Sirvi Autor "Paat, Rainer, juhendaja" järgi

Nüüd näidatakse 1 - 3 3

Kaugjuhitavate mudelautode videoülekande VR lahendus
(Tartu Ülikool, 2021) Lättekivi, Mait; Tunnel, Raimond-Hendrik, juhendaja; Paat, Rainer, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
In cooperation with RCSnail OÜ, a virtual reality solution was created of remote-controlled racing cars, which will hopefully become one of the company's services in the future. Using the created solution one can drive remote control cars using a virtual reality headset. The thesis also compares technologies and explains why alternatives were not selected. Framework A-Frame was used in creating this thesis.
Prototype for Indoor Air Quality Monitoring
(Tartu Ülikool, 2020) Valancauskaite, Rimante; Peets, Alo, juhendaja; Paat, Rainer, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
The purpose of this thesis is to analyse data reliability collected by do-it-yourself indoor air quality monitoring solution and give a comparison overview with a commercial off-the-shelf product called “Smart Home Weather Station” by Netamo. As a result of this thesis a prototype was constructed that was able to collect and store real time readings of temperature, humidity, CO2 and air pressure. The prototype used ESP32 microcontroller together with 2 additional sensors SCD30 and BMP280. All data was stored in a cloud-based database using MQTT bridge for connection. Measured readings resembled reference data gathered by Netamo and despite minor offsets in the data the prototype was concluded reliable
Sample-efficient Online Learning in a Physical Environment
(Tartu Ülikool, 2020) Liivak, Martin; Matiisen, Tambet, juhendaja; Paat, Rainer, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Autonomous driving has been seen as the next breakthrough in transportation. Autonomous vehicles employ a variety of sensors to understand their surroundings, for example multiple cameras, ultrasound sensors, and LiDARs. In this work, a much smaller scale radio-controlled cars, that only carry a central camera, are used. Their effectiveness as a test-bed for validating autonomous driving methods is evaluated. Multiple neural network architectures were proposed, among which a convolutional neural network was selected as the best candidate. The network was then trained using both supervised learning and online learning, the results of which were then compared. Experiments show that online learning in a physical environment, while costly, is a significant improvement over pure supervised learning. Additionally the radio-controlled cars proved to be a good comparative test-bed for evaluating model performance in an interactive physical environment.