Clever copters that learn as they fly
Our scientists are developing robots that can display true autonomy - and even a bit of politeness - when working together in hostile situations.
Engineers at the University's Department of Automatic Control and Systems Engineering are developing robots able to work alongside humans. These robots will play crucial roles in crisis situations such as search and rescue missions, or operate in environments where it would be dangerous for people to work.
Using simple flying robots, octocopters and hexacopters, the team has created software that enables the robot to learn about its surroundings using a forward-facing camera mounted on the machine.
The robot navigates its way around thanks to overlaid frames from the camera. It uses these to select key reference points and builds up a 3D map of its surroundings. Additional sensors pick up barometric and ultrasonic data, which give the robot additional clues about its environment. All this information is fed into an “autopilot software”, which allows the robot not only to navigate safely, but also to learn about the position of nearby objects, such as other robots.
Research leader Professor Sandor Veres said: "We are used to the robots of science fiction films being able to act independently, recognise objects and individuals and make decisions. 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."
We are researching the theory and algorithmic solutions for future autonomous vehicles in the air, on the ground and on the water
Professor Sandor Veres
Another key task for these robots is to be able to interact and co-operate with each other without overloading communications networks – a vital ability in emergency situations where networks will already be overloaded. Programming allows the quadcopters to 'politely' fly among other robots without colliding, allowing other robots to pass.
But these developments aren't limited to copters, according to Professor Veres. "We are researching the theory and algorithmic solutions for future autonomous vehicles in the air, on the ground and on the water."
The researchers used the principles of game theory to programme the copters. In this framework, each robot is a player in the game and must complete its given task in order to ‘win’ the game, which often means to cooperate with other robots.
If the robots play the game repeatedly they start to learn each other’s behaviour. They can then perform their task successfully – in this case getting past the other robot – by using previous experience to estimate the behaviour of the other robot.
"These simple tasks are part of a major research effort in the field of robotics at the University of Sheffield," says Professor Veres. "The next step is to extend the programming capability so that multiple robots can collaborate with each other in more complex tasks, where problem solving is required, enabling fleets of machines to interact and collaborate."