A New Approach to Environment Representation with Its Applications in Robot Navigation

High-precision mapping and localization contribute to mobile robot navigation. It also provides convenience, robustness and safety for navigation. But for the single feature and large-scale scene, to build high-precision mapping and localization has great challenges and difficulties. Meanwhile, high precise is unnecessary for simple task. Therefore, this paper proposes a new methods of environment representation to achieve the presentation of the long corridor environment. Based on this environment representation, the dynamic path planning and state transformation approach are introduced. Finally we construct the robot navigation system and use Gazebo which is a simulation platform in ROS system to implementation. Extensive experiments tested on Gazebo demonstrate that our method reaches the state-of-the-art.

[1]  Wolfram Burgard,et al.  The dynamic window approach to collision avoidance , 1997, IEEE Robotics Autom. Mag..

[2]  Joachim Hertzberg,et al.  Towards semantic maps for mobile robots , 2008, Robotics Auton. Syst..

[3]  Wolfram Burgard,et al.  OctoMap: an efficient probabilistic 3D mapping framework based on octrees , 2013, Autonomous Robots.

[4]  John J. Leonard,et al.  Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age , 2016, IEEE Transactions on Robotics.

[5]  Alberto Elfes,et al.  Occupancy grids: a probabilistic framework for robot perception and navigation , 1989 .

[6]  Benjamin Kuipers,et al.  Factoring the Mapping Problem: Mobile Robot Map-building in the Hybrid Spatial Semantic Hierarchy , 2010, Int. J. Robotics Res..

[7]  Antonios Gasteratos,et al.  Learning spatially semantic representations for cognitive robot navigation , 2013, Robotics Auton. Syst..

[8]  Alberto Elfes,et al.  Sonar-based real-world mapping and navigation , 1987, IEEE J. Robotics Autom..

[9]  Peter Sanders,et al.  Engineering Route Planning Algorithms , 2009, Algorithmics of Large and Complex Networks.

[10]  Anthony Stentz,et al.  Optimal and efficient path planning for partially-known environments , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[11]  Roland Siegwart,et al.  Hybrid simultaneous localization and map building: a natural integration of topological and metric , 2003, Robotics Auton. Syst..

[12]  Brian P. Gerkey Planning and Control in Unstructured Terrain , 2008 .

[13]  Roland Siegwart,et al.  Topological Mapping and Scene Recognition With Lightweight Color Descriptors for an Omnidirectional Camera , 2014, IEEE Transactions on Robotics.

[14]  Wolfram Burgard,et al.  Improved Techniques for Grid Mapping With Rao-Blackwellized Particle Filters , 2007, IEEE Transactions on Robotics.

[15]  Álvaro Sánchez Miralles,et al.  Topological simultaneous localization and mapping: a survey , 2013, Robotica.