• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.3
• /
• pp.344-352
• /
• 1999

There has been requested to automate the welding process in shipyard due to its dependence on skilled operators and the inferior working environments. According to these demands, multiple robot welding system for sub-assembly welding line has been developed, realized and installed at Keoje shipyard. In order to realize automatic welding system, robots have to be equipped with a sensing system to recognize the position of the welding panels. In this research, a camera vision system(CVS) is developed to detect the position of base panels for sub-assembly line in shipbuilding. Two camera vision systems are used in two different stages (fitting and welding) to automate the recognition and positioning of welding lines. For automatic recognition of panel position, various image processing algorithms are proposed in this paper.

• Proceedings of the KIEE Conference
• /
• 1988.11a
• /
• pp.441-444
• /
• 1988

This paper presents a methodology for developing the graphic simulator for a robotic workcell. The Petri Net model is applied to described the system state and the workcell simulation is performed by the event scheduling approach of the model. For the graphic display of simulation process, the information of the workcell resources are stored in hierachically-structured data_babe, and the geometry of the resources is described by robot modelling, component modelling, and world modelling.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.1
• /
• pp.46-51
• /
• 2005

Intelligent Space(ISpace) is the space where many intelligent devices, such as computers and sensors, are distributed. According to the cooperation of many intelligent devices, the environment, it is very important that the system knows the location information to offer the useful services. In order to achieve these goals, we present a method for representing, tracking and human following by fusing distributed multiple vision systems in ISpace, with application to pedestrian tracking in a crowd. And the article presents the integration of color distributions into particle filtering. Particle filters provide a robust tracking framework under ambiguity conditions. We propose to track the moving objects by generating hypotheses not in the image plan but on the top-view reconstruction of the scene. Comparative results on real video sequences show the advantage of our method for multi-object tracking. Simulations are carried out to evaluate the proposed performance. Also, the method is applied to the intelligent environment and its performance is verified by the experiments.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.45-48
• /
• 2006

The system that can generate biological brain information processing mechanism more precisely may have several abilities such as exact cognition, situation decision, learning and inference, and output decision. In this paper, to implement high level information processing and thinking ability in a complex system, the information processing layer based on the biological brain is introduced. The biological brain information processing mechanism, which is analyzed in this paper, provides fundamental information about intelligent engineering system, and the design of the layer that can mimic the functions of a brain through engineering definitions can efficiently introduce an intelligent information processing method having a consistent flow in various engineering systems. The applications proposed in this paper are expected to take several roles as a unified model that generates information process in various areas, such as engineering and medical field, with a dream of implementing humanoid artificial intelligent system.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.3
• /
• pp.372-379
• /
• 2014

This paper surveys past and state-of-the-art SLAM technologies. The standard methods for solving the SLAM problem are the Kalman filter, particle filter, graph, and bundle adjustment-based methods. Kalman filters such as EKF (Extended Kalman Filter) and UKF (Unscented Kalman Filter) have provided successful results for estimating the state of nonlinear systems and integrating various sensor information. However, traditional EKF-based methods suffer from the increase of computation burden as the number of features increases. To cope with this problem, particle filter-based SLAM approaches such as FastSLAM have been widely used. While particle filter-based methods can deal with a large number of features, the computation time still increases as the map grows. Graph-based SLAM methods have recently received considerable attention, and they can provide successful real-time SLAM results in large urban environments.

• Proceedings of the IEEK Conference
• /
• 2002.06e
• /
• pp.13-16
• /
• 2002

In this paper, we newly propose a predictor model which is a method to overcome the time-varying delay in a system and we verify that the predictor model is well suited for the time-delayed system and improves the stability a lot through the experiments. The proposed predict compensator compensates uncertain time delays and minimizes variance of system performance. Therefore it is suitable for the control of uncertain systems and nonlinear systems that are difficult to be modeled. The simulation conditions are set for the cases of various input time delays and simulations are applied for the 2-axis robot arms which are drawing a circle on the plane. Conclusively, the proposed predict compensator represents stable properties regardless of the time delay. As a future research, we suggest to develope a robust control algorithm to compensate the random time delay which occurs in the tole-operated systems.

• Journal of Mechanical Science and Technology
• /
• v.18 no.10
• /
• pp.1691-1699
• /
• 2004

The objective of this study is to present an accurate and simple method to describe the motion of constrained mechanical or structural systems. The proposed method is an elimination method to require less effort in computing Moore-Penrose inverse matrix than the generalized inverse method provided by Udwadia and Kalaba. Considering that the results by numerical integration of the derived second-order differential equation to describe constrained motion veer away the constrained trajectories, this study presents a numerical integration scheme to obtain more accurate results. Applications of holonomically or nonholonomically constrained systems illustrate the validity and effectiveness of the proposed method.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.12 no.1
• /
• pp.64-70
• /
• 2008

Thanks to the breakthroughs in micro fabrication technology, numerous concepts of micro aerospace systems including micro aerial vehicle, nano satellite and micro robot have been proposed. In order to activate these mobile micro systems, high density power in a small scale power source is required. However, we still do not have micro power source that has energy density that can support these systems. In the present article, status of micro power sources are described and alternatives that have been derived from the past experience are proposed.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.945-949
• /
• 1988

In this paper, collision avoidance of two robots working in a common workspace is described. The workspace for a two robot system is defined and classified. JCM (Joint Constraint Map) is designed which shows the region of joint values that must be avoided for collision free motion, and application of the JCM is studied.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.27-34
• /
• 1996

GENIE is a learning-based engine for building intelligent systems. Learning in GENIE proceeds by incrementally modeling its human or technical environment using a neural network and a genetic algorithm. The neural network is used to represent the knowledge for solving a given task and has the ability to grow its structure. The genetic algorithm provides the neural network with training examples by actively exploring the example space of the problem. Integrated into the training examples by actively exploring the example space of the problem. Integrated into the GENIE system architecture, the genetic algorithm and the neural network build a virtually self-teaching autonomous learning system. This paper describes the structure of GENIE and its learning components. The performance is demonstrated on a robot learning problem. We also discuss the lessons learned from experiments with GENIE and point out further possibilities of effectively hybridizing genetic algorithms with neural networks and other softcomputing techniques.