Feature-Based Occupancy Map-Merging for Collaborative SLAM
Abstract
:1. Introduction
- Processing the spatial occupancy probabilities and detecting features based on locally adaptive nonlinear diffusion filtering.
- Developing a procedure to verify and accept the correct transformation to avoid ambiguous map merging.
- Proposing a global grid fusion strategy based on the Bayesian inference, which is independent of the order of merging.
2. Related Literature
- Feature (keypoint) Detection: during this stage, the map image is searched for locally distinctive locations that are likely to match with other images.
- Feature Description: the region around each detected feature is converted into a compact and stable descriptor that can be used to match against other descriptors.
- Feature Matching: finally, at this stage, we efficiently search for likely matching candidates between two set of descriptors to establish the pair wise correspondence.
3. Problem Formulation
4. Proposed Method
4.1. Processing Occupancy Maps
4.2. Feature Detection
4.2.1. Nonlinear Diffusion Filtering
4.2.2. KAZE Features
4.3. Feature Description
4.4. Feature Matching
4.5. Keypoint Detectability
4.6. Outlier Elimination
Algorithm 1, Ntrails) |
inliers ⇐ 0 T ⇐ 0 n ⇐ 0 while n < Ntrails do S ⇐ Randomly select subset of samples with minimum number of correspondences Th ⇐ Hypothesize transformation for the minimal set Inliersh ⇐ Test for number of consistent matches with Th if inliersh > inliers then inliers ⇐ inliers then T ⇐ Th end if end while |
4.7. Grid Fusion
4.7.1. Transformation Verification
- Although only two valid feature correspondences are sufficient to estimate the transformation, it is highly unlikely that the correspondences are true positives. Hence, only the transformation for minimum inlier cardinality (well-over two feature correspondences) is accepted.
- Further, we use the acceptance index based on pairwise cell agreement and disagreement between the map matrix and the transformed map matrix to check the quality of the transformation. The acceptance index is defined as:
4.7.2. Certainty Grid Fusion
4.7.3. Transformation Reliability
5. Collaborative Mapping
Algorithm 2) |
Process the maps to obtain occupancy images , [;] = process Occupancy Maps (;) Detect KAZE keypoints , [;] = detect KAZE features (;) Describe the detected features using the SIFT descriptor. [;] = SIFT description (;;;) Find the nearest-neighbors. = feature Matching (;) Compute the transformation T using the MSAC algorithm. [T] = outlier Elimination () Verify the transformation, and update the global map based on grid. fusion methodology [] = grid Fusion (;;T) |
5.1. Hierarchical Map Fusion
5.2. Motion Planning
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
DHT | Discretized hough transform |
FAST | features from accelerated segment test |
GPS | global positioning system |
ICP | iterative closest point |
KLT | Kanade-Lucas-Tomasi |
MSAC | mean sample consensus |
ORB | oriented FAST and rotated |
PDE | partial differential equations |
RANSAC | random sample consensus |
ROS | robot operating system |
SLAM | simultaneous localization and mapping |
STrICP | scaling trimmed iterative closet point |
SURF | speeded-up robust features |
TrICP | trimmed iterative closest point |
References
- Yu, S.; Fu, C.; Gostar, A.K.; Hu, M. A review on map-merging methods for typical map types in multiple-ground-robot SLAM solutions. Sensors 2020, 20, 6988. [Google Scholar] [CrossRef]
