Affective Robotics For Wellbeing: A Scoping Review (2304.01902v1)

Abstract: Affective robotics research aims to better understand human social and emotional signals to improve human-robot interaction (HRI), and has been widely used during the last decade in multiple application fields. Past works have demonstrated, indeed, the potential of using affective robots (i.e., that can recognize, or interpret, or process, or simulate human affects) for healthcare applications, especially wellbeing. This paper systematically review the last decade (January 2013 - May 2022) of HRI literature to identify the main features of affective robotics for wellbeing. Specifically, we focused on the types of wellbeing goals affective robots addressed, their platforms, their shapes, their affective capabilities, and their autonomy in the surveyed studies. Based on this analysis, we list a set of recommendations that emerged, and we also present a research agenda to provide future directions to researchers in the field of affective robotics for wellbeing.

• The paper presents a scoping review of Human-Robot Interaction research on affective robotics for wellbeing from 2013-2022, identifying key trends and applications.
• Affective robots for wellbeing are primarily used for mental support, frequently employing humanoid platforms like Nao and Pepper, with capabilities focused on emotional expression.
• Recommendations include using autonomous humanoid robots for physical tasks, matching robot shape to function, and developing robots with full affective perception and expression.

This scoping review, "Affective Robotics For Wellbeing: A Scoping Review" (2304.01902), examines the utilization of affective robots in promoting wellbeing, drawing from Human-Robot Interaction (HRI) literature published between January 2013 and May 2022.

Key Findings:

• Affective robots are applied in both mental (emotional support, cognitive stimulation, mindfulness) and physical wellbeing (physical stimulation, food promotion, fall detection). A greater emphasis was observed on mental wellbeing applications.
• Various robotic platforms are used, with Nao and Pepper being the most frequently employed. Bio-inspired robot shapes, especially humanoid forms, are predominant.
• Affective capabilities are mainly geared towards expressive behaviors, such as facial expressions and emotional movements. Emotion recognition and semantic understanding are gaining traction but are less common.
• Most studies involve autonomous or semi-autonomous robots, with a growing trend towards increased autonomy.

Methodology:

• The paper employed a scoping literature review, adhering to the PRISMA schema to mitigate bias.
• Databases including ACM Digital Library, IEEE Explore, and Scopus were searched using a defined search query based on the SPIDER framework.
• Inclusion and exclusion criteria were established based on engineering guidelines for paper selection.
• Data extraction involved the assignment of variables to research questions, focusing on the robot's goal, platform, shape, affective capabilities, and autonomy. Data was categorized as either categorical or qualitative, with qualitative data undergoing pattern-based analysis to identify key themes.

Contributions:

• The review offers a comprehensive overview of the last decade of HRI research in affective robotics for wellbeing.
• The authors propose recommendations for future research:
  • Employ autonomous humanoid robots for physical exercises.
  • Select robot shapes based on functionalities.
  • Equip robots with both expression and affect detection capabilities.
  • Move towards autonomous affective robots.
• The paper identifies a research agenda for advancing the affective robotics field in promoting wellbeing:
  • Investigating optimal robot forms for specific tasks.
  • Focusing on empirical studies involving robots with a complete range of affective capabilities.
  • Addressing technological limitations to enable the use of autonomous robots.