In this paper we rely upon the concept of Spatio-Temporal Affordances (STA) to formalize the objective function to learn affordance descriptors. Such a function allows to better encode action semantics related to the environment. We qualitatively evaluate obtained results over the learned spatial model for two different tasks.
Using Spatio-Temporal Affordances to Represent Robot Action Semantics / Riccio, Francesco; Capobianco, Roberto; Nardi, Daniele. - (2016), pp. -------. (Intervento presentato al convegno Machine Learning Methods for High-Level Cognitive Capabilities in Robotics (Workshop at IROS) tenutosi a Daejeon, South Korea nel 14 October 2016).
Using Spatio-Temporal Affordances to Represent Robot Action Semantics
RICCIO, FRANCESCO;CAPOBIANCO, ROBERTO;NARDI, Daniele
2016
Abstract
In this paper we rely upon the concept of Spatio-Temporal Affordances (STA) to formalize the objective function to learn affordance descriptors. Such a function allows to better encode action semantics related to the environment. We qualitatively evaluate obtained results over the learned spatial model for two different tasks.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
