Researchers at the University of Aberdeen are developing a new generation of software that will allow people to converse with robots and computers. The computer scientists behind the development say that the new systems could help to build “trust” between machines and humans and to boost efficiency, both operationally and financially.

“Autonomous systems – such as robots – are an integral part of modern industry, used to carry out tasks without continuous human guidance,” explains Dr Wamberto Vasconcelos (above), from the University’s School of Natural and Computing Sciences. “These systems can quickly process huge amounts of information when deciding how to act. However, in doing so, they can make mistakes which are not obvious to them – or to a human.

“Evidence shows there may be mistrust when there are no provisions to help a human to understand why an autonomous system has decided to perform a specific task, at a particular time, and in a certain way,” he continues. “What we are creating is a new generation of autonomous systems, which are able to carry out a two-way communication with humans.

“The ability to converse with such systems will provide us with a novel tool to quickly understand – and, if necessary, correct – the actions of an automated system, increasing our confidence in, and the usefulness of, such systems,” Vasconcelos adds.

The new systems – being developed with a £1.1m grant from the UK Engineering and Physical Sciences Research Council – use a technology called natural language generation, which translates complex information and data into simple text summaries.

“Information and data created by the system, originally represented as symbols of mathematical logic, is transformed automatically into a simple text which can be easily understood by humans,” says Vasconcelos. “This enables the system and a human to discuss a plan before a task – such as dismantling a nuclear plant – is undertaken.”

The human can then further interrogate the computer via a keyboard, asking it to provide further justifications for its decisions, or to provide additional information for the computer to integrate into its plans. The human could also suggest alternatives or point out issues with the chosen course of action, all with the aim of ensuring a positive outcome from the project that is being worked on.

“We hope that the systems we are developing will enable a new generation of computer systems – including robots and also, potentially, mobile phones – that can interact with a human in useful ways, which up until now haven’t been explored,” Vasconcelos concludes. “The resulting systems would potentially enhance efficiency in the sectors in which they could be employed.”