Have I Been Here Before? A Method for Detecting Loop Closure With LiDAR

Abstract : Loop closure detection has progressed to operate in real time in areas as massive as an entire city. This impressive result is enabled by the richness and uniqueness of visual stimuli in a city. If a robot were required instead to operate in a deep underground complex of tunnels that is absent of unique features, then a new set of tools is needed to enable a similar level of performance. We present a unified representation for recognizing global loop closure, which incorporates appearance- and spatial-based techniques on a mobile robot system, which has the unfortunate task of exploring a system of austere underground tunnels with only a laser scanner as a guide.

[1]  Juan D. Tardós,et al.  Data association in stochastic mapping using the joint compatibility test , 2001, IEEE Trans. Robotics Autom..

[2]  Gary R. Bradski,et al.  Learning OpenCV - computer vision with the OpenCV library: software that sees , 2008 .

[3]  Nico Blodow,et al.  Fast Point Feature Histograms (FPFH) for 3D registration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[4]  Henrik I. Christensen,et al.  Planar surface SLAM with 3D and 2D sensors , 2012, 2012 IEEE International Conference on Robotics and Automation.

[5]  Yu Zhong,et al.  Intrinsic shape signatures: A shape descriptor for 3D object recognition , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[6]  Gordon Wyeth,et al.  OpenFABMAP: An open source toolbox for appearance-based loop closure detection , 2012, 2012 IEEE International Conference on Robotics and Automation.

[7]  C. N. Liu,et al.  Approximating discrete probability distributions with dependence trees , 1968, IEEE Trans. Inf. Theory.

[8]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.

[9]  Paul Newman,et al.  FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance , 2008, Int. J. Robotics Res..