How can I help you? Comparing engagement classification strategies for a robot bartender (2013)
| Citations: | 6 - 6 self |
BibTeX
@MISC{Foster13howcan,
author = {Mary Ellen Foster and Andre Gaschler and Manuel Giuliani},
title = {How can I help you? Comparing engagement classification strategies for a robot bartender},
year = {2013}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
A robot agent existing in the physical world must be able to under-stand the social states of the human users it interacts with in order to respond appropriately. We compared two implemented methods for estimating the engagement state of customers for a robot bartender based on low-level sensor data: a rule-based version derived from the analysis of human behaviour in real bars, and a trained version using supervised learning on a labelled multimodal corpus. We first compared the two implementations using cross-validation on real sensor data and found that nearly all classifier types significantly outperformed the rule-based classifier. We also carried out feature selection to see which sensor features were the most informative for the classification task, and found that the position of the head and hands were relevant, but that the torso orientation was not. Finally, we performed a user study comparing the ability of the two clas-sifiers to detect the intended user engagement of actual customers of the robot bartender; this study found that the trained classifier was faster at detecting initial intended user engagement, but that the rule-based classifier was more stable.
Keyphrases
robot bartender engagement classification strategy rule-based classifier user engagement physical world human user real bar human behaviour social state labelled multimodal corpus implemented method classification task torso orientation rule-based version robot agent actual customer real sensor data sensor feature low-level sensor data engagement state trained version trained classifier feature selection user study
