On the application of RGB-D SLAM systems for practical localization of mobile robots

• Autorzy: Kostusiak A. , Nowicki M. , Skrzypczyński P.

Identyfikatory

DOI

10.14313/JAMRIS_2-2017/17

• Języki publikacji: EN

Abstrakty

EN

This paper considers the practical application of the RGBD Simultaneous Localization and Mapping (SLAM) techniques for localization of mobile robots. We attempt to answer the question: how the quality of the estimated sensor trajectory depends on the approach to RGB-D data processing in the SLAM system when RGB-D frames acquired on a real mobile robot are used. Experiments are performed on data obtained from robots of different classes, and from different environment types to present the problems characteristic to RGB-D data. Conclusions as to the robustness of particular architectures and solutions applied in SLAM are drawn on the basis of experimental results. Publicly available data sets and well-established performance metrics are used to ensure that the results are verifiable, reproducible and relevant

Słowa kluczowe

EN

SLAM; RGB-D; mobile robot; evaluation

• Wydawca: Łukasiewicz Industrial Research Institute for Automation and Measurements PIAP
• Czasopismo: Journal of Automation Mobile Robotics and Intelligent Systems
• Rocznik: 2017
• Tom: Vol. 11, No. 2
• Strony: 57--66
• Opis fizyczny: Bibliogr. 38 poz., rys.

Twórcy

autor

Kostusiak A.

• Poznań University of Technology, Institute of Control and Information Engineering, ul. Piotrowo 3A, 60-965 Poznań , Poland

autor

Nowicki M.

• Poznań University of Technology, Institute of Control and Information Engineering, ul. Piotrowo 3A, 60-965 Poznań , Poland

autor

Skrzypczyński P.

• Poznań University of Technology, Institute of Control and Information Engineering, ul. Piotrowo 3A, 60-965 Poznań , Poland

