Artificial Intelligence. Outline

Size: px
Start display at page:

Download "Artificial Intelligence. Outline"

Transcription

1 Artificial Intelligence Embodied Intelligence (R. Brooks, MIT) Outline Key perspectives for thinking about how an intelligent system interacts with world Compare mainstream AI to early artificial creature approaches Derive number of morals from comparison Look at some simple animals to see how they operate in their worlds Making comparisons to artificial creatures 2 1

2 GOFAI (Good Old Fashioned AI) Traditional AI approach was/is Identify essence of something Study that, expecting to generalize back to full concept later Playing with blocks Microworld: the blocks world Ignores untidiness of real world Only the essence of building simple block towers is considered Everything represented in a neat, logical calculus to describe a 2-D scene Blocks all same size, and perfectly aligned on top of each other Has perfect perception of world (no ambiguities) 3 GOFAI (Good Old Fashioned AI) B C A A B C Initial situation Goal situation Standard type of problem in microworld Transform stacks of blocks in left scene to stack of blocks in right scene Input to planner might be goal situation (and (on A B) (on B C)) Not the geometrical description that humans see/use Representations chosen are usually highly dependent on the problem to be solved Often constrains the types of problems to work on 4 2

3 GOFAI (Good Old Fashioned AI) Large parts of AI devoted to recasting problems of intelligence in terms similar to simple blocks world descriptions Then finding ways to solve them This has not scaled well Microworlds were used to simplify the study of intelligence to manageable levels Implicitly assumes that intelligence is about problem solving (recall Minsky) The essence of intelligence in solving a puzzle omits lots of details not important to explicit statement of the puzzle 5 An Alternate View Intelligence is all about making judgments when there are large numbers of messy details all around Especially when no clear single best answer Analogy to Sherlock Holmes His strength was perceiving details others did not notice Perception was not abstract and distant At scene of crime, walked along getaway lanes, poked his head into the pantry Directly experienced what was there and where 6 3

4 From an Evolutionary Perspective Consider evolutionary timescale of 4.6 billion years? Single cell entities arose roughly 3.5 billion years ago A billion years passed before photosynthetic plants Fish and vertebrates arrived around 550 million years ago Insects at 450 million years ago Slow start Things now move fast Reptiles appeared 370 million years ago Dinosaurs at 330 million years ago Mammals at 250 million years ago First primates appeared 120 million years ago Predecessors of great apes at 18 million years ago Humankind around 2.5 million years ago Agriculture (19,000), writing (5,000), scientific knowledge (last few hundred years) 7 Another Approach to Intelligence Consider the previous evolutionary perspective Stick with messy detailed world Consider how a creature might get around and survive in the world Evolution spent most of its time in this before getting to us 8 4

5 New AI: Embodied Intelligence Key points Intelligent systems operate in a world that is Complex, uncertain, and not fully perceivable It carries out tasks involving perception and motion Must do some things to survive in world Not do solve problems built into it by researchers Artificial creature is embodied Effects of actions depend on state of external world External world influences perception of creature It must have internal drive to direct operations in world Hunger for electricity Reductionist approach to AI Shift from solving problems to existing within a world and maintaining of goals 9 Embodied AI vs. GOFAI Task Complexity Traditional AI starting region Target Embodied AI starting region Environment Complexity Traditional AI research keeps task difficulty Then tries to make environment complex Embodied AI research starts with most complex world ever to be encountered Then takes up challenge of task to perform in that environment 10 5

6 Braitenberg s Vehicles Valentino Braitenberg Neuroscientist Wrote Vehicles: Experiments in Synthetic Psychology (1984) Series of fourteen thought experiments about building little vehicles to operate in the world Relates physical systems to concepts of psychology, cognition, and free will Each chapter discusses a different vehicle Increasing in sophistication Display increasingly life-like phenomena Eventually exhibit behavior like egotism and optimism 11 The Vehicles Braitenberg s Vehicle 1 One sensor connected to one actuator More stuff sensed makes it go faster Suppose Sensor measures temperature Actuator is little rocket engine, with force proportional to temperature Result In friction environment Go faster when warm, and slower when cold Can veer off straight path due to non-smooth world In frictionless environment (outer space) Vehicle never slows down (acceleration proportional to temperature) Proceeds in straight line Sensor Actuator 12 6

7 Moral 1: Situatedness The behavior of a vehicle, or creature, depends on the environment in which it is embedded or situated 13 The Vehicles Braitenberg s Vehicle 2 Design Two actuators in laterally symmetric position Two sensors facing forward, symmetrically placed Comes in a number of types Depending on how sensors are connected to actuators When actuators apply same force, go straight ahead When right actuator apply more force than the left, vehicle veers left

8 The Vehicles Vehicle 2.a Left sensor is connected to left actuator Right sensor connected to right actuator Suppose Sensors measure intensity of light coming from source Actuators produce more force (speed) when there is higher light intensity level The Vehicles Result of Vehicle 2.a If right sensor closer to light source than left sensor Right sensor gets more light Then right actuator drives harder making it turn left and away from light source Initial turning cause even more turning 16 8

