|
|
Vehicle Control via Reinforcement Learning
Maslowski, Petr ; Uhlíř, Václav (referee) ; Šůstek, Martin (advisor)
The goal of this thesis is a creation of an autonomous agent that can control a vehicle. The agent utilizes reinforcement learning that uses neural networks. The agent interprets images from the front vehicle camera and selects appropriate actions to control the vehicle. I designed and created reward functions and then experimented with hyperparameters setup. Trained agent simulate driving on the road. The result of this thesis shows a possible approach to control an autonomous vehicle agent using machine learning method in CARLA simulator.
|
|
|
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.
|
|
|
Design of a simulation environment for testing the operation of autonomous vehicles
Šůstek, Jan ; Krejsa, Jiří (referee) ; Věchet, Stanislav (advisor)
This thesis deals with the design of simulation environment for testing autonomous vehicles. In the theoretical part, the search of available autonomous driving simulators was carried out. Furthermore, the tools commonly used in autonomous vehicles such as sensors or software modules were presented. In the practical part, the CARLA simulator was selected from the available solutions. Firstly, the installation of CARLA simulator is explained. Then, the simulation map was created by the Roadrunner to simulate a specific street in Brno. Afterwards, the work with the CARLA simulator is shown. Finally, the work with the CARLA simulator is evaluated and the concrete outputs of simulation are shown.
|
|
|
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.
|
|
|
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.
|
|
|
Vehicle Control via Reinforcement Learning
Maslowski, Petr ; Uhlíř, Václav (referee) ; Šůstek, Martin (advisor)
The goal of this thesis is a creation of an autonomous agent that can control a vehicle. The agent utilizes reinforcement learning that uses neural networks. The agent interprets images from the front vehicle camera and selects appropriate actions to control the vehicle. I designed and created reward functions and then experimented with hyperparameters setup. Trained agent simulate driving on the road. The result of this thesis shows a possible approach to control an autonomous vehicle agent using machine learning method in CARLA simulator.
|
guest ::
