Rozdziały
Stały URI dla kolekcji
Przeglądaj
Ostatnie zgłoszenia
Pozycja Valuing Passes in Actions Leading to the Third Zone on the Pitch with Machine Learning Methods(Wydawnictwo Politechniki Łódzkiej, 2023) Tylka, Mateusz; Wałęsa, Sebastian; Girejko, Kornelia; Kaczmarek, Jakub; Grzelak, Bartłomiej; Piłka, TomaszIn football, the ability to make accurate and effective passes to the third zone of the pitch is a key aspect of a team’s success. Evaluating these passes can provide valuable information about a team’s performance and help coaches and analysts make informed decisions about their tactics and strategies. In this article, we will explore the possibility of using artificial intelligence methods to score passes to the third zone on the field, in comparison to traditional metrics.Pozycja On the Selection of a Machine Learning model in TinyML Devices – Preliminary Study(Wydawnictwo Politechniki Łódzkiej, 2023) Puślecki, Tobiasz; Walkowiak, KrzysztofThe expected development of TinyML-related technologies will necessitate the development of methods for efficient use of energy resources. In this article, we present preliminary study of machine learning (ML) model selection in TinyML devices in order to reach a tradeoff between accuracy and energy consumption. We study various use cases with different ML models. Our research shows that the presented method can improve the TinyML system in terms of operation time at the cost of slightly lower accuracy.Pozycja On the Importance of the RGB-D Sensor Model in the CNN-based Robotic Perception(Wydawnictwo Politechniki Łódzkiej, 2023) Zieliński, Mikołaj; Belter, DominikMobile and manipulation robots operating indoors use RGB-D cameras as the environment perception sensors. To process data from RGB and depth cameras neural networks are applied. These neural-based systems are trained using synthetic datasets due to the difficulties of obtaining ground truth data on real robots. As a result, the neural model used on the real robot does not produce satisfactory performance due to the differences between the images used during training and the inference. In this paper, we show the importance of depth sensor modeling while training the neural network on a synthetic dataset. We show that the obtained neural model can be used on the real robot and process the data from the real RGB-D camera.Pozycja On Parameters of Migration in PEA Computing(Wydawnictwo Politechniki Łódzkiej, 2023) Biełaszek, Sylwia; Byrski, AleksanderMetaheuristics, such as evolutionary algorithms have been proven to be (also theoretically, see works of Vose [1]) universal optimization methods. Skolicki and DeJong [2] researched impact of migration intervals on island models. In this article, we explore different migration intervals and amounts of migrating indyviduals, complementing Skolicki and DeJong’s research. In our experiments we use different ways of selecting migrants and pave the way for further research, e.g. involving different topologies and neighborhoods. Besides sketching out the background and presenting the idea of the algorithm we show the experimental results and discuss them in detail.Pozycja Lung Xray Images Analysis for COVID-19 Diagnosis(Wydawnictwo Politechniki Łódzkiej, 2023) Kloska, Anna; Tarczewska, Martyna; Giełczyk, Agata; Marciniak, BeataBackground: The SARS-CoV-2 pandemic began in early 2020. It paralyzed human life all over the world and threatened our security. Thus, proposing some novel and effective approaches to diagnosing COVID-19 infections became paramount. Methods: This article proposes a method for the classification of chest X-ray images based on the transfer learning. We examined also different scenarios of dataset augmentation. Results: The paper reports accuracy=98%, precision=97%, recall=100% and F1-score=98% in the most promising approach. Conclusion: Our research proofs that machine learning can be used in order to support medics in chest X-ray classification and implementing augmentation can lead to improvements in accuracy, precision, recall, and F1-scores.Pozycja Hierarchical Distributed Cluster-based Method for Robotic Swarms(Wydawnictwo Politechniki Łódzkiej, 2023) Mastej, Bartłomiej; Figat, MaksymThe growing interest in autonomous systems inspired by nature has led to a major shift towards swarm robotics. The main characteristics of swarms are independence from global knowledge, scalability and relatively low cost. However, the design of a swarm system is still a challenging task. Most of the existing research focuses on the task-specific solutions, which are hardly applicable to other solutions. Therefore, in this paper we present the method that provides a general guideline for the design of the swarm systems. The approach is verified in the simulation of the letter formation task.Pozycja AMUseBot: Towards Making the Most