Evaluation of a Robot Navigator's Explanations
Raj Korpan, Daniel Tiourine, Sami Chen, Susan L. Epstein · 2025
To achieve trust and acceptance from people, robots that navigate complex human environments should be able to explain their behavior. In an online between-subjects study, this paper explores the impact of explanation detail on human understanding, trust, and comfort with robot navigators. It compares three conditions: no textual information, a simple action description, and a detailed explanation. Results indicate that while detailed explanations improve users' confidence in the robot's navigation ability, simpler descriptions are easier to understand. Participants who received detailed explanations, however, also indicated a better overall understanding of the robot's behavior and decision-making process. These findings highlight how varied levels of detail in explanations can build trust and comprehension.