详情

原文传递 Localization and Mapping of Unknown Locations with Unmanned Ground Vehicles.

题名：	Localization and Mapping of Unknown Locations with Unmanned Ground Vehicles.
作者：	Turnage, D. M.
关键词：	Unmanned ground vehicles, Simultaneous localization and mapping, Autonomous vehicles, Military vehicles, Tunnels, Autonomous navigation, Computer programs, Cartography, Maps, Off the shelf equipment, Terrain, Test beds, Test and evaluation, Algorithms, Kalman filters, Monte carlo method, Robot mapping, Markov processes, Image registration, Underground areas, Cartography programs, Cots (commercial off the shelf), Ugv (unmanned ground vehicles), Stage simulator, Slam (simultaneous localization and mapping), Slam algorithms, Robotic mapping, Mcl (monte carlo localization), Markov localization, Pathfinding, M and s (modeling and simulation), Ground truth maps
摘要：	The main goals of this research are to enhance a commercial off the shelf (COTS) software platform to support unmanned ground vehicles (UGVs) exploring the complex environment of tunnels, to test the platform within a simulation environment, and to validate the architecture through field-testing. Developing this platform enhances the U.S. Army Engineering Research and Development Centers (ERDCs) current capabilities and creates a safe and efficient autonomous vehicle to perform the following functions within tunnels: (1) localizing (e.g., position tracking) and mapping of its environment, (2) traversing varied terrains, (3) sensing the environment for objects of interest, and (4) increasing the level of autonomy of UGVs available at the ERDC. The simulation experiments were performed in the STAGE Simulator, a physics-based, multi-scale numerical test bed developed by Robotic Operating System (ROS). Physical testing was conducted in Vicksburg, MS, using a Coroware Explorer. Both the simulation and physical testing evaluated three simultaneous localization and mapping (SLAM) algorithms, i.e., Hector SLAM, Gmapping, and CORESLAM to determine the superior algorithm. The superior algorithm was then used to localize the robot to the environment and autonomously travel from a start location to a destination location. Completion of this research has increased the ERDCs level of autonomy for UGVs from tether to tele-operated to autonomous.
报告类型：	科技报告