Incremental online learning of objects for robots operating in real environments
| Autor: | Jose L. Part, Oliver Lemon |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Artificial neural network
Computer science business.industry media_common.quotation_subject Cognitive neuroscience of visual object recognition Robotics 02 engineering and technology 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Convolutional neural network Adaptability Data modeling 0202 electrical engineering electronic engineering information engineering Robot 020201 artificial intelligence & image processing Artificial intelligence business Classifier (UML) computer 0105 earth and related environmental sciences media_common |
| Zdroj: | ICDL-EPIROB |
| Popis: | The ability of an object classifier to adapt to new data and incorporate new classes on the fly is of paramount importance for robots operating in the real world. This paper presents an approach for incremental online learning of real-world objects to be used by robots operating in real environments. We combined the representational power of Convolutional Neural Networks with the adaptability features of Self-Organizing Incremental Neural Networks. We evaluated our approach on the RGB-D Object Dataset in terms of classification accuracy and incremental learning of new classes. Our results show that whereas our method does not yet compete with the performance of state-of-the-art batch learning algorithms, it offers the important advantage of being able to adapt to new data and incorporate new classes on the fly. Finally, we aim at establishing a baseline on a publicly available dataset for comparing different approaches to realize online incremental learning in the context of robotics. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|