Size: px
Start display at page:

Download "1.04 1.02 0.98 0.96 0.94 0.92 0.9"

Transcription

1 ANewExtensionoftheKalmanFiltertoNonlinear SimonJ.JulierSystems TheRoboticsResearchGroup,DepartmentofEngineeringScience,TheUniversityofOxford Oxford,OX13PJ,UK,Phone: ,Fax: JereyK.Uhlmann optimality,tractabilityandrobustness.however,theapplicationofthekftononlinearsystemscanbedicult. TheKalmanlter(KF)isoneofthemostwidelyusedmethodsfortrackingandestimationduetoitssimplicity, ABSTRACT widelyusedlteringstrategy,overthirtyyearsofexperiencewithithasledtoageneralconsensuswithinthe trackingandcontrolcommunitythatitisdiculttoimplement,diculttotune,andonlyreliableforsystems whicharealmostlinearonthetimescaleoftheupdateintervals. ThemostcommonapproachistousetheExtendedKalmanFilter(EKF)whichsimplylinearisesallnonlinear modelssothatthetraditionallinearkalmanltercanbeapplied.althoughtheekf(initsmanyforms)isa sampledpointscanbeusedtoparameterisemeanandcovariance,theestimatoryieldsperformanceequivalentto thekfforlinearsystemsyetgeneraliseselegantlytononlinearsystemswithoutthelinearisationstepsrequired bytheekf.weshowanalyticallythattheexpectedperformanceofthenewapproachissuperiortothatofthe EKFand,infact,isdirectlycomparabletothatofthesecondorderGausslter.Themethodisnotrestricted Inthispaperanewlinearestimatorisdevelopedanddemonstrated.Usingtheprinciplethatasetofdiscretely toassumingthatthedistributionsofnoisesourcesaregaussian.wearguethattheeaseofimplementationand moreaccurateestimationfeaturesofthenewlterrecommenditsuseovertheekfinvirtuallyallapplications. Keywords:Navigation,estimation,non-linearsystems,Kalmanltering,sampling. mustbeestimatedfromnoisysensorinformation,somekindofstateestimatorisemployedtofusethedatafrom Filteringandestimationaretwoofthemostpervasivetoolsofengineering.Wheneverthestateofasystem 1 INTRODUCTION andobservationmodelsarelinear,theminimummeansquarederror(mmse)estimatemaybecomputedusing dierentsensorstogethertoproduceanaccurateestimateofthetruesystemstate.whenthesystemdynamics thekalmanlter.however,inmostapplicationsofinterestthesystemdynamicsandobservationequationsare nonlinearandsuitableextensionstothekalmanlterhavebeensought.itiswell-knownthattheoptimalsolution tothenonlinearlteringproblemrequiresthatacompletedescriptionoftheconditionalprobabilitydensityis anumberofsuboptimalapproximationshavebeenproposed6?8;13;16;21. maintained14.unfortunatelythisexactdescriptionrequiresapotentiallyunboundednumberofparametersand

2 TheEKFappliestheKalmanltertononlinearsystemsbysimplylinearisingallthenonlinearmodelssothat thetraditionallinearkalmanlterequationscanbeapplied.however,inpractice,theuseoftheekfhastwo well-knowndrawbacks: ProbablythemostwidelyusedestimatorfornonlinearsystemsistheextendedKalmanlter(EKF)20;22. 1.Linearisationcanproducehighlyunstableltersiftheassumptionsoflocallinearityisviolated. linearsystems,yetgeneraliseselegantlytononlinearsystemswithoutthelinearisationstepsrequiredbythe 2.ThederivationoftheJacobianmatricesarenontrivialinmostapplicationsandoftenleadtosignicant EKF.Thefundamentalcomponentofthislteristheunscentedtransformationwhichusesasetofappropriately InthispaperwederiveanewlinearestimatorwhichyieldsperformanceequivalenttotheKalmanlterfor implementationdiculties. chosenweightedpointstoparameterisethemeansandcovariancesofprobabilitydistributions.wearguethat theexpectedperformanceofthenewapproachissuperiortothatoftheekfand,infact,isdirectlycomparable tothatofthesecondordergausslter.further,thenatureofthetransformissuchthattheprocessand algorithmhassuperiorimplementationpropertiestotheekf.wedemonstratethedierencesinperformancein observationmodelscanbetreatedas\blackboxes".itisnotnecessarytocalculatejacobiansandsothe Kalmanltertononlinearsystems.Wearguethattheprincipleproblemistheabilitytopredictthestateof thenewlterrecommenditsuseovertheekfinvirtuallyallapplications. anexampleapplication,andwearguethattheeaseofimplementationandmoreaccurateestimationfeaturesof thesystem.section3introducestheunscentedtransformation.itspropertiesareanalysedandafullltering algorithm,whichincludestheeectsofprocessnoise,isdeveloped.insection4anexampleispresented.using realisticdata,thecomparisonoftheunscentedlterandekfforthetrackingofareentrybodyisconsidered. Thestructureofthispaperisasfollows.InSection2wedescribetheproblemstatementforapplyinga ConclusionsaredrawninSection5.Acompanionpaper10,extendsthebasicmethodandshowsthatjudiciously selectingadditionalpointscanleadtoanydesiredlevelofaccuracyforanygivenpriordistribution. 2.1ProblemStatement 2 ESTIMATIONINNONLINEARSYSTEMS WewishtoapplyaKalmanltertoanonlineardiscretetimesystemoftheform wherex(k)isthen-dimensionalstateofthesystemattimestepk,u(k)istheinputvector,v(k)istheqdimensionalstatenoiseprocessvectorduetodisturbancesandmodellingerrors,z(k)istheobservationvector (2) x(k+1)=f[x(k);u(k);v(k);k]; z(k)=h[x(k);u(k);k]+w(k); (1) andw(k)isthemeasurementnoise.itisassumedthatthenoisevectorsv(k)andw(k),arezero-meanand \predictor-corrector"structure.let^x(ijj)betheestimateofx(i)usingtheobservationinformationinformation TheKalmanlterpropagatesthersttwomomentsofthedistributionofx(k)recursivelyandhasadistinctive Ev(i)vT(j)=ijQ(i);Ew(i)wT(j)=ijR(i);Ev(i)wT(j)=0;8i;j: uptoandincludingtimej,zj=[z(1);:::;z(j)].thecovarianceofthisestimateisp(ijj).givenanestimate predictedquantitiesaregivenbytheexpectations ^x(kjk),thelterrstpredictswhatthefuturestateofthesystemwillbeusingtheprocessmodel.ideally,the P(k+1jk)=Ehfx(k+1)?^x(k+1jk)gfx(k+1)?^x(k+1jk)gTjZki: ^x(k+1jk)=ef[x(k);u(k);v(k);k]jzk (4) (3)

