Адаптивні системи автоматичного управління : міжвідомчий науково-технічний збірник. – 2025. – № 2 (47)
Постійне посилання зібрання
Переглянути
Нові надходження
Документ Відкритий доступ Artificial intelligence-based decentralized control of a heterogeneous unmanned aerial vehicle swarm under intermittent communication conditions(КПІ ім. Ігоря Сікорського, 2025) Akhaladze, А.; Lisovychenko, O.This paper addresses the problem of partially successful or failed mission execution by multiple drones operated centrally by human pilots over an unreliable control channel. We propose an artificial-intelligence-based approach to the decentralized control of a heterogeneous swarm of unmanned aerial vehicles (UAVs) under intermittent communication. Swarm heterogeneity–stemming from UAVs with diverse sensing, mobility, and endurance capabilities–complicates coordination, while communication outages demand a high degree of on-board autonomy. The method relies on reinforcement-learning techniques that enable individual UAVs to make decisions locally and to adapt to changes in the environment and in swarm composition. The approach improves the resilience, efficiency, and fault tolerance of the system, allowing the swarm to accomplish complex tasks such as reconnaissance, environmental monitoring, and search-and-rescue operations without dependence on a centralized control node. Emphasis is placed on the design of algorithms that ensure effective interaction and cooperative task execution even in the presence of partial or complete loss of inter-UAV communication or the failure of individual agents.Документ Відкритий доступ A comparative study of task formulations for detecting propaganda using large language models(КПІ ім. Ігоря Сікорського, 2025) Oliinyk, V.; Zakharchyn, N.This paper extends existing studies on propaganda detection using large language models by examiningseveral approaches to task formulation and applying them on different LLMs, namely, GPT-4o mini and Gemma / Gemma 2, aiming to find the most effective approach.Using a combination of two text corpora in English and Russian languages with 18 propaganda techniques, we fine-tune models on character-based, phrase-based and class-?fication -only variationsof this dataset with corresponding instructions to define which ins truction yields the best performance. We conducted experiments and evaluated performance across classification, span identification, and joint tasks, demonstrating the clear superiority of the phrase-based approach over the character-based one. At the same time, our findings indi cate that fine-tuning significantly improved model performance on span identification and joint tasks, while offering limited benefit for the classification task alone.Документ Відкритий доступ An efficient real-time gaze tracking method for browser-based applications(КПІ ім. Ігоря Сікорського, 2025) Oliinyk, V.; Korol, S.This paper presents a gaze tracking method based on a hybrid gaze direction prediction model, designed for real real-time operation in web applications under limited computational resources and without specialized hardware. The proposed approach combines geometric normalization of facial landmarks with a lightweight CNN CNN-Transformer network to estimate gaze direction and project it onto 2D screen coordinates. Designed for scalable and privacy privacy-preserving use in web applications, it addresses the limitations of appearanceappearance-only and geometry geometry-only methods. The system uses MediaPipe FaceMesh for 3D landmark detection, followed by normalization, hybrid gaze estimation, and a 9 9-point calibration procedure using regression regression-based mapping. A comprehensive experimental setup was developed to evaluate i ts effectiveness. Results demonstrate that our approach achieves high angular accuracy and lower jitter during a user active head movement, with real-time inference running entirely in-browser using ONNX Web Runtime. The proposed method is suitable for use in adaptive web interfaces, assistive technologies, educational tools, and behavioral research applications. It offers an accessible pathway for integrating gaze-based interaction into widespread browser platforms without the need for dedicated hardware.