Sirvi Autor "Matiisen, Tambet, juhendaja" järgi

Nüüd näidatakse 1 - 20 30

Absoluutne drooni positsioneerimine kasutades aerofotosid
(Tartu Ülikool, 2025) Nepste, Gregor; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Accurate and reliable drone positioning is critical in many domains, including agriculture, search‑and‑rescue, the military, and beyond. Most drones rely primarily on GPS, which can fail in complex environments and is vulnerable to spoofing or jamming in military scenarios. To explore alternative solutions, this project investigates absolute drone positioning methods that use aerial imagery and deep‑learning techniques. Thesis focuses on applying convolutional neural‑network (CNN) architectures for template matching in order to estimate the drone’s position without GPS. The work combines a detailed methodology with experimental validation on city‑scale orthophotos of Tartu provided by the company 3DI. Results demonstrate that deep‑learning approaches achieve ~50-metre‑level accuracy in absolute positioning and show potential for even higher precision in future developments.
Comparing Output Modalities in End-to-End Driving
(Tartu Ülikool, 2022) Aidla, Romet; Matiisen, Tambet, juhendaja; Tampuu, Ardi, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Self-driving car technology has made significant steps in the last ten years with the advancements in neural networks. The first autonomous vehicles are driving in San Francisco and Beijing. One of the promising approaches is end-to-end driving, where a neural network transforms an input image from a camera to output commands to control the vehicle. The most common output modalities are steering angle and trajectory. Both have been extensively benchmarked but not compared in similar settings. Metrics are usually calculated off-policy using a separated test dataset or on-policy using a simulator, but these have proven to correlate weakly with real-life performance. In this thesis, the comparison is made using an autonomous vehicle driving on WRC Rally Estonia tracks. The results show that the trajectory prediction approach is better at road positioning and recovering from non-ideal trajectories, which results in fewer situations where the safety driver has to take over.
Creating High-Definition Vector Maps for Autonomous Driving
(Tartu Ülikool, 2021) Sepp, Edgar; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Autonomous driving holds many promises for transportation - increased safety, lower costs, and less burden to the environment. In light of some recent accidents, it is clear that the technology is not fully ready yet, and the robustness and research in the area need to be increased. Most of the autonomous driving solutions rely on high-definition maps (HD maps) - specialized lane-level maps with very high locational accuracy. Mobile mapping cars (specially equipped vehicles with sensors for map data collection) by big mapping companies are used to collect the data for creating HD maps. Along with required data processing the creating and keeping the HD maps up to date in a changing world is very costly. Availability of the HD maps would considerably lower the bar for adopting autonomous driving at large. To the best of the author’s knowledge, there are no freely available HD maps for self-driving available for Estonia. To be able to conduct research experiments with the University of Tartu's Autonomous Driving Lab (UT ADL) self-driving platform, such maps had to be created. Several available tools for creating the maps and existing data sources were reviewed. The custom workflow was created for mapping and a tool to convert the HD vector map to Autoware vector map format was created. Finally, quantitative measures about time estimates needed to create the HD vector maps and their usage in UT ADL were given.
Creation of Digital Twin for Tartu
(Tartu Ülikool, 2024) Mitt, Allan; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Enne isejuhtiva sõiduki testimist reaalses maailmas on tõhusam katsetada seda simulatsiooni keskkonnas, mis imiteerib pärismaailma. See lõputöö kirjeldab Tartu linna digikaksiku loomist, kasutades avalikke ruumiandmeid ja rakendades erinevaid automatiseerimistehnikaid tööprotsessi kiirendamiseks. Lõpptulemus on ühilduv isejuhtivate sõdukite tarkvaraga ning tartlastele väga äratuntav.
Developing a Volleyball Game with an AI Opponent Using Reinforcement Learning
(Tartu Ülikool, 2021) Marran, Tanel; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
This thesis integrates reinforcement learning into a game development project by creating a competitive volleyball game, where the user can play against an artificial intelligence (AI) trained using reinforcement learning techniques. The work elaborates on what reinforcement learning is, brings forth some of the challenges of adding machine learning to a game, describes the development environment Unity and its machine learning package ML-Agents as well as analyzes the finished game and its AI.
