76
CDR Duane Davis, USN DESIGN, IMPLEMENTATION AND TESTING OF A COMMON DATA MODEL SUPPORTING AUTONOMOUS VEHICLE (AV) COMPATIBILITY AND INTEROPERABILITY Ph.D. Committee: Dr. Don Brutzman Dr. Robert McGhee Dr. Neil Rowe Dr. Christian

CDR Duane Davis, USN

  • Upload
    abel

  • View
    51

  • Download
    3

Embed Size (px)

DESCRIPTION

DESIGN, IMPLEMENTATION AND TESTING OF A COMMON DATA MODEL SUPPORTING AUTONOMOUS VEHICLE (AV) COMPATIBILITY AND INTEROPERABILITY. CDR Duane Davis, USN. Ph.D. Committee: Dr. Don Brutzman Dr. Robert McGhee Dr. Neil Rowe Dr. Christian Darken Dr. Anthony Healey. Outline. Problem Statement - PowerPoint PPT Presentation

Citation preview

Page 1: CDR Duane Davis, USN

CDR Duane Davis, USN

DESIGN, IMPLEMENTATION AND TESTING OF A COMMON DATA MODEL SUPPORTING

AUTONOMOUS VEHICLE (AV) COMPATIBILITY AND INTEROPERABILITY

Ph.D. Committee:Dr. Don BrutzmanDr. Robert McGheeDr. Neil RoweDr. Christian DarkenDr. Anthony Healey

Page 2: CDR Duane Davis, USN

Outline

Problem StatementResearch OverviewSpecific Objectives and ImplementationsResearch ContributionsRecommendations for Future Work

Page 3: CDR Duane Davis, USN

Problem Statement

Examples• Homogeneous vehicle system: Swarming• Programmed compatibility: CJTFEX 04-2 Coordinated

MCM

Current AV interoperability is limited by vehicle-specific data formats and planning systems. This stovepipe approach to AV command and control inhibits effective multi-vehicle operations and hinders the design of such systems.

To date, the preponderance of multi-vehicle research has assumed inherent compatibility: homogeneous vehicle systems or explicitly programmed compatibility.

Page 4: CDR Duane Davis, USN

Research OverviewA Rigorously Defined Common Data Model:

• Vehicle-Independent• Subsumes Vehicle-Specific Data

Format Content• Extensible Markup Language

(XML) Schema GovernedData Model Requirements

• Mission Specification (tasking)• Communications• Mission Results

Automated Conversions• Data Model to Vehicle-Specific

Formats• Vehicle-Specific Formats to

Data ModelExemplar Development and Implementation

Data Mode

l

AAV 1

Support

AUV 2

ASV 2

AAV 2

AUV 1

ASV 1

Page 5: CDR Duane Davis, USN

Research Objective 1

Accurate Representation of Arbitrary Vehicle Tasking• Leverage Similarities—Similar Vehicles do

Similar Things• Identify Activities that Vehicles are Required

to Perform• Develop a Set of Task-Level Behaviors

Capable of Specifying these Activities

Page 6: CDR Duane Davis, USN

Exemplar Data Model Task-Level Behavior Characteristics

Vehicle-Type Specific• 30 UUV Behaviors• 20 UGV Behaviors• 22 USV Behaviors• 26 UAV Behaviors

Behavior Types (determines behavior termination criteria)• Closed-Loop

• Terminating—Implicit Termination Criteria• Open-Ended—Potentially Non-Terminating

• Open-Loop• Non-Control-Related• Special Purpose—Effect Other Behaviors

Behavior Activation—Based on the Preceding Behavior Type• Closed-Loop Terminating—Activate Next Upon Termination• Closed-Loop Non-Terminating—Activate Next Immediately• Open-Loop—Activate Next Immediately• Non-Control-Related—Activate Next Immediately• Special Purpose—Activate Next Upon Termination

Page 7: CDR Duane Davis, USN

Research Objective 2

Develop Translation Mechanisms for Automated Conversion between Vehicle-Specific Formats and the Data Model• Data Mappings Between the Data Model and

Vehicle-Specific Formats of Interest• Types of Translations that Must be Supported

• Data Model to Text-Based Vehicle-Specific Formats• Data Model to Binary Vehicle-Specific Formats• Text-Based Vehicle-Specific Formats to Data Model• Binary Vehicle-Specific Formats to Data Model

Page 8: CDR Duane Davis, USN

Translation of Data Model Data to Text-Based Vehicle-Specific

FormatsExtensible Stylesheet Language for

Transformation (XSLT)

• Many Well-Proven Applications in Numerous Problem Domains

• Relies on Data Mappings from the Model to the Target Format

• Exemplars:• Phoenix UUV Scripting Language• ARIES UUV Waypoint Lists (Track.out files)• Seahorse UUV Orders• REMUS UUV Objectives

