The kick-off meeting of the TORNADO project (foundaTion mOdels for Robots that haNdle smAll, soft and Deformable Objects) took place on January 30th and 31st, hosted by ITML in Athens, Greece, and it was completed with great success.
TORNADO aims to develop an innovative, multifunctional and adaptive cloud robotics platform, supporting advanced navigation of an autonomous mobile robot (AMR) within complex, time-varying, real-world, human-populated indoor environments.
Particular research attention will be given on manipulating small, soft or deformable objects (SSDs) to an unprecedented degree of success, as well as naturally interacting with humans via hand gestures or verbal conversation, by exploiting the zero-shot generalization abilities of deep neural Foundation Models (FMs) for robotics.
The role of our group focuses on the development of artificial intelligence technologies related to: a) Dynamic semantic 3D SLAM, b) On-line adjustment mechanisms for Foundation Models, c) On-demand Learning-from-Demonstration, d) Real-time semantic environment perception, e) Human behavior analysis, modeling and anticipation, and f) XAI-equipped AR-based human-robot interaction.
The Deputy Project Coordinator is Assistant Professor Georgios Th. Papadopoulos of the Department of Informatics and Telematics. He participated with a research group from Harokopio University of Athens specializing in artificial intelligence and computer vision technologies (HUA Computer Vision Group).
