Development of Autonomous Cargo Transport for an Unmanned Aerial Vehicle Using Visual Servoing

This paper presents the design and testing of systems for autonomous tracking, payload pickup, and deployment of cargo via a UAV helicopter. The tracking system uses a visual servoing algorithm and is tested using open loop velocity control of a 3DOF gantry system with a camera mounted via a pan-tilt unit on the end effecter. The pickup system uses vision to control the camera pan tilt unit as well as a second pan tilt unit with a hook mounted on the end of the arm. The ability of the pickup system to hook a target is tested by mounting it on the gantry while recorded helicopter velocities are played back by the gantry. A preliminary semi-autonomous deployment system is field tested, where a manually controlled RC truck is transported by a UAV helicopter under computer control that is manually directed to GPS waypoints using a ground station.