Research on Multi-Agent Systems with

1
Research on Multi-Agent Systems with
Applications to Simulation and Training

• Thomas R. Ioerger
• Associate Professor
• Department of Computer Science
• Texas AM University

2
Historical Context

• University XXI - DoD funding (1999-2000)
• developed TRL for modeling information flow in
  battalion tactical operations centers (TOCs)
• with Volz, Yen, and Jim Wall (Texas Center for
  Appl. Tech.)
• MURI - AFOSR funding (4.3M, 2001-2005)
• worked with cognitive scientists to develop
  theories of how to use agents in training, e.g.
  for AWACS
• with Volz (TAMU), Yen (PSU), Shebilske (Wright)
• NASA-Langley (current)
• SATS future ATC with aircraft self-separation
• with John Valasek (Aero) and John Painter (EE)

3
(No Transcript)
4
TOC Staff - Agent Decomposition
Maintain friendly situation, Maneuver sub-units
Control indirect fire, Artillery, Close
Air, ATK Helicopter
S3
FSO
Maintain enemy situation, Detect/evaluate
threats, Evaluate PIRs
S2
CDR
Move/hold, Make commands/decisions, RFI to
Brigade
Companies
Scouts
Maneuver, React to enemy/orders, Move along
assigned route
Move to OP, Track enemy
5
CAST Collaborative AgentArchitecture for
Simulating Teamwork

• developed at Texas AM part of MURI grant from
  DoD/AFOSR
• multi-agent system implemented in Java
• components
• MALLET a high-level language for describing team
  structure and processes
• JARE logical inference, knowledge base
• Petri Net representation of team plan
• special algorithms for belief reasoning,
  situation assessment, information exchange, etc.

6
MALLET
descriptions of team structure
evaluated by queries to JARE knowledge base

• (role sam scout) (role bill S2) (role joe FSO)
• (responsibility S2 monitor-threats)
• (capability UAV-operator maneuver-UAV)
• (team-plan indirect-fire (?target)
• (select-role (scout ?s)
• (in-visibility-range ?s ?target))
• (process
• (do S3 (verify-no-friendly-units-in-area
  ?target))
• (while (not (destroyed ?target))
• (do FSO (enter-CFF ?target))
• (do ?s (perform-BDA ?target))
• (if (not (hit ?target))
• (do ?s (report-accuracy-of-aim FSO))
• (do FSO (adjust-coordinates ?target))))))

descriptions of team process
7
CAST Architecture
expand team tasks into Petri nets
keep track of who is doing each step
agent teammates
MALLET knowledge base (definition of
roles, tasks, etc.)
messages
human teammates
events, actions state data
JARE knowledge base (domain rules)
simulation
make queries to evaluate conditions, assert/retrac
t information
models of other agents beliefs
Agent
8
Modeling Team Behavior

• Automatic Coordination
• no need to explicitly encode it - agents infer
  the need and communicate as necessary
• Backup Behavior (robustness)
• if one member fails, others help, since they have
  shared goals
• Dynamic Role Selection (flexibility)
• agents dynamically cooperate to assign tasks to
  the most appropriate member
• Proactive Information Exchange (efficiency)
• agents infer what is relevant to teammates based
  on their role in team plan

9
AWACS - DDD (Aptima, Inc.)
10
Agent-Based Coaching in Teams

• Agents can track trainees actions using team
  plan, offer hints (either online or via AAR)
• Standard approach plan recognition
• Team context increases complexity of explaining
  actions and mistakes
• failed because lack domain knowledge, situational
  information, or its not my responsibility?

11
Modeling Command and Control

• Civilian as well as military applications...
• information management is the key
• Cognitive Aspects of C2
• Naturalistic Decision Making (Klein)
• Situation Awareness (Endsley)
• Recognition-Primed Decision Making (RPD)
• situations S1...Sn
• e.g. being flanked, ambushed, bypassed, diverted,
  enveloped, suppressed, directly assaulted
• features associated with each situation
  Fi1...Fim
• evidence(Si)Sj1..m wij . Fij gt qi

12
TAMU Flight Simulation Lab (FSL)

• Dr. John Valasek, director (Aerospace Engr Dept)
• fixed-based F4 cockpit
• flight dynamics models for military (e.g.
  Harrier), and GA (e.g. Commander-700 twin)
• 155º wrap-around projection
• programmable cockpit displays
• projected heads-up display

13
NAV/MAP DISPLAY SYMBOLOGY
14
TRAFFIC Conflict Detection and Resolution AGENT

• Inputs are ADS-B state vectors of aircraft in
  immediate airspace
• On-board agents detect potential traffic
  conflicts
• Use inter-aircraft negotiation to determine
  mutually acceptable trajectory changes based on
  goals, constraints, and intentions

?
?
15
SATS - THE APPROACH Small Aircraft Transportation
System
ATC FAA Air Traffic Control. IAF FAF
Initial- and Final-Approach Fixes. ADS-B
Automatic Dependent Surveillance Broadcast (Radar
Xpndr.) AMM Airport Management Module (Digital
Data-Link)

• ATC Clears Aircraft to SCA Holding Stack at IAF.
  
• Self-Separation via ADS-B (Req. Conflict
  Mgt. Software).
• Approach Sequencing and Airport Info. via AMM.