GuestXR: A Machine Learning Agent for Social Harmony in eXtended Reality

Immersive online social spaces will soon become ubiquitous. However, there is also a warning that we need to heed from social media. User content is the lifeblood of social media.

However, it often stimulates antisocial interaction and abuse, ultimately posing a danger to vulnerable adults, teenagers, and children.In the VR space this is backed up by the experience ofcurrent virtual shared spaces.

While they have many positive aspects, they have also become a space full of abuse.Our vision is to develop GuestXR, a socially interactive multisensory platform system that uses eXtended Reality (virtual and augmented reality) as the medium to bring people together for immersive, synchronous face-to-face interaction with positive social outcomes.The critical innovation is the intervention of artificial agents that learn over time to help the virtual social gathering realise its aims.

This is an agent that we refer to as The Guest that exploits Machine Learning to learn how to facilitate the meeting towards specific outcomes.Underpinning this is neuroscience and social psychology research on group behaviour, which will deliver rules to Agent Based Models (ABM).The combination of AI with immersive systems (including haptics and immersive audio), virtual and augmented reality will be a hugely challenging research task, given the vagaries of social meetings and individual behaviour.

Several proof of concept applications will be developed during the project, including a conflict resolution application in collaboration with the UN.

A strong User Group made up of a diverse range of stakeholders from industry, academia, government and broader society will provide continuous feedback. An Open Call will be held to bring in artistic support and additional use cases from wider society.

Significant work is dedicated to ethics by design, to identify problems and look eventually towards an appropriate regulatory framework for such socially interactive systems.