- Sunil, S. Heterogeneous Collaborative Mapping for Autonomous Mobile Systems. Master’s Thesis, University of Windsor, Windsor, ON, Canada, 2022. [Google Scholar]
- Catal, O.; Verbelen, T.; Wang, N.; Hartmann, M.; Dhoedt, B. Bio-inspired monocular drone SLAM. In Proceedings of the Conference on System Engineering for Constrained Embedded Systems, Budapest, Hungary, 17–19 January 2022; pp. 21–26. [Google Scholar]
- Talebpour, F.; Mozaffari, S.; Saif, M.; Alirezaee, S. Multi-Modal Signal Analysis for Underwater Acoustic Sound Processing. In Proceedings of the IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), Halifax, NS, Canada, 18–20 September 2022; pp. 300–305. [Google Scholar]
- Shao, J.; Zhang, W.; Mellado, N.; Wang, N.; Jin, S.; Cai, S.; Yan, G. SLAM aided forest plot mapping combining terrestrial and mobile laser scanning. ISPRS J. Photogramm. Remote Sens. 2020, 163, 214–230. [Google Scholar] [CrossRef]
- Ge, G.; Zhang, Y.; Wang, W.; Wang, Q. Medical Mobile Robot Localization in Hospital Corridor Environment Using Laser SLAM and Text Features. J. Imaging Sci. Technol. 2022, 8, 12–14. [Google Scholar] [CrossRef]
- Saeedi, S.; Trentini, M.; Seto, M.; Li, H. Multiple-robot simultaneous localization and mapping: A review. J. Field Robot. 2016, 33, 3–46. [Google Scholar] [CrossRef]
- Macario, B.A.; Michel, M.; Moline, Y.; Corre, G.; Carrel, F. A comprehensive survey of visual slam algorithms. Robotics 2022, 11, 24. [Google Scholar] [CrossRef]
- Lee, H.-C.; Lee, S.-H.; Choi, M.H.; Lee, B.-H. Probabilistic map merging for multi-robot RBPF-SLAM with unknown initial poses. Robotica 2012, 30, 205–220. [Google Scholar] [CrossRef]
- Blanco, J.-L.; Gonzalez-Jimenez, J.; Fernandez-Madrigal, J.-A. A robust, multi-hypothesis approach to matching occupancy grid maps. Robotica 2013, 31, 687–701. [Google Scholar] [CrossRef] [Green Version]
- Thrun, S. A probabilistic on-line mapping algorithm for teams of mobile robots. Int. J. Robot. Res. 2001, 20, 335–363. [Google Scholar] [CrossRef]
- Carlone, L.; Ng, M.K.; Du, J.; Bona, B.; Indri, M. Rao-Blackwellized Particle Filters Multi Robot SLAM with Unknown Initial Correspondences and Limited Communication. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Anchorage, AK, USA, 3–8 May 2010; pp. 243–249. [Google Scholar]
- Zhou, X.S.; Roumeliotis, S.I. Multi-robot SLAM with unknown initial correspondence: The robot rendezvous case. In Proceedings of the IEEE/RSJ. International Conference on Intelligent Robots and Systems, Beijing, China, 9–13 October 2006; pp. 1785–1792. [Google Scholar]
- Kwon, J.-W. Cooperative Environment Scans Based on a Multi-Robot System. Sensors 2015, 15, 6483–6496. [Google Scholar] [CrossRef] [Green Version]
- Zhi, W.; Ott, L.; Senanayake, R.; Ramos, F. Continuous occupancy map fusion with fast Bayesian hilbert maps. In Proceedings of the International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada, 20–24 May 2019; pp. 4111–4117. [Google Scholar]
- Williams, S.B.; Dissanayake, G.; Durrant-Whyte, H. Towards multi-vehicle simultaneous localisation and mapping. In Proceedings of the 2002 IEEE International Conference on Robotics and Automation, Washington, DC, USA, 11–15 May 2002; pp. 2743–2748. [Google Scholar]
- Li, H.; Tsukada, M.; Nashashibi, F.; Parent, M. Multivehicle Cooperative Local Mapping: A Methodology Based on Occupancy Grid Map Merging. IEEE Trans. Intell. Transp. Syst. 2014, 15, 2089–2100. [Google Scholar] [CrossRef] [Green Version]
- Chen, H.; Huang, H.; Qin, Y.; Li, Y.; Liu, Y. Vision and laser fused SLAM in indoor environments with multi-robot system. Assem. Autom. 2019, 39, 297–307. [Google Scholar] [CrossRef]