out of a Task-oriented Dialogue System(Wydawnictwo Politechniki Łódzkiej, 2023) Christop, Iwona; Dudzic, Kacper; Krzymiński, MikołajThis paper presents AMUseBot, a task-oriented dialogue system designed to assist the user in completing multi-step tasks. Taking into consideration that the fundamental issues with such systems are poor user ratings and high rates of uncompleted tasks, the main goal of the project is to keep the user focused and provide engaging conversations. We approach these problems by the introduction of dynamic multimodal communication and graph-based task management.Pozycja AloneKnight – Enabling Affective Interaction within Mobile Video Games(Wydawnictwo Politechniki Łódzkiej, 2023) Jemioło, Paweł; Świder, Krzysztof; Storman, Dawid; Adrian, Weronika T.Artificial intelligence is used in various contexts, including video games, where it can enhance the game design and adapt content to players’ emotional states through affective computing. In this paper, we present an example of an affective mobile game and compare participants’ opinions after playing two versions of the game, with and without an affective loop. The game was developed using Unity. In the affective version, physiological data is recorded and analysed to detect emotions based on facial expressions and electrodermal activity, which then affects the game. The study with 11 participants showed positive feedback for the game with affective loop.Pozycja Using Publicly Available Building Data to Improve 3D Map(Wydawnictwo Politechniki Łódzkiej, 2023) Krygiel, Krzysztof; Majek, Karol; Będkowski, JanuszIn this paper, we address the problem of 3D Map accuracy. No access to RTK GPS or LIDAR leads to poor accuracy of the map. High-rise buildings cause even greater trajectory errors. We used artificial intelligence methods to integrate publicly available building data and show that it can improve map accuracy from monocular camera and inaccurate GPS receiver. The main novelty is a method of building elevation detection in sparse point cloud data. We match detected elevations with building data and use modified bundle-adjustment algorithm to improve the map. We show that proposed approach decreases the trajectory error.Pozycja Semi-formal Methods for Security Informed Safety Assessment of Robotic Systems(Wydawnictwo Politechniki Łódzkiej, 2023) Kharchenko, Vyacheslav; Abakumov, Artem; Yakovlev, SergiyPozycja Semantic Segmentation for Autonomous Drone Delivery SUADD’23 Challenge(Wydawnictwo Politechniki Łódzkiej, 2023) Mrukwa, Anna; Majek, KarolThe popularity of drones as well as other different flying devices remains undeterred for several years now, with various industries recognizing their usefulness in a range of applications. However, the effectiveness of such systems is heavily dependent on real-time autonomous surface identification. The goal of this work is to evaluate recently published dataset dedicated to Unmanned Aircraft Systems. We performed experiments using several semantic segmentation neural network architectures. We outline possible improvements for future research and promising results for attentionbased solutions in the field.Pozycja Predictive User Interface for Emerging Experiences(Wydawnictwo Politechniki Łódzkiej, 2023) Kapusta, Paweł; Duch, PiotrThis research paper focuses on the use of predictive techniques to improve interaction with user interfaces in emerging experiences such as Virtual Reality, Augmented Reality, Metaverse, and touchless kiosks and dashboards. We propose the concept of intelligent snapping, which uses gaze tracking, head-pose tracking, hand tracking, as well as gesture recognition and hand posture recognition to catch the intent of the person rather than the actual input.Pozycja NeRF-based RGB-D Images Generation in Robotics – Experimental Study(Wydawnictwo Politechniki Łódzkiej, 2023) Kulecki, Bartłomiej; Belter, DominikMultiple learning-based algorithms in robotics require collecting RGB-D images of the scene from various viewpoints. These procedures are time-consuming, so many methods are trained using synthetic images. Recently, a Neural Radiance Fields (NeRF) model of the scene was proposed. Moreover, recent methods show that this model can be trained in minutes. This opens the possible applications in robotics for training the systems to reconstruct scenes, grasp objects or estimate their 3D poses using RGB-D images generated from a small number of input images. In this paper, we verify the quality of RGB-D images generated by the Instant Neural Graphics Primitives implementation of NeRF. We compare the obtained results from the Instant NeRF with the ground-truth RGB-D images obtained from the Kinect Azure and images generated from the point cloud model of the scene. The results show that the difference between generated RGB-D images and ground truth images