• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.2
• /
• pp.137-143
• /
• 2005

Autonomous mobile robot has an ability to navigate using both map in known environment and sensors for detecting obstacles in unknown environment. In general, autonomous mobile robot navigates by global path planning on the basis of already made map and local path planning on the basis of various kinds of sensors to avoid abrupt obstacles. This paper provides a global path planning method using self-organizing feature map which is a method among a number of neural network. The self-organizing feature map uses a randomized small valued initial weight vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. On the other hand, the modified method in this research uses a predetermined initial weight vectors, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. According to simulation results one can conclude that the modified neural network is useful tool for the global path planning problem of a mobile robot.

• Journal of the Speleological Society of Korea
• /
• no.88
• /
• pp.1-7
• /
• 2008

Recently, it is one of very interest technology of Human Computer Interaction(HCI). Nowadays, it is easy to find out that, for example, inside SF movies people has talking to computer. However, there are difference between CPU language and ours. So, we focus on connecting to CPU. For 30 years many scientists experienced in that technology. But it is really difficult. Our project goal is making that CPU could understand human voice. First of all the signal through a voice sensor will move to BCD (binary code). That elevator helps out people who wants to move up and down. This product's point is related with people's safety. Using a PWM for motor control by ATmega16, we choose a DC motor to drive it because of making a regular speed elevator. Furthermore, using a voice identification module the elevator driven by voice sensor could operate well up and down perfectly from 1st to 10th floor by PWM control with ATmega16. And, it will be clearly useful for high-rise vertical shift with voice recognition sensor driven.

• The Journal of Natural Sciences
• /
• v.12 no.1
• /
• pp.1-9
• /
• 2002

Let G be a connected graph on n vertices. The pebbling number of graph G, f(G), is the least m such that, however m pebbles are placed on the vertices of G, we can move a pebble to any vertex by a sequence of moves, each move taking two pebbles off one vertex and placing one on an adjacent vertex. In this paper, we compute the pebbling number of the Petersen Graph. We also show that the pebbling number of the categorical Product G.H is (m+n)h where G is the complete bipartite graph $K_{m,n}$ and H is the complete graph with $h(\geq4)$ vertices.

• Journal of information and communication convergence engineering
• /
• v.17 no.1
• /
• pp.67-73
• /
• 2019

In the current era of digital technology, and with the help of existing software, digital photo manipulation is becoming easier and faster. One example of this is the development of powerful image processing software that makes it easy for a digital image to be manipulated and edited. It is therefore very important to protect and maintain public trust in digital images. Several methods have been developed to detect image manipulation. In this paper, we compare two methods for detecting image duplication due to copy-move actions, namely the polar coordinate system and the histogram of oriented gradients methods. The former is a method based on the transfer of a Cartesian image to a polar form, making it easy to tell whether there are objects that have undergone a copy/move in an image, while the latter is a method for retrieving information related to the distribution, which uses a target in the local area as a tool to represent the shape of the target. We compare the accuracy, speed and memory usage of these two methods.

• International Journal of Computer Science & Network Security
• /
• v.21 no.4
• /
• pp.1-8
• /
• 2021

The subject of navigation has drawn a large interest in the last few years. Navigation problem (or path planning) finds the path between two points, source location and destination location. In smart cities, solving navigation problem is essential to all residents and visitors of such cities to guide them to move easily between locations. Also, the navigation problem is very important in case of moving robots that move around the city or part of it to get some certain tasks done such as delivering packages, delivering food, etc. In either case, solution to the navigation is essential. The core to navigation systems is the navigation algorithms they employ. Navigation algorithms can be classified into navigation algorithms that depend on maps and navigation without the use of maps. The map contains all available routes and its directions. In this proposal, we consider the first class. In this paper, we are interested in getting path planning solutions very fast. In doing so, we employ a parallel platform, Reconfigurable mesh (R-Mesh), to compute the path from source location to destination location. R-Mesh is a parallel platform that has very fast solutions to many problems and can be deployed in moving vehicles and moving robots. This paper presents two algorithms for path planning. The first assumes maps with linear streets. The second considers maps with branching streets. In both algorithms, the quality of the path is evaluated in terms of the length of the path and the number of turns in the path.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.145-153
• /
• 2021

