AIAI Presentation

1
(No Transcript)
2
__________________________________________________
___________________________ I-Room Intelligent
Collaboration Spaces for Emergency
Response http//www.aiai.ed.ac.uk/project/i-room/
Austin Tate AIAI, University of Edinburgh
3
__________________________________________________
__________ Outline of Talk Background in AI
Planning and Plan Execution Application to
Emergency Response I-X Technology Virtual
Worlds Technology I-Room
4
AIAI, University of EdinburghAI Planning Work

• Over 30 years of excellence in applied Artificial
  Intelligence planning research
• 1975-6 Nonlin original Hierarchical AI
  Planner
• 1983-1999 O-Plan Multi-Perspective Planning
  Architecture and Planning Web Service
• 2000-present I-X Issue Handling, Planning and
  Collaboration Architecture
• ltI-N-C-Agt Knowledge Elicitation, Encoding,
  Modelling, Representation, and Management
• Wide range of collaborations, projects and
  application outcomes
• Focus for last decade on emergency response and
  contribution to a helpful environment of
  collaborating ubiquitous computational agents

5
Edinburgh AI Planners in Productive Use
Used in search and rescue operations for the UK
Royal Air Force and the US Joint Forces Joint
Personnel Recovery Agency
1975 Electricity Turbine Overhaul Procedures for
the UKs Central Electricity Generating Board
(CEGB)
1982 Voyager Mission Planning for NASAs Jet
Propulsion Laboratory (JPL)
Used in commercial applications as diverse as
robot planners, Nynas tanker delivery scheduling,
and helpdesks for financial services call centers
1996 Used for spacecraft assembly, integration
and verification on the European Space Agencys
Ariane IV rocket
http//www.aiai.ed.ac.uk/project/plan/
6
e-Response Vision

• The creation and use of task-centric virtual
  organizations involving people, government and
  non-governmental organizations, automated
  systems, grid and web services working alongside
  intelligent robotic, vehicle, building and
  environmental systems to respond to very dynamic
  events on scales from local to global.

• Multi-level emergency response and aid systems
• Personal, vehicle, home, organization, district,
  regional, national, international
• Backbone for progressively more comprehensive aid
  and emergency response
• Also used for aid-orientated commercial services
• Robust, secure, resilient, distributed system of
  systems
• Advanced knowledge and collaboration technologies
• Low cost, pervasive sensors, computing and
  communications
• Changes in building codes, regulations and
  practices

7
E-Response Relevant AI Technologies

• Sensors and Information Gathering
• sensor facilities, large-scale sensor grids
• human and photographic intelligence gathering
• information and knowledge validation and error
  reduction
• semantic web and meta-knowledge
• simulation and prediction
• data interpretation
• identification of "need"
• Emergency Response Capabilities and Availability
• robust multi-modal communications
• matching needs, brokering and "trading" systems
• agent technology for enactment, monitoring and
  control
• Hierarchical, distributed, large scale systems
• local versus centralized decision making and
  control
• mobile and survivable systems
• human and automated mixed-initiative decision
  making
• trust, security
• Common Operating Methods
• shared information and knowledge bases

8
Adapted from H. Kitano and  S. Tadokoro, RoboCup
Rescue A Grand Challenge for Multiagent and
Intelligent Systems, AI Magazine, Spring, 2001.
9
Adapted from H. Kitano and  S. Tadokoro, RoboCup
Rescue A Grand Challenge for Multiagent and
Intelligent Systems, AI Magazine, Spring, 2001.
10
Examples of AIAIs Work on Cooperative Emergency
Response

• 1991-9 Coalition NEO Non-combatant Evacuation
  Operations
• 1994-6 SAR RAF Search and Rescue Coordination
  Centre (Pitreavie, UK)
• 1998-9 SUO PDA US Army Hostage Rescue in Urban
  Terrain (Fort McKenna, US)
• 2000-2 CoAX Coalition Agents eXperiment (4
  countries, 30 organizations)
• 2000-7 CoAKTinG Collaborative Advanced
  Knowledge Technologies for e-Response
• 2002-3 CoSAR-TS Coalition Search and Rescue
  Task Support
• 2004-5 Co-OPR Collaborative Operations for
  Personnel Recovery
• 2006-9 OpenKnowledge Emergency Response for
  Environmental and Urban Incidents
• 2006-9 FireGrid Emergency Response in the
  Built Environment