9 The Vehicles Vehicle 2.b Crossed sensor/actuator connections Left sensor is connected to right actuator Right sensor connected to left actuator When light falling on right sensor more than falling on left sensor Left actuator produces higher force Causes vehicle to turn to right Towards the light As get closer to light, both actuators increase and vehicle accelerate toward light Eventually running right into it 17 Moral 2: Embodiment The actions of a creature are part of a dynamic with the world and have immediate feedback on the creature s own sensations through direct physical coupling and its consequences 18 9

10 Vehicle Behaviors Braitenberg describes vehicle behaviors in anthropomorphic terms From point of view of an observer Vehicles 2a and 2b both seem to dislike light sources Vehicle 2a is a coward (moves away from light source) Vehicle 2b is aggressive toward light sources (smashing into them at high velocity) There is nothing about like, dislike, or aggression explicitly built into the vehicles But observers do describe the behavior of the vehicles in those terms! 19 Moral 3 Terms descriptive of behavior are in the eye of the observer 20 10

11 Other Vehicles Vehicles 3.a and 3.b Sensors inhibit the actuator The more of the sensed quantity, less force produced by actuator These vehicles slow down in vicinity of light source Steering is opposite to class 2 counterparts Vehicle 3.a (uncrossed wires) Tends to stay centered on light source until stop in front of light Vehicle 3.b (crossed wires) Tends to veer away from light source When eventually faces away from light source, then more influenced by rest of environment Once inhibition added to connection options, opens up possibility to build more behaviors 21 Other Vehicles Vehicles 4.a Adds non-linear relationships to wires connecting sensors and actuators Leads to very complicated behavior in all sorts of environments But too complex to describe the behavior of the vehicles directly Instead use descriptive terms like instinct to describe particular action patterns The resulting behavior is generated by the totality of the system Not by any one piece 22 11

12 Moral 4: Emergence The intelligence of the system emerges from the system s interactions with the world and from sometimes indirect interactions between its components it is sometimes hard to point to one event or place within the system and say that is why some external action was manifested 23 Emergence Emergence is not a linear phenomena Behavior produced by the system is more than the sum of its parts We do not necessarily need to build an explicit behavior into the system itself More with vehicles In Vehicle 4.b, discontinuous connecting elements introduce thresholds into system Vehicles appear to reach decisions at times In Vehicle class 5, networks of non-linear elements are introduced Vehicles now have memory (more on this later ) 24 12

13 Vehicles as Creatures Braitenberg devised artificial creatures (called vehicles) that live in a world Braitenberg did not simplify the world to be clean and neat Instead he describes how properties of world may effect the behavior of his creations Starting from very simple creatures, Braitenberg sketches out how one could proceed in bottom-up manner to reach intelligence 25 Autonomy An autonomous vehicle/creature Able to maintain long-term dynamic with environment without intervention Once switched on, it does what is in its nature to do 26 13

14 Physical Artificial Creatures Tortoises Elmer and Elsie (1950) W. Grey Walter Design Two electric motor actuators Single bump sensor Light sensor Recharging hutch Explored environment with complex behaviors Remarkably unpredictable 27 From 1950 SciAm Article Seeking light Reaction to obstacle 28 14

15 Physical Artificial Creatures MIT 29 Other Robots 30 15

16 Physical Non-Artificial Creatures Are artificial creature behaviors anything (computationally) like real creatures? Animals Frogs Bug detector : respond to size and motion Pigeons Navigation: stars, sun, magnetic fields, olfactory, ultrasound Ranked sensors (layered), not sensor fusion Jumping spiders Responds to moving stimulus (prey, courtship) Bees Dance language for signaling location of food to others Seem to be implementable for artificial creatures 31 Summary Compared mainstream AI to early artificial creature approaches GOFAI Braitenberg s vehicles Looked at some simple animals to see how they operate in their worlds Making comparisons to artificial creatures 32 16

Psychology 452 Week 9: The Synthetic Approach

Psychology 452 Week 9: The Synthetic Approach Psychology 452 Week 9: The Synthetic Approach Analytic approach to psychology The synthetic alternative Grey Walter s Turtles Braitenberg s Vehicles A toy example Grey Walter s Turtles William Grey Walter

More information

Agents and Environments

Agents and Environments Agents and Environments Berlin Chen 2004 Reference: 1. S. Russell and P. Norvig. Artificial Intelligence: A Modern Approach. Chapter 2 AI 2004 Berlin Chen 1 What is an Agent An agent interacts with its

More information

Artificial Intelligence. Intelligent Agents

Artificial Intelligence. Intelligent Agents Artificial Intelligence Intelligent Agents Agent Agent is anything that perceives its environment through sensors and acts upon that environment through effectors. Another definition later (Minsky) Humans

More information

Putting Minsky and Brooks Together. Bob Hearn MIT AI Lab

Putting Minsky and Brooks Together. Bob Hearn MIT AI Lab Putting Minsky and Brooks Together Bob Hearn MIT AI Lab Perception: Irreconcilable Approaches? Minsky Brooks GOFAI vs. Nouvelle AI search vs. behaviors cognition vs. perception / action abstract symbols

More information

Agents and Environments. Stephen G. Ware CSCI 4525 / 5525

Agents and Environments. Stephen G. Ware CSCI 4525 / 5525 Agents and Environments Stephen G. Ware CSCI 4525 / 5525 Agents An agent (software or hardware) has: Sensors that perceive its environment Actuators that change its environment Environment Sensors Actuators

More information

Introduction to Artificial Intelligence 2 nd semester 2016/2017. Chapter 2: Intelligent Agents

Introduction to Artificial Intelligence 2 nd semester 2016/2017. Chapter 2: Intelligent Agents Introduction to Artificial Intelligence 2 nd semester 2016/2017 Chapter 2: Intelligent Agents Mohamed B. Abubaker Palestine Technical College Deir El-Balah 1 Agents and Environments An agent is anything

More information

DYNAMICISM & ROBOTICS

DYNAMICISM & ROBOTICS DYNAMICISM & ROBOTICS Phil/Psych 256 Chris Eliasmith Dynamicism and Robotics A different way of being inspired by biology by behavior Recapitulate evolution (sort of) A challenge to both connectionism

More information

Module 1. Introduction. Version 1 CSE IIT, Kharagpur

Module 1. Introduction. Version 1 CSE IIT, Kharagpur Module 1 Introduction Lesson 2 Introduction to Agent 1.3.1 Introduction to Agents An agent acts in an environment. Percepts Agent Environment Actions An agent perceives its environment through sensors.

More information

Artificial Intelligence Lecture 7

Artificial Intelligence Lecture 7 Artificial Intelligence Lecture 7 Lecture plan AI in general (ch. 1) Search based AI (ch. 4) search, games, planning, optimization Agents (ch. 8) applied AI techniques in robots, software agents,... Knowledge

More information

Chapter 2: Intelligent Agents

Chapter 2: Intelligent Agents Chapter 2: Intelligent Agents Outline Last class, introduced AI and rational agent Today s class, focus on intelligent agents Agent and environments Nature of environments influences agent design Basic

More information

Intelligent Agents. Instructor: Tsung-Che Chiang

Intelligent Agents. Instructor: Tsung-Che Chiang Intelligent Agents Instructor: Tsung-Che Chiang tcchiang@ieee.org Department of Computer Science and Information Engineering National Taiwan Normal University Artificial Intelligence, Spring, 2010 Outline

More information

Animal Behavior. Relevant Biological Disciplines. Inspirations => Models

Animal Behavior. Relevant Biological Disciplines. Inspirations => Models Animal Behavior Relevant Biological Disciplines Neuroscience: the study of the nervous system s anatomy, physiology, biochemistry and molecular biology Psychology: the study of mind and behavior Ethology:

More information

Intelligent Agents. Instructor: Tsung-Che Chiang

Intelligent Agents. Instructor: Tsung-Che Chiang Intelligent Agents Instructor: Tsung-Che Chiang tcchiang@ieee.org Department of Computer Science and Information Engineering National Taiwan Normal University Artificial Intelligence, Spring, 2010 Outline

More information

EEL-5840 Elements of {Artificial} Machine Intelligence

EEL-5840 Elements of {Artificial} Machine Intelligence Menu Introduction Syllabus Grading: Last 2 Yrs Class Average 3.55; {3.7 Fall 2012 w/24 students & 3.45 Fall 2013} General Comments Copyright Dr. A. Antonio Arroyo Page 2 vs. Artificial Intelligence? DEF:

More information

5.8 Departure from cognitivism: dynamical systems

5.8 Departure from cognitivism: dynamical systems 154 consciousness, on the other, was completely severed (Thompson, 2007a, p. 5). Consequently as Thompson claims cognitivism works with inadequate notion of cognition. This statement is at odds with practical

More information

An Escalation Model of Consciousness

An Escalation Model of Consciousness Bailey!1 Ben Bailey Current Issues in Cognitive Science Mark Feinstein 2015-12-18 An Escalation Model of Consciousness Introduction The idea of consciousness has plagued humanity since its inception. Humans

More information

Robot Behavior Genghis, MIT Callisto, GATech

Robot Behavior Genghis, MIT Callisto, GATech Robot Behavior Genghis, MIT Callisto, GATech Today s Objectives To learn what robotic behaviors are To obtain a basic understanding of the design approaches related to behavior-based robotic systems To

More information

Intelligent Agents. Soleymani. Artificial Intelligence: A Modern Approach, Chapter 2

Intelligent Agents. Soleymani. Artificial Intelligence: A Modern Approach, Chapter 2 Intelligent Agents CE417: Introduction to Artificial Intelligence Sharif University of Technology Spring 2016 Soleymani Artificial Intelligence: A Modern Approach, Chapter 2 Outline Agents and environments

More information

CS343: Artificial Intelligence

CS343: Artificial Intelligence CS343: Artificial Intelligence Introduction: Part 2 Prof. Scott Niekum University of Texas at Austin [Based on slides created by Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC Berkeley. All materials

More information

NEURAL SYSTEMS FOR INTEGRATING ROBOT BEHAVIOURS

NEURAL SYSTEMS FOR INTEGRATING ROBOT BEHAVIOURS NEURAL SYSTEMS FOR INTEGRATING ROBOT BEHAVIOURS Brett Browning & Gordon Wyeth University of Queensland Computer Science and Electrical Engineering Department Email: browning@elec.uq.edu.au & wyeth@elec.uq.edu.au

More information

Neurophysiology and Information: Theory of Brain Function

Neurophysiology and Information: Theory of Brain Function Neurophysiology and Information: Theory of Brain Function Christopher Fiorillo BiS 527, Spring 2012 042 350 4326, fiorillo@kaist.ac.kr Part 5: The Brain s Perspective: Application of Probability to the

