• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.699-705
• /
• 2009

This paper is represented to research of driving control for the forklift AGV. The related works that were studied about AGV as heavy equipment used two methods which are magnet-gyro and wire guidance for localization. However, they have weaknesses that are high cost, difficult maintenance according to change of environment. In this paper, we develop localization system through sensor fusion with laser navigation system and encoder, gyro for robustness. Also we design driving controller using fuzzy and proportional control. It considers distance and angle difference between forklift AGV and pallet for engaging work. To analyze performance of the proposed control system, we experiment in same working condition over 10 times. In the results, the average error was presented with 54.16mm between simulation of control navigation and real control navigation. Consequently, experimental result shows that the performance of proposed control system is effective.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.27 no.1
• /
• pp.22-28
• /
• 2017

The Convolutional Neural Network(CNN) can be divided into two stages: feature extraction and classification. The hyperparameters such as kernel size, number of channels, and stride in the feature extraction step affect the overall performance of CNN as well as determining the structure of CNN. In this paper, we propose a method to optimize the hyperparameter in CNN feature extraction stage using Parameter-Setting-Free Harmony Search (PSF-HS) algorithm. After setting the overall structure of CNN, hyperparameter was set as a variable and the hyperparameter was optimized by applying PSF-HS algorithm. The simulation was conducted using MATLAB, and CNN learned and tested using mnist data. We update the parameters for a total of 500 times, and it is confirmed that the structure with the highest accuracy among the CNN structures obtained by the proposed method classifies the mnist data with an accuracy of 99.28%.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.5
• /
• pp.237-242
• /
• 2023

Research on high-performance walking robots is being actively conducted, and quadruped walking robots are receiving a lot of attention due to their excellent mobility and adaptability on uneven terrain, but they are difficult to introduce and utilize due to high cost. In this paper, to increase utilization by applying intelligent functions to a low-cost quadruped robot, we present a method of improving uneven terrain overcoming ability by mounting IMU and reinforcement learning on embedded board and automatically detecting objects using camera and deep learning. The robot consists of the legs of a quadruped mammal, and each leg has three degrees of freedom. We train complex terrain in simulation environments with designed 3D model and apply it to real robot. Through the application of this research method, it was confirmed that there was no significant difference in walking ability between flat and non-flat terrain, and the behavior of performing person detection in real time under limited experimental conditions was confirmed.

• Journal of Practical Engineering Education
• /
• v.16 no.1_spc
• /
• pp.1-9
• /
• 2024

The introduction of smart factory digital twins is a concept that has already been proposed to increase productivity in the manufacturing industry through CPS(Cyber Physics System), and has been applied to specific industrial process stages or partially introduced in stages where simulation is required. However, with the recent development of the 4th Industrial Revolution technology, it is receiving attention again along with XR (Extended Reality) technology. However, because there are not many effective cases, this study analyzed the devices, equipment, and technology of the manufacturing process to build a digital twin applying digital threads and synchronized signals and information to control, remote control, and produce intelligent process automation equipment. A platform capable of analyzing information was proposed and developed. Through this, we designed and built an XR content service platform that can support artificial intelligence and developed it to enable control, remote control, and analysis of production information. A possible platform was proposed and developed. We hope that this study will be helpful in conducting research on many cases, and in the future, expanded research on increasing productivity in each part of the process and production is needed through intelligent models.

• Journal of Advanced Navigation Technology
• /
• v.28 no.4
• /
• pp.566-573
• /
• 2024

Applying autonomous driving technology to construction sites is very difficult due to safety issues. However, the application of various positioning and sensing devices, such as cameras and radars, to construction equipment is very active. Based on these technological trends, the government is making various efforts, including the Serious Accident Punishment Act and support for industrial safety management expenses, to reduce the incidence of accidents caused by construction equipment and industrial vehicles. And, related industries have been developing various safety equipment over the past few years and applying them to the field. In this paper, we investigate the current status of safety equipment-related technologies currently applied to construction equipment and industrial vehicles, and propose a direction for the development of safety technology in construction equipment based on artificial intelligence. Improving the safety and work efficiency of construction equipment based on the technology proposed in this paper should be reviewed through simulation in the future.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.3
• /
• pp.253-261
• /
• 2004

