Quadcopters are being programmed to “learn” and “think” for themselves, and use those abilities to fly complex missions autonomously at the University of Sheffield in England. The research is aimed at developing small, self-controlled aircraft that can operate in environments that would be extremely dangerous to humans, such as the inside of a damaged nuclear reactor.
“We are used to the robots of science fiction films being able to act independently, recognise objects and individuals and make decisions,” said Sandor Veres, the professor who is leading the research, in a news release. “In the real world, however, although robots can be extremely intelligent individually, their ability to co-operate and interact with each other and with humans is still very limited.”
The quadcopters are fitted with cameras, and additional instruments that capture barometric data and ultrasonic signal returns, enabling the autonomous robots to build a 3-D image of their environment with no prior instruction about the placement of objects, or the room’s dimensions. Using this constantly updated stream of data, they can adjust their flight path to accommodate both fixed and moving objects, such as other quadcopters. In essence, they’ve been programmed to be “polite,” and adjust altitude or flight trajectory to avoid collisions, a capability essential to operating in environments such as disaster scenes where communication networks are already pressed to the limit.
“The learning process the robots use here is similar to when two people meet in the street and need to get round each other,” said research fellow Jonathan Aitken. “They will simultaneously go to their left or right until they coordinate and avoid collision.”
The longer the quadcopters fly together, the more data they gather on the behavior of other moving objects in the environment, and use previous experience to anticipate what those other quadcopters will do, and act accordingly.
“These simple tasks are part of a major research effort in the field of robotics at Sheffield University,” Veres said. “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.”