Intelligent Surface Threat Identification System (ISTIS)

1
Intelligent Surface Threat Identification System
(ISTIS)

• IEEE Aerospace Conference 2007

Presented by Robert Richards, Ph.D. Richards_at_S
tottlerHenke.com www.stottlerhenke.com
2
Objectives

• Improve Littoral ID Process, quality, and
  efficiency
• Better ID estimations from available data
• Sooner ID determinations
• Prevention of ID Surprises
• Better use of scarce ID resources
• Investigate littoral, surface ID techniques
• Implement in the Intelligent Surface Threat ID
  System (ISTIS)

3
Related Projects

• Intelligent Identification Software Module (IISM)
• LCS Undersea Threat Assessment
• TAO ITS and ITS authoring tool
• GRTS TAO ITS
• Navy Tactics Representation and Execution System
  (TRES)
• Visual Intelligent Behavior Authoring (SimBionic)
• Advanced Early Warning Real-Time Advisory System
  (AEW/RTAS)

4
MotivationCurrent Identification Problems

• Wide variation in ID abilities
• Knowing whose-who even after ID information
  received
• Track Split/Merge
• Maintaining Competing Hypotheses for a track
• Classified Automatic Track ID Problems
• Remembering Track History (both short and
  long-term)
• Analyzing behavior/correlations
• Correlating new tracks with previous tracks
• Knowing/Executing Optimal ID Procedures
• Quickly Assessing Threat

5
Architecture
6
AI Techniques

• Truth Maintenance
• Case-Based Reasoning
• Behavior Transition Networks (BTNs)
• Fuzzy Logic
• Pattern Recognition/Learning
• Constraint-Based Planning, Scheduling, and
  Resource Optimization
• Knowledge Elicitation / Cognitive Task Analysis
• Expert Systems

7
Example of Density of Contacts that Need
Monitoring and Assessing
8
Example Scenario 1
9
Example Scenario 2.1
10
Example Scenario 2.2
11
Example Scenario 2.3
12
Example Scenario 2.4
13
Example Scenario 2.5 (Pause)
14
Example Scenario 2
15
ISTIS Capabilities

• Intelligent Tactical Memory
• Track attributes (position, velocity, ID
  information, History)
• Associate previous tracks with new track
  information.
• Complete track history (track merge or ID swap)
• Past Relevant Tracks/Patterns used to
  recommend/warn
• Definable ID, Threat Assessment, Notification
  Criteria
• Intelligent Track History Analysis
  (position/velocity/proximity/interactions/behavior
  correlations) to estimate associations hostile
  intentions
• Multiple Competing Hypotheses for ID (type/owner
  country) with Hierarchy of possible ID values
  (type, color/country)

16
ISTIS Capabilities (More Re-stated)

• Merge-Split Processing for Radar Merges and Track
  Fades and Reasoning through Multiple Hypotheses
• Maneuver Correlation Detection
• Surface ID Processing, Fusion, and Behavior
  Analysis
• Action Recommendation based on Heuristics
• Route Planning to ID a Set of Contacts and/or
  Search an Area
• Ability of Tactical Personnel to Edit and Change
  ID, Alerting, and Recommendation Behaviors in
  Real-time

17
ISTIS Dynamic Map Display
18
ISTIS Track Information, Recommendations, and
Alerts Display
19
Demonstration

• Strait of Malacca
• Alerts Leaving commercial lanes / intercepting
• Merge-Split automatic reasoning backward and
  forward
• Multiple hypothesis / Hierarchical reasoning
• Intercept/formation maneuver correlations
• Heading and UAV recommendations
• Immediate Threat alert
• Demo video

20
Conclusion

• ISTIS is an AI system that improves the Littoral
  ID Process, quality, and efficiency by
• Better ID estimations from available data
• Tracking ambiguous signals
• storing and handling past target data
• Sooner ID determinations
• Prevention of ID Surprises
• assessing threat levels notifying users of
  alert conditions
• Better use of scarce ID resources
• filtering out insane data
• keeping track of multiple track hypotheses based
  on the fusion of evidence from multiple sources
• Capable today and continuing to be enhanced
• Lockheed Martin (a LCS Builder) is partner
• Interested in other potential users or partners

21
Intelligent Surface Threat Identification System
(ISTIS)

• IEEE Aerospace Conference 2007

Presented by Robert Richards, Ph.D. Richards_at_S
tottlerHenke.com www.stottlerhenke.com