Trustworthiness Assessment of an Adaptive and Explainable Robot in a Real Environment
This study investigates how human-perceived trust, competence, willingness, and explainability interact in human-robot collaboration within a real museum setting. By testing an adaptive robot capable of adjusting its autonomy using a Theory of Mind model, the research evaluates how behavior explanations impact overall trustworthiness and the mediation effects of explanation evaluations. The findings demonstrate that perceived competence directly influences trustworthiness regardless of explanations, whereas the relationship between willingness and trustworthiness is mediated by the quality and interpretability of the robot's explanations.
Summary and content fields are drawn from the document text and are pending editorial review.
Who issued it
Who it governs
Researchers and developers in human-robot interaction seeking to understand how adaptive autonomy and explainability impact human trust.
What the document contains
The document covers an empirical experiment evaluating human trust, competence, willingness, and explainability in adaptive humanoid robots operating in a real museum environment. It details statistical path analysis examining how behavior explanations mediate trust dynamics.
The text contains no regulatory frameworks, legal compliance mandates, formal governance policies, or enforcement mechanisms.
- Robot competence directly predicts trustworthiness regardless of whether an explanation is provided.
- A robot's willingness to interact strongly influences the evaluation of its explanations, which fully mediates the relationship between willingness and trustworthiness.
- Explanations based on mental states (Theory of Mind) make robot behavior more understandable and acceptable to non-expert users.
- Users tend to evaluate an explanation positively when they comprehend and accept the logic behind the robot's task adoption strategy.
1 Introduction 2 Theoretical Background 3 Related Works 4 Experiment 5 Statistical Analysis 6 Results 7 Discussion 8 Conclusions
How it scores
Each score is backed by a quote verified against the document text. Editorial review has not yet confirmed them.
Accountability
0/5Clear responsibility for AI outcomes
N/A
screening score · 2026-10-24
Fairness
0/5Non-discrimination and equitable treatment
N/A
screening score · 2026-10-24
Human Dignity
0/5Respect for the inherent worth of persons
N/A
screening score · 2026-10-24
Human Oversight
2/5Humans remain in control of consequential decisions
In the study, the humanoid robot Nao played as a museum assistant, engaging with actual museum visitors. Visitors assigned the robot the task of guiding them
4 Experiment
screening score · 2026-10-24
Privacy
0/5Protection of personal data and private life
N/A
screening score · 2026-10-24
Transparency
3/5Openness about how AI systems work and are used
Specifically, it focuses on an adaptive robot capable of adopting a task delegated by the human at various autonomy levels and explaining the reasons behind its actions.
Abstract
screening score · 2026-10-24
Enforcement
0/5Consequences and compliance mechanisms with real force
N/A
screening score · 2026-10-24
Impact Assessment
0/5Required assessment of an AI system's risks/impacts before or during use
N/A
screening score · 2026-10-24