EUCLID RTP 6 1 The GRACE Consortium Objective

EUCLID RTP 6. 1 The GRACE Consortium Objective: To accelerate the application of AI techniques and advanced HCI and software engineering in C 3 I workstations logica THE GR A C E CONSORTIUM

Size of EUCLID RTP 6. 1 • 21 Mecus of which company investment 24% • 125 man-years • 5 years duration - to September 1998 • 7 nations, 18 companies logica THE GR A C E CONSORTIUM

EUCLID RTP 6. 1 Participants EUCLID RTP 6. 1 Management Group UK DERA Denmark France Logica Matra Steria TERMA CSC Datacentralen CRI Italy Datamat Marconi Netherlands Norway Origin Signaal NLR TNO-FEL KOG SINTEF NDRE Spain INDRA CESAT The GRACE Consortium Grouping for Research into Advanced C 3 I for Europe logica THE GR A C E CONSORTIUM

Achieving RTP 6. 1 objectives ü demonstrate key AI and HCI methods and tools applied to C 3 I systems ü define and implement a workstation architecture able to accommodate existing and emerging methods and tools and to forge new standards ü evaluate using domain simulations of land tactical and naval scenarios ü encourage European collaboration in C 3 I R&D logica THE GR A C E CONSORTIUM

EUCLID RTP 6. 1 demonstrator Automated Report Analysis Wide Area Picture Naval Decision Support, Planning and Tasking Army Decision Support, Planning and Tasking Human-Computer Interface Framework CABLE C 3 I Application Building Environment - An environment for developing multi-agent systems logica THE GR A C E CONSORTIUM

Scenarios, simulation & testing Naval Scenario Naval simulator Report s Naval DSPT ARA WAP Army Scenario Army DSPT Army simulator Test Harness logica Report s Evaluation metrics HCI Framework CABLE EUCLID RTP 6. 1 Demonstrator THE GR A C E CONSORTIUM

User facilities • Uses Artificial Intelligence • Give a military benefit • Has a user interface logica THE GR A C E CONSORTIUM

Command tasks supported • Automated Report Analysis – Message handling and report analysis – Wide Area Picture compilation • Army Decision Support, Planning and Tasking – Terrain analysis – Course Of Action construction – Manoeuvre and Fire Support planning • Naval Decision Support, Planning and Tasking – Tactical Threat evaluation – Anti-Surface Warfare planning – Engagement Coordination logica THE GR A C E CONSORTIUM

Automated Report Analysis Reports from Simulators Message Handler Reduce the volume of data and ensure important information is extracted and prioritised. logica Wide Area Picture Compiler Wide Area To DSPT Picture Parse structured messages using Yacc++. Knowledge-based analysis of keywords and content. Common Object Model based on ATCCIS for WAP. Clustering techniques to identify groupings. Fuzzy logic inferencing to identify behaviours. THE GR A C E CONSORTIUM

Army Decision Support, Planning & Tasking Wide Area Picture Terrain Analysis Course of Action Construction Plan quicker than the enemy. Cope with complex constraints. Investigate more alternatives. logica Manoeuvre Planning Fire Support Planning Analyse terrain to identify Mobility Corridors. Compare own and enemy Courses Of Action Combine knowledge- and constraint-based planning. Simulated annealing for fire support planning. Tools for ORBAT browsing and working with time. THE GR A C E CONSORTIUM

Naval Decision Support, Planning & Tasking Wide Area Picture Tactical Threat Evaluation Anti-Surface Warfare Planning Engagement Coordination Planning Time-critical planning. Time, space, resource constraints. Investigate more alternatives. Knowledge-based recognition of enemy’s plan. Constraint-based manoeuvre planning. Anytime analysis of routes and intervisibility. Combined uncertainty- and constraint-based planning Case-based retrieval of relevant existing plans. logica THE GR A C E CONSORTIUM

Multi-agent architecture • Intelligent agents – logical next step combining OO and KBS – autonomous agents – inter-agent communication • Benefits of a multi-agent system – – – cope with complexity intuitive: analogy with human organisations heterogeneous, plug and play, supports integration transparent distribution across a network flexibly partition tasks between humans and machines emergent behaviour logica THE GR A C E CONSORTIUM

CABLE • CABLE – C 3 I Application Building Environment – software to develop and run multi-agent applications • CORBA-compliant – based on ORBIX – inter-agent communication using IDL • Specification, design and implementation of multiagent systems – analogy with human organisations logica THE GR A C E CONSORTIUM

C 3 I Application Building Environment CABLE Agent HCI Framework Agent: an autonomous intelligent software entity Agents communicate Agent Computer 1 Terrain features Mobility corridors Course of action Cooperative working Own forces situation Agent Computer 2 Agents can be distributed Based on CORBA, ORBIX, IDL, STL logica Based on ILOG Views THE GR A C E CONSORTIUM

Continuous, timely planning Deadline Cost of change Re-plan Act Commit Plan New info. Communicate Request & Deadline Cost/quality trade-off Anytime algorithms AI planning Resource request Resource logica Other processes Resource agent THE GR A C E CONSORTIUM

Groupworking of humans and agents Group working controller User interface Computer Agents logica THE GR A C E CONSORTIUM

Conclusions • Support heterogeneous AI techniques • Integrate using a multi-agent architecture • Common representation of military concepts • Architecture & techniques used in 10 projects, £ 2 M • More information – paper, Web site: http: //public. logica. com/~grace – for UK: Final Report, CD-ROM, FTP server logica THE GR A C E CONSORTIUM