29 Aug 2023

Unmanned Ground Vehicle (UGV) Full Coverage Planning with Negative Obstacles

Abstract: We explored approaches that offer full coverage path planning while simultaneously avoiding negative obstacles. These approaches are specific to unmanned ground vehicles (UGVs), which need to constantly interact with a traversable ground surface. We tested multiple potential solutions in simulation, and the results are presented herein. Full coverage path planner (FCPP) approaches were evaluated based on their ability to discretize their paths, use waypoints effectively, and be easily integrated with our current robot platform. For negative obstacles, we explored approaches that will integrate with our current navigation stack. The preferred solution will allow for teleoperation, waypoint navigation, and full autonomy while avoiding positive and negative obstacles

20 Sep 2021

Autonomous Navigation and Mapping in a Simulated Environment

Abstract: Unknown Environment Exploration (UEE) with an Unmanned Ground Vehicle (UGV) is extremely challenging. This report investigates a frontier exploration approach, in simulation, that leverages Simultaneous Localization And Mapping (SLAM) to efficiently explore unknown areas by finding navigable routes. The solution utilizes a diverse sensor payload that includes wheel encoders, three-dimensional (3-D) LIDAR, and Red, Green, Blue and Depth (RGBD) cameras. The main goal of this effort is to leverage frontier-based exploration with a UGV to produce a 3-D map (up to 10 cm resolution). The solution provided leverages the Robot Operating System (ROS).