Bibliografia

• [1] S. Baker, I. Matthews, ”Lucas-Kanade 20 years on: A unifying framework”, Int. Journal of Computer Vision, vol. 56, no. 3, 221–255, 2004. DOI: 10.1023/B:VISI.0000011205.11775.fd.
• [2] H. Bay, A. Ess, T. Tuytelaars, L. Van Gool, ”Speeded-up robust features (SURF)”, Computer Vision and Image Understanding, vol. 110, no. 3, 2008, 346–359. DOI:10.1016/j.cviu.2007.09.014.
• [3] D. Belter, M. Nowicki, P. Skrzypczyński, ”On the performance of pose-based RGB-D visual navigation systems”, In: Computer Vision – ACCV 2014 (D. Cremers et al., eds.), LNCS 9004, Springer, 2015, 407–423. DOI: 10.1007/978-3-319-16808-1_28.
• [4] D. Belter, M. Nowicki, P. Skrzypczyń ski, ”Accurate map-based RGB-D SLAM for mobile robots”, In: Robot 2015: Advances in Robotics (L. P. Reis et al., eds.), AISC 418, Springer, 2015, 533–545. DOI: 10.1007/978-3-319-27149-1_41.
• [5] D. Belter, M. Nowicki, P. Skrzypczyń ski, ”Evaluating map-based RGB-D SLAM on an autonomous walking robot”, In: Challenges in Automation, Robotics and Measurement Techniques, (R. Szewczyk, et al., eds.), AISC 440, Springer, 2016, 469–481. DOI: 10.1007/978-3-319-29357-8_42.
• [6] D. Belter, M. Nowicki, P. Skrzypczyń ski, ”Improving accuracy of feature-based RGB-D SLAM by modeling spatial uncertainty of point features”. In: Proc. IEEE Int. Conf. on Robotics and Automation, Stockholm, 2016, 1279–1284. DOI: 10.1109/ICRA.2016.7487259.
• [7] P. Cƽı́žek, J. Faigl, ”On localization and mapping with RGB-D sensor and hexapod walking robot in rough terrains”. In: Proc. IEEE Int. Conf. on Systems, Man, and Cybernetics, Budapest, 2016, 2273–2278. DOI:: 10.1109/SMC.2016.7844577.
• [8] B. Curless, M. Levoy, ”A volumetric method for building complex models from range images “ Proc. 23rd Conf. on Computer Graphics and Interactive Techniques SIGGRAPH, New Orleans, 1996, 303–312. DOI:10.1145/237170.237269.
• [9] I. Dryanovski, R. Valenti, J. Xiao, ”Fast visual odometry and mapping from RGB-D data”. In: Proc. IEEE Int. Conf. on Robotics & Automation, Karlsruhe, 2013, 5704–5711. DOI: 10.1109/ICRA.2013.6630889.
• [10] D. W. Eggert, A. Lorusso, R. B. Fisher, ”Estimating 3-D rigid body transformations: a comparison of four major algorithms”. Machine Vision and Applications, vol. 9, no. 5–6, 272–290, 1997. DOI:10.1007/s001380050048.
• [11] F. Endres, J. Hess, J. Sturm, D. Cremers, W. Burgard, ”3-D mapping with an RGB-D camera, IEEE Trans. on Robotics, vol. 30. no. 1, 2014, 177–187.DOI: 10.1109/TRO.2013.2279412.
• [12] M. Fallon, H. Johannsson, M. Kaess, J. J. Leonard, ”The MIT Stata Center dataset”, Int. Journal of Robotics Research, vol. 32, no. 14, 2013, 1695–1699. DOI: 10.1177/0278364913509035.
• [13] G. Grisetti, R. Kümmerle, C. Stachniss, W. Burgard, ”A tutorial on graph-based SLAM”, IEEE Intelligent Transportation Systems Magazine, vol. 2, no. 4, 2010, 31–43. DOI: 10.1109/MITS.2010.939925.
• [14] A. Handa, T. Whelan, J. D. McDonald, A. J. Davison, ”A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM”, IEEE Int. Conf. on Robotics & Automation, Hong Kong, 2014, 1524–1531.DOI: 10.1109/ICRA.2014.6907054.
• [15] A. Hornung, K. O. Wurm, M. Bennewitz, C. Stachniss,W. Burgard, OctoMap: An efficient probabilistic 3D mapping framework based on octrees, Autonomous Robots, vol. 34, no. 3, 2013, 189–206. DOI: 10.1007/s10514-012-9321-0.
• [16] A. Kostusiak, ”The comparison of keypoint detectorsand descriptors for registration of RGBD data”, In: Challenges in Automation, Robotics and Measurement Techniques, (R. Szewczyk, et al., eds.), AISC 440, Springer, 2016, 609–622.DOI: 10.1007/978-3-319-29357-8_53.
• [17] A. Kostusiak, M. Nowicki, P. Skrzypczyński, ”On the use of RGB-D SLAM for mobile robots localization”,Zeszyty Naukowe Politechniki Warszawskiej, no. 195, Postȩpy robotyki, tom 2, 2016, 387–396 (in Polish).
• [18] M. Kraft, M. Nowicki, R. Penne, A. Schmidt, P. Skrzypczyński, ”Efficient RGB-D data processing for feature-based self-localization of mobile robots”,Int. Journal of Applied Mathematics and Computer Science, vol. 26, no. 1, 2016, 63–79.DOI: 10.1515/amcs-2016-0005.