Development and Application of a Program for Traversing Drivable Lanes
(Tartu Ülikool, 2025) Raa, Rauno; Matiisen, Tambet, juhendaja; Sepp, Edgar, juhendaja; Pilve, Karl-Johan, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
The purpose of this thesis is to create a program, which finds the shortest path to traverse all the car-drivable lanes in a given geographical area. Another purpose of the thesis is to apply the program to the cities of Tartu, Tallinn and Helsinki. The program adds the possibility to drive all the given area’s car-drivable lanes with minimal time and fuel costs. Traversing all the area’s car-drivable lanes as optimally as possible is beneficial for creating maps for self-driving cars and for planning the path for snow ploughing and street cleaning. The program was applied to the part of the city of Tartu, part of the city of Tallinn and part of the city of Helsinki. An optimal path, which traverses all the car-drivable lanes, was found for all the aforementioned areas.
Energy-Based Models for End-to-End Autonomous Driving
(Tartu Ülikool, 2022) Baliesnyi, Mykyta; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Energy-based models (EBMs), a promising class of machine learning models, have shown impressive results in several domains, from natural language generation to computer vision. Learning to imitate expert demonstrations using an EBM has recently achieved state-of-the-art results in robotics, made possible by EBMs’ better ability to handle multimodal probability distributions and learn behavior with abrupt command changes. In this work, EBMs are tested for the first time in the end-to-end autonomous driving domain on a real car. As a result, it is discovered that a simple EBM variant performs slightly better and is more stable than a baseline conventional neural network architecture. At the same time, EBMs turn out to exhibit a higher variability of predictions over time, or whiteness. As a solution to this problem, this work introduces a regularization technique that makes the predictions more smooth over time. In addition, an energybased uncertainty metric is proposed, but its usefulness could not be assessed with sufficient reliability due to an insufficient number of real car evaluations. The thesis suggests several ideas for future work, such as using a different sampling method and comparing against mixture density networks.
Eyes Wide Shut: Analyzing Object Detection Performance Under Degraded Sensor Input Scenarios
(Tartu Ülikool, 2025) Ploter, Maksim; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Autonomous Driving Systems (ADS) promise safer roads, better traffic flow, and reduced environmental impact. The Society of Automotive Engineers (SAE) International’s J3016 standard [1] stipulates stringent safety requirements for ADS, particularly concerning their operational behavior during dynamic driving task performance-relevant system failures. The perception task, which includes the fundamental computer vision task of object detection, is a key capability that distinguishes ADS from a “regular” vehicle. In the last decade, there has been remarkable progress in various computer vision tasks, and the object detection task in particular. However, many contemporary state-of-the-art models are specialists, with strong inductive biases for specific data types, making them difficult, if not impossible, to use for ADS. To address this limitation, the thesis introduces two novel recurrent architectures: the Recurrent Perceiver (RPerceiver) and its multi-modal variant, the Recurrent Perceiver Multi-Modal (RPerceiverMM). The efficacy of these architectures was evaluated on a novel benchmark dataset, ”detectionmoving-mnist-easy”, proposed in this thesis. The experimental results suggest the proposed models’ effectiveness in leveraging temporal information, particularly in challenging cases such as objects that are partially visible while leaving the video frame. Furthermore, this research investigated specific training procedures designed to simulate complete sensor failures and non-deterministic data availability. The findings indicate that these proposed training strategies significantly improve model robustness, demonstrating enhanced performance when faced with conditions analogous to real-world ADS sensor system failures. This work contributes to the development of more resilient perception systems crucial for the safe deployment of ADS. The code was open-sourced at GitHub 1.
Georeferenced Visual SLAM
(Tartu Ülikool, 2023) Mägi, Erik; Matiisen, Tambet, juhendaja; Sepp, Edgar, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
This thesis presents a complementary localization solution for taxis and ride-hailing operators in situations where GNSS is unavailable or unreliable. The proposed method leverages monocular visual SLAM techniques, specifically the ORB-SLAM 3 library, to create a map of the environment and localize within it. The system uses a car-mounted camera for image capture and an advanced GNSS receiver to record accurate ground truth. This data is then used as input for training a deep learning model to transform SLAM coordinates into georeferenced coordinates. The thesis explores different approaches to solving the coordinate transformation problem, including linear transformation, machine learning regression algorithms, and deep learning with neural networks. Results show that the deep learning based approach provides the best localization accuracy, surpassing that of modern smartphone GNSS. The study contributes a practical solution for real-time localization for ride-hailing operators when GNSS is compromised, with the potential for future implementation using smartphone cameras.
