Artificial Intelligence

Artificial Intelligence

Dr. Napoleon H. Reyes, Ph.D.Dr. Napoleon H. Reyes, Ph.D.Dr. Napoleon H. Reyes, Ph.D.Dr. Napoleon H. Reyes, Ph.D.Computer Science

Institute of Information and Mathematical Sciences

Rm. 2.56 QA, IIMS, Albany Campus or IIMS Lab 7

email: [email protected]@massey.ac.nz

Tel. No.: 64 9 4140800 x 9512 / 41572

Fax No.: 64 9 441 8181

159.302

Lectures:Monday 12pm – 1pm AT8Thursday 12pm – 1pm AT8Friday 12pm – 1pm AT5

Lectures:Monday 12pm – 1pm AT8Thursday 12pm – 1pm AT8Friday 12pm – 1pm AT5

http://www.massey.ac.nz/~nhreyes/Massey/159302.html

Office hours: after lectures (QA2.56 or IIMS Lab 7)

Topics for DiscussionTopics for Discussion

Pre-requisitesCourse OverviewLearning Outcomes

Texts and Course Material

Assessment

Course Schedule

AI Demonstrations

Note:Note:Note:Note:

If a student cannot attend lectures/tutorials it is If a student cannot attend lectures/tutorials it is the student’s responsibility to find out what the student’s responsibility to find out what was discussed in lectures / tutorials was discussed in lectures / tutorials (possible changes to assignments, questions (possible changes to assignments, questions & answers).& answers).

Student Responsibility

Pre-requisites

To take this course you must have passed 159.201159.201 since C or C++ knowledge is required to complete the assignments

*

Step-by-Step Algorithm Details

Course Overview

Discussion of the Theoretical Framework

Application to real-world problems

Teaching ApproachTeaching ApproachTeaching ApproachTeaching Approach

Simulations (A Graphics Engine will be provided to make learning AI more fun)

Learn how to apply AI techniques to different problemsLearning Outcomes

Understand the concepts and theories behind AI technologies

Implement selected AI algorithms

On successful completion of the course, the students should be able to:

Texts and Course Material

Russell S. and Norvig P., Artificial Intelligence A Modern Approach, 3rd Ed, Prentice Hall 2009ISBN-13:  9780136042594

Main text bookMain text book

Other ReferencesOther References

Neural Network and Fuzzy Logic Applications in C/C++ by Stephen T. Welstead

Artificial Intelligence: Structures and Strategies for Complex Problem Solving by George F Luger

MIT OpenCourseWare

Assessment

2 assignments: 40%

Final Exam (3 hours): 60%

Deadline: Deadlines for assignments will be given when assignments are distributed. You will be given 4 weeks to complete each assignment

Penalty: Late submissions (up to 1 week) will be penalised by 10%.

To pass, students have to obtain a cumulative assessment score greater than or equal to 50%.

Assessment

Program solutions that do not compile or do not run in our laboratories get 0 marks.

Late assignments will be penalized

Assignments may be completed in groups

all members of the group should be named in the source file of each assignment, including the contribution of each member.

All submitted assignments will have to be accompanied by a short documentation as well.

There can be at most 3 members in a group.

Assessment

Each group member will receive the same grade.

Students in a team have the authority (in consultation with the lecturer) to "expel" any member that does not meet obligations .

The collaboration is limited only to members within each group.

It is a student responsibility to check their assignment marks and notify in writing any errors they might find no later than 10 days after the day the marks were made available.

Week 1. Week 1. • Introduction (chap 1), Philosophical Issues (chap 26 & 27), Intelligent Agents (chap 2). • Film viewing• Tutorial: Simulation Essentials for the assignments

Week 2. Introduction to SearchWeek 2. Introduction to Search• Background and Motivation• Examples of Graphs• Problem Solving Paradigm• Graph Search as Tree Search• Terminologies• Classes of Search

Week 3. Search StrategiesWeek 3. Search Strategies• Issues of Implementing the Search Strategies• Cost and Performance• Any-Path Search (Uninformed and Informed, Using the Visited List)• Depth-First Algorithm• Breadth-First Algorithm• Best-First Search Algorithm

Course ScheduleCourse Schedule

Week 4. Any-Path Search ExamplesWeek 4. Any-Path Search Examples• Depth-First Algorithm• Breadth-First Algorithm• Best-First Search Algorithm• Tutorial: Problem Solving: Any-Path Search Algorithms

Week 5. Optimal Search: Part 1Week 5. Optimal Search: Part 1• Optimal Uninformed Search• Uniform Cost Search• Why not a Visited List? • Implementing Optimal Search Strategies• Optimal Informed Search• The A* Algorithm, Heuristics, Using the Strict Expanded List)• Tutorial: Problem Solving: Optimal Search Algorithms

