• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1916-1917
• /
• 2011

A development of a new moving obstacle avoidance algorithm using a delay-time Compensation for a network-based autonomous mobile robot is proposed in this paper. The moving obstacle avoidance algorithm is based on a Kalman filter through moving obstacle estimation and a Bezier curve for path generation. And, the network-based mobile robot, that is a unified system composed of distributed environmental sensors, mobile actuators, and controller, is compensated by a network delay compensation algorithm for degradation performance by network delay. The network delay compensation method by a sensor fusion using the Kalman filter is proposed for the localization of the robot to compensate both the delay of readings of an odometry and the delay of reading of environmental sensors. Through some simulation tests, the performance enhancement of the proposed algorithm in the viewpoint of efficient path generation and accurate goal point is shown here.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.9 no.4
• /
• pp.75-84
• /
• 2000

The main goal of our research is to compensate the milled surface errors induced by the tool deflection effects, which occur during the milling process. First, we predict cutting forces and tool deflection amount. Based on predicted deflection effects, we model milled surface shapes. We present a compensation methodology , which can generate a new tool trajectory, which is determined so as to compensate the milled surface errors. By considering manufacturing tolerance, tool path compensation is generalized. To validate the approaches proposed in this paper, we treat an illustrative example of profile milling process by using flat end mill. Simulation and experimental results are shown.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.14 no.6
• /
• pp.1542-1551
• /
• 1990

This paper shown how to measure the machining error in diameter of cylindrical workpiece and compensate the measured machining error in NC turning. Machining error is measured by the electric micrometer mounted on the tool post with the NC part program for probe location path analyzed. Correct NC part program for finish turning is automatically generated to compensate the measured machining error. These concepts have been effectively introduced to a newly developed software for error compensation. In turning experiments with the developed error compensation system, machining error was almost within the specified tolerance, which reveals the effectiveness of the developed system.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.11
• /
• pp.84-92
• /
• 1997

The purpose of this study is to develop a geometric error model and path compensation algorithm for rotating axes of the 5-axis machine tools, by a method to calibrate a rotary table using one master ball and three LVDTs. It was developed a new methodology to measure 3 translation errors of the rotary table and with a compensation procedure for setup errors of the master ball. The method is experimentally verified using a ball-table and on-machine inspection method. The results showed that the geometric error models with the path compensation strategy can be practically used as a means for improving the accuracy of the machine tools with rotary table.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.4
• /
• pp.95-102
• /
• 2004

It is necessary to improve the exactness and adaptation of the working environment in the intelligent robot system. The vision sensor have been studied for this reason fur a long time. However, it is very difficult to perform the camera and robot calibrations because the three dimensional reconstruction and many processes are required for the real usages. This paper suggests the image based visual servoing to solve the problem of old calibration technique and supports OLP(Off-Line-Programming) path compensation. Virtual camera can be modeled from the real factors and virtual images obtained from virtual camera gives more easy perception process. Also, Initial path generated from OLP could be compensated by the pixel level acquired from the real and virtual, respectively. Consequently, the proposed visually assisted OLP teaching remove the calibration and reconstruction process in real working space. With a virtual simulation, the better performance is observed and the robot path error is calibrated by the image differences.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.79-84
• /
• 1992

Path planning is an important task for optimal motion of a robot in structured or unstructured environment. The goal of this paper is to plan the optimal collision-free path in 3D, when a robot is navigated to pick up some tools or to repair some parts from various locations. To accomplish the goal, the Path Coordinator is proposed to have the capabilities of an obstacle avoidance strategy and a traveling salesman problem strategy (TSP). The obstacle avoidance strategy is to plan the shortest collision-free path between each pair of n locations in 2D or in 3D. The TSP strategy is to compute a minimal system cost of a tour that is defined as a closed path navigating each location exactly once. The TSP strategy can be implemented by the Hopfield Network. The obstacle avoidance strategy in 2D can be implemented by the VGraph Algorithm. However, the VGraph Algorithm is not useful in 3D, because it can't compute the global optimality in 3D. Thus, the Path Coordinator is used to solve this problem, having the capabilities of selecting the optimal edges by the modified Genetic Algorithm and computing the optimal nodes along the optimal edges by the Recursive Compensation Algorithm.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2001.04a
• /
• pp.376-381
• /
• 2001

This paper presents a methodology of machining error compensation by using Artificial Neural Network(ANN) model based on the inspection database of On-Machine-Measurement(OMM) system. First, the geometric errors of the machining center and the probing errors are significantly reduced through compensation processes. Then, we acquire machining error distributions from a specimen workpiece. In order to efficiently analyze the machining errors, we define two characteristic machining error parameters. These can be modeled by using an ANN model, which allows us to determine the machining errors in the domain of considered cutting conditions. Based on this ANN model, we try to correct the tool path in order to effectively reduce the errors by using an iterative algorithm. The iterative algorithm allows us to integrate changes of the cutting conditions according to the corrected tool path. Experimentation is carried out in order to validate the approaches proposed in this paper.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1992.10a
• /
• pp.34-38
• /
• 1992

Geometry based CAD/CAM system is hard to achieve "net shape machining" For a net shape machining, the machining errors should be compensated by off-line CAD/CAM system followed by on-line control system. In this paper, we investigate an off-line compensation scheme for the machining errors due to tool deflection in contouring operation. The significance of the deflection errors is first shown, and a compensation is sought via modifying the nominal tool path. In modification, tool deflection amount is iteratively compensated until the deflection amount is iteratively compensated until the deflected path results in the desired contour within a tolerance. The path modification algorithm has been tested via computer simulation. The developed algorithm can be used as a postprocessor for the current CAD/CAM system based on geometric modeling as a means for enhancing the machining accuracy.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.05a
• /
• pp.866-869
• /
• 2000

The finishing process for die is an important process because it has influence on final quality of products. And it is difficult to automatize finishing process so that the process has depended on expert's skill until now. However, recently a study on development of die automatic finishing machine has been progressed, and actually this machine is applied to fabrication of die. But die automatic finishing machine has the problems such as low supply rate and high machine price. In this paper 3-axis machine was applied to the die finishing. And to improve form accuracy of die finishing path was regenerated. The finishing path considered tilting of finishing tool. and variation of machining force with contacting point between finishing and workpiece.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.50-55
• /
• 2021

Multi-path system is a system in which utilizes various networks simultaneously. It is expected that multi-path system can enhance communication speed, reliability, security of network. In this paper, we focus on path selection in multi-path system. To select optimal path, we propose deep reinforcement learning algorithm which is rewarded by the round-trip-time (RTT) of each networks. Unlike multi-armed bandit model, deep Q learning is applied to consider rapidly changing situations. Due to the delay of RTT data, we also suggest compensation algorithm of the delayed reward. Moreover, we implement testbed learning server to evaluate the performance of proposed algorithm. The learning server contains distributed database and tensorflow module to efficiently operate deep learning algorithm. By means of simulation, we showed that the proposed algorithm has better performance than lowest RTT about 20%.