• Journal of Advanced Navigation Technology
• /
• v.25 no.6
• /
• pp.485-492
• /
• 2021

Vision-based autonomous precision landing technology for UAVs requires precise position estimation and landing guidance technology. Also, for safe landing, it must be designed to determine the safety of the landing point against ground obstacles and to guide the landing only when the safety is ensured. In this paper, we proposes vision-based navigation, and algorithms for determining the safety of landing point to perform autonomous precision landings. To perform vision-based navigation, CNN technology is used to detect landing pad and the detection information is used to derive an integrated navigation solution. In addition, design and apply Kalman filters to improve position estimation performance. In order to determine the safety of the landing point, we perform the obstacle detection and position estimation in the same manner, and estimate the speed of the obstacle using LSM. The collision or not with the obstacle is determined based on the CPA calculated by using the estimated state of the obstacle. Finally, we perform flight test to verify the proposed algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.89-96
• /
• 2023

In this paper, we propose a GPU-based method for real-time processing of dynamic re-meshing required for tearing cloth. Thin shell materials are used in various fields such as physics-based simulation/animation, games, and virtual reality. Tearing the fabric requires dynamically updating the geometry and connectivity, making the process complex and computationally intensive. This process needs to be fast, especially when dealing with interactive content. Most methods perform re-meshing through low-resolution simulations to maintain real-time, or rely on an already segmented pattern, which is not considered dynamic re-meshing, and the quality of the torn pattern is low. In this paper, we propose a new GPU-optimized dynamic re-meshing algorithm that enables real-time processing of high-resolution fabric tears. The method proposed in this paper can be used for virtual surgical simulation and physics-based modeling in games and virtual environments that require real-time, as it allows dynamic re-meshing rather than pre-split meshes.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.13-17
• /
• 2024

In this paper, union-based rule antecedent neuro-fuzzy controller, which can guarantee a parsimonious knowledge base with reduced number of rules, is proposed. The proposed neuro-fuzzy controller allows union operation of input fuzzy sets in the antecedents to cover bigger input domain compared with the complete structure rule which consists of AND combination of all input variables in its premise. To construct the proposed neuro-fuzzy controller, we consider the multiple-term unified logic processor (MULP) which consists of OR and AND fuzzy neurons. The fuzzy neurons exhibit learning abilities as they come with a collection of adjustable connection weights. In the development stage, the genetic algorithm (GA) constructs a Boolean skeleton of the proposed neuro-fuzzy controller, while the stochastic reinforcement learning refines the binary connections of the GA-optimized controller for further improvement of the performance index. An inverted pendulum system is considered to verify the effectiveness of the proposed method by simulation and experiment.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.11-19
• /
• 2024

Multi-agent systems can be utilized in various real-world cooperative environments such as battlefield engagements and unmanned transport vehicles. In the context of battlefield engagements, where dense reward design faces challenges due to limited domain knowledge, it is crucial to consider situations that are learned through explicit sparse rewards. This paper explores the collaborative potential among allied agents in a battlefield scenario. Utilizing the Multi-Robot Warehouse Environment(RWARE) as a sparse reward environment, we define analogous problems and establish evaluation criteria. Constructing a learning environment with the QMIX algorithm from the reinforcement learning library Ray RLlib, we enhance the Agent Network of QMIX and integrate Random Network Distillation(RND). This enables the extraction of patterns and temporal features from partial observations of agents, confirming the potential for improving the acquisition of sparse reward experiences through intrinsic rewards.

• Journal of the Society of Naval Architects of Korea
• /
• v.61 no.2
• /
• pp.115-124
• /
• 2024

To detect and prevent structural damage caused by various loads on marine structures and ships, structural health monitoring procedure is essential. Estimating loads acting on the structures which are measured by sensors that are mounted properly are crucial for structural health monitoring. However, attaching an excessive number of sensors to the structure without consideration can be inefficient due to the high costs involved and the potential for inducing structural instability. In this study, we introduce a method to determine the optimal number of sensors and their optimized locations for strain measurement sensors, allowing for accurate load estimation throughout the structure using model expansion method. To estimate the loads exerted on the entire structure with minimal sensors, we construct a strain-load interpolation matrix using the strain mode shapes of the finite element (FE) model and select the optimal sensor locations by applying D-Optimal Design and the row exchange algorithm. Finally, we estimate the loads exerted on the entire structure using the model expansion method. To validate the proposed method, we compare the results obtained by applying the optimal sensor placement and model expansion method to an FE model subjected to arbitrary loads with the loads exerted on the entire FE model, demonstrating efficiency and accuracy.

