According to Dr Wamberto Vasconcelos, who is heading up the project at the university’s School of Natural and Computing Sciences, the software uses technology called Natural Language Generation (NLG) that is able to translate complex information and data into simple text summaries.
The system could enable humans and computers to use common language to plan operations and discuss actions, an advance that Vasconcelos believes will help build trust between machines and humans
‘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,’ Vasconcelos said in a statement. ‘What we are creating is a new generation of autonomous systems, which are able to carry out a two-way communication with humans.’
Vasconcelos claimed that the technology — being developed with the help of an EPSRC grant worth £1.1m — could lead to major operation benefits across a variety of industry sectors, including rail, nuclear and space.
‘The resulting systems would potentially enhance efficiency — both in terms of cost and operation — in the sectors in which they could be employed,’ he said.
In the long term, Vasconcelos believes that the systems under development at Aberdeen could fundamentally alter the way people communicate with machines.
‘We hope the systems we are developing will enable a new generation of computer systems that can interact with a human in useful ways, which up until now haven’t been explored,’ he said.
‘Archaic rules’ torn up to green light new nuclear
Lack of data about windpower being cheaper than nuclear was, I felt, the question that you replied to. and as the context is energy security it would...