http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
신용득,박재한,박경욱,백승호,백문홍 제어로봇시스템학회 2009 제어로봇시스템학회 국내학술대회 논문집 Vol.2009 No.9
The basic issue of an autonomous robot is mapping the environments. There are many literatures for 2D map, but the latest papers propose the 3D map because it can give the robot a lot of information and reduce the ambiguity of the environments. For the 3D map, multiple 3D scans are necessary and each 3D scan has to be merged into a common coordinate system. This process is called registration. There are many successful algorithms for 2D mapping, but the registration for the 3D mapping is performed in 6 dimensions (three position variables and three orientation variables). Therefore applying these algorithms to the 3D mapping does not give us good results. For solving these problems, we use the ICP algorithm. And the result shows that the registration process works well.
이동로봇의 실내 자율주행을 위한 3차원 거리 데이터를 이용한 적응적 평면 추출
신용득,박재한,박경욱,백승호,백문홍 제어로봇시스템학회 2008 제어로봇시스템학회 국내학술대회 논문집 Vol.2008 No.10
The ability that an autonomous mobile robot recognizes the environments is important to complete their tasks. Recent studies use laser range finder to reconstruct the 3D environments and apply it to the object recognition, self localization and path planning by extracting some useful information from 3D data. The information about planes in 3d environment is a good feature for such an application. When using EM for the extracting plane parameters, we need to know the number of planes already. And If we use the least square method for the extracting plane parameters we have to know the correspondence between the 3D data and planes. In our papers, we suggest the method estimation the planes in 3D environment by fusing the EM method and least square method. And we propose the method finding the edge of the one line scan from LRF for the purpose of estimating the number of planes.
A Study on Reliability Enhancement for Laser and Camera Calibration
신용득,백문홍,박재한,배지헌 제어·로봇·시스템학회 2012 International Journal of Control, Automation, and Vol.10 No.1
The laser and camera calibration problem has been the primary issue in the subject of fusion of 3D space and 2D image information. While the solution for the calibration is mathematically well defined as closed-form by least squares techniques, reliability of the solution can be degraded by uncertainties in measurements. To enhance the reliability of calibration results, we adopted the EM (Expectation-Maximization) algorithm as a noise removal process in the sensor system. The simulation and real experimental results show the effectiveness of our approaches.