11
__________________________________________________
__________ I-X Technology
12
_______________________________ I-X
Intelligent Technology http//www.aiai.ed.ac.uk/pr
oject/ix/ The I-X Technology programme has 5
aspects Systems Integration - A broad vision
of an open architecture for the creation of
intelligent systems for synthesis tasks (such as
planning, design and configuration) based on the
handling of "issues" and the management or
maintenance of the constraints describing the
product of the process. Representation - a core
notion of the representation of a synthesis
process and the product(s) of such processes as a
set of nodes making up the process or product,
along with constraints on the relationship
between those nodes, a set of outstanding issues,
and annotations related to these - ltI-N-C-Agt -
Issues, Nodes, (Critical and Auxiliary)
Constraints and Annotations. Engagement with
various standards setting groups is a part of
this work. Reasoning - the provision of reusable
reasoning and constraint or model management
capabilities. User Interfaces - to understand
user roles in performing collaborative activities
and to provide generic modules which present the
state of the processes they are engaged in, their
relationships to others and the status of the
artefacts/products they are working
with. Applications - work in various application
sectors which will seek to create generic
approaches (I-Tools) for the various types of
Task in which users may engage
13
I-XMulti-Agency Emergency Response Planning,
Execution, and Task-Oriented Communications
14
I-X Approach

• The I-X approach involves the use of shared
  models for task-directed communication between
  human and computer agents
• I-X system or agent has two cycles
• Handle Issues
• Manage Domain Constraints
• I-X system or agent carries out a (perhaps
  dynamically determined) process which leads to
  the production of (one or more alternative
  options for) a product
• I-X system or agent views the synthesised
  artefact as being represented by a set of
  constraints on the space of all possible
  artefacts in the application domain

15
ltI-N-C-Agt Framework

• Common conceptual basis for sharing information
  on processes and process products
• Shared, intelligible to humans and machines,
  easily communicated, formal or informal and
  extendible
• Set of restrictions on things of interest
• I Issues e.g. what to do? How to do it?
• N Nodes e.g. include activities or product
  parts
• C Constraints e.g. state, time, spatial,
  resource,
• A Annotations e.g. rationale, provenance,
  reports,
• Shared collaborative processes to manipulate
  these
• Issue-based sense-making (e.g. gIBIS, 7 issue
  types)
• Activity Planning and Execution (e.g.
  mixed-initiative planning)
• Constraint Satisfaction (e.g. AI and OR methods,
  simulation)
• Note making, rationale capture, logging,
  reporting, etc.
• Maintain state of current status, models and
  knowledge
• I-X Process Panels (I-P2) use representation and
  reasoning together with state to present current,
  context sensitive, options for action

Mixed-initiative collaboration model of mutually
constraining things
16
I-X Process Panels and Related Tools
Process Panel
Action pop-upThis shows choices for actions that
can be carried out to perform the listed
activities. The list is context sensitive, using
knowledge of other agents and Standard Operating
Procedures.
Other resourcesVarious viewers can be linked in
to show relevant information in an appropriate
form.
Domain Editor Used to encode Standard Operating
Procedures.
I-Plan toolIntelligent planning aid. Can be used
to complete partial plans, or to explore
alternative options.
Intelligent Process PanelShows issues to
address, activities to-do, various constraints
on the activities, and annotations.
Message windowInstant chat is linked to the
structure of ongoing activities, turning instant
messaging into intelligent messaging.
17
I-P2 aim is a Planning, Workflow andTask
Messaging Catch All

• Can take ANY requirement to
• Handle an issue
• Perform an activity
• Respect a constraint
• Note an annotation
• Deals with these via
• Manual activity
• Internal capabilities
• External capabilities
• Reroute or delegate to other panels or agents
• Plan and execute a composite of these
  capabilities (I-Plan)
• Receives reports and interprets them to
• Understand current status of issues, activities
  and constraints
• Understand current world state, especially status
  of process products
• Help user control the situation
• Copes with partial knowledge of processes and
  organizations

18
__________________________________________________
__________ Our Own Helpful Work
19
e-Response Related Work

• CoAKTinG (Collaborative Advanced Knowledge
  Technologies in the Grid) also I-Rescue (Kobe),
  AKT e-Response and OpenKnowledge
• Linking issue handling, argumentation, process
  support, instance messaging and agent presence
  notification
• Range of natural, industrial and other emergency
  scenarios
• CoSAR-TS (Coalition Search and Rescue Task
  Support)
• Use of OWL ontologies and OWL-S described
  services to describe components
• Co-OPR (Collaborative Operations for Personnel
  Recovery)
• Use of OWL ontologies and OWL-S described
  services to describe components
• FireGrid
• to establish a cross-disciplinary collaborative
  community to pursue fundamental research for
  developing faster than real time emergency
  response systems using the Grid
• e-Response
• Creation and use of task-centric virtual
  organizations to respond to highly dynamic events
  on scales from local to global
• Flood, metropolitan emergency and industrial
  accident scenarios

