http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김정호,권인소,Kim, Jungho,Kweon, In So 대한임베디드공학회 2008 대한임베디드공학회논문지 Vol.3 No.2
Recently many researches on intelligent robots have been studied. An intelligent robot is capable of recognizing environments or objects to autonomously perform specific tasks using sensor readings. One of fundamental problems in vision-based robot applications is to recognize where it is and to decide safe path to perform autonomous navigation. However, previous approaches only consider well-organized environments that there is no moving object and environment changes. In this paper, we introduce a novel navigation strategy to handle occlusions caused by moving objects using various computer vision techniques. Experimental results demonstrate the capability to overcome such difficulties for autonomous navigation.
무인로봇 정밀위치추정을 위한 전술통신 및 영상 기반의 통합항법 성능 분석
최지훈,박용운,송재복,권인소,Choi, Ji-Hoon,Park, Yong-Woon,Song, Jae-Bok,Kweon, In-So 한국군사과학기술학회 2011 한국군사과학기술학회지 Vol.14 No.2
This paper presents a navigation system based on the tactical communication and vision system in outdoor environments which is applied to unmanned robot for perimeter surveillance operations. GPS errors of robot are compensated by the reference station of C2(command and control) vehicle and WiBro(Wireless Broadband) is used for the communication between two systems. In the outdoor environments, GPS signals can be easily blocked due to trees and buildings. In this environments, however, vision system is very efficient because there are many features. With the feature MAP around the operation environments, the robot can estimate the position by the image matching and pose estimation. In the navigation system, thus, operation modes is switched by navigation manager according to some environment conditions. The experimental results show that the unmanned robot can estimate the position very accurately in outdoor environment.