AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
We presented OctoMap, an open source framework for three-dimensional mapping

OctoMap: an efficient probabilistic 3D mapping framework based on octrees

Auton. Robots, no. 3 (2013): 189-206

Cited by: 1817|Views118
EI

Abstract

Three-dimensional models provide a volumetric representation of space which is important for a variety of robotic applications including flying robots and robots that are equipped with manipulators. In this paper, we present an open-source framework to generate volumetric 3D environment models. Our mapping approach is based on octrees and...More

Code:

Data:

0
Introduction
  • Several robotic applications require a 3D model of the environment.
  • These include airborne, underwater, outdoor, or extra-terrestrial missions.
  • 3D models are relevant for many domestic scenarios, for example, for mobile manipulation and navigation tasks.
  • 3D mapping is an integral component of many robotic systems, there exist few readily available, reliable, A.
  • Hornung (B)· K.
  • M. Wurm · M.
  • Bennewitz · C.
  • Stachniss ·
Highlights
  • Several robotic applications require a 3D model of the environment
  • 3D mapping is an integral component of many robotic systems, there exist few readily available, reliable, A
  • In our previous work (Hornung et al 2010), we developed a localization method based on OctoMap as 3D environment model
  • We presented OctoMap, an open source framework for three-dimensional mapping
  • Our approach uses an efficient data structure based on octrees that enables a compact memory representation and multi-resolution map queries
  • We evaluated our approach with various realworld data sets
Results
  • The approach presented in this paper has been evaluated using several real world datasets as well as simulated ones.
  • 5.1 Sensor model for laser range data.
  • Since the realworld datasets were mostly acquired with laser range finders, the authors employ a beam-based inverse sensor model which assumes that endpoints of a measurement correspond to obstacle surfaces and that the line of sight between sensor origin end endpoint does not contain any obstacles.
  • To efficiently determine the map cells which need to be updated, a ray-casting operation is performed that determines voxels along a beam from the sensor origin to the measured endpoint.
Conclusion
  • The authors presented OctoMap, an open source framework for three-dimensional mapping.
  • The authors' approach uses an efficient data structure based on octrees that enables a compact memory representation and multi-resolution map queries.
  • The authors' approach is able to represent volumetric 3D models that include free and unknown areas.
  • The authors evaluated the approach with various realworld data sets.
  • The results demonstrate that the approach is able to model the environment in an accurate way and, at the same time, minimizes memory requirements
Tables
  • Table1: Map accuracy and cross-validation as percentage of correctly mapped cells between evaluated 3D scans and the built map. For the accuracy, we used all scans for map construction and evaluation. For cross-validation, we used 80 % of all scans to build the map, and the remaining 20 % for evaluation
  • Table2: Memory consumption of different octree compression types compared to full 3D occupancy maps (called 3D grid) on a 32-bit architecture. Octree compression in memory is achieved by merging identical children into the parent node (called Pruned). A more efficient but more lossy compression in memory is achieved by converting each node to its maximum-likelihood value (completely free or occupied) followed by pruning the complete tree. A maximum-likelihood tree containing only free and occupied nodes can then be serialized to a compact binary file format (called Lossy file)
Download tables as Excel
Related work
  • Three-dimensional models of the environment are a key prerequisite for many robotic systems and consequently they have been the subject of research for more than two decades.

    A popular approach to modeling environments in 3D is to use a grid of cubic volumes of equal size, called voxels, to discretize the mapped area. Roth-Tabak and Jain (1989)

