• 제어로봇시스템학회논문지
• /
• 제22권11호
• /
• pp.895-903
• /
• 2016

In a fire disaster in a tunnel, people should be rescued immediately using the information obtained from cameras or sensors. However, in heavy smoke from a fire, people cannot be clearly identified by a mounted CCTV, which is only effective in a clear environment. A thermal camera can be an alternative to this in smoky situations and is capable of detecting people from their emitted thermal energy. On the other hand, the thermal image camera has a smaller field of view than an ordinary camera due to its lens characteristics and temperature error, etc. In order to cover a relatively wide area, panoramic image construction needs to be implemented. In this work, a template-based similarity matching algorithm for constructing the panorama image is proposed and its performance is verified through experiments. This scheme provides guidelines for coping with difficulty in image construction, which requires an exact correspondence search for two images in cases of heavy smoke.

• 전자공학회논문지 IE
• /
• 제47권3호
• /
• pp.26-34
• /
• 2010

본 논문에서는 기본적인 형태는 퍼지 제어의 형태를 유지하면서 그 세부적 요소들을 신경회로망으로 구성한 뉴로-퍼지 제어기를 설계하였다. 뉴로-퍼지 제어기는 퍼지 제어 및 신경회로망 제어가 갖는 장단점을 서로 보완할 수 있도록 하였으며 On-Line상태에서 동조가 이루어지도록 하였다. 본 제어기의 성능을 평가하기 위해서 현재 로봇제어에서 많이 사용되고 있는 교류 서보 전동기의 속도제어에 적용시켰다. 가장 보편적인 제어기인 PID제어기 및 퍼지제어기와 비교실험 함으로써 제어기로서의 안정한 특성을 입증하였다. 특히 로봇처럼 급격한 부하변동에 대응할 수 있는 제어기 설계를 위해 부하를 인가하여 실험을 수행하여 성능을 입증하였다.

• ETRI Journal
• /
• 제39권5호
• /
• pp.643-651
• /
• 2017

Human age estimation is one of the key factors in the field of Human-Robot Interaction/Human-Computer Interaction (HRI/HCI). Owing to the development of deep-learning technologies, age recognition has recently been attempted. In general, however, deep learning techniques require a large-scale database, and for age learning with variations, a conventional database is insufficient. For this reason, we propose an age estimation method using artificially generated data. Image data are artificially generated through 3D information, thus solving the problem of shortage of training data, and helping with the training of the deep-learning technique. Augmentation using 3D has advantages over 2D because it creates new images with more information. We use a deep architecture as a pre-trained model, and improve the estimation capacity using artificially augmented training images. The deep architecture can outperform traditional estimation methods, and the improved method showed increased reliability. We have achieved state-of-the-art performance using the proposed method in the Morph-II dataset and have proven that the proposed method can be used effectively using the Adience dataset.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1998년도 제13차 학술회의논문집
• /
• pp.14-19
• /
• 1998

In this paper, a target approachable force-guided control with adaptive accommodation for the complex assembly is presented. The complex assembly (CA) is defined as a task which deals with complex shaped parts including concavity or whose environment is so complex that unexpected contacts occur frequently during insertion. CA tasks are encountered frequently in the field of the manufacturing automation and various robot applications. To make CA successful, both the bounded wrench condition and the target approachability condition should be satisfied simultaneously during insertion. By applying the convex optimization technique, an optimum target approaching twist can be determined at each instantaneous contact state as a global minimum solution. Incorporated with an admissible perturbation method, a new CA algorithm using only the sensed resultant wrench and the target twist is developed without motion planning nor contact analysis which requires the geometry of the part and the environment. Finally, a VME-bus based real-time control system is built to experiment various CA task. T-insertion task as a planar CA and double-peg assembly task as a spacial assembly were successfully executed by implementing the new force-guided control with adaptive accommodation.

• 제어로봇시스템학회논문지
• /
• 제21권11호
• /
• pp.1034-1037
• /
• 2015

In recent years in the field of robotics, various methods have been developed to create an intimate relationship between people and robots. These methods include speech, vision, and biometrics recognition as well as gesture-based interaction. These recognition technologies are used in various wearable devices, smartphones and other electric devices for convenience. Among these technologies, gesture recognition is the most commonly used and appropriate technology for wearable devices. Gesture recognition can be classified as contact or noncontact gesture recognition. This paper proposes contact gesture recognition with IMU and EMG sensors by using the hidden Markov model (HMM) twice. Several simple behaviors make main gestures through the one-stage HMM. It is equal to the Hidden Markov model process, which is well known for pattern recognition. Additionally, the sequence of the main gestures, which comes from the one-stage HMM, creates some higher-order gestures through the two-stage HMM. In this way, more natural and intelligent gestures can be implemented through simple gestures. This advanced process can play a larger role in gesture recognition-based UX for many wearable and smart devices.