• Steel and Composite Structures
• /
• v.51 no.1
• /
• pp.25-41
• /
• 2024

The measurement of pile bearing capacity is crucial for the design of pile foundations, where in-situ tests could be costly and time needed. The primary objective of this research was to investigate the potential use of fuzzy-based techniques to anticipate the maximum weight that concrete driven piles might bear. Despite the existence of several suggested designs, there is a scarcity of specialized studies on the exploration of adaptive neuro-fuzzy inference systems (ANFIS) for the estimation of pile bearing capacity. This paper presents the introduction and validation of a novel technique that integrates the fire hawk optimizer (FHO) and equilibrium optimizer (EO) with the ANFIS, referred to as ANFIS_FHO and ANFIS_EO, respectively. A comprehensive compilation of 472 static load test results for driven piles was located within the database. The recommended framework was built, validated, and tested using the training set (70%), validation set (15%), and testing set (15%) of the dataset, accordingly. Moreover, the sensitivity analysis is performed in order to determine the impact of each input on the output. The results show that ANFIS_FHO and ANFIS_EO both have amazing potential for precisely calculating pile bearing capacity. The R² values obtained for ANFIS_FHO were 0.9817, 0.9753, and 0.9823 for the training, validating, and testing phases. The findings of the examination of uncertainty showed that the ANFIS_FHO system had less uncertainty than the ANFIS_EO model. The research found that the ANFIS_FHO model provides a more satisfactory estimation of the bearing capacity of concrete driven piles when considering various performance evaluations and comparing it with existing literature.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.4
• /
• pp.495-506
• /
• 2024

In this study, we propose the terrain following algorithm using model predictive control and nonlinear disturbance observer-based backstepping sliding mode controller for an aircraft system. Terrain following is important for military missions because it helps the aircraft avoid detection by the enemy radar. The model predictive control is used to replace the generating trajectory and guidance with the flight path angle constraint. In addition, the aircraft is affected to the parameter uncertainty and unknown disturbance such as wind near the mountainous terrain. Therefore, we suggest the nonlinear disturbance-based backstepping sliding mode control method for the aircraft that has highly nonlinearity to enhance flight path angle tracking performance. Through the numerical simulation, the proposed method showed the better tracking performance than the traditional backstepping method. Furthermore, the proposed method presented the terrain following maneuver maintaining the desired altitude.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.17-22
• /
• 2024

This paper introduces the implementation of a secondhand clothing trading system equipped with virtual fitting functionality based on deep learning. The proposed system provides users with the ability to visually try on secondhand clothing items online and assess their fit. To achieve this, it utilizes the Convolutional Neural Network (CNN) algorithm to create virtual representations of users considering their body shape and the design of the clothing. This enables buyers to pre-assess the fit of clothing items online before actually wearing them, thereby aiding in their purchase decisions. Additionally, sellers can present accurate clothing sizes and fits through the system, enhancing customer satisfaction. This paper delves into the CNN model's training process, system implementation, user feedback, and validates the effectiveness of the proposed system through experimental results.

• Journal of Advanced Navigation Technology
• /
• v.28 no.1
• /
• pp.1-14
• /
• 2024

Global navigation satellite system (GNSS) providing position, navigation and timing (PNT) services consist of satellite, ground, and user systems. Monitoring stations, a key element of the ground segment, play a crucial role in continuously collecting satellite navigation signals for service provision and fault detection. These stations detect anomalies such as threats to the signal-in-space (SIS) of satellites, receiver issues, and local threats. They deliver received data and detection results to the master station. This paper introduces the main monitoring algorithms and measurement pre-processing processes for quality assessment and fault detection of received satellite signals in current satellite navigation system monitoring stations. Furthermore, it proposes a strategy for the development of components, architecture, and algorithms for the new regional navigation satellite system (RNSS) monitoring stations.

• Journal of Advanced Navigation Technology
• /
• v.27 no.6
• /
• pp.788-797
• /
• 2023

In this paper, we introduced a test environment to test a vision-aided navigation system, as an alternative navigation system when global positioning system (GPS) is unavailable, for vertical take-off and landing (VTOL) unmanned aerial system. It is efficient to use a virtual environment to test and evaluate the vision-aided navigation system under development, but currently no suitable equipment has been developed in Korea. Thus, the proposed test environment is developed to evaluate the performance of the navigation system by generating input signal modeling and simulating operation environment of the system, and by monitoring output signal. This paper comprehensively describes research procedure from derivation of requirements specifications to hardware/software design according to the requirements, and production of the test environment. This test environment was used for evaluating the vision-aided navigation algorithm which we are developing, and conducting simulation based pre-flight tests.