More information

Choose an approach for your research problem

Choose an approach for your research problem Choose an approach for your research problem This course is about doing empirical research with experiments, so your general approach to research has already been chosen by your professor. It s important

More information

CS324-Artificial Intelligence

CS324-Artificial Intelligence CS324-Artificial Intelligence Lecture 3: Intelligent Agents Waheed Noor Computer Science and Information Technology, University of Balochistan, Quetta, Pakistan Waheed Noor (CS&IT, UoB, Quetta) CS324-Artificial

More information

PCT 101. A Perceptual Control Theory Primer. Fred Nickols 8/27/2012

PCT 101. A Perceptual Control Theory Primer. Fred Nickols 8/27/2012 PCT 101 A Perceptual Control Theory Primer Fred Nickols 8/27/2012 This paper presents a simplified, plain language explanation of Perceptual Control Theory (PCT). PCT is a powerful and practical theory

More information

Artificial Intelligence

Artificial Intelligence Artificial Intelligence COMP-241, Level-6 Mohammad Fahim Akhtar, Dr. Mohammad Hasan Department of Computer Science Jazan University, KSA Chapter 2: Intelligent Agents In which we discuss the nature of

More information

Perceptual Anchoring with Indefinite Descriptions

Perceptual Anchoring with Indefinite Descriptions Perceptual Anchoring with Indefinite Descriptions Silvia Coradeschi and Alessandro Saffiotti Center for Applied Autonomous Sensor Systems Örebro University, S-70182 Örebro, Sweden silvia.coradeschi, alessandro.saffiotti

More information

From Ants to People, an Instinct to Swarm

From Ants to People, an Instinct to Swarm Page 1 of 5 November 13, 2007 From Ants to People, an Instinct to Swarm By CARL ZIMMER If you have ever observed ants marching in and out of a nest, you might have been reminded of a highway buzzing with

More information

AI: Intelligent Agents. Chapter 2

AI: Intelligent Agents. Chapter 2 AI: Intelligent Agents Chapter 2 Outline Agents and environments Rationality PEAS (Performance measure, Environment, Actuators, Sensors) Environment types Agent types Agents An agent is anything

More information

Artificial Intelligence CS 6364

Artificial Intelligence CS 6364 Artificial Intelligence CS 6364 Professor Dan Moldovan Section 2 Intelligent Agents Intelligent Agents An agent is a thing (e.g. program, or system) that can be viewed as perceiving its environment and

More information

PSY 310: Sensory and Perceptual Processes 1

PSY 310: Sensory and Perceptual Processes 1 Prof. Greg Francis PSY 310 Greg Francis Perception We have mostly talked about perception as an observer who acquires information about an environment Object properties Distance Size Color Shape Motion

More information

What is AI? The science of making machines that:

What is AI? The science of making machines that: What is AI? The science of making machines that: Think like humans Think rationally Act like humans Act rationally Thinking Like Humans? The cognitive science approach: 1960s ``cognitive revolution'':

More information

ICS 606. Intelligent Autonomous Agents 1. Intelligent Autonomous Agents ICS 606 / EE 606 Fall Reactive Architectures

ICS 606. Intelligent Autonomous Agents 1. Intelligent Autonomous Agents ICS 606 / EE 606 Fall Reactive Architectures Intelligent Autonomous Agents ICS 606 / EE 606 Fall 2011 Nancy E. Reed nreed@hawaii.edu 1 Lecture #5 Reactive and Hybrid Agents Reactive Architectures Brooks and behaviors The subsumption architecture

More information

Boids. Overall idea. Simulate group behavior by specifying rules for individual behavior (self-organizing distributed system)

Boids. Overall idea. Simulate group behavior by specifying rules for individual behavior (self-organizing distributed system) Boids COS 426 Boids Overall idea Simulate group behavior by specifying rules for individual behavior (self-organizing distributed system) and the thousands off fishes moved as a huge beast, piercing the

More information

Princess Nora University Faculty of Computer & Information Systems ARTIFICIAL INTELLIGENCE (CS 370D) Computer Science Department

Princess Nora University Faculty of Computer & Information Systems ARTIFICIAL INTELLIGENCE (CS 370D) Computer Science Department Princess Nora University Faculty of Computer & Information Systems 1 ARTIFICIAL INTELLIGENCE (CS 370D) Computer Science Department (CHAPTER-3) INTELLIGENT AGENTS (Course coordinator) CHAPTER OUTLINE What

More information

LECTURE 5: REACTIVE AND HYBRID ARCHITECTURES

LECTURE 5: REACTIVE AND HYBRID ARCHITECTURES Reactive Architectures LECTURE 5: REACTIVE AND HYBRID ARCHITECTURES An Introduction to MultiAgent Systems http://www.csc.liv.ac.uk/~mjw/pubs/imas There are many unsolved (some would say insoluble) problems

More information

Intelligent Agents. CmpE 540 Principles of Artificial Intelligence

Intelligent Agents. CmpE 540 Principles of Artificial Intelligence CmpE 540 Principles of Artificial Intelligence Intelligent Agents Pınar Yolum pinar.yolum@boun.edu.tr Department of Computer Engineering Boğaziçi University 1 Chapter 2 (Based mostly on the course slides