XSLT Stylesheet

Vehicle-Specific Message or Script

Data Model

Message or Script

Page 9: CDR Duane Davis, USN

Translation of Text-Based Vehicle-Specific Formats to the

Data ModelParse using a Context Free Grammar (CFG)

• Chomsky Normal Form (CNF)

• Cocke-Younger-Kasami (CYK) Algorithm

• Yields a Binary Parse TreeTranslate Parse Tree to AVCL

• Depth First Traversal• Template-Based Translation

of Individual Parse NodesComparison to XSLT-Based Translations

• Fixed Order vs. Arbitrary Traversal

• Arbitrary vs. In-Order Result Output Document Generation

Example Chomsky Normal Form Rules:Mission -> LaunchCmd + MissionMiddle

Mission -> LaunchCmd + MissionEnd

MissionMiddle -> WaypointCmd + MissionMdl

MissionMiddle -> SurfaceCmd + MissionMdl

MissionMiddle -> WaypointCmd + MissionEnd

MissionMiddle -> SurfaceCmd + MissionEnd

MissionEnd -> WaypointCmd + RendezvousCmd

MissionEnd -> SurfaceCmd + RendezvousCmd

Example (Partial) Parse Tree:

Mission

LaunchCmd MissionMdl

WaypointCmd MissionEnd

RendezvousCmdSurfaceCmd

Page 10: CDR Duane Davis, USN

Translation Between Data Model and Binary Formats

XML Encoding of Binary Format • Serialization of XML to Binary• Reading of Binary to XML• XSLT Conversion between Data Model and XML Encoding

• Intuitive and Repeatable Implementation• Other Efforts

• Distributed Interactive Simulation (DIS) XML• Unmanned Systems Common Service Specification (USCS)

• Exemplar: Joint Architecture for Unmanned Systems (JAUS) Messages

XML

JAUS Binary

Programming Object

AVCL

XSLT XSLT

JAUS XML Schema

Serializer Reader

JAXB

Page 11: CDR Duane Davis, USN

Translation IssuesCommand Parameter Maintenance

• Concurrent Behaviors vs. Self-Contained Commands• XSLT and Side Effects (Immutable Variables)

Simulate Mutable Variables using Parameters and Explicitly Controlled Iteration:

begin XSLT processing variable B = sequential list of task-level-behaviors apply template for B1 with default parameters d1 to dn

end XSLT processing

begin template for task-level-behavior Bi with parameters p1 to pn

for k = 1 to n variable vk

if Bi updates pk

vk = new_pk

else vk = pk

generate required output for Bi apply template for Bi+1 with parameters v1 to vn

end template

Page 12: CDR Duane Davis, USN

Translation Issues (2)

Unmappable Vehicle-Specific Information• REMUS WaitStart Objectives• Seahorse Waypoint Collect Sound Velocity

Profile (SVP) Field• …

• Applicable Content Translated Accordingly• Irrelevant Content Ignored

<UUVCommandScript> … <MetaCommand name=“waitMagnet”/> <MetaCommand name=“collectSVP” content=“true”/> …</UUVCommandScript>

Page 13: CDR Duane Davis, USN

Research Objective 3

Support for Abstract Task Specification• Goals to be Accomplished• Constraints to be Observed• Specified Declaratively• Intuitive

Incorporation into the Common Data Model• Construction of Task-Level Behavior Scripts

to Accomplish Declarative Goals• Inference of Appropriate Goals from Task-

Level Behavior Scripts

Page 14: CDR Duane Davis, USN

Declarative Goal-Based Mission Definition

Finite State Machine (FSM)• States (Goals)

• Operating Area• Goal Description

• Transitions Dependent on Goal Success or Failure

Constraints• Launch and Recovery

Positions• Avoid Areas• Ingress Routing• Egress Routing

Mission Start

Rendezvous with UUV-2 in Area C

Search Area A

Search Area B Sample Environment in Area A

Mission Complete

SucceedFail

SucceedFailSucceed

or Fail

Succeed or Fail

Page 15: CDR Duane Davis, USN

G

S

Avoid

Avoid

Avoid

Avoid

S

G

Conversion of Declarative Missions to Task-Level Behavior

ScriptsGlobal Path Planning

• Transit Between Operating Areas• Observe Routing Requirements• Bypass Avoid Areas

Best-First Search• Shortest Available Path• Each Area Incursion Yields 2 Child Candidate Paths

Local Path Planning (Obstacle Avoidance) Still Required

G

Avoid

Avoid

SS

Avoid

Avoid

G

Page 16: CDR Duane Davis, USN

Generation of Task-Level Behavior Sequences to Accomplish Declarative

GoalsTemplates for Simple Goal Types

• Reposition• MonitorTransmissions• Jam• Illuminate

MONITOR TRANSMISSIONS GOAL DEFINITION:<Goal alert="false"> <MonitorTransmissions/> <OperatingArea> <Rectangle> <NorthwestCorner> <XYPosition x="1950.0" y="1975.0"/> </NorthwestCorner> <Width value="100.0"/> <Height value="150.0"/> </Rectangle> </OperatingArea> <Duration value="600.0"/></Goal>