• [19] M. Kraft, M. Nowicki, A. Schmidt, M. Fularz, P. Skrzypczyński, ”Toward evaluation of visual navigation algorithms on RGB-D data from the firstand second-generation Kinect”, Machine Vision and Applications, vol. 28, no. 1, 2017, 61–74. DOI:10.1007/s00138-016-0802-6.
• [20] R. Kümmerle, G. Grisetti, H. Strasdat, K. Konolige,W. Burgard, ”g2o: A general framework for graph optimization”, Proc. IEEE Int. Conf. on Robotics & Automation, Shanghai, 2011, 3607–3613. DOI:10.1109/ICRA.2011.5979949.
• [21] R. Maier, J. Sturm, D. Cremers, ”Submap-based bundle adjustment for 3D reconstruction from RGB-D data”, In: Pattern Recognition: GCPR 2014,(X. Jiang et al., eds.), LNCS 8753, Springer, 2014,54–65. DOI: 10.1007/978-3-319-11752-2_5.[22] R. Mur-Artal, J. M. M. Montiel, J. D. Tardós,”ORB-SLAM: A versatile and accurate monocular SLAM system”, IEEE Trans. on Robotics, vol. 31, no. 5, 2015, 1147–1163. DOI:10.1109/TRO.2015.2463671.
• [23] R. Mur-Artal, J. D. Tardós, ”ORB-SLAM2: An open-source SLAM system for monocular,stereo and RGB-D cameras, arXiv preprint,arXiv:1610.06475v1, 2016.
• [24] M. Nowicki, P. Skrzypczyński, ”Experimental verification of a walking robot self-localization system with the Kinect sensor”, Journal of Automation,Mobile Robotics & Intelligent Systems, vol.7, no. 4, 2013, 42–51. DOI: 10.14313/JAMRIS_4-2013/43.
• [25] Point Cloud Library, http://pointclouds.org/
• [26] E. Rublee, V. Rabaud, K. Konolige, G. Bradski,”ORB: an efficient alternative to SIFT or SURF”, IEEE Int. Conf. on Computer Vision, Barcelona, 2011, 2564–2571.DOI:10.1109/ICCV.2011.6126544.
• [27] D. Scaramuzza, F. Fraundorfer, ”Visual odometry: Part I the first 30 years and fundamentals”. IEEE Robotics & Automation Magazine, vol. 18, no. 4, 2011, 80–92. DOI: 10.1109/MRA.2011.943233.
• [28] A. Schmidt, M. Kraft, M. Fularz, Z. Domagala, ”‘Comparative assessment of point feature detectors and descriptors in the context of robot navigation”, Journal of Automation, Mobile Robotics & Intelligent Systems, vol. 7, no. 1, 2013, 11–20.
• [29] A. Schmidt, M. Kraft, M. Fularz, Z. Domagala, ”The registration system for the evaluation of indoor visual SLAM and odometry algorithms”, Journal of Automation, Mobile Robotics & Intelligent Systems, vol. 7, no. 2, 2013, 46–51.
• [30] A. Schmidt, A. Kasiński, M. Kraft, M. Fularz, Z. Domagala, ”Calibration of the multi-camera registration system for visual navigation benchmarking”, Int. Journal of Advanced Robotic Systems, vol. 11, no. 83, 2014. DOI: 10.5772/58471.
• [31] P. Skrzypczyński, ”Mobile robot localization: where we are and what are the challenges?”, In: Automation 2017. Innovation in Automation, Robotics and Measurement Techniques, (R. Szewczyk, et al., eds.), AISC 550, Springer, 2017. DOI:10.1007/978-3-319-54042-9.
• [32] F. Steinbrücker, J. Sturm, D. Cremers, ”‘Volumetric 3D mapping in real-time on a CPU”. In: Proc. IEEE Int. Conf. on Robotics & Automation,Hong Kong, 2014, 2021–2028. DOI: 10.1109/ICRA.2014.6907127.
• [33] H. Strasdat, J. M. M. Montiel, A. J. Davison,”Visual SLAM: Why filter?”, Image and Vision Computing, vol. 30, no. 2, 2012, 65–77. DOI:10.1016/j.imavis.2012.02.009.
• [34] H. Strasdat, Local accuracy and global consistency for efficient visual SLAM, PhD Dissertation, Imperial College, London, 2012.
• [35] J. Sturm, N. Engelhard, F. Endres, W. Burgard,D. Cremers, ”A benchmark for the evaluationof RGB-D SLAM systems”. In: Proc. IEEE/RSJ Int. Conf. on Intelligent Robots & Systems, Vilamoura, 2012, 573–580. DOI: 10.1109/IROS.2012.6385773.
• [36] B. Triggs, P. F. McLauchlan, R. I., Hartley, A. W.Fitzgibbon, ”‘Bundle adjustment – a modern synthesis”, In: Vision Algorithms: Theory and Practice, LNCS 1883, Springer, 2000, 298–372.DOI: 10.1007/3-540-44480-7_21.
• [37] T. Whelan, M. Kaess, H. Johannsson, M. Fallon, J. J. Leonard, J. B. McDonald, ”Real-time large-scale dense RGB-D SLAM with volumetric fusion”, Int. Journal of Robotics Research, vol. 34, no. 4–5, 2015, 598–626. DOI:10.1177/0278364914551008.
• [38] A. Wilkowski, T. Kornuta, M. Stefań czyk, W. Kasprzak, Efficient generation of 3D surfel maps using RGB-D sensors, Int. Journal of Applied Mathematics and Computer Science, vol. 26, no. 1, 2016, 99–122. DOI: 10.1515/amcs-2016-0007..

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017)