    as well as Moravec (1996) presented early works using such a representation. A major drawback of rigid grids is their large memory requirement. The grid map needs to be initialized so that it is at least as big as the bounding box of the mapped area, regardless of the actual distribution of map cells in the volume. In large-scale outdoor scenarios or when there is the need for fine resolutions, memory consumption can become prohibitive. Furthermore, the extent of the mapped area needs to be known beforehand or costly copy operations need to be performed every time the map area is expanded.
Funding
  • This work has been supported by the German Research Foundation (DFG) under contract number SFB/TR-8 and by the European Commission under grant agreement numbers FP7-248258-First-MM and FP7-600890-ROVINA
Reference
  • Amanatides, J., & Woo, A. (1987). A fast voxel traversal algorithm for ray tracing. In Proceedings of Eurographics, Amsterdam, The Netherlands.
    Google ScholarLocate open access versionFindings
  • Blodow, N., Goron, L., Marton, Z., Pangercic, D., Ruhr, T., Tenorth, M., & Beetz, M. (2011). Autonomous semantic mapping for robots performing everyday manipulation tasks in kitchen environments. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Botsch, M., Wiratanaya, A., & Kobbelt, L. (2002). Efficient high quality rendering of point sampled geometry. In EGRW ’02 Proceedings of the 13th Eurographics workshop on Rendering, Aire-la-Ville, Switzerland, pp. 53–64.
    Google ScholarLocate open access versionFindings
  • Ciocarlie, M., Hsiao, K., Jones, E. G., Chitta, S., Rusu, R. B., & Sucan, I. A. (2010). Towards reliable grasping and manipulation in household environments. In International Symposium on Experimental Robotics (ISER), Delhi.
    Google ScholarLocate open access versionFindings
  • Cole, D., & Newman, P. (2006). Using laser range data for 3D SLAM in outdoor environments. In Proceedings of International Conference on Robotics & Automation (ICRA), Orlando.
    Google ScholarLocate open access versionFindings
  • Dornhege, C., & Kleiner, A. (2011). A frontier-void-based approach for autonomous exploration in 3D. In IEEE International Symposium on Safety, Security and Rescue Robotics (SSRR), Rio de Janeiro. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Douillard, B., Underwood, J., Melkumyan, N., Singh, S., Vasudevan, S., & Brunner, C., et al. (2010). Hybrid elevation maps: 3D surface models for segmentation. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Taipei. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Dryanovski, I., Morris, W., & Xiao, J. (2010). Multi-volume occupancy grids: An efficient probabilistic 3D mapping model for micro aerial vehicles. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Nice. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Einhorn, E., Schröter, C., & Groß, H. M. (2011). Attention-driven monocular scene reconstruction for obstacle detection, robot navigation and map building. Robotics & Autonomous Systems, 59(5), 296–309.
    Google ScholarLocate open access versionFindings
  • Elseberg, J., Borrmann, D., & Nüchter, A. (2011). Efficient processing of large 3d point clouds. In Proceedings of the XXIII International Symposium on Information, Communication and Automation Technologies (ICAT’11), Sarajevo.
    Google ScholarLocate open access versionFindings
  • Endres, F., Hess, J., Engelhard, N., Sturm, J., Cremers, D., & Burgard, W. (2012). An evaluation of the RGB-D SLAM system. In Proceedings of the IEEE International Conference on Robotics & Automation (ICRA), Guangzhou. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Fairfield, N., Kantor, G., & Wettergreen, D. (2007). Real-time SLAM with octree evidence grids for exploration in underwater tunnels. Journal of Field Robotics, 24, 3–21.
    Google ScholarLocate open access versionFindings
  • Fournier, J., Ricard, B., & Laurendeau, D. (2007). Mapping and exploration of complex environments using persistent 3D model. In Fourth Canadian Conference on Computer and Robot Vision, Montreal, pp. 403–410.
    Google ScholarLocate open access versionFindings
  • Girardeau-Montaut, D., Roux, M., Marc, R., & Thibault, G. (2005). Change detection on points cloud data acquired with a ground laser scanner. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 36, 30–35.
    Google ScholarLocate open access versionFindings
  • Gutmann, J. S., Fukuchi, M., & Fujita, M. (2008). 3D perception and environment map generation for humanoid robot navigation. International Journal of Robotics Research, 27(10), 1117–1134.
    Google ScholarLocate open access versionFindings
  • Habbecke, M., & Kobbelt, L. (2007). A surface-growing approach to multi-view stereo reconstruction. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Hadsell, R., Bagnell, J. A., & Hebert, M. (2009). Accurate rough terrain estimation with space-carving kernels. In Proceedings of Robotics: Science and Systems (RSS), Zaragoza.
    Google ScholarLocate open access versionFindings
  • Hebert, M., Caillas, C., Krotkov, E., Kweon, I. S., & Kanade, T. (1989). Terrain mapping for a roving planetary explorer. In Proceedings of the IEEE International Conference on Robotics & Automation (ICRA), Scottsdale. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Heng, L., Meier, L., Tanskanen, P., Fraundorfer, F., & Pollefeys, M. (2011). Autonomous obstacle avoidance and maneuvering on a vision-guided MAV using on-board processing. In Proceedings of the IEEE International Conference on Robotics & Automation (ICRA), Shanghai. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Hertzberg, C., Wagner, R., Birbach, O., Hammer, T., & Frese, U. (2011). Experiences in building a visual slam system from open source components. In Proceedings of the IEEE International Conference on Robotics & Automation (ICRA), Shanghai. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Hoppe, H., DeRose, T., Duchamp, T., Mcdonald, J., & Stuetzle, W. (1992). Surface reconstruction from unorganized points. SIGGRAPH Computer Graphics, 26(2), 71–78.
    Google ScholarLocate open access versionFindings
  • Hornung, A., Wurm, K. M., & Bennewitz, M. (2010). Humanoid robot localization in complex indoor environments. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Anchorage. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Hornung, A., Phillips, M., Jones, E. G., Bennewitz, M., Likhachev, M., & Chitta, S. (2012). Navigation in three-dimensional cluttered environments for mobile manipulation. In Proceedings of the IEEE International Conference on Robotics & Automation (ICRA), Minneapolis. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Kammerl, J., Blodow, N., Rusu, R. B., Gedikli, S., Beetz, M., & Steinbach, E. G. (2012). Real-time compression of point cloud streams. In Proceedings of the IEEE International Conference on Robotics & Automation (ICRA), Minneapolis. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Kelly, A., Stentz, A., Amidi, O., Bode, M., Bradley, D. M., Diaz-Calderon, A., et al. (2006). Toward reliable off road autonomous vehicles operating in challenging environments. Journal of Robotics Research, 25(5–6), 449–483.
    Google ScholarLocate open access versionFindings
  • Kraetzschmar, G., Gassull, G., & Uhl, K. (2004). Probabilistic quadtrees for variable-resolution mapping of large environments. In M. I. Ribeiro & S. J. Victor (Eds.), Proceedings of the 5th IFAC/EURON Symposium on Intelligent Autonomous Vehicles, Lisbon, Portugal.
    Google ScholarLocate open access versionFindings
  • Krainin, M., Henry, P., Ren, X., & Fox, D. (2011). Manipulator and object tracking for in-hand 3d object modeling. Journal of Robotics Research, 30(11), 1311–1327.
    Google ScholarLocate open access versionFindings
  • Laine, S., & Karras, T. (2010). Efficient sparse voxel octrees. In ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, Washington, DC.
    Google ScholarLocate open access versionFindings
  • Magnusson, M., Duckett, T., & Lilienthal, A. J. (2007). Scan registration for autonomous mining vehicles using 3D-NDT. Journal of Field Robotics, 24(10), 803–827.
    Google ScholarLocate open access versionFindings
  • Maier, D., Hornung, A., & Bennewitz, M. (2012). Real-time navigation in 3d environments based on depth camera data. In Proceedings of the IEEE-RAS International Conference on Humanoid Robots (Humanoids), Osaka. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Mason, J., Ricco, S., & Parr, R. (2011). Textured occupancy grids for monocular localization without features. In Proceedings of the IEEE International Conference on Robotics & Automation (ICRA), Shanghai. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Meagher, D. (1982). Geometric modeling using octree encoding. Computer Graphics and Image Processing, 19(2), 129–147.
    Google ScholarLocate open access versionFindings
  • Moravec, H. (1996). Robot spatial perception by stereoscopic vision and 3D evidence grids. Technical report CMU-RI-TR-96-34. Pittsburgh: Robotics Institute.
    Google ScholarFindings