GENERATED TASK-LEVEL BEHAVIOR SEQUENCE:<GpsFix value="true"/><MetaCommand name="beginGoal" content="monitorTransmissions"/><Loiter description="Station at area center"> <XYPosition x="1875.0" y="2025.0"/> <Depth value="3.0"/> <MakeSpeed value="1.5"/> <LoiterDepth value="1.0"/></Loiter><MetaCommand name="receiverOn" content="true"/><WaitUntilTime value=“600.0”/><MetaCommand name="receiverOn" content="false"/><MetaCommand name="endGoal"/>

Page 17: CDR Duane Davis, USN

Operating Area Coverage Pattern Generation

Decision-Tree Based Pattern Selection• Pattern Options

• International Aeronautical and Maritime Search and Rescue (IAMSAR) Manual• Planner Derived

• Predicate Values• Operating Area Characteristics• Vehicle Characteristics• Goal Requirements

Nearly Rectangular

Point Datum

Nearly Circular Expanding Square

Sector PatternSmall Area

Oriented Expanding Square

Expanding Rectangle

Nearly Square

Planner-Generated Pattern

Nearly Square or Nearly Circular

Shrinking Square

Parallel Track Pattern

True

False

Predicate

Search Pattern Type

Nearly Rectangular

Planner-Generated Pattern

Page 18: CDR Duane Davis, USN

Parametrically Specified IAMSAR Pattern Examples

Expanding-Square Pattern

• Point-Focused Search• Circular or Square

Area• Potentially Large Area

Parallel-Track Pattern• Area-Focused Search• Rectangular, Circular,

or Convex Polygonal Area

Page 19: CDR Duane Davis, USN

IAMSAR Patterns and Irregular (Concave) Polygonal Areas

Page 20: CDR Duane Davis, USN

Fast Solution A* Search Coverage-Pattern Generation

• Search Definition• Area covered with points

spaced at ½ required track spacing

• A point is considered “searched” if a search leg passes within ½ track spacing

• A pattern leg can end at any unsearched point

• The search is complete when all points have been “searched”

• Search Metrics• Partial path cost:

path length + turn penalty• Remaining cost estimate:

unsearched points * trk spacing * 5

• Favors patterns with fewer legs

Page 21: CDR Duane Davis, USN

Hill-Climbing Search Coverage-Pattern Generation

• Identical Search Definition• Search Metrics

• Partial path cost: path length + turn penalty

• Remaining cost estimate:0.25 * unsearched points * trk

spacing

• Favors patterns with shorter travel distances

• Search Progression• Chooses the “best” available

waypoint using an A* heuristic• No Backtracking• Goal state must be reachable

from any intermediate state

Page 22: CDR Duane Davis, USN

Traveling Salesman Problem (TSP) Iterative Improvement Coverage-Pattern

Generation• Search Definition

• Area covered with points spaced at required track spacing

• Each point must be used to end exactly 1 pattern leg

• Search Metrics• Solution cost:

path length + turn penalty• Favors patterns with longer,

straighter legs• Search Progression

• Start with an arbitrary visit order• Conduct pairwise comparison

and swap locations in visit sequence as appropriate

• Algorithm ends when no further improvements are obtainable

Page 23: CDR Duane Davis, USN

TSP Iterative Improvement with Simulated Annealing Coverage-Pattern Generation

• Identical Search Definition• Identical Search Metrics• Search Progression

• Conduct pairwise comparison• Switch order if better (usually)• Probabilistically switch even if

worse• Probabilistically don’t switch

even if better

• Probability of a “bad” swap decision decreases linearly with time

• Termination criteria• System cool (Pbad = 0)

• No further improvements are obtainable

Page 24: CDR Duane Davis, USN

Comparison of Planner-Based Coverage-Pattern Generation

Techniques

0.5

0.7

0.9

1.1

1.3

1.5

1.7

1.9

2.1

2.3

1 2 3 4 5 6 7 8 9 10 AvgSearch Area

Sea

rch

Pla

n T

rack

Len

gth

to

O

BB

-Ali

gn

ed P

aral

lel

Tra

ck

Len

gth

OBB-Aligned Expanding Square OBB-Aligned Parallel TrackBest Search Time A* Combined Best-First / A*Hill Climbing TSP Iterative ImprovementTSP Simulated Annealing

0

5

10

15

20

25

30

35

1 2 3 4 5 6 7 8 9 10 AvgSearch Area

Pla

nn

er R

un

Tim

e (s

ecs)

