Point Cloud Feature Extraction Based Integrated Positioning Method for Unmanned Vehicle

Abstract:

The characteristics of unmanned vehicle makes it be used widely in industrial production, space exploration and other fields and unmanned vehicle navigation positioning technology is the most basic aspects. This paper discusses the integrated positioning technology of unmanned vehicle which combines vision sensor with the dead reckoning to achieve precise positioning of the vehicles. By introducing the normal estimated of point cloud, the expected plane feature of point cloud data can be extracted with RANSAC well, which is done with Point Cloud Library (PCL). The effect of unmanned vehicle positioning is also discussed with the plane feature. The corresponding program is applied in the P3-AT Pioneer Robot for validation.

• Periodical: Applied Mechanics and Materials (Volume 590)
• Pages: 463-469
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.590.463
• Online since: June 2014
• Authors: Yue Ma, Zheng Chao Wei*, Yu Wang
• Keywords: Dead Reckoning (DR), Point Cloud Feature Extraction, Stereo Vision

References

[1] Ahmad Kamal Aijazi, Paul Checchin, and Laurent Trassoudaine. Segmentation Based Classification of 3D Urban Point Clouds: A Super-Voxel Based Approach with Evaluation. Remote Sens. 2013, 5, 1624-1650.

DOI: 10.3390/rs5041624

[2] D. Maier and Alexander Kleiner, Improved GPS Sensor Model for Mobile Robots in Urban Terrain, IEEE Int. Conf. on Robotics and Automation (ICRA), 2010, 4385-4390.

DOI: 10.1109/robot.2010.5509895

[3] Howard, A Real-time stereo visual odometry for autonomous ground vehicles. International conference on Intelligent Robots and Systems. Piscatawa, 2008, pages 3946-3952.

DOI: 10.1109/iros.2008.4651147

[4] Liu Ruizhen, Yu Shiqi. OpenCV tutorials. Beijing: Beihang University Press. 2009. Liu Zhenyu, Jiang Nan, Zhang Lingtao. Self-localization of mobile robots based on artificial landmarks and stereo vision. Computer Engineering And Applications. 41(2010).

[5] Radu Bogdan Rusu, Nico Blodow, Zoltan Csaba Marton, and Michael Beetz. Close-range Scene Segmentation and Reconstruction of 3D Point Cloud Maps for Mobile Manipulation in Human Environments. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), St. Louis, MO, USA, October 11-15 (2009).

DOI: 10.1109/iros.2009.5354683

[6] Stentz Anthony, Kelly Alonzo, Rander Peter, Herman Herman, Amidi Omead, Mandelbaum Robert, Salgian Garbis, and Pedersen Jorgen. Real-Time, Multi-Perspective Perception for Unmanned Ground Vehicles. Robotics Institute. Paper 16. (2003).

[7] Strom, J., Richardson, A., Olson, E., Graph-Based Segmentation for Colored 3D Laser Point Clouds. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Taipei, Taiwan, 18–22 October 2010; p.2131–2136.

DOI: 10.1109/iros.2010.5650459

[8] Thompson S, Kagami S. Stereo Vision Terrain Model for Non-Planar Mobile Robot Mapping and Navigation, IEEE International Conference on System, Man and Cybernetics, volume 6, pages 5392-5397, 10-13 October, (2004).

DOI: 10.1109/icsmc.2004.1401051

[9] Zhu Dehai, Guo Hao, Su Wei. Point Cloud Library tutorials. Beijing: Beijing Institute of Technology Press. (2012).

[10] Klasing, K., Althoff, D., Wollherr, D. Buss, M. Comparison of Surface Normal Estimation Methods for Range Sensing Applications. In Proceedings of the IEEE International Conference on Robotics and Automation, Kobe, Japan, 12–17 May 2009; p.3206.

DOI: 10.1109/robot.2009.5152493

[11] Lingua, A, Marenchino, D, Nex, F, Performance analysis of the SIFT operator for automatic feature extraction and matching in photogrammetric applications. Sensors , 2009, 9, 3745-3766.

DOI: 10.3390/s90503745