An Agent Approach to Data Sharing in Virtual Worlds and CAD Mary Lou Maher, Pak-San Liew, John S Gero Key Centre of Design Computing and Cognition, University.

Slides:



Advertisements
Similar presentations
Some Reflections on Augmented Cognition Eric Horvitz ISAT & Microsoft Research November 2000 Some Reflections on Augmented Cognition Eric Horvitz ISAT.
Advertisements

Modelling with expert systems. Expert systems Modelling with expert systems Coaching modelling with expert systems Advantages and limitations of modelling.
Introduction to Artificial Intelligence
Chapter 6 Security Kernels.
Chapter 1 Section II Fundamentals of Information Systems
ICT work programme ICT 22 Multimodal and natural computer interaction Aleksandra Wesolowska (Unit G.3 - Data Value Chain) Juan Pelegrin (Unit.
Two Research Methods in Design Computing Mary Lou Maher May 2003.
AGENT SOCIETIES. John S Gero Agents – Agent Societies ? environment percepts actions sensors effectors agent Single  Multiple Agents.
SITUATED AGENTS. John S Gero Agents – Situated Agents Basic Ideas Interaction not just encoding Construction not just recall Cognitive Science Dewey (1896):
Agents in Design A course in developing cognitive agents for objects in virtual worlds.
AGENT SOCIETIES Agent Societies Fall 2002 ? environment percepts actions sensors effectors agent Single  Multiple Agents.
A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra.
01 -1 Lecture 01 Intelligent Agents TopicsTopics –Definition –Agent Model –Agent Technology –Agent Architecture.
AGENT MODELS. John Gero Agents – Agent Models ? environment percepts actions sensors effectors agent.
Agent-Based Virtual Architecture John S Gero and Mary Lou Maher and Fall 2002 Time: Tuesday 9-12.
Modelling Motivation for Experience-Based Attention Focus in Reinforcement Learning Candidate Kathryn Merrick School of Information Technologies University.
OVERVIEW OF AGENTS AND AGENT ENVIRONMENTS. Categories of Agent Research.
Intelligent Agents: an Overview. 2 Definitions Rational behavior: to achieve a goal minimizing the cost and maximizing the satisfaction. Rational agent:
The Need of Unmanned Systems
WP 8: Networks for Lifelong Competence Development Alicia Cheak INSEAD CALT (Centre for Advanced Learning Technologies) TEN Competence Kickoff Meeting.
Universe Design Concepts Business Intelligence Copyright © SUPINFO. All rights reserved.
Database System Concepts and Architecture Dr. Ali Obaidi.
© 2007 Cisco Systems, Inc. All rights reserved.Cisco Public 1 Version 4.0 Communicating over the Network Network Fundamentals – Chapter 2.
Mrs. Maninder Kaur 1Maninder Kaur
Smart Learning Services Based on Smart Cloud Computing
“Curious Places” October, 2007 Key Centre of Design Computing and Cognition, University of Sydney A Room that Adapts using Curiosity and Supervised Learning.
 Cloud computing  Workflow  Workflow lifecycle  Workflow design  Workflow tools : xcp, eucalyptus, open nebula.
Chapter 6 System Engineering - Computer-based system - System engineering process - “Business process” engineering - Product engineering (Source: Pressman,
Copyright 2002 Prentice-Hall, Inc. Chapter 1 The Systems Development Environment 1.1 Modern Systems Analysis and Design.
DEVSView: A DEVS Visualization Tool Wilson Venhola.
Object-Oriented Implementation of Reconciliations M.Sc. Seminar Talk by Costa Shapiro under supervision of Prof. Shmuel Katz Computer Science – Technion.
