The capture of a target spacecraft by a chaser is an on-orbit docking operation that requires an accurate, reliable, and robust object recognition algorithm. Vision-based guided spacecraft relative motion during close-proximity maneuvers has been consecutively applied using dynamic modeling as a spacecraft on-orbit service system. This research constructs a vision-based pose estimation model that performs image processing via a deep convolutional neural network. The pose estimation model was constructed by repurposing a modified pretrained GoogLeNet model with the available Unreal Engine 4 rendered dataset of the Soyuz spacecraft. In the implementation, the convolutional neural network learns from the data samples to create correlations between the images and the spacecraft’s six degrees-of-freedom parameters. The experiment has compared an exponential-based loss function and a weighted Euclidean-based loss function. Using the weighted Euclidean-based loss function, the implemented pose estimation model achieved moderately high performance with a position accuracy of 92.53 percent and an error of 1.2 m. The in-attitude prediction accuracy can reach 87.93 percent, and the errors in the three Euler angles do not exceed 7.6 degrees. This research can contribute to spacecraft detection and tracking problems. Although the finished vision-based model is specific to the environment of synthetic dataset, the model could be trained further to address actual docking operations in the future.
In one, docking is defined as “when one incoming spacecraft rendezvous with another spacecraft and flies a controlled collision trajectory in such a manner to align and mesh the interface mechanisms”, and defined docking as an on-orbital service to connect two free-flying man-made space objects. The service should be supported by an accurate, reliable, and robust positioning and orientation (pose) estimation system. Therefore, pose estimation is an essential process in an on-orbit spacecraft docking operation. The position estimation can be obtained by the most well-known cooperative measurement, a Global Positioning System (GPS), while the spacecraft attitude can be measured by an installed Inertial Measurement Unit (IMU). However, these methods are not applicable to non-cooperative targets. Many studies and missions have been performed by focusing on mutually cooperative satellites. However, the demand for non-cooperative satellites may increase in the future. Therefore, determining the attitude of non-cooperative spacecrafts is a challenging technological research problem that can improve spacecraft docking operations. One traditional method, which is based on spacecraft control principles, is to estimate the position and attitude of a spacecraft using the equations of motion, which are a function of time. However, the prediction using a spacecraft equation of motion needs support from the sensor fusion to achieve the highest accuracy of the state estimation algorithm. For non-cooperative spacecraft, a vision-based pose estimator is currently developing for space application with a faster and more powerful computational resource.
คณะเทคโนโลยีสารสนเทศ
This research presents a deep learning method for generating automatic captions from the segmentation of car part damage. It analyzes car images using a Unified Framework to accurately and quickly identify and describe the damage. The development is based on the research "GRiT: A Generative Region-to-text Transformer for Object Understanding," which has been adapted for car image analysis. The improvement aims to make the model generate precise descriptions for different areas of the car, from damaged parts to identifying various components. The researchers focuses on developing deep learning techniques for automatic caption generation and damage segmentation in car damage analysis. The aim is to enable precise identification and description of damages on vehicles, there by increasing speed and reducing the work load of experts in damage assessment. Traditionally, damage assessment relies solely on expert evaluations, which are costly and time-consuming. To address this issue, we propose utilizing data generation for training, automatic caption creation, and damage segmentation using an integrated framework. The researchers created a new dataset from CarDD, which is specifically designed for cardamage detection. This dataset includes labeled damages on vehicles, and the researchers have used it to feed into models for segmenting car parts and accurately labeling each part and damage category. Preliminary results from the model demonstrate its capability in automatic caption generation and damage segmentation for car damage analysis to be satisfactory. With these results, the model serves as an essential foundation for future development. This advancement aims not only to enhance performance in damage segmentation and caption generation but also to improve the model’s adaptability to a diversity of damages occurring on various surfaces and parts of vehicles. This will allow the system to be applied more broadly to different vehicle types and conditions of damage inthe future
คณะเทคโนโลยีสารสนเทศ
Cancer is one of the major health issues in Thailand, particularly as the country enters an aging society. The risk of chronic diseases among the elderly often results in limitations in treatment, making it difficult for most patients to achieve a complete recovery. This necessitates continuous care and the provision of accurate information and guidance about cancer. However, current health record systems for patients lack effective interconnectivity, which hinders data analysis and the development of patient care models. Additionally, incorrect information about cancer spread across social media can lead to misunderstandings among elderly patients. To address these issues, researchers have developed a chatbot system that utilizes Natural Language Processing (NLP) technology to understand human language and accurately respond to questions about elderly cancer patient care. The chatbot provides reliable and up-to-date information based on medical knowledge sourced from a database reviewed by healthcare professionals. Furthermore, a web application has been developed to record and analyze patient assessments according to medical standards, enabling healthcare providers to plan and develop appropriate treatment approaches in a better way. This system also facilitates data sharing and connectivity across hospital systems, allowing information to be used to enhance the precision and modernity of treatment approaches. In addition, the chatbot acts as an assistant, providing information and guidance to patients, reducing the workload of healthcare staff in answering questions and encouraging patients to take a more active role in managing their own health.
คณะศิลปศาสตร์
"Niyom Thai" represents health-centric footwear adorned with traditional Thai patterns, embodying an innovative approach to sustainable development tailored to the current needs of local communities. These shoes utilize natural materials to mitigate fatigue and integrate safety technologies, including location tracking via a mobile application and heart rate monitoring. This addresses the aspects of convenience and well-being in both daily life and travel