- Deutsch, I.; Liu, M.; Siegwart, R. A Framework for Multi-Robot Pose Graph SLAM. In Proceedings of the IEEE International Conference on Real-Time Computing and Robotics (IEEE RCAR), Angkor Wat, Cambodia, 6–10 June 2016; IEEE: New York, NY, USA, 2016; pp. 567–572. [Google Scholar]
- Bosse, M.; Zlot, R. Map matching and data association for large-scale two-dimensional laser scan-based SLAM. Int. J. Robot. Res. 2008, 27, 667–691. [Google Scholar] [CrossRef]
- Schwertfeger, S.; Birk, A. Evaluation of Map Quality by Matching and Scoring High-Level, Topological Map Structures. In Proceedings of the 2013 IEEE International Conference on Robotics and Automation, Karlsruhe, Germany, 6–10 May 2013; pp. 2221–2226. [Google Scholar]
- Mielle, M.; Magnusson, M.; Lilienthal, A.J. Using sketch-maps for robot navigation: Interpretation and matching. In Proceedings of the 14th IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), Lausanne, Switzerland, 23–27 October 2016; Melo, K., Ed.; IEEE: New York, NY, USA, 2016; pp. 252–257. [Google Scholar]
- Kakuma, D.; Tsuichihara, S.; Ricardez, G.A.G.; Takamatsu, J.; Ogasawara, T. Alignment of Occupancy Grid and Floor Maps using Graph Matching. In Proceedings of the 11th IEEE International Conference on Semantic Computing (ICSC), San Diego, CA, USA, 30 January–1 February 2017; pp. 57–60. [Google Scholar]
- Blanco, J.L.; Gonzalez, J.; Fernandez Madrigal, J.A. A new method for robust and efficient occupancy grid-map matching. In Proceedings of the Iberian Conference on Pattern Recognition and Image Analysis, Girona, Spain, 6–8 June 2007; Springer: Berlin/Heidelberg, Germany; pp. 194–201. [Google Scholar]
- Carpin, S. Fast and accurate map merging for multi-robot systems. Auton. Robots 2008, 25, 305–316. [Google Scholar] [CrossRef]
- Ma, L.; Zhu, J.; Zhu, L.; Du, S.; Cui, J. Merging grid maps of different resolutions by scaling registration. Robotica 2016, 34, 2516–2531. [Google Scholar] [CrossRef]
- Konolige, K.; Fox, D.; Limketkai, B.; Ko, J.; Stewart, B. Map merging for distributed robot navigation. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003), Las Vegas, NY, USA, 27–31 October 2003; pp. 212–217. [Google Scholar]
- Forsyth, D.; Ponce, J. Computer Vision: A Modern Approach; Prentice Hall: Hoboken, NJ, USA, 2011; p. 792. [Google Scholar]
- Fischler, M.A.; Bolles, R.C. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 1981, 24, 381–395. [Google Scholar] [CrossRef]
- Lowe, D.G. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 2004, 60, 91–110. [Google Scholar] [CrossRef]
- Bay, H.; Tuytelaars, T.; Van Gool, L. Surf: Speeded up robust features. In Proceedings of the European Conference on Computer Vision, Graz, Austria, 7–13 May 2006; Springer: Berlin/Heidelberg, Germany, 2006; pp. 404–417. [Google Scholar]
- Shi, J. Good features to track. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 21–23 June 1994; pp. 593–600. [Google Scholar]
- Horner, J. Map-Merging for Multi-Robot System. Bachelor’s Thesis, Charles University, Prague, Czech Republic, 25 August 2016. [Google Scholar]
- Lin, Z.; Zhu, J.; Jiang, Z.; Li, Y.; Li, Y.; Li, Z. Merging Grid Maps in Diverse Resolutions by the Context-based Descriptor. ACM Trans. Internet Technol. 2021, 21, 1–21. [Google Scholar] [CrossRef]
- Jiang, Z.; Zhu, J.; Li, Y.; Wang, J.; Li, Z.; Lu, H. Simultaneous merging multiple grid maps using the robust motion averaging. J. Intell. Robot. Syst. 2019, 94, 655–668. [Google Scholar] [CrossRef] [Green Version]
