A Mini-map Alignment Approach using Landmark Observation Information Intrinsic to the Feature-based Visual SLAM Pipeline

Felipe Pires Saraiva; Gustavo Teodoro Laureano; Thiago Henrique de Oliveira

doi:10.22456/2175-2745.143437

Authors

Felipe Pires Saraiva Universidade Federal de Goiás (UFG) https://orcid.org/0009-0007-3819-4479
Gustavo Teodoro Laureano Universidade Federal de Goiás (UFG) https://orcid.org/0000-0003-1475-4818
Thiago Henrique de Oliveira Universidade Federal de Goiás (UFG)

DOI:

https://doi.org/10.22456/2175-2745.143437

Keywords:

Map alignment, ICP, Visual SLAM

Abstract

This work proposes a map alignment approach based on a simple modification of the Iterative Closest Point algorithm to use point confidences based on metrics usually available in feature-based visual SLAM pipelines. In the context of a hierarchical map composed of mini-maps, aligning these mini-maps is an important task to allow metric information to be related between them. This research enumerates three possible SLAM metrics that could be used for representing landmark confidence, and investigate the potential of using these metrics to improve the ICP algorithm. The experiments show evidence that the usage of the confidence metrics might help to improve the convergence of ICP with only a small modification to the data association step.

Downloads

Download data is not yet available.

References

YOUSIF, K.; BAB-HADIASHAR, A.; HOSEINNEZHAD, R. An Overview to Visual Odometry and Visual SLAM: Applications to Mobile Robotics. Intelligent Industrial Systems, v. 1, n. 4, p. 289–311, dez. 2015. ISSN 2363-6912, 2199-854X. Disponível em: ⟨http://link.springer.com/10.1007/s40903-015-0032-7⟩.

SCHLEICHER, D. et al. Real-time hierarchical stereo Visual SLAM in large-scale environments. Robotics and Autonomous Systems, v. 58, n. 8, p. 991–1002, ago. 2010. ISSN 0921-8890. Disponível em: ⟨https://linkinghub.elsevier.com/retrieve/pii/S0921889010000849⟩.

BALLESTA, M. et al. Multi-robot map alignment in visual SLAM. WSEAS TRANSACTIONS on SYSTEMS, v. 9, p. 213–222, fev. 2010.

BESL, P.; MCKAY, N. D. A method for registration of 3-D shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, v. 14, n. 2, p. 239–256, fev. 1992. ISSN 0162-8828, 2160-9292. Disponível em: ⟨http://ieeexplore.ieee.org/document/121791/⟩.

POMERLEAU, F.; COLAS, F.; SIEGWART, R. A Review of Point Cloud Registration Algorithms for Mobile Robotics. Foundations and Trends® in Robotics, v. 4, n. 1, p. 1–104, 2015. ISSN 1935-8253, 1935-8261. Disponível em: ⟨http://www.nowpublishers.com/article/Details/ROB-035⟩.

AZZAM, R. et al. Feature-based visual simultaneous localization and mapping: a survey. SN Applied Sciences, v. 2, n. 2, p. 224, fev. 2020. ISSN 2523-3963, 2523-3971. Disponível em: ⟨http://link.springer.com/10.1007/s42452-020-2001-3⟩.

GAO, X.; ZHANG, T. Introduction to Visual SLAM: From Theory to Practice. Singapore: Springer Singapore, 2021. ISBN 9789811649387, 9789811649394. Disponível em: ⟨https://link.springer.com/10.1007/978-981-16-4939-4⟩.

RUSINKIEWICZ, S.; LEVOY, M. Efficient variants of the ICP algorithm. In: Proceedings Third International Conference on 3-D Digital Imaging and Modeling. Quebec City, Que., Canada: IEEE Comput. Soc, 2001. p. 145–152. ISBN 978-0-7695-0984-6. Disponível em: ⟨http://ieeexplore.ieee.org/document/924423/⟩.

BOSSE, M. et al. An Atlas framework for scalable mapping. In: 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422). Taipei, Taiwan: IEEE, 2003. p. 1899–1906. ISBN 978-0-7803-7736-3. Disponível em: ⟨http://ieeexplore.ieee.org/document/1241872/⟩.

JI, Z. et al. Probabilistic 3D ICP algorithm based on ORB feature. In: 2013 IEEE Third International Conference on Information Science and Technology (ICIST). Yangzhou, Jiangsu, China: IEEE, 2013. p. 282–282. ISBN 978-1-4673-2764-0, 978-1-4673-5137-9, 978-1-4673-2763-3. Disponível em: ⟨http://ieeexplore.ieee.org/document/6747555/⟩.

BAI, H. ICP Algorithm: Theory, Practice and Its SLAM-oriented Taxonomy. Applied and Computational Engineering, v. 2, n. 1, p. 10–21, mar. 2023. ISSN 2755-2721, 2755-273X. Disponível em: ⟨https://www.ewadirect.com/proceedings/ace/article/view/748⟩.

HUANG, X. et al. A comprehensive survey on point cloud registration. arXiv, 2021. Version Number: 2. Disponível em: ⟨https://arxiv.org/abs/2103.02690⟩.

THRUN, S.; BURGARD, W.; FOX, D. Probabilistic Robotics. Cambridge, Mass: MIT Press, 2005. (Intelligent Robotics and Autonomous Agents). OCLC: ocm58451645. ISBN 978-0-262-20162-9.

HARTLEY, R.; ZISSERMAN, A. Multiple View Geometry in Computer Vision. 2nd ed. Cambridge, UK: Cambridge University Press, 2004. OCLC: 171123855. ISBN 978-0-511-18711-7.

RUSU, R. B.; COUSINS, S. 3D is here: Point Cloud Library (PCL). In: 2011 IEEE International Conference on Robotics and Automation. Shanghai, China: IEEE, 2011. p. 1–4. ISBN 978-1-61284-386-5, 978-1-61284-385-8. Disponível em: ⟨https://ieeexplore.ieee.org/document/5980567/⟩.

MUR-ARTAL, R.; TARDOS, J. D. ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras. IEEE Transactions on Robotics, v. 33, n. 5, p. 1255–1262, out. 2017. ISSN 1552-3098, 1941-0468. Disponível em: ⟨http://ieeexplore.ieee.org/document/7946260/⟩.

STURM, J. et al. A benchmark for the evaluation of RGB-D SLAM systems. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems. Vilamoura-Algarve, Portugal: IEEE, 2012. p. 573–580. ISBN 978-1-4673-1736-8, 978-1-4673-1737-5, 978-1-4673-1735-1. TUM RGB-D: https://cvg.cit.tum.de/data/datasets/rgbd-dataset. Disponível em: ⟨http://ieeexplore.ieee.org/document/6385773/⟩.