Best Search Time A* Combined Best-First / A* Hill Climbing

TSP Iterative Improvement TSP Simulated Annealing

Page 25: CDR Duane Davis, USN

Goal Inference from Task-Level Behavior Scripts Overview

Assumptions• No MetaCommand Behaviors• Script Corresponds to a Single Goal• Direct Transit to and from Operating Area

Classification of Scripts as 1 of 5 Goal Types• Point Search• Area Search• Reposition• Patrol• Monitor Transmissions

Page 26: CDR Duane Davis, USN

Goal Inference Using Case-Based Reasoning (CBR)

75-Script Recall Set• 15 of Each Goal Type• 25 of Each Vehicle

Type

15 Characteristics• Values from 0 to 1• Weighted

Closest Match Wins:

CBR Characteristics:Amount of time the vehicle is stationary

Effectiveness of the script to provide area coverage

Degree to which the script focuses on a single point

Degree to which the script calls for parallel tracks

Degree to which the script calls for orthogonal tracks

How frequently the script calls for points to be revisited

Distance between launch and recovery positions

Number of legs (waypoints)

Ratio of sensor sweep width to operating area size

How close early waypoints are to the operating area center

Degree to which the vehicle uses typical “patrol” speed

Degree to which the vehicle uses typical “transit” speed

Degree to which the vehicle utilizes typical “search” speed

Amount of time a UUV spends on the surface

Amount of time depth or altitude are constant

15

1

,ii i

i

distance r x w c x c r

Page 27: CDR Duane Davis, USN

Goal Inference Using Naïve Bayes (NB) Reasoning

Conditional Probability and Bayes Formula:

14 Characteristics• Discrete (mostly

Boolean) Values • Assumed Independence

Probabilities • 104 Script Recall Set• Manual Adjustment in

some Cases

Maximum a Posteriori (MAP) Classification Wins

NB Characteristics:Significant stationary positioning

Area effectively covered

Script focuses on a single location

Script contains of many parallel tracks

Script contains many orthogonal tracks

Many points are visited more than once

Mission finishes close to the launch point

Script contains many waypoints

Operating area is small relative to the sensor sweep width

Early waypoints are near the center of the operating area

Vehicle maintains a constant speed

Waypoints form sectors

Vehicle maintains a constant depth or altitude

Vehicle spends a lot of time on the surface

i

ii cPcP

HcPHcPHPccHP

...

|...|...|

1

11

Page 28: CDR Duane Davis, USN

Comparison of CBR and NB Goal Inference

0.3

0.4

0.5

0.6

0.7

0.8

0.9

1.0

Area Search Point Search Patrol MonitorTransmissions

Reposition Overall

CBR Precision (Ideal) NB Precision (Ideal)CBR Precision (Acceptable) NB Precision (Acceptable)CBR Recall (Ideal) NB Recall (Ideal)CBR Recall (Acceptable) NB Recall (Acceptable)

Page 29: CDR Duane Davis, USN

Research Objective 4

Development of a Hybrid Control Architecture Inherently Relying on the Common Data Model• Vehicle Independent

• Provides High-Level Direction using the Existing Vehicle Controller

• Requires Minimal Modification to Existing Controller• Relies on Previous Research Objectives

• Overview• Uses a Declarative Goal-Based Mission Definition• Generates Task-Level Behavior Scripts to Accomplish

Goals• Converts Task-Level Behavior Scripts to Vehicle-Specific

Commands• Issues Vehicle-Specific Commands to Vehicle Controller• Replans as Required

Page 30: CDR Duane Davis, USN

The Extended Rational Behavior Model (ERBM)

Based on the Rational Behavior Model (RBM)• Three-Layer Hybrid Architecture Analogous to

the Command Structure of a Naval Vessel• Strategic Level—High Level Mission Control (CO)• Tactical Level—Implementation of High-Level

Direction (watch officers)• Execution Level—Hardware Interface (enlisted

watches)

• Leverages Other Research Objectives• Declarative and Task-Level Mission Specification• Generation Task-Level Behavior Sequences to

Accomplish Declarative Goals• Translation of Task-Level Behaviors to Vehicle-

Specific Commands

Page 31: CDR Duane Davis, USN

ERBM Architecture

Strategic Level

Tactical Level

Execution Level (existing vehicle controller)

