Contributo in atti di convegno, 2020, ENG, 10.1109/RO-MAN47096.2020.9223605

A Two-Layered Approach to Adaptive Dialogues for Robotic Assistance

De Benedictis R.; Umbrico A.; Fracasso F.; Cortellessa G.; Orlandini A.; Cesta A.

National Research Council of Italy, ISTC-CNR - Institute of Cognitive Sciences and Technologies, Italy

Socially assistive robots should provide users with personalized assistance within a wide range of scenarios such as hospitals, home or social settings and private houses. Different people may have different needs both at the cognitive/physical support level and in relation to the preferences of interaction. Consequently the typology of tasks and the way the assistance is delivered can change according to the person with whom the robot is interacting. The authors' long-term research goal is the realization of an advanced cognitive system able to support multiple assistive scenarios with adaptations over time. We here show how the integration of model-based and model-free AI technologies can contextualize robot assistive behaviors and dynamically decide what to do (assistive plan) and how to do it (assistive plan execution), according to the different features and needs of assisted persons. Although the approach is general, the paper specifically focuses on the synthesis of personalized therapies for (cognitive) stimulation of users.

29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), pp. 82–89, 31/08/2020 - 04/09/2020

Keywords

Personalized interaction, User modeling, Automated planning, Reactive reasoning

CNR authors

Cortellessa Gabriella, Orlandini Andrea, Fracasso Francesca, De Benedictis Riccardo, Umbrico Alessandro, Cesta Amedeo

CNR institutes

ISTC – Istituto di scienze e tecnologie della cognizione