센서 융합을 통한 환경지도 기반의 강인한 전역 위치추정
Robust Global Localization based on Environment map through Sensor Fusion
2
조회
0
다운로드
6
인용
0
참고문헌
키워드
초록
Global localization is one of the essential issues for mobile robot navigation. In this study, anindoor global localization method is proposed which uses a Kinect sensor and a monocular upwardlookingcamera. The proposed method generates an environment map which consists of a grid map, aceiling feature map from the upward-looking camera, and a spatial feature map obtained from theKinect sensor. The method selects robot pose candidates using the spatial feature map and updatessample poses by particle filter based on the grid map. Localization success is determined by calculatingthe matching error from the ceiling feature map. In various experiments, the proposed method achieveda position accuracy of 0.12m and a position update speed of 10.4s, which is robust enough for realworldapplications.
Abstract
Global localization is one of the essential issues for mobile robot navigation. In this study, anindoor global localization method is proposed which uses a Kinect sensor and a monocular upwardlookingcamera. The proposed method generates an environment map which consists of a grid map, aceiling feature map from the upward-looking camera, and a spatial feature map obtained from theKinect sensor. The method selects robot pose candidates using the spatial feature map and updatessample poses by particle filter based on the grid map. Localization success is determined by calculatingthe matching error from the ceiling feature map. In various experiments, the proposed method achieveda position accuracy of 0.12m and a position update speed of 10.4s, which is robust enough for realworldapplications.
참고문헌 (14)
- R. Siegwart, "Introduction to Autonomous Mobile Robots" (2004), MIT Press
- D. Fox, "Active Markov Localization for Mobile Robots", Robotics and Autonomous Systems, 25, pp.195~207 (1998)
- S. Y. Hwang, "Clustering and probabilistic matching of arbitrarily shaped ceiling features for monocular vision-based SLAM", Advanced Robotics, 27(10), pp.739~747 (2013)
- M. Montemerlo, "FastSLAM 2.0: An improved particle filtering algorithm for simultaneous localization and mapping that provably converges", Proc. of the 16th Int. Joint Conf. on Artificial Intelligence (2003)
- D. Xu, "Ceiling-Based Visual Positioning for an Indoor Mobile Robot With Monocular Vision", IEEE Trans. on Industrial Electronics, 56(5), pp.1617~1628 (2009)
- S. Y. Hwang, "Monocular Vision-based Global Localization Using Position and Orientation of Ceiling Features", Proc. of the IEEE Int. Conf. on Robotics and Automation (2013)
- D. G. Lowe, "Distinctive image features from scaleinvariant keypoints", Int. Journal of Computer Vision, 60(2), pp.91~110 (2004)
- R. Rusinkiewicz, "Efficient Variants of the ICP Algorithm", Int. Conf. on 3D Digital Imaging and Modeling, pp.145~153 (2001)
- S. Se, "Vision-based global localization and mapping for mobile robots", IEEE Trans. on Robotics, 21(3), pp.364~375 (2005)
- M. Ocana, "Automatic training method applied to a WiFi + ultrasound POMDP navigation system", pp.1049~1061 (2009), Robotica
- A. Elfes, "Using Occupancy grids for mobile robot perception and navigation", IEEE Journal of Computer, 22, pp.46~57 (1989)
- S. Thrun, "Probabilistic Robotics" (2005), The MIT Press
- 남창주, "광범위 환경에서 EKF-SLAM의 일관성 향상을 위한 새로운 관찰모델", 로봇학회 논문지, 7(1), pp.29~34 (2012), 한국로봇학회
- 김석용, "패턴 매칭을 이용한 EKF 기반 이동 로봇 실내 위치 추정", 로봇학회 논문지, 7(1), pp.45~56 (2012), 한국로봇학회