http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
[전기 전자부문] 원격 무인주행 차량의 비젼시스템에 관한 연구
문희창(Heechang Moon),김창민(Changman Kim),김상겸(Sanggyum Kim),김정하(Jungha Kim) 한국자동차공학회 2001 한국자동차공학회 춘 추계 학술대회 논문집 Vol.2001 No.11_2
The purpose of this paper is application of vision system for the tele-operate unmanned vehicle. Tele-operate unmanned vehicle demand sensing of variable surrounding environment, speed of vehicle, unexpected accident and other conditions. The vehicle should tell the operator all condition and surroundings of vehicle. For kno'M1 these things, we suggest new tele-operate unmanned vehicle.<br/> Tele-operate unmanned vehicle is devide into two parts. One is longitudinal control part and the other is lateral control part Longitudinal control part is operated by acceleration and deceleration. For longitudinal control we used DC motor and hole sensor. For lateral control we used vision system and stepping motor. This vision system is specially designed for lane detection. In this paper, we suggest lane detection algorithm.<br/> Through fusion of several sensor, integration of parts system and new lane detection algorithm, we propose the advanced tele-operate unmanned vehicle.<br/>
문희창(Heechang Moon),이운성(Woonsung Lee),김정하(Jungha Kim) 한국자동차공학회 2003 한국자동차공학회 춘 추계 학술대회 논문집 Vol.- No.-
Our goal of this research is developing the tele-operated unmanned vehicle. In case of emergency, it needs the autonomous intelligent functions. Now we are trying to make a miniaturized unmanned vehicle, which is equipped with vision sensor before developing a full scale one. This system is classified by three major components. First, the vision system is composed of small CCD camera, wireless video transmitter and receiver, and host computer. Second, the vehicle control system which is combined with sensors and actuators. In here, we use photo interrupts and 2 DC motors for vehicle velocity and also a potential meter and a RC scrvo motor for steering angle control. Third, we need a communication system, which can transmit vehicle condition data to host computer and receive control value from it Therefore, we designed real time full duplex communication method by using wireless RF modules. Finally, we will make a miniaturized unmanned vehicle by using vision system. And also, we suggest the control method of vehicle and the wireless RF communication method.
무인자동차의 주행을 위한 국부지도 생성방법에 대한 연구
문희창(HeeChang Moon),이홍철(HongChul Lee),김정하(JungHa Kim) 한국자동차공학회 2006 한국자동차공학회 Symposium Vol.- No.-
This paper deals with local map building method using obstacle detecting sensors such as laser scanner, camera, and ultra sonic sensor for unmanned ground vehicle(UGV). The UGV is consists of several systems. For example navigation system, obstacle detecting system, vehicle control system and arbiter system. Among the systems, obstacle detecting system is to detect obstacles in front of the vehicle using obstacle detecting sensors. These sensors generate various types of output data. So fusing sensors data is vary important. The local map is good for adding the sensors data. In this paper, we introduce our UGV systems and local map building method for sensor data fusing.
차량 영상 데이터 베이스 구축을 위한 계측 시스템 개발
손성효(Seonghyo Son),문희창(Heechang Moon),김민관(Minkwan Kim),최명식(Myung Sik Choi) 한국자동차공학회 2009 한국자동차공학회 학술대회 및 전시회 Vol.2009 No.11
According as intelligence of vehicle is getting improved, vehicle is getting to recognize outside environment and driver's status by itself, and find out how to guarantee safety in urgent or dangerous situation or let the driver know the situation and react safely. Diverse systems have been and are being developed related this tendency and some systems have been conveyed to customers. Among several sensors used in these systems, major portion is occupied by cameras. Camera do a dominate role for sensing outside situations. PAS, LDWS, BSD are the representative applications using camera. To develop these kind of systems with high performance and quality, countless tests have to be performed during developing procedure. Via these tests, many image database in various driving situations are accumulated and analyzed for developing processing algorithm. Based on this purpose, a test vehicle and image database acquisition system was developed and is introduced in this paper. The test system can acquire CAN information of vehicle, front and side obstacle information from laser scanner and image data from 8 analog cameras simultaneously. And some softwares for editing and analyzing the acquired data are introduced additionally. We expect that high-technologized driving assistance systems will be developed efficiently through this test system.
