A New Knowledge Primitive of Digits Recognition for NAO Robot Using MNIST Dataset and CNN Algorithm for Children’s Visual Learning Enhancement

Aim/Purpose: Our study is focused on prototyping, development, testing, and deployment of a new knowledge primitive for the humanoid robot assistant NAO, in order to enhance student visual learning by establishing a human-robot interaction. Background: This new primitive, utilizing a convolutional neural network (CNN), enables real-time recognition of handwritten digits captured by the NAO robot, a humanoid robot assistant developed by SoftBank Robotics. It is equipped with advanced capabilities, including a wide range of sensors, cameras, and interactive features. By integrating the proposed primitive, the NAO robot gains the ability to accurately recognize handwritten digits, contributing to improved student visual learning experiences. Methodology: Our developed primitive consists of the use of a convolutional neural network (CNN) so that the robot is able to recognize the handwriting of the digits present in the input image received in real-time. The NAO robot establishes interaction with the learners through a scenario based on a predefined assignment. In this scenario, NAO captures the digit handwritten by the learner via its camera, recognizes the digit using the deep learning model generated by the MNIST dataset, and announces to the learner the handwritten digit in the input image. The prototype is realized using the concept of a distributed system allowing the distribution of tasks in four different computing nodes. Contribution: Our research makes a significant contribution by equipping the humanoid robot NAO with a cognitive intelligence system through the integration of a new knowledge primitive based on handwriting digit recognition (HWDR). Our approach used to create and implement this primitive in the NAO robot is interesting and innovative, and presents a promising provision for enhancing the visual learning experience of children and young students with special needs, based on the use of distributed systems that divide the work using various components distributed over several nodes, coordinating their efforts to perform tasks more efficiently than a single device besides the NAO robot. Findings: We designed our model using specific parameters and a fully convolutional neural network architecture, which includes three residual depthwise separable convolutions, each followed by batch normalization and ReLU activation. To evaluate the performance of our model, we tested it on the MNIST dataset, where we achieved a remarkable accuracy, F1 sc