Object-Sorting-by-Color in a Variety of Lighting Conditions Using Neural Networks and Lego Mindstorms Robot

Book One

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 21

Mobile Robot Competition and Exhibition Abstracts

Recognizing object color in a variety of lighting conditions is a challenging area of pattern-recognition. Neural networks have been found to be a good solution for that problem, and they are also quick and accurate, and can be used in real-time. We use a LEGO Mindstorms [1] robot to sort objects based on color in a variety of lighting conditions. We will start from simpler objects (LEGO pieces) and move onto more complex objects (apples, oranges, etc). This project is in progress and we hope to achieve classification accuracies of at least 90%.