In Search of the Best Activation Function
(Tartu Ülikool, 2022) Liibert, Marti Ingmar; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
The choice of an activation function in neural networks can have great consequences on the performance of the network. Designing and discovering new activation functions that increase the performance or solve problems of existing activation functions is an active research field. In this thesis, a kind of trainable activation function is proposed - a weighted linear combination of activation functions where the weights are normalized using Softmax, inspired by the DARTS network architecture search method. The activation function is applied at the layer, kernel, and neuron levels. Optimizing the activation function weights is done on training loss and validation loss, as was done in DARTS. The activation function here was tested on two simple datasets, sine wave, and spiral datasets, on image classification tasks and on a robotics task. In the case of image classification, on CIFAR10 using the trainable activation function for initial training the accuracy increased 5% over the baseline, on ImageNet the accuracy increased 1% over the baseline. For the robotics task, CartPole, the mean reward increased by 10 points out of a maximum of 200 when using the already learned activation functions in the case of Deep Q-learning. In the case of Proximal Policy Optimization, the mean reward increased by 2 points approximately over the baseline. For future work, more difficult tasks could be explored for robotics tasks and longer initial search could be explored for image classification tasks.
Inimlik kiirus kurvides
(Tartu Ülikool, 2021) Rudi, Eduard; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Bakalaureusetöö eesmärk oli leida võrrand, mille sisendiks on joone kõverus ja tagastab teelõigu kiiruse, mis on konstrueeritud inimese juhtimisandmete põhjal. Töös antakse lühiülevaade tänapäeva isejuhtimisüsteemi tarkvara ehitamise lähenemistest. Samuti tutvustatakse varasemaid uuringuid. Töös kirjeldatakse põhjalikult andmete töötlemisest ning mida nendega tehti. Kirjeldatakse detailselt lahti, kuidas võrrand implementeeriti Autoware’i ja kuidas algoritm arvutab kiirused mingi teekonnale. Lõpuks antakse ülevaade testimise tulemustest.
Lane Centerline Detection from Orthophotos using Transformer Networks
(Tartu Ülikool, 2024) Pilve, Karl-Johan; Matiisen, Tambet, juhendaja; Sepp, Edgar, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Sõiduradade andmeid sisaldav täppiskaart on isejuhtivate sõidukte opereerimisel väga oluline komponent. Samas on täppiskaardi loomine suurema ala kohta sageli ajakulukas ning töömahukas protsess. Hiljuti on transformeri arhitektuuri kasutavad tehisnärvivõrgud näidanud paljulubavaid tulemusi masinnägemise valdkonnas. Üks selline näide on RNGDet, mis genereerib iteratiivselt teedevõrgu graafi aerofotode põhjal. Käesolevas töös uuritakse võimalust peenhäälestada RNGDet mudelit sõiduradade andmetega, et genereerida kogu Tartu linna kattev sõiduradade graaf kasutades kõrge resolutsiooniga ortofotosid. Töös saadud tulemused näitavad, et RNGDeti on põhimõtteliselt võimalik kasutada sõiduradade graafi genereerimiseks. Samas oleks mudeli arhitektuuris vaja tõenäoliselt teha suuremaid muudatusi, et võtta arvesse teedevõrgu ja sõiduradade andmete vahelisi erinevusi. Kuna ortofotodel ei pruugi alati olla kogu vajaliku informatsioon sõiduradade õigesti genereerimiseks, siis kõige paremaid tulemusi andis mudel, mis kasutas ortofotodele rasterdatud mõõdistussõiduki poolt kogutud töötlemata GPS trajektoore. Saadud tulemused näitavad veel, et täppiskaardi jaoks sobiva kvaliteediga sõiduradade genereerimiseks oleks vaja koguda täiendavaid treeningandmeid.
Learning Competitive Minecraft Minigames with Reinforcement Learning
(Tartu Ülikool, 2022) Sisask, Laur; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
In recent years, deep reinforcement learning methods have successfully been used to play complex games like Go, StarCraft II, and Dota 2 at a professional level. In this thesis, reinforcement learning methods are used to train artificial agents in the game of Minecraft. Various competitive 1v1 Minecraft minigames from one of the most popular Minecraft servers Hypixel are selected. Deep neural networks are trained to play each of these games using proximal policy optimization algorithms and self-play. In all the games, artificial agents were able to play the game at least on a beginner level. In one game, the agent reached the level of expert human players.
