Information Technology Reference
In-Depth Information
Natural Language Interpretation for an Interactive
Service Robot in Domestic Domains
Stefan Schiffer, Niklas Hoppe, and Gerhard Lakemeyer
Knowledge-Based Systems Group, RWTH Aachen University, Aachen, Germany
niklas.hoppe@rwth-aachen.de,
{
schiffer,gerhard
}
@cs.rwth-aachen.de
Abstract.
In this paper, we propose a flexible system for robust natural language
interpretation of spoken commands on a mobile robot in domestic service robotics
applications. Existing language processing for instructing a mobile robot is often
restricted by using a simple grammar where precisely pre-defined utterances are
directly mapped to system calls. These approaches do not regard fallibility of hu-
man users and they only allow for binary processing of an utterance; either a com-
mand is part of the grammar and hence understood correctly, or it is not part of
the grammar and gets rejected. We model the language processing as an interpre-
tation process where the utterance needs to be mapped to the robot's capabilities.
We do so by casting the processing as a (decision-theoretic) planning problem
on interpretation actions. This allows for a flexible system that can resolve am-
biguities and which is also capable of initiating steps to achieve clarification. We
show how we evaluated several versions of the system with multiple utterances
of different complexity as well as with incomplete and erroneous requests.
Keywords:
Natural
Language
Processing,
Interpretation,
Decision-theoretic
Planning, Domestic Service Robotics, RoboCup@Home.
1
Introduction
In this paper we present a system for flexible command interpretation to facilitate nat-
ural human-robot interaction in a domestic service robotics (DSR) domain. We partic-
ularly target the
General Purpose Service Robot
test from the RoboCup@Home com-
petition [21], where a robot is confronted with ambiguous and/or faulty user inputs in
form of natural spoken language. The main goal of our approach is to provide a system
capable of resolving these ambiguities and of interactively achieving user satisfaction
in the form of doing the right thing, even in the face of incomplete, ill-formed, or faulty
commands.
We model the processing of natural spoken language input as an interpretation
process. More precisely, we first analyse the given utterance syntactically by using a
grammar. Then, we cast the interpretation as a planning problem where the individual
actions available to the planner are to interpret syntactical elements of the utterance. If,
in the course of interpreting, ambiguities are detected, the system uses decision-theory
to weigh different alternatives. The system is also able to initiate clarification to resolve
ambiguities and to handle errors as to arrive at a successful command interpretation
