- The European project GuestXR is to examine individual and group behaviour in extended reality environments by drawing on existing theoretical models from the neuroscience and social psychology standpoint.
- The innovation seeks to help avert conflicts and cyberbullying in digital interaction environments, make it easier for people with communication problems to get involved, detect antisocial behaviour and tackle other similar issues.
- The solution is to be tested in contexts in which discussion topics such as climate change might generate heated debate.
The European project GuestXR is to develop an immersive virtual social space anchored in extended reality. It will feature a machine learning agent designed to unlock interactions between participants and help them achieve their goals while it additionally supports addressing conflicts in virtual environments such as the metaverse.
A machine learning system called ‘The Guest’ is to be devised as an agent that can examine participants’ individual and group behaviour by drawing on existing theoretical models from the neuroscience and social psychology standpoint. Deep Reinforcement Learning will also give it the ability to learn over time and become more effective in terms of social interaction, learning from both simulations and real human meetings.
“Every gathering of people in virtual and augmented reality has a purpose – either an explicit one, such as to reach an agreement on a topic of discussion, or an implicit one such as enjoyment. The fundamental idea of ‘the Guest’ is to help the group of people realise this purpose. This involves exciting research with a strong interdisciplinary component, breaking new ground, and hopefully contributing to the success of social Virtual and Augmented Reality,” says Mel Slater, GuestXR scientific leader from the University of Barcelona.
To modulate this social interaction, ‘The Guest’ will be able to perform a range of multisensory actions “using, for instance, visual or auditory features to create particular states of mind and stimulate a relaxed environment when it identifies a conflict,” says Aurora Sesé, GuestXR project coordinator at the Eurecat technology centre.
This project “is designed to help deliver solutions to existing challenges in online environments of social interaction like cyberbullying, for which there is no specific European legislation as yet,” she adds.
The intervention of the machine learning system will be initially tested in conflict resolution situations, in interactions involving hearing impaired participants or in contexts that trigger debate such as climate change.
Finally, there will be two open calls to include other innovative use cases to check the system’s effectiveness: one addressed to the general society (including companies, associations, etc.) and the other one specifically addressed to people from the arts world.
The GuestXR technology will be developed under the “Ethics by Design” approach. This entails considering any potential ethical issues which may come up when using Artificial Intelligence such as respect for human autonomy, prevention of harm, fairness and explicability.
The GuestXR consortium is coordinated by the Eurecat technology centre together with the University of Barcelona and it is made up of eight organisations from six countries featuring a multidisciplinary team with backgrounds in extended reality, machine learning, artificial intelligence, social psychology, the neuroscience of emotions, multisensory integration, research ethics and technology transfer.
Alongside Eurecat, four universities (the University of Maastricht, the University of Warsaw, the University of Barcelona and the Reichman University), a research institute (Inria) and two businesses (Virtual Bodyworks and g.tec medical engineering GMBH) are also taking part in the project.
Project key facts
Full Project Title: A Machine Learning Agent for Social Harmony in eXtended Reality
Project Acronym: GuestXR
Start date: 1 January 2022
End date: 31 December 2025
Budget: € 4,499,519.76
Coordinator: Eurecat Technology Centre