A Minimalistic Approach to User Group Adaptation of Robot Behaviors using Movement and Speech Analysis

Speech characteristics have shown potential as a tool to identify personality factors in humans but usually demands longer interactions or elaborate sensor requirements. This paper presents a novel robot system that uses speech and body movement characteristics to recognize and distinguish between users-groups interacting with it through small sets of interactions. It clusters people with similar characteristics together and measures the affective impact of specific robot behaviors. The system was tested using a custom-created affective robot through 36 interactions with 6 human participants aging from 11 to 70. 186 samples were collected in two different physical contexts and the similarity of the samples for each user was compared. The preliminary results indicate that the speech and movement characteristics have the potential as a tool to recognize specific users and as a guide to form user groups. This was found using only basic sensors available in most robots through a limited set of interactions. The results further highlight that there are significant differences between measurements for the same users in different physical contexts meaning that the participants move and talk differently with each context. This paper suggests combining the speech and movement characteristics with information on the physical context to gain better user adaptation in robot behaviors for future projects.