Watch a research seminar exploring the evolution from Spatial AI to Embodied AI, presented by Dr. Alessio Del Bue, director of the PAVIS research unit at the Italian Institute of Technology. Discover how advanced visual scene representation techniques like NeRF and 3DGS are enabling the creation of detailed, semantically-rich environmental models. Learn about the progression toward autonomous systems that can actively interact with and learn from their surroundings, including applications in navigation, object detection, and search capabilities. Examine how visual and multi-modal data contribute to developing Embodied AI models for humanoid robotic platforms. Gain insights from Del Bue's extensive experience in 3D scene understanding using multi-modal inputs (images, depth, audio) and his work in advancing assistive Artificial Intelligence systems.