Researchers have developed LiPUP-MA, a novel multi-agent framework designed to enhance participatory urban planning by incorporating simulated residential living experiences. This closed-loop system, LiPUP, iteratively adjusts urban plans based on feedback gathered from simulated residents, addressing challenges in grounding experiences and translating subjective input into actionable planning adjustments. The framework utilizes a Plan-centric Graph-based Experience Bank to organize feedback and a Spatially-constrained Skill-Augmented Planner agent to revise plans by integrating experiential, visual, and geospatial data. Experiments demonstrate LiPUP-MA's superior performance over existing methods in both static and living-based planning metrics. AI
IMPACT This framework could lead to more responsive and resident-centric urban development by integrating simulated lived experiences into the planning process.
RANK_REASON This is a research paper detailing a new AI framework for urban planning. [lever_c_demoted from research: ic=1 ai=1.0]
- Hang Ni
- LiPUP-MA
- Living-in-the-loop Participatory Urban Planning
- LLM-based agents
- Plan-centric Graph-based Experience Bank
- Spatiyally-constrained Skill-augmented Planner
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
