Autonomous UAV Navigation in an indoor Environment for warehouse inventory recording

UAV’s are currently used extensively in outdoor environments for various applications, including wildfire monitoring, and agricultural surveying, their use in indoor applications have been fairly restricted, owing mainly to the difficulty to maneuver them in smaller indoor spaces and the inability to use GPS-based navigation system. Nevertheless, there are many indoor applications where UAVs could provide a safe, reliable and resilient means to perform operations that are dangerous for humans such as surveillance inside chemical plants, inventory scanning in cold storages etc., Autonomous UAV navigation in an indoor environment can be achieved by finding a collision-free flight path to pass over each point in an environment. To solve the coverage problem in a structured manner, a coverage path planning algorithm, Boustrophedon Cellular Decomposition (BCD) is used to determine a set of waypoints in the environment that the robot should travel to so that it is able to cover every portion of the free space in an environment using its sensor, such as camera, landmine detection sensor, etc. The BCD is extended to 3-D plane, where the environment is dynamically divided into polygon-shaped cells of free space by the UAV as it covers the environment; each cell is then covered using back and forth sweeping motions. The results of this research are being used toward implementing an indoor warehouse inventory management system using a UAV where it autonomously flies in front of warehouse shelves to scan inventory using its camera and sends data back to a base station for analysis