作者: Chri Lang , Marc Hanheide , Manja Lohse , Heiko Wersing , Gerhard Sagerer
DOI: 10.1109/ROMAN.2009.5326199
关键词: Human–computer interaction 、 Artificial intelligence 、 Robot 、 Context (language use) 、 Facial expression 、 Term (time) 、 Computer science 、 Nonverbal communication 、 Human–robot interaction 、 Interpretation (philosophy) 、 Conversation 、 Computer vision
摘要: In everyday conversation besides speech people also communicate by means of nonverbal cues. Facial expressions are one important cue, as they can provide useful information about the conversation, for instance, whether interlocutor seems to understand or appears be puzzled. Similarly, in human-robot interaction facial give feedback situation. We present a Wizard Oz user study an object-teaching scenario where subjects showed several objects robot and taught objects' names. Afterward, should term correctly. first evaluation, we let other watch short video sequences this study. They decided looking at face human answer was correct (unproblematic situation) incorrect (problematic situation). conducted experiments under specific conditions varying amount temporal visual context compare results with related described literature.