Navigatsioonirakenduse sisendi renderdamine autot juhtivale närvivõrgule
(Tartu Ülikool, 2021) Maks, Erik Marcus; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
This thesis describes the making of a navigation application that can be used as an input for a neural network. The application will receive GPS coordinates and will render step-by-step directions on screen. This rendering will be used together with camera images as an input for the neural network.
Navigeerimine välistingimustes mudelautoga
(Tartu Ülikool, 2025) Kahju, Kennar; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
The development of autonomous vehicles is primarily focused on cars operating on roads. The goal of this bachelor’s thesis was to develop a vehicle to navigate in off-road environments. The Donkey Car S1 platform was used as a base, to which custom-designed and 3D-printed frames were added to mount a GNSS device and a LiDAR sensor. Necessary functionality was developed to the Donkey Car project to enable waypoint-based navigation. To evaluate the self-driving capability, various tests were conducted both on asphalt and in a park environment. Navigation between waypoints was successful, even when the waypoint was behind the car. Both GNSS and LiDAR worked as expected, with the GNSS evaluated to the accuracy of 2 cm and LiDAR achieving a measurement accuracy within 5 cm. However, obstacle avoidance proved to be ineffective and the possible reasons for this were analyzed. It was also found that the frame of the chosen platform was not suitable for off-road driving. This thesis concludes with recommendations for further development and suggestions for avoiding similar issues in future implementations.
Object Recognition Using a Sparse 3D Camera Point Cloud
(Tartu Ülikool, 2023) Tiirats, Timo; Matiisen, Tambet, juhendaja; Bogdanov, Jan, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
The demand for higher precision and speed of computer vision models is increasing in autonomous driving, robotics, smart city and numerous other applications. In that context, machine learning is gaining increasing attention as it enables a more comprehensive understanding of the environment. More reliable and accurate imaging sensors are needed to maximise the performance of machine learning models. One example of a new sensor is LightCode Photonics’ 3D camera. The thesis presents a study to evaluate the performance of machine learning-based object recognition in an urban environment using a relatively low spatial resolution 3D camera. As the angular resolution of the camera is smaller than in commonly used 3D imaging sensors, using the camera output with already published object recognition models makes the thesis unique and valuable for the company, providing feedback for LightCode Photonics’ current camera specifications for machine learning tasks. Furthermore, the knowledge and materials could be used to develop the company’s object recognition pipeline. During the thesis, a new dataset is generated in CARLA Simulator and annotated, representing the 3D camera in a smart city application. Changes to CARLA Simulator source code were implemented to represent the actual camera closely. The thesis is finished with experiments where PointNet semantic segmentation and PointPillars object detection models are applied to the generated dataset. The generated dataset contained 4599 frames, of which 2816 were decided to use in this thesis. PointNet model applied to the dataset could predict the semantically segmented scene with similar accuracy as in the original paper. A mean accuracy of 44.15% was achieved with PointNet model. On the other hand, PointPillars model was unable to perform on the new dataset.
Optimization of Battery Energy Storage System in the Estonian Energy Markets using Reinforcement Learning
(Tartu Ülikool, 2025) Mykhailenko, Yaroslava; Cabral Pinheiro, Victor Henrique, juhendaja; Matiisen, Tambet, juhendaja; Scellier, Jean-Baptiste, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
The integration of renewable energy sources into electricity markets has increased the need for efficient energy management solutions. Battery Energy Storage Systems (BESS) help balance fluctuating supply and demand by storing excess energy and supplying it during shortages, so determining an optimal charge-discharge schedule becomes a core optimization task for market participants. Currently, Eesti Energia addresses this task with linear optimization techniques that are effective yet limited, because they cannot fully capture nonlinear battery dynamics or adapt to complex market patterns. This thesis explores the potential of model-free reinforcement learning (RL) algorithms, specifically Deep Deterministic Policy Gradient (DDPG) and Proximal Policy Optimization (PPO), to optimize battery trading strategies in Estonia's day-ahead electricity market. The primary objective is to assess whether RL models can potentially surpass traditional linear optimization benchmarks in terms of profitability and decision quality. Results demonstrate that in a six-hour trading horizon the optimized DDPG agent consistently outperformed PPO and closely approached the performance of the linear optimizer, capturing 85.5% of its profit. When extended to a full 24-hour horizon, it relative performance fell to 65%. Qualitative analysis of evaluation logs confirmed market-aware behavior, with the agent charging when prices were low, discharging near peaks, and preserving capacity for anticipated high-price periods. Overall, the findings suggest that, when carefully tuned, model-free RL can provide a competitive alternative to linear optimization for battery trading in volatile electricity markets, with the potential to account for nonlinear battery aging and integrate multi-market signals. This lays the groundwork for future applications in even more dynamic settings such as balancing markets.
