Introduction to Softcomputing Son Kuswadi Robotic and Automation

  • Slides: 30
Download presentation
Introduction to Softcomputing Son Kuswadi Robotic and Automation Based on Biologicallyinspired Technology (RABBIT) Electronic

Introduction to Softcomputing Son Kuswadi Robotic and Automation Based on Biologicallyinspired Technology (RABBIT) Electronic Engineering Polytechnic Institute of Surabaya Institut Teknologi Sepuluh Nopember

Agenda AI and Softcomputing ¢ From Conventional AI to Computational Intelligence ¢ Neural Networks

Agenda AI and Softcomputing ¢ From Conventional AI to Computational Intelligence ¢ Neural Networks ¢ Fuzzy Set Theory ¢ Evolutionary Computation ¢

AI and Softcomputing ¢ User AI: predicate logic and symbol manipulation techniques Inference Engine

AI and Softcomputing ¢ User AI: predicate logic and symbol manipulation techniques Inference Engine Response Knowledge Engineer Human Expert User Interface Question Explanation Facility Knowledge Acquisition Expert Systems Global Database KB: • Fact • rules

AI and Softcomputing ANN Learning and adaptation Fuzzy Set Theory Knowledge representation Via Fuzzy

AI and Softcomputing ANN Learning and adaptation Fuzzy Set Theory Knowledge representation Via Fuzzy if-then RULE Genetic Algorithms Systematic Random Search

AI and Softcomputing ANN Learning and adaptation Fuzzy Set Theory Knowledge representation Via Fuzzy

AI and Softcomputing ANN Learning and adaptation Fuzzy Set Theory Knowledge representation Via Fuzzy if-then RULE Genetic Algorithms Systematic Random Search AI Symbolic Manipulation

AI and Softcomputing cat cut Animal? Neural character recognition knowledge cat

AI and Softcomputing cat cut Animal? Neural character recognition knowledge cat

From Conventional AI to Computational Intelligence ¢ Conventional AI: Focuses on attempt to mimic

From Conventional AI to Computational Intelligence ¢ Conventional AI: Focuses on attempt to mimic human intelligent behavior by expressing it in language forms or symbolic rules l Manipulates symbols on the assumption that such behavior can be stored in symbolically structured knowledge bases (physical symbol system hypothesis) l

From Conventional AI to Computational Intelligence ¢ Perceptions Actions Intelligent Systems Sensing Devices (Vision)

From Conventional AI to Computational Intelligence ¢ Perceptions Actions Intelligent Systems Sensing Devices (Vision) Machine Learning Task Generator Inferencing (Reasoning) Natural Language Processor Knowledge Handler Planning Mechanical Devices Data Handler Knowledge Base

Neural Networks

Neural Networks

Neural Networks f yp(k+1) u(k) z-1 0 z-1 N + 1 e(k+1) y^p(k+1) ^

Neural Networks f yp(k+1) u(k) z-1 0 z-1 N + 1 e(k+1) y^p(k+1) ^ z-1 0 ^ z-1 1 Parameter Identification - Parallel

Neural Networks f yp(k+1) u(k) z-1 0 z-1 N + 1 e(k+1) ^ yp(k+1)

Neural Networks f yp(k+1) u(k) z-1 0 z-1 N + 1 e(k+1) ^ yp(k+1) ^ z-1 0 ^ z-1 1 Parameter Identification – Series Parallel

Neural Networks ¢ Control Learning Error Feedforward controller ANN + + + Gc(s) R(s)

Neural Networks ¢ Control Learning Error Feedforward controller ANN + + + Gc(s) R(s) - ANN - + Feedback controller Plant Gp(s) C(s)

Neural Networks ¢ Control Current-driven magnetic field Controller Iron ball Ball-position sensor

Neural Networks ¢ Control Current-driven magnetic field Controller Iron ball Ball-position sensor

Neural Networks

Neural Networks

Neural Networks ¢ Experimental Results Feedback control only Feedback with ANN Feedforward controller Feedback

Neural Networks ¢ Experimental Results Feedback control only Feedback with ANN Feedforward controller Feedback with fixed gain feedforward control

Fuzzy Sets Theory ¢ What is fuzzy thinking l Experts rely on common sense

Fuzzy Sets Theory ¢ What is fuzzy thinking l Experts rely on common sense when they solve the problems l How can we represent expert knowledge that uses vague and ambiguous terms in a computer l Fuzzy logic is not logic that is fuzzy but logic that is used to describe the fuzziness. Fuzzy logic is theory of fuzzy sets, set that calibrate the vagueness. l Fuzzy logic is based on the idea that all things admit of degrees. Temperature, height, speed, distance, beauty – all come on a sliding scale. Jim is tall guy It is really very hot today

Fuzzy Set Theory ¢ Communication of “fuzzy “ idea This box is too heavy.