Declarative AVCL Mission

High-Level World Model

Mid-Level World Model

State and Sensor Data

Translator

Task-L

evel

Beh

avior S

cript

Veh

icle-Sp

ecific

Co

mm

and

Co

mm

and

Statu

s

& P

ositio

n U

pd

ate

Scrip

t Statu

s

Script Control

Agenda Control

Planner

Task-Level Behavior

Goal

Command Flow

Visible Data

Communications

Extended Rational Behavior Model Controller

Page 32: CDR Duane Davis, USN

FSM-Based Strategic Level Control

Complete

Search Pattern Set Alert

Transit to Area

start

in area, alert=true

in area, alert=false

activate

target locatedsingle target=true

time out ti

me

ou

t

pattern complete

target locatedsingle target=false

Complete

Patrol Pattern Set Alert

Transit to Area

start

in area, alert=truein area, alert=false

activate

time outtime outtarget

detected

pattern complete

Search Goal FSM

Patrol Goal FSM

Page 33: CDR Duane Davis, USN

On-Vehicle ERBM Implementation

ERBM Controller

PC104

QNXE

ERBMConnection Process

RExec Process

Shared Memory

Script Status Flag

Hard Drive

track.out

ARIES Waypoint Lists

“TacticalEnding” Message

“Position X Y” Messages“ScriptComplete” Messages

“ScriptFail” Messages

Actuators

Telemetry

Simulation VE

Data and Message Flow

Hardware-in-the-Loop Simulation Data Flow

The NPS ARIES UUV

Page 34: CDR Duane Davis, USN

Virtual Environment (VE) TestingModeling

• UUV, USV and UAV Models• 6-DOF Rigid-Body Dynamics

Visualization• X3D• DIS

• Standalone (AUVW only)• Vehicle Hardware in the

Loop

Page 35: CDR Duane Davis, USN

ARIES UUV ERBM ResultsMission Consisting of a Single Reposition Goal

• No Avoid Areas• Required Routing• In-Water Results from Monterey Bay (16 June 2006)

Page 36: CDR Duane Davis, USN

ARIES ERBM Results (2)Mission Consisting of a Single Monitor

Transmissions Goal• 1 Circular Avoid Area• Rectangular Operating Area• VE Results using On-Vehicle Implementation

Page 37: CDR Duane Davis, USN

ARIES ERBM Results (3)Missions Consisting of Similar Single Area-Search Goals

• Single-Target (Left) and Multi-Target Search• Target Detection (Simulated) as Indicated• In Water Results from Monterey Bay (25 July 2006)

Page 38: CDR Duane Davis, USN

ARIES ERBM Results (4)Multi-Goal Mission

• Executes Single-Target Area Search First• On Success (Left) Executes Patrol Goal• On Failure (Right) Executes Monitor Transmissions Goal

• VE Results using On-Vehicle Implementation

Page 39: CDR Duane Davis, USN

Research Conclusions and Contributions

Leveraging of dissimilar vehicle commonalities in the development of a vehicle-independent AV data model

Viability of XML as a format of choice for this common data model

Practical application of the common data model to actual vehicles

Page 40: CDR Duane Davis, USN

Research Conclusions and Contributions (2)

Implementation of a set of vehicle-independent task-level behaviors with deterministic time-arc semantics

Demonstration of the use of these behaviors to encode tasking for arbitrary vehicles

Page 41: CDR Duane Davis, USN

Research Conclusions and Contributions (3)

Development of translation mechanisms for conversion between the XML-based common data model and vehicle-specific data formats (text and binary)• XSLT• CFGs• Intermediate XML Form

Page 42: CDR Duane Davis, USN

Research Conclusions and Contributions (4)

Development of a declarative mechanism relying on high-level goals for AV task specification that is more abstract and intuitive than typical AV tasking formats

Implementation and refinement of techniques for converting between declarative goals and task-level behavior scripts

Page 43: CDR Duane Davis, USN

Research Conclusions and Contributions (5)

Design and implementation of a hybrid control architecture that leverages the declarative-to-task-level and task-level-to-vehicle-specific translation capabilities provided by the common data model to extend the autonomous capability of arbitrary vehicles with minimal modification to existing control software

Page 44: CDR Duane Davis, USN

Recommendations for Future Work

• Testing with More Actual Vehicles of Different Types• More Rigorous Analysis of UGV, USV, and UAV Requirements• Standard Mission Systems, Payload, and Manipulator

Interface and Incorporation into the Task-Level Behavior Set• Planner Generation of Multi-Vehicle and Multi-Pass Searches• Study of Goal-Type / Script Characteristics Relationships and

Improved Goal-from-Script Inference• Improved ERBM Tactical Level Functionality• Use of the Common Data Model in Direct Support of

Coordinated Operations• Exploration of Various Message-Translation Options During

Coordinated Operations• Use of the Common Data Model to Facilitate Interface

between AV Systems and More General Command and Control Systems

• Possible Evolution from Data Model to Ontology

Page 45: CDR Duane Davis, USN

Questions

Page 46: CDR Duane Davis, USN

Backup Slides

Page 47: CDR Duane Davis, USN

Task-Level Behaviors

Similar Efforts• Joint Architecture for Unmanned Systems

(JAUS)• NATO Standardization Agreement (STANAG)

4586• Common Command Language (CCL)

Commonalities• Potential Command Types

• Closed-Loop—Control Relies on State Feedback• Open-Loop—Explicit Actuator Settings• Non-Control-Related—Mode and Selection Switches