European Network of Excellence in AI Planning Intelligent Planning & Scheduling An Innovative Software Technology Susanne Biundo.
Database System Concepts and Architecture
Situated Design of Virtual Worlds Using Rational Agents Mary Lou Maher and Ning Gu Key Centre of Design Computing and Cognition University of Sydney.
6 Chapter Databases and Information Management. File Organization Terms and Concepts Bit: Smallest unit of data; binary digit (0,1) Byte: Group of bits.
Key Centre of Design Computing and Cognition – University of Sydney Concept Formation in a Design Optimization Tool Wei Peng and John S. Gero 7, July,
Ihr Logo Fundamentals of Database Systems Fourth Edition El Masri & Navathe Chapter 2 Database System Concepts and Architecture.
Self-assembling Agent System Presentation 1 Donald Lee.
University of Windsor School of Computer Science Topics in Artificial Intelligence Fall 2008 Sept 11, 2008.
First Meeting of the AgentLink SIG on Intelligent Information Agents (I2A) Hotel Euroflat, Brussels September 24-25, 1998 Report Innes A. Ferguson, SIG.
REU 2004 Computer Science and Engineering Department The University of Texas at Arlington Research Experiences for Undergraduates in Distributed Rational.
SOFTWARE DESIGN. INTRODUCTION There are 3 distinct types of activities in design 1.External design 2.Architectural design 3.Detailed design Architectural.
31 March 2009 MMI OntDev 1 Autonomous Mission Operations for Sensor Webs Al Underbrink, Sentar, Inc.
Feng Zhiyong Tianjin University Fall  An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that.
Intelligent Agents Introduction Rationality Nature of the Environment Structure of Agents Summary.
Chapter 2 Agents. Intelligent Agents An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment.
Slide no 1 Cognitive Systems in FP6 scope and focus Colette Maloney DG Information Society.
Mary Lou Maher MIT Fall 2002 Production Systems for Rational Agents Agent-Based Virtual Worlds.
Computer Science and Engineering Department The University of Texas at Arlington MavHome: An Intelligent Home Environment.
Intelligent Agents Chapter 2. How do you design an intelligent agent? Definition: An intelligent agent perceives its environment via sensors and acts.
Virtual World = Architectural Design + Computational Elements Mary Lou Maher and Ning Gu ANZAScA 2002 KCDCC Virtual Worlds = Architectural Design + Computational.
Introduction to UML and Rational Rose UML - Unified Modeling Language Rational Rose 98 - a GUI tool to systematically develop software through the following.
The Agent and Environment Presented By:sadaf Gulfam Roll No:15156 Section: E.
1 Design Object Oriented Solutions Object Oriented Analysis & Design Lecturer: Mr. Mohammed Elhajj
Done by Fazlun Satya Saradhi. INTRODUCTION The main concept is to use different types of agent models which would help create a better dynamic and adaptive.
Service-Oriented Computing: Semantics, Processes, Agents
Intelligent Agents Chapter 2.
Service-Oriented Computing: Semantics, Processes, Agents
MANAGING KNOWLEDGE FOR THE DIGITAL FIRM
هوش مصنوعي فصل دوم عاملهاي هوشمند.
هوش مصنوعي فصل دوم عاملهاي هوشمند.
DrillSim July 2005.
Lesson Objectives Aims
What Are Databases? Organized by Dr. Farrokh Alemi PhD
AGENT MODELS.
Service-Oriented Computing: Semantics, Processes, Agents
Cognitive Dynamic System
Database System Concepts and Architecture
Social Abstractions for Information agents
DSS Concepts, Methodologies and Technologies
Presentation transcript:

