• Korean Journal of Remote Sensing
• /
• v.24 no.5
• /
• pp.473-481
• /
• 2008

This paper presents an approach to Back-propagation and Radial Basis Function neural network method with various training set for automatic vehicle detection from aerial images. The initial extraction of candidate object is based on Mean-shift algorithm with symmetric property of a vehicle structure. By fusing the density and the symmetry, the method can remove the ambiguous objects and reduce the cost of processing in the next stage. To extract features from the detected object, we describe the object as a log-polar shape histogram using edge strengths of object and represent the orientation and distance from its center. The spatial histogram is used for calculating the momentum of object and compensating the direction of object. BPNN and RBFNN are applied to verify the object as a vehicle using a variety of non-car training sets. The proposed algorithm shows the results which are according to the training data. By comparing the training sets, advantages and disadvantages of them have been discussed.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.1
• /
• pp.39-46
• /
• 2012

An unmanned aerial vehicle (UAV) is a powered aerial vehicle that does not carry a human operator, uses aerodynamic forces to provide vehicle lift, can fly autonomously or be piloted remotely, can be expendable or recoverable, and can carry a lethal or non-lethal payload. An UAV is very important weapon system and is currently being employed in many military missions (surveillance, reconnaissance, communication relay, targeting, strike, etc.) in the war. To accomplish UAV's missions, guarantee of survivability should be preceded. The main objective of this study is a local path planning to maximize survivability for UAV on the battlefield of dynamic threats (obstacles, surface-to-air missiles, radar etc.). A local path planning is capable of producing a new path in response to environmental changes. This study suggests a $Smart$ $A^*$ (Smart A-star) algorithm for local path planning. The local path planned by $Smart$ $A^*$ algorithm is compared with the results of existing algorithms ($A^*$ $Replanner$, $D^*$) and evaluated performance of $Smart$ $A^*$ algorithm. The result of suggested algorithm gives the better solutions when compared with existing algorithms.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.2
• /
• pp.131-138
• /
• 2004

Automatic flight control system (AFCS) for a low-cost unmanned aerial vehicle is described in this paper. Development process and block diagram of the AFCS are introduced. The flight control law for longitudinal and lateral channel autopilot is designed using optimization process. In this procedure, the performance index is composed of desired location of closed loop system poles and H$_2$norm of the resultant flight control system. This procedure is applied to the autopilot design of an unmanned target vehicle. Performance of the AFCS is evaluated by processor-in-the-loop simulation test and flight test. These results show that the AFCS has acceptable performance fur low cost UAV.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.2
• /
• pp.61-68
• /
• 2005

This paper is concerned with attitude control of 2 rotor 1 DOF aerial vehicle. The proposed controller consists of two parts: the attitude estimation filter part and PID controller part. For attitude estimation, performance of 3 different filters (complementary filters, Kalman filter, indirect Kalman filters) are tested and compared. For the PID controller, characteristic ratio assignment methods are used to assign PID coefficients. Through experiments, it is shown that attitude of the vehicle successfully follows the step command.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2007.06a
• /
• pp.727-728
• /
• 2007

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.44 no.12
• /
• pp.1095-1102
• /
• 2016

This paper presents the results of the design, fabrication and tether test for a gross weight 20 kg tilt-duct VTOL aerial robot. The tilt-duct vehicle, a tri-ducts air-vehicle, which composed of two main tilt ducts for thrust and an aft-fan for pitch attitude control, has been developed as an aerial platform. The research on the air vehicle has been focused on the hover characteristics and controllability to improve the thrust and stability. The tether test for measuring various performance of vehicle and evaluating controllability have been carried out to figure out effects of modified main-prop linkage, actuator, duct configuration and control surfaces.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.32 no.10
• /
• pp.127-133
• /
• 2004

This paper described development of the portable ground control system(PGCS) for unmanned aerial vehicle. In the design of GCS, it upload mission planning that aircraft has to perform and has to receive position, attitude, state, navigation information all about the aircraft. Aircraft states and trajectory are displayed using this system on line. The PGCS is composed of commercial notebook computer, RF modem for communication between aircraft and PGCS, input/output board, remote control receiver, switches and lamps. Performance of this system is verified by flight test of small unmanned aerial vehicle.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.5
• /
• pp.55-72
• /
• 2016

This study aims at providing a methodology for retaining international technology competitiveness, marketable industry, and sustainable promising technology in a field of new growth engine industry such as national unmanned aerial vehicle industry. We draw a result by analysing with tools such as KrKwic, Excel, NetMiner, presenting methods of a Social Network Analysis, sub-group analysis, and cognitive map analysis based on patent data in a field of unmanned aerial vehicle industry. As a result, some future promising technologies are prospected as what worths concentrated investment, such as 'pilot control tech', 'identification of friend or foe tech'.

• Journal of Advanced Navigation Technology
• /
• v.13 no.6
• /
• pp.813-819
• /
• 2009

Designing actuator controllers of aircraft, which control aileron, flap, elevator and so on, is quiet difficult, because they have time variant nonlinear mechanical structures and also have many kinds of disturbances which are not been able to model easily. This paper reports about the performance of Fuzzy Auto gain tuning Control algorithm applied unmaned aerial vehicle. Fuzzy Auto gain tuning PID control uses PID control and Fuzzy control, therefore It can be applied very easily and it also has advances of PID control. It can control a unmaned aerial vehicle actuators adaptively even though the designer does not have enough information of plant.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.15 no.4
• /
• pp.424-434
• /
• 2012

This paper presents a path planning algorithm of the unmanned aerial vehicle for the neutralization of the enemy firepower. The long range firepower of the ememy is usually located at the rear side of the mountain which is difficult to bomb. The path planner not only consider the differential constraints of the Unmanned Aerial Vehicle (UAV) but also consider the final approaching angle constraint. This problem is easily solved by incorporating the analytical upper bounded continuous curvature path smoothing algorithm into the Rapidly Exploring Random Tree (RRT) planner. The proposed algorithm can build a feasible path satisfying the kinematic constraints of the UAV on the fly. In addition, the curvatures of the path are continuous over the whole path. Simulation results show that the proposed algorithm can generate a feasible path of the UAV for the bombing mission regardless of the posture of the tunnel.