Can AR-Embedded Visualizations Foster Appropriate Reliance on AI in Spatial Decision Making? A Comparative Study of AR See-Through vs. 2D Minimap

2025-07-18

AI Summary

In high-stakes, time-critical spatial decision-making (e.g., emergency evacuation), AI recommendations presented on 2D maps impose excessive cognitive load and foster inappropriate reliance. This study investigates how embedded visualization modalities affect human-AI collaborative judgment by comparing augmented reality (AR) see-through displays against conventional 2D mini-maps in a simulated crisis environment integrating indoor sensing and AI. Results demonstrate that AR significantly enhances spatial mapping and egocentric mental imagery; however, perceptual challenges and visual illusions induce heightened overtrust—specifically, inappropriate acceptance of erroneous AI suggestions. These findings challenge the assumption that immersive visualization inherently improves human-AI collaboration. To our knowledge, this is the first empirical evidence that AR may exacerbate dependence bias under high-pressure spatial reasoning tasks. The work provides critical implications for designing trustworthy AI interfaces, highlighting both risks of unmitigated AR deployment and new directions for mitigating overreliance through perceptually informed interface optimization.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

In high-stakes, time-critical scenarios-such as emergency evacuation, first responder prioritization, and crisis management -- decision-makers must rapidly choose among spatial targets, such as exits, individuals to assist, or areas to secure. Advances in indoor sensing and artificial intelligence (AI) can support these decisions by visualizing real-time situational data and AI suggestions on 2D maps. However, mentally mapping this information onto real-world spaces imposes significant cognitive load. This load can impair users' ability to appropriately judge AI suggestions, leading to inappropriate reliance (e.g., accepting wrong AI suggestions or rejecting correct ones). Embedded visualizations in Augmented Reality (AR), by directly overlaying information onto physical environments, may reduce this load and foster more deliberate, appropriate reliance on AI. But is this true? In this work, we conducted an empirical study (N = 32) comparing AR see-through (embedded visualization) and 2D Minimap in time-critical, AI-assisted spatial target selection tasks. Contrary to our expectations, users exhibited greater inappropriate reliance on AI in the AR condition. Our analysis further reveals that this is primarily due to over-reliance, with factors specific to embedded visualizations, such as perceptual challenges, visual proximity illusions, and highly realistic visual representations. Nonetheless, embedded visualizations demonstrated notable benefits in spatial reasoning, such as spatial mapping and egocentric spatial imagery. We conclude by discussing the empirical insights, deriving design implications, and outlining important directions for future research on human-AI decision collaboration in AR.

Problem

• Evaluates AR's impact on AI reliance in spatial decisions
• Compares AR see-through vs 2D minimap visualization effectiveness
• Identifies causes of over-reliance in AR embedded visualizations

Innovation

• AR-embedded visualizations reduce cognitive load
• Comparative study of AR see-through vs 2D Minimap
• Analyzed over-reliance factors in AR visualizations