For large-scale unknown environments, a method of topological node matching based on visual feature is presented, and a local scan matching strategy is integrated to realize map merging for multi-robot system under RTM (robot technology middleware) framework. A main-auxiliary structure model of multiple robots is developed, and an improved SP2ATM algorithm is adopted to incrementally constructing topological map in unknown environments. Based on this, the hierarchical topology structure including SIFT (scale-invariant feature transform) feature information is presented, which is combined with ICP (iterative closest point) algorithm to realize map merging of multi-robot systems. RTM is taken as communication platform to improve the realtime performance, flexibility and robustness of the system. Simulation on USARSim and experimental results in actual environments verify the effectiveness of the proposed method.
 Gea S S, Zhang Q, Abraham A T, et al. Simultaneous path planning and topological mapping (SP2ATM) for environment exploration and goal oriented navigation[J]. Robotics and Autonomous Systems, 2011, 59(3/4): 228-242. Abraham A T, Ge S S, Tao P Y. A topological approach of path planning for autonomous robot navigation in dynamic environments[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, NJ, USA: IEEE, 2009: 4907-4912. Howard A. Multi-robot simultaneous localization and mapping using particle filters[J]. International Journal of Robotics Research, 2006, 25(12): 1243-1256.  Hahnel D, Burgard W, Fox D, et al. An efficient FastSLAM algorithm for generating maps of large-scale cyclic environments from raw laser range measurements[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, NJ, USA: IEEE, 2003: 206-211. Zhou X S, Roumeliotis S I. Multi-robot SLAM with unknown initial correspondence: The robot rendezvous case[C]// IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, NJ, USA: IEEE, 2006: 1785-1792. Yu Y, Wang N, Liang A, et al. Integrating line segment based maps in multi-robots exploration[C]//2nd International Conference on Future Information Technology and Management Engineering. Piscataway, NJ, USA: IEEE, 2009: 230-233. Lee H C, Lee B H. Improved feature map merging using virtual supporting lines for multi-robot systems[J]. Advanced Robotics, 2011, 25(13/14): 1675-1696. Ozkucur N E, Akin H L. Cooperative multi-robot map merging using Fast-SLAM[C]//Lecture Notes in Artificial Intelligence: vol.5949. Berlin, Germany: Springer Verlag, 2010: 449-460. Jia S M, Murakami T, Chugo D, et al. Interactive robot system for supporting object acquisition based on robot technology middleware[C]//IEEE International Conference on Information and Automation. Piscataway, NJ, USA: IEEE, 2008: 966-971. Ando N, Suehiro T, Kitagaki K, et al. Implementation of RT composite components and a component manager[C]//22nd Annual Conference of the Robotic Society of Japan. Japan: RSJ, 2004: IC26. Jia S M, Wang K, Li X Z, et al. Map building for mobile robot based on distributed control technology[C]//2011 International Conference on Information and Automation. Piscataway, NJ, USA: IEEE, 2011: 279-284. Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.  Besl P J, McKay N D. A method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2): 239-256.  祝继华,郑南宁,袁泽剑,等.基于ICP算法和粒子滤波的未知环境地图创建[J].自动化学报,2009,35(8):1107-1113.Zhu J H, Zheng N N, Yuan Z J, et al. A SLAM approach by combining ICP algorithm and particle filter[J]. Acta Automatica Sinica, 2009, 35(8): 1107-1113.