SUO Planning & Decision Aids Austin Tate, John Levine, Peter Jarvis, Jeff Dalton, AIAI, University of Edinburgh David Wilkins, Tom Lee, SRI International.

Slides:



Advertisements
Similar presentations
Tactical (Combat) Orders
Advertisements

Tactical Operations Orders
Application of the Troop Leading Procedures
VIRGINIA MILITARY INSTITUTE NCO ACADEMY
Shared Models of Activity To Underpin Small Unit Operations Austin Tate, Jeff Dalton, John Levine & Peter Jarvis Artificial Intelligence Applications Institute.
PROJECT RISK MANAGEMENT
JSIMS 28-Jan-99 1 JOINT SIMULATION SYSTEM Modeling Command and Control (C2) with Collaborative Planning Agents Randall Hill and Jonathan Gratch University.
Lecture # 2 : Process Models
SUO/PDA ARPI Fall 1999 Workshop 1ARPI Small Unit Operations SUO/PDA Austin Tate & David Wilkins AIAI & SRI International
TROOP LEADING PROCEDURES FM 7-8
TROOP LEADING PROCEDURES
Troop Leading Procedures
Unit 8: Tests, Training, and Exercises Unit Introduction and Overview Unit objectives:  Define and explain the terms tests, training, and exercises. 
Fundamentals of Information Systems, Second Edition
Pertemuan Matakuliah: A0214/Audit Sistem Informasi Tahun: 2007.
Military Decision Making Process (MDMP)
The Software Product Life Cycle. Views of the Software Product Life Cycle  Management  Software engineering  Engineering design  Architectural design.
Army Doctrine Publication (ADP) 3-37; and Army
Session 8 Coordination. Session Objectives Define the Principle of Coordination Define the Principle of Coordination Identify characteristics of successful.
Evaluation IMD07101: Introduction to Human Computer Interaction Brian Davison 2010/11.
What is Business Analysis Planning & Monitoring?
Campaign Planning Process Step 3B – System Center of Gravity Analysis
S/W Project Management
Unit 5:Elements of A Viable COOP Capability (cont.)  Define and explain the terms tests, training, and exercises (TT&E)  Explain the importance of a.
Campaign Planning Process 29 March 2006 Step 7 – Prepare Operations Plan (OPLAN) / Operations Order (OPORD) & Assess UNCLASSIFIED.
Industrial Software Project Management Some views on project managing industrial and business software projects.
The Military Decision Making Process
Battle Drills Break Contact React to Ambush React to Contact
What is a Business Analyst? A Business Analyst is someone who works as a liaison among stakeholders in order to elicit, analyze, communicate and validate.
Management & Development of Complex Projects Course Code MS Project Management Perform Qualitative Risk Analysis Lecture # 25.
SUO Planning & Decision Aids Austin Tate, AIAI, University of Edinburgh David Wilkins, SRI International Capability to communicate, refine, execute and.
Troop Leading Procedures
Software Engineering Principles Principles form the basis of methods, techniques, methodologies and tools Principles form the basis of methods, techniques,
Software Development Cycle What is Software? Instructions (computer programs) that when executed provide desired function and performance Data structures.
1 Introduction to Software Engineering Lecture 1.
TYPES OF ORDERS ADMINISTRATIVE ORDER: COVERS NORMAL ADMINISTRATIVE OPERATIONS IN GARRISON OR IN THE FIELD. THEY INCLUDE GENERAL, SPECIFIC, & MEMORANDUM.
Military Decision Making Process – Multinational (MDMP-M)
Notes of Rational Related cyt. 2 Outline 3 Capturing business requirements using use cases Practical principles  Find the right boundaries for your.
Military Decision-Making Process
Fundamentals of Information Systems, Second Edition 1 Systems Development.
Information & Decision Superiority Case studies in applying AI planning technologies to military & civil applications Dr Roberto Desimone Innovations.
Advanced Decision Architectures Collaborative Technology Alliance An Interactive Decision Support Architecture for Visualizing Robust Solutions in High-Risk.
AI on the Battlefield: an Experimental Exploration Alexander Kott BBN Technologies Robert Rasch US Army Battle Command Battle Lab Views expressed in this.
Military Decision Making Process (MDMP)
1 Joint Doctrine: The Authoritative Vocabulary For and Explanation of Joint Warfare and Joint Operations October 16, 2015 Representing Reality\Big Data\Big.
Military Decision Making Process (MDMP)
1 Artificial Intelligence Applications Institute Centre for Intelligent Systems and their Applications A Shared Model for Mixed-initiative Synthesis Tasks.
ANALYSIS PHASE OF BUSINESS SYSTEM DEVELOPMENT METHODOLOGY.
The Course of Action Challenge Problem (COA CP). Basic Stuff COA CP replaces the BS CP SME’s author COA’s and the knowledge used to critique them SHAKEN.
Course of Action Comparison Purpose u Define course of action comparison and its role in the crisis action planning process u Discuss the associated task.
SUO Planning & Decision Aids PDA Thread 2 - Sniper Suppression Prototyping Peter Jarvis, John Levine, Austin Tate, Jeff Dalton AIAI, University of Edinburgh.
Operations Study Guide. Categories OF Orders ADMINISTRATIVE ORDER: Covers normal administrative operations in garrison or in the field. They include general,
Staff (Running) Estimate
Modern Systems Analysis and Design Third Edition Chapter 2 Succeeding as a Systems Analyst 2.1.
USJFCOM 27 Jul EXECUTIVE OVERVIEW Col David Brown, USAF JFIIT Commander UNCLASSIFIED Joint Fires Integration and Interoperability Team (JFIIT)
Project Management Processes for a Project Chapter 3 PMBOK® Fourth Edition.
Company LOGO. Company LOGO PE, PMP, PgMP, PME, MCT, PRINCE2 Practitioner.
LECTURE 5 Nangwonvuma M/ Byansi D. Components, interfaces and integration Infrastructure, Middleware and Platforms Techniques – Data warehouses, extending.
A Knowledge-Based Tool for Planning of Military Operations: the Coalition Perspective Larry Ground Alexander Kott Ray Budd BBN Technologies Presented by.
AUDIT STAFF TRAINING WORKSHOP 13 TH – 14 TH NOVEMBER 2014, HILTON HOTEL NAIROBI AUDIT PLANNING 1.
Leaders Reference Principles of Leadership
Religious Inputs/Outputs
The MDMP Process MDMP Inputs MDMP Outputs Step 1 MDMP Inputs Step 5
Peacekeeping and Stability Operations Institute The Army’s only organization for Peace and Stability Operations at the strategic and operational level.
Conduction of a simulation considering cascading effects
TROOP LEADING PROCEDURES
<I-N-C-A> and the I-Room
TYPES OF ORDERS ADMINISTRATIVE ORDER: COVERS NORMAL ADMINISTRATIVE OPERATIONS IN GARRISON OR IN THE FIELD. THEY INCLUDE GENERAL, SPECIFIC, & MEMORANDUM.
TROOP LEADING PROCEDURES
TROOP LEADING PROCEDURE
Presentation transcript:

SUO Planning & Decision Aids Austin Tate, John Levine, Peter Jarvis, Jeff Dalton, AIAI, University of Edinburgh David Wilkins, Tom Lee, SRI International Pete Haglich, ISX (for SRI) Capability to generate, refine, select, communicate, execute and repair plans across multiple echelons from company level to platoon and squad level. Two examples of Planning & Decision Aid use: –one offensive (MOUT); –one defensive (Halt an Attack in Restrictive Terrain).

SUO/PDA Preliminary Workplan Phase 1: Familiarization & Domain Modeling Dec98--->Mar99 Apr >Jun99 Jul >Dec99 Jan00--->Mar00 Phase 2: Demo Storyboard, Concept Proofs & Further Domain Modeling Phase 3: System Adaptation & Demo Production Phase 4: Transfer Of Results

Basic Planning Techniques Plans are doctrinally correct and of uniform high quality Situation Resources Constraints SOPs Objectives Advice Planner Plan:Actions&Constraints Soldiers and Sensors in the Field (Apply SOPs) Actions System Monitor working with the Commander Rapidly respond to events, changing actions and reallocating resources, comms. to other echelons if necessary The underlying plan representations must be done correctly to support the desired command and control loop

Potential Technical Contributions to Draw On  Overall management of the command, planning and control process steps to improve coordination.  Situation dependent option filtering (sometimes reducing the choices normally open to one “obvious” one [Klein p.17-18].  Satisficing search to find the first suitable plan that meets the essential criteria [Klein p. 20].  Anytime algorithms which seek to improve on the best previous solution if time permits.  Expansion of a high level abstract plan into greater detail where necessary.

