ฝัง
- เผยแพร่เมื่อ 11 ก.ย. 2024
- We're pleased to share our research combining crowd simulation with generative AI to control individual agents, pushing the boundaries of replicating human behavior in complex scenarios.
This research opens new avenues for urban planning, security management, disaster response, public health, and training. We are excited about the potential of LLMs to revolutionize crowd simulation and deepen our understanding of human behavior in complex scenarios.
𝐅𝐫𝐚𝐦𝐞𝐰𝐨𝐫𝐤
Our architectural framework integrates 6 modules, i.e., advanced persona, perception, memory, planning, action, and reflection, to emulate human-like behavior in dynamic environments. The design uses the dual-process theory of cognition, which distinguishes between two modes thinking: Fast and instinctive versus Cautious and analytical.
The framework allows agents to process, store, and retrieve information efficiently, enabling adaptive and realistic decision-making. By incorporating higher-level reflections and adaptive planning, the system enhances the agents' ability to interact coherently and effectively within complex simulations.
The 𝐏𝐞𝐫𝐬𝐨𝐧𝐚 module ensures diverse agent behavior by combining three profiling methods: manual creation, automatic generation via prompts, and dataset alignment.
The 𝐏𝐞𝐫𝐜𝐞𝐩𝐭𝐢𝐨𝐧 module enables agents to understand and interact with their environment by processing textual inputs and spatial information in real-time.
The 𝐌𝐞𝐦𝐨𝐫𝐲 module allows agents to reason about past and current experiences to improve future decision-making.
The 𝐏𝐥𝐚𝐧𝐧𝐢𝐧𝐠 module empowers agents with human-like planning and decision-making capabilities, incorporating long-term planning, task decomposition, and immediate planning to navigate both immediate circumstances and long-term objectives.
The 𝐀𝐜𝐭𝐢𝐨𝐧 module translates agents' decisions into specific outcomes by connecting to the game engine’s goal-setting functions, facilitating tasks such as communication, environment navigation, and task completion without physical manipulation.
The 𝐑𝐞𝐟𝐥𝐞𝐜𝐭𝐢𝐨𝐧 module enables agents to process vast amounts of observational data by generating higher-level inferences and insights, filtering out noise, and facilitating well-informed decision-making.
𝐍𝐞𝐱𝐭 𝐬𝐭𝐞𝐩𝐬
While our engine can handle 0.5M agents in real-time on a modern PC or 1M+ in the cloud, the video showed a capability demonstrator in SimCrowds / @Unity with at most 500 agents. We intend to scale this up to a city with 1M+ real-time agents based on realistic personas, and scale in quality.
𝐂𝐚𝐥𝐥 𝐭𝐨 𝐚𝐜𝐭𝐢𝐨𝐧
Are you working on a digital twin application that needs a realistic pattern-of-life (PoL) simulation, a synthetic single world that needs intelligent crowds, a research project that can use our contributions, or powerful visualizations of corresponding crowds, please don’t hesitate to contact us.
Let's collaborate and bring your vision to life!
#Crowd #Simulation #GenerativeAI #PatternsOfLife #LLM #SimCrowds #Digitaltwins
Research credits: Nizar Ntarouis (MSc student AI at Utrecht University) and the uCrowds team.
Music credits: Inari by Tigerblood Jewel. Source: www.epidemicso...
