1 PLAN RECOGNITION & USER INTERFACES Sony Jacob March 4 th, 2005.

Slides:



Advertisements
Similar presentations
CONCEPTUAL WEB-BASED FRAMEWORK IN AN INTERACTIVE VIRTUAL ENVIRONMENT FOR DISTANCE LEARNING Amal Oraifige, Graham Oakes, Anthony Felton, David Heesom, Kevin.
Advertisements

Division of Information Management Engineering User Interface Laboratory 11 Fall 09 Human Interface UI Evaluating Design Proposals for Complex Systems.
ARCHITECTURES FOR ARTIFICIAL INTELLIGENCE SYSTEMS
CA 2012 ELD Standards Appendix B
Towel: Towards an Intelligent ToDo List Ken Conley Jim Carpenter SRI International AAAI Spring Symposium 2007.
COMPSCI 105 S Principles of Computer Science 12 Abstract Data Type.
Systems Analysis and Design in a Changing World, 6th Edition
Systems Analysis and Design in a Changing World, 6th Edition
Approaches to Systems Development
Objective Develop an understanding of Appendix B: CA ELD Standards Part II: Learning About How English Works.
I-Room : Integrating Intelligent Agents and Virtual Worlds.
To Err is Human Computational Limits to Human Thinking : Implications for the Design of Human Centered Interfaces Raj Reddy Carnegie Mellon University.
Task Learning in COLLAGEN The COLLAGEN Architecture; Task Learning from Demonstrations Mitshubishi Electric Research Labs Andrew Garland, Neal.
Software Engineering Techniques for the Development of System of Systems Seminar of “Component Base Software Engineering” course By : Marzieh Khalouzadeh.
CAP 252 Lecture Topic: Requirement Analysis Class Exercise: Use Cases.
Think. Learn. Succeed. Aura: An Architectural Framework for User Mobility in Ubiquitous Computing Environments Presented by: Ashirvad Naik April 20, 2010.
Knowledge Acquisitioning. Definition The transfer and transformation of potential problem solving expertise from some knowledge source to a program.
The Data Mining Visual Environment Motivation Major problems with existing DM systems They are based on non-extensible frameworks. They provide a non-uniform.
Introduction to Software Architecture. What is Software Architecture?  It is the body of methods and techniques that help us to manage the complexities.
Presentation Outline  Project Aims  Introduction of Digital Video Library  Introduction of Our Work  Considerations and Approach  Design and Implementation.
CAD/CAM Design Process and the role of CAD. Design Process Engineering and manufacturing together form largest single economic activity of western civilization.
© Lethbridge/Laganière 2001 Chapter 7: Focusing on Users and Their Tasks1 7.1 User Centred Design (UCD) Software development should focus on the needs.
What is adaptive web technology?  There is an increasingly large demand for software systems which are able to operate effectively in dynamic environments.
Course Instructor: Aisha Azeem
Community Manager A Dynamic Collaboration Solution on Heterogeneous Environment Hyeonsook Kim  2006 CUS. All rights reserved.
Matthew J Mattia CSC  Cumbersome Code  Consistent/Predictable design (GUEPs #5, CD’s #10)  Display “proper” amount of information  Including.
Professional Growth= Teacher Growth
Chapter 1 The Systems Development Environment
Debbie Poslosky Taken from the Common Core Standard Document.
a Service Oriented Architecture
INFO415 Approaches to System Development: Part 2
ARTIFICIAL INTELLIGENCE [INTELLIGENT AGENTS PARADIGM]
CSE 303 – Software Design and Architecture
Author: James Allen, Nathanael Chambers, etc. By: Rex, Linger, Xiaoyi Nov. 23, 2009.
