Enrich Humanoids With Large Language Models (LLM)

Abstract

Human-like social robots (or humanoids) such as Softbank's NAO<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">6</sup>, have been proven valuable assistants, able to advance State-of-the-Art of Technology in Education and Learning (TEL) as they are quite impressive “clones” of human behavior, and due to their relatable form, are often perceived as superior social companions. The rise of accessible Large Language Models and cloud computing, could transform robots like NAO<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">6</sup> - a rather obsolete robot with quite low computing capacity (Pentium CPU, 2–4 GB RAM)- into a capable social agent, able to adopt A.I. behavior. In the current paper, we present a solution to enrich Softbank NAO<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">6</sup> with A.I. capacity, in order to act as an LLM vessel. Specifically, we managed to connect an augmented AI chatbot to NAO<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">6</sup> by deploying corresponding Python APIs. In our showcase, a NAO<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">6</sup> acts as the ancient Greek Philosopher Plato that “guides the one who seeks wisdom” based on his theory. Our solution has been evaluated in real crowded settings as a proof-of-concept. Next steps involve to evaluate our solution in school classrooms.