• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.15 no.1
• /
• pp.12-19
• /
• 2015

In order to guide the robots move along a collision-free path efficiently and reach the goal position quickly in the unknown multi-obstacle environment, this paper presented the navigation problem of a wheel mobile robot based on proximity sensors by fuzzy logic controller. Then a genetic algorithm was applied to optimize the membership function of input and output variables and the rule base of the fuzzy controller. Here the environment is unknown for the robot and contains various types of obstacles. The robot should detect the surrounding information by its own sensors only. For the special condition of path deadlock problem, a wall following method named angle compensation method was also developed here. The simulation results showed a good performance for navigation problem of mobile robots.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.319-322
• /
• 1995

This paper addresses that through the use of Fuzzy Logic Control, a reactiv behavior (e.g. avoiding obstacles on the way) are smoothly blended into one sequence of control action. In this classical problem, the aim is to guide a mobile robot along its path to avoid any static obstacles in front of it. This controller presented here uses three sub-controllers. This fuzzy controller was apply to a miniature mobile robot. This robot follows a left wall, maintining a minimum distance.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.04a
• /
• pp.234-239
• /
• 2003

A cylindrical shape object is widely used as a mechanical part and a water pipe or an oil pipeline which are of cylindrical shape are widely used in the infrastructure. In order to handling such objects automatically using a robot, the posture i.e. orientation in 3D space should be recognized. However, since there is no edge or vertex in the pipe, it is very difficult task for the robot. In this paper in order to guide the robot, two kind of algorithms which find the axis using the measured range data from the robot to the object surface are to be developed. The algorithms are verified using both the simulated range data and the measured one.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2017.05a
• /
• pp.272-273
• /
• 2017

As businesses put a greater emphasis on outward appearances, the demand for external window cleaning has been on the rise. However, with the conventional labor-intensive window cleaning method, it is hard to meet this demand. Therefore, this study proposes a Life Cycle Cost (LCC) analysis model for a guiderail-type cleaning robot, and estimate the LCCs of the conventional method and the cleaning robot. The findings of this research are expected to serve as a guide for future development of a cleaning robot.

• Proceedings of the KIEE Conference
• /
• 2002.11c
• /
• pp.501-504
• /
• 2002

This research embodied DGPS (Differential GPS) system that robot detects users present position in outside environment as part of Lacteal gland robot that is sight obstacle. Therefore, introduced GPS system that is effective means that can save essential world coordinate to realize global navigation. However, it is no the effectiveness to use GPS that is having error of tens meter to apply to lacteal gland robot that is sight obstacle without revision. Therefore, this research embodied Localization system of lacteal gland robot that is sight obstacle using DGPS that make use of FM DARC system to use DGPS to heighten navigation accuracy of this.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2017.11a
• /
• pp.203-204
• /
• 2017

In case of developing a guide-rail type window cleaning robot, only the first prototype has been developed. In this study, it was considered that the size and the load of the window cleaning robot was not optimized, and through the structural analysis of the self-weight of the window cleaning robot, the stress concentration area was derived and the concentrated stress was quantified. Analysis showed that the upper rail shaft had a bending stress of 9.964Mpa and the bolt had a shear stress of 19.544Mpa. The results of this study will be used as basic data for designing future prototypes.

• Journal of Sensor Science and Technology
• /
• v.16 no.4
• /
• pp.286-293
• /
• 2007

For safe walking of the people who are blind, walking assistance robot which can detecting and avoiding the obstacle was investigated. The implemented prototype walking assistance robot consists of a obstacle detecting module, a user interface using acoustic signal and a driving module. The obstacle detecting module uses 6 ultrasonic sensors those located at the front part of the robot can perceive the obstacle which is in 3 meter distances and $180^{\circ}$ degrees. It calculates the distance and degree from the obstacle using TOF (time of flight) method and decides the 3-dimensional location of the obstacle. The obstacle information is delivered to the user using acoustic alarm and guide sound. The robot is designed to avoid by itself when the obstacle is detecting and the user only follows it to safe walking. After the designed robot was implemented, driving and obstacle detecting experiments were carried out. The result showed that the designed walking assistance robot will help the people who are blind to walk around safe.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.40-49
• /
• 2019

Reinforcement learning has been applied to various problems in robotics. However, it was still hard to train complex robotic manipulation tasks since there is a few models which can be applicable to general tasks. Such general models require a lot of training episodes. In these reasons, deep neural networks which have shown to be good function approximators have not been actively used for robot manipulation task. Recently, some of these challenges are solved by a set of methods, such as Guided Policy Search, which guide or limit search directions while training of a deep neural network based policy model. These frameworks are already applied to a humanoid robot, PR2. However, in robotics, it is not trivial to adjust existing algorithms designed for one robot to another robot. In this paper, we present our implementation of Guided Policy Search to the robotic arms of the Baxter Research Robot. To meet the goals and needs of the project, we build on an existing implementation of Baxter Agent class for the Guided Policy Search algorithm code using the built-in Python interface. This work is expected to play an important role in popularizing robot manipulation reinforcement learning methods on cost-effective robot platforms.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2008.06a
• /
• pp.7-8
• /
• 2008

• Proceedings of the Korean Nuclear Society Conference
• /
• 2005.10a
• /
• pp.699-700
• /
• 2005