Towards a multimodal topic tracking system for a mobile robot

Topics in situated and task oriented communication depend heavily on the given, often changing environment, making the detection of predetermined topics in many cases useless. Detection of non-predefined topics can enhance Human-Robot-Interaction (HRI) in a variety of ways, though. In this paper we propose a way to dynamically determine topics during Human-Robot-Communication using well established techniques such as Latent Semantic Analysis (LSA). The procedure is based on multimodal cues, supporting the view that topics are not simply a property of spoken or written language, but of multimodal situated communication. An online version of the topic detection system has been developed and is currently being tested on our mobile robot BIRON. To demonstrate the feasibility of our approach, we present the results of an evaluation of our system on the BITT corpus.