Home Grants
Home Grants
Towards a theoretical framework for learning multi-modal patterns for embodied agents
Year: 2009 Keywords: Multi-modal learning, regression theory, grasp classification
Authors: Nicoletta Noceti, B. Caputo, C. Castellini, L. Baldassarre, Annalisa Barla, Lorenzo Rosasco, Francesca Odone, G. Sandini  
Editor: Pasquale Foggia and Carlo Sansone and Mario Vento Volume: 5716
Series: Leacture Notes in Computer Science Pages: 239-248
Month: September
Multi-modality is a fundamental feature that characterizes biological systems and lets them achieve high robustness in understand- ing skills while coping with uncertainty. Relatively recent studies showed that multi-modal learning is a potentially e ective add-on to arti cial systems, allowing the transfer of information from one modality to an- other. In this paper we propose a general architecture for jointly learn- ing visual and motion patterns: by means of regression theory we model a mapping between the two sensorial modalities improving the perfor- mance of arti cial perceptive systems. We present promising results on a case study of grasp classi cation in a controlled setting and discuss future developments.
Digital version