Localization And Mapping Of Unknown Locations And Tunnels With Unmanned Ground Vehicles

The main goals of this research were 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 will enhance the U. S. Army Engineering Research and Development Center’s (ERDC’s) current capabilities and create a safe and efficient autonomous vehicle to perform the following functions within tunnels: (1) localization (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 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 ERDC’s level of autonomy for UGVs from tether to tele-operated to autonomous