Robot drones, unmanned aerial vehicles (UAVs), are being used extensively not only for military applications, law enforcement and environmental monitoring.
Typically UAVs depend on GPS technology and supervision from a human operator, who sends commands to the aircraft and receive images from its on-board cameras with varying degrees of autonomy.
Now researchers at McGill University's Mobile Robotics Lab, in Montreal, Canada, are enhancing the capability of these crafts. They have developed a UAV control system that uses aerial images to identify visual cues on the landscape and steer the aircraft autonomously. These aerial vehicles guided by advanced vision capabilities could help track wildfires, oil spills, and even animal herds. The aircraft would carry out monitoring and mapping missions requiring no human supervision or GPS coordinates.
The researchers presented their results at the IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems in October. Anqi Xu, a PhD student, and his advisor, Professor Gregory Dudek, director of the Mobile Robotics Lab, say that their current system can indentify varied topography, that is, it can follow a coastline or a road surrounded by forests.
They used a fixed-wing UAV called the Unicorn from Procerus Technologies, which is controlled through software. The UAV carries a gimbal-mounted camera that streams video over a radio link. A Linux notebook computer analyzes the video feed and sends heading updates to the UAV in real time.
The vision algorithm specially written for this purpose allows the UAV to track coastlines by analyzing colour properties in the images to distinguish between water and land. It can also analyze texture cues to track a highway in a forested region. Once the algorithm has identified the boundaries between different areas, it then determines a heading to follow.
The researchers took their UAV to the beach for testing. The test area comprised a kilometer long "S" shaped tropical coastline. After manually aligning the UAV, their control system took over and successfully steered the aircraft along the stretch of the shore. The UAV travelled at an altitude of 150 meters with an average ground speed of 13 meters per second with lateral wind speed of 7 meters per second.
To compare this performance with that of a human operator, the researchers asked five volunteers to watch the recorded images and specify headings to keep the UAV following the coastline. Though there were discrepancies between the headings produced by the algorithm and by the volunteers, the researchers concluded that their system can perform nearly as well as a human operator.
In a next phase of the project, the researchers plan to use their aerial tracker to transmit navigation data to another of their systems, an amphibian robot designed to study coral reefs.