Potential Technical Contributions to Draw On  High level “chunks” of procedural knowledge (SOP, TTP) at a human scale [Klein p. 52].  Retain a high level overview. [Klein, p.227] “Include only the detail necessary to establish a plan is possible – do not fall into the trap of choreographing each of their movements”].  Analysis of potential interactions as plans are expanded or developed [Klein p 53].  Identification of problems, flaws and issues with the plan [Klein p. 63 & 71].  Establishment of a space of alternative options based on different assumptions [Klein p. 23].  Monitoring of the execution of events as they are expected to happen within the plan, watching for deviations (often ahead of problem) [Klein p. 32].

Potential Technical Contributions to Draw On  AI planning techniques represent the dynamic state of the world at points in the plan and can be used for “mental simulation” of the plan [Klein p. 45].  Pruning of choices according to given requirements or constraints [Klein p. 94 “singular strategy”].  Heuristic evaluation and prioritisation of multiple possible choices within the constraint search space [Klein p. 94].  Repair of plans while respecting plan structure and intentions.  Uniform use of a common plan representation with embedded rationale to improve plan quality, shared understanding, etc.

Long-term Contributions of PDA to the Soldier Shared plan representations cognisant of military principles, doctrine, SOPs and TTPs. Makes possible: Doctrinally correct plans usable by everyone. Fast generation of multiple distinct COAs, including ones the commander may not have considered. Support commander creativity through human guidance. Uniformly high plan quality, even during high-stress crises. Continuous analysis of the plan using multiple metrics. Monitor plan execution and respond quickly to events, helping the commander modify the plan appropriately. Provide relevant information to other echelons, allowing fast communication while preserving bandwidth.

Technical Contributions by SRI/AIAI to SUO Contribution to the representation of shared objectives, plans, processes, SOPs and TTPs in SUO. Generation of multiple qualitatively distinct alternative COAs dependent upon alternative assumptions and advice about the situation. Support for mixed-initiative incremental plan development, manipulation and use. Situation-dependant plan repair as situation changes. Systems integration framework for modular planning and plan analysis systems. Management of planning and execution process - promotion of intelligent process management and workflow concepts.

SUO/PDA Input to SUO/SAS Program Aim is to communicate and transfer some of the relevant results of the ARPI/PDA work to SUO. To do this by joining in the SUO Community and understanding its requirements. To demonstrate some appropriate and relevant Advanced Planning & Decision Aids Technology. To be helpful to the contracting team(s). AIAI/SRI want to act as a conduit to the work of others where they can see its potential relevance.

Context wrt FM 7-10 & FM 7-20 Processes FM 7-20 The Infantry Battalion, FM 7-10 The Infantry Rifle Company and FM 7-8 The Infantry Rifle Platoon and Squad - Command and Control - Augmented by Respective Military Training Plans (MTPs) Suggested as a point of comparison by Jim Madden, IDA Context of diagram is an overall process involving perhaps several COAs and a command, planning, communication, execution and control process. Diagram covers core part from FM 7-10 of situation assessment and COA generation (relevant to SUO/SAS and SUO/PDA activities)