• Deterministic Time Arc Semantics

Page 48: CDR Duane Davis, USN

Research Objective 1a

Inter-Vehicle Message Set Development• Identify Messaging Requirements• Implement Messages Meeting these

Requirements

Page 49: CDR Duane Davis, USN

Inter-Vehicle MessagingRelated Efforts

• Remotely Operated Vehicle (ROV) Systems• Inherently Message Based• JAUS, STANAG 4586

• Vehicle-Independent AV Systems• CCL• Compact Control Language (C2L)• Cooperative Distributed Oceanographic Sampling Network

(CoDA)• Foundation for Physical Agents (FIPA) Communicative Act

Library Specification (CALS)• Request-Inform Model

Message Type Description Message Category

Command the vehicle to perform an action Request (activity)

Request information from the vehicle Request (information)

Provide vehicle state or event information Inform

Provide vehicle capabilities or characteristics information Inform

Initiate or request cooperative group maintenance Request (activity)

Page 50: CDR Duane Davis, USN

XSLT-Based Translation Issues

Limited Numerical Processing• Turing Complete, but not Necessarily Easy• Example: Trigonometry

XSLT Extensions—Typically Implemented in Java

360

2 0LatLatRx

360

cos2 0LonLonLatRy

02

360Lat

R

xLat

0cos2

360Lon

LatR

yLon

<xsl:value-of

select=“ java:LatitudeLongitudeConversion.getXFromLatitude($geoOriginLat,

./LatitudeLongitude/@latitude) ”/>

Extension Namespace

Static Java Method Invocation

Method Parameters (XPath)

Page 51: CDR Duane Davis, USN

Mapping from the Data Model to ARIES and Seahorse UUV

Waypoints

ARIES Waypoint Fields

Cartesian Y

Cartesian X

Right Screw Speed

Left Screw Speed

Vertical Control Flag

Waypoint

MakeAltitude

MakeDepth

MakeKnots

MakeSpeed

SetPower

Ordered Transit Altitude

Ordered Transit Depth

GPS Popup Flag

GPS Popup Duration (computed)

Watch Radius

Time Out (computed)GpsFix

Standoff

Seahorse Waypoint Navigation

Homing Mode

Location

Depth / Altitude

Transit Speed

Use SSS

Waypoint

MakeAltitude

MakeDepth

MakeKnots

MakeSpeed

SetPower

MetaCommand

Content will be mapped

Content may be mapped

Page 52: CDR Duane Davis, USN

Mapping from the Data Model to REMUS UUV and JAUS Waypoints

REMUS Navigate or Dead Reckon

Offset Y Axis (0)

Destination

Offset Direction (0)

Offset Distance (0)

Depth Control Mode

Waypoint

MetaCommand

MakeAltitude

MakeDepth

MakeKnots

MakeSpeed

SetPower

Content will be mapped

Content may be mapped

Depth / Altitude / Triangle

Speed

Follow Trackline

Sidescan Range

Timeout (auto)

JAUS Set Global Waypoint

Elevation

Waypoint Number (computed)

Latitude

Longitude

Waypoint

MakeAltitude

MakeDepth

MakeAltitudeAGL

MakeAltitudeMSL

Page 53: CDR Duane Davis, USN

Mapping from the ARIES and Seahorse UUV Waypoints to the

Data Model

ARIES Waypoint Fields

Cartesian Y

Cartesian X

Right Screw Speed

Left Screw Speed

Vertical Control Flag

Ordered Transit Altitude

Ordered Transit Depth

GPS Popup Flag

GPS Popup Duration (computed)

Watch Radius

Time Out (computed)

Cartesian X

Cartesian Y

Waypoint

Transit Power

Depth or Altitude

GPS Fix

Standoff Distance

Time Out

Seahorse Waypoint Navigation

Homing Mode

Location

Depth / Altitude

Transit Speed

Use SSS

name (“useSSS”)

content

MetaCommand

value

MakeSpeed or MakeKnots

value

MakeDepth or MakeAltitude

LatitudeLongitude or RelativeXYPosition

HomingMode

Waypoint

Page 54: CDR Duane Davis, USN

Mapping from the REMUS UUV Waypoint Objectives to the Data

Model

Navigate, Dead Reckon or Transponder Home

Destination

Depth Control Mode

Depth / Altitude / Triangle

Speed

Follow Trackline

Track Ping Interval

Timeout

Type

name (“waypointNavMode”)

content

MetaCommand

name (“transponderLabel”)

content

MetaCommand

name (“triangle…”)

content

MetaCommand (3 or 4)

value

MakeDepth or MakeAltitude

value

MakeSpeed or MakeKnots

name (“trackPingInterval”)

content

MetaCommand

name (“sidescanRange”)

content

MetaCommand

Sidescan Range

LatitudeLongitude

HomingMode

Waypoint

TimeOut

Behavior will be generated

Behavior may be generated

Page 55: CDR Duane Davis, USN

ERBM Modifications to the RBM

Extension Formalizes and Extends (Nicholson, 04)• Allows Numerical Processing at Strategic Level to

