• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.4
• /
• pp.65-73
• /
• 1997

This paper proposes a new method of the structure pruning of dynamic recurrent neural networks (DRNN) using evolutionary computations. In general, evolutionary computations are population-based search methods, therefore it is very useful when several different properties of neural networks need to be optimized. In order to prune the structure of the DRNN in this paper, we used the evolutionary programming that searches the structure and weight of the DRNN and evolution strategies which train the weight of neuron and pruned the net structure. An addition or elimination of the hidden-layer's node of the DRNN is decided by mutation probability. Its strategy is as follows, the node which has mhnimum sum of input weights is eliminated and a node is added by predesignated probability function. In this case, the weight is connected to the other nodes according to the probability in all cases which can in- 11:ract to the other nodes. The proposed pruning scheme is exemplified on the stabilization and position control of the inverted-pendulum system and visual servoing of a robot manipulator and the effc: ctiveness of the proposed method is demonstrated by numerical simulations.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.2
• /
• pp.276-283
• /
• 2012

In this paper, a practical quasi-optimal DOA(direction of arrival) estimator is proposed in order to develop a one-axis gimbaled ultrasonic source tracker for mobile robot applications. With help of the gimbal structure, the ultrasonic moving source tracking problem can be simply reduced to the DOA estimation. The DOA estimation is known as one of the representative long-pending nonlinear filtering problems, but the conventional nonlinear filters might be restrictive in many actual situations because it cannot guarantee the reliable performance due to the use of nonlinear signal model. This motivates us to reformulate the DOA estimation problem in the linear robust state estimation setting. Based on the assumption that the received ultrasonic signals are noisy sinusoids satisfying linear prediction property, a linear uncertain measurement model is newly derived. To avoid the DOA estimation performance degradation caused by the stochastic parameter uncertainty contained in the linear measurement model, the recently developed NCRKF (non-conservative robust Kalman filter) scheme [1] is utilized. The proposed linear DOA estimator provides excellent DOA estimation performance and it is suitable for real-time implementation for its linear recursive filter structure. The effectiveness of the suggested DOA estimation scheme is demonstrated through simulations and experiments.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1945-1948
• /
• 2004

This paper describes the design and construction of a micro robotic system addressing such important aspects as versatility and low cost for rapid development and test of new control algorithm. The design and structure of micro robots are presented in detail. The supervision oriented concept is designed for controlling a group of micro robots. In this concept, the vision system recognizes the environment and the host computer decides the micro robot action based on the information from the vision system. In addition, the micro robots can be implemented cheaply and small in size because the structure of supervision oriented system is simplest. The experimental results and the performance of the proposed micro robotic system are discussed.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.25 no.9
• /
• pp.1-7
• /
• 2011

A performance delivers the contents and feeling through human bodies and stage settings in the limited space of a stage. Among the stage settings, the lighting creates overall atmospheres effectively according to the situations of the performance such as a time flow, a change of seasons, an expression of the mental state of the performer. As the LED lighting is used more widely, the number and the size of the lighting is being decreased, which makes it possible for various devices to be used. However, just as conventional lighting devices, most of them are fixed. So it is difficult to use them at a blind spot and to replace them. To solve this problem, this article suggests a system which replaces lighting automatically and moves. As it can moved to a spot we want on a rail, and the lighting system can be replaced by itself, it can have various lighting effects, increasing the effectiveness of the performance. Additionally, it can also decrease the danger of a worker operating the lighting device located at a high place. At the mock-up experiment, its mobility and stability on a rail were tested using the wheel of the Modular Robot.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.11
• /
• pp.1147-1152
• /
• 2014

This paper describes the design of a four-axis force/torque sensor with PSPBs (Parallel Step Plate Beams). The sensor is composed of eight PSPBs, a force/torque transmitting block, and fixing blocks. It is designed by using the FEM(Finite Element Method), and fabricated by using strain gages. The characteristic tests of the sensor are carried out, and the interference error, repeatability error, and non-linearity error are less than 2.21%, 0.03% and 0.03%. Furthermore, the structure of the four-axis force/torque sensor with PSPBs has a larger rated capacity than that of the four-axis force/torque sensor with PPBs under the same overall sensor size and the same rated output. It is thought that the developed four-axis force/torque sensor with PSPBs can be used for measuring the forces and torques in an intelligent robot, automation devices, etc.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.11 s.176
• /
• pp.82-90
• /
• 2005

