Embodied artificial intelligence (EAI) represents a transformative paradigm in which AI is integrated into physical bodies. Its embodied interaction and native multimodal perception naturally enhance and extend next-generation multimedia applications.
Meanwhile, EAI systems are no longer designed merely to perform pre-programmed tasks in structured settings. Driven by its core capabilities, such as cognition, learning, and collaboration, EAI systems are now being designed to coexist and collaborate with humans in open, dynamic environments, supporting a broad range of application domains, including smart manufacturing, public service, logistics, healthcare, and home automation, and creating growing demands for interoperable platforms, multimodal frameworks, and scalable system architectures.
The ITU Focus Group on Embodied AI for Multimedia Technologies (FG-EAI) was established by ITU-T Study Group 21 on 19 February 2026. FG-EAI will study how EAI can support human‑centric multimedia applications by examining its core technical abilities, such as understanding the physical world, learning from trial and error, and collaborating with humans and their environments. It will investigate foundational technologies including real and virtual datasets, closed‑loop control, world‑model training, and advanced human–machine interaction. More details are found in the ToR.
Parent Group: ITU-T SG21