is small, especially near the object.Pozycja Mixing Synthetic and Real-world Datasets Strategy for Improved Generalization of the CNN(Wydawnictwo Politechniki Łódzkiej, 2023) Młodzikowski, Kamil; Belter, DominikIn this paper, we deal with the problem of supervised training neural networks with an insufficient number of real-world training examples. We propose a method that at the beginning trains the neural network using a relatively simple synthetic dataset. In the following epochs, we add more challenging and real-life images to the training dataset. We compare the proposed strategy with other methods of using artificial and real-world datasets for training the neural network. The obtained results show that the proposed strategy allows for obtaining the neural network with higher generalization capabilities than competitive methods.Pozycja Improving RGB-D Visual Odometry with Depth Learned from a Better Sensor’s Output(Wydawnictwo Politechniki Łódzkiej, 2023) Kostusiak, AleksanderThis paper compares the results obtained from an indoor Visual Odometry (VO) system with RGB-D images provided by a Kinect v1 camera against those achieved by a VO with enhanced depth channel. For this purpose, we have used two classic image inpainting methods and a deeplearning approach for scene depth estimation employing Kinect v2 depth maps as reference data. The ability to enhance lower-quality data is crucial to reduce the cost of VO applications because higher-quality information can be infused through deep learning in systems using budget sensors.Pozycja Evolution of Robotic System Specification Methodology(Wydawnictwo Politechniki Łódzkiej, 2023) Figat, Maksym; Zieliński, CezaryDesign of robotic systems is a challenging task. More than 30 years ago some members of our team have embarked on a quest to find a general methodology for the design of any robotic system. Here we present the results that have been obtained thus far – a Robotic System Specification Methodology (RSSM). The foundation of RSSM is a metamodel – the scaffolding of any robotic system. Appropriate definition of the parameters of the metamodel transforms it into a model of a particular system, thus providing its specification, which in turn is translated into the control system code.Pozycja Intelligent Anticipatory Mobile Robot Networks for Autonomous Fruit Harvesting(Wydawnictwo Politechniki Łódzkiej, 2023) Skulimowski, Andrzej M.J.; Karimi, MasoudA relevant class of decision problems solved by autonomous robots consists in deriving consensus strategies for coordinated group task performance. This paper presents preference models for the above consensus problems termed anticipatory networks (AN). By definition, an AN is a multidigraph where temporally ordered agents are linked by a causal relation. Another partial order relation is anticipatory feedback which expresses preferences regarding some future decisions. We will present an application of the above model to coordinating fruit harvesting by autonomous robot teams. A graded freedom of the decision choice allows the robots to achieve desirable efficiency of the harvesting process.Pozycja Beacon-based Swarm Search and Rescue(Wydawnictwo Politechniki Łódzkiej, 2023) Ratnayake, Sunil; Figat, MaksymPozycja BDOT10k-seg: A Dataset for Semantic Segmentation(Wydawnictwo Politechniki Łódzkiej, 2023) Kos, Aleksandra; Majek, KarolIn this work, we describe BDOT10k-seg, a novel aerial dataset for semantic and instance segmentation. Our data covers almost the entire territory of Poland (314,000 km2) and provides precise pixel-level annotations for 286 classes of topographical objects, including buildings, roads, rivers, lakes, airports, agricultural areas, and forests. BDOT10-seg consists of 60,718 images with a resolution of 3 to 75 centimeters per pixel, and more than 40 million object instances. The average image size is 12,367 px because, unlike other publicly available datasets, we do not modify the source orthoimages. The code for generating the BDOT10k-seg dataset is publicly available.Pozycja A Reinforcement Learning Framework for Motion Planning of Autonomous Vehicles(Wydawnictwo Politechniki Łódzkiej, 2023) Orłowski, Mateusz; Skruch, PawełThe paper introduces a framework that has been developed for the design and verification of motion planning algorithms for autonomous driving. The framework allows for the use of reinforcement learning for autonomous driving that requires complex and computationally intensive simulations. The key element in the presented approach plays a multi-agent closed-loop simulation of the traffic environment. Using the framework, the training process can be performed in parallel on high-performance computing clusters. Therefore, the framework provides an easy way to explore the potential of reinforcement learning for autonomous driving applications.