From Commands to Goal-Based Dialogs: A Roadmap to Achieve Natural Language Interaction in RoboCup@Home

Abstract

On the one hand, speech is a key aspect to people's communication. On the other, it is widely acknowledged that language proficiency is related to intelligence. Therefore, intelligent robots should be able to understand, at least, people's orders within their application domain. These insights are not new in RoboCup@Home, but we lack of a long-term plan to evaluate this approach. In this paper we conduct a brief review of the achievements on automated speech recognition and natural language understanding in RoboCup@Home. Furthermore, we discuss main challenges to tackle in spoken human-robot interaction within the scope of this competition. Finally, we contribute by presenting a pipelined road map to engender research in the area of natural language understanding applied to domestic service robotics.

Trends, Challenges and Adopted Strategies in RoboCup@Home

“…Nonetheless, quite often informative services also make good press to the robots. Moreover, sometimes their 6 The generation and use of a corpus for HRI in RoboCup@Home has been proposed and is discussed in [23]. optimism harms what they are trying to exalt, raising expectations beyond what robots can actually do today.…”

“…The most broadly adopted solution to deal with speech consists in a pipeline in which a filtered audio signal feeds an Automatic Speech Recognition (ASR) engine to get a texttranscript for further processing. Then, the transcript is sent to a Natural Language Processing (NLP) unit that extracts all Figure 3: Trends in Automatic Speech Recognition relevant information that is passed to a high-level task planner that triggers the pertinent behaviors [29,30].…”

“…A key aspect to people's communication, speech in Robo-Cup@Home is mostly restricted to issuing commands to robots [2,29]. These commands are generated using grammars given in advance to teams under noise conditions which are far from those found in domestic environments [2,29]. Further, experts take part in all interactions, meaning that the way to address a robot is not entirely natural [2,29].…”

“…An thorough study, available in [29], was conducted addressing these troubling aspects in spoken HRI, followed by a roadmap and a set of strategies to tackle them and foster dialog-based natural language interactions in RoboCup@Home.…”

“…The generation and use of a corpus for HRI in RoboCup@Home has been proposed and is discussed in[23].…”