Facilitate Planning• Makes Strategic and Tactical Levels Interruptible• Replaces Pull-Only Communications Model with Push-

Pull Model• Allows Each Level to Maintain a World Model

Commensurate with the Level of Decision-Making• Separates Mission Definition from Strategic Level

Implementation and Behavior Activation

Page 56: CDR Duane Davis, USN

Rendezvous

Departure GPS

Location

Depth / Altitude

Transit Speed

Arrival GPS

Waypoint

GpsFix

MakeAltitude

MakeDepth

MakeKnots

MakeSpeed

SetPowerContent will be mapped

Content may be mapped

Task-Level Behavior Mapping to a Seahorse UUV Rendezvous

Command

Page 57: CDR Duane Davis, USN

Station Keep

Until When

Location

Transit Depth / Altitude

Loiter Depth

Loiter

MakeAltitude

MakeDepth

WaitUntilTime

Surface Comms

Take GPS Fix

Collect SVP

Return to Depth (False)

Return to Start (False)

Perform RF Comms

GPS FixCollect SVP

Return to Start (False)

GpsFix

MetaCommand

Content will be mapped

Content may be mapped

Task-Level Behavior Mappings to Seahorse UUV GPS Fix, Surface Comms, and Station Keep

Commands

Page 58: CDR Duane Davis, USN

Set Position

Destination Longitude

Destination Latitude

Offset Distance (0)

Offset Direction (0)

Offset Y Axis (0)

SetPosition

Content will be mapped

Content may be mapped

REMUS Surface Objective

Timeout (auto)

Speed

MakeKnots

MakeSpeed

SetPower

Task-Level Behavior Mappings to REMUS UUV Set Position and Surface

Objectives

Page 59: CDR Duane Davis, USN

Transponder Home

Offset Y Axis (0)

Label

Offset Direction (0)

Offset Distance (0)

Depth Control Mode

Waypoint

MetaCommand

MakeAltitude

MakeDepth

MakeKnots

MakeSpeed

SetPower Content will be mapped

Content may be mapped

Depth / Altitude / Triangle

Speed

Follow Trackline

Sidescan Range

Timeout (auto)

Task-Level Behavior Mapping to a REMUS UUV Transponder Home

Objective

Page 60: CDR Duane Davis, USN

Rendezvous

Departure GPS

Location

Depth / Altitude

Transit Speed

Arrival GPS

value

MakeDepth or MakeAltitude

value

MakeSpeed or MakeKnots

LatitudeLongitude

ObtainGps

Waypoint

GpsFix

value (computed)

Wait

Quit

Behavior will be generated

Behavior may be generated

Mapping from a Seahorse Rendezvous Command to Task-Level

Behaviors

Page 61: CDR Duane Davis, USN

Station Keep

Until When

Location

Transit Depth / Altitude

Loiter Depth

value

MakeDepth or MakeAltitude

LatitudeLongitude or RelativeXYPosition

Depth

Loiter

value

WaitUntilTime

Mapping from a Seahorse UUV Station Keep Command to Task-

Level Behaviors

Page 62: CDR Duane Davis, USN

Surface Comms

Take GPS Fix

Collect SVP

Return to Depth

Return to Start

Perform RF Comms

name (“rfComms”)

content

MetaCommand

name (“obtainSVP”)

content

MetaCommand

value (computed)

Wait

value (0)

MakeDepth

GpsFix

value (previous)

MakeDepth

LatitudeLongitude (previous)

Waypoint

Behavior will be generated

Behavior may be generated

Mapping from a Seahorse UUV Surface Comms Command to Task-Level

Behaviors

Page 63: CDR Duane Davis, USN

GPS FixCollect SVP

Return to Start

name (“obtainSVP”)

content

MetaCommand

LatitudeLongitude (previous)

Waypoint

GpsFix

Behavior will be generated

Behavior may be generated

Mapping from a Seahorse UUV GPS Fix Command to Task-Level

Behaviors

Page 64: CDR Duane Davis, USN

Hardware Location

Location

Type (not equal to “waypoint”)

Transponder Depth

name (“hardware”)

content

MetaCommand

name (“latitude”)

content

MetaCommand

name (“longitude”)

content

MetaCommand

name (“depth”)

content

MetaCommand

Mapping from a REMUS UUV Hardware Location to Task-Level

Behaviors

Page 65: CDR Duane Davis, USN

Navigate Rows

Destination

Depth Control Mode

Depth / Altitude / Triangle

Speed

Follow Trackline

Track Ping Interval

Timeout

name (“triangle…”)

content

MetaCommand (3 or 4)

value

MakeDepth or MakeAltitude

value

MakeSpeed or MakeKnots

name (“trackPingInterval”)

content

MetaCommand

name (“sidescanRange”)

content

MetaCommand

Sidescan Range

LatitudeLongitude (computed)

HomingMode

Waypoint (multiple)

TimeOut

Behavior will be generated

Behavior may be generated

Num Rows

Row Spacing

name (“waypointNavMode”)

content (“best”)

MetaCommand

Mapping from a REMUS UUV Navigate Rows Objective to Task-

Level Behaviors

Page 66: CDR Duane Davis, USN

Compass Calibration

Clear Calibration?

