Driverless cars and other industries that use robotics and computing for safety could benefit from the approach

Swarm robots reduce human error

A swarm of 600 robots that are each individually programmed, but work as a collective, has been shown to effectively carry out tasks while negating elements of human error present in the code.

Driverless cars and industrial facilities could benefit from the approach, where robotics is an important part of safety and quick decision making can make all the difference.

Swarm robotics is the study of how large groups of robots can interact with each other in simple ways to solve relatively complex tasks cooperatively.

While previous research into swarms used trial and error methods to automatically program groups of robots, it often resulted in unpredictable and undesirable behaviour.

Moreover, the resulting source code is time-consuming to maintain, which makes it difficult to use in the real-world.

The team of researchers from the University of Sheffield took a different approach by using ‘supervisory control theory’, which reduces the need for human input and the resulting errors.

They used a graphical tool to define the tasks they wanted the robots to achieve and a machine then automatically programmes and translates this to the robots.

The program uses ‘a form of linguistics’ that is comparable to using the alphabet in the English language.

The robots use this to construct words, with the ‘letters’ of these words relating to what the robots perceive and to the actions they choose to perform.

The supervisory control theory helps the robots to choose only those actions that eventually result in valid ‘words’. Hence the behaviour of the robots is guaranteed to meet the specification.

With an increasing reliance on software and technology, machines that are capable of taking higher-level commands and programming themselves to behave in predictable ways that are less error-prone than traditional methods of human input could be very valuable.

Dr Roderich Gross, with the University of Sheffield, said: “Our research poses an interesting question about how to engineer technologies we can trust – are machines more reliable programmers than humans after all?

“We, as humans, set the boundaries of what the robots can do so we can control their behaviour, but the programming can be done by the machine, which reduces human error.”

The Google-owned Boston Dynamics recently unveiled the latest version of its Atlas robot, a humanoid machine that is designed to function in a variety of scenarios.

Recent articles

Info Message

Our sites use cookies to support some functionality, and to collect anonymous user data.

Learn more about IET cookies and how to control them