NVIDIA Partners Bring Physical AI and New Smart City Technologies to Dublin, Ho Chi Minh City, Raleigh and More

NVIDIA has expanded its smart city ecosystem by integrating physical AI, digital twins, and vision language models into urban infrastructure projects across the globe. Announced at the Smart City Expo World Congress, these partnerships aim to address the challenges of rapid urbanization, which is expected to add 2.5 billion people to cities by 2050. By leveraging the NVIDIA Blueprint for smart city AI, municipalities are deploying advanced traffic management and safety solutions to improve urban mobility and operational efficiency.

The NVIDIA Blueprint for smart city AI integrates digital twins with NVIDIA Omniverse libraries, synthetic data generation, and vision language models (VLMs) to create a streamlined workflow for real-time urban simulation and video analytics. This initiative comes as the smart traffic management market is projected to reach $20 billion by 2027, driven by the urgent need for sustainable public services in densifying urban centers. New updates to the platform include the NVIDIA Cosmos world foundation models, which provide physical reasoning capabilities and photorealistic synthetic data to train vision AI agents for complex tasks like video search and summarization.

In Raleigh, North Carolina, mapping firm Esri is collaborating with NVIDIA and Microsoft to develop an AI agent that visualizes camera data on interactive geospatial maps, helping city operators automate streetlight timing and reduce carbon emissions. Meanwhile, Milestone Systems is incorporating generative AI into its XProtect platform using NVIDIA Cosmos Reason VLMs, which were trained on 75,000 hours of traffic video. This technology is expected to reduce operator alarm fatigue by up to 30% by filtering false alarms, with pilot programs planned for Dubuque, Iowa, and Genoa, Italy.

Smart Dublin is utilizing Bentley Systems’ Cesium platform and NVIDIA Omniverse to analyze micromobility trends, integrating data from VivaCity’s AI-powered sensors to track cyclists and pedestrians. This setup has already allowed city officials to determine that weather conditions have a negligible impact on cycling volume while identifying high-risk road locations across the Irish capital. In Vietnam, Linker Vision is deploying the NVIDIA Blueprint in Ho Chi Minh City and Danang to monitor construction and traffic, building on previous success in Kaohsiung City where similar AI platforms reduced incident response times by 80%.