Robot Mapping and Localisation for Feature Sparse Water Pipes Using Voids as Landmarks

Robotic systems for water pipe inspection do not generally include navigation components for mapping the pipe network and locating damage. Such navigation systems would be highly advantageous for water companies because it would allow them to more effectively target maintenance and reduce costs. In water pipes, a major challenge for robot navigation is feature sparsity. In order to address this problem, a novel approach for robot navigation in water pipes is developed here, which uses a new type of landmark feature - voids outside the pipe wall, sensed by ultrasonic scanning. The method was successfully demonstrated in a laboratory environment and showed for the first time the potential of using voids for robot navigation in water pipes.

[1]  Michael Burrow,et al.  Condition assessment of the buried utility service infrastructure , 2012 .

[2]  Hugh F. Durrant-Whyte,et al.  Simultaneous localization and mapping: part I , 2006, IEEE Robotics & Automation Magazine.

[3]  Josep M. Mirats Tur,et al.  Robotic devices for water main in‐pipe inspection: A survey , 2010, J. Field Robotics.

[4]  Aníbal Ollero,et al.  A robotic system for internal inspection of water pipelines , 1999, IEEE Robotics Autom. Mag..

[5]  Hugh F. Durrant-Whyte,et al.  A solution to the simultaneous localization and map building (SLAM) problem , 2001, IEEE Trans. Robotics Autom..

[6]  Homayoun Najjaran,et al.  Development of Visual Simultaneous Localization and Mapping (VSLAM) for a Pipe Inspection Robot , 2007, 2007 International Symposium on Computational Intelligence in Robotics and Automation.

[7]  Simo Särkkä,et al.  Bayesian Filtering and Smoothing , 2013, Institute of Mathematical Statistics textbooks.

[8]  Sebastian Thrun,et al.  FastSLAM: A Scalable Method for the Simultaneous Localization and Mapping Problem in Robotics , 2007 .

[9]  Simo Srkk,et al.  Bayesian Filtering and Smoothing , 2013 .

[10]  Byung-Ju Yi,et al.  SLAM in indoor pipelines with 15mm diameter , 2008, 2008 IEEE International Conference on Robotics and Automation.