More information

Competing Frameworks in Perception

Competing Frameworks in Perception Competing Frameworks in Perception Lesson II: Perception module 08 Perception.08. 1 Views on perception Perception as a cascade of information processing stages From sensation to percept Template vs. feature

More information

Competing Frameworks in Perception

Competing Frameworks in Perception Competing Frameworks in Perception Lesson II: Perception module 08 Perception.08. 1 Views on perception Perception as a cascade of information processing stages From sensation to percept Template vs. feature

More information

Artificial Intelligence

Artificial Intelligence Artificial Intelligence Intelligent Agents Chapter 2 & 27 What is an Agent? An intelligent agent perceives its environment with sensors and acts upon that environment through actuators 2 Examples of Agents

More information

CS 771 Artificial Intelligence. Intelligent Agents

CS 771 Artificial Intelligence. Intelligent Agents CS 771 Artificial Intelligence Intelligent Agents What is AI? Views of AI fall into four categories 1. Thinking humanly 2. Acting humanly 3. Thinking rationally 4. Acting rationally Acting/Thinking Humanly/Rationally

More information

Learning and Adaptive Behavior, Part II

Learning and Adaptive Behavior, Part II Learning and Adaptive Behavior, Part II April 12, 2007 The man who sets out to carry a cat by its tail learns something that will always be useful and which will never grow dim or doubtful. -- Mark Twain

More information

KECERDASAN BUATAN 3. By Sirait. Hasanuddin Sirait, MT

KECERDASAN BUATAN 3. By Sirait. Hasanuddin Sirait, MT KECERDASAN BUATAN 3 By @Ir.Hasanuddin@ Sirait Why study AI Cognitive Science: As a way to understand how natural minds and mental phenomena work e.g., visual perception, memory, learning, language, etc.

More information

Computation on Information, Meaning and Representations. An Evolutionary Approach.

Computation on Information, Meaning and Representations. An Evolutionary Approach. Chapter A Computation on Information, Meaning and Representations. An Evolutionary Approach. Christophe Menant. Bordeaux France. Revised Oct 20, 2009 http://crmenant.free.fr/home-page/index.htm Chapter

More information

CHAPTER 10 COMPUTATION ON INFORMATION, MEANING AND REPRESENTATIONS. AN EVOLUTIONARY APPROACH

CHAPTER 10 COMPUTATION ON INFORMATION, MEANING AND REPRESENTATIONS. AN EVOLUTIONARY APPROACH CHAPTER 10 COMPUTATION ON INFORMATION, MEANING AND REPRESENTATIONS. AN EVOLUTIONARY APPROACH Christophe Menant Bordeaux.France E-mail: christophe.menant@hotmail.fr Abstract: Understanding computation as

More information

A brief comparison between the Subsumption Architecture and Motor Schema Theory in light of Autonomous Exploration by Behavior

A brief comparison between the Subsumption Architecture and Motor Schema Theory in light of Autonomous Exploration by Behavior A brief comparison between the Subsumption Architecture and Motor Schema Theory in light of Autonomous Exploration by Behavior Based Robots Dip N. Ray 1*, S. Mukhopadhyay 2, and S. Majumder 1 1 Surface

More information

Beyond the Centralized Mindset

Beyond the Centralized Mindset Topics for today Beyond the centralized mindset CPR Assignment 1 Beyond the Centralized Mindset How shall we explain behavior? What background assumptions guide our thinking? A long tradition of centralized

More information

Agents. Environments Multi-agent systems. January 18th, Agents

Agents. Environments Multi-agent systems. January 18th, Agents Plan for the 2nd hour What is an agent? EDA132: Applied Artificial Intelligence (Chapter 2 of AIMA) PEAS (Performance measure, Environment, Actuators, Sensors) Agent architectures. Jacek Malec Dept. of

More information

(Visual) Attention. October 3, PSY Visual Attention 1

(Visual) Attention. October 3, PSY Visual Attention 1 (Visual) Attention Perception and awareness of a visual object seems to involve attending to the object. Do we have to attend to an object to perceive it? Some tasks seem to proceed with little or no attention

More information

Unmanned autonomous vehicles in air land and sea

Unmanned autonomous vehicles in air land and sea based on Gianni A. Di Caro lecture on ROBOT CONTROL RCHITECTURES SINGLE AND MULTI-ROBOT SYSTEMS: A CASE STUDY IN SWARM ROBOTICS Unmanned autonomous vehicles in air land and sea Robots and Unmanned Vehicles

More information

Oscillatory Neural Network for Image Segmentation with Biased Competition for Attention

Oscillatory Neural Network for Image Segmentation with Biased Competition for Attention Oscillatory Neural Network for Image Segmentation with Biased Competition for Attention Tapani Raiko and Harri Valpola School of Science and Technology Aalto University (formerly Helsinki University of

More information

CS148 - Building Intelligent Robots Lecture 5: Autonomus Control Architectures. Instructor: Chad Jenkins (cjenkins)

CS148 - Building Intelligent Robots Lecture 5: Autonomus Control Architectures. Instructor: Chad Jenkins (cjenkins) Lecture 5 Control Architectures Slide 1 CS148 - Building Intelligent Robots Lecture 5: Autonomus Control Architectures Instructor: Chad Jenkins (cjenkins) Lecture 5 Control Architectures Slide 2 Administrivia

