StreetDesignAI: A Multi-Persona Evaluation System for Inclusive Infrastructure Design

2026-01-22

AI Summary

This study addresses the lack of inclusivity in urban cycling infrastructure design, which often stems from conflicting needs among diverse user groups—such as cautious versus confident cyclists. To tackle this challenge, we propose the first interactive evaluation system that integrates multi-agent simulation with an explicit conflict representation mechanism, using “disagreement” as a fundamental interaction primitive. Built upon street-level imagery and GIS data, the system enables designers to receive real-time, parallel feedback from simulated cyclist personas and visually explore perspective conflicts during iterative design. By combining computer vision, multi-agent modeling, and an interactive interface, our approach shifts design thinking from single-perspective optimization toward inclusive trade-off reasoning. A user study with 26 transportation professionals demonstrated that the tool significantly enhances their understanding of diverse user needs, improves conflict identification, and boosts design confidence, yielding high satisfaction and strong willingness to adopt.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Designing inclusive cycling infrastructure requires balancing competing needs of diverse user groups, yet designers often struggle to anticipate how different cyclists experience the same street. We investigate how persona-based multi-agent evaluation can support inclusive design by making experiential conflicts explicit. We present StreetDesignAI, an interactive system that enables designers to (1) ground evaluation in street context through imagery and map data, (2) receive parallel feedback from cyclist personas spanning confident to cautious users, and (3) iteratively modify designs while surfacing conflicts across perspectives. A within-subjects study with 26 transportation professionals demonstrates that structured multi-perspective feedback significantly improves designers'understanding of diverse user perspectives, ability to identify persona needs, and confidence in translating them into design decisions, with higher satisfaction and stronger intention for professional adoption. Qualitative findings reveal how conflict surfacing transforms design exploration from single-perspective optimization toward deliberate trade-off reasoning. We discuss implications for AI tools that scaffold inclusive design through disagreement as an interaction primitive.

Problem

• inclusive design
• cycling infrastructure
• user personas
• experiential conflict
• multi-perspective evaluation

Innovation

• multi-persona evaluation
• inclusive design
• conflict surfacing
• AI-assisted design
• transportation infrastructure