An educational robot system of visual question answering for preschoolers

Abstract

The educational robotics is a novel technology for preschooler's companion and can be used for lower level education. This paper presents an AI-based robot system for achieving educational aims, such as metacognition tutoring and geometrical thinking training, with characteristics of contextual teaching by mining knowledge from the real world directly. For metacognition tutoring in our system, objects in real world are detected and a set of learning materials associated with the objects is presented for learners. For example, when a cat is detected, the robot will teach learners to pronounce the “Cat” in different languages, and more knowledge about cat will be pushed to the learners. For geometrical thinking training, an automatic questioning-and-answering section is employed to engage the learner to think, which is carried by a voice interaction between learners and robots. In our experiment, a set of specific object images are captured to validate the feasibility and efficiency of the proposed system. Our study indicated that the proposed system succeeded in captivating the children and parents in maximizing the children's desire to explore.