In this paper the problem of algorithms’ interoperability in the context of an intelligent child-robot interaction for special education is studied. Given a technically demanding intervention scenario designed by experts, the set of algo-rithms that needed to implement the scenario are defined explicitly. Following a test case implementation involving a NAO robot, a feasibility analysis of the al-gorithms’ synergy, with respect to the adopted architecture consisting of the ro-bot, its sensory modules and the timing performance of the incorporated algo-rithms is presented. The developed algorithms have been tested both in laboratory conditions as well as in a pilot study involving three children. The experiments reveal the hardware and software requirements for the implementation of such an intervention scenario with high intelligent child-robot interaction capabilities and highlight the need for an alternative system architecture.
G. K. Sidiropoulos, C. Bazinas, C. Lytridis, G. A. Papakostas, V. G. Kaburlasos, P. Kechayas, E. Kourampa, S.-R. Katsi, H. Karatsioras, “Synergy of intelligent algorithms for efficient child-robot interaction in special education: a feasibility study”, 11th International Conference on Robotics in Education (RiE), Bratislava, Slovakia, 30 September – 2 October 2020