Journal of Institute of Control, Robotics and Systems (제어로봇시스템학회논문지)

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지

Automatic Extraction of Stable Visual Landmarks for a Mobile Robot under Uncertainty

이동로봇의 불확실성을 고려한 안정한 시각 랜드마크의 자동 추출

  • 문인혁 (연세대학교 의공학과, 의공학연구소, 첨단의료기기기술혁신센터)
  • Published : 2001.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a method to automatically extract stable visual landmarks from sensory data. Given a 2D occupancy map, a mobile robot first extracts vertical line features which are distinct and on vertical planar surfaces, because they are expected to be observed reliably from various viewpoints. Since the feature information such as position and length includes uncertainty due to errors of vision and motion, the robot then reduces the uncertainty by matching the planar surface containing the features to the map. As a result, the robot obtains modeled stable visual landmarks from extracted features. This extraction process is performed on-line to adapt to an actual changes of lighting and scene depending on the robot’s view. Experimental results in various real scenes show the validity of the proposed method.

본 논문에서는 랜드마트 정보 없이 장해물의 위치 정도 지도만 주어졌을 때 스테레오 시작(stereo vision)을 가진 이동로봇이 관측위치와 조명의 변화에도 강인한 시각 특징을 랜드마크로써 추출하는 수법을 제안한다. 장해물의편평한 면사에서 보다 안쪽영역에 존재하는 특징이 관측위치의 변화에 영향을 덜 받기 때문에 안쪽 영역에 존재하는 수직선 세그먼트(vertical line segment) 특징을 랜드마크로 선택한다. 그러나 선택된 특징에서는 로봇의 이동과 관측이 오차에 의해 불확실성(uncertainty)이 포함되어 있기 때문에 추정해야만 한다. 이를 위해 영역기반 스테레오 정합과 특징기반 스테레오 정합법을 이용하여 정합된 특징을 선택하고 확장 칼만필터(Extended Kalman Filter)를 이용여 선택된 특징의 위치, 길이를 추정하여 랜드마크로써 등록한다. 실내 이동환경에서의 실험을 통해 제안된 수법의 유용성을 보인다.

Keywords

References

  1. I. J. Cox, 'Blanche-an experiment in guidness and navigation of an autonomous robot vehicle,' IEEE Trans. on Robotics and Automation, vol. 7, no. 2, pp. 193-204, 1991 https://doi.org/10.1109/70.75902
  2. C. Backer, J. Salas, K. Tokusei, and J. C. Latombe, 'Reliable navigation using landmarks,' Proc. of IEEE Int. Conf. on Robotics and Automation, pp. 401-406, 1995 https://doi.org/10.1109/ROBOT.1995.525317
  3. I. Moon, J. Miura, and Y. Shirai, 'Dynamic motion planning for efficient visual navigation under uncertainly,' in: Y. Kakazu et al., Intelligent Autonomous System (IAS-5), IOS press, pp. 172-179, 1998
  4. R. Talluri and J. K. Aggarwal, 'Mobile robot self-location using model-image feature correspondence,' IEEE Trans. on Robotics and Automation, vol. 12, no. 1, pp. 63-77, 1996 https://doi.org/10.1109/70.481751
  5. G. Hager, D. Kriegman, E. Yeh, and C. Rasmussen, 'Image-based prediction of landmark features for mobile robot navigation,' Proc. of IEEE Int. Conf. on Robotics and Automation, pp. 1040-1046, 1997 https://doi.org/10.1109/ROBOT.1997.614272
  6. R. Sim and G. Dudek, 'Mobile robot localization from learned landmarks,' Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, pp. 1060-1065, 1998 https://doi.org/10.1109/IROS.1998.727439
  7. D. Fox and W. Burgard, 'Active Markov localization for mobile robots,' Robotics and Autonomous Systems, vol. 25, pp. 195-207, 1999 https://doi.org/10.1016/S0921-8890(98)00049-9
  8. J. J. Little, J. Lu, and D. R. Murray, 'Selecting stable image features for robot localization using stereo,' Proc. of IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, pp. 1072-1077, 1998 https://doi.org/10.1109/IROS.1998.727441
  9. J. Miura and Y. Shirai, 'Vision and motion planning for a mobile robot under uncertainly,' Int. Journal of Robotics Research, vol. 16, pp. 806-825, 1997 https://doi.org/10.1177/027836499701600606
  10. I, Moon, J. Miura, and Y. Shirai, 'On-line viewpoint and motion planning for effecient visual navigation under uncertainly,' Robotics and Autonomous Systems, vol. 28, pp. 237-248, 1999 https://doi.org/10.1016/S0921-8890(99)00020-2
  11. P. S. Maybeck, 'The Kalman filter : An introduce to concepts,' I. J. Cox and G. T. Wilfong, eds., Autonomous Robot Vehicles, pp. 194-204, 1990
  12. S. H. Lee and J. J. Leou, 'A dynamic programming approach to line segment matching in stereo vision,' Pattern Recognition, vol. 28, no. 8, pp. 961-986, 1994 https://doi.org/10.1016/0031-3203(94)90138-4
  13. I. Moon, J. Miura, and Y. Shirai, 'On-line selection of stable visual landmarks for a mobile robot under uncertainly,' Proc. of IJCAI'99 Workshop on Reading with Uncertainly in Robot Navigation, pp. 35-42, 1999
  14. N. Ayache and O. D. Faugeras, 'Maintaining representations of the enviroment of a mobile robot,' IEEE Transm on Robotics and Autonomous, vol. 5, no. 6, pp. 804-819, 1989 https://doi.org/10.1109/70.88101