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.
คณะวิศวกรรมศาสตร์
Nowadays, rail transportation has a significant impact on people's lives and economic growth. Consequently, the number of rail systems being built around our country has dramatically increased. This process causes various types of pollution, such as noise and rail-way vibration, which can badly affect the life of citizens who live nearby. The most popular way to solve this problem recently is to decrease the noise from the sound source or to adjust the vibration by attaching a Track Damper to the railway. This technique is being used in many countries especially in Europe and Australia because it is cheap and has high efficiency. The key piece called Track Dampers are made by AUT company’s Thailand for a period of time. The company produces Track Dampers for the owner of the technology so as to sell more than 300,000 pieces of it overseas. Furthermore, the demand of Track Dampers grows as the railway systems expand. Unfortunately, the imported synthetic materials, which are used to create Track Dampers, are made from environmentally unfriendly sources. As a result, this research aims to develop the product to be environmentally-safe by replacing some imported materials with Thai’s local content; which are natural rubber and rubber crumbs. Furthermore, the product will be added value by mounting with embedded sensors for real-time monitoring of track vibration, noise, and rail temperature. All embedded devices developed will sense, collect, and automatically send to cloud by wireless technology platform. The AI and IOT platform will also be developed for safety, security, and maintenance proposed of railway track system. However, in conducting research, there will be close collaboration with AUT company through design, production, and testing. The outcome of this research is to upgrade AUT company from tier 2 manufacturer (TRL 8-9) to tier 1 manufacturer (TRL 7-8) which will be served the Thailand competitiveness enhancing strategic goal.
คณะเทคโนโลยีการเกษตร
"Eco Mango Pack: Eco-friendly Packaging for a Sustainable Future" focuses on developing innovative packaging for Nam Dok Mai mangoes, considering fruit safety, shelf life, and environmental impact. The selected materials include a box made from coconut husk, and dry water hyacinth stems have been utilized as internal cushioning to enhance shock resistance. Additionally, dried coffee grounds are incorporated into the packaging to extend the mango's shelf life. The design also takes into account the needs of small-scale farmers, making the packaging suitable for community enterprise production and reducing production costs. This project aims to add value to Thai agricultural products, support the circular economy concept, and promote the use of environmentally friendly materials in the packaging industry.
คณะวิทยาศาสตร์
Currently, climate change and human activities are causing rapid deterioration of coral reefs worldwide. Monitoring coral health is essential for marine ecosystem conservation. This project focuses on developing an Artificial Intelligence (AI) model to classify coral health into four categories: Healthy, Bleached, Pale, and Dead using Deep Learning techniques. With pre-trained convolutional neural network (CNN) for image classification. To improve accuracy and mitigate overfitting, 5-fold Cross-Validation is employed during training, and the best-performing model is saved. The results of this project can be applied to monitor coral reef conditions and assist marine scientists in analyzing coral health more efficiently and accurately. This contributes to better conservation planning for marine ecosystems in the future.