Journal of IKEEE (전기전자학회논문지)

Institute of Korean Electrical and Electronics Engineers (한국전기전자학회)
권호 표지

Mobile Robot Localization and Mapping using Scale-Invariant Features

스케일 불변 특징을 이용한 이동 로봇의 위치 추정 및 매핑

  • Published : 2005.07.01
Download PDF
⟨ Previous Next ⟩

Abstract

A key component of an autonomous mobile robot is to localize itself accurately and build a map of the environment simultaneously. In this paper, we propose a vision-based mobile robot localization and mapping algorithm using scale-invariant features. A camera with fisheye lens facing toward to ceiling is attached to the robot to acquire high-level features with scale invariance. These features are used in map building and localization process. As pre-processing, input images from fisheye lens are calibrated to remove radial distortion then labeling and convex hull techniques are used to segment ceiling region from wall region. At initial map building process, features are calculated for segmented regions and stored in map database. Features are continuously calculated from sequential input images and matched against existing map until map building process is finished. If features are not matched, they are added to the existing map. Localization is done simultaneously with feature matching at map building process. Localization. is performed when features are matched with existing map and map building database is updated at same time. The proposed method can perform a map building in 2 minutes on $50m^2$ area. The positioning accuracy is ${\pm}13cm$, the average error on robot angle with the positioning is ${\pm}3$ degree.

로봇이 자율주행을 하는데 있어 중요한 요소는 로봇 스스로 위치를 추정하고 동시에 주위 환경에 대한 지도를 작성하는 것이다 본 논문에서는 스케일 불변 특정을 이용한 비전 기반 위치 추정 및 매핑 알고리즘을 제안한다. 로봇에 어안렌즈가 부착된 카메라를 천정을 바라볼 수 있도록 부착하여 스케일 불변 특정을 갖는 고급의 영상 특정을 구하여 맹 빌딩과 위치 추정을 수행한다. 먼저, 전처리 과정으로 어안렌즈를 통해 입력된 영상을 카메라 보정을 행하여 축방향 왜곡을 제거하고 레이블링과 컨벡스헐을 적용하여 천정영역과 벽영역으로 분할한다 최초 맵 빌딩시에는 분할된 영역에 대해 특정점을 구하고 맵 데이터베이스에 저장한다. 맵 빌딩이 종료될 때까지 연속하여 입력되는 영상에 대해 특정점들을 구하고 이미 작성된 맵과 매칭되는 점들을 찾고 매칭되지 않은 점들에 대해서는 기존의 맴에 추가하는 과정을 반복한다. 위치 추정은 맵 빌딩과정에서 매칭되는 점들을 찾을 때 동시에 수행되어 진다. 그리고 임의의 위치에서 기존의 작성된 맵과 매칭되는 점들을 찾음으로서 위치 추정이 행해지며 동시에 기존의 맵 데이터베이스의 특정점들을 갱신하게 된다. 제안한 방법은 $50m^2$의 영역에 대해 맵 빌딩을 2 분내에 수행할 수 있었으며, 위치의 정확도는 ${\pm}13cm$, 위치에 대한 로봇의 자세(각도)는 ${\pm}3$도의 오차를 갖는다.

Keywords

References

  1. IEEE Trans. on Robotics and Automation v.12-5 Measurement and correction of systematic orlometry errors in mobile robots Borenstein, J.;Feng, L.
  2. Navigating Mobile Robots : System and Techniques Borenstein, J.;Everett, B.;Feng, L.;Peters, A.K.
  3. Geometry from visual motion;Active Vision Ranis, C.;Blake, A.(ed.);Yuille, A.(ed.)
  4. Machine Learning and Autonomous Robotics v.31-5 A probabilities approach to concurrent mapping and localization for mobile robots Thrun, S.;Burgard, W.;Fox, D.
  5. IEEE Int., Conference on Robotics and Automation(ICRA) A real-time algorithm for mobile robot mapping with applications to multi-robot and 3D mapping Thrun, S.;Burgard, W.;Fox, D.
  6. Proc. of IEEE Conference on Computer Vision and Pattern Recognition(CVPR'99) Using the condensation algorithm for robust, vision based mobile robot localization Dellaert, F.;Burgard, W.;Fox, D.;Thrun, S.
  7. Proc., of the IEEE International Conference on Robotics and Automation(ICRA) Experiments on augmenting condensation for mobile robot localization Jensfelt, P.;Wijk, O.;Austin, D.J.;Andersson, M.
  8. Proc., of the Seventh Intemational Conference on Computer Vision(ICCV'99) Learning and evaluating visual features for pose estimation Sim, R.;Dudek, G.
  9. 4th Int. Symposium on Robotics Research A stochastic map for uncertain spatial relationships Smith, R.;Self, M.;Cheeseman, P.
  10. Proc., of IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS) Simultaneous map building and localization for an autonomous mobile robot Leonard, J.J.;Durrant-Whyte, H.F.
  11. Proc. of 6th Int. Symposium an Experimental Robotics Sensor influence in the performance of simultaneous loc:a1isation and map building Castellanos, J.A.;Montial, J.M.M.;Neira, J.;Tardoo, J.D.
  12. Proc., of Int., Conference on Robotics and Automation(ICRA) Autonomous underwater simultaneous localisation and map building Williams, S.B.;Newman, P.;Dissanayake, G.;Durrant-Whyte, H.
  13. Proc. of IEEE Int. Conference on Robotics and Automation Simultaneous localisation and map building for mobile robots A landmark-based approach Castellanos, J.A.;Devy, M.;Tardos, J.D.
  14. 9th International Symposium of Robotics Research A computational efficient method for large-scale concurrent mapping and localizationw Leonard, J.J.;Feder, H.J.S.
  15. Mobile Robot Navigation Using Active Vision Davison, A.J.
  16. Proc., of IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS) Towards constant time slam using postponement Knight, J.;Davison, A.;Reid, I.
  17. Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition An efficient and accurate camera calibration teclrnique for 3-D machine vision Tsai, R.
  18. IEEE Trans. Pattern Anal Machine Intell. v.14 no.10 Camera calibration with distortion models and accuracy evaluation Weng, J.;Cohen, P.;Herniou, M.
  19. Computer Vision, Graphics and Image Processing v.35 Calibration of a camera and light source by fitting tv a physical model Mansbach, P.
  20. Multiple View Geometry in Computer Vision Hartley, Richard;Zisserman, Andrew
  21. Machine Vision Theory Algorithms Practices Davies, E.R.
  22. Proceedings of Computer Vision and Pattern Recognition A performance evaluation of local descriptors Mikolajczyk, K.;Schmid, C.
  23. International Journal of Computer Vision v.60 no.2 Distinctive image features from scale invariant keypoints Lowe, D.G.
  24. Proceedings of International Conference on Computer Vision Object recognition from local scale invanlillt features Lowe, D.G.
  25. 10th International Conference on Computer Vision(ICCV2003) Recognizing Panoramas Brown, M.;Lowe, D.G.
  26. Proc. of lnt. Conf. on lROS2004 Care Technologies for Sevice Robotics Niklas Karlsson(et al.)