izpis_h1_title_alt

Stabilizacija kvadrokopterja z vizualnim sledenjem oznaki : diplomsko delo
ID Slabanja, Jurij (Author), ID Skočaj, Danijel (Mentor) More about this mentor... This link opens in a new window

URLURL - Presentation file, Visit http://eprints.fri.uni-lj.si/2739/ This link opens in a new window

Abstract
V tem delu smo implementirali postopek, s katerim lahko kvadrokopter Parrot AR.Drone sledi premikajočemu se objektu. Temelji na razvojnem okolju ROS. Uporabili smo platformo iRobot Roombo, nanjo nalepili oznako in jo vozili po prostoru, kvadrokopter pa se je moral ves čas držati čim bolj točno nad njo. Kvadrokopter je oznako zaznaval s pomočjo sprednje kamere, krmiljenje pa je bilo izvedeno s krmilnikom PID. Nalogo smo ovrednotili s tremi različnimi eksperimenti. Najprej smo ovrednotili kako natančna je naša metoda ocenjevanja višine kvadrokopterja v primerjavi s privzetim načinom. Nato smo ovrednotili kako natančno in robustno se zna kvadrokopter držati nad mirujočo oznako. Nazadnje smo ovrednotili še natančnost in robustnost pri premikajoči se oznaki. Rezultati kažejo, da lahko z uporabo sistema implementiranega v tej nalogi kvadrokopter precej bolj stabilno lebdi nad oznako in ocenjuje razdaljo do nje, v primerjavi s privzetimi metodami, ki so vgrajene v Parrot AR.Drone.

Language:Slovenian
Keywords:kvadrokopter, ROS, oznaka, kalibracija kamere, sledenje robov, Ramer-Douglas-Peucker algoritem, krmilnik PID, računalništvo, računalništvo in informatika, univerzitetni študij, diplomske naloge
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FRI - Faculty of Computer and Information Science
Publisher:[J. Slabanja]
Year:2014
Number of pages:49 str.
PID:20.500.12556/RUL-68922 This link opens in a new window
UDC:004.93(043.2)
COBISS.SI-ID:1536118467 This link opens in a new window
Publication date in RUL:10.07.2015
Views:1269
Downloads:268
Metadata:XML RDF-CHPDL DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Quadcopter stabilization using visual marker-based tracking
Abstract:
In this thesis we implemented a system, which Parrot AR.Drone can use to track a moving target. The system is based on ROS. We used an iRobot Roomba as the target, put a marker on top of it, and drove it around. The drone's goal was to stay as directly as possible above the target. The drone tracked the marker using its front camera. Its movement was controlled by PID controllers. We conducted three experiments to evaluate the system. First we evaluated how accurate our method of determining the drone's height was, compared to its default method. Then how accurately and robustly the drone can hover over a stationary target. Lastly, we evaluated the accuracy and robustness of the drone hovering over a moving target. The results show that our system allows the drone to hover much more reliably over the marker, compared to its default stabilization methods. The system also provides a better means of estimating the distance of the drone from the marker, compared to the built-in sonar.

Keywords:quadcopter, ROS, marker, camera calibration, edge following, Ramer-Douglas-Peucker algorithm, PID controller, computer science, computer and information science, diploma

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back