• Journal of the Semiconductor & Display Technology
• /
• v.17 no.1
• /
• pp.88-92
• /
• 2018

Currently drone industry has become one of the fast growing markets and the technology for unmanned aerial vehicles are expected to continue to develop at a rapid rate. Especially small unmanned aerial vehicle systems have been designed and utilized for the various field with their own specific purposes. In these fields the path planning problem to find the shortest path between two oriented points is important. In this paper we introduce a path planning strategy for an autonomous flight of unmanned aerial vehicles through reinforcement learning with self-positioning technique. We perform Q-learning algorithm, a kind of reinforcement learning algorithm. At the same time, multi sensors of acceleraion sensor, gyro sensor, and magnetic are used to estimate the position. For the functional evaluation, the proposed method was simulated with virtual UAV environment and visualized the results. The flight history was based on a PX4 based drones system equipped with a smartphone.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.7
• /
• pp.1074-1080
• /
• 2015

In the last decades, the increasing interest in unmanned aerial vehicle(UAV) for military, surveillance, and rescue applications made necessary the development of flight control theory and body structure more and more efficient and fast. In this paper, we describe the design and performance of a prototype hexarotor UAV platform featuring an inertial measurement unit(IMU) based autonomous-flying for use in bluetooth communication environments. The proposed system comprises the construction of the test hexarotor platform, the implementation of an IMU, dynamic modeling and simulation in the hexarotor helicopter. Furthermore, the hexarotor helicopter with implemented IMU is connected with a micro controller unit(ARM-cortex) board. The P-PD control algorithm was used to control the hexarotor. We used the Matlab software to help us to tune the P-PD control parameters for quick response and minimizing the fluctuation. The control simulation and experiment on the real system are implemented in the test platform, evaluated and compared against each other.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.4
• /
• pp.482-487
• /
• 2008

In case of flooding, the underwater flight vehicle (UFV) executes the blowing by blowing ballast tanks off using high pressure air (HPA), while it also uses control planes and a propulsion unit to reduce the overshoot depth caused by a flooding and blowing sequence. However, the conventional whole HPA blow-off method lets the body on the surface after blowing despite slight flooding. This results in the unnecessary mission failure or body exposure. Therefore, it is necessary to keep the body at the near surface by the blowing control while reducing the overshoot depth. To solve this problem, an adaptive blowing control algorithm, which is based on the decomposition method expanding the expert knowledge in depth control and the adaptive method using fuzzy basis function expansion (FBFE), is proposed. To verify the performance of the proposed algorithm, the blowing control of UFV is performed. Simulation results show that the proposed algorithm effectively solves the problems in the UFV blowing control system online.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.38 no.5
• /
• pp.490-498
• /
• 2010

This paper presents an autonomous target tracking approach and technique for transmitting ground control station image periodically for an unmanned aerial vehicle using onboard gimbaled(pan-tilt) camera system. The miniature rotary UAV which was used in this study has a small, high-performance camera, improved target acquisition technique, and autonomous target tracking algorithm. Also in order to stabilize real-time image sequences, image stabilization algorithm was adopted. Finally the target tracking performance was verified through a real flight test.

• Journal of Advanced Navigation Technology
• /
• v.16 no.2
• /
• pp.197-203
• /
• 2012

In this paper, study the substantial issues which occurs upon free flight environment by performing separation assurance under multiple conflict(over 3 Aircraft), recovery en route under the terms of time constrains and fixed way point after the conflict avoidance, correlations between conflict detection distance and separation assurance by utilizing Autonomous flight algorithm. Result of this experiment demonstrates that the extension of detection distance is advantageous to solution of separation assurance and enhancing of flight efficiency, choose to maneuver by applying time constrain terms and fixed way point according to the situation of conflict prediction in case of recovery maneuver after the conflict avoidance. And separation assurance can be solved by applying 2 degrees or more of bank angle. When choosing the optimal bank angle could be drastically improved flight efficiency.