Recognition of meeting actions using information obtained from different modalities Natasa Jovanovic TKI University of Twente.
1 ICAS’2008 – Gosier, March 16-21, 2008 A Transformational Approach for Pattern-based Design of User Interfaces Costin Pribeanu Jean Vanderdonckt National.
Systems Analysis and Design in a Changing World, 6th Edition 1 Chapter 8 - Approaches to System Development.
Towards Cognitive Robotics Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Christian.
User Documentation Stored information about how to use a system –Reference manuals, tutorials, online help –Many systems show up with a diverse set of.
Through the development of advanced middleware, Grid computing has evolved to a mature technology in which scientists and researchers can leverage to gain.
Odyssey A Reuse Environment based on Domain Models Prepared By: Mahmud Gabareen Eliad Cohen.
Hyper/J and Concern Manipulation Environment. The need for AOSD tools and development environment AOSD requires a variety of tools Life cycle – support.
Chapter 6 – Architectural Design CSE-411, Dr. Shamim H Ripon.
1 Systems Analysis and Design in a Changing World, Thursday, January 18, 2007.
Chapter 8 Object Design Reuse and Patterns. Object Design Object design is the process of adding details to the requirements analysis and making implementation.
Service Oriented Architecture CCT355H5 Professor Michael Jones Suezan Makkar.
Systems Analysis and Design in a Changing World, Fourth Edition
Towards a Pattern Language for User Interface Design
Systems Analysis and Design in a Changing World, 6th Edition
1 Chapter 12. Web Information Integration Using Multiple Character Agents Soft computing Laboratory Yonsei University October 27, 2004.
Software Design Process
Chapter 6 – Architectural Design Lecture 1 1Chapter 6 Architectural design.
Generic Tasks by Ihab M. Amer Graduate Student Computer Science Dept. AUC, Cairo, Egypt.
Digital Libraries1 David Rashty. Digital Libraries2 “A library is an arsenal of liberty” Anonymous.
Activity Flow Design Gabriel Spitz 1 Lecture # 12 Guiding the flow of activities.
1 Introduction to Design. 2 Outline Basics of design Design approaches.
1 Galatea: Open-Source Software for Developing Anthropomorphic Spoken Dialog Agents S. Kawamoto, et al. October 27, 2004.
‘Activity in Context’ – Planning to Keep Learners ‘in the Zone’ for Scenario-based Mixed-Initiative Training Austin Tate, MSc in e-Learning Dissertation.
REST By: Vishwanath Vineet.
Advanced Web Technologies Lecture # 5 By: Faraz Ahmed.
SEESCOASEESCOA SEESCOA Meeting Activities of LUC 9 May 2003.
Basics of SOA Testing Assurance Services Unit 24 February 2016.
MERL 1 COLLAGEN: Applying Collaborative Discourse Theory to Human-Computer Interaction Charles Rich Candace L. Sidner Neal Lesh Mitsubishi Electric Research.
Study & Conclusions. Perspectives on Face-to-face Interaction Success at anticipating the actions of the other – Implies need for Model of user that supports.
Systems Analysis and Design in a Changing World, 6th Edition
A Speech Interface to Virtual Environment Authors Scott McGlashan and Tomas Axling Swedish Institute of Computer Science.
Agent-Based Dialogue Management Discourse & Dialogue CMSC November 10, 2006.
Andrew Garland, Neal Lesh, and Charles Rich Mitsubishi Electric Research Laboratories Responding to and Recovering from Mistakes during Collaboration.
User Documentation Stored information about how to use a system
Object Oriented Analysis and Design
Presentation transcript:

1 PLAN RECOGNITION & USER INTERFACES Sony Jacob March 4 th, 2005

2 AGENDA Motivation – Examples Introduction – Collaboration Plan Recognition vs. Traditional Systems Plan Recognition System “Steve” Conclusions Discussion

3 EXAMPLE: TRADITIONAL SYSTEM Microsoft Interactive help system Provides “jump-in” help instead of relevant on-going collaborative help Unable to comprehend overall goals and does not use task model Most users are unable to use this feature successfully

4 EXAMPLE: PLAN RECOGNITION SYSTEM Charles Rich Candy Sidner Neal Lesh Andrew Garland Shane Booth Markus Chimani 2004 Mistubishi Electric Research Laboratory

5 EXAMPLE: PLAN RECOGNITION SYSTEM Charles Rich Candy Sidner Neal Lesh Andrew Garland Shane Booth Markus Chimani 2004 Mistubishi Electric Research Laboratory

6 MOTIVATION Minimize amount of initiative required from user Create simple and consistent interfaces Guide user without limiting capability

7 COLLABORATION DIAGRAM SHARED ARTIFACT (GUI) GOALS COMMUNICATION PRIMIVITIVE ACTIONS PRIMIVITIVE ACTIONS Model for Plan Recognition in user interfaces

8 COLLABORATION FRAMEWORK Defined as an Interaction between “Agent” and User – Mutual Goals – Agent and user can perform actions – Agent uses Plan Tree Hierarchal partially ordered representation of actions to achieve goals Methods of interaction – Discussion between agent and user – User conveys intentions through actions – Agent solicits clarification

9 EXAMPLE: PLAN TREE Charles Rich Neal Lesh Andrew Garland 2002 Mistubishi Electric Research Laboratory

10 EXAMPLE: PLAN RECOGNIZER Charles Rich Candy Sidner Neal Lesh 1998 Mistubishi Electric Research Laboratory

11 RESPONSES Possible actions for an agent – Move user to next step of task (goal oriented) – Confirm completion of a goal – Allow user initiative – Focus user to current goal – Explain steps needed for a task – Discover and report incorrect actions

12 RESPONSES CONTINUED Traditional responses – Application dependent If(user pressed button A) Call function A Collaborative responses – Application independent If(user completed a step in current task) Go to next step of task

13 INTERACTION Traditional system – Limited range 1. Tutoring systems – Agent has majority of plan knowledge and initiative 2. Help system – User has majority of plan knowledge and initiative – Turn based interaction User performs action and agent responds

14 INTERACTION CONTINUED Collaborative System – Broad range System can shift incrementally within this range – Examples mentioned in Traditional systems represent extremes of this range Mode depends on current task – Non-turn based interaction User may perform 0 or more actions followed by 1 or more communications Agent may perform 0 or more actions followed by 1 or more communications

15 COMMUNICATION Traditional Communication – User initiates system actions through “commands” – Requires user to have knowledge of command Collaborative Communication – On-going Discourse between agent and user Define goals and how to achieve them Discuss task being performed – Requires user to have common goal with agent

16 HELP SYSTEMS Traditional help systems – Wizards, Tool-tips, Help Assistants – Attempt to compensate for lack of user knowledge – Requires separate interaction by user Collaborative help system – Integrated as part of the interface – User knowledge level does not affect level of help system interaction

17 EXAMPLE: WIZARDS Wizards – Provide a guided interaction for user – Partially follows collaborative paradigm Lacks versatility to allow user to take initiative Goals cannot be adjusted

18 ADVANTAGES OF DIAMOND HELP Provides consistent interaction paradigm – Different applications of Diamond help will be familiar to user – Appearance and operation remains the same Used for appliances and control systems Possible expansion allows for speech- enabled interaction – Agent speaks interaction and performs speech recognition for user

19 PLAN RECOGNITION SYSTEM EXAMPLE: STEVE Training agent – Steve (Soar Training Expert for Virtual Environments)Soar Virtual reality tutoring system, agent embodiment Uses plan recognition to guide user Actions taken by user are interpreted and compared to plan tree Steve orients user towards goal based on plan tree Advises user when a deviation is made from the plan tree or when help is needed for the next step Demo –

20 CONCLUSIONS Effective Collaboration – Abstract representation of situation Key to reuse and modularity of components – Well-designed task model Hierarchy must model tasks which complete a goal or sub-goal – Focus must be maintained If goal is modified, focus “stack” must be adjusted

21 CONCLUSIONS CONTINUED Complexity and scalability – Must be able to create abstract representations for various tasks – Depends on modularity and reusability of components – For complex interactions, must allow more direct user actions – Require Sub-goals for top goals

22 DISCUSSION Questions? How do we program a collaborative system? What are the drawbacks of creating this system? How does the agent realize a plan for a complex system? How would I implement this in my workplace environment?

23 PROGRAMMING TECHNIQUE Object Oriented Plug-ins – Use separate components to construct desired interface Composable and reusable components Abstract class definitions for dialogs Low-level functionality is controlled and monitored by high-level plan recognition system

24 References Note: Web addresses only