Spelling suggestions: "subject:"chineseelectronic engineering."" "subject:"chineseelectronic ingineering.""
451 |
Minimum congestion routing for a 17 GHz wireless ad hoc networkKotze, Daniel Johannes Van Wyk 03 1900 (has links)
Thesis (MScEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2011. / ENGLISH ABSTRACT: An investigation is made to find a suitable routing protocol for a millimeter wave ad hoc
wireless network. It is discovered that a hierarchical routing protocol is ideal for a high
node density. Due to the high bandwidth that is possibly available, with millimeter wave
transmission, packets are used to keep links between nodes active and to control data packet
congestion. Cluster leaders are elected and use token packets to provide nodes with more
queued messages with more transmission chances, assisting the network in congestion control.
Hello messages are sent frequently to keep routing information at nodes fresh and to detect
broken links quickly. If a broken link is found a new route is readily available, within a
second. A simulation is created to test the protocol. Changes are made to the original
proactive cluster routing protocol to reduce the route length and lessen routing overhead.
A theoretical model is developed to estimate the mean waiting time for a packet. Although
insight is gained by modelling the latency with queueing theory it is suggested, due to the
protocol’s complexity, to use other mathematical modelling techniques such as a Markov
state model or a Petri net. / AFRIKAANSE OPSOMMING: Ondersoek word ingestel na ’n geskikte roete protokol vir ’n millimeter golflengte ad hoc radio
pakkie netwerk. Daar word gevind dat ’n hi¨erargiese kluster roete protokol ideaal is vir ’n
ho¨e digtheid van nodusse. As gevolg van die ho¨e bandwydte, wat moontlik beskikbaar is
met millimeter golflengte transmissie, word pakkies gebruik om kommunikasie skakels tussen
nodes in stand te hou en data pakkie verkeersopeenhoping te beheer. Kluster leiers word
verkies en gebruik teken-pakkies om nodes met ’n groter data pakkie las meer transmissie
kanse te gee. Sodoende word die verkeersopeenhoping van data pakkies verminder. Hallo
pakkies word gereeld gestuur om die roete inligting vars te hou en gebroke kommunikasie
skakels vinnig op te spoor. As ’n gebroke skakel gevind word, word ’n alternatiewe roete
vinnig opgestel, binne ’n sekonde. ’n Simulasie word opgestel om die protokol te toets.
Veranderinge aan die oorspronklike proaktiewe kluster protokol word aangebring om roete
lengte te verklein en oorhoofse roete inligting kommunikasie te verminder. ’n Teoretiese
model gebasseer op tou-staan teorie word ontwikkel om die wagtyd van ’n pakkie te bepaal.
Alhoewel, insig verkry is deur die protokol te analiseer deur middel van tou-staan teorie, word
daar voorgestel, as gevolg van die protokol se kompleksiteit, om eerder ander wiskundige
modelleeringstegnieke te gebruik soos ’n Markov toestands model of ’n Petri net.
|
452 |
The design and implementation of vision-based autonomous rotorcraft landingDe Jager, Andries Matthys 03 1900 (has links)
Thesis (MScEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2011. / ENGLISH ABSTRACT: This thesis presents the design and implementation of all the subsystems required to
perform precision autonomous helicopter landings within a low-cost framework.
To obtain high-accuracy state estimates during the landing phase a vision-based approach,
with a downwards facing camera on the helicopter and a known landing target, was used.
An e cient monocular-view pose estimation algorithm was developed to determine the
helicopter's relative position and attitude during the landing phase. This algorithm was
analysed and compared to existing algorithms in terms of sensitivity, robustness and
runtime.
An augmented kinematic state estimator was developed to combine measurements from
low-cost GPS and inertial measurement units with the high accuracy measurements from
the camera system. High-level guidance algorithms, capable of performing waypoint navigation
and autonomous landings, were developed.
A visual position and attitude measurement (VPAM) node was designed and built to perform
the pose estimation and execute the associated algorithms. To increase the node's
throughput, a compression scheme is used between the image sensor and the processor
to reduce the amount of data that needs to be processed. This reduces processing requirements
and allows the entire system to remain on-board with no reliance on radio
links. The functionality of the VPAM node was con rmed through a number of practical
tests. The node is able to provide measurements of su cient accuracy for the subsequent
systems in the autonomous landing system.
The functionality of the full system was con rmed in a software environment, as well as
through testing using a visually augmented hardware-in-the-loop environment. / AFRIKAANSE OPSOMMING: Hierdie tesis beskryf die ontwikkeling van die substelsels wat vir akkurate outonome helikopter
landings benodig word. 'n Onderliggende doel was om al die ontwikkeling binne
'n lae-koste raamwerk te voltooi.
Hoe-akkuraatheid toestande word benodig om akkurate landings te verseker. Hierdie
metings is verkry deur middel van 'n optiese stelsel, bestaande uit 'n kamera gemonteer
op die helikopter en 'n bekende landingsteiken, te ontwikkel. 'n Doeltreffende mono-visie
posisie-en-orientasie algoritme is ontwikkel om die helikopter se posisie en orientasie, relatief
tot die landingsteiken, te bepaal. Hierdie algoritme is deeglik ondersoek en vergelyk
met bestaande algoritmes in terme van sensitiwiteit, robuustheid en uitvoertyd.
'n Optimale kinematiese toestandswaarnemer, wat metings van GPS en inersiele sensore
kombineer met die metings van die optiese stelsel, is ontwikkel en deur simulasie bevestig.
Hoe-vlak leidingsalgoritmes is ontwikkel wat die helikopter in staat stel om punt-tot-punt
navigasie en die landingsprosedure uit te voer.
'n Visuele posisie-en-orientasie meetnodus is ontwikkel om die mono-visie posisie-en orientasie algoritmes uit te voer. Om die deurset te verhoog is 'n saampersingsalgoritme
gebruik wat die hoeveelheid data wat verwerk moet word, te verminder. Dit het die
benodigde verwerkingskrag verminder, wat verseker het dat alle verwerking op aanboord
stelsels kan geskied. Die meetnodus en mono-visie algoritmes is deur middel van praktiese
toetse bevestig en is in staat om metings van voldoende akkuraatheid aan die outonome
landingstelsel te verskaf.
Die werking van die volledige stelsel is, deur simulasies in 'n sagteware en hardeware-indie-
lus omgewing, bevestig.
|
453 |
The design and implementation of a video compression development boardAlalait, Suliman 03 1900 (has links)
Thesis (MScEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2011. / This thesis describes the design and implementation of a video compression development board as a standalone embedded system.
The board can capture images, encode them and stream out a video to a destination over a wireless link. This project was done to allow users to test and develop video compression encoders that are designed for UAV applications.
The board was designed to use an ADSP-BF533 Blackfin DSP from Analog Devices with the purpose of encoding images, which were captured by a camera module and then streamed out a video through a WiFi module. Moreover, an FPGA that has an interface to a logic analyzer, the DSP, the camera and the WiFi module, was added to accommodate other future uses, and to allow for the debugging of the board.
The board was tested by loading a H.264 BP/MP encoder from Analog Devices to the DSP, where the DSP was integrated with the camera and the WiFi module. The test was successful and the board was able to encode a 2 MegaPixel picture at about 2 frames per second with a data rate of 186 Kbps. However, as the frame rate was only 2 frames per second, the video was somewhat jerky.
It was found that the encoding time is a system limitation and that it has to be improved in order to increase the frame rate. A proposed solution involves dividing the captured picture into smaller segments and encoding each segment in parallel. Thereafter, the segments can be packed and streamed out. Further performance issues about the proposed structure are presented in the thesis.
|
454 |
Design of an ad hoc wireless network for wildlife telemetry tracking in the CederbergBrits, Johan George 03 1900 (has links)
Thesis (MScEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2011. / ENGLISH ABSTRACT: This thesis involves research on wildlife telemetry tracking for the Cape Leopard Trust
(CLT). The CLT needed a network to transfer GPS data and single frame photos from
remote locations in the Cederberg to a researcher's base station. The proposed solution
is an ad hoc wireless network, where nodes perform polling of leopard collars and send
information via the multi-hop network to the researcher's base once it is downloaded from
a collar. The literature study involved medium access control - and routing protocols for
e ectively transferring information. The solution was implemented in hardware and range
tests were done in the Cederberg to determine feasible locations for nodes in this network
for covering most of the CLT study area. Link budgets for this area was determined with
Radio Mobile to compare with actual ranges as measured. The simulation of protocols
was done in OMNET++ which could be compared with actual results from the physical
network. / AFRIKAANSE OPSOMMING: Hierdie tesis handel oor navorsing wat gedoen is vir die Kaapse Luipaard Trust (CLT)
vir die opsporing van luipaarde. Die CLT het 'n netwerk nodig gehad wat GPS data en
enkel raam fotos van afgeleë gebiede in die Cederberge na 'n navorser se basis stuur. Die
voorgestelde oplossing is 'n ad hoc draadlose netwerk, waar nodisse luipaard nekbande
oproep om data af te laai en dan te stuur deur die multi-hop netwerk na die navorser
se basis. Die literatuurstudie handel oor medium toegangs beheer - en roete verkryging
protokolle vir die effektiewe oordrag van informasie. Die oplossing is in hardeware geïmplimenteer
en radio-afstand-toetse is gedoen in die Cederberge om goedgeleë posisies vir
nodisse te bepaal om die grootste gedeelte van die CLT studie area te dek. Radio Mobile
is gebruik om voorspellings te maak rakende die afstande verkrygbaar tussen radios om
te vergelyk met die fisiese metings in die veld. Die simulasie van protokolle is gedoen in
OMNET++ en vergelyk met prestasie metings op die fisiese netwerk.
|
455 |
Unsupervised clustering of audio data for acoustic modelling in automatic speech recognition systemsGoussard, George Willem 03 1900 (has links)
Thesis (MScEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2011. / ENGLISH ABSTRACT: This thesis presents a system that is designed to replace the manual process of
generating a pronunciation dictionary for use in automatic speech recognition.
The proposed system has several stages.
The first stage segments the audio into what will be known as the subword
units, using a frequency domain method. In the second stage, dynamic
time warping is used to determine the similarity between the segments of each
possible pair of these acoustic segments. These similarities are used to cluster
similar acoustic segments into acoustic clusters. The final stage derives a
pronunciation dictionary from the orthography of the training data and corresponding
sequence of acoustic clusters. This process begins with an initial
mapping between words and their sequence of clusters, established by Viterbi
alignment with the orthographic transcription. The dictionary is refined iteratively
by pruning redundant mappings, hidden Markov model estimation and
Viterbi re-alignment in each iteration.
This approach is evaluated experimentally by applying it to two subsets of
the TIMIT corpus. It is found that, when test words are repeated often in the
training material, the approach leads to a system whose accuracy is almost as
good as one trained using the phonetic transcriptions. When test words are
not repeated often in the training set, the proposed approach leads to better
results than those achieved using the phonetic transcriptions, although the
recognition is poor overall in this case. / AFRIKAANSE OPSOMMING: Die doelwit van die tesis is om ’n stelsel te beskryf wat ontwerp is om die
handgedrewe proses in die samestelling van ’n woordeboek, vir die gebruik
in outomatiese spraakherkenningsstelsels, te vervang. Die voorgestelde stelsel
bestaan uit ’n aantal stappe.
Die eerste stap is die segmentering van die oudio in sogenaamde sub-woord
eenhede deur gebruik te maak van ’n frekwensie gebied tegniek. Met die tweede
stap word die dinamiese tydverplasingsalgoritme ingespan om die ooreenkoms
tussen die segmente van elkeen van die moontlike pare van die akoestiese segmente
bepaal. Die ooreenkomste word dan gebruik om die akoestiese segmente
te groepeer in akoestiese groepe. Die laaste stap stel die woordeboek
saam deur gebruik te maak van die ortografiese transkripsie van afrigtingsdata
en die ooreenstemmende reeks akoestiese groepe. Die finale stap begin met
’n aanvanklike afbeelding vanaf woorde tot hul reeks groep identifiseerders,
bewerkstellig deur Viterbi belyning en die ortografiese transkripsie. Die woordeboek
word iteratief verfyn deur oortollige afbeeldings te snoei, verskuilde
Markov modelle af te rig en deur Viterbi belyning te gebruik in elke iterasie.
Die benadering is getoets deur dit eksperimenteel te evalueer op twee subversamelings
data vanuit die TIMIT korpus. Daar is bevind dat, wanneer
woorde herhaal word in die afrigtingsdata, die stelsel se benadering die akkuraatheid
ewenaar van ’n stelsel wat met die fonetiese transkripsie afgerig is.
As die woorde nie herhaal word in die afrigtingsdata nie, is die akkuraatheid
van die stelsel se benadering beter as wanneer die stelsel afgerig word met die
fonetiese transkripsie, alhoewel die akkuraatheid in die algemeen swak is.
|
456 |
The development of Sun and Nadir sensors for a solar sail CubeSatLoubser, Hanco Evert 03 1900 (has links)
Thesis (MScEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2011. / ENGLISH ABSTRACT: This thesis describes the development of attitude sensors required for the Attitude Determination and
Control System (ADCS) for a Cubesat. The aim is to find the most suitable sensors for use on a small picosatellite
by implementing miniaturised sensors with available commercial-off-the-shelf (COTS) technology.
Specifically, the algorithms, hardware prototypes, software and filters required to create accurate sensors
to determine the 3-axis orientation of a CubeSat are discussed. / AFRIKAANSE OPSOMMING: Hierdie tesis beskryf die ontwikkeling van oriëntasiesensors wat benodig word vir die oriëntasiebepaling
en -beheerstelsel (Engels: ADCS) van ’n CubeSat. Die doelwit is om sensors te vind wat die geskikste is om
in ’n klein picosatelliet te gebruik, deur miniatuursensors met kommersiële maklik verkrygbare tegnologie
(Engels: COTS technology) te implementeer. Daar word in die bespreking veral aandag geskenk aan die
algoritmes, hardewareprototipes, programmatuur en filters wat benodig word om akkurate sensors te
skep wat op hul beurt 3-as oriëntasie van die CubeSat kan bepaal.
|
457 |
Visual servo control for a human-following robotBurke, Michael Glen 03 1900 (has links)
Thesis (MScEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2011. / ENGLISH ABSTRACT: This thesis presents work completed on the design of control and vision components
for use in a monocular vision-based human-following robot. The use
of vision in a controller feedback loop is referred to as vision-based or visual
servo control. Typically, visual servo techniques can be categorised into imagebased
visual servoing and position-based visual servoing. This thesis discusses
each of these approaches, and argues that a position-based visual servo control
approach is more suited to human following.
A position-based visual servo strategy consists of three distinct phases:
target recognition, target pose estimation and controller calculations. The
thesis discusses approaches to each of these phases in detail, and presents a
complete, functioning system combining these approaches for the purposes of
human following.
Traditional approaches to human following typically involve a controller
that causes platforms to navigate directly towards targets, but this work argues
that better following performance can be obtained through the use of a
controller that incorporates target orientation information. Although a purely
direction-based controller, aiming to minimise both orientation and translation
errors, suffers from various limitations, this thesis shows that a hybrid,
gain-scheduling combination of two traditional controllers offers better targetfollowing
performance than its components.
In the case of human following the inclusion of target orientation information
requires that a definition and means of estimating a human’s orientation
be available. This work presents a human orientation measure and experimental
results to show that it is suitable for the purposes of wheeled platform
control. Results of human following using the proposed hybrid, gain-scheduling
controller incorporating this measure are presented to confirm this. / AFRIKAANSE OPSOMMING: Die ontwerp van ’n visiestelsel en beheer-komponente van ’n enkel-kamera robot
vir die volging van mense word hier aangebied. Die gebruik van visuele
terugvoer in die beheerlus word visie-gebaseerde of visuele servobeheer genoem.
Visuele servobeheer tegnieke kan tipies onderskei word tussen beeld-gebaseerde
servobeheer en posisie-gebaseerde visuele servobeheer. Altwee benaderings
word hier bespreek. Die posisie-gebaseerde benadering word aanbeveel vir
die volging van mense.
Die posisie-gebaseerde servobeheertegniek bestaan uit drie duidelike fases:
teiken herkenning, teiken oriëntasie bepaling en die beheerder berekeninge.
Benaderings tot elk van hierdie fases word hier in detail bespreek. Dan word
’n volledige funksionele stelsel aangebied wat hierdie fases saamvoeg sodat
mense gevolg kan word.
Meer tradisionele benaderings tot die volging van mense gebruik tipies ’n
beheerder wat die platvorm direk laat navigeer na die teikens, maar hier word
geargumenteer dat beter werkverrigting verkry kan word deur ’n beheerder
wat die teiken oriëntasie inligting ook gebruik. ’n Suiwer rigting-gebaseerde
beheerder, wat beide oriëntasie en translasie foute minimeer, is onderhewig
aan verskeie beperkings. Hier word egter aangetoon dat ’n hibriede, aanwinsskedulerende
kombinasie van die twee tradisionele beheerders beter teikenvolging
werkverrigting bied as die onderliggende twee tegnieke.
In die geval van die volging van mense vereis die insluiting van teiken oriëntasie
inligting dat ’n definisie van die persoon se oriëntasie beskikbaar is en
dat dit geskat kan word. ’n Oriëntasie maatstaf vir mense word hier aangebied
en dit word eksperimenteel getoon dat dit geskik is om ’n platvorm met
wiele te beheer. Die resultate van die volging van mense wat die voorgestelde
hibriede, aanwins-skedulerende beheerder gebruik, met hierdie maatstaf, word
ter ondersteuning aangebied.
|
458 |
Dynamic reconfigurable platform for swarm roboticsHeath, Gerhardus 03 1900 (has links)
Thesis (MScEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2011. / ENGLISH ABSTRACT: Swarm intelligence research was inspired by biological systems in nature. Working ants and
bees has captivated researchers for centuries, with the ant playing a major role in shaping the
future of robotic swarm applications. The ants foraging activity can be adapted for different
applications of robotic swarm intelligence. Numerous researchers have conducted theoretical
analysis and experiments on the ants foraging activities and communication styles.
Combining this information with modern reconfigurable computing opens the door to more
complex behaviour with improved system dynamics. Reconfigurable computing has
numerous applications in swarm intelligence such as true hardware parallel processing,
dynamic power save algorithms and dynamic peripheral changes to the CPU core.
In this research a brief study is made of swarm intelligence and its applications. The ants'
foraging activities were studied in greater detail with the emphasis on a layered control system
designed implementation in a robotic agent. The robotic agent’s hardware was designed using
a partial self reconfigurable FPGA as the main building element. The hardware was designed
with the emphasis on system flexibility for swarm application drawing attention to power
reduction and battery life. All of this was packaged into a differential drive chassis designed
specifically for this project. / AFRIKAANSE OPSOMMING: Die motivering vir swerm robotika kom van die natuur. Vir eeue fassineer swerm insekte
soos bye en miere navorsers. Dit is verstommend hoe ’n groep klein en nietige insekte sulke
groot take kan verrig. Die mier speel ‘n belangrike rol en is die sentrale tema van menige
publikasies. Die mier se kos-soek aktiwiteit kan aangepas word vir swerm robotika
toepassings. Hierdie aktiwiteit vervat verskeie sleutel konsepte wat belangrik is vir robotika
toepassings.
Deur bv. die mier se aktiwiteite te kombineer met dinamies herkonfigureerbare hardeware,
kan meer komplekse gedrag bestudeer word. Die stelsel dinamika verbeter ook, aangesien dit
nou moontlik is om sekere take in parallel uit te voer. Deur ’n interne prosesseerder in die
herkonfigureerbare hardeware in te sluit, is dit nou vir die stelsel moontlik om homself te
verander tydens taak verrigting. Komplekse krag bestuur gedrag is ook moontlik deurdat die
prosesseerder die spoed en rand apparaat kan verander soos benodig. ‘n Verdere voordeel is
dat die stelsel aanpasbaar is en dus vir verskeie navorsingsprojekte gebruik kan word.
In hierdie navorsing word ’n literatuur studie van swerm robotika gemaak en word daar ook
na toepassings gekyk. Met die klem op praktiese implementering, word die mier se kos-soek
aktiwiteit in detail ondersoek deur gebruik te maak van ’n laag beheerstelsel. In hierdie laag
beheerstelsel verteenwoordig elke laag ’n hoër vlak gedrag. Stelsel aanpasbaarheid en lae
kragverbruik speel ’n deurslaggewende rol in die ontwerp, en om hierdie rede vorm ’n FPGA
die hart van die sisteem.
|
459 |
Waveguide antenna feed for the Square Kilometre ArraySchoeman, Karla 03 1900 (has links)
Thesis (MscEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2011. / ENGLISH ABSTRACT: The aim of this thesis is to investigate the suitability of TEM (Transverse Electromagnetic) horn
antennas for use as feed structures for the Square Kilometre Array (SKA) radio telescope, in particular
with regard to the roundness of the radiation pattern. A literature study shows that existing
TEM horn designs do not yield a round radiation pattern over a wide bandwidth and that an alternative
is required. The Method of Moments (MoM) is a computational electromagnetic (CEM)
technique typically used in the analysis of TEM horn antennas. An in-house MoM solver is successfully
developed to analyse such antennas and is able to calculate the current density on the
surface of a conductor, as well as the farfield patterns of an antenna. A modification to an exponential
TEM horn antenna is proposed and simulations show the modification is successful in
yielding a round radiation pattern over a wide bandwidth. The modified exponential TEM horn has
a convex triangular arc at the end of each antenna plate and is constructed for measurement. Due to
limited construction capabilities, the measurements deviate slightly from the simulated results but
still indicate the potential of the structure to yield a round radiation pattern over a wide bandwidth. / AFRIKAANSE OPSOMMING: Die doel van hierdie tesis is om die geskiktheid van transverse elektromagnetiese (TEM) horing
antennas te ondersoek vir die gebruik as voerstrukture vir die Square Kilometre Array (SKA)-
radioteleskoop, veral met betrekking tot die rondheid van die stralingspatroon. ’n Literatuurstudie
toon dat bestaande TEM horing ontwerpe nie ’n ronde stralingspatroon oor ’n wye bandwydte
lewer nie, en dat ’n alternatief nodig is. Die metode van momente is ’n rekenbare elektromagnetiese
tegniek wat tipies gebruik word in die ontleding van TEM horing antennas. ’n In-huis metode van
momente ontleder is suksesvol ontwikkel om sulke antennas te analiseer en is in staat om die
stroomdigtheid op die oppervlak van ’n geleier, sowel as die vêrveld patrone van die antenna te
bereken. ’n Wysiging van ’n eksponensiële TEM horing antenna word voorgestel en simulasies
toon dat die veranderings suksesvol is om ’n ronde stralingspatroon oor ’n wye bandwydte te skep.
Die verander eksponensiële TEM horing het ’n konvekse driehoekige boog aan die einde van elke
antenna plaat en is gebou vir meting. Weens beperkte konstruksie vermoëns, toon die metings ’n
afwyking van die gesimuleerde resultate, maar dui nogsteeds die potensiaal aan van die struktuur
om ’n ronde stralingspatroon te lewer oor ’n wye bandwydte.
|
460 |
Stereo vision for simultaneous localization and mappingBrink, Wikus 12 1900 (has links)
Thesis (MScEng)--Stellenbosch University, 2012. / ENGLISH ABSTRACT: Simultaneous localization and mapping (SLAM) is vital for autonomous robot navigation. The robot
must build a map of its environment while tracking its own motion through that map. Although
many solutions to this intricate problem have been proposed, one of the most prominent issues that
still needs to be resolved is to accurately measure and track landmarks over time. In this thesis we
investigate the use of stereo vision for this purpose.
In order to find landmarks in images we explore the use of two feature detectors: the scale-invariant
feature transform (SIFT) and speeded-up robust features (SURF). Both these algorithms find salient
points in images and calculate a descriptor for each point that is invariant to scale, rotation and
illumination. By using the descriptors we match these image features between stereo images and
use the geometry of the system to calculate a set of 3D landmark measurements. A Taylor approximation
of this transformation is used to derive a Gaussian noise model for the measurements.
The measured landmarks are matched to landmarks in a map to find correspondences. We find that
this process often incorrectly matches ambiguous landmarks. To find these mismatches we develop
a novel outlier detection scheme based on the random sample consensus (RANSAC) framework. We
use a similarity transformation for the RANSAC model and derive a probabilistic consensus measure
that takes the uncertainties of landmark locations into account. Through simulation and practical
tests we find that this method is a significant improvement on the standard approach of using the
fundamental matrix.
With accurately identified landmarks we are able to perform SLAM. We investigate the use of three
popular SLAM algorithms: EKF SLAM, FastSLAM and FastSLAM 2. EKF SLAM uses a Gaussian
distribution to describe the systems states and linearizes the motion and measurement equations
with Taylor approximations. The two FastSLAM algorithms are based on the Rao-Blackwellized
particle filter that uses particles to describe the robot states, and EKFs to estimate the landmark
states. FastSLAM 2 uses a refinement process to decrease the size of the proposal distribution and
in doing so decreases the number of particles needed for accurate SLAM.
We test the three SLAM algorithms extensively in a simulation environment and find that all three
are capable of very accurate results under the right circumstances. EKF SLAM displays extreme
sensitivity to landmark mismatches. FastSLAM, on the other hand, is considerably more robust
against landmark mismatches but is unable to describe the six-dimensional state vector required for
3D SLAM. FastSLAM 2 offers a good compromise between efficiency and accuracy, and performs
well overall.
