Sinergistic Next-Generation Virtual Environments and Extended Realities with Generative Intelligence Agents

SYNERGIA aims to address the limitations of current virtual training and support systems, which remain rigid, scripted and unable to respond to the cognitive, emotional and accessibility needs of diverse users. This lack of adaptivity undermines safety, inclusiveness and trust in domains where human-machine interaction is critical, from industrial assembly to healthcare rehabilitation and humanrobot collaboration.

The project envisions the next generation of Generative AI for Virtual Worlds, combining multimodal sensing, immersive content creation and explainable governance into a coherent framework for hyper-personalised, human-centric interaction. It builds upon 4 key pillars: (i) lightweight multimodal inference models capturing facial, vocal, gestural and physiological cues in real time, deployable at the edge with privacy protection; (ii) generative 3D assistants capable of emotionally responsive, multilingual and accessible interaction, including gesture and sign language; (iii) immersive pipelines that transform text, images and video into adaptive 3D environments with dynamic storytelling and collaborative scenario generation; and (iv) a GDPR-compliant learning dataspace ensuring interoperability, user control, explainability and trustworthy governance.

SYNERGIA is made for 12 partners from 5 EU countries (Greece, France, Sweden, Spain, Italy),