Cooperative visual SLAM system for vehicle based environmental perception
Abstract
For autonomous vehicles, accurate assessment of the environment and reliable localization are crucial. To do this, we present a cooperative visual SLAM system, where one vehicle creates a map with a monocular camera and calibrates this map to a global scale using GNSS reference coordinates. The second vehicle visually localizes itself using the created map interpreted in the global coordinate system. We used a self-generated dataset to evaluate the presented method. Based on the results, it can be concluded that the method increases the accuracy of localization and allows the reuse of maps between vehicles.
References
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., Leonard, J. J. (2016) Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age. IEEE Transactions on Robotics, 32(6), pp. 1309–1332. DOI: https://doi.org/10.1109/TRO.2016.2624754
Campos, C., Elvira, R., Gómez Rodríguez, J. J., Montiel, J. M. M., Tardós, J. D. (2021) ORB-SLAM3: An accurate open source library for visual, visual–inertial, and multimap SLAM. IEEE Transactions on Robotics, 37(6), 1874–1890. DOI: https://doi.org/10.1109/TRO.2021.3075644
Chen, X., Miao, Y., Wang, J., Li, Y. (2018) GVORB-SLAM: A GPS-aided visual SLAM system. ISPRS International Journal of Geo-Information, 7(11), 425. DOI: https://doi.org/10.36227/techrxiv.23898246
Geiger, A., Lenz, P., Stiller, C., Urtasun, R. (2012) Vision meets robotics: The KITTI dataset. International Journal of Robotics Research, 32(11), pp. 1231–1237. DOI: https://doi.org/10.1177/0278364913491297
Grupp, M. (2017) evo: Python package for the evaluation of odometry and SLAM [Computer software]. GitHub repository. URL: https://github.com/MichaelGrupp/evo
Kiss, B., Illés, G., Tóth, C. K. (2019) GPS-SLAM: Global localization using visual SLAM and GPS measurements. Sensors, 19(12), 2740.
Leutenegger, S., Lynen, S., Bosse, M., Siegwart, R., Furgale, P. (2015) Keyframe-based visual–inertial odometry using nonlinear optimization. International Journal of Robotics Research, 34(3), pp. 314–334. DOI: https://doi.org/10.1177/0278364914554813
Macenski, S., Foote, T., Gerkey, B., Lalancette, F., Woodall, W. (2022) Robot Operating System 2: Design, architecture, and uses in robotics. Science Robotics, 7(66), eabm6074. DOI: https://doi.org/10.1126/scirobotics.abm6074
Mur-Artal, R., Montiel, J. M. M., Tardós, J. D. (2015) ORB-SLAM: A versatile and accurate monocular SLAM system. IEEE Transactions on Robotics, 31(5), pp. 1147–1163. DOI: https://doi.org/10.1109/TRO.2015.2463671
Mur-Artal, R., Tardós, J. D. (2017). ORB-SLAM2: An open-source SLAM system for monocular, stereo, and RGB-D cameras. IEEE Transactions on Robotics, 33(5), pp. 1255–1262. DOI: https://doi.org/10.1109/TRO.2017.2705103
Qin, T., Li, P., Shen, S. (2018) VINS-Mono: A robust and versatile monocular visual–inertial state estimator. IEEE Transactions on Robotics, 34(4), pp. 1004–1020. DOI: https://doi.org/10.1109/TRO.2018.2853729
Scaramuzza, D., Fraundorfer, F. (2011) Visual odometry [Tutorial]. IEEE Robotics & Automation Magazine, 18(4), 80–92. DOI: https://doi.org/10.1109/MRA.2011.943233
Wang, Y., Zhang, J., Zhao, H. (2022) Map reuse and cooperative localization for multi-agent SLAM systems. Robotics and Autonomous Systems, 148, 103922.
Zhang, J., Singh, S. (2014) LOAM: Lidar odometry and mapping in real-time. In Proceedings of Robotics: Science and Systems (RSS). DOI: https://doi.org/10.15607/RSS.2014.X.007
Zhang, Z., Qin, T., Shen, S. (2019) LD-SLAM: A robust and efficient monocular SLAM system based on line and point features. IEEE Robotics and Automation Letters, 4(2), pp. 1378–1385.
Copyright (c) 2026 Károly Fodor, András Rövid
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge. There are no Open Access (OA) fees or charges (APCs) charged to either authors or readers, i.e. the articles can be used for non-commercial purposes, without changes or modifications.
All articles published in the journal are licensed under CC-BY-NC-ND 4.0 license.
The names and email addresses entered in this journal site will be used exclusively for the stated purposes of this journal and will not be made available for any other purpose or to any other party and will not be used for any other purpose or be accessible to any other party.