자동 발렛 파킹을 위한 테스트 플랫폼 설계 및 주행 검증
우훈제(HoonJe Woo),손성효(SungHyo Son),문희창(HeeChang Moon),성경복(KyungBok Sung),김정하(JungHa Kim) 한국자동차공학회 2011 한국자동차공학회 부문종합 학술대회 Vol.2011 No.5
This paper introduces an automated valet parking system (AVP) which applies an autonomous driving concept into the current parking assistant system (PAS). The present commercial PAS technology is limited into vehicle. It means vehicle only senses and controls by and for itself to assist the parking. Therefore, the present PAS is restricted to simple parking events. But AVP includes wider parking events and planning because it uses infra-sensor network as well as vehicle sensor. For the realization of AVP, the commercial steering system of a compact vehicle was modified into steer-by-wire structure and various sensors like LRF (Long Range Finder) and camera were installed in a parking area. And local & global server decides where and when the vehicle can go and park in the testing area after recognized the status of environment and vehicle from those sensors. GPS solution was used to validate the AVP performance. More various parking situations, vehicles and obstacles will be considered in the next research stages based on these results. And we expect this AVP solution with more intelligent vehicles can be applied in a big parking lot like a market, an amusement park, etc.
C-EPS의 보조력 및 복원력제어 알고리즘 검증을 위한 시뮬레이터설계
장재훈(Jaehoon Jang),박명욱(Myungwook Park),문희창(Heechang Moon),김정하(Jungha Kim) 한국자동차공학회 2010 한국자동차공학회 부문종합 학술대회 Vol.2010 No.5
Electric Power Steering(EPS) works with the help of an electric motor and a control unit which has some sensors. The motor runs on battery and will use electric power to assist the movement of steering when the driver turns the wheel. EPS system has many advantages over traditional HPS (Hydraulic Power Steering) system in space efficiency, engine efficiency and environmental problem. For exemple, Compared with a hydraulic power steering system that continuously drives a hydraulic pump, the EPS system drives the EPS motor only when necessary, resulting in reduced fuel consumption. EPS system is consist of many sensors and brushless motor(BLDC motor). The main function of EPS system is Assist control and Return control, damping compensation control, friction compensation control, Inertia compensation control. In this paper, the EPS system"s control logic for various functions that will be validated practically through HILS and vehicle.
경로점 기반 자율주행 배달 로봇의 주행 안정성을 위한 GPS 모듈과 SLAM 모듈의 비교 연구
김봉상(Bongsang Kim),남일진(Iljin Nam),류제규(Jaekyu Ryu),문희창(Heechang Moon) 대한전자공학회 2022 전자공학회논문지 Vol.59 No.12
본 논문에서는 경로점 기반 자율주행 배달 로봇의 주행 안정성을 위한 GPS 모듈과 SLAM 모듈에 대한 비교 연구를 제시한다. GPS 모듈은 야외에서 실시간으로 위치를 인식할 수 있는 대표적인 방법이지만 인공 및 자연 구조물과 같은 외부 환경에 방해받기 쉽다. 그래서 도심과 같은 복잡한 환경에서 정확한 위치 인식을 위해 LiDAR를 이용한 SLAM 방식이 개발되었다. 하지만 SLAM 방식도 모든 환경에서 사용할 수 없을 것이며 이 부분을 명확하게 찾아 보완하는 방법을 개발해야 한다. 따라서 이 연구는 경로점 주행 기법이 적용된 자율주행 플랫폼을 이용하여 비정형 환경이 조성된 동일한 조건에서 GPS 위치 인식 자율주행과 SLAM 위치 인식 자율주행을 비교하고 향후 GPS 모듈과 SLAM 모듈의 융합 가능성을 확인한다. In this paper, we present a comparative study on GPS module and SLAM module for driving stability of Waypoint-based autonomous driving delivery robots. The GPS module is a representative method of recognizing a location in real time outdoors. However, it is easy to be disturbed by external environments such as artificial and natural structures. Therefore, the SLAM method using LiDAR was developed for accurate location recognition in complex environments such as urban areas. However, the SLAM method will not be available in all environments, and it is necessary to develop a method to clearly find and supplement this part. Therefore, this study compares GPS position recognition autonomous driving and SLAM position recognition autonomous driving under the same conditions in which an unstructured environment is created using an autonomous driving platform applied with Waypoint driving technique, and confirms the possibility of future fusion of GPS modules and SLAM modules.
Solid-State LiDAR 기반 밭 농업용 자율주행 로봇의 두둑 감지를 통한 실시간 주행 경로 생성 알고리즘
백승범(Seungbeom Baek),김봉상(Bongsang Kim),이재욱(Jaewook Lee),문희창(Heechang Moon) 제어로봇시스템학회 2022 제어·로봇·시스템학회 논문지 Vol.28 No.2
Autonomous robots driving in agricultural environments need to create accurate routes to prevent damaging farmland. Herein, a real-time path planning algorithm based on ridge detection using the Livox Mid70 LiDAR is proposed. The field has a steep slope between the furrow and the ridge, and we find data corresponding to this slope from the lidar data. Using two Mid70 LiDARs, we collect the left and right slope data and linearly fit the slope data using the RANSAC algorithm. Finally, the driving route is obtained from the average of the two straight lines. To verify the algorithm, the steering angle needed to follow the driving path was calculated, and an autonomous driving test was conducted in the actual field environment: it was observed that the robot drove stably. Additional tests will be conducted in more rugged terrain.