• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.12
• /
• pp.2308-2312
• /
• 2008

As power plant facilities are being deteriorated, their safety is getting more important, and more routine surveillance is being required. For this purpose, this paper presents an indoor localization system for field robot system which performs the surveillance of power plant facilities instead of human workers from the viewpoint of the workers' safety and work efficiency.

• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.11-14
• /
• 2003

In this paper, we use Fuzzy Logic and Potential field method for optimal path planning of an autonomous mobile robot and apply to navigation for real-time mobile robot in 2D dynamic environment. For safe navigation of the robot, we use both Global and Local path planning. Global path planning is computed off-line using sell-decomposition and Dijkstra algorithm and Local path planning is computed on-line with sensor information using potential field method and Fuzzy Logic. We can get gravitation between two feature points and repulsive force between obstacle and robot through potential field. It is described as a summation of the result of repulsive force between obstacle and robot which is considered as an input through Fuzzy Logic and gravitation to a feature point. With this force, the robot fan get to desired target point safely and fast avoiding obstacles. We Implemented the proposed algorithm with Pioneer-DXE robot in this paper.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1459-1466
• /
• 2018

Robots which detect human and recognize action are important factors for human interaction, and many researches have been conducted. Recently, deep learning technology has developed and learning based robot's technology is a major research area. These studies require a database to learn and evaluate for intelligent human perception. In this paper, we propose a multi-modal sensor-based image database condition considering the security task by analyzing the image database to detect the person in the outdoor environment and to recognize the behavior during the running of the robot.

• Journal of Drive and Control
• /
• v.17 no.4
• /
• pp.103-112
• /
• 2020

Field robots are used in various fields, such as agriculture, forestry, manufacturing, and construction; their use has recently expanded to include submarine areas. Field robots can aid in various tasks, such as soil transport, ground clearance, and dismantling of buildings. As field robots are used in a variety of different areas, the difficulty of the work is also quite varied. Increased difficulty is associated with an increased risk of accidents involving the field robot. In order to reduce the accident rate of field robot workers, the need for digitalization and automation of field robots is becoming more of an issue. To this end, it is necessary to study a system that enables workers to do their work without directly contacting a field robot. Therefore, in this paper, we introduce a control system for wireless remote control of a small field robot. The field robot can be wirelessly controlled by a worker in a remote location if the worker cannot be present at the work site. The implemented remote system is tested according to the type of work, and the operating characteristics of the remote system are assessed.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.10a
• /
• pp.496-499
• /
• 1997

Field robot represented by excavator can be applied for various kinds of working in manufacturing, construction, agriculture etc. because of the flexibility of its multi-joint mechanism and the high power of hydraulic actuators. In general, the dynamics of field robot have strong coupling, various kinds of non-linearity, and time-varying parameters according to working conditions. Therefore, it is very difficult to describe the system well, and design controller systematically based on its model. This paper established the mathematical model of field robot driven by electro-hydraulic servomechanism and constructed the adaptive control system robust to external load variations. The proposed control system for the field robot was evaluated by the computer simulation and the performance results of trajectory tracking were compared with that of PID control system.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.1018-1021
• /
• 2003

This dissertation is reference to measure visual information about the configuration of magnetic field automatically and materialize the new magnetic field mapping system for the rapid and clear measure by using of the mediocrity orthogonal robot in the three- dimensional space required the measure of magnetic field concurrently. The measuring sensor is composed to be available for the measure of three-dimensional direction of magnetic field by vertically conjoining each of three hall sensors utilized of the hall effect and installed Gaussmeter, which is devised to receive the sensor result and the robot controller, away from the measuring robot in order to minimize the affection of magnetic field. Also, the controller and Gaussmeter are composed of Use interface, RS-232C and IEEE-488.2 communication. Interface system is written in NI's LabVIEW and composed to be able to set up a measuring area, the measuring number of times, two and three-dimensional graph, the velocity of robot and the magnetic field distribution graph of each element by inputting parameters. The materialized magnetic field mapping system expert the collection of the data easily and the effect of utilizing data.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.25 no.6
• /
• pp.486-491
• /
• 2016

Disturbance/vibration reduction is critical in many applications using machine vision. The off-focusing or blurring error caused by vibration degrades the machine performance. In line with this, real-time disturbance estimation and avoidance are proposed in this study instead of going with a more familiar approach, such as the vibration absorber. The instantaneous motion caused by the disturbance is sensed by an attitude heading reference system module. A periodic vibration modeling is conducted to provide a better performance. The algorithm for vibration avoidance is described according to the vibration modeling. The vibration occurrence function is also proposed, and its parameters are determined using the genetic algorithm. The proposed algorithm is experimentally tested for its effectiveness in the vision inspection system.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.7 no.1
• /
• pp.9-21
• /
• 1998

This paper a new solution approach to moving obstacle avoidance problem of a mobile robot. A new concept avoidability measure (AVM) is defined to describe the state of a pair of a robot and an obstacle regarding the collision between them. As an AVM, virtual distance function (VDF), is derived as a function of the distance from the obstacle to the robot and outward speed of the obstacle relative to the robot. By keeping the virtual distance above some positive limit value, the robot avoids the obstacle. In terms of the VDF ,an artificial potential field is constructed to repel the robot away from the obstacle and to attract the robot toward a goal location. At every sampling time, the artificial potential field is updated and the force driving the robot is derived from the gradient of the artificial potential field. The suggested algorithm drives the robot to avoid moving obstacles in real time. Since the algorithm considers the mobility of the obstacle as well as the distance, it is effective for moving obstacle avoidance. Some simulation studies show the effectiveness of the proposed approach.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1998.03a
• /
• pp.88-93
• /
• 1998

This paper presents a new solution approach to moving obstacle avoidance problem for a mobile robot. A new concept avoidability measure(AVM) is defined to describe the state of a pair of a robot and an obstacle regarding the collision between them. As an AVM, virtual distance function(VDF) is derived as a function of the distance from the obstacle to the robot and outward speed of the obstacle relative to the robot. By keeping the virtual distance above some positive limit value, the robot avoids the obstacle. In terns of the VDF, an artificial potential field is constructed to repel the robot away from the obstacle and to attract the robot toward a goal location. At every sampling time, the artificial potential field is updated and the force driving the robot is derived form the gradient of the artificial potential field. The suggested algorithm drives the robot to avoid moving obstacles in real time. Since the algorithm considers the mobility of the obstacle as well as the distance, it is effective for moving obstacle avoidance. Some simulation studies show the effectiveness of the proposed approach.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2002.10a
• /
• pp.481-486
• /
• 2002

Automation of Field Robot has many advantages for efficiency and convenience. In this paper, mathematical equation of field robot is established and automation system is constructed. Hydraulic and Dynamic equation of field robot are constructed in this paper. Inputs of system are angle data from each link (boom, arm, bucket, swing) and pressure data from in, out port of each cylinder. Outputs of system are voltage into electo-proportional valve.