelligent Control, Corona Pub. (1988) (in Japanese) 3.B.Widrow, E.Walach: Adaptive Inverse Control,Prentice Hall (1996) 2018/9/21