• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.11
• /
• pp.809-817
• /
• 2022

The development of unmanned robots and UAVs has increased the need for path planning methods such as RRT^* algorithm. It mostly works well in various environments and is utilized in many fields. A lot of research has been conducted to obtain a better path in terms of efficiency through various modifications to the RRT^* algorithm, and the performance of the algorithm is continuously improved thanks to these efforts. In this study, a method using the limitation of sampling range is proposed as an extension of these efforts. Based on the idea that a path passing close to obstacles is similar to the optimal path in obstacle environments, nodes are produced around the obstacle. Also, rewiring algorithm is modified to quickly obtain the path. The performance of the proposed algorithm is validated by comparative analysis of the previous basic algorithm and the generated path is tracked by a UAV's kinematic model for further verification.

• Journal of Korea Game Society
• /
• v.17 no.6
• /
• pp.139-152
• /
• 2017

In this paper, we propose a ground area detection technique based on region segmentation in the spherical image. We modified the Watershed planar image segmentation method to segment spherical images. After regions are segmented, the ground area is detected by comparing colors and textures of pixels of the assumed ground region with the pixels of other regions. The ground detection technique for planar images cannot be used for spherical images due to the spherical distortion. Considering the spherical distortion, we designed the ground shape detection algorithm to detect the ground area in the spherical images. Our experimental results show that the proposed technique properly detects ground areas both for the flat ground and the obstacle-filled ground environments.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.12
• /
• pp.909-909
• /
• 2022

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.329-332
• /
• 2023

3D Object Detection using deep neural network has been developed a lot for obstacle detection in autonomous vehicles because it can recognize not only the class of target object but also the distance from the object. But in the case of 3D Object Detection models, the detection performance for distant objects is lower than that for nearby objects, which is a critical issue for autonomous vehicles. In this paper, we introduce a technique that increases the performance of 3D object detection models, particularly in recognizing distant objects, by generating virtual 3D vehicle data and adding it to the dataset used for model training. We used a spherical point tracing method that leverages the characteristics of 3D LiDAR sensor data to create virtual vehicles that closely resemble real ones, and we demonstrated the validity of the virtual data by using it to improve recognition performance for objects at all distances in model training.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.37 no.2
• /
• pp.181-186
• /
• 2009

The objective of this study is ensuring safety of cabin when the blade impacts into a obstacle by verifying safety of the rotor mast and the transmission using impact loads calculated from the simulation. The rotor mast shall not fail and the transmission shall not be displaced into occupiable space when the main rotor composite blade impact into a 8 inch rigid cylinder in diameter on the outer 10% of the blade at operational rotor speed. To calculate the reaction loads at the spherical bearing and lead-lag damper, blade impact analysis was performed with FE model consist of composite blade, tree(or rigid cylinder) using elastic-plastic with damage material and several contact surfaces which were created to describe a progress of actual failure. Also, the reaction loads were investigated in change of blade rotation speed and pitch angle.