http://thuvienso.dut.udn.vn/handle/DUT/9812 2026-10-03T09:33:45Z http://thuvienso.dut.udn.vn/handle/DUT/25180 Title: Autonomous robot integrating Aruco Marker-based vision positioning technology developed on the ROS Authors: Nguyễn, Đoàn Thảo Thư Abstract: The positioning system is designed by combining absolute and relative positioning methods. It is developed on the Robot Operating System (ROS) and utilizes sensors such as cameras, LiDAR (Light Detection and Ranging), and ultrasonic sensors to perceive the environment. In this context, absolute positioning refers to determining the robot’s location based on fixed references in the environment (e.g., map frame or known landmarks like Aruco markers), while relative positioning relies on incremental measurements (e.g., wheel encoders or odometry) to estimate movement from a known point. Description: DA.FA.25.183 121 tr. 2025-01-01T00:00:00Z http://thuvienso.dut.udn.vn/handle/DUT/25178 Title: Research,design,intergration and manufacture of controller for industrial and commercial scale rooftop solar power plant PPC-Power Plant Controller for C&I rooftop solar power plants meets connection requirement with SCADA/EMS system of local power dispatch Authors: Đoàn, Lê Xuân An Abstract: Graduation project "Research and integration of controllers for industrial and commercial-scale rooftop solar power plants. PPC-Power Plant Controller for C&I rooftop solar power plant meets the requirements of connecting to the SCADA/EMS system of the local power unit dispatcher''. Description: DA.FA.25.179 73 tr. 2025-01-01T00:00:00Z http://thuvienso.dut.udn.vn/handle/DUT/25177 Title: Personalized text-to-image generation Authors: Phạm, Thị Thùy Dương Abstract: To address this, prior methods such as Textual Inversion [4] rely on random initialization, resulting in weak identity retention. Cross Initialization [5] improves this by using semantic information from the subject’s name, but remains limited to known identities within the training data. To overcome these limitations, I propose an improved token initialization strategy that integrates linguistic information with visual features extracted from a reference image. Specifically, I introduce fusion_cross_init-a novel method that combines both textual and visual information at the token initialization stage. This method incorporates a Fusion Transformer module to enhance the alignment between the visual features of the reference image and the semantic information related to the subject. Furthermore, it leverages CLIP’s [6] multi-modal encoders to synchronize semantic and visual signals from the outset, thereby significantly improving identity consistency in personalized text-to-image generation. The method is implemented on top of the pre-trained Stable Diffusion [3] model, ensuring high image quality while optimizing computational efficiency. Description: DA.FA.25.177 93 Tr. 2025-01-01T00:00:00Z http://thuvienso.dut.udn.vn/handle/DUT/25179 Title: Autonomous Robot for Temperature Monitoring Using a Thermal Camera and SLAM-based Localization with LiDAR Authors: Huỳnh, Ngọc Lâm; Trần, Đức Công; Nguyễn, Duy Minh Abstract: This project presents an autonomous mobile robot designed for temperature monitoring using a thermal camera and LiDAR-based SLAM. The system enables real-time thermal imaging to detect heat anomalies and uses SLAM algorithms for self-localization and mapping in unknown environments. Implemented with ROS 2, the robot can navigate and monitor indoor spaces autonomously, making it suitable for applications such as fire prevention, equipment inspection, and environmental assessment. Experimental results confirm the system’s effectiveness in accurate thermal detection and reliable autonomous navigation. Description: DA.FA.25.181 105 Tr. 2025-01-01T00:00:00Z