|
|
3D Mapping from Sparse LiDAR Data
Veľas, Martin ; Hofierka,, Jaroslav (referee) ; Kaartinen,, Harri (referee) ; Herout, Adam (advisor)
Tato práce se zabývá návrhem nových algoritmů pro zpracování řídkých 3D dat senzorů LiDAR, včetně kompletního návrhu batohovího mobilního mapovacího řešení. Tento výzkum byl motivován potřebou takových řešení v oblasti geodézie, mobilního průzkumu a výstavby. Nejprve je prezentován iterační algoritmus pro spolehlivou registraci mračen bodů a odhad odometrie z měření 3D LiDARu. Problém řídkosti a velikosti těchto dat je řešen pomocí náhodného vzorkování pomocí Collar Line Segments (CLS). Vyhodnocení na standardní datové sadě KITTI ukázalo vynikající přesnost oproti známému algoritmu General ICP. Konvoluční neuronové sítě hrají důležitou roli ve druhé metodě odhadu odometrie, která zpracovává kódovaná data LiDARu do 2D matic. Metoda je schopna online výkonu, zatímco je zachována přesnost, když požadujeme pouze parametry posunu. To může být užitečné v situacích, kdy je vyžadován online náhled mapování a parametry rotace mohou být spolehlivě poskytnuty např. senzorem IMU. Na základě algoritmu CLS bylo navrženo a implementováno batohové mobilní mapovací řešení 4RECON. S využitím kalibrovaného a synchronizovaného páru LiDARů Velodyne a s nasazením řešení GNSS/INS s duální anténou, byl vyvinut univerzální systém poskytující přesné 3D modelování malých vnitřních i velkých otevřených prostředí. Naše hodnocení prokázalo, že požadavky stanovené pro tento systém byly splněny -- relativní přesnost do $5$~cm a průměrná chyba georeferencí pod $12$~cm. Poslední stránky obsahují popis a vyhodnocení další metody založené na konvolučních neuronových sítích -- navržených pro segmentaci země v mračnech bodů 3D LiDARu. Tato metoda překonala současný stav techniky v této oblasti a představuje způsob, jakým může být sémantická informace vložena do 3D laserových dat.
|
|
|
Analysis of AHRS unit robustness
Honkyš, Pavel ; Králík, Jan (referee) ; Spáčil, Tomáš (advisor)
This work deals with the measurement of low cost MEMS sensors and their measurement inaccuracy caused by acceleration, this effect is described as G-sensitivity. The aim was to put the test station into operation, to design electronics containing a microcontroller, which sends the measured information to a computer using a wireless module, here to estimate the angle of rotation of the sensor using a suitable algorithm and to design a compensation algorithm to suppress the effect of acceleration. The measured data were processed using Madgwick's algorithm, where the error of the measured angle of rotation occurred during the action of acceleration.
|
|
|
Trilobot Upgrade
Polášek, Patrik ; Hrubý, Martin (referee) ; Rozman, Jaroslav (advisor)
The main aim of this work is to create a robot moving on wheels, create communication among all the sensors and microcomputers with the help of the Robot Operating System (ROS). Sensors are mounted on a plastic handle that is printed on 3D printer. The Arduino microcomputer manages low-level signals for reading sensor data and signals to control the engine, the another one and more powerful ODROID-XU4 microcomputer runs the core of ROS and a graphical application that allows controlling robot on the touchscreen.
|
|
| |
|
|
Utilization of Motion Sensor Data for User Activity Analysis
Eršek, Martin ; Zemčík, Pavel (referee) ; Beran, Vítězslav (advisor)
This bachelor thesis aims to provide a design and implementation of an algorithm for analysis of user activity based on data from motion sensors. The thesis explores possibilities of classification and counting repetitions of 7 basic body-weight exercises, namely: push ups, squats, planks, sit-ups, seated knee raises, tricep dips and lunges. Data from motion sensors are collected by a mobile device located in top pocket of exercising user's trousers. Selection of used methods and their parameters as well as number and type of extracted features is chosen with regard to low computational complexity. When designing a solution, emphasis was put on the fact that it is irrelevant how the device is positioned in the user's pocket. For the thesis, a dataset containing 7 training sessions from 4 different users was created. Designed method was implemented as a desktop application with Command Line Interface and consequently validated on the created dataset. The solution was able to reach metrics of F1-score in range 45.3 % - 74.9 % for analysis and counting repetitions of an unseen user's training session. For an unseen training session of a known user, the metrics of F1-score was up to 94 %.
|
|
|
Telemetry System For Rc Airplane With Navigation
Orolin, Jakub
This project is focused on design of telemetric system for radio controlled aircraft. The output of the system will be relevant flight data such as velocity, altitude, direction of flight, rotation or geographical position on the map. Furthermore, the system will be able to check all internal board status parameters. All these parameters will be displayed in real time in the receiving station, which will include voice navigation for landing. Another part of the receiving station will be flight recorder or a database used for registration of particular information and post- flight analysis.
|
|
|
Collision Avoidance For Ateros Robotic System
Ligocki, Adam
This paper describes the details of a collision avoidance algorithm for an ATEROS robotic system. The solution, developed and tested on the Orpheus robotic platform is based on a Velodyne HDL-32E laser scanner. The LiDAR point cloud input data are filtered to remove data redundancy and clustered to separate possible collision objects from the background. Based on prior environment knowledge and the current LiDAR scan, the surrounding occupancy grid map is estimated, and the planned path is validated against possible collision. In the case of a non-zero probability that the robot collides with an obstacle, a new path is proposed by the A* algorithm. Subsequently, the newly estimated waypoints are relaxed, and the mission plan is updated.
|
|
|
Data Acquisition Sensory Framework For
Autonomous Robots
Ligocki, Adam
In this paper there are described the basic hardware idea of complex sensory framework design and construction. This framework will be used to develop high bandwidth data acquisition system in the first phase and lately to use collected data to propose highly antonomous algorithms for field-operating robots. Entire system is divided into four parts. The scalable sensory cluster with highly modular architecture which allows to connect practically arbitrary number of sensing devices, the data acquisition unit, high computational power computer which aggregates all sensor data, preprocess them and storage them in database to provide future access and usage for following applications. The third part is interconnecting network, which provides high bandwidth communication channels to exchange data between sensors and central computer. The last part is battery-based power supply system designed to fulfill 500W energy requirements of entire mobile framework system.
|
|
| |
|
|
Determining of Dron Localization Using Navigation Systems
Nosál, Jan ; Goldmann, Tomáš (referee) ; Drahanský, Martin (advisor)
The thesis describes problems of drone navigation using navigation systems with which the navigation modules that have been tested are able to work. Next the issue with flight path and the determination of the incline and direction of the flight of the drones was solved also. Drones are more and more popular devices used for military, agricultural and commercial purposes. The thesis contains information about most used navigation systems which we encounter every day especially in cars and aircrafts. There were tested two navigation modules for drone localization. Modules capable of handling five navigation systems GPS, Glonass, Galileo, Beidou, QZSS and they can communicate with the Arduino board and IMU controller for drone positioning.
|
guest ::