Prepare a COA statement and sketch to enhance clarity. The sketch should show the3 maneuver aspects of the COA Assign control measures to clarify respon- sibilities and synchronize the efforts of subordinates to support the main effort. Allow as much freedom of effort as possible Determine essential task(s) for subordinate units (main and supporting efforts) to achieve the purposes stated above Identify type of forces required to accomplish the mission, considering only organic and attached units. Weigh the main effort; take more risk in non-main effort areas (economy of force) Do not consider assets such as CAS or FRASCAM, which may be unavailable during execution. Determine essential task(s) for subordinate units (main and supporting efforts) to achieve the purposes stated above Determine purposes to be achieved by main and supporting efforts by linking the the main effort’s purpose directly to the battalion’s purpose and the supporting efforts’ purposes directly to the main purpose Determine what supporting efforts are needed by asking the question, “What else must be done to allow the main effort to succeed?” Determine the decisive point where the enemy is most vulnerable. Ideally, where an enemy weakness is or where the enemy will be positioned at a time when the battalion can generate overwhelming combat power against the enemy What is the unit’s purpose within the higher commander’s intent? Which tasks allow the unit to accomplish its purpose? How do terrain/weather factors affect the soldiers/subunits? How do terrain/weather factors effect placement of weapons? Where can commander focus his combat power to accomplish his mission? What are the critical time aspects of the operation? How can unit’s strength be focused on enemy weaknesses? How can commander make his best use of is combat power given the current status of his units? What are the enemy’s most probable courses of action give the terrain and his probable objectives? Where will contact first occur and how will enemy be arrayed? What are probably enemy weaknesses and vulnerabilities? Receive Mission Mission (Assigned) Next higher commanders con- cept of operations and intent? Subunit tasks Unit tasks -Specified? -Implied? Conduct METT-T Analysis Formulate Assumptions & DeductionsDevelop Course of Action Terrain/Weather Analysis Obstacles? Avenues of approach? Key terrain? Observation and fields of fire? Cover and concealment? Weather? Other characteristics? Time Available LD time/Defend no later time? Time to begin movement? Time available to plan? Time available to prepare? Time available to rehearse? Time available for reconnaissance? Troops Composition? Disposition? Strength? Significant activities? Peculiarities and weaknesses? Enemy Composition? Disposition? Strength? Significant activities? Peculiarities and weaknesses? Enemy capabilities? Enemy probable courses of action? Limitations?

Opportunities for PDA Support in SUO Overall Process from Receipt of Mission to Success Deliberative Planning & Rehearsal En-route Rehearsal & Replanning Low Tempo Adaptation & Plan Repair High Tempo Monitoring & Plan Selection After Action Planning & Support In AdvanceDuring MissionAfter Action

More Detailed Slides If Required

ARPI/PDA Goal, Themes & Participants ARPI DARPA GOAL: Develop, demonstrate, and transition advanced knowledge-based technology for automatic and interactive planning, scheduling, and decision making to allow better, faster planning in complex, stressed situations Integrated Planning & Scheduling CMU Kestrel Arizona St. University U Oregon Case-Based Planning CMU MITRE U. Maryland Modeling Simulation & Evaluation U. Mass Klein Northwestern University U. Edinburgh U. Rochester KB Planning Systems SRI Representation & Intelligent KB USC/ISI Loral GE CRD Planning Under Uncertainty Brown University Rockwell Int’l U Washington ISTI U. Edinburgh Workflow Management & Process Control MCC U Wisconsin UCLA ISX BBN Honeywell

SUO Planning & Decision Aids Advanced Planning Technology Schedule 1QCY99 - Domain familiarization. Domain modeling. Create initial plan and activity templates for offensive and defensive scenarios. 2QCY99 - SUO Scenario and storyboard/demo script development. Walk through of technology requirements, mockup of non-working parts. Produce demo script and scenarios. 3QCY99 - Technology and demonstration development first pass, mock demonstration. 4QCY99 - Full demonstration development. 1QCY00 - Transition and communication of results to SUO contractor. Refinement of demonstration and technology. Integration of further modules to support more effective demonstrations. Use results of DARPA/AFRL Planning Initiative (ARPI) and Planning & Decision Aids (PDA) work Multi-Agent Planning Architecture (MPA) and O-Plan Systems Integration Architecture SIPE-2 and O-Plan Generative Planners Mixed Initiative Planning Aids Planning Domain Knowledge Acquisition Tools/Editors Plan Repair Algorithms Planning Process Panels Rich Shared Plan Representations SUO/PDA Objective Demonstrate capability to generate, refine, select, communicate, execute and repair plans across multiple echelons from company level to platoon and squad level relevant to SUO/SAS environment. Two examples of COA plan generation and use: - one offensive (MOUT); - one defensive (Halt an Attack in Restrictive Terrain).

