Situated Dialogue and Spatial Organization: What, Where… and Why?

Abstract

The paper presents an HRI architecture for human-augmented mapping, which has been implemented and tested on an autonomous mobile robotic platform. Through interaction with a human, the robot can augment its autonomously acquired metric map with qualitative information about locations and objects in the environment. The system implements various interaction strategies observed in independently performed Wizard-of-Oz studies. The paper discusses an ontology-based approach to multi-layered conceptual spatial mapping that provides a common ground for human-robot dialogue. This is achieved by combining acquired knowledge with innate conceptual commonsense knowledge in order to infer new knowledge. The architecture bridges the gap between the rich semantic representations of the meaning expressed by verbal utterances on the one hand and the robot's internal sensor-based world representation on the other. It is thus possible to establish references to spatial areas in a situated dialogue between a human and a robot about their environment. The resulting conceptual descriptions represent qualitative knowledge about locations in the environment that can serve as a basis for achieving a notion of situational awareness.

Conceptual spatial representations for indoor mobile robots

“…In [24] we present the cognitive architecture of our robotic system and give details on its dialogue capabilities. We furthermore discuss how these components are used for interactive map acquisition.…”

“…Because dialogues in human-robot interaction are inherently situated, the robot also tries to ground the utterance content in the situated context -including past and current visuo-spatial contexts (reification of visuo-spatial references), and future contexts (notably, planned events and states). Below we highlight several aspects; for more detail, we refer the reader to [22,24].…”

“…This significantly reduces the number of false positives. We additionally used the method presented in [46,24] for clarification dialogue to handle the few false doors that are still found. The disadvantage with this door detection scheme is that the robot is unable to detect doors where it has not traveled so far.…”

Semantic Labeling of Places with Mobile Robots

“…We additionally use a linguistic framework that actively supports the map acquisition process and is used for situated dialogue about the environment. More details about the dialog capabilities of the system are given in [Kruijff et al, 2007].…”

An Nlp-Based Approach for Improving Human-Robot Interaction

“…The use of spatial relations to ease humanrobot communication is investigated in [15]. Kruijff et al in [16] propose a multi-layered conceptual spatial mapping to provide a common ground for human-robot dialogues. In [17] Hasanuzzaman et al define a knowledge-based management system for person-centric gesture interpretation.…”