Week 6. Optimal Search: Part 2Week 6. Optimal Search: Part 2• The A* and Expanded List• Uniform Cost and Strict Expanded List• Consistency• Optimality and Worst Case Complexity• Tutorial: Problem Solving: Optimal Search Algorithms

Course ScheduleCourse Schedule

Week 7. Fuzzy LogicWeek 7. Fuzzy Logic Fuzzification, Defuzzification, Fuzzy logic operators, Fuzzy Inference Systems,

Fuzzy Control Systems Inverted Pendulum Problem, Robot Navigation, Colour Object Recognition

Week 8. Machine LearningWeek 8. Machine Learning Neural Networks Pattern Recognition

Week 9. Constraint Satisfaction Problems and Games: Part 1Week 9. Constraint Satisfaction Problems and Games: Part 1 Binary CSP Constraints Constraint Propagation (Arc Consistency) Constraint Propagation Example Backtracking and Constraint Propagation Backtracking with Forward Checking (BT-FC)

Course ScheduleCourse Schedule

Week 10. Constraint Satisfaction Problems and Games: Part 2Week 10. Constraint Satisfaction Problems and Games: Part 2• BT-FC with Dynamic Ordering• Incremental Repair• Introduction to Games• Board Games and Search• Alpha-Beta Pruning• Practical Matters• Tutorial: Problem Solving: Minimax, Alpha Beta Pruning.

*Week 11. Propositional Logic & First Order Logic*Week 11. Propositional Logic & First Order Logic• Syntax, Semantics, Proof System, Sentences• Semantic Rules• Satisfiability• Satisfiability Problems• Propositional Logic Proof• Natural Deduction, Proof Systems, Conjunctive Normal Form, Propositional Resolution• Natural Language ProcessingWeek 11. Alternatively, Genetic Algorithms + Propositional Logic could be taught.Week 11. Alternatively, Genetic Algorithms + Propositional Logic could be taught.Week 12. Review for FinalsWeek 12. Review for Finals

Course ScheduleCourse Schedule

Demonstrations

Search Algorithms (Tree Search + Heuristics)

Sample application: 8-Puzzle

Fuzzy Logic – based on how we humans think

Sample applications: Robot Navigation, Inverted Pendulum

Neural Network – based on the architecture of the brain

Sample application: pattern recognition

Genetic Algorithm – based on theory of evolution

Sample application: optimisation

Assignment #1Assignment #1

C:\Core\Massey Papers\159302\Assignments 2008\Assign #1 - 2008\8 Puzzle - beta v.3.0

Input: x, v, theta, angular velocity

Control System: Inverted Pendulum Control System: Inverted Pendulum ProblemProblem

Control System: Inverted Pendulum Control System: Inverted Pendulum ProblemProblem

Output: Force, direction

Otherwise known as Broom-Balancing Problem

The mathematical solution uses a second-order differential equation that describes cart motion as a function of pole position and velocity:

sinsin)cos(cos)sin(2

2

2

2

mglllt

mllxt

m

Fuzzy RulesFuzzy rule base and the corresponding FAMM for the velocity and position vectors of the inverted pendulum-balancing problem

1. IF cart is on the left AND cart is going left THEN largely push cart to the right2. IF cart is on the left AND cart is not moving THEN slightly push cart to the right3. IF cart is on the left AND cart is going right THEN don’t push cart4. IF cart is centered AND cart is going left THEN slightly push cart to the right5. IF cart is centered AND cart is not moving THEN don’t push cart6. IF cart is centered AND cart is going right THEN slightly push cart to the left7. IF cart is on the right AND cart is going left THEN don’t push cart8. IF cart is on the right AND cart is not moving THEN push cart to the left9. IF cart is on the right AND cart is going right THEN largely push cart to the left

Input: x, v, theta, angular velocityInput: x, v, theta, angular velocity

Fuzzy Control System

Output: Force, directionOutput: Force, direction

Inverted Pendulum Problem

If the cart is too near the end of the path, then regardless of the state of the broom angle push the cart towards the other end.

If the cart is too near the end of the path, then regardless of the state of the broom angle push the cart towards the other end.

X 

N ZE P

N PL ZE ZE

X’ ZE ZE ZE ZE

P ZE ZE NL

If the broom angle is too big or changing too quickly, then regardless of the location of the cart on the cart path, push the cart towards the direction it is leaning to.

If the broom angle is too big or changing too quickly, then regardless of the location of the cart on the cart path, push the cart towards the direction it is leaning to.

