From Planning Data to Decision Support: Applied AI for Rule-Based Urban Development in Early Stages
| Reference number | |
| Coordinator | Parametric Solutions AB |
| Funding from Vinnova | SEK 3 499 000 |
| Project duration | April 2026 - April 2028 |
| Status | Ongoing |
| Venture | Advanced digitalization - Industrial needs-driven innovation |
| Call | Industrial applied AI by advanced digitalization 2026 |
Purpose and goal
The project aims to develop an AI-based decision support that enables an automated transition from unstructured plan data to decision-making data in the early stages of urban planning. The goal is to combine AI interpretation of detailed plans with generative 3D modeling so that plan-compliant development alternatives can be generated and evaluated within minutes instead of weeks. The solution will support architects, property developers and municipalities with human-in-the-loop.
Expected effects and result
The project delivers a verified method for AI-based interpretation of detailed plans into machine-readable constraints, a connection to Hektar´s generative engine and an agent-based decision support via MCP that reasons around regulatory requirements, geometry and user intentions. The effect is shorter lead times, more analyzed alternatives and better informed decisions in early stages. The results are commercialized through Hektar AI´s established user base.
Planned approach and implementation
The project is being implemented over 24 months by Parametric Solutions AB and Insikt, with support by an external reference group. The work is being carried out agilely in four work packages: AP1 requirements analysis and method design, AP2 AI-baserad interpretation of plans, AP3 agent-based decision and integration in Hektar, and AP4 validation and utilization. Iterative deliveries, workshops and continuous testing in real project with Swedish municipalities and actors ensure anchoring.