- Hern’andez, C.A.V.; Ortiz, F.A.P. A real-time map merging strategy for robust collaborative reconstruction of unknown environments. Expert Syst. Appl. 2020, 145, 113109. [Google Scholar] [CrossRef]
- Alcantarilla, P.F.; Bartoli, A.; Davison, A.J. KAZE features. In Proceedings of the European Conference on Computer Vision, Florence, Italy, 12 October 2012; Springer: Berlin/Heidelberg, Germany, 2012; pp. 214–227. [Google Scholar]
- Tipaldi, G.D.; Arras, K.O. FLIRT-Interest Regions for 2D Range Data. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Anchorage, AK, USA, 3–8 May 2010; pp. 1–7. [Google Scholar]
- Heigele, C.; Mielenz, H.; Heckel, J.; Schramm, D. Accurate and fast localization in unstructured environment based on shape context keypoints. In Proceedings of the 17th International Conference on Information Fusion (FUSION), Salamanca, Spain, 7–10 July 2014; pp. 1–7. [Google Scholar]
- Tian, Y.; Song, W.; Sun, S.; Fong, S.; Zou, S. 3D object recognition method with multiple feature extraction from LiDAR point clouds. J. Supercomput. 2019, 75, 4430–4442. [Google Scholar] [CrossRef]
- Calonder, M.; Lepetit, V.; Strecha, C.; Fua, P. Brief: Binary robust independent elementary features. In Proceedings of the Computer Vision–ECCV: 11th European Conference on Computer Vision, Heraklion, Greece, 5–11 September 2010; pp. 778–792. [Google Scholar]
- Perona, P.; Malik, J. Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 1990, 12, 629–639. [Google Scholar] [CrossRef] [Green Version]
- Tsardoulias, E.G.; Protopapas, M.; Symeonidis, A.L.; Petrou, L. A Comparative Analysis of Pattern Matching Techniques towards OGM Evaluation. J. Intell. Robot. Syst. 2020, 98, 733–758. [Google Scholar] [CrossRef]
- Torr, P.H.; Zisserman, A. MLESAC: A new robust estimator with application to estimating image geometry. Comput. Vis. Image Underst. 2000, 78, 138–156. [Google Scholar] [CrossRef] [Green Version]
- Bar-Shalom, Y.; Li, X.R.; Kirubarajan, T. Estimation with Applications to Tracking and Navigation: Theory Algorithms and Software; John Wiley & Sons: Hoboken, NJ, USA, 2004. [Google Scholar]
- Singandhupe, A.; La, H.M. A review of slam techniques and security in autonomous driving. In Proceedings of the 2019 Third IEEE International Conference on Robotic Computing (IRC), Naples, Italy, 25–27 February 2019; IEEE: New York, NY, USA, 2019; pp. 602–607. [Google Scholar]
(Cells/m) | (Cells/m) | Wall-Clock Time (sec) | |Inliers| | Rotation (deg.) | Ranslation (m) | |
---|---|---|---|---|---|---|
25 | 25 | 33 | ||||
20 | 20 | 35 | ||||
10 | 10 | 21 | ||||
25 | 20 | 28 | ||||
25 | 10 | 25 | ||||
20 | 10 | 22 |
MSAC Algorithm | RANSAC Algorithm | ||||||||
---|---|---|---|---|---|---|---|---|---|
(Cells/m) | (Cells/m) | Acceptance Index (ω) | |Inliers| | Rotation (deg.) | Translation (m) | Acceptance Index (ω) | |Inliers| | Rotation (deg.) | Translation (m) |
25 | 25 | 33 | 28 | ||||||
20 | 10 | 22 | 19 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Sunil, S.; Mozaffari, S.; Singh, R.; Shahrrava, B.; Alirezaee, S. Feature-Based Occupancy Map-Merging for Collaborative SLAM. Sensors 2023, 23, 3114. https://doi.org/10.3390/s23063114
Sunil S, Mozaffari S, Singh R, Shahrrava B, Alirezaee S. Feature-Based Occupancy Map-Merging for Collaborative SLAM. Sensors. 2023; 23(6):3114. https://doi.org/10.3390/s23063114
Chicago/Turabian StyleSunil, Sooraj, Saeed Mozaffari, Rajmeet Singh, Behnam Shahrrava, and Shahpour Alirezaee. 2023. "Feature-Based Occupancy Map-Merging for Collaborative SLAM" Sensors 23, no. 6: 3114. https://doi.org/10.3390/s23063114