An Agent Approach to Data Sharing in Virtual Worlds and CAD Mary Lou Maher, Pak-San Liew, John S Gero Key Centre of Design Computing and Cognition, University of Sydney

Collaborative Virtual Worlds

Object-Based Virtual Worlds

? environment percepts actions sensors effectors agent Autonomous Agents

What the world is like now Condition-action rules What action I should do now Agent Sensors Effectors Environment Rational Agents

Virtual World Agent Model Perception Conception Hypothesizer Action Sensors Effectors The World

Agents as a Production System Facts Perception Conception Hypothesizer Action Controller Sensors Effectors

Object Database (EDM) CAD #1 CAD #2 SPFSPF SPFSPF Application #1 Application #2 InterfaceInterface … … Virtual World (Active World) SPF: STEP Physical File Society of Agents : Building Monitor data Agents to Support Data Sharing

Object Database (EDM) CAD #1 CAD #2 SPFSPF SPFSPF Application X … Virtual World (Active World) DB Sensor FacadeFacade DB Effector VR Sensor VR Effector Working Memory Semantic Memory Procedural Memory Interface Agent action data pull data push action data pull data push AX SensorAX EffectorDB SensorDB Effector Facade Working Memory Procedural Memory Semantic Memory Interface Agent X SPF: STEP Physical File

Object Database (EDM) Virtual World (Active World) FacadeFacade DB Effector VR Perceptor VR Effector Working Memory Semantic Memory Procedural Memory Interface Agent VR Sensor Memory System Conceptor DB Sensor DB Perceptor data pull data push action data path

Object Database (EDM) Virtual World (Active World) FacadeFacade DB Effector VR Effector Agent Representation Of Model Interface Agent VR Sensor DB Sensor Controller Perception Conception Hypothesizer Action CAD System #1 STEP Physical File … CAD System #2 STEP Physical File Reasoning Component

Object Database (EDM) Virtual World (Active World) FacadeFacade DB Effector VR Effector Agent Representation Of Model Interface Agent VR Sensor DB Sensor Controller Perception Conception Hypothesizer Action CAD System #1 STEP Physical File … CAD System #2 STEP Physical File Reasoning Component Object Agent DB Effector VR Effector VR Sensor

Walls as defined in ArchiCAD Walls for collaborative design in Active Worlds Example: Agents for information Flows between ArchiCAD and Active Worlds

Roles of Walls Agent: An Example of an Interface Agent Maintains consistency of geometrical data between EDM database and AW. Controls two reversible processes of information flow. Creates wall agents.

Roles of Wall Agents: An Example of an Object Agent Assist walls agent to complete the information flow from EDM database to AW. Build wall objects in AW. Provide intelligent reasoning to the wall objects in AW.

Walls Agent Controls Info Flows From EDM database: senses a wall assembly of four separated walls. To AW: create four wall agents and passes the EDM wall sense data to the wall agents. Walls Agent Virtual World Wall Agent Society of Agents Object Database Wall Agent

Wall Agents Assist Info Flows From walls agent: each wall agent receives the EDM sense data of a specific wall. To AW: each wall agent creates a wall object based on the EDM sense data. In AW: each wall agent provide a kind of intelligent agency to the wall it builds. Walls Agent Virtual World Wall Agent Society of Agents Object Database

Walls Agent Controls Info Flows From AW: senses the changes of the wall objects built by the wall agents, during design collaborations. To EDM database: update the EDM database to reflect the above changes. Walls Agent Virtual World Society of Agents Object Database

Walls Agent and Wall Agents Hierarchical: walls agent creates wall agents. Walls agent communicates with both EDM database and AW. Wall agents focus on supporting intelligent agencies in AW. Any communication with EDM database is through walls agent.

Behaviours of Walls Agent Maintain consistency of geometrical data between EDM database and AW. Allows querying on non-geometrical information (regarding the whole wall assembly) specified in EDM database from AW.

Behaviours of Wall Agents Allow querying on non-geometrical information (regarding one specific wall each of the wall agent represents) specified in EDM database from AW. Reflexive and reflective behaviours during design collaborations: justify issues like fire rating, acoustics, disability control and etc.

Summary Object-based Virtual Worlds support synchronous collaborative design Rational agents provide autonomous and proactive data sharing capability between Virtual World platform and CAD Rational agents support modifications during a collaborative design session

Acknowledgements Coauthors: Pak-San Liew, John S Gero Ning Gu for development of wall agent behaviours Greg Smith for development of agent package for Active Worlds Funded by the CRC for Construction Innovation in Australia