  • Moravec, H., & Elfes, A. (1985). High resolution maps from wide angle sonar. In Proceedings of the IEEE International Conference on Robotics & Automation (ICRA) (pp. 116–121), St. Louis. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Müller, J., Kohler, N., & Burgard, W. (2011). Autonomous miniature blimp navigation with online motion planning and re-planning. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Nice. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Newcombe, R., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., & Davison, A., et al. (2011). KinectFusion: Real-time dense surface mapping and tracking. In 10th IEEE International Symposium on Mixed and Augmented Reality (ISMAR) (pp. 127–136). New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Nüchter, A., Lingemann, K., Hertzberg, J., & Surmann, H. (2007). 6D SLAM-3D mapping outdoor environments: Research articles. Journal of Field Robotics, 24(8–9), 699–722.
    Google ScholarLocate open access versionFindings
  • Oßwald, S., Hornung, A., & Bennewitz, M. (2012). Improved proposals for highly accurate localization using range and vision data. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vilamoura. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Pathak, K., Birk, A., Poppinga, J., & Schwertfeger, S. (2007). 3D forward sensor modeling and application to occupancy grid based sensor fusion. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), San Diego. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Payeur, P., Hebert, P., Laurendeau, D., & Gosselin, C. (1997). Probabilistic octree modeling of a 3-d dynamic environment. In Proceedings of the IEEE International Conference on Robotics & Automation (ICRA), Albuquerque. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Pfaff, P., Triebel, R., Stachniss, C., Lamon, P., Burgard, W., & Siegwart, R. (2007). Towards mapping of cities. In Proceedings of the IEEE International Conference on Robotics & Automation (ICRA), Rome, Italy. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Roth-Tabak, Y., & Jain, R. (1989). Building an environment model using depth information. Computer, 22(6), 85–90.
    Google ScholarLocate open access versionFindings
  • Ryde, J., & Hu, H. (2010). 3D mapping with multi-resolution occupied voxel lists. Autonomous Robots, 28(2), 169–185.
    Google ScholarLocate open access versionFindings
  • Schnabel, R., & Klein, R. (2006). Octree-based point-cloud compression. In Symposium on Point-Based Graphics 2006, Boston.
    Google ScholarLocate open access versionFindings
  • Shade, R., & Newman, P. (2011). Choosing where to go: Complete 3D exploration with stereo. In Proceedings of the IEEE International Conference on Robotics & Automation (ICRA), New Orleans. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Sibley, G., Mei, C., Reid, I., & Newman, P. (2009). Adaptive relative bundle adjustment. In Proceedings of Robotics Science and Systems (RSS), Seattle.
    Google ScholarLocate open access versionFindings
  • Smith, M., Baldwin, I., Churchill, W., Paul, R., & Newman, P. (2009). The new college vision and laser data set. International Journal for Robotics Research (IJRR), 28(5):595–599. http://dx.doi.org/10.1177/0278364909103911.
    Locate open access versionFindings
  • Stoyanov, T., Magnusson, M., Andreasson, H., & Lilienthal, A. J. (2010). Path planning in 3d environments using the normal distributions transform. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Taipei. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Sturm, J., Engelhard, N., Endres, F., Burgard, W., & Cremers, D. (2012). A benchmark for the evaluation of RGB-D slam systems. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). New York: IEEE Press. http://cvpr.in.tum.de/data/datasets/rgbd-dataset/download.
    Locate open access versionFindings
  • Surmann, H., Nüchter, A., & Hertzberg, J. (2003). An autonomous mobile robot with a 3d laser range finder for 3d exploration and digitalization of indoor environments. Robotics and Autonomous Systems, 45(3), 181–198.
    Google ScholarLocate open access versionFindings
  • Triebel, R., Pfaff, P., & Burgard, W. (2006). Multi-level surface maps for outdoor terrain mapping and loop closing. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Beijing. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Weise, T., Wismer, T., Leibe, B., & Van Gool, L. (2009). In-hand scanning with online loop closure. In ICCV Workshops, Kyoto.
    Google ScholarLocate open access versionFindings
  • Whelan, T., Kaess, M., Fallon, M., Johannsson, H., Leonard, J., & McDonald, J. (2012). Kintinuous: Spatially extended KinectFusion. Technical report. http://hdl.handle.net/1721.1/71756.
