A Comparative Study of Rule-Based and AI-Based Educational Robots for Vision-Based Waste Sorting

Abstract

The integration of educational robots in pre-university education provides valuable opportunities for developing technical and computational thinking skills. This study analyses the use of LEGO Mindstorms robots and artificial intelligence robots from the NextLab.tech platform for recognising and manipulating objects of different colours, aiming to simulate an automated sorting system for waste with identical shapes. The research focuses on the design and validation of a robotic system capable of object classification using rule-based deterministic methods and Machine Learning algorithms, integrated into a pick-and-place mechanism. System performance is evaluated using indicators such as classification accuracy, error rate, sorting time, productivity, and efficiency. The results enable a comparison between the two approaches and highlight the advantages of integrating computer vision into robotic control. The study also emphasises the role of these technologies in transitioning towards the active use of robots in applied educational processes.