We consider object recognition in the context oflifelong learning, where a robotic agent learns to discriminate between a growing number of object classes as it accumulates experience about the environment. We propose an incremental variant of the Regularized Least Squares for Classification(RLSC) algorithm, and exploit its structure to seamlessly addnew classes to the learned model. The presented algorithm addresses the problem of having an unbalanced proportion oftraining examples per class, which occurs when new objectsare presented to the system for the first time.We evaluate our algorithm on both a machine learning benchmark dataset and two challenging object recognition tasks in a robotic setting. Empirical evidence shows that our approach achieves comparable or higher classification performance than its batch counterpart when classes are unbalanced, while being significantly faster.

Incremental robot learning of new objects with fixed update time

CAMORIANO, RAFFAELLO;Giulia Pasquale;Carlo Ciliberto;Lorenzo Rosasco;Giorgio Metta
2017

Abstract

We consider object recognition in the context oflifelong learning, where a robotic agent learns to discriminate between a growing number of object classes as it accumulates experience about the environment. We propose an incremental variant of the Regularized Least Squares for Classification(RLSC) algorithm, and exploit its structure to seamlessly addnew classes to the learned model. The presented algorithm addresses the problem of having an unbalanced proportion oftraining examples per class, which occurs when new objectsare presented to the system for the first time.We evaluate our algorithm on both a machine learning benchmark dataset and two challenging object recognition tasks in a robotic setting. Empirical evidence shows that our approach achieves comparable or higher classification performance than its batch counterpart when classes are unbalanced, while being significantly faster.
File in questo prodotto:
File Dimensione Formato  
Incremental Robot.pdf

accesso aperto

Tipologia: Documento in Post-print
Dimensione 1.33 MB
Formato Adobe PDF
1.33 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11567/888637
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact