Perceiving, Generating, and Interpreting Affect in Human-Robot Interaction (HRI)

Over the past few years, there has been a growing presence of robots in our daily lives, leading to more frequent interactions between robots and humans, who possess emotions. Establishing and maintaining trust and mutual adaptation during such human-robot interactions (HRI) requires an affective approach to building a positive social relationship between human interactors and robots, as well as showcasing social-emotional competence. Effective HRI systems require a robot's social intelligence and relationship with humans to be designed in a way that influences the outcomes, such as acceptance of the robot's recommendations. Other social-emotional interaction strategies include a range of external human-like behaviors and internal capabilities, such as recognition of gestures, facial expressions, emotions, dimensions of affect, mental health, and personality traits.

This Research Topic aims to bring together interdisciplinary researchers from fields, including human-robot interaction, affective computing, emotion recognition, deep learning, and healthcare communities. Some key research questions that we would like to address include, but are not limited to:
● How to perceive unimodal or multimodal affective human behavior adaptively/accurately in HRI?
● How to efficiently generate natural and affective robot behavior in HRI?
● How to advantageously facilitate human users’ mental and physical well-being with affective HRI applications?

In collaboration with the workshop series on affective human-robot interaction (AHRI) at the International Conference on Affective Computing and Intelligent Interaction (ACII), this Research Topic focuses on the social-emotional dimension of human-robot interaction and collaboration. We welcome workshop participants and external contributions alike. If you are submitting an extended version of your workshop papers, please include at least 30% new content. Topics of interest include but are not limited to:

• Affective and emotion-aware human-robot interaction
• Contextual factors in human-robot interaction and collaboration in-the-wild
• Graph Neural Networks for human behavior understanding
• Graph representation learning for human behavior understanding
• Theory of mind and imitation learning in empathic robots
• Multimodal emotion recognition in-the-wild
• Microexpression recognition and generation
• Robust affect and personality recognition
• Verbal/nonverbal emotional behavior generation for robots and intelligent agents
• Affection for human-robot trust and transparency
• Affective and social intelligence in healthcare and elderly care robot
• Artificial emotions in robots and intelligent agents
• Personalized and adaptive robots in longitudinal interaction
• Ethical considerations of affective systems and robotic applications