R. Billingsley

D. B. Skillicorn, R. Billingsley, M. -A. Williams

We consider the design space available for social robots in terms of a hierarchy of functional definitions: the essential properties in terms of a locus of interaction, autonomy, intelligence, awareness of humans as possessors of mental state, and awareness of humans as social interactors. We also suggest that the emphasis on physical embodiment in some segments of the social robotics community has obscured commonalities with a class of agents that are identical in all other respects. These definitions naturally suggest research issues, directions, and possibilities which we explore. Social robotics also lacks compelling 'killer apps' which we suggest would help focus the community on a research agenda.

D. B. Skillicorn, N. Alsadhan, R. Billingsley et al.

Social robots need to understand the affective state of the humans with whom they interact. Successful interactions require understanding mood and emotion in the short term, and personality and attitudes over longer periods. Social robots should also be able to infer the desires, wishes, and preferences of humans without being explicitly told. We investigate how effectively affective state can be inferred from corpora in which documents are plausible surrogates for what a robot might hear. For mood, emotions, wishes, desires, and attitudes we show highly ranked documents; for personality dimensions, estimates of ground truth are available and we report performance accuracy. The results are surprisingly strong given the limited information in short documents.