Mapping and localization module in a mobile robot for insulating building crawl spaces

Abstract This paper presents a novel robotic system that applies spray foam insulation in underfloor voids in order to improve the energy efficiency of buildings. The work focuses on solving the mapping and localization problems in such environments, since they are a key factor in the autonomy of the robot. Solving these tasks in underfloor voids is especially challenging because the terrain is extremely uneven due to the presence of stones, bricks and sand. Within these environments, the robot should be able to localize itself and apply the insulation foam to the underside of the floor. The robot is equipped with a 2D laser sensor which permits building point clouds from several positions of the underfloor environment. The localization process is solved by estimating the position of the robot with respect to previously known positions. For this purpose, the alignment between point clouds is calculated. This paper describes two algorithms to robustly obtain the alignment between two positions. The proposed algorithms are tested with a set of point clouds captured with a laser scan in several environments under real working conditions. The results show that the localization problem can be solved in such challenging underfloor voids by using depth information.

[1]  Jun Xie,et al.  Fine registration of 3D point clouds fusing structural and photometric information using an RGB-D camera , 2015, J. Vis. Commun. Image Represent..

[2]  Chang-Soo Han,et al.  Auto inspection system using a mobile robot for detecting concrete cracks in a tunnel , 2007 .

[3]  Wolfram Burgard,et al.  An evaluation of the RGB-D SLAM system , 2012, 2012 IEEE International Conference on Robotics and Automation.

[4]  David Valiente,et al.  Visual SLAM Based on Single Omnidirectional Views , 2014 .

[5]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[6]  Guido M. Cortelazzo,et al.  3D scanning of cultural heritage with consumer depth cameras , 2016, Multimedia Tools and Applications.

[7]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[8]  Roland Siegwart,et al.  BRISK: Binary Robust invariant scalable keypoints , 2011, 2011 International Conference on Computer Vision.

[9]  Sheng Fu,et al.  SLAM for mobile robots using laser range finder and monocular vision , 2007, 2007 14th International Conference on Mechatronics and Machine Vision in Practice.

[10]  Paul Newman,et al.  Using laser range data for 3D SLAM in outdoor environments , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[11]  Jia-Ruey Chang,et al.  Strategies for autonomous robots to inspect pavement distresses , 2011 .

[12]  D. J. Harris,et al.  Heat losses from suspended timber floors: Laboratory experiments measuring heat losses through flooring utilizing a variety of insulation and ventilation rates to determine appropriate strategies for retrofitting insulation , 1997 .

[13]  Heinz Hügli,et al.  Fast ICP Algorithms for Shape Registration , 2002, DAGM-Symposium.

[14]  Dieter Fox,et al.  RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments , 2012, Int. J. Robotics Res..

[15]  Tomasz Kornuta,et al.  Point-Based Object Recognition in RGB-D Images , 2014, IEEE Conf. on Intelligent Systems.

[16]  George Vosselman,et al.  Mapping Indoor Spaces by Adaptive Coarse-to-Fine Registration of RGB-D Data , 2016, IEEE Geoscience and Remote Sensing Letters.

[17]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Peter R.N. Childs,et al.  A robot for spray applied insulation in underfloor voids , 2016 .

[19]  Kostas Daniilidis,et al.  Monocular visual odometry in urban environments using an omnidirectional camera , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[20]  Brenda McCabe,et al.  Automated computer vision-based detection of components of under-construction indoor partitions , 2017 .

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

[22]  K. S. Arun,et al.  Least-Squares Fitting of Two 3-D Point Sets , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Rajesh Elara Mohan,et al.  Toward a framework for robot-inclusive environments , 2016 .

[24]  Yi Ping Hung,et al.  A fast automatic method for registration of partially-overlapping range images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[25]  Olivier Stasse,et al.  MonoSLAM: Real-Time Single Camera SLAM , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.