CONSORTIUM

 

http://www.iccs.gr/eng/
http://www.ntua.gr/index_en.html
http://www.ece.ntua.gr/en

Contact info: Dr. Costas Tzafestas (ktzaf@cs.ntua.gr),
Prof. Petros Maragos (maragos@cs.ntua.gr),
Dr. Xanthi Papageorgiou (xpapag@mail.ntua.gr)

Institute of Communication and Computer Systems (ICCS)

The National Technical University of Athens (NTUA) is the oldest and most prestigious educational institution of Greece in the field of technology. The Institute of Communications and Computer Systems (ICCS) is a non-profit Academic Research Body established in 1989 to carry research and development activities in the fields of all diverse aspects of communications, computer systems and techniques and their applications. ICCS is associated with the School of Electrical and Computer Engineering of NTUA and is supervised by the Hellenic Ministry of Education. Partner ICCS will participate I-SUPPORT with the “Intelligent Robotics and Automation Laboratory (IRAL)”, which was established in 1985 and covers teaching, research and development in Artificial Intelligence, Control, Automation, Robotics, Intelligent and Cognitive Systems. A part of IRAL is also the Computer Vision, Speech Communication and Signal Processing (CVSP) Research Group.

Role in I-SUPPORT:

  • ICCS will act as the Project‘s Scientific and Technical Manager.
  • ICCS will lead WP4 dealing with the control system design and implementation. A multi-layer control architecture will be designed that will endow sufficient intelligence to the I-SUPPORT platform to assist the elderly in the envisaged activities. Robot motion planning and control tasks, complex interaction of the soft-robot with the environment, as well the shared control for elderly assistance are challenging issues in I-SUPPORT that will be addressed by ICCS.More specifically ICCS will:
    • adapt machine learning schemes to address the challenges posed by soft-arm position and shape control, enabling motion and path planning of continuum robot manipulators with obstacle avoidance and global convergence properties.
    • extend impedance/admittance and hybrid force/position control schemes to endow a soft manipulator arm with actively adjustable and adaptive dynamic interaction properties, particularly taking into account the hyperredundant nature of such systems.
    • incorporate control strategies enabling robot reflexive behaviours, to properly and promptly react to sudden or unexpected human movements and/or events as well as for intuitive and effortless guiding of the assistive device (soft-arm).
    • incorporate novel schemes for learning of motion and action primitives, addressing the specific challenges of soft robot arms operating in physical interaction tasks involving deformable objects and dynamic environment attributes incorporate dynamic virtual fixtures schemes into novel user-robot collaboration strategies, which will fuse cognitive information ranging from low-level shaped impedance to higher-level context-awareness, aiming to adapt to the specific needs of the user and the targeted application requirements.
    • incorporate autonomous and semi-autonomous control modes, generating novel and challenging assistance behaviours that take into account human intention, as inferred from multimodal kinesthetic data, including human body / upper limbs motion and force interaction patterns.