Recently, the in-line vision inspection has become the subject of growing research area in the visual control systems and robotic intelligent fields that are required exact three-dimensional pose. The objective of this article is to study the pc based in line visual inspection with the hand-eye structure. This paper suggests three dimensional structured light measuring principle and design method of laser sensor header. The hand-eye laser sensor have been studied for a long time. However, it is very difficult to perform kinematical analysis between laser sensor and robot because the complicated mathematical process are needed for the real environments. In this problem, this paper will propose auto-calibration concept. The detail process of this methodology will be described. A new thinning algorithm and constrained hough transform method is also explained in this paper. Consequently, the developed in-line inspection module demonstrate the successful operation with hole, gap, width or V edge.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.7
• /
• pp.870-874
• /
• 2005

This paper presents capacitive tactile sensor that can detect normal and shear forces. This tactile sensor consists of index plate, sensing plate, and elastic dielectric layer. The calculated sensing character is based on the changes of space between two horizontal plate. Larger overlap areas and narrow space between top and bottom plate guarantees higher sensitivity. Tactile sense information can be calculated from the changes of phase of output signal. The symmetric arrangement of sensing plates makes the manufacturing process easier and guarantees the stability of the structure. In this paper, the sensor structure is designed, the mechanism of the Proposed sensor is theoretically explained, and the simulated result is presented.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.9
• /
• pp.796-802
• /
• 2000

A master-slave system for teleoperation is usually used to control the robor's motion on remote place such as abyss, outer space etc.. When the slave robot is a humanoid one, it can make a better performance if the configuration of the master arm is similar to that of the slave arm and of the human. The master arm proposed in this paper has a type to be put on the human arm, that is, the exoskeleton type, and has a combination of serial joint and parallel mechanism imitating the human's arm structure of muscles and bones, so called hybrid mechanism so that it can follow arm's movement effectively. But it is easy to solve the forward kinematis of the parallel structure because relating equations are implicit functions. In order to solve that, the virtual joint angle corresponding to human arm's joint is introduced and a sequential computation step is employed in calculating virtual joint angles and the posture of the end effector. Also validity is checked up through computational simulation.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.6 no.3
• /
• pp.652-669
• /
• 2014

This paper concerns the kinematic characteristics of a coupling device in a deep-seabed mining system. This coupling device connects the buffer system and the flexible pipe. The motion of the buffer system, flexible pipe and mining robot are affected by the coupling device. So the coupling device should be considered as a major factor when this device is designed. Therefore, we find a stable kinematic device, and apply it to the design coupling device through this study. The kinematic characteristics of the coupling device are analyzed by multi-body dynamics simulation method, and finite element method. The dynamic analysis model was built in the commercial software DAFUL. The Fluid Structure Interaction (FSI) method is applied to build the deep-seabed environment. Hydrodynamic force and moment are applied in the dynamic model for the FSI method. The loads and deformation of flexible pipe are estimated for analysis results of the kinematic characteristics.

• The Journal of Korea Robotics Society
• /
• v.17 no.4
• /
• pp.407-416
• /
• 2022

Multiple AMRs have been proved to be effective in improving warehouse productivity by eliminating workers' wasteful walking time. Although Multi-agent Path Finding (MAPF)-based solution is an optimal approach for this task, its deployment in practice is challenging mainly due to its imperfect plan-execution capabilities and insufficient computing resources for high-density environments. In this paper, we present a MAPF-based fleet management system architecture that robustly manages multiple robots by re-computing their paths whenever it is necessary. To achieve this, we defined four events that trigger our MAPF solver framework to generate new paths. These paths are then delivered to each AMR through ROS2 message topic. We also optimized a graph structure that effectively captures spatial information of the warehouse. By using this graph structure we can reduce computational burden while keeping its rescheduling functionality. With proposed MAPF-based fleet management system, we can control AMRs without collision or deadlock. We applied our fleet management system to the real logistics warehouse with 10 AMRs and observed that it works without a problem. We also present the usage statistic of adopting AMRs with proposed fleet management system to the warehouse. We show that it is useful over 25% of daily working time.