Southwest Research Institute

Stephen A Geiger

Omar D Medjaouri

David J Anthony

Justin B Daniel

Logan A Elliott

Anthony J Wagner

An on-board navigation system for an unmanned aircraft system (UAS) operating in an unknown environment. A point-cloud sensor system generates point cloud data representing the unknown environment. An on-board processing system processes the point cloud data to generate both a 2-D occupancy grid and a 3-D voxel map, with the 2-D occupancy grid having cells with known (seen) and unknown data. Additional processing determines an amount of known-to-unknown (transitional) data in each cell, thereby determining unexplored regions. A cost is assigned to each unexplored region, based at least in part on the amount of transitional data in cells of the region. The unexplored regions are then sorted based on their costs, thereby determining an optimal region to explore. The 3-D voxel map is used to find a safe area within the optimal region where the UAS may fly. A flight path to the optimal region is then calculated.

Navigation system for unmanned aircraft in unknown environments

A method of providing a collision avoiding travel path for an autonomous vehicle. A sensor system obtains stereo image data of a scene in the environment ahead of the normal travel path. This image data is used to generate a disparity image. The disparity image is processed to generate an occupancy map that assigns values to areas of the scene based on levels of visual clutter. The occupancy map is then converted to a potential field, which assigns each pixel in the scene with a force value that corresponds to its proximity to one or more obstacles. These force value are summed and used to modify the vehicle's path is a collision is likely.

Growing community of inventors

San Antonio, TX, United States of America

Stephen A Geiger