Ceci N'est Pas un Drone: Investigating the Impact of Design Representation on Design Decision Making When Using GenAI

2025-11-05

AI Summary

This study investigates how different design representation modalities—visual renderings, numerical performance data, and their combination—affect designers’ ability to select optimal drone concepts generated by AI. Method: A controlled experiment was conducted to compare selection accuracy and preference patterns across these modalities. Contribution/Results: Contrary to conventional reliance on visual cues, designers achieved the highest accuracy in identifying optimal solutions when provided with numerical performance data alone. Furthermore, a strong, statistically significant preference for axially symmetric外观 emerged, indicating implicit bias from visual conventions that compromises objective evaluation. This work provides the first empirical evidence of the superiority of numerical representations in AI-assisted design assessment, challenging entrenched visual-centric paradigms. It yields critical cognitive insights and actionable interface design implications for enhancing human-AI co-design workflows, particularly in early-stage generative design evaluation.

Technology Category

• Knowledge Representation and Reasoning: Preferences
• Humans and AI: Learning Human Values and Preferences
• Search and Optimization: Evaluation and Analysis

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

With generative AI-powered design tools, designers and engineers can efficiently generate large numbers of design ideas. However, efficient exploration of these ideas requires designers to select a smaller group of potential solutions for further development. Therefore, the ability to judge and evaluate designs is critical for the successful use of generative design tools. Different design representation modalities can potentially affect designers'judgments. This work investigates how different design modalities, including visual rendering, numerical performance data, and a combination of both, affect designers'design selections from AI-generated design concepts for Uncrewed Aerial Vehicles. We found that different design modalities do affect designers'choices. Unexpectedly, we found that providing only numerical design performance data can lead to the best ability to select optimal designs. We also found that participants prefer visually conventional designs with axis-symmetry. The findings of this work provide insights into the interaction between human users and generative design systems.

Problem

• Investigating how design representation modalities affect designer decision-making
• Examining impact of visual vs numerical data on AI-generated concept selection
• Determining optimal information presentation for evaluating generative design outputs

Innovation

• Numerical performance data enhances optimal design selection
• Combined visual and numerical modalities influence designer choices
• Visual conventionality with axis-symmetry affects designer preference