From Image Generation to Infrastructure Design: a Multi-agent Pipeline for Street Design Generation
This work addresses the need for efficient, data-light generative design tools in active transportation planning, offering an incremental improvement over existing AI-assisted methods.
The paper tackles the problem of generating realistic street-design scenarios for public engagement in transportation planning by introducing a multi-agent system that edits bicycle facilities directly on street-view imagery, demonstrating adaptation to diverse urban conditions with visually coherent results.
Realistic visual renderings of street-design scenarios are essential for public engagement in active transportation planning. Traditional approaches are labor-intensive, hindering collective deliberation and collaborative decision-making. While AI-assisted generative design shows transformative potential by enabling rapid creation of design scenarios, existing generative approaches typically require large amounts of domain-specific training data and struggle to enable precise spatial variations of design/configuration in complex street-view scenes. We introduce a multi-agent system that edits and redesigns bicycle facilities directly on real-world street-view imagery. The framework integrates lane localization, prompt optimization, design generation, and automated evaluation to synthesize realistic, contextually appropriate designs. Experiments across diverse urban scenarios demonstrate that the system can adapt to varying road geometries and environmental conditions, consistently yielding visually coherent and instruction-compliant results. This work establishes a foundation for applying multi-agent pipelines to transportation infrastructure planning and facility design.