National Repository of Grey Literature 121 records found  beginprevious36 - 45nextend  jump to record: Search took 0.00 seconds. 
Robotic Shopping Cart
Kuřátko, Jiří ; Beran, Vítězslav (referee) ; Materna, Zdeněk (advisor)
This bachelor’s thesis deals with the project of application about planning the robot’s movement in order to follow the specified person. At the beginning of the work, the Microsoft Kinect sensor which is used for sensing nearby objects is described. Hereinafter the possible methods how to identify human figures on the basis of depth data from the Microsoft Kinect sensor are discussed as well. The reader is also familiar with the methods determining the direction of arrival of acoustic signals. Last chapters of the work are dedicated to the motion control of the robot. Finally the complete implementation of the robot software for the platform of Robotic Operating System (ROS) is described.
Doors Opening for PR2
Senčuch, Daniel ; Materna, Zdeněk (referee) ; Kapinus, Michal (advisor)
This thesis aims to explore possibilities of door opening by the PR2 robotic platform based on information about the location and properties of the doors. This information must be obtained from another program that follows the protocol designed in this thesis. This thesis' effort should then produce a working program for the Robotic Operating System which - when run on the PR2 - is able to at least open doors in the direction from the robot and get the robot through them. The result has been successfully tested on the doors to the faculty robotic laboratory.
Dataset Annotator for Neural Network Training
Schneider, Martin ; Materna, Zdeněk (referee) ; Beran, Vítězslav (advisor)
The goal of this thesis is design and implementation of a system for image data annotation which will learn neural networks. An important feature of this system is the iterative approach of learning, where the annotated set is extended by the neural network itself and users make corrections of these extensions. The system consists of an information system with an embedded annotation tool. Information system communicates with neural network management program. The information system is designed according to the MVC architectural model. The frontend of the application is built on JavaScript library - React and is designed according to Material Design conventions using the Material-UI framework. The frontend maintains a permanent connection to the Python backend using the WebSocket protocol, which is also used by the backend to communicate with the neural network management program. The NoSQL database system uses MongoDB technology. 
Fear Factor of Gaming Artificial Intelligence
Mištík, Matej ; Materna, Zdeněk (referee) ; Chlubna, Tomáš (advisor)
The goal of this thesis is to present the fear factor by gaming artificial intelligence. The work focuses on the player's interaction with artificial intelligence, whose fear factor is addressed by evaluating complex conditions and the subsequent selection of the state of behaviour. The created system works for combat and escape of artificial intelligence. The outcome of this thesis is the implementation of human emotion, mainly the fear for gaming artificial intelligence in the enviroment of Unity engine.
Diagnostics of a Mobile Robot
Benček, Vladimír ; Beran, Vítězslav (referee) ; Materna, Zdeněk (advisor)
Early diagnostics and prediction of future conditions of robotic systems can minimize the costs for their maintenance. This thesis is focused on diagnostics and monitoring of monile robot TB2. It includes familiarisation with the robot, its operating system and describes the design and implementation of the diagnostic package, that analyses different robot parts and provides the information about them to the user.
Smart Home: Learning Control of Heating
Milostný, Tomáš ; Bažout, David (referee) ; Materna, Zdeněk (advisor)
This bachelor thesis deals with the implementation of a prototype smart home ecosystem focused on home heating. The goal is to create software running on a Raspberry Pi device that, with the help of machine learning predictions, will be able to control and monitor a network of electric direct heating convectors controlled by switching a simple Wi-Fi relay Shelly 1PM. The resulting solution should also have a lower price than conventional smart thermostats.
Smart Home: Digital Thermostatic Valve Controlled via WiFi
Smejkal, Jan ; Kapinus, Michal (referee) ; Materna, Zdeněk (advisor)
This bachelor thesis deals with smart home heating in households with radiators. The goal is to design a cheap digital heating head and to integrate it via WiFi and MQTT into the Home Assistant system. I have focused on keeping good design, head functions and a good user experience. Home Assistant enables showing graphs using InfluxDB and Grafana. Using a program in tool Node-RED enables it to lower heating temperature at the times of user absence and to schedule heating temperatures. The price of the complete unit is under 400 CZK. Temperature regulation was provided by a prediction controller, but it was replaced by a PID controller. The controller can regulate with the difference of maximal and minimal temperature of around 2 C. The user can control the boost mode of the head via a physical button or using the Home Assistant system. The resulting product is a good basis for a low-cost smart heating system. 
Automatic Text Recognition for Robots
Hartman, Zdeněk ; Materna, Zdeněk (referee) ; Španěl, Michal (advisor)
This bachelor thesis describe module design for text detection and recognition for use in robotic systems. To detect charters is used Stroke Width transform, which is applied on the input edge image. In the output image after Stroke Width transform are found connected components. For letter grouping into a words is used Hough transform, which is applied on the created binary image. This image contains points, which corresponding positions of found connected components. To recognize signs in detected areas is used Tesseract library. Before recognition detected areas are extracted and rotated into a horizontal position. This proposed detector can detect even rotated text.  Accuracy of detection of the text is 75% above the test set "informační tabule".
Interaction Methods for Advanced Control of a Robotic Arm
Vida, Juraj ; Kapinus, Michal (referee) ; Materna, Zdeněk (advisor)
The purpose of this thesis is to extend the functionality of ARTable system, which is based on principles of simplified robot programming. These principles aim to simplify the human-robot interaction. The new instruction is added, which enables to teach the robot to place objects of the same type into a grid, for example a box. This instruction consists of two parts: (i) the extension of GUI, and (ii) the extension of the robot functionality. These extensions are implemented in Python using Qt framework, The Robot Operating System (ROS) and MoveIt! framework. The extension of ARTable is fully functional assuming that grasps are generated only on the y axis sides.
User Interface for Autopilot of Quadcopter
Klein, Ondřej ; Materna, Zdeněk (referee) ; Beran, Vítězslav (advisor)
Bachelor's thesis describes the design and implementation of user interface for autopilot of quadcopter. Controlling the quadcopter is done via tablet computer. It provides manual and semi-autonomous mode and the option to control quadcopter by virtual joysticks or device movement. Part of the thesis is detailed analysis of quadcopter's abilities and description of existing solutions, which serves as a basis for the design of the application. The final program is tested and the results are evaluated.

National Repository of Grey Literature : 121 records found   beginprevious36 - 45nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.