Simultaneous localisation and mapping algorithm for topological maps with dynamics

A simultaneous localisation and mapping (SLAM) algorithm for topological maps is proposed. Especially, this algorithm deals with a semi-permanent dynamics induced by door opening and closing. To deal with the semi-permanent dynamics, nodes are classified into two types. One is an invariant node that is free from the dynamics, and the other is a variant node that is not affected by door opening and closing. Two different approaches are used at the same time: a quasi-static SLAM for the invariant nodes and a dynamic SLAM for the variant nodes. A gross shape of the given environment is represented by the quasi-static SLAM algorithm, and a detailed shape of the environment is revealed via the dynamic SLAM. Experimental results validate that the proposed algorithm produces a topologically consistent map under the semi-permanent dynamics.

[1]  P. Newman,et al.  SLAM in large-scale cyclic environments using the Atlas framework , 2003 .

[2]  Jean-Arcady Meyer,et al.  Incremental vision-based topological SLAM , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Howie Choset,et al.  Hierarchical simultaneous localization and mapping , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[4]  Wan Kyun Chung,et al.  A Robust Localization Algorithm in Topological Maps with Dynamics , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[5]  Howie Choset,et al.  An enhanced occupancy map for exploration via pose separation , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[6]  Roland Siegwart,et al.  Incremental robot mapping with fingerprints of places , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Maarja Kruusmaa,et al.  Global Navigation in Dynamic Environments Using Case-Based Reasoning , 2003, Auton. Robots.

[8]  Keiji Nagatani,et al.  Topological simultaneous localization and mapping (SLAM): toward exact localization without explicit localization , 2001, IEEE Trans. Robotics Autom..

[9]  Peter Cheeseman,et al.  On the Representation and Estimation of Spatial Uncertainty , 1986 .

[10]  정완균,et al.  A Simultaneous Localization And Mapping Algorithm for Topological Maps with Dynamics , 2007 .

[11]  V. F. F. Leavers.  Shape Detection in Computer Vision Using the Hough Transform , 2011 .

[12]  Javier González,et al.  Toward a Unified Bayesian Approach to Hybrid Metric--Topological SLAM , 2008, IEEE Transactions on Robotics.

[13]  Wan Kyun Chung,et al.  The robust construction of a generalized Voronoi graph (GVG) using partial range data for guide robots , 2008, Ind. Robot.

[14]  Jingyan Song,et al.  Control Mechanism Analysis of Small-Agent Networks Using a Distinguished Node Model for Urban Traffic Controls , 2008, IEEE Transactions on Automation Science and Engineering.

[15]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[16]  Roland Siegwart,et al.  Cognitive maps for mobile robots - an object based approach , 2007, Robotics Auton. Syst..

[17]  Michael Bosse,et al.  Simultaneous Localization and Map Building in Large-Scale Cyclic Environments Using the Atlas Framework , 2004, Int. J. Robotics Res..

[18]  R. H. Myers,et al.  Probability and Statistics for Engineers and Scientists , 1978 .

[19]  Benjamin Kuipers,et al.  Towards Autonomous Topological Place Detection Using the Extended Voronoi Graph , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.