• 한국정보통신학회논문지
• /
• 제18권2호
• /
• pp.276-281
• /
• 2014

본 논문은 산업용 로봇을 위한 힘 피드백 제어는 사람의 감각을 기반으로 한 작업을 대체하여 구현하기에 적합한 연마 시스템을 제안하였다. 기존 연마작업의 표면 연마, 비드처리, 기계 가공 디버링 등의 공정은 그 복잡성에서 자동화가 가장 곤란하다고 인식되어 주로 인력에 의존 해왔다. 본 연구에서는 연마 공구를 파지시킨 힘 제어 로봇에 의한 자동 연마 시스템의 구축과 힘 센서로부터 신호 피드백 제어 방식의 특성 파악과 연마 공정에 적응성을 검증했다. 또한 실용화를 목적을 위한 선박의 바닥 및 측면 연마에의 응용을 진행했다. 따라서 자체 제작한 연마로봇을 활용 한 표면 연마작업을 통하여 실험결과를 검증하였다.

• 전기학회논문지
• /
• 제61권1호
• /
• pp.57-63
• /
• 2012

A surfaced permanent magnet spherical motor is capable of operating as three degree of freedom that used for the joints of the robot's arm, leg, and eyes. Ongoing research like new concept is essential part of motor field, it will make a great contribution in the future the overall portion of the motor, is becoming expected. The author analysis torque characteristics in spherical motor with state of rotating and positioning. And future design direction is smaller motors with equivalent or higher output. Solutions as torque and efficiency improvements are selecting the core with special processing type like powder metallurgy materials. Their special characteristic is high permeability and low eddy current losses at high speed, so improved the torque and efficiency.

• 한국산업융합학회 논문집
• /
• 제23권4_2호
• /
• pp.653-659
• /
• 2020

In this study, seismic verification of the bellows used in the plant field was conducted. The pressure used in the analysis was analyzed by applying the design pressure of 15.7bar. For the seismic analysis, the natural frequency of the bellows system was obtained and the stability of the system was evaluated by static seismic analysis comparing the lowest order natural frequency with the dominant frequency of 33 Hz. The material of the bellows system is STS304, and the safety factor is obtained in comparison with the allowable stress. For the seismic analysis, the design response spectrum was prepared and the maximum acceleration was applied to the static seismic analysis and the stability of the entire system was confirmed. Compared to the structural analysis results, the maximum stress of the bellows system increased by about 16.4% and the maximum strain increased by about 3 times when seismic analysis was performed.

• 한국산업융합학회 논문집
• /
• 제24권5호
• /
• pp.573-579
• /
• 2021

In this study, flow analysis was performed on three types of strainers for ships with different flow rates to predict the pressure drop of the strainer due to the filter of strainer. In the case of flow analysis, the flow analysis was performed by applying the porous media method by applying the resistance value derived by Ergun's equation to the filter position. As a result of the analysis, it was found that when the dimensions of the strainer body were small, the influence of the flow rate on the pressure drop was large. In addition, the amount of pressure drop and the flow rate are almost linearly proportional, and an analysis formula that can predict the amount of pressure drop was derived. In order to predict the amount of pressure drop of the strainer when blockage exist in the strainer filter, the analysis was performed by introducing the resistance ratio to derive the prediction equation. Using this equation, it is thought that it will be possible to predict the performance of the strainer due to blockage in the future strainer design and field application.

• 로봇학회논문지
• /
• 제16권2호
• /
• pp.94-102
• /
• 2021

This study addresses a method for 3D reconstruction using acoustic data with heterogeneous sonar devices: Forward-Looking Multibeam Sonar (FLMS) and Profiling Sonar (PS). The challenges in sonar image processing are perceptual ambiguity, the loss of elevation information, and low signal to noise ratio, which are caused by the ranging and intensity-based image generation mechanism of sonars. The conventional approaches utilize additional constraints such as Lambertian reflection and redundant data at various positions, but they are vulnerable to environmental conditions. Our approach is to use two sonars that have a complementary data type. Typically, the sonars provide reliable information in the horizontal but, the loss of elevation information degrades the quality of data in the vertical. To overcome the characteristic of sonar devices, we adopt the crossed installation in such a way that the PS is laid down on its side and mounted on the top of FLMS. From the installation, FLMS scans horizontal information and PS obtains a vertical profile of the front area of AUV. For the fusion of the two sonar data, we propose the probabilistic approach. A likelihood map using geometric constraints between two sonar devices is built and a monte-carlo experiment using a derived model is conducted to extract 3D points. To verify the proposed method, we conducted a simulation and field test. As a result, a consistent seabed map was obtained. This method can be utilized for 3D seabed mapping with an AUV.