Urban Generative Intelligence (UGI): A Foundational Platform for Agents in Embodied City Environment

TL;DR

This paper introduces Urban Generative Intelligence (UGI), a foundational platform that integrates Large Language Models into urban systems to create embodied agents for city management and simulation, advancing urban intelligence and complexity understanding.

Contribution

It presents a novel platform combining LLMs, city-specific data, and simulation environments to develop embodied agents for urban challenges, bridging technological capabilities and practical urban applications.

Findings

Development of CityGPT, a city-specific foundation model.

Creation of embodied agents for urban tasks.

Open platform enabling diverse urban agent applications.

Abstract

Urban environments, characterized by their complex, multi-layered networks encompassing physical, social, economic, and environmental dimensions, face significant challenges in the face of rapid urbanization. These challenges, ranging from traffic congestion and pollution to social inequality, call for advanced technological interventions. Recent developments in big data, artificial intelligence, urban computing, and digital twins have laid the groundwork for sophisticated city modeling and simulation. However, a gap persists between these technological capabilities and their practical implementation in addressing urban challenges in an systemic-intelligent way. This paper proposes Urban Generative Intelligence (UGI), a novel foundational platform integrating Large Language Models (LLMs) into urban systems to foster a new paradigm of urban intelligence. UGI leverages CityGPT, a foundation model trained on city-specific multi-source data, to create embodied agents for various urban tasks. These agents, operating within a textual urban environment emulated by city simulator and urban knowledge graph, interact through a natural language interface, offering an open platform for diverse intelligent and embodied agent development. This platform not only addresses specific urban issues but also simulates complex urban systems, providing a multidisciplinary approach to understand and manage urban complexity. This work signifies a transformative step in city science and urban intelligence, harnessing the power of LLMs to unravel and address the intricate dynamics of urban systems. The code repository with demonstrations will soon be released here https://github.com/tsinghua-fib-lab/UGI.