Enhancing autonomy transparency: an option-centric rationale approach

TL;DR

This paper introduces an option-centric rationale display to improve transparency in autonomous systems, leading to increased trust, faster trust calibration, and better task performance in a human-AI collaborative game.

Contribution

It proposes a novel rationale display approach and empirically demonstrates its effectiveness in enhancing trust and performance in autonomous systems.

Findings

Participants showed higher trust with the rationale display.

Faster trust calibration was observed.

Increased acceptance of AI recommendations and task performance.

Abstract

While the advances in artificial intelligence and machine learning empower a new generation of autonomous systems for assisting human performance, one major concern arises from the human factors perspective: Humans have difficulty deciphering autonomy-generated solutions and increasingly perceive autonomy as a mysterious black box. The lack of transparency contributes to the lack of trust in autonomy and sub-optimal team performance. To enhance autonomy transparency, this study proposed an option-centric rationale display and evaluated its effectiveness. We developed a game Treasure Hunter wherein a human uncovers a map for treasures with the help from an intelligent assistant, and conducted a human-in-the-loop experiment with 34 participants. Results indicated that by conveying the intelligent assistant's decision-making rationale via the option-centric rationale display, participants had higher trust in the system and calibrated their trust faster. Additionally, higher trust led to higher acceptance of recommendations from the intelligent assistant, and in turn higher task performance.