More information

MOBILE & SERVICE ROBOTICS RO OBOTIC CA 01. Supervision and control

MOBILE & SERVICE ROBOTICS RO OBOTIC CA 01. Supervision and control CY 02CFIC CFIDV MOBILE & SERVICE ROBOTICS Supervision and control Basilio Bona DAUIN Politecnico di Torino Basilio Bona DAUIN Politecnico di Torino 001/1 Supervision and Control 02CFIC CY a priori knowledge

More information

SRS Achievement Statements. Science

SRS Achievement Statements. Science SRS Achievement Statements Science Scales SRS Achievement Statements for Science 2018/19 2 Year 1 Achievement Statements Working Scientifically talk about what I see, hear, smell, taste or touch ask you

More information

Intelligent Agents. Chapter 2 ICS 171, Fall 2009

Intelligent Agents. Chapter 2 ICS 171, Fall 2009 Intelligent Agents Chapter 2 ICS 171, Fall 2009 Discussion \\Why is the Chinese room argument impractical and how would we have to change the Turing test so that it is not subject to this criticism? Godel

More information

Feeling. Thinking. My Result: My Result: My Result: My Result:

Feeling. Thinking. My Result: My Result: My Result: My Result: Source of Energy [P]erception of Info [J]udgment of Info External Lifestyle Where You Process How You Inform How You Make How Others See Your Decision-Making Extraverted intuitive Feeling Judging Introvert

More information

Part I Part 1 Robotic Paradigms and Control Architectures

Part I Part 1 Robotic Paradigms and Control Architectures Overview of the Lecture Robotic Paradigms and Control Architectures Jan Faigl Department of Computer Science Faculty of Electrical Engineering Czech Technical University in Prague Lecture 02 B4M36UIR Artificial

More information

Agents and Environments

Agents and Environments Artificial Intelligence Programming s and s Chris Brooks 3-2: Overview What makes an agent? Defining an environment Types of agent programs 3-3: Overview What makes an agent? Defining an environment Types

More information

The Advantages of Evolving Perceptual Cues

The Advantages of Evolving Perceptual Cues The Advantages of Evolving Perceptual Cues Ian Macinnes and Ezequiel Di Paolo Centre for Computational Neuroscience and Robotics, John Maynard Smith Building, University of Sussex, Falmer, Brighton, BN1

More information

We are an example of a biological species that has evolved

We are an example of a biological species that has evolved Bio 1M: Primate evolution (complete) 1 Patterns of evolution Humans as an example We are an example of a biological species that has evolved Many of your friends are probably humans Humans seem unique:

More information

Overview. What is an agent?

Overview. What is an agent? Artificial Intelligence Programming s and s Chris Brooks Overview What makes an agent? Defining an environment Overview What makes an agent? Defining an environment Department of Computer Science University

More information

Outline. Chapter 2 Agents & Environments. Agents. Types of Agents: Immobots

Outline. Chapter 2 Agents & Environments. Agents. Types of Agents: Immobots Outline Chapter 2 Agents & Environments Agents and environments Rationality PEAS specification Environment types Agent types 2 Agents An agent is anything that can be viewed as perceiving its environment

More information

Vorlesung Grundlagen der Künstlichen Intelligenz

Vorlesung Grundlagen der Künstlichen Intelligenz Vorlesung Grundlagen der Künstlichen Intelligenz Reinhard Lafrenz / Prof. A. Knoll Robotics and Embedded Systems Department of Informatics I6 Technische Universität München www6.in.tum.de lafrenz@in.tum.de

More information

(2) In each graph above, calculate the velocity in feet per second that is represented.

(2) In each graph above, calculate the velocity in feet per second that is represented. Calculus Week 1 CHALLENGE 1-Velocity Exercise 1: Examine the two graphs below and answer the questions. Suppose each graph represents the position of Abby, our art teacher. (1) For both graphs above, come

More information

Indiana Academic Standards Addressed By Zoo Program WINGED WONDERS: SEED DROP!

Indiana Academic Standards Addressed By Zoo Program WINGED WONDERS: SEED DROP! Indiana Academic Standards Addressed By Zoo Program WINGED WONDERS: SEED DROP! Program description: Discover how whether all seeds fall at the same rate. Do small or big seeds fall more slowly? Students

More information

EICA: Combining Interactivity with Autonomy for Social Robots

EICA: Combining Interactivity with Autonomy for Social Robots EICA: Combining Interactivity with Autonomy for Social Robots Yasser F. O. Mohammad 1, Toyoaki Nishida 2 Nishida-Sumi Laboratory, Department of Intelligence Science and Technology, Graduate School of Informatics,

More information

Lesson 6 Learning II Anders Lyhne Christensen, D6.05, INTRODUCTION TO AUTONOMOUS MOBILE ROBOTS

Lesson 6 Learning II Anders Lyhne Christensen, D6.05, INTRODUCTION TO AUTONOMOUS MOBILE ROBOTS Lesson 6 Learning II Anders Lyhne Christensen, D6.05, anders.christensen@iscte.pt INTRODUCTION TO AUTONOMOUS MOBILE ROBOTS First: Quick Background in Neural Nets Some of earliest work in neural networks

