• Journal of the Korea Institute of Military Science and Technology
• /
• 제27권4호
• /
• pp.474-484
• /
• 2024

Reinforcement learning, which are also studied in the field of defense, face the problem of sample efficiency, which requires a large amount of data to train. Transfer learning has been introduced to address this problem, but its effectiveness is sometimes marginal because the model does not effectively leverage prior knowledge. In this study, we propose a stochastic initial state randomization(SISR) method to enable robust knowledge transfer that promote generalized and sufficient knowledge transfer. We developed a simulation environment involving a cooperative robot transportation task. Experimental results show that successful tasks are achieved when SISR is applied, while tasks fail when SISR is not applied. We also analyzed how the amount of state information collected by the agents changes with the application of SISR.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.427-427
• /
• 2000

In this study, singularity of two types of mobile robots for various input joints are investigated: One is the mobile robot with three caster wheels and the other is the mobile robot with two conventional wheels and one caster wheel. Kinematic models are derived via the transfer method of generalized coordinates. Then, determinants of the Jacobian of the mobile robots are used to identify the singularity configurations.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 한국정밀공학회 2005년도 추계학술대회 논문집
• /
• pp.744-747
• /
• 2005

This research studied 6-Axes Articulated Robot Manipulator's gain Tuning in consideration of dynamic. First of all, search fur proportional gain of velocity control loop by dynamic signal analyzer. Proportional gain of velocity control loop is connected to dynamic signal analyzer. Next Select free Proportional Gain value. And Select amplitude X of sinusoidal properly so that enough Velocity Feedback Signal may be paid as there is no group to utensil department. Next step, We can get Bode Diagram of Closed loop transfer function response examination in interested frequency. Integral calculus for gain of velocity loop is depended on integral calculus correction's number. We can obtain open loop transfer function by integrator. And we can know bode diagram's special quality from calculated open loop transfer function. With this, Velocity Control Loop's Parameter as inner loop is controlled. Next In moving, when vibration occurs, it controls notch filter. And finally, we have to control fred-forward filter parameter for elevation of control performance.

• Journal of the Microelectronics and Packaging Society
• /
• 제31권2호
• /
• pp.45-53
• /
• 2024

The maintenance of semiconductor equipment is crucial for the continuous growth of the semiconductor market. System management is imperative given the anticipated increase in the capacity and complexity of industrial equipment. Ensuring optimal operation of manufacturing processes is essential to maintaining a steady supply of numerous parts. Particularly, monitoring the status of substrate transfer robots, which play a central role in these processes, is crucial. Diagnosing failures of their major components is vital for preventive maintenance. Fault diagnosis methods can be broadly categorized into physics-based and data-driven approaches. This study focuses on data-driven fault diagnosis methods due to the limitations of physics-based approaches. We propose a methodology for data acquisition and preprocessing for robot fault diagnosis. Data is gathered from vibration sensors, and the data preprocessing method is applied to the vibration signals. Subsequently, the dataset is trained using Gradient Tree-based XGBoost machine learning classification algorithms. The effectiveness of the proposed model is validated through performance evaluation metrics, including accuracy, F1 score, and confusion matrix. The XGBoost classifiers achieve an accuracy of approximately 92.76% and an equivalent F1 score. ROC curves indicate exceptional performance in class discrimination, with 100% discrimination for the normal class and 98% discrimination for abnormal classes.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• 제20권1호
• /
• pp.146-153
• /
• 1996

A SCARA type direct drive robot which can be used in the assembly operation was designed and manufactured. Graphite fiber epoxy composite material was used in the fabrication of the robot arm structure in order to improve the speed of the robot arm with a high damping effect. For model-based control and sensitivity analysis of system parameters, the dynamic model of robot arm and drive servo amplifier parameters such as equivalent gains of PWM driver and velocity gains of servo system were estimated from frequency response tests. The complete dynamic model for overall robot system was used in the simulation of the open-loop control. The simulation results agreed reasonably well to the experimental results. The feedforward control using the dynamic models improved the trajectory tracking performance, decreasing the tracking error by factor of three compared with PID control. This study found that the inverse dynamic model of the robot arm including the drive servo system showed better performances than the case of arm dynamic model only.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국제학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.160-163
• /
• 1993

