|
|
Mobilní kamera realizovaná prostředky ROS2
Onderka, Daniel ; Peringer, Petr (referee) ; Janoušek, Vladimír (advisor)
This thesis focuses on the middleware Robot Operating System 2. Specifically, it aims to explore and demonstrate its capabilities. It utilizes an Adeept AWR 4WD robot as the foundational hardware platform, onto which the ROS2 system is deployed. The system offers both manual control and a wandering mode equipped with obstacle avoidance functionality. In addition to its primary goal, the thesis explores various related subjects. One of them is the integration of the developed system with the Gazebo simulator. All functionality implemented on the real physical robot has been duplicated in the simulation environment. Furthermore, the original Adeept AWR kit was extended with additional hardware. This extension allowed for the use of slam_toolbox and Nav2 libraries for mapping and navigation purposes. The final extension involves the use of ros2_control for controlling robot motion.
|
|
|
Aplikace posilovaného učení v řízení Smart Home
Biel, Gabriel ; Zbořil, František (referee) ; Janoušek, Vladimír (advisor)
Táto práca skúma, ako môže strojové učenie zlepšiť riadenie inteligentných domácností s dôrazom na optimalizáciu riadenia teploty a zvýšenie energetickej účinnosti. Konkrétne sa porovnávajú dva pokročilé algoritmy posilňovaného učenia, Deep Q-Learning (DQL) a Proximal Policy Optimization (PPO). Tieto modely sú testované v simulovanom prostredí, ktoré napodobňuje reálne podmienky, aby sa zhodnotila ich schopnosť prispôsobiť sa správaniam užívateľov a zmenám v prostredí. Ukázalo sa, že model PPO je obzvlášť účinný vďaka svojej stabilite a schopnosti predpovedať návrat obyvateľov. Tento výskum ponúka cenné poznatky o praktických aplikáciách AI technológií v inteligentných domácnostiach.
|
|
|
Practical Aspects of Reducing Technical Debt in Software Products
Hricovová, Alžbeta ; Janoušek, Vladimír (referee) ; Kočí, Radek (advisor)
This thesis focuses on practical aspects of reducing technical debt in software products, focusing on testing, refactoring, and continuous integration. Technical debt arises from compromises made during software development and, if unaddressed, can negatively impact the product and the company developing it. One of the solutions to reduce technical debt is continuous refactoring and code maintenance. This work describes identified violations of good object-oriented programming principles in the selected product and procedures applied to the product to mitigate the impact of its technical debt.
|
|
|
Automatická tvorba diagramů časování
Dítě, Jindřich ; Janoušek, Vladimír (referee) ; Kočí, Radek (advisor)
This works topic is the creation of a tool which could be usable for automatic generation of clocking diagrams based on its structural description, and exporting it to a format usable for further manual editing. This aims to ease one of internal development processes in the company NXP. The created application can successfully import the diagram layout from the structural description, unsuccesfuly tries to apply an automatic graph layout algorithm, and exports the resulting diagram in the format specified by the TinyCAD application.
|
|
|
Lokalizace na bázi Bluetooth
Machyňák, Augustin ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
The thesis deals with the development of a device localization system using ESP. The system uses signal strength information to estimate the distance and then uses multilateration techniques to estimate device positions. To obtain the relative positions of the receivers it also uses signal strength, making it very user friendly to setup and configure. The resulting positions are either processed on the ESP itself with simple visualization or it is possible to use an external server implementation to process them with historical data and a more suitable visualisation of the positions. However, the accuracy is not satisfactory and only suggests the use of map generating techniques for each specific environment using which to determine, what combinations of received signal strength values correspond to each position is a more appropriate method for localization.
|
|
|
Object Detection on the i.MX RT Microcontroller
Kravchuk, Marina ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
This work focuses on the use of machine learning, particularly convolutional neural networks, in industrial applications. The course of work involves investigating the implementation of these networks directly on embedded devices, specifically NXP i.MX RT microcontrollers. During the course of the study, materials related to the training and use of neural networks and their optimization for deployment on low power devices were reviewed. Several neural network models were trained and tested, the best of which was used in the final version of the application. The application itself is divided into two parts: one part is written in C/C++ in the MCUXpresso IDE, where the main functionality of the program is implemented, while the other part of the work, i.e. the creation of a graphical user interface to control the program, is done in Python. The result is a functional application for the MIMXRT1170-EVK microcontroller that is able to detect and recognize small colored objects of certain shapes from a predefined data set.
|
|
|
Hexapod Robot Movement Control
Kocich, Martin ; Janoušek, Vladimír (referee) ; Rozman, Jaroslav (advisor)
At the beginning of the research, the skeleton of the hexapod robot was equipped with servomotors only and no control unit or sensors. The objective of this thesis is to develop an overall solution for the control of the robot in question. Furthermore, to create a graphical interface to control and monitor the robot using Qt environment. Raspberry Pi 4 and ROS software running on operational system Ubuntu 20.04 was chosen to control the hexapod. While researching available software options, an existing solution was found. This solution was extended with feedback from the servo motors and the control algorithms were modified. Furthermore, new hardware was tested, e.g.: cameras with depth sensing capability. The found solution is extended e.g. with additional motion modes, graphical interface, support for new hardware, updates to the outdated version of ROS and its components. All problems during the implementation of the solution have been sufficiently solved. This thesis walks through the entire research process and then breaks down the commissioning of the robot from skeleton to working solution.
|
|
|
Garbage Collector for PNtalk Objects
Štěpán, Filip ; Janoušek, Vladimír (referee) ; Kočí, Radek (advisor)
Tato práce představuje komplexní výzkum technik garbage collection přizpůsobených speciálně pro PNtalk se zaměřením na použití standardní automatické správy paměti. Tato práce zkoumá nutnost, principy a výhody automatické správy paměti a zdůrazňuje význam al- goritmů garbage collection pro optimalizaci využití paměti a zvýšení výkonu aplikací. Na základě těchto teoretických základů se práce zabývá návrhem, implementací, testováním a srovnávacím testováním garbage collectoru.
|
|
|
Prostředky pro zajištění interoperability Arduino/ESP a ROS2
Fabo, Matúš ; Beran, Jan (referee) ; Janoušek, Vladimír (advisor)
Táto práca skúma integráciu nízkonákladovej rady mikrokontrolérov ESP32 s Robot Oper- ating System 2 (ROS2), populárnym frameworkom v oblasti robotiky. Primárnym cieľom je vyvinúť metódy a nástroje, ktoré uľahčia bezproblémovú integráciu mikrokontrolérov ESP32 do vývojového ekosystému ROS2 s využitím existujúcich middleware riešení posky- tovaných tretími stranami. Zameraním sa na začlenenie projektov ESP-IDF do nástrojov ROS2 sa výskum zameriava na zefektívnenie nasadenia a riadenia systémov založených na ESP32 v robotických aplikáciách. Tento prístup zvyšuje dostupnosť a užitočnosť ROS2, čo umožňuje efektívnejšie využitie mikrokontrolérov ESP32 v rôznych robotických kontextoch.
|
|
|
Adaptivní systém pro řízení osvětlení ve Smart Home
Valík, Tomáš ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
The thesis deals with the issue of lighting control in smart homes. In most smart homes, it is necessary to manually control the lighting using switches or mobile devices. The thesis introduces an adaptive control system based on recurrent neural networks, which gradually learns user manipulation with the lighting and eventually begins to independently control the lighting after a certain period of time.
|
guest ::
RSS feed.