From sensors to sense: Integrated heterogeneous ontologies for Natural Language Generation

Abstract

We propose the combination of a robotics ontology (KnowRob) with a linguistically motivated one (GUM) under the upper ontology DUL. We use the DUL Event, Situation, Description pattern to formalize reasoning techniques to convert between a robot's beliefstate and its linguistic utterances. We plan to employ these techniques to equip robots with a reason-aloud ability, through which they can explain their actions as they perform them, in natural language, at a level of granularity appropriate to the user, their query and the context at hand.

Curiously exploring affordance spaces of a pouring task

“…In parallel work we have started to investigate how the understanding of qualitative terms (e.g., 'elastic' or 'heavy') could be done in more functional terms, that is, in terms of how such qualities influence behaviour, rather than only as grounded in some distribution Pomarlan, Righetti, and Bateman (2022) as well as how functional rules in terms of image schemas can be used to guide action selection Pomarlan, Hedblom, et al (2022). A next step would now be to investigate how this more functional understanding can guide the process of adjusting the probability distributions in a more robust way such that regularities in the possible ways of performing a task are uncovered.…”