What Is My Robot Thinking? Design Considerations for Transparent and Trustworthy Shared Autonomy

2026-06-04

AI Summary

This study addresses the challenge of misaligned goals and eroded trust in shared autonomy assistive robots, stemming from the opacity of robot intent inference. To enhance intention alignment and user trust, the authors manipulate interface transparency through feedback modality and informational richness in a visually mediated shared autonomy system. Findings reveal that goal readability is critical for effective collaboration, while trust is best supported by task-appropriate disclosure rather than maximal information. User experiments indicate a preference for visual feedback and demonstrate that optimal information density dynamically varies with task complexity. Notably, full disclosure of belief distributions does not consistently improve performance. Building on these insights, the work proposes design principles for transparent shared autonomy systems that balance informativeness with usability.

Abstract

Assistive robots operating under shared autonomy must balance user control with autonomous assistance. Because robot actions depend on internal intent inference that is not directly observable, mismatches between inferred and intended goals can undermine coordination and trust. We investigate how interface-level transparency, including feedback modality (visual vs. auditory) and information richness (sparse vs. rich), shapes interaction in a vision-based shared autonomy system. In a user study with N=25 participants across two assistive manipulation tasks, we evaluate how these designs influence coordination and trust. Providing feedback significantly improves intent alignment and reduces corrective intervention, indicating that making the inferred goal legible accelerates convergence in shared control. Participants preferred visual over auditory feedback, while preferences for sparse versus rich information depended on task complexity. We also found that revealing the full belief distribution did not consistently improve alignment or trust. Together, these findings indicate that effective transparency enhances coordination primarily through goal legibility, while trust depends on task-appropriate information exposure rather than maximal disclosure. Based on these results, we outline guidelines for designing transparent shared autonomy systems.

Problem

• shared autonomy
• transparency
• trust
• intent alignment
• human-robot interaction

Innovation

• shared autonomy
• transparency
• intent alignment
• human-robot interaction
• trust