ROE Simulation Program

Similar documents
DMSO Human Performance Program

ENHANCED HUMAN-AGENT INTERACTION: AUGMENTING INTERACTION MODELS WITH EMBODIED AGENTS BY SERAFIN BENTO. MASTER OF SCIENCE in INFORMATION SYSTEMS

ARMY RDT&E BUDGET ITEM JUSTIFICATION (R2 Exhibit)

Development of CBRN Impact Assessment Capabilities

Target Behavioral Response Laboratory

Agents for Serious gaming: Challenges and Opportunities

Robotic Systems. Jeff Jaster Deputy Associate Director for Autonomous Systems US Army TARDEC Intelligent Ground Systems

Multiplayer Computer Games: A Team Performance Assessment Research and Development Tool

2018 Research Campaign Descriptions Additional Information Can Be Found at

ASSAULT RIFLE SIMULATOR

MEC HA: A Tool in the Decision Making Toolbox

Co-evolution of agent-oriented conceptual models and CASO agent programs

Academia. Elizabeth Mezzacappa, Ph.D. & Kenneth Short, Ph.D. Target Behavioral Response Laboratory (973)

THE MECA SAPIENS ARCHITECTURE

Autonomous Robotic (Cyber) Weapons?

SECURITY SYSTEMS SAC LITE. In security you cannot choose the second best option. indracompany.com

An Unreal Based Platform for Developing Intelligent Virtual Agents

Overview Agents, environments, typical components

BDI: Applications and Architectures

Report to Congress regarding the Terrorism Information Awareness Program

Applied Robotics for Installations and Base Operations (ARIBO)

Lesson 17: Science and Technology in the Acquisition Process

REPORT DOCUMENTATION PAGE

STE Standards and Architecture Framework TCM ITE

Learning from Each Other Sustainability Reporting and Planning by Military Organizations (Action Research)

UK DEFENCE RESEARCH PRIORITIES

C2 Theory Overview, Recent Developments, and Way Forward

Health Happens In The White Space

SITUATED DESIGN OF VIRTUAL WORLDS USING RATIONAL AGENTS

Dr. Barton Halpern Advanced Small Unit Small Arms Technology Concepts Project 15 May 2012

Extending the STRADA Framework to Design an AI for ORTS

DESIGN AGENTS IN VIRTUAL WORLDS. A User-centred Virtual Architecture Agent. 1. Introduction

Governing Lethal Behavior: Embedding Ethics in a Hybrid Reactive Deliberative Architecture

Chapter 2 Threat FM 20-3

Survivability on the. ART Robotics Vehicle

Knowledge Management for Command and Control

Joining Forces University of Art and Design Helsinki September 22-24, 2005

Outline. Agents and environments Rationality PEAS (Performance measure, Environment, Actuators, Sensors) Environment types Agent types

The Human in Defense Systems

REQUEST FOR INFORMATION (RFI) United States Marine Corps Experimental Forward Operating Base (ExFOB) 2014

AFRL-RH-WP-TR

Violent Intent Modeling System

Authoring & Delivering MR Experiences

Knowledge Enhanced Electronic Logic for Embedded Intelligence

Situational Awareness Object (SAO), A Simple, Yet Powerful Tool for Operational C2 Systems

REPORT D Proposal for a cluster governance model in the Adriatic Ionian macroregion. (Activity 3.4)

APPLYING THE DOMAINS OF CONFLICT TO INFORMATION OPERATIONS INFORMATION OPERATIONS/ASSURANCE. Marc Romanych

U.S. Army Training and Doctrine Command (TRADOC) Virtual World Project

UNIT-III LIFE-CYCLE PHASES

MSc(CompSc) List of courses offered in

Improving Performance through Superior Innovative Antenna Technologies

DESIGN AND CAPABILITIES OF AN ENHANCED NAVAL MINE WARFARE SIMULATION FRAMEWORK. Timothy E. Floore George H. Gilman

Linking Emergency Response Teams and the Military using VMF/ Tactical Data Links

Artificial Intelligence: Implications for Autonomous Weapons. Stuart Russell University of California, Berkeley

CMRE La Spezia, Italy

ACHIEVING SEMI-AUTONOMOUS ROBOTIC BEHAVIORS USING THE SOAR COGNITIVE ARCHITECTURE

The Development Of Selection Criteria For Game Engines In The Development Of Simulation Training Systems

Artificial Intelligence: Implications for Autonomous Weapons. Stuart Russell University of California, Berkeley

A NEW SIMULATION FRAMEWORK OF OPERATIONAL EFFECTIVENESS ANALYSIS FOR UNMANNED GROUND VEHICLE

Virtual Reality Devices in C2 Systems

Agent Models of 3D Virtual Worlds

Development of an Intelligent Agent based Manufacturing System

Pervasive Services Engineering for SOAs

Weapons of Mass Destruction. These slides are provided courtesy of the Naval Post-graduate School Center for Homeland Defense and Security

Expression Of Interest

Author, Design, Additional Graphics: Steven Trustrum Cover & Illustrations: Eric Lofgren

Communication and Culture Concentration 2013

UNCLASSIFIED FY 2016 OCO. FY 2016 Base

Methodology for Agent-Oriented Software

1,024 Kilobot Robots Studying Collective Behaviors & Swarm Intelligence with Little Bitty Robots

Ethics in Artificial Intelligence

AF Life Cycle Management Center

Advanced Research Methods

A new role for Research and Development within the Swedish Total Defence System

PRINCIPAL INVESTIGATOR: Bartholomew O. Nnaji, Ph.D. Yan Wang, Ph.D.

UK OFFICIAL. Crown copyright Published with the permission of the Defence Science and Technology Laboratory on behalf of the Controller of HMSO

Strategic Path Planning on the Basis of Risk vs. Time

Autonomy Test & Evaluation Verification & Validation (ATEVV) Challenge Area

DoD Research and Engineering Enterprise

ARMY COMMANDER - GREAT WAR INDEX

DARPA MULTI-CELL & DISMOUNTED COMMAND AND CONTROL PROGRAM

Asymmetric Adversary Tactics for Synthetic Training Environments

An Assessment of Acquisition Outcomes and Potential Impact of Legislative and Policy Changes

Battle Station Star Force Book 5

EDUCATIONAL PROGRAM YEAR bachiller. The black forest FIRST YEAR OF HIGH SCHOOL PROGRAM

VICTER: AN EMBEDDED VIRTUAL SIMULATION SYSTEM FOR LAND WARRIOR (LW)

Digital Engineering Support to Mission Engineering

U.S. Army RDECOM - Atlantic

Transitioning the Opportune Landing Site System to Initial Operating Capability

A Demonstrator for Command and Control Technology Experimentation

Blending Autonomy and Control: Creating NPCs for Tom Clancy s The Division

Combining High Dynamic Range Photography and High Range Resolution RADAR for Pre-discharge Threat Cues

E-commerce Technology Acceptance (ECTA) Framework for SMEs in the Middle East countries with reference to Jordan

HUMAN FACTORS IN VEHICLE AUTOMATION

LATE 19 th CENTURY WARGAMES RULES Based on and developed by Bob Cordery from an original set of wargames rules written by Joseph Morschauser

DoD Research and Engineering Enterprise

Visualization of Self-Reporting Entities for Command and Control

USING A FUZZY LOGIC CONTROL SYSTEM FOR AN XPILOT COMBAT AGENT ANDREW HUBLEY AND GARY PARKER

Agent-Based Systems. Agent-Based Systems. Agent-Based Systems. Five pervasive trends in computing history. Agent-Based Systems. Agent-Based Systems

MIN-Fakultät Fachbereich Informatik. Universität Hamburg. Socially interactive robots. Christine Upadek. 29 November Christine Upadek 1

Transcription:

ROE Simulation Program Rick Evertsz 1, Frank E. Ritter 2, Simon Russell 3, David Shepperdson 1 1 AOS, 2 Penn State, 3 QinetiQ BRIMS 2007 26 March 2007 Supported by AFRL/MLKH award FA8650-04-C-6440 and by the UK MOD's Analysis, Experimentation and Simulation corporate research programme (Project No: RT/COM/3/006). We thank Bill Knarr for helpful comments on ROE, and Colin Sheppard for useful discussions.

Outline of Presentation Overview of Project Outline ROE3 Demonstration Discussion 2

Motivation ROE "Directives issued by competent military authority that delineate the circumstances and limitations under which United States forces will initiate and/or continue combat engagement with other forces encountered" Driven by legal/military/political Subtle overlap; multi-national; unconventional foe Must be easy to apply, respect warfighter s RTSD ROE can put friendly forces at risk Trial and error too risky in modern environment Simulation-based ROE evaluation Environment 3

Project Objectives Primary Proof-of-concept Simulation tool where ROE affect behavior of synthetic entities ROE independent of tactics Secondary Human variability (e.g., stress, fear, fatigue) SME-friendly tactics/roe representation ROE inspection and tracing tools Reusable ROE and tactics Behavior models controlling and reacting to state of entities in the synthetic battlespace 4

ROE Classification Based on ROE Handbook for Judge Advocates (CLAMO, May 2000) Political/legal/military dimensions Also Looked at: FM 27-100 [Joint Publication 1-02] Legal Support to Operations 5

ROE Software Perspective Types of ROE requiring different software implementation techniques? ROE determine permissible military action **Right to self-defense** Restrictive Permissive Preference Define ROE-relevant criteria You may presume that civilians in public armed with crew-served weapons, automatic weapons or rifles are members of the national police or paramilitary groups, and therefore may be treated as hostile 6

ROE3 ROE Framework ROE Modeling (Meta-Plans) CoJACK Tactics Modeling (JACK Plans) ROE Moderators Behavior Moderation JACK Teams (CoJACK) Tactics CGF Interface Layer (BabelBox) Situation Mapping Embodiment Situation Mapping API extensions BabelBox(JACKSIM) OTB 2 7

ROE Framework ROE represented as Meta-knowledge Meta-Plans choose amongst Plans Tactics annotated with ROErelevant effects Shoot(X) = LethalForce(X) 8

ROE Framework ROE Framework CoJACK JACK Teams Situation Mapping BabelBox OTB 2 9

ROE Framework ROE Framework JACK Teams (Tactics) Threat assessment Situation Assessment Is a protected entity under threat? no yes Hostile Intent has been demonstrated Is the targeting lethal? no nox X yes Increment the threat assessment Epinephrine Reservoir Fear Concentration Memory of Similar Episodes 10 Pre-task Appraisal COJACK (Moderators)

ROE Methodology ROE are restraints/preferences on tactical options Need to know ROE-relevant effects Label plans having ROE-relevant actions Annotate plans with ROE-relevant actions Table mapping concrete actions to abstract ROE categories Augment for new scenarios, e.g., ROEcategory(grenade, lethalforce) 11

ROE Meta-Plan Filtering 12

13

14

CoJACK ROE Framework CoJACK JACK Teams Situation Mapping BabelBox OTB 2 16

CoJACK Extends JACK with some features of a cognitive architecture and a representation for behavior moderators Moderators time-based functions Sensitivity to moderators Define moderator exposures 17

JACK Teams ROE Framework CoJACK JACK Teams Situation Mapping BabelBox OTB 2 18

JACK Teams JACK is an agent-based COTS product based on the BDI paradigm Agents/teams, plans, events, beliefsets Agents/teams synthetic entities, inc. organizational structures Events trigger reasoning and action plans how to respond to events Beliefsets agent s knowledge 19

Situation Mapping ROE Framework CoJACK JACK Teams Situation Mapping BabelBox OTB 2 20

