• 한국공작기계학회논문집
• /
• 제15권5호
• /
• pp.14-20
• /
• 2006

In recent year, as the robot technology is developed, the researches on the artificial muscle actuator that enables robot to move dexterously like biological organ become active. Actuators are key technologies underpinning robotics. Breakthroughs in actuator technology, particular in terms of power-to-weight ratio, or energy-density, will have significant impacts upon the design and control of robotic system. In this paper, a new approach to design and control of shape memory alloy(SMA) actuator is presented to drive the robot hand. SMA wire is divided into many segments and their thermal states of the SMA are controlled individually in a binary manner. This control manner will reduce the hysteresis that the SMA material has and it becomes the fundamental technology to develop the anthropomorphic robot hand. In this paper, the mechanism In the digital step motor of the shape memory alloy that is driven by the segmented binary control, which is a new control technique, is studied. This SMA digital step actuator applies for the robot hand and the driving mechanism of the robot hand is investigated.

• 한국전기전자재료학회논문지
• /
• 제25권1호
• /
• pp.53-57
• /
• 2012

In this paper, by designing 20 W class driving circuit for driving high-power LED (Light Emitting Diode), we are going to comparatively carry out the analysis of characteristics for power circuit according to each design method. In this case, 200 V 60 Hz was performed as input data. The electrical characteristics such as voltage, current and ripple are checked for constant current circuit and constant voltage circuit in the LED module. In addition, as the ripple has an influence on illumination of LED light, low temperature working (-20 [$^{\circ}C$]) and high temperature working(80 [$^{\circ}C$]) are measured to make sure the ripple characteristics in accordance with temperature. In low temperature operation -20 [$^{\circ}C$] measurements, both constant current circuit and constant-voltage circuit were less impacted on input fluctuation, whereas in the high temperature operation 80 [$^{\circ}C$], current voltage in constant voltage circuit was surge after 430 [hour]. Voltage current ripple of constant current circuit was much less than constant voltage circuit, therefore we can show that constant current circuit is more stable.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2002년도 전력전자학술대회 논문집
• /
• pp.435-438
• /
• 2002

The Objects of this paper are developing and also improving a high-speed driving system of bushless DC motor(BLDCM) with economical and practical performance. Because BLDC motors are manufactured that each motor can create proper torque for their individual purpose, it is difficult to increase over the rated speed when a motor speed (with it's rated road) is reaching to a maximum speed so the motor torque cannot be increased. This paper verifies the effects of Leading Angle Algorithm, that is proposed on this paper, with examining existing methods to maximize the torque of a motor in high-speed driving area. The arithmetic processor for this experiment is TMS320C240 DSP controller that is designed for a special purpose of motor control in Texis Instrument Inc., and the used Inverter is PM10CSJ060, a Intelligent Power Module of Mitsubishi Corporation.

• 한국생산제조학회지
• /
• 제22권3_1spc호
• /
• pp.607-614
• /
• 2013

This paper proposes a robot driving system and sensor implementation for use with an education robot. This robot has multiple functions and was designed so that children could use it with interest and ease. The robot recognizes the location of a user and follows that user at a specific distance when the robot and user communicate with each other. In this work, the robot was designed and manufactured to evaluate its performance. In addition, an embedded board was installed with the purpose of communicating with a smart phone, and a camera mounted on the robot allowed it to monitor the environment. To allow the robot to follow a moving user, a set of sensors combined with an RF module and ultrasonic sensors were adopted to measure the distance between the user and the robot. With the help of this ultrasonic sensors arrangement, the location of the user couldbe identified in all directions, which allowed the robot to follow the moving user at the desired distance. Experiments were carried out to see how well the user's location could be recognized and to investigate how accurately the robot trackedthe user, which eventually yielded a satisfactory performance.

• Journal of international Conference on Electrical Machines and Systems
• /
• 제2권2호
• /
• pp.190-196
• /
• 2013

It presents a unification of buck-boost and flyback converter for driving a cascaded H-bridge multilevel inverter with a single independent DC voltage source. Cascaded H-bridge multilevel inverter is useful to make many output voltage levels for sinusoidal waveform by combining two or more H-bridge modules. However, each H-bridge module needs an independent DC voltage source to generate multi levels in an output voltage. This topological characteristic brings a demerit of increasing the number of independent DC voltage sources when it needs to increase the number of output voltage levels. To solve this problem, we propose a converter combining a buck-boost converter with a flyback converter. The proposed converter provides independent DC voltage sources at back-end two H-bridge modules. After analyzing theoretical operation of the circuit topology, the validity of the proposed approach is verified by computer-aided simulations using PSIM and experiments.

• 드라이브 ㆍ 컨트롤
• /
• 제20권1호
• /
• pp.8-15
• /
• 2023

With the recent trend of intelligence and automation of construction work, a double-blade road cutter is being developed that automatically enables cutting along the cutting line marked on the road using a vision system. The road cutter can recognize the cutting line through the camera and correct the driving route in real-time, and it detects the load of the cutting blade in real-time to control the driving speed in case of overload to protect workers and cutting blades. In this study, a vision system mounted on a double-blade road cutter was developed. A cutting route recognition technology was developed to stably recognize cutting lines displayed on non-uniform road surfaces, and performance was verified in similar environments. In addition, a vision sensor protection module was developed to prevent foreign substances (dust, water, etc.) generated during cutting from being attached to the camera.

• 방송공학회논문지
• /
• 제28권2호
• /
• pp.230-237
• /
• 2023

자율주행은 4차 산업의 핵심 기술로 차, 드론, 자동차, 로봇 등 다양한 곳에 응용 가능하다. 그 중 위치 추정 기술은 GPS, 센서, 지도 등을 활용하여, 객체나 사용자의 위치를 파악하는 기술로 자율주행을 구현하기 위한 핵심적인 기술 중 하나이다. GPS나 LIDAR 등의 센서를 이용하여 위치 추정이 가능하지만, 이는 매우 고가이고 무거운 장비를 탑재해야 하며 지하 혹은 터널 등 전파 방해가 있는 곳의 경우 정밀한 위치 추정이 어렵다는 단점이 있다. 본 논문에서는 이를 보완하기 위해 저가의 비전 카메라로 획득한 컬러 영상을 입력으로 하여 관심 영역 추출 네트워크와 영상 분할 지도를 이용한 영상 검색 기술을 제안한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.1996-2015
• /
• 2023

High-definition (HD) maps can provide precise road information that enables an autonomous driving system to effectively navigate a vehicle. Recent research has focused on leveraging semantic segmentation to achieve automatic annotation of HD maps. However, the existing methods suffer from low recognition accuracy in automatic driving scenarios, leading to inefficient annotation processes. In this paper, we propose a novel semantic segmentation method for automatic HD map annotation. Our approach introduces a new encoder, known as the convolutional transformer hybrid encoder, to enhance the model's feature extraction capabilities. Additionally, we propose a multi-level fusion module that enables the model to aggregate different levels of detail and semantic information. Furthermore, we present a novel decoupled boundary joint decoder to improve the model's ability to handle the boundary between categories. To evaluate our method, we conducted experiments using the Bird's Eye View point cloud images dataset and Cityscapes dataset. Comparative analysis against stateof-the-art methods demonstrates that our model achieves the highest performance. Specifically, our model achieves an mIoU of 56.26%, surpassing the results of SegFormer with an mIoU of 1.47%. This innovative promises to significantly enhance the efficiency of HD map automatic annotation.

• 한국ITS학회 논문지
• /
• 제21권5호
• /
• pp.274-286
• /
• 2022

이동객체 추적은 컴퓨터 비전 분야에서 오랜 시간 동안 연구가 진행되어 온 분야로 자율주행이나 운전 보조 시스템 등의 시스템에서 아주 중요한 역할을 수행하고 있다. 이동객체 추적 기술은 일반적으로 객체를 검출하는 검출기와 검출된 객체를 추적하는 추적기의 결합으로 이루어져 있다. 검출기는 다양한 데이터셋이 공개되어 사용되고 있기 때문에 쉽게 좋은 모델을 학습할 수 있지만, 추적기의 경우 상대적으로 공개된 데이터셋도 적고 직접 데이터셋을 구성하는 것도 검출기 데이터셋에 비해 굉장히 오랜 시간을 소요한다. 이에 검출기를 따로 개발하고, 별도의 추적기를 학습 기반이 아닌 방식을 활용하여 개발하는 경우가 많은데 이런 경우 두 개의 시스템이 차례로 작동하게 되어 전체 시스템의 속도를 느리게 하고 앞단의 검출기의 성능이 변할 때마다 별도로 추적기 또한 조정해줘야 한다는 단점이 있다. 이에 본 연구는 검출용 데이터셋만을 사용하여 검출과 추적을 동시에 수행하는 모델을 구성하는 방법을 제안한다. 데이터 증강 기술과 샴 네트워크를 사용하여 단일 이미지에서 객체를 검출 및 추적하는 방법을 연구하였다. 공개 데이터셋에 실험을 진행하여 학습 결과 높은 속도로 작동하는 이동객체 검출 및 추적기를 학습할 수 있음을 검증하였다.

• 한국산학기술학회논문지
• /
• 제19권6호
• /
• pp.639-645
• /
• 2018

본 논문은 자율주행 자동차 및 자율주행이 가능한 이동체를 대상으로 광범위하게 적용 가능한 지능형 의사결정 모델을 개발하기 위한 연구이다. 개발된 모듈은 다양한 주행환경에 적용하기 위하여 독립적인 모듈 구성형태를 갖추고 이를 유기적으로 운영하기 위한 플랫폼을 기반으로 각 모듈을 Deep Learning 기법을 이용한 강화학습을 통해 이동체의 차선변경 의사 결정 및 안전 확보에 관하여 연구하였다. 운행 중인 자율주행 이동체는 주행상태의 변경을 위하여 기능별로 속도결정 모델과 차선변경 의사결정이 반드시 선행되어야 이동체의 다음 행동이 이루어 질 수 있는 특징을 갖고 있다. 또한, 일반 도로상에 주행 중인 이동체들이 모두 자율주행 기능을 갖춘 상태라면 특정 이동체의 돌발적인 변화 및 주변 환경의 변화가 발생하면 그에 따른 각각의 이동체들 사이에 발생할 수 있는 연쇄반응 요소는 고려되기 어려운 특징을 갖고 있다. 이런 부분을 함께 고려하여 자율주행 플랫폼에 적용하고 이를 위한 개별 이동체의 차선변경 의사결정 시스템 연구와 모듈형 학습 방법을 이용하여 시스템 복잡도를 줄이고 학습시간의 단축과 향후 모델의 교체를 할 수 있는 의사결정 모델을 연구하였다.