NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 1 Learning in Worlds with Objects Leslie Pack Kaelbling MIT Artificial Intelligence Laboratory.

Slides:



Advertisements
Similar presentations
1 Knowledge Representation Introduction KR and Logic.
Advertisements

Cognitive Systems, ICANN panel, Q1 What is machine intelligence, as beyond pattern matching, classification and prediction. What is machine intelligence,
Presentation on Artificial Intelligence
ARCHITECTURES FOR ARTIFICIAL INTELLIGENCE SYSTEMS
Focus on Instructional Support
Planning Module THREE: Planning, Production Systems,Expert Systems, Uncertainty Dr M M Awais.
Some questions o What are the appropriate control philosophies for Complex Manufacturing systems? Why????Holonic Manufacturing system o Is Object -Oriented.
Artificial Intelligence and Lisp TDDC65 Course leader: Erik Sandewall Lab assistants: Henrik Lundberg, John Olsson Administrator: Anna Grabska Eklund Webpage:
Perception and Perspective in Robotics Paul Fitzpatrick MIT Computer Science and Artificial Intelligence Laboratory Humanoid Robotics Group Goal To build.
DARPA Mobile Autonomous Robot SoftwareMay Adaptive Intelligent Mobile Robotics William D. Smart, Presenter Leslie Pack Kaelbling, PI Artificial.
COLLAGEN: When Agents Collaborate with People Charles Rich and Candace L. Sidner Presented by Daniel Schulman.
The Creative Curriculum Developmental Continuum Assessment System
Yiannis Demiris and Anthony Dearden By James Gilbert.
Common Core State Standards in Mathematics: ECE-5
1 Lecture 35 Brief Introduction to Main AI Areas (cont’d) Overview  Lecture Objective: Present the General Ideas on the AI Branches Below  Introduction.
A Summary of the Article “Intelligence Without Representation” by Rodney A. Brooks (1987) Presented by Dain Finn.
Awareness and Distributed Collaboration David Ledo.
Intelligence without Reason
Marakas: Decision Support Systems, 2nd Edition © 2003, Prentice-Hall Chapter Chapter 7: Expert Systems and Artificial Intelligence Decision Support.
Intelligent Agents revisited.
Programming Fundamentals (750113) Ch1. Problem Solving
McGraw-Hill/Irwin ©2005 The McGraw-Hill Companies, All rights reserved ©2005 The McGraw-Hill Companies, All rights reserved McGraw-Hill/Irwin.
Artificial Intelligence
8/9/20151 DARPA-MARS Kickoff Adaptive Intelligent Mobile Robots Leslie Pack Kaelbling Artificial Intelligence Laboratory MIT.
Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Cognitive Robots © 2014, SNU CSE Biointelligence Lab.,
Moving forward with Scalable Game Design. The landscape of computer science courses…  Try your vegetables (sneak it in to an existing course)  Required.
Wilma Bainbridge Tencia Lee Kendra Leigh
Wheeler Lower School Mathematics Program Grades 4-5 Goals: 1.For all students to become mathematically proficient 2.To prepare students for success in.
Some Thoughts to Consider 6 What is the difference between Artificial Intelligence and Computer Science? What is the difference between Artificial Intelligence.
1 Lyle H. Ungar, University of Pennsylvania What is AI? “Artificial Intelligence is the study of how to make computers do things at which, at the moment,
Yvonne M. Hansen Visualization for Thinking, Planning, and Problem Solving Simple, graphic shapes, the building blocks of a graphical language, play an.
Artificial Intelligence CIS 479/579 Bruce R. Maxim UM-Dearborn.
Chapter 14: Artificial Intelligence Invitation to Computer Science, C++ Version, Third Edition.
Piedmont K-5 Math Adoption May 29, Overview What Elementary Math Looks Like Historical Perspective District Philosophy Process and Criteria Why.
Towards Cognitive Robotics Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Christian.
Academic Needs of L2/Bilingual Learners
1 Artificial Intelligence GholamReza GhassemSani Fall 1383.
1 Lecture 1: Introduction to Artificial Intelligence.
An Ontological Framework for Web Service Processes By Claus Pahl and Ronan Barrett.
Lesson Study Group 1: Topping Off an Algebra Sundae Tracy Foss Wendy Goldfein ** Host Teacher Ellen King Cheryl Nelson John Ryan.
I Robot.
University of Windsor School of Computer Science Topics in Artificial Intelligence Fall 2008 Sept 11, 2008.
Course Instructor: K ashif I hsan 1. Chapter # 1 Kashif Ihsan, Lecturer CS, MIHE2.
1 The main topics in AI Artificial intelligence can be considered under a number of headings: –Search (includes Game Playing). –Representing Knowledge.
Learning in the Large Information Processing Technology Office Learning Workshop April 12, 2004 Seedling Overview Learning in the Large MIT CSAIL PIs:
DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; January Adaptive Intelligent Mobile Robotics Leslie Pack Kaelbling Artificial Intelligence.
Course Overview  What is AI?  What are the Major Challenges?  What are the Main Techniques?  Where are we failing, and why?  Step back and look at.
OPERATING SYSTEMS CS 3530 Summer 2014 Systems and Models Chapter 03.
Artificial Intelligence: Research and Collaborative Possibilities a presentation by: Dr. Ernest L. McDuffie, Assistant Professor Department of Computer.
MIT Artificial Intelligence Laboratory — Research Directions Intelligent Agents that Learn Leslie Pack Kaelbling.
Artificial Intelligence, simulation and modelling.
Some Thoughts to Consider 5 Take a look at some of the sophisticated toys being offered in stores, in catalogs, or in Sunday newspaper ads. Which ones.
Artificial Intelligence Knowledge Representation.
Learning Procedural Knowledge through Observation -Michael van Lent, John E. Laird – 인터넷 기술 전공 022ITI02 성유진.
Algorithms and Flowcharts
Functionality of objects through observation and Interaction Ruzena Bajcsy based on Luca Bogoni’s Ph.D thesis April 2016.
Introduction to Machine Learning, its potential usage in network area,
Knowledge Representation Techniques
OPERATING SYSTEMS CS 3502 Fall 2017
Learning Fast and Slow John E. Laird
Lecture #1 Introduction
Done Done Course Overview What is AI? What are the Major Challenges?
Intelligent Adaptive Mobile Robots
CH. 1: Introduction 1.1 What is Machine Learning Example:
Learning through Designing
Course Instructor: knza ch
Meeting Students Where They Are…
Programming Fundamentals (750113) Ch1. Problem Solving
Learning in Worlds with Objects
Habib Ullah qamar Mscs(se)
Presentation transcript:

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 1 Learning in Worlds with Objects Leslie Pack Kaelbling MIT Artificial Intelligence Laboratory With Tim Oates, Natalia Hernandez, Sarah Finney

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 2 What is an Agent? A system that has an ongoing interaction with an external environment household robot factory controller web agent Mars explorer pizza delivery robot Environment Action Observation

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 3 Agents Must Learn Learning is a crucial aspect of intelligent behavior human programmers lack required knowledge agents should work in a variety of environments agents should work in changing environments What to learn? World dynamics: What happens when I take a particular action? Reward: What world states are good?

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 4 Current state-of-the-art learning methods will not work in domains with multiple objects: These are crucial domains for robots of the future. Crisis ?

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 5 Representation Learning requires some sort of representation of states of the world. The choice of representation affects what information can be represented what kinds of generalizations the agent can make

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 6 Attribute Vector State-of-the-art representation for learning temperature = 48.2 pressure = 57.9 mB valve1 = open valve2 = closed time = 10:48AM backlog = 78 volume = 32.2 production = 45.5 …

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 7 Generalization over Attribute Vectors temp > 22 time < 10AM pressure < 3 close valve increase temp add reagent open valve temp time x

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 8 Complex Everyday Domains book1-on-book2:true book2-on-book1:false pen-is-yellow:true pen-is-blue:false lamp-on:true lamp-off:false ink-bottle-level:50% lamp-in-bottle:false bottle-on-lamp:false paper1-color:gray paper2-color:white fabric-behind-lamp:true book2-is-clear:false book4-is-clear:false book1-is-clear:true block1-on-block2:false block3-unstable:true block2-on-table:false block1-in-front-of-lamp:true … Attribute vector is impossibly big

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 9 Generalization over Objects If book1 is on book2 and I move book2, then book1 will move If the cup is on the table and I move the table, then the cup will move If the pen is on the paper and I move the paper, then the pen will move If the coat is on the chair and I move the chair, then the coat will move For all objects A and B: If A is on B and I move B, then A will move

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 10 Referring to Objects Traditional symbolic AI has the problem of “symbol grounding”: How do I know what object is named by book1? on(book1,book2)

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 11 Deictic Expressions “Deixis” is Greek for “pointing” koko ima watashi-ga motteiru hakowatashi-ga miteiru hako

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 12 Automatic Generalization If I have an object in my hand and I open my hand, then the object that was in my hand is now on the table This is true, no matter what object is in your hand.

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 13 Communicating with Humans Natural language communication speaks of the world in terms of objects and their relationships uses deictic expressions Our robots of the future will have to be able to understand and generate human descriptions of the world

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 14 Long-Term Research Goal A robotic system with hand and cameras that can learn to achieve tasks efficiently through trial and error acquire natural language descriptions of the objects and their properties through “conversation” with humans

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 15 Short-Term Research Plan Explore deictic, object-based representation for learning algorithms build simulated hand-eye robot system that manipulates blocks (with real physics) have simulated robot learn to carry out tasks from trial and error Demonstrate empirically and theoretically that deictic representation is crucial for efficient learning

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 16 First Example Domain Unreliable block stacking: robot is rewarded for making tall piles of blocks the taller a pile is, the more likely it is to fall over when another block is added a pile can be made more stable by building piles to its sides Once the robot learns to do this task, keep the physics of the domain the same, but reward a more complex behavior.

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 17 Learning by Doing Having an initial task to perform focuses the robot’s attention on aspects of the environment Use extension of Utree learning algorithm to select important aspects of the environment Generate new deictic expressions dynamically: the-block-on-top-of(the-block-I-am-looking-at) Extend reinforcement learning methods to apply to object-based representations

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 18 Extracting General Rules There are too many facts that are true in any interesting environment. Solving tasks focuses attention on particular objects (named with deictic expressions) particular properties of those objects These objects and properties are likely of general importance: use them as input to association-rule learning algorithm to learn facts like: The thing that is on the thing that I am holding will probably fall off if I move

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 19 Enabling Planning Given general rules, the agent can “think” about the consequences of its actions and decide what to do, rather than learn through trial and error.

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 20 In Future An ambitious research project vision algorithms for learning segmentation and object recognition learning good properties and relations for characterizing the domain (“concept learning”) connect with natural language learning for word meanings

NTT-MIT Collaboration Meeting, 2001Leslie Pack Kaelbling 21 Don’t miss any dirt!