JACKSIM Situation Mapping ROE Framework JACK Cognitive Architecture (COJACK) (extension to BDI core) JACK Teams BDI Platform (agent-based infrastructure) JACKSIM Actions Percepts JACKSIM (situation mapping) Babel Box Actions Simulation State CGF Integration Layer + Babel Box OTB v2.0 (synthetic environment) 21

BabelBox and OTB ROE Framework CoJACK JACK Teams Situation Mapping BabelBox OTB 2 22

Overview (OTB) BabelBox OTB 2 BabelBox Provides COJACK with access to private-level OTB data Allows tasking and modification of entities Gathers key Situational Awareness data OTB v2.0 Int l modified to provide additional functionality Added library to overcome OTB architectural limitations Fine control of IC movement Requirement for multi-tasking move, shoot and throw grenade concurrently Need to represent verbal communications, rock throwing, additional postures 23

SAF (OTB) Interaction 24 BabelBox OTB 2

BabelBox Design BabelBox OTB 2 25

Changes to OTB (1) BabelBox OTB 2 Libvicbb new task for external control Allows concurrent tasking (e.g., shoot while moving) Gives complete control over timing and execution Encapsulates existing IC libraries vicmove, vthrowgrenade etc. New IC entity (based on M16A2) Disabled background targeting behaviors Added radio to represent speaking uses messages display 26

Changes to OTB (2) 27 BabelBox OTB 2

Changes to OTB (3) New Posture State Added waving gun posture Simple 2-state animation New rock munition Based on existing flashbang grenade Creates a detonation which can be detected by SAF entities, but causes no damage 28 BabelBox OTB 2

BabelBox/OTB Capabilities (1) Reporting data from OTB1/2 BabelBox OTB 2 Implementation State Entity s type BB & OTB Entity s location & orientation BB & OTB List of entities spotted BB & OTB Posture and weapon state BB & OTB Damage state BB & OTB Entity s SAF-specific ROE BB & OTB 29

BabelBox/OTB Capabilities (2) BabelBox OTB 2 Control of entities via external systems Implementation State Entity movement & orientation BB & OTB Fire upon a target entity or location (with grenades and ballistic weapons) BB & OTB Changing weapon and posture states BB & OTB Mounting and dismounting of vehicles BB & OTB 30

ROE3 Summary ROE Framework: ROE independent of tactics JACK + CoJACK: tactics and behavior moderators JACKSIM: embodiment and situation mapping BabelBox: CGF interface layer 31

Building a Scenario Behavior Models Agents, Tactics, ROE, Moderators Scenario-specific initialization files Physical Models Messaging API Extras e.g., 3D Visualization 32

Demonstration Scenario Convoy Roadblock Rebels Marines 34

Common Scenario Intro 35

Common Scenario Intro 36

Scenario Variations Moderator: fear If the Marines Have experience of waving weapon with lethal consequences for friendlies, high fear Perceive it as hostile Put weapon down Rebels target Marines Rebels charge, weapons ready Throw rock at vehicle 37

Conclusions ROE Framework: ROE independent of tactics, Can be added to an architecture JACK + CoJACK: tactics and behavior moderators JACKSIM: embodiment and situation mapping BabelBox: CGF interface layer Multiple Layers help

References Busetta, P., Rönnquist, R., Hodgson, A., & Lucas, A. (1999). JACK intelligent agents - Components for intelligent agents in JAVA. AgentLink News Letter, 2(Jan.). The Judge Advocate General s School, U.S. Army (2000a). Rules of Engagement (ROE) Handbook for Judge Advocates. Charlottesville, VA: US Army's Center for Law and Military Operations. The Judge Advocate General s School, U.S. Army (2000b). FM 27-100, Legal Support to Operations,Department of Defense Dictionary of Military and Associated Terms. Washington DC: Headquarters, Department of the Army. Ritter, F. E., & Norling, E. (2006). Including human variability in a cognitive architecture to improve team simulation. In R. Sun (ed.), Cognition and multi-agent interaction: From cognitive modeling to social simulation (pp. 417-427). Cambridge, UK: Cambridge.