Fuzzy Set Theory ¢ Communication of “fuzzy “ idea This box is too heavy. . Therefore, we need a lighter one…

Fuzzy Sets Theory ¢ Boolean logic l ¢ Uses sharp distinctions. It forces us

Fuzzy Sets Theory ¢ Boolean logic l ¢ Uses sharp distinctions. It forces us to draw a line between a members of class and non members. Fuzzy logic l Reflects how people think. It attempt to model our senses of words, our decision making and our common sense -> more human and intelligent systems

Fuzzy Sets Theory ¢ Prof. Lotfi Zadeh

Fuzzy Sets Theory ¢ Prof. Lotfi Zadeh

Fuzzy Sets Theory ¢ No Classical Set vs Fuzzy set Name Height (cm) Degree

Fuzzy Sets Theory ¢ No Classical Set vs Fuzzy set Name Height (cm) Degree of Membership of “tall men” Crisp Fuzzy 1 Boy 206 1 1 2 Martin 190 1 1 3 Dewanto 175 0 0. 8 4 Joko 160 0 0. 7 5 Kom 155 0 0. 4

Fuzzy Sets Theory ¢ Classical Set vs Fuzzy set Membership value 1 1 0

Fuzzy Sets Theory ¢ Classical Set vs Fuzzy set Membership value 1 1 0 0 175 Height(cm) Universe of discourse 175 Height(cm)

Fuzzy Sets Theory ¢ Classical Set vs Fuzzy set Let X be the universe

Fuzzy Sets Theory ¢ Classical Set vs Fuzzy set Let X be the universe of discourse and its elements be denoted as x. In the classical set theory, crisp set A of X is defined as function f. A(x) called the characteristic function of A In the fuzzy theory, fuzzy set A of universe of discourse X is defined by function called the membership function of set A

Fuzzy Sets Theory ¢ Membership function

Fuzzy Sets Theory ¢ Membership function

Fuzzy Sets Theory ¢ Fuzzy Expert Systems Kecepatan (KM) Jarak (JM) Posisi Pedal Rem

Fuzzy Sets Theory ¢ Fuzzy Expert Systems Kecepatan (KM) Jarak (JM) Posisi Pedal Rem (PPR)

0 Fuzzy Sets Theory ¢ Membership function Sangat Lambat Sangat Dekat Cukup Cepat Lambat

0 Fuzzy Sets Theory ¢ Membership function Sangat Lambat Sangat Dekat Cukup Cepat Lambat 40 60 Kecepatan (km/jam) Injak Penuh Sedang Agak Jauh Agak Dekat 80 0 1 2 3 Jarak (m) Injak Sedang Injak Sedikit Injak Agak Penuh Injak Sedikit Sekali Jauh Sekali Cepat Sekali 20 PPR JM KM 4 0 10 20 30 Posisi pedal rem (0) 40

Fuzzy Sets Theory ¢ Fuzzy Rules Aturan 1: Bila kecepatan mobil cepat sekali dan

Fuzzy Sets Theory ¢ Fuzzy Rules Aturan 1: Bila kecepatan mobil cepat sekali dan jaraknya sangat dekat maka pedal rem diinjak penuh Aturan 2: Bila kecepatan mobil cukup dan jaraknya agak dekat maka pedal rem diinjak sedang Aturan 3: Bila kecepatan mobil cukup dan jaraknya sangat dekat maka pedal rem diinjak agak penuh

Fuzzy Sets Theory Fuzzy Expert Systems ¢ Aturan 1: Cepat Sekali 0 20 40

Fuzzy Sets Theory Fuzzy Expert Systems ¢ Aturan 1: Cepat Sekali 0 20 40 60 80 Kecepatan (km/jam) Sangat Dekat 0 1 2 Injak Penuh 3 4 Jarak (m) 0 10 20 30 Posisi pedal rem (0) 40

Fuzzy Sets Theory ¢ Fuzzy Expert Systems Aturan 2: Cukup 0 20 40 60

Fuzzy Sets Theory ¢ Fuzzy Expert Systems Aturan 2: Cukup 0 20 40 60 80 Kecepatan (km/jam) Agak Dekat 0 1 2 Injak Sedang 3 4 Jarak (m) 0 10 20 30 40 Posisi pedal rem (0)

Fuzzy Sets Theory ¢ Fuzzy Expert Systems Aturan 3: Cukup 0 20 40 60

Fuzzy Sets Theory ¢ Fuzzy Expert Systems Aturan 3: Cukup 0 20 40 60 80 Kecepatan (km/jam) Sangat Dekat 0 1 2 Injak Agak Penuh 3 4 Jarak (m) 0 10 20 30 Posisi pedal rem 40 (0 )

Fuzzy Sets Theory ¢ Fuzzy Expert Systems MOM : PPR = 200 MOM COA

Fuzzy Sets Theory ¢ Fuzzy Expert Systems MOM : PPR = 200 MOM COA 10 x 0, 2+20 x 0, 4 COA : PPR = 0 10 20 30 Posisi pedal rem (0) 40 0, 2+0, 4 = 16, 670