Põllukultuuride tuvastamise masinõppe mudeli tunnuste olulisuse hindamine
(Tartu Ülikool, 2021) Järveoja, Mihkel; Voormansik, Kaupo, juhendaja; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Remotely sensed, in particular satellite data, is already widely used in agricultural parcels monitoring, and this trend is not showing signs of diminishing. Wide range of machine learning algorithms have significantly reduced the burden to interpret bulky and often complex satellite data, contributing to the exploration of new use-cases and services. In this study Random Forest classification model is used to separate 28 crop type classes in Estonia. Input data consisted of two seasons (2018, 2019) of Estonian agricultural parcels and features calculated from Sentinel-1 and Sentinel-2 satellite images, meteorological records and soil maps. Achieved multiclass weighted F1 score for year 2018 test set was 0.82 and for year 2019 0.85. Among most important features were Sentinel-1 VH and VV polarization back-scatter intensities and Sentinel-2 PSRI, NDVI and TC-vegetation indices. It was discovered that Sentinel-2 features were more prominent in early (May) and late season (August), but during mid-season (June, July) their importance decreased significantly. Sentinel-1 back-scatter features were more important during mid-season. It was concluded, that using both radar and optical satellite data ensure better classification result than using any of them separately, since they complement each other.
Reaalajas kinemaatilise mõõtmisviisi referentsjaama ülesseadmine ja täpsuse hindamine
(Tartu Ülikool, 2025) Kopli, Jaagup; Matiisen, Tambet, juhendaja; Sepp, Edgar, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
The aim of this thesis is to provide an overview of the setup process of a real-time kinematic reference station and to evaluate the accuracy of its measurements. The work covers the stages of establishing and configuring a reference station. Measurements are carried out on points from the Estonian Land and Spatial Development Board’s local geodetic network and compared with the results obtained from the national reference station network ESTPOS, as well as with standard GPS measurements where no real-time kinematic (RTK) corrections are used. In addition, the thesis provides an overview of how global navigation satellite systems (GNSS) operate and explains the working mechanism behind RTK technology. As a result, a reference station was established on the roof of the Delta building, which demonstrated the accuracy comparable to that offered by ESTPOS.
Real-time 3D Object Detection on Point Clouds
(Tartu Ülikool, 2020) Ozipek, Enes; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Abstract: The demand for precise and fast object detection frameworks has increased since the autonomous vehicle industry started to attract more attention. While the progress made so far in 2D object detection task with state-of-the-art approaches such as convolutional neural networks seems promising, we still struggle to obtain the same level of performance in 3D modalities such as lidar point clouds. The main reasons are that point cloud is sparse and in 3D while state-of-the-art 2D object detection models work on camera images. Some of the early works have tried to ease the aforementioned challenges using either 3D convolutional neural networks or bird’s eye view approaches, nevertheless, they were not able to achieve the desired level of performance in 3D perception. PointPillars is one of the recent models running fast with a good accuracy on point clouds. Its main advantage arises from the way it encodes the points in pillars into spatial features using PointNet. It basically divides the whole point cloud into grids of vertical pillars and applies state-of-the-art 2D detection network on this top-down view in which spatial features are encoded. Even though this operation enables the network to keep the positional information of the points within each pillar, yet, it does not take into account the point densities in different parts of the point cloud. This thesis aims to improve PointPillars network by utilizing the positional encoding and extending the detection area. Positional encoding helps the network utilize positional features by introducing two additional input channels before each convolutional and deconvolutional layer. Additionally, different positional encoding schemes are compared to have more insight about the effectiveness of the positional channels introduced. Moreover, this thesis also presents a simple scheme to train 360-degrees model with ground truths provided for only camera Field-of-View (FOV). Positional encoding scheme provides better accuracy at a similar speed as the original network. On the other hand, even though 360-degrees model is supposedly the type of a model that should be used with lidar, in experiments, it is observed that it outputs many False-Positives (FPs).