• The Journal of Korea Robotics Society
• /
• v.11 no.4
• /
• pp.262-269
• /
• 2016

Flight of an autonomous unmanned aerial vehicle (UAV) generally consists of four steps; take-off, ascent, descent, and finally landing. Among them, autonomous landing is a challenging task due to high risks and reliability problem. In case the landing site where the UAV is supposed to land is moving or oscillating, the situation becomes more unpredictable and it is far more difficult than landing on a stationary site. For these reasons, the accurate and precise control is required for an autonomous landing system of a UAV on top of a moving vehicle which is rolling or oscillating while moving. In this paper, a vision-only based landing algorithm using dynamic gimbal control is proposed. The conventional camera systems which are applied to the previous studies are fixed as downward facing or forward facing. The main disadvantage of these system is a narrow field of view (FOV). By controlling the gimbal to track the target dynamically, this problem can be ameliorated. Furthermore, the system helps the UAV follow the target faster than using only a fixed camera. With the artificial tag on a landing pad, the relative position and orientation of the UAV are acquired, and those estimated poses are used for gimbal control and UAV control for safe and stable landing on a moving vehicle. The outdoor experimental results show that this vision-based algorithm performs fairly well and can be applied to real situations.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.12
• /
• pp.49-56
• /
• 2018

As the era of the 4th industrial revolution comes, there is a growing interest in the use of UAVs. While various technologies are being developed using drones, controlling flight of drones is the most basic. Hovering control is essential in order to enable autonomous flight, especially during flight control of drones. In this paper, we design drones based on ATmega2560, Sonar, Optical Flow, and acceleration / gyro 6 axis sensor for drones hovering control, and developed horizontal control, altitude control, position tracking and fixed algorithm based on PID control. In this research, in order to measure the objective result of the drone, keeping the altitude immediately after the drone takes off according to the time, measure the movement value until the position is fixed and stable hovering is maintained and compared analyzed. Experimental results show that the drones can stably hover within 4cm horizontal and 2cm vertical from 50cm above the reference coordinates.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.38 no.3
• /
• pp.228-235
• /
• 2010

This paper deals with an autonomous flight controller design problem for a tilt-rotor aircraft in rotary-wing mode. The inner-loop algorithm is designed using the output-based approximate feedback linearization. The model error originated from the feedback linearization is cancelled within allowable tolerance by using single-hidden-layer neural network. According to Lyapunov direct stability theory, the adaptive update law is derived to run the neural network on-line, which is based on the linear observer dynamics. Moreover, the outer-loop algorithm is designed to track the trajectory generated from way-point guidance. Especially, heading and flight-path angle line-of-sight guidance are applied to the outer-loop to improve accuracy of the landing tracking performance. The 6-DOF nonlinear simulation shows that the overall performance of the flight control algorithm is satisfactory even though the collective input response shows instantaneous actuator saturation for a short time due to the lack of the neural network and the saturation protection logic in that loop.

• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.2_2
• /
• pp.255-261
• /
• 2020

We consider the problem of autonomously flying a quadcopter in indoor environments. Navigation in indoor settings poses two major issues. First, real time recognition of the marker captured by the camera. Second, The combination of the distributed images is used to determine the position and orientation of the quadcopter in an indoor environment. We autonomously fly a miniature RC quadcopter in small known environments using an on-board camera as the only sensor. We use an algorithm that combines data-driven image classification with image-combine techniques on the images captured by the camera to achieve real 3D localization and navigation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.10
• /
• pp.1247-1255
• /
• 2016

The safety and autonomous flight function of micro UAV or drones is crucial to its commercial application. The requirement of own building stable drones is still a non-trivial obstacle for researchers that want to focus on the intelligence function, such vision and navigation algorithm. The paper present a GCS using commercial drone and hardware platforms, and open source software. The system follows modular architecture and now composed of the communication, UI, image processing. Especially, lane-keeping algorithm. are designed and verified through testing at a sports stadium. The designed lane-keeping algorithm estimates drone position and heading in the lane using Hough transform for line detection, RANSAC-vanishing point algorithm for selecting the desired lines, and tracking algorithm for stability of lines. The flight of drone is controlled by 'forward', 'stop', 'clock-rotate', and 'counter-clock rotate' commands. The present implemented system can fly straight and mild curve lane at 2-3 m/s.