More information

22c:145 Artificial Intelligence

22c:145 Artificial Intelligence 22c:145 Artificial Intelligence Fall 2005 Intelligent Agents Cesare Tinelli The University of Iowa Copyright 2001-05 Cesare Tinelli and Hantao Zhang. a a These notes are copyrighted material and may not

More information

Robot Learning Letter of Intent

Robot Learning Letter of Intent Research Proposal: Robot Learning Letter of Intent BY ERIK BILLING billing@cs.umu.se 2006-04-11 SUMMARY The proposed project s aim is to further develop the learning aspects in Behavior Based Control (BBC)

More information

A Control-Based Architecture for Animal Behavior

A Control-Based Architecture for Animal Behavior 44 A Control-Based Architecture for Animal Behavior Michael Ramsey 44.1 Introduction 44.2 A Control System 44.3 Perceptual Control Systems Negative Feedback 44.4 Hierarchy of Control Systems 44.5 Control

More information

Agents & Environments Chapter 2. Mausam (Based on slides of Dan Weld, Dieter Fox, Stuart Russell)

Agents & Environments Chapter 2. Mausam (Based on slides of Dan Weld, Dieter Fox, Stuart Russell) Agents & Environments Chapter 2 Mausam (Based on slides of Dan Weld, Dieter Fox, Stuart Russell) Outline Agents and environments Rationality PEAS specification Environment types Agent types 2 Agents An

More information

The Re(de)fined Neuron

The Re(de)fined Neuron The Re(de)fined Neuron Kieran Greer, Distributed Computing Systems, Belfast, UK. http://distributedcomputingsystems.co.uk Version 1.0 Abstract This paper describes a more biologically-oriented process

More information

Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence

Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence To understand the network paradigm also requires examining the history

More information

Introduction. Chapter The Perceptual Process

Introduction. Chapter The Perceptual Process Chapter 1 Introduction Most of us take for granted our ability to perceive the external world. However, this is no simple deed at all. Imagine being given a task of designing a machine that can perceive,

More information

ATHLETIC SPEED THE WAY I SEE IT

ATHLETIC SPEED THE WAY I SEE IT ATHLETIC SPEED THE WAY I SEE IT WE ARE GOING TO HAVE AN OPEN DISCUSSION ABOUT HOW THE PURITY OF SPEED INSPIRED ME! The nonsensical comments by coaches when I was an athlete drove me to discover through

More information

Web-Mining Agents Cooperating Agents for Information Retrieval

Web-Mining Agents Cooperating Agents for Information Retrieval Web-Mining Agents Cooperating Agents for Information Retrieval Prof. Dr. Ralf Möller Universität zu Lübeck Institut für Informationssysteme Karsten Martiny (Übungen) Literature Chapters 2, 6, 13, 15-17

More information

Intelligent Autonomous Agents. Ralf Möller, Rainer Marrone Hamburg University of Technology

Intelligent Autonomous Agents. Ralf Möller, Rainer Marrone Hamburg University of Technology Intelligent Autonomous Agents Ralf Möller, Rainer Marrone Hamburg University of Technology Lab class Tutor: Rainer Marrone Time: Monday 12:15-13:00 Locaton: SBS93 A0.13.1/2 w Starting in Week 3 Literature

More information

Sensation vs. Perception

Sensation vs. Perception PERCEPTION Sensation vs. Perception What s the difference? Sensation what the senses do Perception process of recognizing, organizing and dinterpreting ti information. What is Sensation? The process whereby

More information

Reflecting on Reflexes

Reflecting on Reflexes Reflecting on Reflexes Pre-Lesson Quiz 1. What happens when you accidentally touch a hot plate? 2. Name two human reflexes and state how they work. 2 Pre-Lesson Quiz Answers 1. What happens when you accidentally

More information

Behavior Architectures

Behavior Architectures Behavior Architectures 5 min reflection You ve read about two very different behavior architectures. What are the most significant functional/design differences between the two approaches? Are they compatible

More information

Bio 1M: The evolution of apes (complete) 1 Example. 2 Patterns of evolution. Similarities and differences. History

Bio 1M: The evolution of apes (complete) 1 Example. 2 Patterns of evolution. Similarities and differences. History Bio 1M: The evolution of apes (complete) 1 Example Humans are an example of a biological species that has evolved Possibly of interest, since many of your friends are probably humans Humans seem unique:

More information

ERA: Architectures for Inference

ERA: Architectures for Inference ERA: Architectures for Inference Dan Hammerstrom Electrical And Computer Engineering 7/28/09 1 Intelligent Computing In spite of the transistor bounty of Moore s law, there is a large class of problems

More information

Anatomy of a Martian Iguana

Anatomy of a Martian Iguana Anatomy of a Martian Iguana Paul Fitzpatrick Embodied Intelligence (6.836) MIT ID 984985527 paulfitz@ai.mit.edu Abstract Adaptive behavior is best understood through study of the complete action-perception

More information

A PCT Primer. Fred Nickols 6/30/2011

A PCT Primer. Fred Nickols 6/30/2011 Fred Nickols 6/30/2011 This paper presents a simplified, plain language explanation of Perceptual Control Theory (PCT). PCT is a powerful theory of human behavior and one that I find far more satisfying

