Learning grasping affordance using probabilistic and ontological approaches

Download PDF
Open Webpage

Carl Barck-Holst, Maria Ralph, Fredrik Holmar, Danica Kragic

Published: 2009, Last Modified: 15 Jan 2026ICAR 2009EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: We present two approaches to modeling affordance relations between objects, actions and effects. The first approach we present focuses on a probabilistic approach which uses a voting function to learn which objects afford which types of grasps. We compare the success rate of this approach to a second approach which uses an ontological reasoning engine for learning affordances. Our second approach employs a rule-based system with axioms to reason on grasp selection for a given object.