Abstract
This paper proposes a unified framework called GPmap for reconstructing surface meshes and building continuous occupancy maps using sparse Gaussian processes. Previously, Gaussian processes have been separately applied for surface reconstruction and occupancy mapping with different function definitions. However, by adopting the signed distance function as the latent function and applying the probabilistic least square classification, we solve two different problems in a single framework. Thus, two different map representations can be obtained at a single cast, for instance, an object shape for grasping and an occupancy map for obstacle avoidance. Another contribution of this paper is reduction of computational complexity for scalability. The cubic computational complexity of Gaussian processes is a well-known issue limiting its applications for large-scale data. We address this by applying the sparse covariance function which makes distant data independent and thus divides both training and test data into grid blocks of manageable sizes. In contrast to previous work, the size of grid blocks is determined in a principled way by learning the characteristic length-scale of the sparse covariance function from the training data. We compare theoretical complexity with previous work and demonstrate our method with structured indoor and unstructured outdoor datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Borrmann, D., Nüchter, A.: The robotic 3d scan repository of Jacobs University, http://kos.informatik.uni-osnabrueck.de/3Dscans/
Dragiev, S., Toussaint, M., Gienger, M.: Gaussian process implicit surfaces for shape estimation and grasping. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 2845–2850 (2011)
Hadsell, R., Bagnell, J., Huber, D., Hebert, M.: Space-carving kernels for accurate rough terrain estimation. The International Journal of Robotics Research 29(8), 981–996 (2010)
Herbert, M., Caillas, C., Krotkov, E., Kweon, I.S., Kanade, T.: Terrain mapping for a roving planetary explorer. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 997–1002 (1989)
Herbrich, R., Lawrence, N.D., Seeger, M.: Fast sparse Gaussian process methods: The informative vector machine. In: Advances in Neural Information Processing Systems 14, pp. 609–616. MIT Press (2002)
Hollinger, G., Englot, B., Hover, F., Mitra, U., Sukhatme, G.: Active planning for underwater inspection and the benefit of adaptivity. The International Journal of Robotics Research 32(1), 3–18 (2013)
Hornung, A.: Octomap 3d scan dataset, http://ais.informatik.uni-freiburg.de/projects/datasets/octomap/
Hornung, A., Wurm, K.M., Bennewitz, M., Stachniss, C., Burgard, W.: Octomap: an efficient probabilistic 3d mapping framework based on octrees. In: Autonomous Robots, pp. 1–18 (2013)
Kim, S., Kim, J.: Towards large-scale occupancy map building using Dirichlet and Gaussian processes. In: Proceedings of the Australasian Conference on Robotics and Automation (2011)
Kim, S., Kim, J.: Building large-scale occupancy maps using an infinite mixture of Gaussian process experts. In: Proceedings of the Australasian Conference on Robotics and Automation (2012)
Kim, S., Kim, J.: Building occupancy maps with a mixture of Gaussian processes. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 4756–4761 (2012)
Kim, S., Kim, J.: Continuous occupancy maps using overlapping local gaussian processes. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (2013)
Kim, S., Kim, J.: Occupancy mapping and surface reconstruction using local gaussian processes with kinect sensors. IEEE Transactions on Cybernetics 43(5), 1335–1346 (2013)
Lang, T., Plagemann, C., Burgard, W.: Adaptive non-stationary kernel regression for terrain modeling. In: Proceedings of Robotics: Science and Systems (2007)
Lorensen, W., Cline, H.: Marching cubes: A high resolution 3D surface construction algorithm. ACM SIGGRAPH Computer Graphics 21, 163–169 (1987)
Melkumyan, A., Ramos, F.: A sparse covariance function for exact Gaussian process inference in large datasets. In: Proceedings of International Joint Conference on Artificial Intelligence, pp. 1936–1942 (2009)
Moravec, H., Elfes, A.: High resolution maps from wide angle sonar. In: Proceedings of the IEEE International Conference on Robotics and Automation, vol. 2, pp. 116–121 (1985)
O’Callaghan, S., Ramos, F.: Continuous occupancy mapping with integral kernels. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1494–1500 (2011)
O’Callaghan, S., Ramos, F.: Gaussian process occupancy maps. The International Journal of Robotics Research 31(1), 42–62 (2012)
Plagemann, C., Mischke, S., Prentice, S., Kersting, K., Roy, N., Burgard, W.: Learning predictive terrain models for legged robot locomotion. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 3545–3552 (2008)
Platt, J.C.: Probabilities for SV Machines. In: Advances in Large Margin Classifiers, pp. 61–74. MIT Press (2000)
Pomerleau, F., Liu, M., Colas, F., Siegwart, R.: Challenging data sets for point cloud registration algorithms. The International Journal of Robotics Research 31(14), 1705–1711 (2012)
Rasmussen, C., Williams, C.: Gaussian Processes for Machine Learning. MIT Press (2006)
Rusu, R.B., Cousins, S.: 3d is here: Point cloud library (pcl). In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 1–4 (2011)
Seeger, M., Williams, C.K., Lawrence, N.D.: Fast forward selection to speed up sparse Gaussian process regression. In: Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics (2003)
Shen, Y., Ng, A., Seeger, M.: Fast Gaussian process regression using kd-trees. In: Advances in Neural Information Processing Systems 18, pp. 1225–1232. MIT Press (2006)
Smith, M., Posner, I., Newman, P.: Adaptive compression for 3d laser data. The International Journal of Robotics Research 30(7), 914–935 (2011)
Solak, E., Murray-Smith, R., Leithead, W.E., Leith, D.J., Rasmussen, C.E.: Derivative observations in Gaussian process models of dynamic systems. In: Advances in Neural Information Processing Systems 13, pp. 1057–1064. MIT Press (2003)
Steder, B., Kümmerle, R.: The outdoor dataset of the University of Freiburg, http://ais.informatik.uni-freiburg.de/projects/datasets/fr360/
Vasudevan, S., Ramos, F., Nettleton, E., Durrant-Whyte, H.: Gaussian process modeling of large-scale terrain. Journal of Field Robotics 26(10), 812–840 (2009)
Williams, O., Fitzgibbon, A.: Gaussian process implicit surfaces. In: Proceedings of the Workshop on Gaussian Processes in Practice (2006)
Wurm, K.M., Hornung, A., Bennewitz, M., Stachniss, C., Burgard, W.: Octomap: A probabilistic, flexible, and compact 3D map representation for robotic systems. In: Proceedings of the ICRA Workshop on Best Practice in 3D Perception and Modeling for Mobile Manipulation (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Kim, S., Kim, J. (2015). GPmap: A Unified Framework for Robotic Mapping Based on Sparse Gaussian Processes. In: Mejias, L., Corke, P., Roberts, J. (eds) Field and Service Robotics. Springer Tracts in Advanced Robotics, vol 105. Springer, Cham. https://doi.org/10.1007/978-3-319-07488-7_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-07488-7_22
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-07487-0
Online ISBN: 978-3-319-07488-7
eBook Packages: EngineeringEngineering (R0)