Move Away Duration

Surface

Timeout

Speed

name (“compassCalibration”)

MetaCommand

Value (computed)

Wait

value

MakeDepth

value

MakeSpeed, MakeKnots or SetPower

name (“moveAway”)

content

MetaCommand

name (“clearCalibration”)

content

MetaCommand

Mapping from REMUS UUV Compass Calibration and Surface Commands to

Task-Level Behaviors

Page 67: CDR Duane Davis, USN

JAUS XML Message

Message Data

Header

JAUS XML Message List

AVCL Message

body

head

AVCL Message List

JAUS XML Message

Message Data

Header

JAUS XML Message List

name (“senderID”)

MetaCommand

AVCL Task-Level Script

name (“destinationID”)

content

MetaCommand

name (“acknowledge”)

content

MetaCommand

Task-Level Command

MetaCommand …

content

Mapping from JAUS Messages to AVCL Messages

Page 68: CDR Duane Davis, USN

Set Global Vector

Elevation

Speed

Heading

Roll

Pitch

value

MakeSpeed

value

MakeDepth (UUV Only)

value

MakeAltitude (UAV Only)

value

MakeHeadingIndicates Optional Data

Mapping from a JAUS Set Global Vector Message to Task-Level

Behaviors

Page 69: CDR Duane Davis, USN

Set Wrench Effort

PropulsiveLinearY

PropulsiveLinearX

PropulsiveLinearZ

PropulsiveRotationalX

PropulsiveRotationalY

PropulsiveRotationalZ

value

SetPower

lateralThrusters

SetThrusters (UUV Only)

verticalThrusters

SetThrusters (UUV Only)

value

SetClimbRate (UAV Only)

value

SetAileron (UAV Only)

value

SetPlanes (UUV Only)

value

SetElevator (UAV Only)

value

SetRudder (USV Only)

value

SetTurnRate (UAV Only)

value

SetRotate (UUV Only)

Indicates Optional Data

ResistiveLinearY

ResistiveLinearX

ResistiveLinearZ

ResistiveRotationalX

ResistiveRotationalY

ResistiveRotationalZ

Mapping of a JAUS Set Wrench Effort Message to Task-Level Behaviors

Page 70: CDR Duane Davis, USN

Combined Best-First / A* Search Coverage-Pattern Generation

• Identical Search Definition• Search Metrics

• Partial path cost: path length + turn penalty

• Remaining cost estimate:0.25 * unsearched points * trk

spacing

• Favors patterns with shorter travel distances

• Search Progression• Standard A* search• Commits to best partial solution

after 5 steps and restarts from there

• Goal state must be reachable from any intermediate state

Page 71: CDR Duane Davis, USN

Complete

Illuminate or Jam Set Alert

Transit to Area

start

in area, alert=truein area, alert=false

activate

time outtime out

ERBM Jam or Illuminate Goal FSM Control

Page 72: CDR Duane Davis, USN

Complete

Monitor Set Alert

Transit to Area

start

in area, alert=truein area, alert=false

activate

time outtime out

transmission detected

ERBM Monitor Transmissions Goal FSM Control

Page 73: CDR Duane Davis, USN

Complete

Sampling Pattern Set Alert

Transit to Area

start

in area, alert=truein area, alert=false

activate

time outpattern complete

contaminant detected

time out

ERBM Sample Environment Goal FSM Control

Page 74: CDR Duane Davis, USN

Mark Target

Complete

Search Pattern Set Alert

Transit to Area

start

in area, alert=truein area, alert=false

activate

target found

time o

ut

time o

ut

tim

e o

ut

pattern complete

ERBM Mark Target Goal FSM Control

Page 75: CDR Duane Davis, USN

Decontaminate

Complete

Sampling Pattern Set Alert

Transit to Area

start

in area, alert=truein area, alert=false

activate

contaminant detected

time o

ut

pattern complete

tim

e o

utcontaminant

removed

time out

ERBM Decontaminate Goal FSM Control

Page 76: CDR Duane Davis, USN

Engage Target

Complete

Search Pattern Set Alert

Transit to Area

start

in area, alert=truein area, alert=false

activate

target found

target en

gag

edsin

gle targ

et=tru

e

time o

ut ti

me

ou

ttarget engagedsingle target=false

time o

ut

pattern complete

ERBM Attack or Demolish Goal FSM Control