In this paper, design of an automatic grinding robot system for car brazing bead is introduced. Car roof and side panels are joined using brazing, and then the brazing bead is processed so that the bead is invisible after painting. Up to now the grinding process is accomplished manually. The difficulties in automation of the grinding process are induced by variation of position and shape of the bead and non-uniformity of the grinding area due to surface deformation. For each car, the grinding area including the brazing bead is sensed and then modeled using a 2-D optical sensor system. Using these model data, the position and the direction of discrete points on the car, body surface are obtained to produce grinding path for a 6 degrees of freedom grinding robot. During the process, it is necessary to sense the reaction forces continuously to prepare for the unexpected circumstances. In addition, to meet the line cycle time it is necessary to reduce the required time in sensing, signal processing, modeling, path planning and data transfer by utilizing real-time communication of the information. The key technique in the communication and integration of the complex information is obtaining in-field reliability. This automatic grinding robot system may be regarded as a jump in the intelligent robot processing technique.

• Journal of the Korean Society of Industry Convergence
• /
• 제22권3호
• /
• pp.281-292
• /
• 2019

This paper proposed a new technology to control a path forging parts in limited narrow space of manufacturing process automation for smart factory. In the motion control, we adapted the obstacle avoidance technology based on ultrasonic sensors. The new motion control performance test for a mobile robot is experimented in narrow space environments. The travelling path control is performed by a fuzzy control logic. which plays a role for selecting an appropriate behavior in accordance with the situation in the vicinity of the mobile robot. Ultrasonic sensors installed at the front face of the mobile robot are used. In order to update the current position and heading angle of the mobile robot, a new approch is adapted. The reliability is illustrated by simulation and experiments.

• Nuclear Engineering and Technology
• /
• 제54권4호
• /
• pp.1374-1381
• /
• 2022

Under the influence of nuclear radiation, the reliability of steam generators (SGs) is an important factor in the efficiency and safety of nuclear power plant (NPP) reactors. Motion planning that remotely manipulates an SG mobile tube-inspection robot to inspect SG heat transfer tubes is the mainstream trend of NPP robot development. To achieve motion planning, conditional traversal is usually used for base position optimization, and then the A^* algorithm is used for path planning. However, the proposed approach requires considerable processing time and has a single expansion during path planning and plan paths with many turns, which decreases the working speed of the robot. Therefore, to reduce the calculation time and improve the efficiency of motion planning, modifications such as the matrix method, improved parent node, turning cost, and improved expanded node were proposed in this study. We also present a comprehensive evaluation index to evaluate the performance of the improved algorithm. We validated the efficiency of the proposed method by planning on a tube sheet with square-type tube arrays and experimenting with Model SG.

• Korea Trade Review
• /
• 제47권5호
• /
• pp.241-251
• /
• 2022

As a 4th industrial revolution technology, robots are changing the form of labor market and trade in Korea. In the future, changes in the international trade order are expected to move in the direction of shortening global supply chains and restricting trade between countries. Accordingly, reshoring of relocating overseas production facilities to Korea or near-shoring of relocating overseas production facilities to neighboring allies may expand. In this context, this study analyzed the impact of robot introduction on the domestic labor market and trade based on firm-level data. As a result of analysis based on the 'business activity data' accumulated from 2017 to 2019, the introduction of robot technology was analyzed to expand low-wage, low-skilled employment. Analysis on trade shows that the introduction of robots decreases exports and increases imports. In order to expand exports through the technology of the 4th industrial revolution, employment expansion and robot introduction should occur at the same time, rather than replacing the labor force with robots. In addition, it is thought that reshoring's goal of risk management can be achieved when a stable supply chain for imports of raw materials or essential goods, which are difficult to transfer to Korea, is established together.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 한국건축시공학회 2023년도 가을학술발표대회논문집
• /
• pp.263-264
• /
• 2023

3D printing technology is recognized as a core technology that will lead the next generation, and is a field that can have a large ripple effect if it innovates the existing construction production method. Therefore, this study deals with the development of a 3d printing system using an articulated robot for construction purposes. In this system, ABB robot was used to control the developed cement gun accurately. The system is composed of mixer to mix cementitious materials, pump to transfer the materials, abb robot to motion control and cement gun to extrude the materials to print required construction parts. Using the system developed in this study, a suitable mix ratio of cementitious materials was found and successively printed a 1m high structure that demonstrated possibility of printing structures using 3d printer. In the future, we plan to build a foundation for automated construction through research on construction methods and materials that can be continuously layered for the system.