Fusion Based Knowledge for the Objective Force: A Science and Technology Objective Presented August 20, 2003 By Joan E. Forester Workshop on Satellite Data Applications and Information Extraction
Army Science Board* Estimates of Technology Readiness for Select Fields Technology Readiness Levels Enabling Technologies Aided ATR Smart Portals to push pull Mobile Wireless (pagers, PDA) Malicious Mobile Code Visualization - Presentation Data Extraction Virtual environment Automatic routers, priorities 2004 3 6 6 1 4 6 3 5 Data fusion, information fusion 2 3 Secure Intelligent Agents Encryption and authentication Exploitation Algorithms and assist RTIC Future Internet Individual Soldier Tech. Collaboration Technologies Sync Distributed Secure Data base Secure Access Technology Biometrics Translingual language transcription Soldier Education Associates Next Generation Internet 2 4 2 5 6 4 3 4 6 6 6 5 7 2 8 9 7 8 6 8 7 9 *ASB Study - Knowledge Management and Information Assurance, dated 09/01 2008 3 9 9 2 7 8 6 8 Commercial 2 9 7 3 6 8 6 5 7 6 2 9 5 8 5 5 7 7 5 9
Joint Directors of Laboratories (JDL) Fusion Levels Level 0: Sensor-level target identification - Processing raw data near the sensor Level 1: Where is the enemy? (Multi-sensor correlation) - Multi INT Correlation for highly detailed Enemy Situation -------------------------------------- Level 2: What is the enemy doing? - Aggregation for COP Interpreting activities in context Develop hypotheses about current ECOA Level 3: What are the enemy’s goals? - Future ECOA’s - Predict Intent and Strategy Level 4: How should we respond? − How do we redirect the ISR system to get better SU?
DARPA Programs Related to Levels 2 & 3 Fusion Where What When Who Level 2: Situation Refinement Level 1: Object Refinement Why How Level 3: Global Threat Refinement How well Level 4: Performance Refinement DATA FUSION PROCESSING ENABLING TECHNOLOGIES physical objects individual organizations events Evidence Extraction & Link Detection specific aggregated environment & enemy tactics local Dynamic Data Exchange global enemy doctrine objectives & capability Co. ABS DAML RKF CPOF local global friendly vulnerabilities & mission Dynamic Tactical Targeting Battle Adv. Assessment & ISR Data Mgmt Dissemination (SUO-SAA) Ref: DARPA IXO Information Fusion Workshop, final briefing, 28 Feb 2002 options needs effectiveness battle theatre resource management local global
Why We Need Fusion Information volume exceeds war-fighter capabilities to develop situational understanding required for planning and acting within the adversary’s decision cycle Echelon # Msg’s per hour* # full time Analysts, w/ workstations Latency for Level III Fusion 15 1 Hr Legacy Division 400 -600 Future UA Bde 17, 000** 0 -6 (TBD) NRT (req) Future UA Bn 4, 000** Zero NRT (req) Future UA Company 1, 200** Zero NRT (req) * Current and estimated bottom-up sensor feeds; Top-down feed is much larger ** (Date) Sensor briefing from CG, USAIC&FH to Dir, UAMBL / MAPEX indicates an order of magnitude increase
Reports Without Fusion UE Bde COP Bn COP Plus…Information from echelons above UA 170 K+ Reports/Hour Report count based on DCGS-A MAPEX results using Caspian Sea Scenario Co COP Co Reports generated from FCS EO/IR and COMINT Sensors only. Add MASINT sensors and reporting at UA goes to @ 600 K/hour. 56 K+ Reports/Hour m pl ex it 18 K+ Reports/Hour y PLT COP Mr. Hayward’s Brief, Force Operating Capability (FOC) S&T Assessment Review 6 K+ Reports/Hour
FCS C 4 ISR Software Brick “Fusion” is a component of the C 2 Application Software Warfighter Machine Interface (WMI) Administration Applications Do. D Enterprise Applications Information Warfare Comm Systems Airspace Mgt C 2 Weapon Sys Mission Applications Vehicle Applications SOS/Domain Application Programming Services (API’s. Applets/Servlets, …) SOS Knowledge Management Services Info Access & Control Services Interoperability Services Security Services Network Centric Services Distributed Framework System, Fault Mgt, Health Monitoring Information Discovery Services Information Dissemination Services Tactical Configuration Services User Profile Services SOS Framework Services System Agent Framework Services Inference Engine Services Web Services Security Services Routing Services Distribution Middleware Services Logical Storage Database & Retrieval Operating System Abstraction Services Virtual Memory Run-Time Process Threads Sockets Select IO Comp Dynamic Linking Memory Mapping Operating System Virtual Memory COTS NDI Common Support Services Communications Process/Threads Network Foundation – (e. g, LAN, Hardware Device Drivers ) Shull FCS LSI Concept Brief at MAPEX COTS NDI
The Objective Force Sensor Grid Interdependent, Multi-Echelon, Cross-BOS, Net. Centric SPACE SYSTEMS ) BS /G BS l (I a ion U 2 R at /N ter a Joint ISR to FCS Via DCGS-A GLOBAL HAWK RJ MC 2 A he T Direct Linkage(s) to CDR, Staff & Shooters JSTARS UE ) X XX ACS / XX ( ALLIED/ COALITION TUAV PREDATOR X) A ( (II) U A U UA (I) PROPHET Theater Presented by Col Ron Nelson 11 Dec 02 DCGS-A UE Right Information…Right Time…to the Point of Decision 2 R
