• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2002.04a
• /
• pp.393-398
• /
• 2002

Neural networks are used in the framework of sensorbased tracking control of robot manipulators. They learn by practice movements the relationship between PSD (an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. forthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple backpropagation networks one of which is selected according to which division (corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.04a
• /
• pp.253-257
• /
• 2004

Neural networks are works are used in the framework of sensor based tracking control of robot manipulators. They learn by practice movements the relationship between PSD(an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple back propagation networks one of which is selected according to which division(corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2001.04a
• /
• pp.239-243
• /
• 2001

Neural networks are used in the framework of sensorbased tracking control of robot manipulators. They learn by practice movements the relationship between PSD (an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple backpropagation networks one of which is selected according to which division (corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• Proceedings of the IEEK Conference
• /
• 2003.07a
• /
• pp.190-193
• /
• 2003

The DOA(Direction Of Arrival) estimation to select a best beam for receiving a particular signal in switched beam antenna systems, and to shape the optimal beam in adaptive array antenna systems, is typically performed under the assumption that the target user motion is almost negligible. In this paper, we model the user as the time-varying source and adopt the LPA(Local Polynomial Approximation) tracking algorithm, proposed by Katkovnik, to solve the time-varying DOA estimation problem. Then, we compare the power spectrum functions between the LPA beamformer and the conventional beamformer, also, the normalized SNRs of each beamformer. The results show that the LPA beamformer is robuster than the conventional beamformer in tine-varying environments. In addition, in case of the conventional beamformer, more array elements give rise to more degradation in the aspect of SNR.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.04a
• /
• pp.171-175
• /
• 2000

Neural networks are in the framework of sensorbased tracking control of robot manipulators. They learn by practice movements the relationship between PSD (an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple backpropagation networks one of which is selected according to which division (corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.10a
• /
• pp.108-112
• /
• 2000

Neural networks are used in the framework of sensorbased tracking control of robot manipulators. They learn by practice movements the relationship between PSD (an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple backpropagation networks one of which is selected according to which division (corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• Journal of the Korean Society of Industry Convergence
• /
• v.7 no.2
• /
• pp.167-172
• /
• 2004

Neural networks are used in the framework of sensor based tracking control of robot manipulators. They learn by practice movements the relationship between PSD(an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple back propagation networks one of which is selected according to which division (Corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• Journal of IKEEE
• /
• v.13 no.2
• /
• pp.150-158
• /
• 2009

For the autonomous movement, the optimal path planning connecting between current and target positions is essential, and the optimal path of mobile robot means obstacle-free and the shortest length path to a target position. Many actual mobile robots should move without any information of surrounded obstacles. Thus, this paper suggests new methods of path planning and obstacle avoidment, suitable in unknown environments. This method of path planning always tracks the local target expected as the optimal one, and the result of continuous tracking becomes the first generated moving path. This path, however, do not regard the collision with obstacles. Thus, this paper suggests a new method of obstacle avoidance resembled with the Potential Field method. Finally, a simulation confirms the performance and correctness of the path planning and obstacle avoidance, suggested in this paper.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.11
• /
• pp.898-905
• /
• 2018

In this work, infrared targets for a developed hardware-in-the-loop simulation(HILS) system are proposed for a performance test of a dual-sensor imaging seeker equipped with an infrared and a visible sensor that can lock and track for ground and air targets. This integrated system is composed of 100 modules of heat and light sources to simulate various kinds of target and the trajectory of moving targets based on scenarios. It is possible to simulate not only the position, velocity, and direction for these targets but also background clutter and jamming environments. The design and measurement results of an infrared target, such as the HILS system configuration, developed for testing and evaluation of a dual-sensor imaging seeker are described. In the future, it is planned to test the lock-on and tracking performance of an imaging seeker equipped with single or dual sensors dynamically in real time based on a simulation flight scenario in the developed HILS system.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.25 no.1
• /
• pp.99-107
• /
• 2014

Abruptly occurred obstacles on highway threaten driving safety. Radar draws the attention to the collision avoidance system because it can be fully operational in all weather, and day and night condition. This paper presents the design, implementation and performance test results of pulsed Doppler radar system for detection and warning of road obstacles. The system is designed to consider highway environment and detection capability about various fixed and moving obstacles. The system consists of 4 subsystems, which include antenna unit, transmitter and receiver unit, radar signal & data processing unit, and controller & display unit. The core technologies include clutter map based change detection for fixed obstacles detection, Doppler estimation for velocity detection of moving targets, and azimuth angle estimation method using monopulse for lane estimation and tracking. The design performance of the developed radar system is verified through experiments using a fixed reference target and moving vehicles in test highway.