|
|
Concept design of a multi-environment mobile robot
Zezula, Benjamin ; Burian, František (referee) ; Kopečný, Lukáš (advisor)
This thesis presents the design of a multi-enviroment mobile robot that combines the simple principle of movement both in water and on land. In particular, the design of a~four-wheeled vehicle is presented, whose innovation lies in the use of blades on the rear wheels. A suitable type of propulsion system is chosen based on a~study of~different types of~robots. During the research of already functional solutions, great emphasis is put on the advantages and disadvantages of~the different actuators as well as their mathematical and physical analysis. The proposed solution includes the proven design of four differentially controlled wheels for movement on land and the use of~blades on the rear wheels for movement in water. This concept is described in detail using a~mathematical-physical model, on the basis of~which a~working prototype has been developed. The thesis concludes with an experimental verification of~the agreement between the mathematical model and the real prototype. This verification focuses on the motion dynamics and the behaviour of the robot in different environments. The differences observed are attributed to external influences such as the resistance of the gears or the manufacturing tolerances of the individual components.
|
|
|
Acoustic detection of starlings through artificial intelligence
Zezula, Benjamin ; Vlachová Hutová, Eliška (referee) ; Marcoň, Petr (advisor)
To protect the vineyards from starlings is very costly and ineffective with the available resources over a period of time. In my project, I have designed a detection module that relays information about the flock location in the vineyard to the control module and thus produces scaring. I have designed two kinds of detection modules, which are compared. The first variant consists of a single directional microphone that rotates and sequentially senses the entire area of the vineyard. The second variant consists of four microphones, each one is directed to the cardinal point and based on the intensity of sound, the module will provide the information about the direction where the flock is located. Both detection modules process the signal in a Raspberry Pi 4 single board computer using an artificial neural network algorithm powered by MobileNetV2 architecture.
|
|
|
Acoustic detection of starlings through artificial intelligence
Zezula, Benjamin ; Vlachová Hutová, Eliška (referee) ; Marcoň, Petr (advisor)
To protect the vineyards from starlings is very costly and ineffective with the available resources over a period of time. In my project, I have designed a detection module that relays information about the flock location in the vineyard to the control module and thus produces scaring. I have designed two kinds of detection modules, which are compared. The first variant consists of a single directional microphone that rotates and sequentially senses the entire area of the vineyard. The second variant consists of four microphones, each one is directed to the cardinal point and based on the intensity of sound, the module will provide the information about the direction where the flock is located. Both detection modules process the signal in a Raspberry Pi 4 single board computer using an artificial neural network algorithm powered by MobileNetV2 architecture.
|
guest ::
RSS feed.