More information

Katsunari Shibata and Tomohiko Kawano

Katsunari Shibata and Tomohiko Kawano Learning of Action Generation from Raw Camera Images in a Real-World-Like Environment by Simple Coupling of Reinforcement Learning and a Neural Network Katsunari Shibata and Tomohiko Kawano Oita University,

More information

Perception Lie Paradox: Mathematically Proved Uncertainty about Humans Perception Similarity

Perception Lie Paradox: Mathematically Proved Uncertainty about Humans Perception Similarity Perception Lie Paradox: Mathematically Proved Uncertainty about Humans Perception Similarity Ahmed M. Mahran Computer and Systems Engineering Department, Faculty of Engineering, Alexandria University,

More information

Animal Behavior. How can we explain behavior? Behavior. Innate or instinctive behavior. Instinctive behavior. Instinctive behavior 11/26/2017

Animal Behavior. How can we explain behavior? Behavior. Innate or instinctive behavior. Instinctive behavior. Instinctive behavior 11/26/2017 Animal Behavior Chapter 51 How can we explain behavior? How it works physiologically Proximate answer The adaptive value of the behavior Ultimate answer So, behavioral scientists study what behavior an

More information

what is behavior? by Tio

what is behavior? by Tio what is behavior? by Tio If you already know what TROM is about you can skip this part. If not, it is quite important to watch this brief introduction explaining what this project is about: We have already

More information

Intelligent Agents. Outline. Agents. Agents and environments

Intelligent Agents. Outline. Agents. Agents and environments Outline Intelligent Agents Chapter 2 Source: AI: A Modern Approach, 2 nd Ed Stuart Russell and Peter Norvig Agents and environments Rationality (Performance measure, Environment, Actuators, Sensors) Environment

More information

Affective Agent Architectures

Affective Agent Architectures Affective Agent Architectures Matthias Scheutz Artificial Intelligence and Robotics Laboratory Department of Computer Science and Engineering University of Notre Dame Notre Dame, IN 46556, USA mscheutz@cse.nd.edu

More information

Artificial Intelligence Programming Probability

Artificial Intelligence Programming Probability Artificial Intelligence Programming Probability Chris Brooks Department of Computer Science University of San Francisco Department of Computer Science University of San Francisco p.1/25 17-0: Uncertainty

More information

Dr. Mustafa Jarrar. Chapter 2 Intelligent Agents. Sina Institute, University of Birzeit

Dr. Mustafa Jarrar. Chapter 2 Intelligent Agents. Sina Institute, University of Birzeit Lecture Notes, Advanced Artificial Intelligence (SCOM7341) Sina Institute, University of Birzeit 2 nd Semester, 2012 Advanced Artificial Intelligence (SCOM7341) Chapter 2 Intelligent Agents Dr. Mustafa

More information

Agents. This course is about designing intelligent agents Agents and environments. Rationality. The vacuum-cleaner world

Agents. This course is about designing intelligent agents Agents and environments. Rationality. The vacuum-cleaner world This course is about designing intelligent agents and environments Rationality The vacuum-cleaner world The concept of rational behavior. Environment types Agent types 1 An agent is an entity that perceives

More information

Reasoning: The of mathematics Mike Askew

Reasoning: The of mathematics Mike Askew Reasoning: The of mathematics Mike Askew info@mikeaskew.net mikeaskew.net @mikeaskew26 What is Teaching? Creating a common experience to reflect on and so bring about learning. Maths is NOT a spectator

More information

What Science Is and Is Not

What Science Is and Is Not What Is Science? Key Questions What are the goals of science? What procedures are at the core of scientific methodology? Vocabulary science observation inference hypothesis controlled experiment independent

More information

AQUA 101: Principles of Water

AQUA 101: Principles of Water AQUA 101: Principles of Water Here is a summary of what you are about to learn: Laws of Motion: Sir Isaac Newton An object in motion will stay in motion (same with rest) Action/ Reaction: for every action

More information

Solutions for Chapter 2 Intelligent Agents

Solutions for Chapter 2 Intelligent Agents Solutions for Chapter 2 Intelligent Agents 2.1 This question tests the student s understanding of environments, rational actions, and performance measures. Any sequential environment in which rewards may

More information

Visual Design. Simplicity, Gestalt Principles, Organization/Structure

Visual Design. Simplicity, Gestalt Principles, Organization/Structure Visual Design Simplicity, Gestalt Principles, Organization/Structure Many examples are from Universal Principles of Design, Lidwell, Holden, and Butler 1 Why discuss visual design? You need to present

More information

Ontologies for World Modeling in Autonomous Vehicles

Ontologies for World Modeling in Autonomous Vehicles Ontologies for World Modeling in Autonomous Vehicles Mike Uschold, Ron Provine, Scott Smith The Boeing Company P.O. Box 3707,m/s 7L-40 Seattle, WA USA 98124-2207 michael.f.uschold@boeing.com Craig Schlenoff,

More information

Neurophysiology and Information: Theory of Brain Function

Neurophysiology and Information: Theory of Brain Function Neurophysiology and Information: Theory of Brain Function Christopher Fiorillo BiS 527, Spring 2012 042 350 4326, fiorillo@kaist.ac.kr Part 1: Inference in Perception, Cognition, and Motor Control Reading:

More information