University UAS efforts focus on interaction with humans and wildlife conservation
For this month's University Update section we take a look at two innovative unmanned aircraft research projects, one being conducted by a university in the U.K. and one in the U.S. One involves flying quadcopters with programming that can enable them to work alongside humans, while the other looks to curb poaching in Africa.
Researchers at the University of Sheffield in the United Kingdom are looking to improve robot and human relations with their work on a software system that "enables the robot to learn about its surroundings using a forward facing camera mounted at the front of the machine," according to a University news release.
The team – based in Sheffield's Department of Automatic Control and Systems Engineering (ACSE) – wants to enable robots to be able to work intelligently with humans; the aim is to have the robots perform search-and-rescue missions or work in harsh environments that are unsuitable to humans.
"We are used to the robots of science-fiction films being able to act independently, recognize objects and individuals, and make decisions," says Professor Sandor Veres, who is leading the research. "In the real world, however, although robots can be extremely intelligent individually, their ability to cooperate and interact with each other and with humans is still very limited. As we develop robots for use in space or to send into nuclear environments – places where humans cannot easily go – the goal will be for them to understand their surroundings and make decisions based on that understanding."
The robot, a quadcopter in this case, starts with no data about its environment and the objects within it. Different frames from the camera are then overlaid and key reference points are selected within the scene to build up a 3-D map of the world around it. Other sensors then pick up barometric and ultrasonic data, which provide the robot with additional clues about its environment. All this information is fed into autopilot software to enable the robot to navigate safely, but also to learn about the objects nearby and navigate to specific items, according to the Sheffield release.
The Sheffield team also developed a software program to enable "the Quadcopters to work out how to ‘politely' fly past each other without colliding. The robots start off flying at the same altitude and then need to collaborate to work out which robot would fly higher and which would fly lower so they are able to pass."
"The learning process the robots use here is similar to when two people meet in the street and need to get round each other," says ACSE research fellow Dr. Jonathan Aitken. "They will simultaneously go to their left or right until they coordinate and avoid collision."
The researchers used game theory to program the quadcopters to learn each robot's behavior to determine how to get past the other robot – by using previous experience to estimate the behavior of the other robot. "The next step is to extend the programming capability so that multiple robots can collaborate with each other, enabling fleets of machines to interact and collaborate on more complex tasks," Professor Veres says.
Drones in the jungle
Students and researchers at the University of Colorado, Boulder are designing the payload, communications, and sensors for an unmanned aircraft system (UAS) as part of a competition called the Wildlife Conservation UAV Challenge, which aims to design, build, and fly a UAS to help stop poaching at the Kruger National Park in South Africa.
The Colorado team is one of four university teams working on AREND, which stands for Aircraft for Rhino and Environmental Defense. The others are the University of Pretoria in South Africa (fuselage and environmental testing), the University of Stuttgart in Germany (wings and empennage), and the Metropolia University in Finland (ground network), according to the mission section of their website: www.teamarend.com.
AREND's overall systems-engineering project leadership is housed at the University of Colorado, Boulder. Individual students assigned to select subsystems work with the teams at the partner universities to develop the correct system-interface documents.
The AREND aircraft will perform aerial surveillance over wildlife areas to protect "rhinos, elephants, and other endangered species" from poachers. The UAS sensors will detect people, large animals, and specific shapes such as crashed aircraft.
It has a modular sensor system that can be rearranged depending on its mission. Sensors that track rhinos or poachers may also be used cost-effectively locate people and vehicles, including aircraft that crash in the wilderness, according to the AREND website.
A search-and-rescue capability would enable this team to take their invention well beyond the world of poaching.