Ontology-Assisted Generalisation of Robot Action Execution Knowledge

TL;DR

This paper presents an ontology-based method for robots to generalise manipulation actions across different objects, enabling more adaptable and efficient execution policies by combining prior ontological knowledge with experiential refinement.

Contribution

It introduces a novel strategy that uses object ontologies to determine when robot action models can be generalized to new objects, reducing unnecessary learning.

Findings

The robot can successfully generalise grasping and stowing actions to related objects.

The approach reduces the need for additional learning when ontological similarity is sufficient.

The method effectively identifies cases requiring new execution knowledge.

Abstract

When an autonomous robot learns how to execute actions, it is of interest to know if and when the execution policy can be generalised to variations of the learning scenarios. This can inform the robot about the necessity of additional learning, as using incomplete or unsuitable policies can lead to execution failures. Generalisation is particularly relevant when a robot has to deal with a large variety of objects and in different contexts. In this paper, we propose and analyse a strategy for generalising parameterised execution models of manipulation actions over different objects based on an object ontology. In particular, a robot transfers a known execution model to objects of related classes according to the ontology, but only if there is no other evidence that the model may be unsuitable. This allows using ontological knowledge as prior information that is then refined by the robot's own experiences. We verify our algorithm for two actions - grasping and stowing everyday objects - such that we show that the robot can deduce cases in which an existing policy can generalise to other objects and when additional execution knowledge has to be acquired.