|
|
Vývoj v oblasti elektronických systémů automobilů a jejich diagnostika
Šenk, Vladislav
The topic of this bachelor's thesis is the development in the field of electronic systems and their diagnostics. In the first part, the work is focused on ADAS assistance systems, where individual sensors used by assistance systems are described. Furthermore, their basic division is presented here, followed by a description of the individual assistance systems. The following section is focused on the occurrence of artificial intelligence in automobiles. Definitions, development and learning strategies are provided here. Diagnostic systems are presented in the third chapter. The chapter ends with the application of artificial intelligence as a diagnostic system. The next chapter describes the electrical installation and describes the types of wiring systems. The last chapter is devoted to autonomous systems, whether they are in use today or systems that have their own text summaries but the technology for them has not been developed. This chapter also covers environmental and driver monitoring and achieving minimal risk.
|
|
|
Autonomous driving concept for Formula Student
Pavel, Matěj ; Štětina, Josef (referee) ; Porteš, Petr (advisor)
The goal of the paper is to propose a new iteration of TU Brno Racing’s autonomous driving system. It first concerns itself with a general overview of autonomous vehicles and the rules of the Formula Student competition and an analysis of the current solution, with discussion of its flaws. Next, a solution is proposed to one of those flaws – vehicle localization utilizing an Extended Kalman Filter (EKF) for sensor fusion. Necessary filtering and transformations of the data are discussed. Finally, the paper contains a choice of sensors potentially useful for further increases in accuracy of the localization system.
|
|
|
Self Driving of Car Model in Unknown Environment Using SLAM
Jahn, Filip ; Bidlo, Michal (referee) ; Strnadel, Josef (advisor)
This thesis aims to build a model of a vehicle that will be able to autonomously navigate in the environment while mapping its surroundings. Another goal of the work was to understand embedded systems and their development in more detail, and therefore the programming was deliberately implemented at the hardware level (bare metal) without the use of an operating system or other existing solutions. From the SLAM techniques, a grid-based method was chosen, which uses a grid as the basic spatial representation of the environment. In this method, sensors are used to measure the distance and determine the position of the robot in a given space. This information is then processed and used to create a map of the environment, which the robot uses to orient and move through the space. After traversing a previously unknown path, the robot builds a map of the space and saves it as an excel file on an SD card to make the map easy to read. The contribution of this thesis is the detailed description of each component used. The work was written from the beginning so that the individual modules are independently functional. This created libraries that when inserted into the project will be fully functional.
|
|
|
Fuzzy decision models
Starý, Josef ; Karpíšek, Zdeněk (referee) ; Žák, Libor (advisor)
This master's thesis is focused on fuzzy decision-making using fuzzy inference systems. In the first part, the math theory necessary in this field is described. The main objective of the thesis is to create a fuzzy inference system with adaptive cruise control function. Mathematical software MATLAB is used to accomplish this goal. The system evalutes situations and decides on the vehicle's response based on input variables such as the vehicles's speed, the speed of the previous vehicle, and the distance between vehicles. Its functionality is tested in this thesis using simulations of fictional scenarios, and then the system is compared to real adaptive cruise control systems using real data.
|
|
|
Computational model of the environment of an autonomous vehicle
Doležel, Radek ; Píštěk, Václav (referee) ; Kučera, Pavel (advisor)
The aim of this thesis is to develop a functional computational model for vehicle motion prediction based on a search of sensors and their locations on the vehicle, neural networks for computer vision, datasets for network learning, and programs for creating simulations and virtual environments. The paper describes the process of creating the vehicle virtual environment and simulation. In addition, sensor placement designs including their parameters are developed. Subsequently, the programmed vehicle trajectory prediction algorithm including learning and neural network implementation is presented. Finally, the results of the developed algorithm are presented.
|
|
|
Using Synthetic Data for Improving Detection of Cyclists and Pedestrians in Autonomous Driving
Kopčilová, Zuzana ; Musil, Petr (referee) ; Smrž, Pavel (advisor)
This thesis deals with creating a synthetic dataset for autonomous driving and the possibility of using it to improve the results of vulnerable traffic participants' detection. Existing works in this area either do not disclose the dataset creation process or are unsuitable for 3D object detection. Specific steps to create a synthetic dataset are proposed in this work, and the obtained samples are validated by visualization. In the experiments, the samples are then used to train the object detection model VoxelNet.
|
|
|
Automatic detection of driving lanes geometry based on aerial images and existing spatial data
Růžička, Jakub
The aim of the thesis is to develop a method to identify driving lanes based on aerial images and existing spatial data. The proposed method uses up to date available data in which it identifies road surface marking (RSM). Polygons classified as RSM are further processed to obtain their vector line representation as the first partial result. While processing RSM vectors further, borders of driving lanes are modelled as the second partial result. Furthermore, attempts were done to be able to automatically distinguish between solid and broken lines for a higher amount of information contained in the resulting dataset. Proposed algorithms were tested in 20 case study areas and results are presented further in this thesis. The overall correctness as well as the positional accuracy proves effectivity of the method. However, several shortcomings were identified and are discussed as well as possible solutions for them are suggested. The text is accompanied by more than 70 figures to offer a clear perspective on the topic. The thesis is organised as follows: First, Introduction and Literature review are presented including the problem background, author's motivation, state of the art and contribution of the thesis. Secondly, technical and legal requirements of RSM are presented as well as theoretical concepts and...
|
|
|
Mobile platform for testing autonomous vehicle sensors
Valla, Tomáš ; Ramík, Pavel (referee) ; Štětina, Josef (advisor)
The aim of this diploma thesis is to create a design of a mobile platform. The platform contains all the necessary electronics from conventional RC models and thus the RC control itself is guaranteed. It is also equipped with a light but solid platform, which is suitable for attaching the necessary sensors, lidars, cameras and other necessary accessories. Part of the work is also a brief overview of the division of RC models and evaluation of the components used for possible construction of the model. The final chapter is devoted to FEM analysis, where the load-bearing capacity of the platform under different load models is checked by means of structural analysis. Using modal analysis, the platform's own critical frequencies were determined and compared to the frequencies that are transmitted when driving on the road.
|
|
|
Neural Networks for Autonomous Car Driving
Dopita, Marek ; Hradiš, Michal (referee) ; Smrž, Pavel (advisor)
In this work, the principles of neural networks are introduced with a focus on autonomous vehicles. Based on this information, a proposal for the implementation of a system is created, which allows to drive a car without a driver. It builds on tools that allow easy creation and testing of autonomous vehicles. It is CARLA simulator and ranking.The proposal divides vehicle routes into three different situations. Each situation requires the use of different sensors, so a specific autonomous agent is created that is able to recognize the situation and switch between different neural network designs. Each such network is specific in its inputs and is taught in a specific situation.Programs are created that are able to easily collect a data set using the CARLA Leaderboard. Then, a way is introduced to how the collected data can be divided into categories so that each category can be used to learn its neural network.
|
|
| |
guest ::
