Exploring Sidewalk Sheds in New York City through Chatbot Surveys and Human Computer Interaction

2026-01-30

AI Summary

This study addresses the lack of empirical research on how sidewalk awnings influence pedestrian visibility, storefront legibility, and walking behavior in urban planning. It proposes an interactive survey methodology that integrates generative AI with image annotation, uniquely coupling a large language model (Google Gemini-1.5-flash-001) with a street-view interface to elicit design perceptions and path-choice data from 25 participants through guided dialogue. Participants evaluated awning characteristics—including clearance height, column spacing, and color—under varying conditions. A logistic mixed-effects model was employed to analyze the responses. Findings reveal that awnings significantly impair pedestrians’ ability to identify ground-floor storefront entrances, and that both awning design and weather conditions jointly affect sidewalk route selection. The study offers empirical evidence and a scalable human-centered evaluation framework to inform regulations for temporary street infrastructure.

Technology Category

• Humans and AI: AI for Accessibility
• Planning, Routing, and Scheduling: Planning with Language Models
• Application Domains: Humanities & Computational Social Science

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Sidewalk sheds are a common feature of the streetscape in New York City, reflecting ongoing construction and maintenance activities. However, policymakers and local business owners have raised concerns about reduced storefront visibility and altered pedestrian navigation. Although sidewalk sheds are widely used for safety, their effects on pedestrian visibility and movement are not directly measured in current planning practices. To address this, we developed an AI-based chatbot survey that collects image-based annotations and route choices from pedestrians, linking these responses to specific shed design features, including clearance height, post spacing, and color. This AI chatbot survey integrates a large language model (e.g., Google's Gemini-1.5-flash-001 model) with an image-annotation interface, allowing users to interact with street images, mark visual elements, and provide structured feedback through guided dialogue. To explore pedestrian perceptions and behaviors, this paper conducts a grid-based analysis of entrance annotations and applies logistic mixed-effects modeling to assess sidewalk choice patterns. Analysis of the dataset (n = 25) shows that: (1) the presence of scaffolding significantly reduces pedestrians'ability to identify ground-floor retail entrances, and (2) variations in weather conditions and shed design features significantly influence sidewalk selection behavior. By integrating generative AI into urban research, this study demonstrates a novel method for evaluating sidewalk shed designs and provides empirical evidence to support adjustments to shed guidelines that improve the pedestrian experience without compromising safety.

Problem

• sidewalk sheds
• pedestrian visibility
• pedestrian navigation
• urban planning
• storefront visibility

Innovation

• AI chatbot survey
• generative AI
• image annotation
• human-computer interaction
• urban design evaluation