http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Extraction of Different Types of Geometrical Features from Raw Sensor Data of Two-dimensional LRF
Rui-Jun Yan(염서군),Jing Wu(무경),Chao Yuan(원조),Chang-Soo Han(한창수) 제어로봇시스템학회 2015 제어·로봇·시스템학회 논문지 Vol.21 No.3
This paper describes extraction methods of five different types of geometrical features (line, arc, corner, polynomial curve, NURBS curve) from the obtained raw data by using a two-dimensional laser range finder (LRF). Natural features with their covariance matrices play a key role in the realization of feature-based simultaneous localization and mapping (SLAM), which can be used to represent the environment and correct the pose of mobile robot. The covariance matrices of these geometrical features are derived in detail based on the raw sensor data and the uncertainty of LRF. Several comparison are made and discussed to highlight the advantages and drawbacks of each type of geometrical feature. Finally, the extracted features from raw sensor data obtained by using a LRF in an indoor environment are used to validate the proposed extraction methods.
누적 센서 데이터 갱신을 이용한 아크/라인 세그먼트 기반 SLAM
염서군(Rui-Jun Yan),최윤성(Youn-sung Choi),무경(Jing Wu),한창수(Chang-soo Han) 제어로봇시스템학회 2015 제어·로봇·시스템학회 논문지 Vol.18 No.12
This paper presents arc/line segments-based Simultaneous Localization and Mapping (SLAM) by updating accumulated laser sensor data with a mobile robot moving in an unknown environment. For each scan, the sensor data in the set are stored by a small constant number of parameters that can recover the necessary information contained in the raw data of the group. The arc and line segments are then extracted according to different limit values, but based on the same parameters. If two segments, whether they are homogenous features or not, from two scans are matched successfully, the new segment is extracted from the union set with combined data information obtained by means of summing the equivalent parameters of these two sets, not combining the features directly. The covariance matrixes of the segments are also updated and calculated synchronously employing the same parameters. The experiment results obtained in an irregular indoor environment show the good performance of the proposed method.
누적 센서 데이터 갱신을 이용한 아크/라인 세그먼트 기반 SLAM
염서군,최윤성,무경,한창수,Yan, Rui-Jun,Choi, Youn-sung,Wu, Jing,Han, Chang-soo 제어로봇시스템학회 2015 제어·로봇·시스템학회 논문지 Vol.21 No.10
This paper presents arc/line segments-based Simultaneous Localization and Mapping (SLAM) by updating accumulated laser sensor data with a mobile robot moving in an unknown environment. For each scan, the sensor data in the set are stored by a small constant number of parameters that can recover the necessary information contained in the raw data of the group. The arc and line segments are then extracted according to different limit values, but based on the same parameters. If two segments, whether they are homogenous features or not, from two scans are matched successfully, the new segment is extracted from the union set with combined data information obtained by means of summing the equivalent parameters of these two sets, not combining the features directly. The covariance matrixes of the segments are also updated and calculated synchronously employing the same parameters. The experiment results obtained in an irregular indoor environment show the good performance of the proposed method.
Extraction of Different Types of Geometrical Features from Raw Sensor Data of Two-dimensional LRF
염서군,무경,원조,한창수,Yan, Rui-Jun,Wu, Jing,Yuan, Chao,Han, Chang-Soo Institute of Control 2015 제어·로봇·시스템학회 논문지 Vol.21 No.3
This paper describes extraction methods of five different types of geometrical features (line, arc, corner, polynomial curve, NURBS curve) from the obtained raw data by using a two-dimensional laser range finder (LRF). Natural features with their covariance matrices play a key role in the realization of feature-based simultaneous localization and mapping (SLAM), which can be used to represent the environment and correct the pose of mobile robot. The covariance matrices of these geometrical features are derived in detail based on the raw sensor data and the uncertainty of LRF. Several comparison are made and discussed to highlight the advantages and drawbacks of each type of geometrical feature. Finally, the extracted features from raw sensor data obtained by using a LRF in an indoor environment are used to validate the proposed extraction methods.
Adaptive RRT 를 사용한 고 자유도 다물체 로봇 시스템의 효율적인 경로계획
김동형(Dong-Hyung Kim),최윤성(Youn-Sung Choi),염서군(Rui-Jun Yan),라로평(Lu-Ping Luo),이지영(Ji Yeong Lee),한창수(Chang-Soo Han) 제어로봇시스템학회 2015 제어·로봇·시스템학회 논문지 Vol.21 No.3
This paper proposes an adaptive RRT (Rapidly-exploring Random Tree) for path planning of high DOF multibody robotic system. For an efficient path planning in high-dimensional configuration space, the proposed algorithm adaptively selects the robot bodies depending on the complexity of path planning. Then, the RRT grows only using the DOFs corresponding with the selected bodies. Since the RRT is extended in the configuration space with adaptive dimensionality, the RRT can grow in the lower dimensional configuration space. Thus the adaptive RRT method executes a faster path planning and smaller DOF for a robot. We implement our algorithm for path planning of 19 DOF robot, AMIRO. The results from our simulations show that the adaptive RRTbased path planner is more efficient than the basic RRT-based path planner.