FBKOF: Overcoming Information Overload BARRIERS • • • Limited computational models Knowledge is METT-TC dependent COTS knowledge acquisition technology too slow Information sources poorly integrated Knowledge discovery tool limited APPROACH • • • Cognitive engineering and user-centered design Apply Blackboard architecture, diverse knowledge representation and inferencing, approximation techniques, and “to each his own” cooperative human-machine problem solving Exploit DARPA rapid knowledge formation technologies to develop knowledge-intensive reasoning for interpretation Leverage Semantic Web techniques for source integration. Integrate and tailor COTS tools for directed knowledge discovery DELIVERABLES • • SW for knowledge generation and explanation to answer PIR’s in a timely manner Ontology based information agents for objective force systems User-directed knowledge discovery tools Modeling and simulation tools
Schedule FY 03 FY 04 Tasks • Baseline / Assess Knowledge tools and Fusion Algorithms • Knowledge Acquisition FY 05 FY 06 FY 07 2 3 4 3 4 • Mining-Component Development • Knowledge Infrastructure Development 3 4 5 • Modeling and Simulation Support • C 4 I experiments and evaluations • Transitions Decision Points TOTAL $24. 3 CECOM ARL 1. 7 2. 1 2. 2 2. 1 3. 0 2. 1 4. 0 1. 0
Notional Blackboard Architecture for Fusion Subsystem Levels of Analysis Answers to PIRs COAs and COA Fragments Relations between objects (command hierarchy, behavioral) Events & Activities Objects (equipment and platform-level entities) Knowledge Sources Blackboard Plans KS • History : • Doctrine • Terrain & Weather • Activities KS • Force Structure : • Commo Patterns • Tactics • Terrain & Weather Sensor-Data Fusion KS : • Platform & Equipment Classification and Movement Attributes • Terrain & Weather CONTROL
Providing a Knowledge Environment (Agents and Ontologies) Interfac e Data- Database OLAP GOALS • Minimize burden on user – • • Automate well-structured problems – DBMS Support ill-structured problems Interface tuned to the task and to the user Task centered, not tool centered Support information push and pull Support collaboration Accommodate multi-modal data types Visualization tools to support understanding Smarter integration of sources Knowledge Base Fusion – Limit the number of required retrievals (bandwidth) – – Minimize exploration after retrieval (time constrained) Automate and personalize the process Interfac e Web Search Engine
Why Agents? What are they? (ATL) • • The concept of software agents represents a new way of applying artificial intelligence techniques such as machine reasoning and learning. Software agents are computer programs designed to operate in a manner analogous to human agents. Human agents, such as real-estate agents, carry out tasks on your behalf using expertise you may not have. Software agents carry out information processing functions in the same manner. Agents can be thought of, in software engineering terms, as a step beyond the objects of object-oriented programming. Whereas objects are passive entities that must be invoked to execute, agents use AI mechanisms such as machine reasoning to actively operate as autonomous entities. Research has shown greatest utility in multi-agent applications is information mgmt. How do they help? • • • Huge problem broken into small components Much can be handled in parallel rather than serially Reflect changes in priorities without coding changes Technology is coming of age Many web applications [6, 9]: mediator, personal assistant Active, persistent sw components that perceive, reason, act and communicate -- Huhns
Agent Functionality • • • Filter (ATL) Monitors (ATL) Alert (ATL) Retrieve – pull (ATL) Disseminate – push (ATL) Adapt to the user priority (CTA, OH S U) Adapt to the environmental changes (CTA, OH S U) Mediate across legacy systems (UMD) Intruder detection (HPC, UMINN) Policy enforcement (CTA, U W Fl) PROBLEMS • Agents new, few success stories and limited developmental environments • Present complex parallel processing paradigm • Issues of teaming, security, mobility, efficiency • Establishing optimum ontology size/approach • Integrating ontologies across heterogeneous sources (single, multiple, hybrid)
Why Ontology-Based? • Information heterogeneous (type, syntax, semantics) • Heterogeneity of semantics results in conflicts (naming, scaling, confounding) • Ontologies explicitly describe information sources • Identify and share formal descriptions of domain-relevant concepts • Identify classes of objects and organized them hierarchically • Characterize classes by the properties they share • Identify important relationships between classes Brigade level Mediato r Agent DCGS-A Data Store Single-INTs Fusion Prioritzer Reasoner Agent Commo Module Agent Ontology COMINT ELINT MASINT Imagery Images/ Video/ Audio MTI HUMINT Other Multimedia Open Source External COPs (above/below/beside) COP COP COP MIDB Blue Asset Mgmt Terrain Weather Targets CCIR/ OPLANs Alert/ Search Criteria All Source Fusion (ASFDB) Units Pieces of Equipment Facilities Events Individuals Organizations And their interrelationships
