SpatialLLM: From Multi-modality Data to Urban Spatial Intelligence
This provides a novel approach for urban intelligent analysis and management, though it is incremental as it adapts existing LLMs to a new domain.
The authors tackled the problem of performing spatial intelligence tasks in urban scenes without requiring geographic analysis tools or domain expertise, and achieved accurate zero-shot execution of tasks like urban planning and traffic management using pre-trained LLMs.
We propose SpatialLLM, a novel approach advancing spatial intelligence tasks in complex urban scenes. Unlike previous methods requiring geographic analysis tools or domain expertise, SpatialLLM is a unified language model directly addressing various spatial intelligence tasks without any training, fine-tuning, or expert intervention. The core of SpatialLLM lies in constructing detailed and structured scene descriptions from raw spatial data to prompt pre-trained LLMs for scene-based analysis. Extensive experiments show that, with our designs, pretrained LLMs can accurately perceive spatial distribution information and enable zero-shot execution of advanced spatial intelligence tasks, including urban planning, ecological analysis, traffic management, etc. We argue that multi-field knowledge, context length, and reasoning ability are key factors influencing LLM performances in urban analysis. We hope that SpatialLLM will provide a novel viable perspective for urban intelligent analysis and management. The code and dataset are available at https://github.com/WHU-USI3DV/SpatialLLM.