Hybrid Topological Map Fusion Based on Memory Sphere

doi:10.1007/s12204-025-2824-6

Abstract

Abstract: A topological map with the spatial relationship is an inescapable object in the research of map fusion, as it is a priori knowledge for planning path. However, there are some difficulties in topological map fusion in a dynamic environment. Therefore, this paper proposes a fusion method for the hybrid topological map based on the memory sphere. A hybrid topological map is composed of occupancy grid maps and the topological structure. The hybrid map fusion can rely on rich features in occupancy grid maps. By analyzing the process of recalling scene, a memory sphere is designed to store the features and the semantic label extracted from occupancy grid maps. Then the core is the matching of the memory sphere, which is divided into two parts, fast retrieval and fine matching. We verify the effectiveness of our method in simulation and real environments, demonstrating that our method has a great performance in the dynamic environment.

Key words: hybrid topological map, map fusion, semantic label, memory sphere, hierarchical matching

摘要： 具有空间关系的拓扑地图是地图融合研究中不可忽视的对象，因为它是路径规划的先验知识。然而，拓扑地图的融合在动态环境中存在一些困难。本文提出了一种基于记忆球的混合拓扑地图融合方法。混合拓扑地图由占据栅格地图和拓扑结构组成。混合地图融合可以依赖于占据栅格地图中的丰富特征。通过分析回忆的过程，设计了一个记忆球来存储从占据栅格地图中提取的特征和语义标签。接着，记忆球体的匹配过程是核心，其分为两部分：快速检索和精匹配。在仿真和实际环境中验证了该方法的有效性；结果表明，在动态环境中，该方法具有出色的性能。

关键词: 混合拓扑地图，地图融合，语义标签，记忆球，层次匹配

CLC Number:

TP242.6

Peng Chengyu, Chen Baifan, Li Siyu, Jin Yuxuan, Wan Jiadong, Fu Yuesi. Hybrid Topological Map Fusion Based on Memory Sphere[J]. J Shanghai Jiaotong Univ Sci, 2026, 31(1): 130-142.

References

[1] LAJOIE P Y, RAMTOULA B, WU F, et al. Towards collaborative simultaneous localization and mapping: A survey of the current research landscape [J]. Field Robotics, 2022, 2: 971-1000.

[2] YU S E, FU C Y, GOSTAR A K, et al. A review on map-merging methods for typical map types in multiple-ground-robot SLAM solutions [J]. Sensors, 2020, 20(23): 6988.

[3] CHOSET H, NAGATANI K. Topological simultaneous localization and mapping (SLAM): Toward exact localization without explicit localization [J]. IEEE Transactions on Robotics and Automation, 2001, 17(2): 125-137.

[4] CHEONG H, PARK S, PARK S K. Topological map building and exploration based on concave nodes [C]//2008 International Conference on Control, Automation and Systems. Seoul: IEEE, 2008: 1115-1120.

[5] SAEEDI S, TRENTINI M, SETO M, et al. Multiple-robot simultaneous localization and mapping: A review [J]. Journal of Field Robotics, 2016, 33(1): 3-46.

[6] HOWARD A. Multi-robot simultaneous localization and mapping using particle filters [J]. The International Journal of Robotics Research, 2006, 25(12): 1243-1256.

[7] DURDU A, KORKMAZ M. A novel map-merging technique for occupancy grid-based maps using multiple robots: A semantic approach [J]. Turkish Journal of Electrical Engineering & Computer Sciences, 2019, 27(5): 3980-3993.

[8] VELÁSQUEZ HERNÁNDEZ C A, PRIETO ORTIZ F A. A real-time map merging strategy for robust collaborative reconstruction of unknown environments [J]. Expert Systems with Applications, 2020, 145: 113109.

[9] LEE H. Tomographic feature-based map merging for multi-robot systems [J]. Electronics, 2020, 9(1): 107.

[10] KOHONEN T, OJA E, SIMULA O, et al. Engineering applications of the self-organizing map [J]. Proceedings of the IEEE, 1996, 84(10): 1358-1384.

[11] SAEEDI S, PAULL L, TRENTINI M, et al. Neural network-based multiple robot simultaneous localization and mapping [J]. IEEE Transactions on Neural Networks, 2011, 22(12): 2376-2387.

[12] CHEN B F, LI S Y, ZHAO H W, et al. Map merging with suppositional box for multi-robot indoor mapping [J]. Electronics, 2021, 10(7): 815.

[13] LEE H, LEE S. Extended spectra-based grid map merging with unilateral observations for multi-robot SLAM [J]. IEEE Access, 2021, 9: 79651-79662.

[14] BONANNI T M, GRISETTI G, IOCCHI L. Merging partially consistent maps [M]// Simulation, modeling, and programming for autonomous robots. Cham: Springer, 2014: 352-363.

[15] HUANG W H, BEEVERS K R. Topological map merging [J]. The International Journal of Robotics Research, 2005, 24(8): 601-613.

[16] SAEEDI S, PAULL L, TRENTINI M, et al. Efficient map merging using a probabilistic generalized Voronoi diagram [C]//2012 IEEE/RSJ International Conference on Intelligent Robots and Systems. Vilamoura-Algarve: IEEE, 2012: 4419-4424.

[17] HOU J W, KUANG H F, SCHWERTFEGER S, et al. Fast 2D map matching based on area graphs [C]//2019 IEEE International Conference on Robotics and Biomimetics. Dali: IEEE, 2019: 1723-1729.

[18] CHEN H Y, HUANG H L, QIN Y, et al. Vision and laser fused SLAM in indoor environments with multi-robot system [J]. Assembly Automation, 2019, 39(2): 297-307.

[19] FERREIRA F, DIAS J, SANTOS V. Merging topological maps for localisation in large environments [M]//Advances in mobile robotics. Coimbra. World Scientific, 2008: 122-129.

[20] BONANNI T M, DELLA CORTE B, GRISETTI G. 3-D map merging on pose graphs [J]. IEEE Robotics and Automation Letters, 2017, 2(2): 1031-1038.

[21] KARAOĞUZ H, BOZMA H I. An integrated model of autonomous topological spatial cognition [J]. Autonomous Robots, 2016, 40(8): 1379-1402.

[22] KARAOĞUZ H, BOZMA H I. Merging appearance-based spatial knowledge in multirobot systems [C]//2016 IEEE/RSJ International Conference on Intelligent Robots and Systems. Daejeon: IEEE, 2016: 5107-5112.

[23] SUSA RINCON J L, CARPIN S. Time-constrained exploration using toposemantic spatial models: A reproducible approach to measurable robotics [J]. IEEE Robotics & Automation Magazine, 2019, 26(3): 78-87.

[24] PULIGILLA S S, TOURANI S, VAIDYA T, et al. Topological mapping for Manhattan-like repetitive environments [C]//2020 IEEE International Conference on Robotics and Automation. Paris: IEEE, 2020: 6268-6274.

[25] RINCON J L S, CARPIN S. Map merging of oriented topological semantic maps [C]//2019 International Symposium on Multi-Robot and Multi-Agent Systems. New Brunswick: IEEE, 2019: 202-208.

[26] SAMATOVA N F, OSTROUCHOV G, GEIST A, et al. RACHET: An efficient cover-based merging of clustering hierarchies from distributed datasets [J]. Distributed and Parallel Databases, 2002, 11(2): 157-180.