Providing User-Directed Knowledge Discovery Tools • • On Line Analytical Processing (OLAP) emerged in the early 90’s (Inmon, Codd) Multi-dimensional data structure Better (more flexibly) address decision process (forecasting, time-series analysis, link analysis) More natural & efficient storage and retrieval mechanism Provides a mechanism for accommodating time and space Flexible graphical interface Commercial Product Natural Transition to Data Mining PROBLEMS • • • Representation of space and time Complexity of user interface Inefficiency of algorithms
Partners and Leveraged Programs • • • RDECOM(provisional) RDEC I 2 WD Army G 2 (Woodson/ ISR Working Group) Huachuca (Schlabach – Cahill) BAH (Brown - Army MI SME) ADA CTA (U W Fl, UMD, SA Tech) ARMY HPC Program (UMINN, Data mining) ARL CENTERS OF EXCELLENCE (CAU, Data mining) PENN State (Yen, Teaming Agents) C 2 CUT and Warrior’s Edge DARPA: Taylor (RKF, Staff Officer in a Box); Alex Kott (AIM); Burke (DAML, Co. ABS Grid) • ENDORSEMENTS: BCBL-H; BCBL-L; PM DCGS-A, PM IE, PM FCS
Status FY 03 : (1) Conduct cognitive engineering with SME to identify users’ goals, tasks and info requirements most germane to the Intel BOS in support of higher level fusion -- identify candidate tasks to focus on in FY 04. (2) Develop initial human-machine and software-level evaluation plan for fusion. Design and conduct pilot experiment for fusion. (3) Develop a small prototype Knowledge Environment (KE) that uses agent techniques to access the two highest priority data sources. This will establish a baseline system on which to build in out years, demonstrate our initial concept of the use of ontologies by the KE agent communities, and provide a mechanism for integrating CECOM’s fusion modules. (3) Conduct an internal demonstration of the baseline system to support refinement of the HCI/KE concepts. FY 04 : (1) Integrate two more data sources into the baseline system to assess the extensibility of the infrastructure and provide the CECOM fusion module access to a greater variety of data sources. (2) Develop and populate a prototype (1) User involvement multi-dimensional data structure for user directed data mining or knowledge discovery (KD). This will allow us to explore the use of user-in-the-loop fusion tools to supplement CECOM automated fusion techniques. (3) Conduct an (2) Working with ATL’s EMAA to establish internal joint CECOM/ARL demonstration to refine the HCI and KE concepts. mediators and baseline architecture. FY 05 : (1) Modify the KE system architecture, based on the FY 04 evaluation and integrate 5 th data/information source. Warrior’s Edge (WE) link may increase the (2) Jointly demonstrate to DCGS-A and user communities the integration of CECOM’s fusion algorithms, the usersize and scope targeted transition system developers directed KD tools and 5 data sources. This provides a formal review for theof this effort. ATL also (FCS/DCGS-A) of the refined approach at a point when working a portion of CECOM’s fusion effort. all the required components are in place. FY 06 : (1) Finalize user-directed mining scripts and system architecture, scheduled for late September. will be to (3) Internal demo based on FY 05 evaluation. The goal simplify access to the KD tools. (3) Develop information agents to support I 2 WD fusion task. with WE. More visible demo may occur These agents will be directed toward increasing the efficiency and effectiveness of information push/pull. (2) Internally demonstrate automated cross-source integration using the enhanced agent environment and work with CECOM to evaluate and enhance the (4) (+) CAU/UMINN Date Mining demo system’s functionality. FY 07 : (1) Finalize system development, based on FY 06 evaluation. (2) Jointly conduct the final system demonstration and evaluation to support system transition to FCS LSI contractor, PM-CGS, and PM-IF.
Conclusion • Goal: Facilitate quick war fighting decisions that fully leverage the huge volumes of information that the UA will receive. – RDECOM I 2 WD user-centered fusion system design (architecture, inferencing techniques, algorithms, representations, and HCI) – ARL knowledge management infrastructure – ARL user-directed knowledge discovery tools • Proposed relatively modest software readiness levels, due to difficulty of the task, but driving to get a transition: – PM DCGS-A demonstration in 05, with a transition decision point in 07 – PM IE demonstration in 05, transition decision point in 07 – Demonstration to FCS LSI 05, AMSAA transition decision point in 07 • Data mining resources far exceed initial expectations. • First year of agents development will receive a boost from related ARL programs (C 2 CUT, Warrior’s Edge) • Strong support from user community
Скачать презентацию Fusion Based Knowledge for the Objective Force A
11ee23cb311b5ea2b2f8f9622e6c134c.ppt