Extending Referring Expression Generation through shared knowledge about past Human-Robot collaborative activity

Abstract

Being able to refer to an object, a person, or a place in a non-ambiguous manner is a need when one has to achieve collaborative activities with a partner. This is the socalled Referring Expression Generation (REG) problem. While widely used for Human-Robot Interaction, state of the art approaches restrict its use to the current environment. We propose a novel extension to the REG which takes full advantage of the Human-Robot shared knowledge about past actions as additional information to generate Referring Expressions. We show that our approach is usable with a domain-independent ontology as a knowledge base and that it can also use a semantic representation of past activity to generate RE. We illustrate our method through simulated situations and discuss its efficiency and pertinence.

TOP-JAM: A bio-inspired topology-based model of joint attention for human-robot interaction

“…Consequently, active and reactive behavior should be conditioned not only to the robot's intrinsic goals, but also to those of other agents. This perspective taking ability is considered at all decisional levels, from situation assessment based on theory of mind skills ( [20,27]), to human-aware motion and task planning ( [31,4]) and to communication management ( [28]), among others. In addition, some works have dealt with more specific problems (e.g.…”