3 ofx(k),conditiononzk,isknown.however,thisdistributionhasnogeneralformandapotentiallyunbounded niteandtractablenumberofparametersneedbepropagated.itisconventionallyassumedthatthedistribution ofx(k)isgaussianfortworeasons.first,thedistributioniscompletelyparameterisedbyjustthemeanand numberofparametersarerequired.inmanyapplications,thedistributionofx(k)isapproximatedsothatonlya Whenf[]andh[]arenonlinear,theprecisevaluesofthesestatisticscanonlybecalculatedifthedistribution informative3. covariance.second,giventhatonlythersttwomomentsareknown,thegaussiandistributionistheleast thekalmanlteralinearupdateruleisspeciedandtheweightsarechosentominimisethemeansquarederror oftheestimate.theupdateruleis Theestimate^x(k+1jk+1)isgivenbyupdatingthepredictionwiththecurrentsensormeasurement.In P(k+1jk+1)=P(k+1jk)?W(k+1)P(k+1jk)WT(k+1) ^x(k+1jk+1)=^x(k+1jk)+w(k+1)(k+1); Itisimportanttonotethattheseequationsareonlyafunctionofthepredictedvaluesofthersttwomoments ofx(k)andz(k).therefore,theproblemofapplyingthekalmanltertoanonlinearsystemistheabilityto W(k+1)=Px(k+1jk)P?1 (k+1)=z(k+1)?^z(k+1jk) predictthersttwomomentsofx(k)andz(k).thisproblemisaspeciccaseofageneralproblem tobe (k+1jk): abletocalculatethestatisticsofarandomvariablewhichhasundergoneanonlineartransformation. form.supposethatxisarandomvariablewithmeanxandcovariancepxx.asecondrandomvariable,yis 2.2TheTransformationofUncertainty relatedtoxthroughthenonlinearfunction Theproblemofpredictingthefuturestateorobservationofthesystemcanbeexpressedinthefollowing WewishtocalculatethemeanyandcovariancePyyofy. Thestatisticsofyarecalculatedby(i)determiningthedensityfunctionofthetransformeddistributionand y=f[x]: (5) closedformsolutionsexist.however,suchsolutionsdonotexistingeneralandapproximatemethodsmustbe (ii)evaluatingthestatisticsfromthatdistribution.insomespecialcases(forexamplewhenf[]islinear)exact, ecientandunbiased. used.inthispaperweadvocatethatthemethodshouldyieldconsistentstatistics.ideally,theseshouldbe holds.thisconditionisextremelyimportantforthevalidityofthetransformationmethod.ifthestatisticsare Thetransformedstatisticsareconsistentiftheinequality notconsistent,thevalueofpyyisunder-estimated.ifakalmanlterusestheinconsistentsetofstatistics,it willplacetoomuchweightontheinformationandunderestimatethecovariance,raisingthepossibilitythat Pyy?Ehfy?ygfy?ygTi0 (6) ofthelefthandsideofequation6shouldbeminimised.finally,itisdesirablethattheestimateisunbiasedor thelterwilldiverge.byensuringthatthetransformationisconsistent,thelterisguaranteedtobeconsistent greatlyinexcessoftheactualmeansquarederror.itisdesirablethatthetransformationisecient thevalue aswell.however,consistencydoesnotnecessaryimplyusefulnessbecausethecalculatedvalueofpyymightbe consideringthetaylorseriesexpansionofequation5aboutx.thisseriescanbeexpressed(usingratherinformal ye[y]. Theproblemofdevelopingaconsistent,ecientandunbiasedtransformationprocedurecanbeexaminedby

4 notation)as: wherexisazeromeangaussianvariablewithcovariancepxx,andrnfxnistheappropriatenthorderterm f[x]=f[x+x] inthemultidimensionaltaylorseries.takingexpectations,itcanbeshownthatthetransformedmeanand =f[x]+rfx+12r2fx2+13!r3fx3+14!r4fx4+ (7) covariancearey=f[x]+12r2fpxx+12r4fex4+ Pyy=rfPxx(rf)T+1 13!r3fEx4(rf)T+: 24!r2fEx4?Ex2Pyy?EPyyx2+P2yy(r2f)T+ (8) Inotherwords,thenthordertermintheseriesforxisafunctionofthenthordermomentsofxmultipliedby thenthorderderivativesoff[]evaluatedatx=x.ifthemomentsandderivativescanbeevaluatedcorrectly (9) uptothenthorder,themeaniscorrectuptothenthorderaswell.similarcommentsholdforthecovariance byaprogressivelysmallerandsmallerterm,thelowestordertermsintheseriesarelikelytohavethegreatest equationaswell,althoughthestructureofeachtermismorecomplicated.sinceeachtermintheseriesisscaled impact.therefore,thepredictionprocedureshouldbeconcentratedonevaluatingthelowerorderterms. thisassumption, LinearisationassumesthatthesecondandhigherordertermsofxinEquation7canbeneglected.Under Pyy=rfPxx(rf)T: y=f[x]; (10) thesecondandhigherordertermsinthemeanandfourthandhigherordertermsinthecovariancearenegligible. ComparingtheseexpressionswithEquations8and9,itisclearthattheseapproximationsareaccurateonlyif However,inmanypracticalsituationslinearisationintroducessignicantbiasesorerrors.Anextremelycommon (11) andimportantproblemisthetransformationofinformationbetweenpolarandcartesiancoordinatesystems10;15. Thisisdemonstratedbythesimpleexamplegiveninthenextsubsection. 2.3Example returnspolarinformation(rangerandbearing)andthisistobeconvertedtoestimatetocartesiancoordinates. Thetransformationis: Supposeamobilerobotdetectsbeaconsinitsenvironmentusingarange-optimisedsonarsensor.Thesensor Thereallocationofthetargetis(0;1).Thedicultywiththistransformationarisesfromthephysicalproperties xy=rcos ofthesonar.fairlygoodrangeaccuracy(with2cmstandarddeviation)istradedotogiveaverypoorbearing rsinwithrf=cos?rsin sinrcos: tobeviolated. measurement(standarddeviationof15).thelargebearinguncertaintycausestheassumptionoflocallinearity

5 comparedwiththosecalculatedbythetruestatistics linearisation,itsvaluesofthestatisticsof(x;y)were Toappreciatetheerrorswhichcanbecausedby isticswereobtained.theresultsareshowninfigure1. usedtoensurethataccurateestimatesofthetruestat- totheslowconvergenceofrandomsamplingmethods, anextremelylargenumberofsamples(3:5106)were whicharecalculatedbymontecarlosimulation.due 1.04 Thisgureshowsthemeanand1contoursforwhich arecalculatedbyeachmethod.the1contouristhe locusofpointsfy:(y?y)p? graphicalrepresentationofthesizeandorientationof y(y?y)=1gandisa isextremelysubstantial.linearisationerrorseectivelyintroduceanerrorwhichisover1.5timesthelatesthemeanatandtheuncertaintyellipseis 0.9 thepositionis1mwhereasinrealityitis96.7cm.this therangedirection,wherelinearisationestimatesthat Pyy.Ascanbeseen,thelinearisedtransformationis biasedandinconsistent.thisismostpronouncedinfigure1:themeanandstandarddeviationel- lipsesfortheactualandlinearisedformofthe 0.94 uncertaintyellipseissolid.linearisationcalcu- transformation.thetruemeanisatandthe 0.92 mittedeachtimeacoordinatetransformationtakes dashed place.eveniftherewerenobias,thetransformation itself,thesameerrorwiththesamesignwillbecom- isabiaswhicharisesfromthetransformationprocess standarddeviationoftherangemeasurement.sinceit True mean: x EKF mean: o isinconsistent.itsellipseisnotlongenoughintherdirection.infact,thenatureoftheinconsistencycompounds ismuchsmallerthanthetruevalue. theproblemofthebiased-ness:notonlyistheestimateorrinerror,butalsoitsestimatedmeansquarederror sizeofthetransformedcovariance.thisisonepossibleofwhyekfsaresodiculttotune sucientnoise mustbeintroducedtoosetthedefectsoflinearisation.however,introducingstabilisingnoiseisanundesirable solutionsincetheestimateremainsbiasedandthereisnogeneralguaranteethatthetransformedestimateremains consistentorecient.amoreaccuratepredictionalgorithmisrequired. Inpracticetheinconsistencycanberesolvedbyintroducingadditionalstabilisingnoisewhichincreasesthe 3.1TheBasicIdea 3 THEUNSCENTEDTRANSFORM foundedontheintuitionthatitiseasiertoapproximateagaussiandistributionthanitistoapproximatablewhichundergoesanonlineartransformation.itis Theunscentedtransformationisanew,novel methodforcalculatingthestatisticsofarandomvari- anarbitrarynonlinearfunctionortransformation23. (orsigmapoints)arechosensothattheirsamplemean TheapproachisillustratedinFigure2.Asetofpoints functionisappliedtoeachpointinturntoyieldacloud andsamplecovariancearexandpxx.thenonlinear oftransformedpointsandyandpyyarethestatisticsofthetransformedpoints.althoughthismethod baresasupercialresemblancetomontecarlo-typeform. Figure2:Theprincipleoftheunscentedtrans- Nonlinear Transformation

