Contribution: Jiong Sun, et al.

Categories of touch: Classifying human touch using a soft tactile sensor

Jiong Sun1, Erik Billing1, Fernando Seoane2, Bo Zhou3, Dan Högberg4 and Paul Hemeren1
1School of Informatics, 4School of Engineering Science, University of Skövde Box 408, 541 28, Skövde, Sweden
2Swedish School of Textiles, University of Borås, 501 90, Borås, Sweden; Inst. for Clinical Science, Intervention and Technology, Karolinska Institutet, 14186 Stockholm, Sweden; Dept. Biomedical Engineering, Karolinska University Hospital, 14186 Stockholm, Sweden
3German Research Center for Artificial Intelligence Trippstadter Strasse 122, D-67663 Kaiserslautern, Germany

Social touch plays an important role not only in human communication but also in human-robot interaction. We here report results from an ongoing study on affective human-robot interaction. In our previous research, touch type is shown to be informative for communicated emotion. Here, a soft matrix array sensor is used to capture the tactile interaction between human and robot and a method based on PCA and kNN is applied in the experiment to classify different touch types, constituting a pre-stage to recognizing emotional tactile interaction. Results show an average recognition rate for classified touch type of 71%, with a large variability between different types of touch. Results are discussed in relation to affective HRI and social robotics.