Technology Enhanced Learning Using Humanoid Robots

摘要: In this paper we present a mixture of technologies tailored for e-learning related to the Deep Learning, Sentiment Analysis, and Semantic Web domains, which have employed show four different use cases that validated in field Human-Robot Interaction. The approach has been designed using Zora, humanoid robot can be easily extended with new software behaviors. goal is make able engage users through natural language tasks. Using our (i) talk user understand their sentiments dedicated Analysis engine; (ii) answer open-dialog utterances by means Generative Conversational Agent; (iii) perform action commands leveraging defined Robot Action ontology utterances; (iv) detect objects handing convolutional neural networks trained on huge collection annotated objects. Each module more data information overall architectural design general, flexible, scalable expanded other components, thus enriching interaction human. Different applications within domains are foreseen: either trainer autonomously physical actions (e.g., rehabilitation centers) or it interact (performing simple tests even identifying emotions) according program developed teachers.