6 methods,thereisanextremelyimportantandfundamentaldierence.thesamplesarenotdrawnatrandom butratheraccordingtoaspecic,deterministicalgorithm.sincetheproblemsofstatisticalconvergencearenot anissue,highorderinformationaboutthedistributioncanbecapturedusingonlyaverysmallnumberofpoints. pointsgivenby Then-dimensionalrandomvariablexwithmeanxandcovariancePxxisapproximatedby2n+1weighted Xi+n=x?p(n+)PxxiWi+n=1=2(n+) X0 =x+p(n+)pxxiwi W0 =1=2(n+) ==(n+) where2<,p(n+)pxxiistheithroworcolumnofthematrixsquarerootof(n+)pxxandwiisthe (12) weightwhichisassociatedwiththeithpoint.thetransformationprocedureisasfollows: 1.Instantiateeachpointthroughthefunctiontoyieldthesetoftransformedsigmapoints, 2.Themeanisgivenbytheweightedaverageofthetransformedpoints, Yi=f[Xi]: 3.Thecovarianceistheweightedouterproductofthetransformedpoints, y=2nxi=0wiyi: (13) Thepropertiesofthisalgorithmhavebeenstudiedindetailelsewhere9;12andwepresentasummaryofthe Pyy=2nXi=0WifYi?ygfYi?ygT: (14) resultshere: 1.Sincethemeanandcovarianceofxarecapturedpreciselyuptothesecondorder,thecalculatedvalues ofthemeanandcovarianceofyarecorrecttothesecondorderaswell.thismeansthatthemeanis orderofaccuracy.however,therearefurtherperformancebenets.sincethedistributionofxisbeing calculatedtoahigherorderofaccuracythantheekf,whereasthecovarianceiscalculatedtothesame 2.Thesigmapointscapturethesamemeanandcovarianceirrespectiveofthechoiceofmatrixsquareroot approximatedratherthanf[],itsseriesexpansionisnottruncatedataparticularorder.itcanbeshown thattheunscentedalgorithmisabletopartiallyincorporateinformationfromthehigherorders,leadingto evengreateraccuracy. 3.Themeanandcovariancearecalculatedusingstandardvectorandmatrixoperations.Thismeansthatthe whichisused.numericallyecientandstablemethodssuchasthecholeskydecomposition18canbeused. 4.providesanextradegreeoffreedomto\netune"thehigherordermomentsoftheapproximation,and notnecessarytoevaluatethejacobianswhichareneededinanekf. algorithmissuitableforanychoiceofprocessmodel,andimplementationisextremelyrapidbecauseitis canbeusedtoreducetheoverallpredictionerrors.whenx(k)isassumedgaussian,ausefulheuristicisto selectn+=3.ifadierentdistributionisassumedforx(k)thenadierentchoiceofmightbemore appropriate.

7 5.Althoughcanbepositiveornegative,anegativechoiceofcanleadtoanon-positivesemideniteestimate densitydistributions8;16;21.inthissituation,itispossibletouseamodiedformofthepredictionalgorithm. Themeanisstillcalculatedasbefore,butthe\covariance"isevaluatedaboutX0(k+1jk):Itcanbe ofpyy.thisproblemisnotuncommonformethodswhichapproximatehigherordermomentsorprobability shownthatthemodiedformensurespositivesemi-denitenessand,inthelimitas(n+)!0, Inotherwords,thealgorithmcanbemadetoperformexactlylikethesecondOrderGaussFilter,but withouttheneedtocalculatejacobiansorhessians. (n+)!0y=f[x]+12r2fpxx;lim (n+)!0pyy=rfpxx(rf)t: meansand1contoursdeterminedbythedierent transformcanbeseeninfigure3whichshowsthe methods.thetruemeanliesatwithadottedcovariancecontour.thepositionoftheunscentedmean Theperformancebenetsofusingtheunscented value onthescaleofthegraph,thetwopointslieon topofoneanother.further,theunscentedtransform isindicatedbya?anditscontourissolid.thelinearisedmeanisatandusedadashedcontour.ascanbe seentheunscentedmeanvalueisthesameasthetrue thanthetruecontourintherdirection. isconsistent infact,itscontourisslightlylarger isbettersuitedthanlinearisationforlteringapplica- andeaseofimplementation,theunscentedtransform tions.indeed,sinceitcanpredictthemeanandcovari- ancewithsecondorderaccuracy,anylterwhichuses Givenitspropertiesofsuperiorestimationaccuracy Figure3:Theunscentedtransformasappliedto theunscentedtransformtothelteringproblemanddevelopstheunscentedlter. ans.thenextsubsectionexaminestheapplicationof doesnotrequirethederivationofjacobiansorhessi- theunscentedtransformwillhavethesameperformanceasthetruncatedsecondordergaussfilter1butthemeasurementexample. 3.2TheUnscentedFilter ThetransformationprocesseswhichoccurinaKalmanlterconsistofthefollowingsteps: Predictthenewstateofthesystem^x(k+1jk)anditsassociatedcovarianceP(k+1jk).Thisprediction Predicttheexpectedobservation^z(k+1jk)andtheinnovationcovarianceP(k+1jk).Thisprediction musttakeaccountoftheeectsofprocessnoise. Finally,predictthecross-correlationmatrixPxz(k+1jk): shouldincludetheeectsofobservationnoise. models.first,thestatevectorisaugmentedwiththeprocessandnoisetermstogiveanna=n+qdimensional Thesestepscanbeeasilyaccommodatedbyslightlyrestructuringthestatevectorandprocessandobservation True mean: x EKF mean: o Kappa mean: +

8 1.ThesetofsigmapointsarecreatedbyapplyingEquation12totheaugmentedsystemgivenbyEquation15. 2.Thetransformedsetisgivenbyinstantiatingeachpointthroughtheprocessmodel, 3.Thepredictedmeaniscomputedas Xi(k+1jk)=f[Xai(kjk);u(k);k]: 4.Andthepredictedcovarianceiscomputedas ^x(k+1jk)=2na Xi=0WiXai(k+1jk): 5.Instantiateeachofthepredictionpointsthroughtheobservationmodel, P(k+1jk)2na Xi=0WifXi(k+1jk)?^x(k+1jk)gfXi(k+1jk)?^x(k+1jk)gT 6.Thepredictedobservationiscalculatedby Zi(k+1jk)=h[Xi(k+1jk);u(k);k] 7.Sincetheobservationnoiseisadditiveandindependent,theinnovationcovarianceis ^z(k+1jk)=2na Xi=1WiZi(k+1jk): 8.Finallythecrosscorrelationmatrixisdeterminedby P(k+1jk)=R(k+1)+2na Xi=0WifZi(kjk?1)?^z(k+1jk)gfZi(kjk?1)?^z(k+1jk)gT Pxz(k+1jk)=2na Xi=0WifXi(kjk?1)?^x(k+1jk)gfZi(kjk?1)?^z(k+1jk)gT vector, Box3.1:Thepredictionalgorithmusingtheunscentedtransform. Theprocessmodelisrewrittenasafunctionofxa(k), xa(k)=x(k) x(k+1)=f[xa(k);u(k);k] v(k): andtheunscentedtransformuses2na+1sigmapointswhicharedrawnfrom Thematricesontheleadingdiagonalarethecovariancesando-diagonalsub-blocksarethecorrelations ^xa(kjk)=^x(kjk) 0q1andPa(kjk)=P(kjk)Pxv(kjk) Pxv(kjk) Q(k): (15) betweenthestateerrorsandtheprocessnoises.althoughthismethodrequirestheuseofadditionalsigma points,itmeansthattheeectsoftheprocessnoise(intermsofitsimpactonthemeanandcovariance)are introducedwiththesameorderofaccuracyastheuncertaintyinthestate.theformulationalsomeansthat

9 expressionfortheunscentedtransformisgivenbytheequationsinbox3.1. correlatednoisesources(whichcanariseinschmidt-kalmanlters19)canbeimplementedextremelyeasily.the withprocessand/orobservationnoise,thentheaugmentedvectorisexpandedtoincludetheobservationterms. agivenapplication.forexample,iftheobservationnoiseisintroducedinanonlinearfashion,oriscorrelated Thissectionhasdevelopedtheunscentedtransformsothatitcanbeusedinlteringandtrackingapplications. Variousextensionsandmodicationscanbemadetothisbasicmethodtotakeaccountofspecicdetailsof ThenextsectiondemonstratesitsbenetsovertheEKFforasampleapplication. 4 EXAMPLEAPPLICATION ofthebodyistobetrackedbyaradarwhichaccurately athighaltitudeandataveryhighspeed.theposition lustratedinfigure4:avehicleenterstheatmosphere measuresrangeandbearing.thistypeofproblemhas Inthissectionweconsidertheproblemwhichisil- whichact.themostdominantisaerodynamicdrag, particularlystressfulforltersandtrackersbecauseof beenidentiedbyanumberofauthors1;2;5;17asbeing actonthevehicle.therearethreetypesofforces thestrongnonlinearitiesexhibitedbytheforceswhich tialnonlinearvariationinaltitude.thesecondtypeof whichisafunctionofvehiclespeedandhasasubstan- forceisgravitywhichacceleratesthevehicletowards atmosphereincreases,drageectsbecomeimportant thecentreoftheearth.thenalforcesarerandom buetingterms.theeectoftheseforcesgivesatrajectoryoftheformshowninfigure4:initiallythe almostvertical.thetrackingproblemismademore dicultbythefactthatthedragpropertiesofthe andthevehiclerapidlydeceleratesuntilitsmotionis trajectoryisalmostballisticbutasthedensityofthe vehiclemightbeonlyverycrudelyknown. isthesamplevehicletrajectoryandthesolidline Figure4:Thereentryproblem.Thedashedline trackanobjectwhichexperiencesasetofcomplicated,highlynonlinearforces.thesedependonthecurrent Insummary,thetrackingsystemshouldbeabletooftheradarismarkedbya. isaportionoftheearth'ssurface.theposition positionandvelocityofthevehicleaswellasoncertaincharacteristicswhicharenotknownprecisely.thelter's aerodynamicproperties(x5).thevehiclestatedynamicsare statespaceconsistsofthepositionofthebody(x1andx2),itsvelocity(x3andx4)andaparameterofits _x1(k)=x3(k) _x2(k)=x4(k) _x3(k)=d(k)x3(k)+g(k)x1(k)+v1(k) _x4(k)=d(k)x4(k)+g(k)x2(k)+v2(k) _x5(k)=v3(k) (16) whered(k)isthedrag-relatedforceterm,g(k)isthegravity-relatedforcetermandv(k)aretheprocessnoise terms.deningr(k)=px21(k)+x2(k)asthedistancefromthecentreoftheearthandv(k)=px23(k)+x24(k) x 2 (km) x 1 (km)

10 asabsolutevehiclespeedthenthedragandgravitationaltermsare D(k)=?(k)exp[R0?R(k)] V(k);G(k)=?Gm0 Forthisexampletheparametervaluesare0=?0:59783,H0=13:406,Gm0=3: andR0=6374and and(k)=0expx5(k): r3(k) reecttypicalenvironmentalandvehiclecharacteristics2.theparameterisationoftheballisticcoecient,(k), reectstheuncertaintyinvehiclecharacteristics5.0istheballisticcoecientofa\typicalvehicle"anditis scaledbyexpx5(k)toensurethatitsvalueisalwayspositive.thisisvitalforlterstability. andbearingatafrequencyof10hz,where Themotionofthevehicleismeasuredbyaradarwhichislocatedat(xr;yr).Itisabletomeasureranger rr(k)=p(x1(k)?xr)2+(x2(k)?yr)2+w1(k) w1(k)andw2(k)arezeromeanuncorrelatednoiseprocesseswithvariancesof1mand17mradrespectively4.the highupdaterateandextremeaccuracyofthesensormeansthatalargequantityofextremelyhighqualitydatais (k)=tan?1x2(k)?yr x1(k)?xr+w2(k) availableforthelter.thebearinguncertaintyissucientlythattheekfisabletopredictthesensorreadings accuratelywithverylittlebias. Thetrueinitialconditionsforthevehicleare x(0)= 0 B@?1:8093?6: :4 349:14 0: CAandP(0)= ?610?6 10?6 Inotherwords,thevehicle'scoecientistwicethenominalcoecient ? : Thevehicleisbuetedbyrandomaccelerations, Q(k)=242:406410?5 0 2:406410?50 0 Theinitialconditionsassumedbythelterare, 3 5 ^x(0j0)= 0 B@?1:8093?6: :4 349:141CAandP(0j0)= ?610?6 10?6 Thelterusesthenominalinitialconditionand,toosetfortheuncertainty,thevarianceonthisinitialestimate ? : is1ḃothlterswereimplementedindiscretetimeandobservationsweretakenatafrequencyof10hz.however, duetotheintensenonlinearitiesofthevehicledynamicsequations,theeulerapproximationofequation16was onlyvalidforsmalltimesteps.theintegrationstepwassettobe50mswhichmeantthattwopredictionswere

11 10 0 Mean squared error and variance of x Mean squared error and variance of x Mean squared error and variance of x Position variance km (a)resultsforx1. (b)resultsforx Figure5:ThemeansquarederrorsandestimatedcovariancescalculatedbyanEKFandan unscentedlter.inallthegraphs,thesolidlineisthemeansquarederrorcalculatedbytheekf, (c)resultsforx Time s Time s errorandthedot-dashedlineitsestimatedcovariance. andthedottedlineisitsestimatedcovariance.thedashedlineistheunscentedmeansquared Time s madeperupdate.fortheunscentedlter,eachsigmapointwasappliedthroughthedynamicsequationstwice. error(thediagonalelementsofp(kjk))againstactualmeansquaredestimationerror(whichisevaluatedusing FortheEKF,itwasnecessarytoperformaninitialpredictionstepandre-linearisebeforethesecondstep. 100MonteCarlosimulations).Onlyx1,x3andx5areshown theresultsforx2aresimilartox1,andx4isthe sameasthatforx3.inallcasesitcanbeseenthattheunscentedlterestimatesitsmeansquarederrorvery accurately,anditispossibletobecondentwiththelterestimates.theekf,however,ishighlyinconsistent: TheperformanceofeachlterisshowninFigure5.Thisgureplotstheestimatedmeansquaredestimation thepeakmeansquarederrorinx1is0:4km2,whereasitsestimatedcovarianceisoveronehundredtimessmaller. error.finally,itcanbeseenthatx5ishighlybiased,andthisbiasonlyslowlydecreasesovertime.thispoor performanceisthedirectresultoflinearisationerrors. Similarly,thepeakmeansquaredvelocityerroris3:410?4km2s?2whichisover5timesthetruemeansquared theneedtoconsistentlypredictthenewstateandobservationofthesystem.wehaveintroducedanewltering InthispaperwehavearguedthattheprincipledicultyforapplyingtheKalmanltertononlinearsystemsis 5 CONCLUSIONS advantagesovertheekf.first,itisabletopredictthestateofthesystemmoreaccurately.second,itismuch algorithm,calledtheunscentedlter.byvirtueoftheunscentedtransformation,thisalgorithmhastwogreat lessdiculttoimplement.thebenetsofthealgorithmweredemonstratedinarealisticexample. Inacompanionpaper11,weextendthedevelopmentoftheunscentedtransformandyieldageneralframeworkfor itsderivationandapplication.itisshownthatthenumberofsigmapointscanbeextendedtoyieldalterwhich matchesmomentsuptothefourthorder.thishigherorderextensioneectivelyde-biasesalmostallcommon nonlinearcoordinatetransformations. Thispaperhasconsideredonespecicformoftheunscentedtransformforoneparticularsetofassumptions. Velocity variance (km/s) 2 Coefficient variance

12 [1]M.Athans,R.P.WishnerandA.Bertolini.Suboptimalstateestimationforcontinuous-timenonlinearsystemsfrom discretenoisymeasurements.ieeetransactionsonautomaticcontrol,tac-13(6):504{518,october1968. REFERENCES [2]J.W.AustinandC.T.Leondes.StatisticallyLinearizedEstimationofReentryTrajectories.IEEETransactionson [3]D.E.Catlin.Estimation,controlandthediscretekalmanlter.InAppliedMathematicalSciences71,page84. [4]C.B.Chang,R.H.WhitingandM.Athans.OntheStateandParameterEstimationforManeuveringReentry AerospaceandElectronicSystems,AES-17(1):54{61,January1981. [5]P.J.Costa.AdaptiveModelArchitectureandExtendedKalman-BucyFilters.IEEETransactionsonAerospaceand Springer-Verlag,1989. [6]F.E.Daum.Newexactnonlinearlters.InJ.C.Spall,editor,BayesianAnalysisofTimeSeriesandDynamic Vehicles.IEEETransactionsonAutomaticControl,AC-22:99{105,February1977. [7]N.J.Gordon,D.J.SalmondandA.F.M.Smith.NovelApproachtoNonlinear/non-GaussianBayesianState ElectronicSystems,AES-30(2):525{533,April1994. [8]A.H.Jazwinski.StochasticProcessesandFilteringTheory.AcademicPress,1970. Models,chapter8,pages199{226.MarcelDrekker,Inc.,1988. [9]S.J.JulierandJ.K.Uhlmann.AGeneralMethodforApproximatingNonlinearTransformationsofProbability Estimation.IEEProceedings-F,140(2):107{113,April1993. [10]S.J.JulierandJ.K.Uhlmann.AConsistent,DebiasedMethodforConvertingBetweenPolarandCartesian Distributions.WWWhttp:// CoordinateSystems.InTheProceedingsofAeroSense:The11thInternationalSymposiumonAerospace/Defense [12]S.J.Julier,J.K.UhlmannandH.F.Durrant-Whyte.ANewApproachfortheNonlinearTransformationofMeans [11]S.J.Julier,J.K.UhlmannandH.F.Durrant-Whyte.ANewApproachforFilteringNonlinearSystems.InThe ProceedingsoftheAmericanControlConference,Seattle,Washington.,pages1628{1632,1995. Sensing,SimulationandControls,Orlando,Florida.SPIE,1997.Acquisition,TrackingandPointingXI. [13]H.J.Kushner.Approximationstooptimalnonlinearlters.IEEETransactionsonAutomaticControl,AC-12(5):546{ andcovariancesinlinearfilters.ieeetransactionsonautomaticcontrol,1996. [15]D.LerroandY.K.Bar-Shalom.TrackingwithDebiasedConsistentConvertedMeasurementsvs.EKF.IEEE [14]H.J.Kushner.Dynamicalequationsforoptimumnon-linearltering.JournalofDierentialEquations,3:179{190, 556,October1967. [16]P.S.Maybeck.StochasticModels,Estimation,andControl,volume2.AcademicPress,1982. [17]R.K.Mehra.AComparisonofSeveralNonlinearFiltersforReentryVehicleTracking.IEEETransactionson TransactionsonAerospaceandElectronicsSystems,AES-29(3):1015{1022,July1993. [18]W.H.Press,S.A.Teukolsky,W.T.VetterlingandB.P.Flannery.NumericalRecipesinC:TheArtofScientic [19]S.F.Schmidt.Applicationsofstatespacemethodstonavigationproblems.InC.T.Leondes,editor,Advanced AutomaticControl,AC-16(4):307{319,August1971. [20]H.W.Sorenson,editor.Kalmanltering:theoryandapplication.IEEE,1985. ControlSystems,volume3,pages293{340.AcademicPress,1966. Computing.CambridgeUniversityPress,2edition,1992. [21]H.W.SorensonandA.R.Stubberud.Non-linearlteringbyapproximationoftheaposterioridensity.International [22]J.K.Uhlmann.Algorithmsformultipletargettracking.AmericanScientist,80(2):128{141,1992. [23]J.K.Uhlmann.Simultaneousmapbuildingandlocalizationforrealtimeapplications.Technicalreport,University JournalofControl,8(1):33{51,1968. ofoxford,1994.transferthesis.

Whole-body dynamic motion planning with centroidal dynamics and full kinematics

Whole-body dynamic motion planning with centroidal dynamics and full kinematics Sep. 18. 2014 Introduction Linear Inverted Pendulum compute ZMP with point-mass model linear system, analytical solution co-planar contact solve kinematics separately Our approach dynamic constraint for

More information

Understanding and Applying Kalman Filtering

Understanding and Applying Kalman Filtering Understanding and Applying Kalman Filtering Lindsay Kleeman Department of Electrical and Computer Systems Engineering Monash University, Clayton 1 Introduction Objectives: 1. Provide a basic understanding

More information

Introduction: Overview of Kernel Methods

Introduction: Overview of Kernel Methods Introduction: Overview of Kernel Methods Statistical Data Analysis with Positive Definite Kernels Kenji Fukumizu Institute of Statistical Mathematics, ROIS Department of Statistical Science, Graduate University

More information

Data Sensor Fusion for Autonomous Robotics

Data Sensor Fusion for Autonomous Robotics 19 Data Sensor Fusion for Autonomous Robotics Özer Çiftçioğlu and Sevil Sariyildiz Delft University of echnology, Faculty of Architecture, Delft he Netherlands 1. Introduction Multi-sensory information

More information

Least Squares Estimation

Least Squares Estimation Least Squares Estimation SARA A VAN DE GEER Volume 2, pp 1041 1045 in Encyclopedia of Statistics in Behavioral Science ISBN-13: 978-0-470-86080-9 ISBN-10: 0-470-86080-4 Editors Brian S Everitt & David

More information

CORRELATION ANALYSIS

CORRELATION ANALYSIS CORRELATION ANALYSIS Learning Objectives Understand how correlation can be used to demonstrate a relationship between two factors. Know how to perform a correlation analysis and calculate the coefficient

More information

POLYNOMIAL AND MULTIPLE REGRESSION. Polynomial regression used to fit nonlinear (e.g. curvilinear) data into a least squares linear regression model.

POLYNOMIAL AND MULTIPLE REGRESSION. Polynomial regression used to fit nonlinear (e.g. curvilinear) data into a least squares linear regression model. Polynomial Regression POLYNOMIAL AND MULTIPLE REGRESSION Polynomial regression used to fit nonlinear (e.g. curvilinear) data into a least squares linear regression model. It is a form of linear regression

More information

Adaptive Demand-Forecasting Approach based on Principal Components Time-series an application of data-mining technique to detection of market movement

Adaptive Demand-Forecasting Approach based on Principal Components Time-series an application of data-mining technique to detection of market movement Adaptive Demand-Forecasting Approach based on Principal Components Time-series an application of data-mining technique to detection of market movement Toshio Sugihara Abstract In this study, an adaptive

More information

How To Build A Hybrid Fusion Module

How To Build A Hybrid Fusion Module LIVIC CVIS-POMA presentation Hybrid Fusion module with IMM approach for Cooperative Vehicle Infrastructure Systems (CVIS) Sébastien Glaser Dominique Gruyer, Alexandre Ndjeng Ndjeng [email protected]

More information

United Arab Emirates University College of Sciences Department of Mathematical Sciences HOMEWORK 1 SOLUTION. Section 10.1 Vectors in the Plane

United Arab Emirates University College of Sciences Department of Mathematical Sciences HOMEWORK 1 SOLUTION. Section 10.1 Vectors in the Plane United Arab Emirates University College of Sciences Deartment of Mathematical Sciences HOMEWORK 1 SOLUTION Section 10.1 Vectors in the Plane Calculus II for Engineering MATH 110 SECTION 0 CRN 510 :00 :00

More information

Vectors. Objectives. Assessment. Assessment. Equations. Physics terms 5/15/14. State the definition and give examples of vector and scalar variables.

Vectors. Objectives. Assessment. Assessment. Equations. Physics terms 5/15/14. State the definition and give examples of vector and scalar variables. Vectors Objectives State the definition and give examples of vector and scalar variables. Analyze and describe position and movement in two dimensions using graphs and Cartesian coordinates. Organize and

More information

Data Mining Part 5. Prediction

Data Mining Part 5. Prediction Data Mining Part 5. Prediction 5.7 Spring 2010 Instructor: Dr. Masoud Yaghini Outline Introduction Linear Regression Other Regression Models References Introduction Introduction Numerical prediction is

More information

MAT 242 Test 3 SOLUTIONS, FORM A

MAT 242 Test 3 SOLUTIONS, FORM A MAT Test SOLUTIONS, FORM A. Let v =, v =, and v =. Note that B = { v, v, v } is an orthogonal set. Also, let W be the subspace spanned by { v, v, v }. A = 8 a. [5 points] Find the orthogonal projection

More information

Automated Stellar Classification for Large Surveys with EKF and RBF Neural Networks

Automated Stellar Classification for Large Surveys with EKF and RBF Neural Networks Chin. J. Astron. Astrophys. Vol. 5 (2005), No. 2, 203 210 (http:/www.chjaa.org) Chinese Journal of Astronomy and Astrophysics Automated Stellar Classification for Large Surveys with EKF and RBF Neural

More information

Data Mining and Data Warehousing. Henryk Maciejewski. Data Mining Predictive modelling: regression

Data Mining and Data Warehousing. Henryk Maciejewski. Data Mining Predictive modelling: regression Data Mining and Data Warehousing Henryk Maciejewski Data Mining Predictive modelling: regression Algorithms for Predictive Modelling Contents Regression Classification Auxiliary topics: Estimation of prediction

More information

COMPUTATION OF THREE-DIMENSIONAL ELECTRIC FIELD PROBLEMS BY A BOUNDARY INTEGRAL METHOD AND ITS APPLICATION TO INSULATION DESIGN

COMPUTATION OF THREE-DIMENSIONAL ELECTRIC FIELD PROBLEMS BY A BOUNDARY INTEGRAL METHOD AND ITS APPLICATION TO INSULATION DESIGN PERIODICA POLYTECHNICA SER. EL. ENG. VOL. 38, NO. ~, PP. 381-393 (199~) COMPUTATION OF THREE-DIMENSIONAL ELECTRIC FIELD PROBLEMS BY A BOUNDARY INTEGRAL METHOD AND ITS APPLICATION TO INSULATION DESIGN H.

More information

A repeated measures concordance correlation coefficient

A repeated measures concordance correlation coefficient A repeated measures concordance correlation coefficient Presented by Yan Ma July 20,2007 1 The CCC measures agreement between two methods or time points by measuring the variation of their linear relationship

More information

LIST OF TABLES. 4.3 The frequency distribution of employee s opinion about training functions emphasizes the development of managerial competencies

LIST OF TABLES. 4.3 The frequency distribution of employee s opinion about training functions emphasizes the development of managerial competencies LIST OF TABLES Table No. Title Page No. 3.1. Scoring pattern of organizational climate scale 60 3.2. Dimension wise distribution of items of HR practices scale 61 3.3. Reliability analysis of HR practices

More information

TIME SERIES ANALYSIS & FORECASTING

TIME SERIES ANALYSIS & FORECASTING CHAPTER 19 TIME SERIES ANALYSIS & FORECASTING Basic Concepts 1. Time Series Analysis BASIC CONCEPTS AND FORMULA The term Time Series means a set of observations concurring any activity against different

More information

Example: Credit card default, we may be more interested in predicting the probabilty of a default than classifying individuals as default or not.

Example: Credit card default, we may be more interested in predicting the probabilty of a default than classifying individuals as default or not. Statistical Learning: Chapter 4 Classification 4.1 Introduction Supervised learning with a categorical (Qualitative) response Notation: - Feature vector X, - qualitative response Y, taking values in C

More information

Regression III: Advanced Methods

Regression III: Advanced Methods Lecture 4: Transformations Regression III: Advanced Methods William G. Jacoby Michigan State University Goals of the lecture The Ladder of Roots and Powers Changing the shape of distributions Transforming

More information

Dimensionality Reduction: Principal Components Analysis

Dimensionality Reduction: Principal Components Analysis Dimensionality Reduction: Principal Components Analysis In data mining one often encounters situations where there are a large number of variables in the database. In such situations it is very likely

More information

8. Linear least-squares

8. Linear least-squares 8. Linear least-squares EE13 (Fall 211-12) definition examples and applications solution of a least-squares problem, normal equations 8-1 Definition overdetermined linear equations if b range(a), cannot

More information

Phys222 Winter 2012 Quiz 4 Chapters 29-31. Name

Phys222 Winter 2012 Quiz 4 Chapters 29-31. Name Name If you think that no correct answer is provided, give your answer, state your reasoning briefly; append additional sheet of paper if necessary. 1. A particle (q = 5.0 nc, m = 3.0 µg) moves in a region

More information

A multi-scale approach to InSAR time series analysis

A multi-scale approach to InSAR time series analysis A multi-scale approach to InSAR time series analysis M. Simons, E. Hetland, P. Muse, Y. N. Lin & C. DiCaprio U Interferogram stack time A geophysical perspective on deformation tomography Examples: Long

More information

System Identification for Acoustic Comms.:

System Identification for Acoustic Comms.: System Identification for Acoustic Comms.: New Insights and Approaches for Tracking Sparse and Rapidly Fluctuating Channels Weichang Li and James Preisig Woods Hole Oceanographic Institution The demodulation

More information

{(i,j) 1 < i,j < n} pairs, X and X i, such that X and X i differ. exclusive-or sums. ( ) ( i ) V = f x f x

{(i,j) 1 < i,j < n} pairs, X and X i, such that X and X i differ. exclusive-or sums. ( ) ( i ) V = f x f x ON THE DESIGN OF S-BOXES A. F. Webster and S. E. Tavares Department of Electrical Engineering Queen's University Kingston, Ont. Canada The ideas of completeness and the avalanche effect were first introduced

More information

An Online Estimation of Rotational Velocity of Flying Ball via Aerodynamics

An Online Estimation of Rotational Velocity of Flying Ball via Aerodynamics Preprints of the 19th World Congress The International Federation of Automatic Control An Online Estimation of Rotational Velocity of Flying via Aerodynamics Akira Nakashima Takeshi Okamoto Yoshikazu Hayakawa

More information

Numerical Analysis. Gordon K. Smyth in. Encyclopedia of Biostatistics (ISBN 0471 975761) Edited by. Peter Armitage and Theodore Colton

Numerical Analysis. Gordon K. Smyth in. Encyclopedia of Biostatistics (ISBN 0471 975761) Edited by. Peter Armitage and Theodore Colton Numerical Analysis Gordon K. Smyth in Encyclopedia of Biostatistics (ISBN 0471 975761) Edited by Peter Armitage and Theodore Colton John Wiley & Sons, Ltd, Chichester, 1998 Numerical Analysis Numerical

More information

4.3 Least Squares Approximations

4.3 Least Squares Approximations 18 Chapter. Orthogonality.3 Least Squares Approximations It often happens that Ax D b has no solution. The usual reason is: too many equations. The matrix has more rows than columns. There are more equations

More information

Manifold Learning Examples PCA, LLE and ISOMAP

Manifold Learning Examples PCA, LLE and ISOMAP Manifold Learning Examples PCA, LLE and ISOMAP Dan Ventura October 14, 28 Abstract We try to give a helpful concrete example that demonstrates how to use PCA, LLE and Isomap, attempts to provide some intuition

More information

Solving DEs by Separation of Variables.

Solving DEs by Separation of Variables. Solving DEs by Separation of Variables. Introduction and procedure Separation of variables allows us to solve differential equations of the form The steps to solving such DEs are as follows: dx = gx).

More information

Chapter 13 Introduction to Nonlinear Regression( 非 線 性 迴 歸 )

Chapter 13 Introduction to Nonlinear Regression( 非 線 性 迴 歸 ) Chapter 13 Introduction to Nonlinear Regression( 非 線 性 迴 歸 ) and Neural Networks( 類 神 經 網 路 ) 許 湘 伶 Applied Linear Regression Models (Kutner, Nachtsheim, Neter, Li) hsuhl (NUK) LR Chap 10 1 / 35 13 Examples

More information

Logistic Regression. Jia Li. Department of Statistics The Pennsylvania State University. Logistic Regression

Logistic Regression. Jia Li. Department of Statistics The Pennsylvania State University. Logistic Regression Logistic Regression Department of Statistics The Pennsylvania State University Email: [email protected] Logistic Regression Preserve linear classification boundaries. By the Bayes rule: Ĝ(x) = arg max

More information

SOLUTIONS. Would you like to know the solutions of some of the exercises?? Here you are

SOLUTIONS. Would you like to know the solutions of some of the exercises?? Here you are SOLUTIONS Would you like to know the solutions of some of the exercises?? Here you are Your first function : remember Introduction: Text: A function is a relationship between two sets by which we assign

More information

Week 5: Multiple Linear Regression

Week 5: Multiple Linear Regression BUS41100 Applied Regression Analysis Week 5: Multiple Linear Regression Parameter estimation and inference, forecasting, diagnostics, dummy variables Robert B. Gramacy The University of Chicago Booth School

More information

Sections 2.11 and 5.8

Sections 2.11 and 5.8 Sections 211 and 58 Timothy Hanson Department of Statistics, University of South Carolina Stat 704: Data Analysis I 1/25 Gesell data Let X be the age in in months a child speaks his/her first word and

More information

Linearly Independent Sets and Linearly Dependent Sets

Linearly Independent Sets and Linearly Dependent Sets These notes closely follow the presentation of the material given in David C. Lay s textbook Linear Algebra and its Applications (3rd edition). These notes are intended primarily for in-class presentation

More information

Physics Kinematics Model

Physics Kinematics Model Physics Kinematics Model I. Overview Active Physics introduces the concept of average velocity and average acceleration. This unit supplements Active Physics by addressing the concept of instantaneous

More information

Mean = (sum of the values / the number of the value) if probabilities are equal

Mean = (sum of the values / the number of the value) if probabilities are equal Population Mean Mean = (sum of the values / the number of the value) if probabilities are equal Compute the population mean Population/Sample mean: 1. Collect the data 2. sum all the values in the population/sample.

More information

3.2 Sources, Sinks, Saddles, and Spirals

3.2 Sources, Sinks, Saddles, and Spirals 3.2. Sources, Sinks, Saddles, and Spirals 6 3.2 Sources, Sinks, Saddles, and Spirals The pictures in this section show solutions to Ay 00 C By 0 C Cy D 0. These are linear equations with constant coefficients

More information

Big Data: The curse of dimensionality and variable selection in identification for a high dimensional nonlinear non-parametric system

Big Data: The curse of dimensionality and variable selection in identification for a high dimensional nonlinear non-parametric system Big Data: The curse of dimensionality and variable selection in identification for a high dimensional nonlinear non-parametric system Er-wei Bai University of Iowa, Iowa, USA Queen s University, Belfast,

More information

Computer exercise 2: Least Mean Square (LMS)

Computer exercise 2: Least Mean Square (LMS) 1 Computer exercise 2: Least Mean Square (LMS) This computer exercise deals with the LMS algorithm, which is derived from the method of steepest descent by replacing R = E{u(n)u H (n)} and p = E{u(n)d

More information

Learning Outcomes. Distinguish between Distance and Displacement when comparing positions. Distinguish between Scalar and Vector Quantities

Learning Outcomes. Distinguish between Distance and Displacement when comparing positions. Distinguish between Scalar and Vector Quantities Dr Pusey Learning Outcomes Distinguish between Distance and Displacement when comparing positions Distinguish between Scalar and Vector Quantities Add and subtract vectors in one and two dimensions What

More information

Automatic Detection of Emergency Vehicles for Hearing Impaired Drivers

Automatic Detection of Emergency Vehicles for Hearing Impaired Drivers Automatic Detection of Emergency Vehicles for Hearing Impaired Drivers Sung-won ark and Jose Trevino Texas A&M University-Kingsville, EE/CS Department, MSC 92, Kingsville, TX 78363 TEL (36) 593-2638, FAX

More information

Smoothing. Fitting without a parametrization

Smoothing. Fitting without a parametrization Smoothing or Fitting without a parametrization Volker Blobel University of Hamburg March 2005 1. Why smoothing 2. Running median smoother 3. Orthogonal polynomials 4. Transformations 5. Spline functions

More information

Manufacturing Equipment Modeling

Manufacturing Equipment Modeling QUESTION 1 For a linear axis actuated by an electric motor complete the following: a. Derive a differential equation for the linear axis velocity assuming viscous friction acts on the DC motor shaft, leadscrew,

More information

Concepts in Investments Risks and Returns (Relevant to PBE Paper II Management Accounting and Finance)

Concepts in Investments Risks and Returns (Relevant to PBE Paper II Management Accounting and Finance) Concepts in Investments Risks and Returns (Relevant to PBE Paper II Management Accounting and Finance) Mr. Eric Y.W. Leung, CUHK Business School, The Chinese University of Hong Kong In PBE Paper II, students

More information

Assessment of Numerical Methods for DNS of Shockwave/Turbulent Boundary Layer Interaction

Assessment of Numerical Methods for DNS of Shockwave/Turbulent Boundary Layer Interaction 44th AIAA Aerospace Sciences Meeting and Exhibit, Jan 9 Jan 12, Reno, Nevada Assessment of Numerical Methods for DNS of Shockwave/Turbulent Boundary Layer Interaction M. Wu and M.P. Martin Mechanical and

More information

Principle Component Analysis and Partial Least Squares: Two Dimension Reduction Techniques for Regression

Principle Component Analysis and Partial Least Squares: Two Dimension Reduction Techniques for Regression Principle Component Analysis and Partial Least Squares: Two Dimension Reduction Techniques for Regression Saikat Maitra and Jun Yan Abstract: Dimension reduction is one of the major tasks for multivariate

More information

Community Mining from Multi-relational Networks

Community Mining from Multi-relational Networks Community Mining from Multi-relational Networks Deng Cai 1, Zheng Shao 1, Xiaofei He 2, Xifeng Yan 1, and Jiawei Han 1 1 Computer Science Department, University of Illinois at Urbana Champaign (dengcai2,

More information

Optimal Design of α-β-(γ) Filters

Optimal Design of α-β-(γ) Filters Optimal Design of --(γ) Filters Dirk Tenne Tarunraj Singh, Center for Multisource Information Fusion State University of New York at Buffalo Buffalo, NY 426 Abstract Optimal sets of the smoothing parameter

More information

Flexible Neural Trees Ensemble for Stock Index Modeling

Flexible Neural Trees Ensemble for Stock Index Modeling Flexible Neural Trees Ensemble for Stock Index Modeling Yuehui Chen 1, Ju Yang 1, Bo Yang 1 and Ajith Abraham 2 1 School of Information Science and Engineering Jinan University, Jinan 250022, P.R.China

More information

Further Mathematics for Engineering Technicians

Further Mathematics for Engineering Technicians Unit 28: Further Mathematics for Engineering Technicians Unit code: QCF Level 3: Credit value: 10 Guided learning hours: 60 Aim and purpose H/600/0280 BTEC Nationals This unit aims to enhance learners

More information

Equations of Lines and Planes

Equations of Lines and Planes Calculus 3 Lia Vas Equations of Lines and Planes Planes. A plane is uniquely determined by a point in it and a vector perpendicular to it. An equation of the plane passing the point (x 0, y 0, z 0 ) perpendicular

More information

The dynamic equation for the angular motion of the wheel is R w F t R w F w ]/ J w

The dynamic equation for the angular motion of the wheel is R w F t R w F w ]/ J w Chapter 4 Vehicle Dynamics 4.. Introduction In order to design a controller, a good representative model of the system is needed. A vehicle mathematical model, which is appropriate for both acceleration

More information

Results of wake simulations at the Horns Rev I and Lillgrund wind farms using the modified Park model

Results of wake simulations at the Horns Rev I and Lillgrund wind farms using the modified Park model Downloaded from orbit.dtu.dk on: Feb 15, 216 Results of wake simulations at the Horns Rev I and Lillgrund wind farms using the modified Park model Pena Diaz, Alfredo; Réthoré, Pierre-Elouan; Hasager, Charlotte

More information

GRAPHICAL METHOD OF FACTORING THE CORRELATION

GRAPHICAL METHOD OF FACTORING THE CORRELATION VOL. 30, 1944 PS YCHOLOGYY: L. L. THURSTONE 129 GRAPHCAL METHOD OF FACTORNG THE CORRELATON MA TRX BY L. L. THURSTONE THE PSYCHOMETRC LABORATORY, THE UNVERSTY OF CHCAGO Communicated April 14, 1944 Multiple

More information

Fitting Subject-specific Curves to Grouped Longitudinal Data

Fitting Subject-specific Curves to Grouped Longitudinal Data Fitting Subject-specific Curves to Grouped Longitudinal Data Djeundje, Viani Heriot-Watt University, Department of Actuarial Mathematics & Statistics Edinburgh, EH14 4AS, UK E-mail: [email protected] Currie,

More information

Lecture 3: Linear methods for classification

Lecture 3: Linear methods for classification Lecture 3: Linear methods for classification Rafael A. Irizarry and Hector Corrada Bravo February, 2010 Today we describe four specific algorithms useful for classification problems: linear regression,

More information

Design-Simulation-Optimization Package for a Generic 6-DOF Manipulator with a Spherical Wrist

Design-Simulation-Optimization Package for a Generic 6-DOF Manipulator with a Spherical Wrist Design-Simulation-Optimization Package for a Generic 6-DOF Manipulator with a Spherical Wrist MHER GRIGORIAN, TAREK SOBH Department of Computer Science and Engineering, U. of Bridgeport, USA ABSTRACT Robot

More information

NOWCASTING OF PRECIPITATION Isztar Zawadzki* McGill University, Montreal, Canada

NOWCASTING OF PRECIPITATION Isztar Zawadzki* McGill University, Montreal, Canada NOWCASTING OF PRECIPITATION Isztar Zawadzki* McGill University, Montreal, Canada 1. INTRODUCTION Short-term methods of precipitation nowcasting range from the simple use of regional numerical forecasts

More information

Appliedand Computational NISTIR5916 Mathematics Division ComputingandAppliedMathematicsLaboratory ServiceforSpecialFunctions AProposedSoftwareTest DanielW.Lozier October1996 NationalInstituteofStandardsandTechnology

More information

Motion. Complete Table 1. Record all data to three decimal places (e.g., 4.000 or 6.325 or 0.000). Do not include units in your answer.

