http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
RFID 를 이용한 이동 로봇의 위치 추정을 위한 실내 공간에서의 태그 배치 알고리듬
김현태(Hyun-Tae Kim),지용관(Yong-Kwan Ji),박장현(Jahng-Hyon Park) 대한기계학회 2006 대한기계학회 춘추학술대회 Vol.2006 No.6
Recently, researches on estimating a mobile robot's position using RFID tags get attention as the RFID cost goes down. In this paper, an optimizing algorithm for arranging RFID tags in indoor environments is proposed in order to improve the position estimation and to reduce the number of the tags. Firstly, the stochastic sensor model of RFID is derived and the design factors including the maximum identifiable distance, the identification direction and the read success rate are obtained. The arrangement algorithm is developed with consideration of those factors for a variety of RFID antenna configurations and different indoor environments. The algorithm is implemented on a mobile robot and improvement in position error is experimentally demonstrated.
LSTM 기반 Model-Free LKAS 조향 각 생성
김현우(Hyun-Woo Kim),박장현(Jahng-Hyon Park) 제어로봇시스템학회 2017 제어·로봇·시스템학회 논문지 Vol.23 No.9
In this paper, we propose a lateral upper controller that predicts vehicle motion and generates a model-free LKAS steering angle by applying long-term memory (LSTM), one of the deep learning techniques. The apparent and distinct advantage of this LSTM model is that the relationship of nonlinear sensor data can be grasped and learned devoid of a mathematical model while using the time information. In this sense, the LKAS steering angle can be generated by predicting the movement of the vehicle in consideration of the past vehicle motion based on the sensor data. In addition, the time delay problem due to the difference of sampling time on each sensor can be simply solved by learning based on a time table which has a synchronized sampling time. The input values of the upper controller are the coefficient of the road model and the vehicle dynamic characteristics are obtained from the image processing data from the camera sensor. As for the target values, the steering angles in the next state are selected. The learning model was developed by learning the many-to-one LSTM prediction model with serial connection of LSTM and Fully-Connected (FC) Multilayer Perceptron (MLP). For implementation of the learning model, Tensorflow is employed and the data from a real test road was used. With this model, the learning is conducted and its effectiveness is shown by comparing with a LKAS lateral controller using a model-based multi rate Kalman Filter (MKF).
다양한 이유에서 오는 알 수 없는 오차들의 추정 보상을 위한 오차 기반 RBF 신경망 적응 백스테핑 제어기 설계
김현우(Hyun-Woo Kim),박장현(Jahng-Hyon Park),박상현(Sang-Hyun Park) 제어로봇시스템학회 2018 제어·로봇·시스템학회 논문지 Vol.24 No.6
The servomechanism of the dual axis pan tilt system is used across a wide range of fields. Hence, it requires a robust controller that can control it under any circumstance. In this paper, a dynamic modeling of the dual axis pan tilt system is presented in a strict feedback form, and a backstepping controller is designed. Moreover, an adaptive backstepping controller is designed in a strict feedback form using error state-based radial basis function (RBF) neural networks (NN). The proposed controller prevent any unknown errors due to modeling errors, disturbances, uncertain parameters, or input saturation from undermining control performance. The activation function of the hidden layer was changed. As a result, minimum inputs decrease learning time, thereby allowing the fast estimation and compensation of unknown errors, improving the control performance by change activation function.
황준연(Junyeon Hwang),허건수(Kunsoo Huh),조동일(Dong-il Cho),박장현(Jahng-hyun Park) 한국자동차공학회 2006 한국자동차공학회 춘 추계 학술대회 논문집 Vol.- No.-
Obstacle detection is a crucial issue for driver assistance system as well as for autonomous vehicle guidance function and it has to be performed with high reliability to avoid any potential collision. The vision-based obstacle detection systems are regarded promising for this purpose because they require little infrastructure on a highway. However, the feasibility of these systems in passenger car requires accurate and robust sensing performance. In this paper, an obstacle detection system using stereo vision sensors is developed. This system utilizes ROI setup, feature extraction, feature clustering and feature matching regarded epipoplar constraint in order to robustly detect the initial corresponding pairs. After the initial detection, the system executes the tracking algorithm for the obstacles. Then, the position parameters of the obstacles or leading vehicles can be obtained. The proposed obstacle detection system is implemented on a passenger car and its performances are verified experimentally.
단일 1차원 거리센서를 이용한 이동 로봇의 2차원 위치 추정 알고리즘
전형국(Hyeong-Guk Jeon),정진한(Jin-Han Jeong),김진수(Jin-Soo Kim),윤육현(Yook-Hyun Yoon),박장현(Jahng-Hyon Park) 제어로봇시스템학회 2017 제어·로봇·시스템학회 논문지 Vol.23 No.10
This paper proposes a position estimation algorithm of mobile robots, which estimates the x and y coordinates in a 2D map using a particle filter and a single distance sensor. In addition, this paper describes a method for the indoor global localization of mobile robots by combining the proposed algorithm and Monte Carlo localization algorithm. The combination of the two algorithms can compensate for the disadvantages of the Monte Carlo localization algorithm and remarkably reduce the required time for global localization of a mobile robot. The indoor global localization method using the proposed algorithm is verified by simulation using the MATLAB Robotics System Toolbox and Gazebo simulator of ROS (Robot Operating System). Various simulations confirm that the proposed method successfully operates.