Indoor Topological Mapping with Place Recognition and Scan Matching
- 作者: Muravyev K.F.1
-
隶属关系:
- Federal Research Center “Computer Science and Control” of Russian Academy of Sciences
- 期: 编号 3 (2024)
- 页面: 28-38
- 栏目: Intelligent systems and technologies
- URL: https://journals.rcsi.science/2071-8632/article/view/286113
- DOI: https://doi.org/10.14357/20718632240303
- EDN: https://elibrary.ru/CFSQSG
- ID: 286113
如何引用文章
详细
Map building is one of the key tasks of autonomous mobile robots’ navigation. Traditional mapping methods build dense metric map (e.g. as an occupancy grid). Maintaining such map in case of long-term navigation is difficult because of high computational costs and odometry error accumulation. Representing the environment as a sparse topological structure (e.g. a graph of locations) lets us eliminate these drawbacks and provide fast path planning. In this work, we propose a topological mapping method which builds and updates a graph of locations without use of global metric coordinates. For localization, the proposed method uses neural network-based place recognition in pair with 2D projection-based scan matching. We carry out experiments with our method in several photorealistic simulated scenes and on data from a real robot. In simulation, we compare our method with some state-of-the-art topological mapping methods. According to the results, the proposed method significantly outperforms competitors in terms of navigational efficiency, keeping graph connectivity, high scene coverage, and low part of inconsistent edges.
作者简介
Kirill Muravyev
Federal Research Center “Computer Science and Control” of Russian Academy of Sciences
编辑信件的主要联系方式.
Email: muraviev@isa.ru
младший научный сотрудник
俄罗斯联邦, Moscow参考
- Швец Е. А. Разработка моделей картирования и патрулирования коллективом беспилотных наземных роботов, использующих техническое зрение и эхолокацию: Автореф. дисс. канд. техн. наук: [Место защиты: Институт проблем передачи информации им. АА Харкевича РАН]. – 2016. – 139 с //Режим доступа: http://iitp. ru/upload/content/1327/synopsis. pdf. – 2016.
- Боковой А. В. Исследование методов одновременного картирования и локализации беспилотных летательных аппаратов по видеопотоку, полученному с единственной камеры //Второй Всероссийский научно-практический семинар "Беспилотные транспортные средства с элементами искусственного интеллекта". – 2015. – С. 26-33.
- Labbé M., Michaud F. RTAB< Map as an open< source lidar and visual simultaneous localization and mapping library for large< scale and long< term online operation //Journal of field robotics. – 2019. – Vol. 36. – No. 2. – P. 416-446.
- Hess W. et al. Real-time loop closure in 2D LIDAR SLAM
- //2016 IEEE international conference on robotics and automation (ICRA). – IEEE, 2016. – P. 1271-1278.
- Muravyev K., Yakovlev K. Evaluation of RGB-D SLAM in large indoor environments //International Conference on Interactive Collaborative Robotics. – Cham: Springer International Publishing, 2022. – P. 93-104.
- Щеголева Л. В., Воронов Р. В. Построение дорожного графа для маршрутизации мобильного робота в замкнутой системе коридоров //Инженерный вестник Дона. – 2015. – Т. 37. – №. 3. – С. 43.
- Blochliger F. et al. Topomap: Topological mapping and navigation based on visual slam maps //2018 IEEE International Conference on Robotics and Automation (ICRA). – IEEE, 2018. – P. 3818-3825.
- Gomez C. et al. Hybrid topological and 3d dense mapping through autonomous exploration for large indoor environments //2020 IEEE International Conference on Robotics and Automation (ICRA). – IEEE, 2020. – P. 9673-9679.
- Schmid L. et al. A unified approach for autonomous volumetric exploration of large scale environments under severe odometry drift //IEEE Robotics and Automation Letters. – 2021. – Vol. 6. – No. 3. – P. 4504-4511.
- Chen X. et al. Fast 3D sparse topological skeleton graph generation for mobile robot global planning //2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). – IEEE, 2022. – P. 10283-10289.
- Hughes N., Chang Y., Carlone L. Hydra: A real-time spatial perception system for 3D scene graph construction and optimization //arXiv preprint arXiv:2201.13360. – 2022.
- Yuan Y., Schwertfeger S. Incrementally building topology graphs via distance maps //2019 IEEE International Conference on Real-time Computing and Robotics (RCAR). – IEEE, 2019. – P. 468-474.
- Kim N. et al. Topological semantic graph memory for image-goal navigation //Conference on Robot Learning. – PMLR, 2023. – P. 393-402.
- Kwon O. et al. Visual graph memory with unsupervised representation for visual navigation //Proceedings of the IEEE/CVF International Conference on Computer Vision. – 2021. – P. 15890-15899.
- Wiyatno R. R., Xu A., Paull L. Lifelong topological visual navigation //IEEE Robotics and Automation Letters. – 2022. – Vol. 7. – No. 4. – P. 9271-9278.
- Yin P. et al. General place recognition survey: Towards the real-world autonomy age //arXiv preprint arXiv:2209.04497. – 2022.
- Muravyev K., Yakovlev K. Evaluation of Topological Mapping Methods in Indoor Environments //IEEE Access. – 2023. – Vol. 11. – P. 132683-132698.
- Muravyev K. et al. PRISM-TopoMap: Online Topological Mapping with Place Recognition and Scan Matching //arXiv preprint arXiv:2404.01674. – 2024.
- Harris C. et al. A combined corner and edge detector //Alvey vision conference. – 1988. – Vol. 15. – No. 50. – P. 10-5244.
- Rublee E. et al. ORB: An efficient alternative to SIFT or SURF //2011 International conference on computer vision. – IEEE, 2011. – P. 2564-2571.
- Muja M., Lowe D. Flann-fast library for approximate nearest neighbors user manual //Computer Science Department, University of British Columbia, Vancouver, BC, Canada. – 2009. – Vol. 5. – P. 6.
- Komorowski J. Minkloc3d: Point cloud based large-scale place recognition //Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. – 2021. – С. 1790-1799.
- Chang A. et al. Matterport3d: Learning from rgb-d data in indoor environments //arXiv preprint arXiv:1709.06158. – 2017.
- Bavle H. et al. S-graphs+: Real-time localization and mapping leveraging hierarchical representations //arXiv preprint arXiv:2212.11770. – 2022.
补充文件