20
Advanced Knowledge Technologies,Collaboration
Aids, Semantic Web
http//www.aktors.org/coakting
21
Oil Spill (Industrial Accident) Scenario

• Oil spill off Fawley Marshes close to
  Southampton
• Scientific advisors and tools to assist emergency
  responders
• Links to Semantic Web Services

22
Metropolitan e-Response Scenario

• AKT e-Response Scenario
• Cargo airplane crash over central London
• Multiple fires with damage and potential spread
• Injured people with medical and evacuation issues
• Much information of potential use
• Many coordination issues
• Use of Kobe earthquake simulation base

23
Kobe Earthquake Simulation

• RoboCup Rescue Simulator
• Simulates the Kobe earthquake
• Sends sensorial information to agents, receiving
  back action commands
• I-X Agents
• Divided in three hierarchical decision-making
  levels
• Support ideas such as activity oriented planning,
  coordination and knowledge sharing
• Interaction I-X to Kobe Simulator
• Information from RCRS to I-X is converted to the
  ltI-N-C-Agt format

24
Kobe Earthquake Simulation
25
OpenKnowledge e-Response

• Amsterdam
• Barcelona
• Edinburgh
• Open University
• Southampton
• Trento

26
OpenKnowledge e-ResponseFlooding Scenario in
Trentino
OpenKnowledge e-ResponseFlooding Scenario in
Trentino

• Main hazard for Trentino is represented by a
  flooding of the Fiume Adige and its related
  fluvial network
• Our goal is to describe a flooding event and to
  describe how a system like OpenKnowledge could be
  useful
• Based on
• Interviews with local authorities
• Plan of Civil Protection for Trento city
• Guidelines for the civilian protection of the
  Trento Province
• A multilingual glossary of civil protection for
  EU citizens, Project INTERREG IIIC, October 2005.

• Amsterdam
• Barcelona
• Edinburgh
• Open University
• Southampton
• Trento

27
FireGrid Aims
http//firegrid.org

• Mission statement
• To establish a cross-disciplinary collaborative
  community to pursue fundamental research for
  developing real time emergency response systems
  using the Grid.
• Initial domain is fire emergencies.
• Challenges
• Sensing instantaneous and continuous relay of
  data from emergency location to response system
  via the Grid.
• Modelling model the evolution of fire and impact
  on building, and relate this to intervention
  alternatives and evacuation strategies.
• Forecast all simulations, analyses and
  communications done in super real-time.
• Response effective co-ordination of response
  with intelligent decision-support system.
• Feedback continuously update simulations,
  predictions and response using latest data from
  sensors and responders.
• Status
• FireGrid Community Club users, business,
  academia, 2005 on.
• DTI/University of Edinburgh/Industry-funded
  project, total value 2.23M, April 2006 to April
  2009.

28
http//firegrid.org
Other Universities
29
FireGrid Technologies
http//firegrid.org
Tens of Thousands of Sensors Monitors
Emergency Responders
Knowledge Systems, Planning Control
Maps, Models, Scenarios
Computational Grid
Super-real-time Simulation
30
I-X as C3I Interface in FireGrid
http//firegrid.org
31
Safety and Companion Robots
32

• Co-OPR
• Collaborative Operations for Personnel Recovery
• Collaborative Sensemaking, Planning and Execution
• via sharing of issues, activity options,
  constraints and annotations
• Austin Tate, Jeff Dalton, Jussi Stader, Gerhard
  Wickler
• AIAI, University of Edinburgh
• Simon Buckingham-Shum, Al Selvin
• KMi, Open University, Compendium Institute
  Verizon
• Jeff Hansberger
• US Joint Forces Command J9 Expt.

