Affective human-robot interaction is still an active area of research in part due to the great advances in artificial intelligence. Now, the design of autonomous devices that work in real therapeutic environments has become a plausible reality. Affective human-robot interaction requires a robot to analyze the emotional state of the human interlocutor and interpret emotional responses that can be used, not merely in the interaction but, for example, to provoke desired therapeutic responses. It is, therefore, necessary to broaden experimental techniques into more realistic paradigms, where the capacity of emotion estimation can be completely explored. This exploratory paper proposes a realistic experimental paradigm in which the robot employs a dramatic story to evoke emotions in the users, and tests previously self-designed methodologies to be able to make estimates of the users’ emotional state in real-time. Regardless of the multiple impediments and restrictions, and all the aspects that could still be improved, this paper can outline the feasibility of the proposed methodology in realistic scenarios.

Affective human-robot interaction requires lightweight software and cheap wearable devices that could further this field. However, the estimation of emotions in real-time poses a problem that has not yet been optimized. An optimization is proposed for the emotion estimation methodology including artifact removal, feature extraction, feature smoothing, and brain pattern classification. The challenge of filtering artifacts and extracting features, while reducing processing time and maintaining high accuracy results, is attempted in this work. First, two different approaches for real-time electro-oculographic artifact removal techniques are tested and compared in terms of loss of information and processing time. Second, an emotion estimation methodology is proposed based on a set of stable and meaningful features, a carefully chosen set of electrodes, and the smoothing of the feature space. The methodology has proved to perform on real-time constraints while maintaining high accuracy on emotion estimation on the SEED database, both under subject dependent and subject independent paradigms, to test the methodology on a discrete emotional model with three affective states.