GPGPU implementation of On-Line point to plane 3D data registration

The paper concerns the result of the implementation of classic point to plane 3D data registration method with an improvement based on GPGPU parallel computation. 3D data is delivered by mobile robot equipped with 3D laser measurement system for INDOOR and OUTDOOR environments. Presented empirical analysis of the implementation shows the On-Line computation capability using modern graphic processor unit NVIDIA GF 580. The implementation is a part of a project “Semantic simulation engine” composed of following modules: data registration module, semantic entities identification module, semantic simulation. The goal of the project is to deliver software tools capable to create virtual model of the environment based on robot observations and perform semantic simulation, where all virtual entities correspond to real one. Possible practical application of the project are supervision and control of robotic system and mobile robot operator training using Augmented Reality techniques. Data registration module is composed of the implementation of point to point and point to plane classic methods improved by the usage of parallel computation. In this paper it has been shown that the implementation of GPGPU point to plane registration method is accurate in INDOOR structured environment but it has some difficulties in accurate alignment in OUTDOOR environment.

[1]  Andrew W. Fitzgibbon.  Robust registration of 2D and 3D point sets , 2003, Image Vis. Comput..

[2]  Wolfram Burgard,et al.  A real-time algorithm for mobile robot mapping with applications to multi-robot and 3D mapping , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[3]  H. Jensen.  Realistic Image Synthesis Using Photon Mapping , 2001 .

[4]  J. Będkowski,et al.  "Semantic simulation engine" for mobile robotic applications , 2011 .

[5]  Michel Barlaud,et al.  Fast k nearest neighbor search using GPU , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[6]  Sebastian Thrun,et al.  A Multi-Resolution Pyramid for Outdoor Robot Terrain Perception , 2004, AAAI.

[7]  Pat Hanrahan,et al.  Photon mapping on programmable graphics hardware , 2003, HWWS '03.

[8]  Tom Duckett,et al.  A comparison of 3D registration algorithms for autonomous underground mining vehicles , 2005 .

[9]  Tom Duckett,et al.  Scan registration for autonomous mining vehicles using 3D‐NDT , 2007, J. Field Robotics.

[10]  Joachim Hertzberg,et al.  Automatic model refinement for 3D reconstruction with mobile robots , 2003, Fourth International Conference on 3-D Digital Imaging and Modeling, 2003. 3DIM 2003. Proceedings..

[11]  Michael Garland,et al.  Designing efficient sorting algorithms for manycore GPUs , 2009, 2009 IEEE International Symposium on Parallel & Distributed Processing.

[12]  Joachim Hertzberg,et al.  An Explicit Loop Closing Technique for 6D SLAM , 2009, ECMR.

[13]  Joachim Hertzberg,et al.  Towards semantic maps for mobile robots , 2008, Robotics Auton. Syst..

[14]  Soon-Yong Park,et al.  An accurate and fast point-to-plane registration technique , 2003, Pattern Recognit. Lett..

[15]  Soon-Yong Park,et al.  Real-time 3D registration using GPU , 2011, Machine Vision and Applications.

[16]  Marc Levoy,et al.  Efficient variants of the ICP algorithm , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[17]  Sunil Arya,et al.  Algorithms for fast vector quantization , 1993, [Proceedings] DCC `93: Data Compression Conference.

[18]  Nico Blodow,et al.  Persistent Point Feature Histograms for 3D Point Clouds , 2008 .

[19]  P. Kowalski,et al.  Computer training with ground teleoperated robots for de-mining , 2011 .

[20]  Janusz Bedkowski,et al.  Methodology of control and supervision of web connected mobile robots with CUDA technology application , 2011 .

[21]  Tim Foley,et al.  KD-tree acceleration structures for a GPU raytracer , 2005, HWWS '05.

[22]  Oliver Grau,et al.  A scene analysis system for the generation of 3-D models , 1997, Proceedings. International Conference on Recent Advances in 3-D Digital Imaging and Modeling (Cat. No.97TB100134).

[23]  Hubert Nguyen,et al.  GPU Gems 3 , 2007 .

[24]  Joachim Hertzberg,et al.  Cached k-d tree search for ICP algorithms , 2007, Sixth International Conference on 3-D Digital Imaging and Modeling (3DIM 2007).

[25]  Helmut Pottmann,et al.  Registration without ICP , 2004, Comput. Vis. Image Underst..

[26]  Martial Hebert,et al.  Fully automatic registration of multiple 3D data sets , 2003, Image Vis. Comput..

[27]  Juan Andrade-Cetto,et al.  Graph-based Segmentation of Range Data with Applications to 3D Urban Mapping , 2009, ECMR.

[28]  Andreas Nüchter,et al.  GPU-Accelerated Nearest Neighbor Search for 3D Registration , 2009, ICVS.

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

[30]  Robust Registration of 2 D and 3 D Point Sets , 2001 .

[31]  Rüdiger Dillmann,et al.  Sequential 3D-SLAM for mobile action planning , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).