Robust AUV Localization Based on Switchable Constraints

In mission of marine exploration, AUV is often used to perform seabed exploration and map construction on the sea floor. As there are many similar sea-floor images, AUV often suffers false positive loop closures in similar underwater environments during Simultaneous Localization and Mapping (SLAM). In this paper, a robust optimization method is proposed to eliminate loop closures during AUV localization and mapping, based on switchable constraints. The proposed method is verified both qualitatively and quantitatively in simulation and underwater experiments.

[1]  Markus König,et al.  Natural markers for augmented reality-based indoor navigation and facility maintenance , 2014 .

[2]  Daniel Cremers,et al.  Semi-dense Visual Odometry for a Monocular Camera , 2013, 2013 IEEE International Conference on Computer Vision.

[3]  X. Jin.  Factor graphs and the Sum-Product Algorithm , 2002 .

[4]  Paul Newman,et al.  Highly scalable appearance-only SLAM - FAB-MAP 2.0 , 2009, Robotics: Science and Systems.

[5]  Frank Dellaert,et al.  Incremental smoothing and mapping , 2008 .

[6]  Wolfram Burgard,et al.  Efficient Sparse Pose Adjustment for 2D mapping , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Niko Sünderhauf,et al.  Switchable constraints for robust pose graph SLAM , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[8]  Wolfram Burgard,et al.  G2o: A general framework for graph optimization , 2011, 2011 IEEE International Conference on Robotics and Automation.

[9]  John J. Leonard,et al.  Place Recognition using Near and Far Visual Information , 2011 .

[10]  Niko Sünderhauf.  Robust optimization for simultaneous localization and mapping , 2012 .

[11]  Edwin Olson,et al.  Fast iterative alignment of pose graphs with poor initial estimates , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..