Comparing Robot and Human guided Personalization: Adaptive Exercise Robots are Perceived as more Competent and Trustworthy

This academic paper investigates the effects of different levels of automation in socially assistive robots during physical exercise sessions by comparing an adaptive robot using online preference learning with an adaptable robot directly controlled by the user. The authors conducted a between-subject study with 40 participants, evaluating the impact of these personalization mechanisms on perceived competence, warmth, trust in the alliance, and user motivation. The findings indicate that users evaluate adaptive robots as significantly more competent and warm, report a higher working alliance, and that perceived competence statistically mediates this improved alliance.

Summary and content fields are drawn from the document text and are pending editorial review.

1 Introduction
2 Adaptation, Automation and Alliance
3 System Design
4 Study Design
5 Results
6 Discussion
7 Conclusion