N ZE P

N NL NM

ZE

’ ZE NM

ZE PM

P ZE PM

PL

Input: Multiple Obstacles: x, y, angleTarget’s x, y, angle

Robot Navigation

Output: Robot angle, speed

Obstacle Avoidance, Target Pursuit, Opponent Evasion

Cascade of Fuzzy SystemsCascade of Fuzzy Systems

Adjusted Speed

Adjusted Angle

Next Waypoint

N

Y

Adjusted Speed

Adjusted Angle

Fuzzy System 1: Target PursuitFuzzy System 1: Target Pursuit

Fuzzy System 2: Speed Control for Target Pursuit

Fuzzy System 3: Obstacle Avoidance

Fuzzy System 4: Speed Control for Obstacle Avoidance

ObstacleDistance < MaxDistanceTolerance and closer than Target

Actuators

Path planning Layer:

The A* Algorithm

Multiple Fuzzy Systems employ the various robot behavioursMultiple Fuzzy Systems employ the various robot behaviours

Fuzzy System 1Fuzzy System 1

Fuzzy System 2Fuzzy System 2

Fuzzy System 3Fuzzy System 3

Fuzzy System 4Fuzzy System 4

Path Planning LayerPath Planning Layer

CentralControl

Target Target PursuitPursuit

ObstacleObstacleAvoidanceAvoidance

Input: Obstacles’ x, y, angleTarget’s x, y, angle

Hybrid Fuzzy A*

Output: Robot angle, speed

C:\Core\Massey Papers\159302\Assignments 2008\Assign #2 - 2008\Robot Navigation - v.9.4 - FL-AStar

Simulations

3-D Hybrid Fuzzy A* Navigation System3-D Hybrid Fuzzy A* Navigation System

Cascade of Fuzzy SystemsCascade of Fuzzy Systems

Nature as Problem Solver

• Beauty-of-nature argument

• How Life Learned to Live (Tributsch, 1982, MIT Press)

• Example: Nature as structural engineer

25

Genetic Algorithm

• Let’s see the demonstration for a GA that maximizes the function

n

c

xxf

)(

n =10cc = 230 -1 = 1,073,741,823

26

Simple GA ExampleSimple GA Example• Function to evaluate:

• coeff – chosen to normalize the x parameter when a bit string of length lchrom =30 is chosen.

• Since the x value has been normalized, the max. value of the function will be:

when for the case when lchrom=30

10

( )x

f xcoeff

302 1coeff

( ) 1.0f x

302 1x

Fitness Function or Objective

Function

27

Test Problem CharacteristicsTest Problem Characteristics

• With a string length=3030, the search space is much larger, and random walk or enumeration should not be so profitable.

• There are 223030=1.07(10=1.07(101010) points) points. With over 1.07 billion points in the space, one-at-a-time methods are unlikely to do very much very quickly. Also, only 1.051.05 percent of the points have a value greater than 0.90.9.

28

Simple GA ImplementationInitial population of chromosomes

Calculate fitness value

PopulationOffspring

Stop

SolutionFound?

Evolutionaryoperations

Yes

No

Identifying Colour ObjectsIdentifying Colour Objectswitwithh

Robot Soccer Set-upRobot Soccer Set-up

Colour objects

Fluorescent lampsOverhead Camera

Exploratory environment is indoor – room totally obstructed from sunlight

Multiple monochromatic light sources – fluorescent / fluoride lamps

Colour Object Recognition (Recognition speed: < 33ms)

www.Fira.net

IIMS Lab 7IIMS Lab 7

**

Machine Vision SystemMachine Vision System

3D Scene

Optics (Lens)

Image Sensors

Camera Frame Grabber 2D Digital Image

CCD (Charge Coupled Device)CID (Charge Injection Device)

PDA (Photo Diode Array)

Firewire camera

Emmitted light2-D Intensity ImageContinuous charge signal

HARDWARE OUTLINE

**

Colour as the machine sees itColour as the machine sees it

Colour constancy is inherent in us humans, but not in cameras.Colour constancy is inherent in us humans, but not in cameras.

Color is not captured by the camera as we humans see it.

Yellow object turns pale under strong white illumination

A Green object tends to appear more as a whitish yellow object under bright white illumination.

Illumination ConditionsIllumination Conditions

Colour objects traversing the field under spatially varying Colour objects traversing the field under spatially varying illumination intensitiesillumination intensities

We need to automatically compensate for theWe need to automatically compensate for theeffects of varying illumination intensities in effects of varying illumination intensities in the scene of traversalthe scene of traversal

**

Dark

Bright

Dim

Lens focusLens focus

Object rotationObject rotation

Quantum electrical effectsQuantum electrical effects

ShadowsShadows

Presence of similar coloursPresence of similar colours

Other Factors:Other Factors:

Recent Developments

To some extent, the algorithm can see in the dark

Applying the colour contrast operations to compensate for the effects of glare, hue and saturation drifting also allows for colour correction

Experiments performed at IIMS Lab 7

Recent Developments

Experiments performed at IIMS Lab 7

PINK colour patches can be amplified to revert back close to its original colour

**

Robots in action

The Fuzzy Vision algorithm employed in the game…

Old system

Robots in Massey (QA 2.42)

C:\Core\Research\Conferences\ICONIP08