Unmanned Mobile Sensor Net - Ben SnivelyProblem / MotivationMarine Sensing EquipmentSensor Network DetailsOverviewMobile Sensors and SinkDomain DefinitionDomain ExampleSearch PathsTracks ExampleGlider GroupsGlider Groups ExampleYAES SimulationsBackground Information on SimulationSimulation 1: Boundary TestSimulation 2 : Interior GlidersSimulation 3 : Boundary and Interior GlidersExtending NetworkGlider AgentsPlanning / Decision ProcessQuestions?Unmanned Mobile Sensor Net- Ben SnivelyUnmanned Underwater GlidersSurvey and extensions to work from:COOPERATIVE CONTROL OF COLLECTIVE MOTION FOR OCEAN SAMPLING WITH AUTONOMOUS VEHICLES; Derek A. PaleyUniversity of Central FloridaManual Ocean Sampling labor, resource, and time intensive.Objectives/SensingGradient ClimbingFeature TrackingBoundary MonitoringPerimeter SurveillanceMappingAutonomous Distributed Agents both reduce over costs, improve accuracy, and reduce latency for critical data.Problem / MotivationUniversity of Central FloridaMarine Sensing EquipmentNOAA Manual Ocean SurveyShips with complex survey equipmentPerforms in both shallow and deep water collections.AUV – Autonomous Underwater VehicleShallow water survey using GPS and Satellite communicationUniversity of Central FloridaSensor Network DetailsSink Satellite CommunicationAgents/Sensors Mobile GlidersEvery Glider in Range of Sink / GPSSatellite only communicate with satellite when at surfaceCannot control movement at surface (just floats) – has control only when submerged.GCCS – Glider Coordinated Control System GCCS steers groups/sets of glidersGliders controlled remotelyNo Agenda/Beliefs/PlanningGCCSUniversity of Central FloridaOverview“Apply a cooperative control methodology to control a fleet of autonomous underwater gliders. Underwater gliders soar through the water on a pair of fixed wings, collecting valuable oceanographic data for weeks at a time. We describe the Glider Coordinated Control System (GCCS), which steers multiple gliders to a set of coordinated trajectories. The GCCS automatically controlled up to six gliders continuously for over three weeks in a 800 km2 region in California’s Monterey Bay in August 2006. The GCCS enables oceanographers to specify and adapt glider sampling patterns with minimal human intervention.”(Paley)University of Central FloridaMobile Sensors and SinkUniversity of Central FloridaDomain DefinitionDomain:Outer Search AreaUniversity of Central FloridaDomain Example<domain><rectangle><x><units>deg</units><value>-122.3817</value></x><y><units>deg</units><value>36.9765</value></y><a><units>met</units><value>20000</value></a><b><units>met</units><value>10000</value></b><ori><units>deg</units><value>137</value></ori></rectangle></domain>Center Point LongitudeCenter Point LongitudeWidthHeightAngleUniversity of Central FloridaSearch PathsTracks Search PathsUniversity of Central FloridaTracks Example<tracks><superellipse><name>track1</name><x><units>deg</units><value>-122.2713</value></x><y><units>deg</units><value>36.8950</value></y><a><units>met</units><value>10000</value></a><b><units>met</units><value>6667</value></b><ori><units>deg</units><value>47</value></ori><p><value>3</value></p></superellipse></tracks>Shape/NameCenter PointWidthHeightUniversity of Central FloridaGlider GroupsGlider Tree:Entities, which paths to use,Comm model.University of Central FloridaGlider Groups Example<group><group><phase> <value>0</value> <units>pct</units> </phase><glider><mnf>w</mnf> <!-- Manufacturer --><sn>7</sn> <!-- Serian Number --><model>e</model><track>track1</track><direction>1</direction><phase> <!-- Curve Phase --><value>0</value><units>pct</units> </phase><control> sellipse control </control></glider><glider> . . . </glider></group></group>University of Central FloridaYAES SimulationsSimulations Performed1. 4 Boundary Gliders rotating same direction2. 4 Boundary and 6 Interior Sensors, All positioned in ideal/planned position.3. 4 Boundary and 6 Interior Gliders, all starting from hub locationActual software from research done in Matlab. Software allows for both simulated and real testsUniversity of Central FloridaBackground Information on SimulationXML Configurations drive simulation setup and context.Much like the Real system, xml configuration files define gliders, tracks, and other system configuration. (The XML Schema was slightly modified in order to simplify configuration)Main Simulation class allows for selection of which simulation to perform.JAXB used to parse XML Input / Java 1.6 SDK/Runtime(JAXB = Java API for XML Binding)University of Central FloridaSimulation 1: Boundary TestSink Communication at surface4 Boundary GlidersUniversity of Central FloridaSimulation 2 : Interior Gliders6 Interior Gliders covering Area3 Groups, 2 Gliders in each.(Gliders communicate w/ Sink at Surface)University of Central FloridaSimulation 3 : Boundary and Interior GlidersSink Communication at surface4 Boundary Gliders6 Interior GlidersFlow adds error (off track) when Glider is at surfaceUniversity of Central FloridaExtending NetworkCurrent LimitationsCentral control/PlanningPlanning communication only done at surface (when gliders are floating and have no control – drift)Limited Inter-glider communication.Extending Sensor network principals to the systemGliders become agents with beliefs, agendas, and planningSensor communication models and MDP principals (Specifically Partially Observable - MDP)This is critical due to the fluxations and inconsistencies in the robot control.University of Central FloridaGlider AgentsKey DifferenceGlider has Agenda, Goal, and isn’t pure input/sensing device.Glider communicate with each otherGoal:Cover area (and plan) that hasnot been covered by other agents.Inform others plan/area covered.Single Sink transmitter could be at surface, to bridge under-water to satellite gap.University of Central FloridaPlanning / Decision ProcessPO-MDP (Partially Observable Mark-ov Decision Process.Outcome from Glider commands uncertain.Policy mapping between States / Actions Perceived new State.Routing issues isn’t applicable due to every glider having access to the sink (via satellite).Routing issues could be introduced in a more complex system where messages between gliders and to sink are transmitted.University of Central
View Full Document