Robots as Mental Well-being Coaches: Design and Ethical Recommendations

TL;DR

This paper tackles the lack of cohesive guidelines for robotic coaches aimed at promoting mental well-being. It adopts a three-study, user-centered design approach, employing Thematic Analysis and a qualitative meta-analysis to distill design and ethical guidelines from diverse perspectives including prospective users and professional coaches. The primary contributions are a cohesive set of design guidelines (covering form, voice, turn-taking, adaptation, and safety) and a structured ethical framework addressing consent, safeguarding, and transparency. The findings offer practical guidance for researchers and roboticists to build more effective, respectful, and privacy-conscious robotic well-being coaches, while also highlighting gaps related to longitudinal use, cultural diversity, and vulnerable populations that warrant future work.

Abstract

The last decade has shown a growing interest in robots as well-being coaches. However, insightful guidelines for the design of robots as coaches to promote mental well-being have not yet been proposed. This paper details design and ethical recommendations based on a qualitative analysis drawing on a grounded theory approach, which was conducted with a three-step iterative design process which included user-centered design studies involving robotic well-being coaches, namely: (1) a user-centred design study conducted with 11 participants consisting of both prospective users who had participated in a Brief Solution-Focused Practice study with a human coach, as well as coaches of different disciplines, (2) semi-structured individual interview data gathered from 20 participants attending a Positive Psychology intervention study with the robotic well-being coach Pepper, and (3) a user-centred design study conducted with 3 participants of the Positive Psychology study as well as 2 relevant well-being coaches. After conducting a thematic analysis and a qualitative analysis, we collated the data gathered into convergent and divergent themes, and we distilled from those results a set of design guidelines and ethical considerations. Our findings can inform researchers and roboticists on the key aspects to take into account when designing robotic mental well-being coaches.

Figures (9)

• Figure 1: Results of participant votes using the Miro board to indicate what would stop them from using the robotic well-being coach. Originally published in axelsson2021participatory.
• Figure 2: Results of participants' ranking robot embodiment for well-being coaching (discussion group of four participants, each having their own colour). While Pepper was preferred by this group, Miro and Jibo were also preferred by some, indicating that preferences vary across individuals. Originally published in axelsson2021participatory.
• Figure 3: Study 1: Themes defined in the TA are presented in orange, while codes related to these themes are presented in blue, and sub-codes are presented in yellow (best viewed in colour), from axelsson2021participatory.
• Figure 4: Participant and Pepper interacting with each other.
• Figure 5: Study 2: Themes defined in the TA are presented in orange, while codes related to these themes are presented in blue (best viewed in colour).