This thesis deals with robot modelling and simulation of the robot behavior. At first we discuss a benefit of this kind of simulation. Next we describe the general scheme of robot. After that we select the environment where robot will be simulated in. There is a conception of this robot and explanation of the implementation in chosen environment. We continue with design and realization of the communication interface of this robot. The result of this procedure is robot with independent movement able to response to the obstructions and avoid them. Robot is able to create a map of the environment and use this map to find out the optimal way to the scheduled goal using the A* algorithm and achieve this goal. There is a possibility to use more robots in the scene. These communicate and the nearest one is able to get the goal.

This study is concerned with digital two-dimensional rivers for games. Specifically the aim is to create a river shape from the basis of a spline curve and make it look like a river with a water flow-rate. This is achieved by developing an artifact capable of river simulations in 2D, with the flow-rate calculated using the necessary hydraulics equations. The scientific process described in Design Science Research Methodology for Information Systems Research is presented and followed. Artifact simulations are demonstrated and evaluated, especially calculations for river mean velocity and discharge are shown to be possible by assuming that the river channel is of trapezoidal shape. Simulations show a type of river not usually seen in games, a river with more accuracy than other game simulations. The artifact river simulations are however limited by a missing smoothness when going between different channel shapes. Also there could be a way of improving the texture used, or possibly use more then one texture in one simulation. The conclusion is that the methods used for river generation by this study could be part of a design tool that targets 2D games.

Master´s thesis deals with creation of digitalized cadastral map in cadastral district Šošůvka. Analog maps in the old cadastral scale 1 : 2880 in the urban part of cadastral territory is revised. Externals was revised on the basis of comprehensive landscaping to digital cadastral map. Creation of digitalized is processed according to the current Instructions for Reconstruction cadastral including both amendments. The first part is devoted to the theory of cadastral and development and course of digitization. The main part of the thesis consists of the processing of the measured data and provided data by land registry.

Autonomous driving is an emerging area that has been receiving an increasing amount of interest from different companies and researchers. 3D point cloud map is a significant foundation of autonomous driving as it provides essential information for localization and environment perception. However, when trying to gather road information for map creation, the presence of dynamic objects like vehicles, pedestrians, and cyclists will add noise and unnecessary information to the final map. In order to solve the problem, this thesis presents a novel two-stage model that contains a scan-to-scan removal stage and a scan-to-map generation stage. By designing the new three-branch neural network and new attention-based fusion block, the scan-to-scan part achieves a higher mean Intersection-over-Union (mIoU) score. By improving the ground plane estimation, the scan-to-map part can preserve more static points while removing a large number of dynamic points. The test on SemanticKITTI dataset and Scania dataset shows our two-stage model outperforms other baselines. / Autonom körning är ett nytt område som har fått ett allt större intresse från olika företag och forskare. Kartor med 3D-punktmoln är en viktig grund för autonom körning eftersom de ger viktig information för lokalisering och miljöuppfattning. När man försöker samla in väginformation för kartframställning kommer dock närvaron av dynamiska objekt som fordon, fotgängare och cyklister att lägga till brus och onödig information till den slutliga kartan. För att lösa problemet presenteras i den här avhandlingen en ny tvåstegsmodell som innehåller ett steg för borttagning av skanningar och ett steg för generering av skanningar och kartor. Genom att utforma det nya neurala nätverket med tre grenar och det nya uppmärksamhetsbaserade fusionsblocket uppnår scan-to-scan-delen högre mean Intersection-over-Union (mIoU)-poäng. Genom att förbättra uppskattningen av markplanet kan skanning-till-kartor-delen bevara fler statiska punkter samtidigt som ett stort antal dynamiska punkter avlägsnas. Testet av SemanticKITTI-dataset och Scania-dataset visar att vår tvåstegsmodell överträffar andra baslinjer.