…relational symbol grounding through affordance learning.

The problem of symbol grounding attempts to associate symbols from language with a corresponding referent in the environment. Traditionally, research has focused on identifying single objects and their properties. Similarly, affordances learning in robotics tend to focus on single objects. These approaches often do not consider the full context of the environment, which contains multiple different objects and their properties as well as relationships among the objects. Furthermore, the state of the environment (e.g., which relationships are true, etc.) affords (i.e., permits executing) certain actions. This project hypothesizes that the grounding process must consider the full context of the environment in order to perform symbol grounding and to better adapt to a new language and a new environment.

[metaslider id=473]
ReGround is a CHIST-ERA coordinated European project, which involves collaborators from Örebro University (Sweden), KU Leuven (Belgium), and Koç University (Turkey). In particular, the role of Örebro University, in this project, is to investigate how to establish the connections between multi-modal inputs (e.g., perception and language), and maintain such connections over time.  For this purpose, we rely on the notations presented in perceptual anchoring. Our aim for this project is to develop a novel approach, as well as a framework, for associating symbols (i.e., anchoring) with a large number of previously unknown referent objects that can occur in a new environment. The output of such framework will then provide the groundwork for relational symbol ground, action learning, as well as learning of object affordances.

Project web page: