The preprint of These Aren’t The Droids You Are Looking for: Promises and Challenges for the Intersection of Affective Science and Robotics/AI, Kappas & Gratch is out today.
AI research focused on interactions with humans, particularly in the form of robots or virtual agents, has expanded in the last two decades to include concepts related to afective processes. Afective computing is an emerging feld that deals with issues such as how the diagnosis of afective states of users can be used to improve such interactions, also with a view to demonstrate afective behavior towards the user. This type of research often is based on two beliefs: (1) artifcial emotional intelligence will improve human computer interaction (or more specifcally human robot interaction), and (2) we understand the role of afective behavior in human interaction sufciently to tell artifcial systems what to do. However, within affective science the focus of research is often to test a particular assumption, such as “smiles afect liking.” Such focus does not provide the information necessary to synthesize afective behavior in long dynamic and real-time interactions. In consequence, theories do not play a large role in the development of artifcial afective systems by engineers, but self-learning systems develop their behavior out of large corpora of recorded interactions. The status quo is characterized by measurement issues, theoretical lacunae regarding prevalence and functions of afective behavior in interaction, and underpowered studies that cannot provide the solid empirical foundation for further theoretical developments. This contribution will highlight some of these challenges and point towards next steps to create a rapprochement between engineers and afective scientists with a view to improving theory and solid applications.
Keywords Robotics · Afective computing · Human robot interaction · Artifcial intelligence
Kappas, A., Gratch, J. These Aren’t The Droids You Are Looking for: Promises and Challenges for the Intersection of Affective Science and Robotics/AI. Affec Sci (2023). https://doi.org/10.1007/s42761-023-00211-3