Constructing 3d maps for dynamic environments using autonomous UAVs

This paper presents the design and implementation of an Unmanned Aerial Vehicle (UAV), which can navigate autonomously in dynamic environments. The goal of the project is to minimize the risks to workers' safety by deploying UAVs to inaccessible places which are frequently found in the Oil & Gas Industry such as confined pipelines. The autonomous UAV can fly through a series of pipes to generating a 3D map of the flight path. We used Light Detection and Ranging (LIDAR) technology to map the surrounding environment as the UAV flies through the environment. The feedback from the LIDAR sensors is used for real-time autonomous navigation and obstacle avoidance. The route is also logged for subsequent navigation. As a UAV navigates the environment, it records a video of all it sees which can then be watched by the maintenance engineers. Our approach involves running a simulation using the Robotics Operating System (ROS) to assert and fine-tune our navigation algorithms before applying them directly to the physical hardware. At this stage, we have successfully implemented the autonomous navigation using LIDAR scanners in the ROS simulation environment. We also implemented an algorithm to manage the battery life of the UAV through which it can use to return home when the battery level drops down to a certain percentage. We expect that this research will help autonomous UAVs to safely navigate new spaces by themselves in different domains such as in industrial maintenance and rescue operations.