In order to evaluate the complete system we test it with real world data. We find that our outlier
detection algorithm is very effective and greatly increases the accuracy of the SLAM systems. We
compare results obtained by all three SLAM systems, with both feature detection algorithms, against
DGPS ground truth data and achieve accuracies comparable to other state-of-the-art systems.
From our results we conclude that stereo vision is viable as a sensor for SLAM. / AFRIKAANSE OPSOMMING: Gelyktydige lokalisering en kartering (simultaneous localization and mapping, SLAM) is ’n noodsaaklike
proses in outomatiese robot-navigasie. Die robot moet ’n kaart bou van sy omgewing en
tegelykertyd sy eie beweging deur die kaart bepaal. Alhoewel daar baie oplossings vir hierdie ingewikkelde
probleem bestaan, moet een belangrike saak nog opgelos word, naamlik om landmerke
met verloop van tyd akkuraat op te spoor en te meet. In hierdie tesis ondersoek ons die moontlikheid
om stereo-visie vir hierdie doel te gebruik.
Ons ondersoek die gebruik van twee beeldkenmerk-onttrekkers: scale-invariant feature transform
(SIFT) en speeded-up robust features (SURF). Altwee algoritmes vind toepaslike punte in beelde en
bereken ’n beskrywer vir elke punt wat onveranderlik is ten opsigte van skaal, rotasie en beligting.
Deur die beskrywer te gebruik, kan ons ooreenstemmende beeldkenmerke soek en die geometrie
van die stelsel gebruik om ’n stel driedimensionele landmerkmetings te bereken. Ons gebruik ’n
Taylor- benadering van hierdie transformasie om ’n Gaussiese ruis-model vir die metings te herlei.
Die gemete landmerke se beskrywers word dan vergelyk met dié van landmerke in ’n kaart om
ooreenkomste te vind. Hierdie proses maak egter dikwels foute. Om die foutiewe ooreenkomste
op te spoor het ons ’n nuwe uitskieterherkenningsalgoritme ontwikkel wat gebaseer is op die
RANSAC-raamwerk. Ons gebruik ’n gelykvormigheidstransformasie vir die RANSAC-model en lei ’n
konsensusmate af wat die onsekerhede van die ligging van landmerke in ag neem. Met simulasie en
praktiese toetse stel ons vas dat die metode ’n beduidende verbetering op die standaardprosedure,
waar die fundamentele matriks gebruik word, is.
Met ons akkuraat geïdentifiseerde landmerke kan ons dan SLAM uitvoer. Ons ondersoek die gebruik
van drie SLAM-algoritmes: EKF SLAM, FastSLAM en FastSLAM 2. EKF SLAM gebruik ’n Gaussiese
verspreiding om die stelseltoestande te beskryf en Taylor-benaderings om die bewegings- en meetvergelykings
te lineariseer. Die twee FastSLAM-algoritmes is gebaseer op die Rao-Blackwell partikelfilter
wat partikels gebruik om robottoestande te beskryf en EKF’s om die landmerktoestande af te
skat. FastSLAM 2 gebruik ’n verfyningsproses om die grootte van die voorstelverspreiding te verminder
en dus die aantal partikels wat vir akkurate SLAM benodig word, te verminder.
Ons toets die drie SLAM-algoritmes deeglik in ’n simulasie-omgewing en vind dat al drie onder die
regte omstandighede akkurate resultate kan behaal. EKF SLAM is egter baie sensitief vir foutiewe
landmerkooreenkomste. FastSLAM is meer bestand daarteen, maar kan nie die sesdimensionele
verspreiding wat vir 3D SLAM vereis word, beskryf nie. FastSLAM 2 bied ’n goeie kompromie
tussen effektiwiteit en akkuraatheid, en presteer oor die algemeen goed.
Ons toets die hele stelsel met werklike data om dit te evalueer, en vind dat ons uitskieterherkenningsalgoritme
baie effektief is en die akkuraatheid van die SLAM-stelsels beduidend verbeter. Ons
vergelyk resultate van die drie SLAM-stelsels met onafhanklike DGPS-data, wat as korrek beskou
kan word, en behaal akkuraatheid wat vergelykbaar is met ander toonaangewende stelsels.
Ons resultate lei tot die gevolgtrekking dat stereo-visie ’n lewensvatbare sensor vir SLAM is.
|
Page generated in 0.0741 seconds