Automated Guided Vehicle (AGV) is commonly used in manufacturing plant, warehouse, distribution center, and terminal. AGV is self-driven vehicle used to transport material between workstations in the shop floor without the help of an operator, and AGV includes a material transfer system located on the top and driving system at the bottom to move the vehicle as desired. For navigation, AGV mostly uses lane paths, signal paths or signal beacons. Various predominant sensors are also used in the AGV. However, in the conventional AGV, there is a problem of not turning or damaging nearby objects or AGV in a narrow space. In this paper, a new driving system is proposed to move the vehicle in a narrow space. In the proposed driving system, two sets of the combined steering-drive unit are adopted to solve the above problem. A prototype of AGV with the new driving system is developed for the comparative analysis with the conventional AGV. In addition, the experimental result shows the improved performance of the new driving system in the maximum speed, braking distance and positioning precision tests.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.584-590
• /
• 2021

This paper proposes a removal method of signal interference between ultrasound sensors where ghost signals due to interference are excluded and correct signal is recognized in distance mensurement using ultrasound sensors. The proposed method detects and excludes ghost signals when previous measured distance is compared to current measured distance and the distance difference exceeds a threshold. The threshold is fixed in conventional methods, so ghost signals cannot be correctly excluded when ultrasound sensor or target object move rapidly. On the contrary, to improve accuracy, the threshold is not fixed in the proposed method, and the threshold is adpatively determined based on the relative velocity when ultrasound sensor or target object move. Experiments of distance measurement with ultrasound signal interference are carried out where multiple ultrasound sensors of same type are exploited with maximum interference, and the results show that the proposed method efficiently exclude ghost signals.

• International Journal of Advanced Culture Technology
• /
• v.10 no.3
• /
• pp.371-376
• /
• 2022

The purpose of this study is to develop a walking assistance system with mobility support and life support functions so that the elderly with reduced physical ability and patients who are uncomfortable when moving can move comfortably indoors and outdoors, and help social life. An obstacle recognition sensor module that can be applied indoors and outdoors is installed on a lightweight walking aid. The purpose of this study is to develop a walking assistance system with mobility support and life support functions so that the elderly with reduced physical ability and patients who are uncomfortable when moving can move comfortably indoors and outdoors, and help social life. An obstacle recognition sensor module that can be applied indoors and outdoors is installed on a lightweight walking aid. It is a system structure of an integrated actuator and brake system that can avoid obstacles in consideration of the safety of the elderly and is easy to install on the device. In this paper, the design of a lightweight walking aid was designed to increase the convenience of the socially disadvantaged and the elderly with reduced exercise ability. In addition, in order to overcome the disadvantage of being inconvenient to use indoors due to the noise and vibration of the motor during operation, an In-Wheel type motor is applied to develop and apply a low noise, low vibration and high efficiency drive system.

• Journal of information and communication convergence engineering
• /
• v.20 no.3
• /
• pp.181-188
• /
• 2022

An intelligent distributed multi-agent system (IDMS) using reinforcement learning (RL) is a challenging and intricate problem in which single or multiple agent(s) aim to achieve their specific goals (sub-goal and final goal), where they move their states in a complex and cluttered environment. The environment provided by the IDMS provides a cumulative optimal reward for each action based on the policy of the learning process. Most actions involve interacting with a given IDMS environment; therefore, it can provide the following elements: a starting agent state, multiple obstacles, agent goals, and a cluttered index. The reward in the environment is also reflected by RL-based agents, in which agents can move randomly or intelligently to reach their respective goals, to improve the agent learning performance. We extend different cases of intelligent multi-agent systems from our previous works: (a) a proposed environment-clutter-based-index for agent sub-goal selection and analysis of its effect, and (b) a newly proposed RL reward scheme based on the environmental clutter-index to identify and analyze the prerequisites and conditions for improving the overall system.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.55 no.6
• /
• pp.954-959
• /
• 2022

Marine outfalls are used to discharge treated liquid effluents to the environment. An efficiently designed, constructed and operated marine outfall effectively dilutes the discharged effluent, thereby reducing the risk to biota and humans dependent upon the marine environment. In this study, we investigated the effluent transport from a marine outfall at different depths in Masan Bay. A particle-tracking model was used to predict the dispersion of effluent. The model results indicate that some particles released from a depth of 13 m move to the inner area of Masan Bay within 48 h. As the release depth increases after 48 h, the particles move further southward. This suggests that effluent from the outer area of Masan Bay can affect the inner area, and that this effect can be reduced by increasing the depth of effluent release.