• Journal of the Semiconductor & Display Technology
• /
• v.16 no.3
• /
• pp.127-130
• /
• 2017

In this research, we present a path planning method for an autonomous flight of unmanned aerial vehicles (UAVs) through reinforcement learning under simulated environment. We design the simulator for reinforcement learning of uav. Also we implement interface for compatibility of Deep Q-Network(DQN) and simulator. In this paper, we perform reinforcement learning through the simulator and DQN, and use Q-learning algorithm, which is a kind of reinforcement learning algorithms. Through experimentation, we verify performance of DQN-simulator. Finally, we evaluated the learning results and suggest path planning strategy using reinforcement learning.

• Aerospace Engineering and Technology
• /
• v.6 no.2
• /
• pp.45-51
• /
• 2007

The various levels of test are performed to verify the correctness, completeness, and quality of the developed flight software. The three main test levels are unit test, integration test and verification test. The flight software unit test is performed on the individual PC environment using target simulator. And integration and verification test is mainly performed on STB(S/W Test Bed) which provides test and debugging environments for flight software on the target board This document is to present the test environment for the next generation low earth orbit satellite flight software development.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.189-192
• /
• 2021

This study applies a deep learning-based long short-term memory(LSTM) model to track tracking technology. In the case of existing track tracking technology, the weight of constant velocity, constant acceleration, stiff turn, and circular(3D) flight is automatically changed when tracking track in real time using LMIPDA based on Kalman filter according to flight characteristics of an aircraft such as constant velocity, constant acceleration, stiff turn, and circular(3D) flight. In this process, it is necessary to improve performance of changing flight characteristic weight, because changing flight characteristics such as stiff turn flight during constant velocity flight could incur the loss of track and decreasing of the tracking performance. This study is for improving track tracking performance by predicting the change of flight characteristics in advance and changing flight characteristic weigh rapidly. To get this result, this study makes deep learning-based Long Short-Term Memory(LSTM) model study the plot and target of simulator applied with radar error model, and compares the flight tracking results of using Kalman filter with those of deep learning-based Long Short-Term memory(LSTM) model.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.32 no.4
• /
• pp.95-100
• /
• 2004

This paper represents the development of a CLS(Control Loading System) for a target a airplane (KT-1) with mechanical linkage reversible flight control system. The system is composed of mechanical frame, controller, sensing part to measure the force from the stick, driving system generating the reaction forces. The DS1103 DSP(Digital Signal Processor) of the dSpace Corp. was used as the controller. The control algorithm of the CLS and the operational environment including monitoring software and evaluation tools are described. The evaluation of the system was conducted according to the requirement specification. The results of the test were analyzed by comparing with the actual data of the target airplane.

• Aerospace Engineering and Technology
• /
• v.3 no.1
• /
• pp.170-178
• /
• 2004

This paper deals with six degree-of-freedom HILS(hardware-in-the-loop-simulation) of KSR-III rocket using a TAFMS(three axis flight motion simulator). This TAFMS HILS test is accomplished before main HILS tests in order to verify the control stability in the presence of TAFMS dynamic effects. The TAFMS HILS test includes initial attitude holding tests for INS initial alignment procedures, timer synchronization tests with an auxiliary lift-off signal, real-time calibration tests using an external thermal recorder, open-loop TAFMS operating tests, and final closed-loop TAFMS HILS tests using the TAFMS attitude measurements as inputs to the closed control loop. The HILS tests are accomplished for several flight conditions composed with nominal flight condition, TWD effect added condition, slosh modes and/or bending modes existing condition, and windy condition, etc.

• Journal of the Korea Convergence Society
• /
• v.8 no.6
• /
• pp.9-16
• /
• 2017

Researchers are now faced with a limited flight time of the hoverable UAV due to the sluggish technological advances of the Li-Po energy density and try to find a bypassing solution for the fully autonomous hoverable UAV mission planning. Although there are several candidate solutions, automated wireless charging is the most likely and realistic candidate and we are focusing on the autolanding strategy of the hoverable UAV in this paper since it is the main technology of it. We developed a hoverable UAV flight simulator including Li-Po battery pack simulator using MATLAB/Simulink and UAV flight and battery states are analyzed. The maximum motor power measured as 1,647 W occurs during the takeoff and cell voltage decreases down to 3.39 V during the procedure. It proves that the two Li-Po battery packs having 22 Ah and connected in series forming 12S1P are appropriate for the autolanding mission planning.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.3
• /
• pp.208-216
• /
• 2017

This paper presents the design method of an FMCW(frequency-modulated continuous-wave) altitude simulator which generates propagation delay signals according to target distances to test the radar altimeter. To improve the conventional RF method for creating delay signals, the simulator is designed by the RF-optics-RF method using optical delay lines. In addition, it is designed to simulate the Doppler shift and jamming that may occur in actual flight environment. In order to evaluate the performance of the developed simulator, the integration tests have been conducted with the radar altimeter. Through the test, we successfully verified the performance of the simulator.

• Journal of Astronomy and Space Sciences
• /
• v.27 no.4
• /
• pp.377-382
• /
• 2010

In lunar explorer development program, computer simulator is necessary to provide virtual environments that vehicle confronts in lunar transfer, orbit, and landing missions, and to analyze dynamic behavior of the spacecraft under these environments. Objective of simulation differs depending on its application in spacecraft development cycle. Scope of use cases considered in this paper includes simulation of software based, processor and/or hardware in the loop, and support of ground-based flight test of developed vehicle. These use cases represent early phase in development cycle but reusability of modeling results in the next design phase is considered in defining requirements. A simulator architecture in which simulator platform is located in the middle and modules for modeling, analyzing, and three dimensional visualizing are connected to that platform is suggested. Baseline concepts and requirements for simulator development are described. Result of trade study for selecting simulation platform and approaches of defining other simulator components are summarized. Finally, characters of lunar elevation map data which is necessary for lunar terrain generation is described.

• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.33-36
• /
• 1999

The KOMPSAT, which is scheduled to be launched by Taurus launch vehicle in late November of 1999, will be in a sun-synchronous orbit with an altitude of 685km, eccentricity of 0.001, inclination of 98deg and local time of ascending node of 10:50 a.m. Electronics and Telecommunications Research Institute and Daewoo Heavy Industry had jointly developed a KOMPSAT Simulator as a component of the KOMPSAT Mission Control Element. The MCE had been delivered to Korea Aerospace Research Institute for the KOMPSAT ground operation. It is being used for training of KOMPSAT ground station personnel. Each of satellite subsystems and space environment were mathematically modeled in the simulator. To verify the overall function of KOMPSAT simulator, a Launch and Early Orbit Phase(LEOP) operation simulations have been performed. The simulator had been verified through various tests such as functional level test, subsystem test, interface test, system test, and acceptance test. In this paper, simulation results for LEOP operations to verify flight software adapted into simulator, satellite subsystem models and environment models are presented.

• Journal of Satellite, Information and Communications
• /
• v.6 no.1
• /
• pp.50-56
• /
• 2011

During the development of flight software, the processor emulator and satellite simulator are essential tools for software development and verification. SWT/KARI developed the software-based spacecraft simulator based on TSIM-ERC32 processor emulator from Aeroflex Gaisler. But when developing flight software using TSIM-ERC32, there are much limitation for understanding of exact behavior of ERC32 processor, and it is impossible to change or modify the emulator core to develop the satellite simulator. To reslove this problem, this paper presents the development of new cycle-true ERC32 emulator as laysim-erc32 and describes the software development and debugging method on VxWorks/RTEMS RTOS.