    Findings
  • Wilhelms, J., & Van Gelder, A. (1992). Octrees for faster isosurface generation. ACM Transactions on Graphics, 11(3), 201–227.
    Google ScholarLocate open access versionFindings
  • Wurm, K. M., Hornung, A., Bennewitz, M., Stachniss, C., & Burgard, W. (2010). 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 (IROS), Anchorage.
    Google ScholarLocate open access versionFindings
  • Wurm, K. M., Hennes, D., Holz, D., Rusu, R. B., Stachniss, C., Konolige, K., & Burgard, W. (2011). Hierarchies of octrees for efficient 3d mapping. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), San Francisco, CA, USA. New York: IEEE Press.
    Google ScholarLocate open access versionFindings
  • Yguel, M., Aycard, O., & Laugier, C. (2007a). Update policy of dense maps: Efficient algorithms and sparse representation. In Results of the International Conference Field and Service Robotics, FSR 2007, Chamonix, Vol. 42, pp. 23–33.
    Google ScholarLocate open access versionFindings
  • Yguel, M., Keat, C. T. M., Braillon, C., Laugier, C., & Aycard, O. (2007b). Dense mapping for range sensors: Efficient algorithms and sparse representations. In Proceedings of Robotics: Science and Systems. Cambridge: MIT Press.
    Google ScholarLocate open access versionFindings
  • Armin Hornung is a research scientist and PhD student in the Humanoid Robots Laboratory at the University of Freiburg. In 2009, he received his Diplom (Master’s) degree in computer science with specialization in artificial intelligence and robotics from University of Freiburg, Germany. His main research focus lies in humanoid robot navigation in complex indoor environments.
    Google ScholarFindings
  • Kai M. Wurm is an engineer at Siemens Corporate Technology. From 2007 to 2012 he worked as a research scientist at the University of Freiburg (Germany). He studied computer science at the University of Freiburg and received his diploma degree in 2007. His research interests lie in the fields of multi-robot coordination, terrain classification, SLAM, and 3D mapping.
    Google ScholarFindings
  • Maren Bennewitz is an assistant professor for Computer Science at the University of Freiburg Germany. She got her Ph.D. in Computer Science from the University of Freiburg in 2004. From 2004 to 2007, she was a Postdoc in the humanoid robots laboratory at the University of Freiburg which she heads since 2008. The focus of her research lies on robots acting in human environments. In the last few years, she has been developing novel solutions for intuitive human-robot interaction and navigation of robots in complex indoor environments.
    Google ScholarFindings
  • Cyrill Stachniss studied computer science at the University of Freiburg and received his Ph.D. degree in 2006. After his Ph.D., he was a senior researcher at ETH Zurich. From 2007 on, he was an academic advisor at the University of Freiburg in the Laboratory for Autonomous Intelligent Systems and also served as a guest lecturer at the University of Zaragoza in 2009. He received his habilitation in 2009 and is currently a lecturer at the University of Freiburg. Since 2008, he is an associate editor of the IEEE Transactions on Robotics and since 2010 a Microsoft Research Faculty Fellow. His research interests lie in the areas of robot navigation, exploration, SLAM, as well as robot learning approaches.
    Google ScholarLocate open access versionFindings
  • Wolfram Burgard is a professor for computer science at the University of Freiburg, Germany, where he heads the Laboratory for Autonomous Intelligent Systems. He studied Computer Science at the University of Dortmund and received his Ph.D. degree in computer science from the University of Bonn in 1991. His areas of interest lie in artificial intelligence and mobile robots. In the past, Wolfram Burgard and his group developed several innovative probabilistic techniques for robot navigation and control. They cover different aspects including localization, map-building, path planning, and exploration. For his work, Wolfram Burgard received several best paper awards from outstanding national and international conferences. In 2009, Wolfram Burgard received the Gottfried Wilhelm Leibniz Prize, the most prestigious German research award. In 2010, he received an Advanced Grant of the European Research Council. Wolfram Burgard is Fellow of AAAI and ECCAI.
    Google ScholarLocate open access versionFindings
Your rating :
0

 

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科