Motion. Complete Table 1. Record all data to three decimal places (e.g., 4.000 or 6.325 or 0.000). Do not include units in your answer. Labs for College Physics: Mechanics Worksheet Experiment 2-1 Motion As you work through the steps in the lab procedure, record your experimental values and the results on this worksheet. Use the exact

More information

MATHEMATICS FOR ENGINEERING BASIC ALGEBRA

MATHEMATICS FOR ENGINEERING BASIC ALGEBRA MATHEMATICS FOR ENGINEERING BASIC ALGEBRA TUTORIAL 3 EQUATIONS This is the one of a series of basic tutorials in mathematics aimed at beginners or anyone wanting to refresh themselves on fundamentals.

More information

Course 8. An Introduction to the Kalman Filter

Course 8. An Introduction to the Kalman Filter Course 8 An Introduction to the Kalman Filter Speakers Greg Welch Gary Bishop Kalman Filters in 2 hours? Hah! No magic. Pretty simple to apply. Tolerant of abuse. Notes are a standalone reference. These

More information

Time Series Data Mining in Rainfall Forecasting Using Artificial Neural Network

Time Series Data Mining in Rainfall Forecasting Using Artificial Neural Network Time Series Data Mining in Rainfall Forecasting Using Artificial Neural Network Prince Gupta 1, Satanand Mishra 2, S.K.Pandey 3 1,3 VNS Group, RGPV, Bhopal, 2 CSIR-AMPRI, BHOPAL [email protected]

More information

The Credibility of the Overall Rate Indication

The Credibility of the Overall Rate Indication The Credibility of the Overall Rate Indication Paper by Joseph Boor, FCAS Florida Office of Insurance Regulation Presented by Glenn Meyers, FCAS, MAAA, ISO Background-Why is this needed? Actuaries in North

More information

Mechanics i + j notation

Mechanics i + j notation Mechanics i + j notation Guaranteeing university rejection since the year whenever (this presentation will be focusing on the bits most likely causing university rejection) By Stephen the Mechanical Master

More information

Modelling and Forecasting financial time series of «tick data» by functional analysis and neural networks

Modelling and Forecasting financial time series of «tick data» by functional analysis and neural networks Modelling and Forecasting financial time series of «tick data» by functional analysis and neural networks S DABLEMONT S VAN BELLEGEM M VERLEYSEN Université catholique de Louvain Machine Learning Group

More information

physics 112N magnetic fields and forces

physics 112N magnetic fields and forces physics 112N magnetic fields and forces bar magnet & iron filings physics 112N 2 bar magnets physics 112N 3 the Earth s magnetic field physics 112N 4 electro -magnetism! is there a connection between electricity

More information

Probability Hypothesis Density filter versus Multiple Hypothesis Tracking

Probability Hypothesis Density filter versus Multiple Hypothesis Tracking Probability Hypothesis Density filter versus Multiple Hypothesis Tracing Kusha Panta a, Ba-Ngu Vo a, Sumeetpal Singh a and Arnaud Doucet b a Co-operative Research Centre for Sensor and Information Processing

More information

On the Efficiency of Competitive Stock Markets Where Traders Have Diverse Information

On the Efficiency of Competitive Stock Markets Where Traders Have Diverse Information Finance 400 A. Penati - G. Pennacchi Notes on On the Efficiency of Competitive Stock Markets Where Traders Have Diverse Information by Sanford Grossman This model shows how the heterogeneous information

More information

Cloud Analytics for Capacity Planning and Instant VM Provisioning

Cloud Analytics for Capacity Planning and Instant VM Provisioning Cloud Analytics for Capacity Planning and Instant VM Provisioning Yexi Jiang Florida International University Advisor: Dr. Tao Li Collaborator: Dr. Charles Perng, Dr. Rong Chang Presentation Outline Background

More information

MATH 185 CHAPTER 2 REVIEW

MATH 185 CHAPTER 2 REVIEW NAME MATH 18 CHAPTER REVIEW Use the slope and -intercept to graph the linear function. 1. F() = 4 - - Objective: (.1) Graph a Linear Function Determine whether the given function is linear or nonlinear..

More information

Modeling and Optimization of Performance of Four Stroke Spark Ignition Injector Engine

Modeling and Optimization of Performance of Four Stroke Spark Ignition Injector Engine Modeling and Optimization of Performance of Four Stroke Spark Ignition Injector Engine Okafor A. A. Achebe C. H. Chukwuneke J. L. Ozoegwu C. G. Mechanical Engineering Department, Nnamdi Azikiwe University,

More information

X X X a) perfect linear correlation b) no correlation c) positive correlation (r = 1) (r = 0) (0 < r < 1)

X X X a) perfect linear correlation b) no correlation c) positive correlation (r = 1) (r = 0) (0 < r < 1) CORRELATION AND REGRESSION / 47 CHAPTER EIGHT CORRELATION AND REGRESSION Correlation and regression are statistical methods that are commonly used in the medical literature to compare two or more variables.

More information

Field Data Recovery in Tidal System Using Artificial Neural Networks (ANNs)

Field Data Recovery in Tidal System Using Artificial Neural Networks (ANNs) Field Data Recovery in Tidal System Using Artificial Neural Networks (ANNs) by Bernard B. Hsieh and Thad C. Pratt PURPOSE: The field data collection program consumes a major portion of a modeling budget.

More information

The Big Picture. Correlation. Scatter Plots. Data

The Big Picture. Correlation. Scatter Plots. Data The Big Picture Correlation Bret Hanlon and Bret Larget Department of Statistics Universit of Wisconsin Madison December 6, We have just completed a length series of lectures on ANOVA where we considered

More information

POTENTIAL OF STATE-FEEDBACK CONTROL FOR MACHINE TOOLS DRIVES

POTENTIAL OF STATE-FEEDBACK CONTROL FOR MACHINE TOOLS DRIVES POTENTIAL OF STATE-FEEDBACK CONTROL FOR MACHINE TOOLS DRIVES L. Novotny 1, P. Strakos 1, J. Vesely 1, A. Dietmair 2 1 Research Center of Manufacturing Technology, CTU in Prague, Czech Republic 2 SW, Universität

More information

Typical Linear Equation Set and Corresponding Matrices

Typical Linear Equation Set and Corresponding Matrices EWE: Engineering With Excel Larsen Page 1 4. Matrix Operations in Excel. Matrix Manipulations: Vectors, Matrices, and Arrays. How Excel Handles Matrix Math. Basic Matrix Operations. Solving Systems of

More information

Deterministic Sampling-based Switching Kalman Filtering for Vehicle Tracking

Deterministic Sampling-based Switching Kalman Filtering for Vehicle Tracking Proceedings of the IEEE ITSC 2006 2006 IEEE Intelligent Transportation Systems Conference Toronto, Canada, September 17-20, 2006 WA4.1 Deterministic Sampling-based Switching Kalman Filtering for Vehicle

More information

A methodology for monitoring and leakage reduction in water distribution systems

A methodology for monitoring and leakage reduction in water distribution systems Water Utility Journal 2: 23-33, 2011. 2011 E.W. Publications A methodology for monitoring and leakage reduction in water distribution systems M. Nicolini University of Udine Department of Chemistry, Physics

More information

Univariate Regression

Univariate Regression Univariate Regression Correlation and Regression The regression line summarizes the linear relationship between 2 variables Correlation coefficient, r, measures strength of relationship: the closer r is

More information

Identification of Hybrid Systems

Identification of Hybrid Systems Identification of Hybrid Systems Alberto Bemporad Dip. di Ingegneria dell Informazione Università degli Studi di Siena [email protected] http://www.dii.unisi.it/~bemporad Goal Sometimes a hybrid model

More information