33
Typical Rescue Coordination Center
information board
incident board
asset board
fax operators desk
computer operators desk
JPRC directors desk
area map
bin
34
Typical Rescue Coordination Center
35
(No Transcript)
36
The Role of I-X inEmergency Response Systems

• Supports the organization and communication of
  search and rescue components
• Uses ltI-N-C-Agt shared model for task-directed
  cooperation between human and computer agents
• Allows task coordination via refinement of plans,
  delegation of activities and calls on services
• Provides reasoning, constraint management and
  other functional capabilities as plug-ins

37
I-X Modes for Preparedness,Training and Emergency

• Design Mode
• Supporting domain knowledge capture, modelling
  and management, generation of pre-built options,
  and identifying key tasks in the domain
• Training Mode
• What-if exercises, rehearsal, lessons-learned,
  key topics
• Response Mode
• Planning, decision support and execution

38
I-X in a Rescue Coordination Center
Communications Simple Chat Structured
chat Information sharing Task Support Checklists T
o do list Progress reporting Plan option
aids Whiteboards Incident Weather/Codes/Info Asset
s Mapboards Web Resources Fact Book Phone
List Codes Active Mission Folders
39
__________________________________________________
__________ Helpful Organizations
40
Combined Civilian Military AssistanceE.g.
Unified Assistance CSF-536
41
(No Transcript)
42
(No Transcript)
43
(No Transcript)
44
MPAT Needs

• Sensor data flows
• Accurate information
• Correlation and validation
• Relevant and understandable communication
• Contact making
• Requests for assistance and matching to available
  capabilities
• Standard Operating Procedures and alarms
• Planning and coordination
• Communication and collaboration
• Scale and robustness

45
(No Transcript)
46
Emergency Operations Vehicles
47
http//www.capwin.org/
48
General e-Response Organization Needs

• Sensor data flows
• Accurate information
• Correlation and validation
• Relevant and understandable communication
• Contact making
• Dealing with requests for assistance and matching
  to available capabilities
• Standard Operating Procedures and Alarms
• Planning and coordination
• Scale and robustness

49
__________________________________________________
__________ Virtual Worlds Technology
50
Virtual Worlds for Work, Play Help
51
Social Networking
Collaborative Systems
Instant Messaging
Community Knowledge
Semantic Web
Agent Presence
Content Creation
Teleconferencing
Intelligent Agents
Web Services
VoIP
3D Views onto the Internet
52
(No Transcript)
53
(No Transcript)
54
UoE Departments in Vue

• University Offices
• Corporate PR Office
• Development Alumni
• Information Services
• IT User Services
• Library and Collections
• Talbot Rice Gallery
• School of Informatics
• Knowledge Transfer Commercialisation Center
• Edinburgh-Stanford Link
• AIAI e-Response, I-Room
• HCRC/ICCS Eye Tracking Experiments Group
• School of Education
• MSc in e-Learning
• Higher Community Education
• Child Development
• Management School
• School of Arts, Culture Environment
• School of Medicine Veterinary Medicine

55
(No Transcript)
56
Vue Uses of Virtual Worlds

• Awareness, Recruitment Promotional Activities
• e-Learning and Social Networking Course Support
• Distance Learning
• Continuing Professional Development
• Innovative Assessment Practices
• PhD Research Projects using Simulations
• Collaboration
• Links from Real to Virtual Meeting Spaces
  Teleconferences
• Alumni Networking
• Courses
• MSc in Entrepreneurship Business Building
• MSc in Design Digital Media
• MSc in e-Learning
• Management School Courses
• Coming Soon
• Live Event Streaming into Virtual Worlds
• 3D View onto Historical Materials, Arts and
  Museum Style Access
• Further MSc and other courses, Field Trips
• Communication for Autism

57
(No Transcript)
58
(No Transcript)
59
(No Transcript)
60
(No Transcript)
61
__________________________________________________
__________ Virtual Collaboration Centers and
I-Room
62
(No Transcript)
63
(No Transcript)
64
(No Transcript)
65
(No Transcript)
66
(No Transcript)
67
(No Transcript)
68
Helpful Environment

• The creation and use of task-centric virtual
  organizations involving people, government and
  non-governmental organizations, automated
  systems, grid and web services working alongside
  intelligent robotic, vehicle, building and
  environmental systems to respond to very dynamic
  events on scales from local to global.
• ltI-N-C-Agt shared conceptualization as a basis for
  task-oriented communication and collaboration in
  emergency response environments.

69
Helpful Environment
Tate, A. (2006) The Helpful Environment
Geographically Dispersed Intelligent Agents That
Collaborate, Special Issue On "The Future of AI",
IEEE Intelligent Systems, May-June 2006, Vol. 27,
No. 3, pp 57-61. IEEE Computer Society.
70
__________________________________________________
__________ Further Information www.aiai.ed.ac.u
k/project/plan/ www.aiai.ed.ac.uk/project/ix/ ww
w.aiai.ed.ac.uk/project/i-room/ i-x.info
e-response.org