Game theory is mathematical analysis developed to study involved in making decisions. In 1928, Von Neumann proved that every two-person, zero-sum game with finitely many pure strategies for each player is deterministic. As well, in the early 50's, Nash presented another concept as the basis for a generalization of Von Neumann's theorem. Another central achievement of game theory is the introduction of evolutionary game theory, by which agents can play optimal strategies in the absence of rationality. Not the rationality but through the process of Darwinian selection, a population of agents can evolve to an Evolutionary Stable Strategy (ESS) introduced by Maynard Smith. Keeping pace with these game theoretical studies, the first computer simulation of co-evolution was tried out by Hillis in 1991. Moreover, Kauffman proposed NK model to analyze co-evolutionary dynamics between different species. He showed how co-evolutionary phenomenon reaches static states and that these states are Nash equilibrium or ESS introduced in game theory. Since the studies about co-evolutionary phenomenon were started, however many other researchers have developed co-evolutionary algorithms, in this paper we propose Game theory based Co-Evolutionary Algorithm (GCEA) and confirm that this algorithm can be a solution of evolutionary problems by searching the ESS.To evaluate newly designed GCEA approach, we solve several test Multi-objective Optimization Problems (MOPs). From the results of these evaluations, we confirm that evolutionary game can be embodied by co-evolutionary algorithm and analyze optimization performance of GCEA by comparing experimental results using GCEA with the results using other evolutionary optimization algorithms.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.2
• /
• pp.218-224
• /
• 2012

Recently, as the needs of developing the micro autonomous underwater vehicle (AUV) are increasing, the acquisition of the elementary technology is urgent. While they mostly utilizes information of the forward looking sonar (FLS) in conventional studies of the local path control as an elementary technology, it is desirable to use the obstacle avoidance sonar (OAS) because the size of the FLS is not suitable for the micro AUV. In brief, the local path control system based on the OAS for the micro AUV operates with the following problems: the OAS offers low bearing resolution and local range information, it requires the system that has reduced power consumption to extend the mission execution time, and it requires an easy design procedure in terms of its structures and parameters. To solve these problems, an intelligent local path control algorithm based on the beam modeling of OAS with the evolution strategy (ES) and the fuzzy logic controller (FLC), is proposed. To verify the performance and analyze the characteristic of the proposed algorithm, the course control of the underwater flight vehicle (UFV) is performed in the horizontal plane. Simulation results show that the feasibility of real application and the necessity of additional work in the proposed algorithm.

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.302-310
• /
• 2020

In this paper, we have implemented the living waste analysis system based on IoT and AI(Artificial Intelligence), and proposed effective waste process and management method. The Jeju location have the strong point to devise a stratagem and estimate waste quantization, rather than others. Especially, we can recognized the amount variation of waste to the residence people compare to the sightseer number, and the good example a specific waste duty. Thus this paper have developed the IoT device for interconnecting the existed CCTV camera, and use the AI algorithm to analysis the waste image. By using these decision of image analysis, we can inform their deal commend and a decided information to the map of the waste cars. In order to evaluate the performance of IoT, we have experimented the electromagnetic compatibility under a national official authorization KN-32, KN61000-4-2~6, and obtained the stable experimental results. In the further experimental results, we can applicable for an data structure for precise definition command by using the simulated several waste image with artificial intelligence algorithm.

• Journal of the Korean Institute of Gas
• /
• v.19 no.1
• /
• pp.28-37
• /
• 2015

This study presents the development of a well placement optimization model, combining an artificial neural network, which enables high-speed calculation, with a simulated annealing algorithm. The conventional FDM simulator takes excessive time when used to perform a field scale reservoir simulation. In order to solve this problem, an artificial neural network was applied to the model to allow the simulation to be executed within a short time. Also by using the given result, the optimization method, SA algorithm, was implemented to automatically select the optimal location without taking any subjective experiences into consideration. By comparing the result of the developed model with the eclipse simulator, it was found that the prediction performance of the developed model has become favorable, and the speed of calculation performance has also been improved. Especially, the optimum value was estimated by performing a sensitivity analysis for the cooling rate and the initial temperature, which is the control parameter of SA algorithm. From this result, it was verified that the calculation performance has been improved, as well. Lastly, an optimization for the well placement was performed using the model, and it concluded the optimized place for the well by selecting regions with great productivity.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.2
• /
• pp.362-368
• /
• 2018

Making proper judgements in urgent situations facing a submarine at the sea is very critical. This is because the commander's misjudgments could drive the entire ally to destruction in a moment. In order to generate appropriate tactics on behalf of the human commander and to analyze the effectiveness in such emergency situations, studies using intelligent agents and genetic algorithms have been conducted. In this study, inference engine based intelligent agent is adopted to each warship and submarine to generate optimal tactics on the variable environment with genetic algorithms. And we analyze the risk of the alliance according to the performance of the enemy submarine through a simple simulation and generate appropriate tactics using the genetic algorithm. Also generated tactics are evaluated and the results are analyzed to figure out why such results are formed.