A New Approach for Large-Scale Localization and Mapping： Hybrid Metric-Topological SLAM英文资料.pdfVIP

2007 IEEE International Conference on ThB1.5 Robotics and Automation Roma, Italy, 10-14 April 2007 A New Approach for Large-Scale Localization and Mapping: Hybrid Metric-Topological SLAM Jose-Luis Blanco, Juan-Antonio Fernández-Madrigal, Javier Gonzalez Dept. of System Engineering and Automation University of Malaga Málaga, Spain {jlblanco,jafma,jgonzalez}@ctima.uma.es Abstract—Most successful works in Simultaneous relative to the current area (metric path), and (ii) the Localization and Mapping (SLAM) aim to build a metric map sequence of areas the robot goes through (topological path). under a probabilistic viewpoint employing Bayesian filtering Under this perspective, loop closure becomes finding a techniques. This work introduces a new hybrid metric- partition in the sequence of all the areas in the map [22]. topological approach, where the aim is to reconstruct the path The meaning of the topological map in this work of the robot in a hybrid continuous-discrete state space which naturally combines metric and topological maps. Our strongly differs from the one considered in many other works. In the literature we can find works t