SUO/PDA Provisional Coordination Plan Agreed with ITT/SRI Contracting Team 1-Jul-99 Kick-off with delivery of SUO/PDA AIAI Phase 2 Report 30-Sep-99 Comments on scenario from ITT/SRI to SUO/PDA, agreement on SUO/SAS state descriptions used in scenario 31-Dec-99 SUO/PDA Demonstration 1-Jan-00 Technology Transfer Phase - Joint Work 31-Mar-00 ITT/SRI Team show link between SUO/SAS and SUO/PDA Demonstration end of current SUO/PDA project Jan-00 Possible start on SUO/PDA Phase 3 Option 31-Dec-00 ITT/SRI SUO/PDA Deliverable 30-Jun-01 End of SUO Technology Transfer Phase

SUO/PDA Preliminary Systems Sketch Knowledge Acquisition Stage Process Modelling Methods & Tools Modeller or Knowledge Engineer Army CALL Bulletins Doctrine, SOP, TTP Subject Matter Experts Domain Model Activity Templates & Constraints

SUO/PDA Preliminary Systems Sketch Planning & Decision Aids Use Stage Echelon N Planning & Execution System Other Modules Echelon N Planning Related Modules OPORD FRAGO Reports Echelon N+1 Planning & Execution System Other Modules Echelon N+1 Planning Related Modules OPORD FRAGO Reports Platoon Level Fire Team Level Domain Model Activity Templates & Constraints Echelon N-1 Planning & Execution System Echelon N-1 Planning Related Modules Company Level

SUO/PDA Preliminary System Sketch Instantiation of Components E.g., MPA, SIPE-2, O-Plan, ACP 3 E.g., Plan Sketch Tool E.g., Web O-Plan, O-P 3 E.g., ModSAF, Sextant, Blue/Red Force Laydown E.g., Act Editor, CPF Echelon N Planning & Execution System Other Modules Echelon N Planning Related Modules OPORD FRAGO Reports Echelon N+1 Planning & Execution System Other Modules Echelon N+1 Planning Related Modules OPORD FRAGO Reports Platoon Level Fire Team Level Domain Model Activity Templates & Constraints Echelon N-1 Planning & Execution System Echelon N-1 Planning Related Modules Company Level

Example of SRI ARPI/PDA Work Giving Advice to a Planner Integrating human judgement fixes many shortcomings of automated planning technology Heuristic search algorithm  plans quickly  maintains all constraints State of the World Actions One Might Take Objective s Beliefs, Resources, Constraints Operators Goals SIPE-2 Planner PLAN: Action Structure SIPE-2 Execution Monitor and Replanner Actions Commander’s Guidance Advice Advice:  qualitatively different COAs  “directed” search of options

Example of AIAI ARPI/PDA Work Edinburgh O-Plan Project Using domain constraints to support the coordinated development of plans. Communication between users acting as Task Assigner and Planner. Intelligent workflow model of planning based on “issue” handling (agenda/to-do list). Simplified planner interfaces to allow ”plug and plan” component integration. Uniform manipulation of plans as a set of constraints ( model). MILESTONES ( ) NEW IDEAS IMPACT CONCEPT Task Direction & Plan Analysis COA-2COA-1Planning Workflow Option: COA-2 Phase: Deployment World View Option COA-2 Authority:... Order Issued:.. Plan View Plan Development & Refinement Task Assigner Planner... Criteria 1 Criteria 2 Criteria 3... Q4/Y1 Q4/Y2 Q4/Y3 MIP Demonstration in Pacifica NEO Initial Evaluation Matrix Demonstration scenario development Workflow Planning Aid Experiments TIE with Rochester on Tasking Release of O-Plan Version 3.1 Evaluation Experiments Interim Report Mixed Initiative Planning Demo. TIE with USC/ISI on plan evaluation Release of O-Plan Version 3.2 Final Evaluation Report Generation of multiple qualitatively distinct alternative COAs dependent upon alternative assumptions concerning the emerging crisis. Support for mixed-initiative incremental plan development, manipulation and use. Promotion of intelligent process management and workflow concepts. Integration framework for large-scale modular planning systems. Contribution to shared plan representations.