Manchester team aims for more empathetic robots

Experts at Manchester University have been awarded €2.5m funding to help design ‘smarter’, more empathetic robots that could better understand human feelings.

Angelo Cangelosi and his team have been awarded funding to develop the next generation of smart robots who will be able to better understand humans by appreciating our feelings through improved language skills
Angelo Cangelosi and his team have been awarded funding to develop the next generation of smart robots who will be able to better understand humans by appreciating our feelings through improved language skills - Manchester University

The funding aims to support development of robots that could have more meaningful dialogue with humans after developing improved insight into human inner feelings through language.

Funding was awarded by the European Research Council (ERC) to Professor Angelo Cangelosi, co-director of the Manchester Centre for Robotics and AI as part of the ‘eTALK’ project.

The Manchester team will combine expertise in AI and psychology to focus on the fact that smart machines still only understand about a third of the meaning of human language.

To progress their ability to understand humans more fully, robots will act as ‘tutors’ to help children better understand numerical and abstract concepts. This will then help robots engage more meaningfully with older generations of humans, researchers said.

Cangelosi, professor of Machine Learning and Robotics at Manchester University, explained that language is the most natural means of communication among people to talk about and share experiences – and for robots to understand and communicate with us.

For example, humans use concrete words to describe objects and their features (such as ‘Look at this red pen’) and to talk about actions and events (‘I write with the pen’). However, humans most commonly use abstract words to describe social situations and relationships (such as, ‘Mary likes John’), emotional states (‘I wish you happiness’), and numbers and quantities (1, 2, 10, or ‘some’, ‘many’, etc).

“In fact, the great majority – a total of 72 per cent – of words we use are abstract words; but today’s robots can only understand the concrete words. So, how can we have meaningful interaction with robots if they cannot understand most of the words we use?” said Cangelosi.

To meet this challenge, the ERC Advanced eTALK project will take direct inspiration from the way children and adults use and learn abstract words - and use methods from AI and psychology to develop a new generation of robots capable of communicating with people about internal feelings, numbers, and other abstract words.

The award of the project builds on expertise from Cangelosi and his team in combining psychological concepts with AI and robotics to design robots that positively impact society.

The ERC has announced the awarding of 218 Advanced Grants, totalling €244m, to research leaders across Europe as part of the Horizon Europe programme.