NVIDIA Partners Accelerate Smart City AI Deployments Across Global Urban Centers

With an estimated 2.5 billion more people expected to live in urban areas by 2050, cities worldwide face an urgent need for sustainable planning and improved public services. Artificial intelligence (AI) is emerging as a critical tool to meet these demands, particularly in areas like traffic management, which is projected to become a $20 billion market by 2027.

NVIDIA is at the forefront of this transformation, showcasing its expanding ecosystem of physical AI partners at the Smart City Expo World Congress (SCEWC) in Barcelona this week. Companies like Bentley Systems, Deloitte, Esri, Linker Vision, and Milestone Systems are demonstrating cutting-edge applications designed to enhance public spaces, transit, and city operations.

The core of these advancements is the NVIDIA Blueprint for smart city AI, initially unveiled at NVIDIA GTC Paris. This comprehensive framework integrates digital twins with NVIDIA Omniverse libraries, synthetic data generation, AI model training with vision language models (VLMs), and video analytics AI agents utilizing the NVIDIA Blueprint for video search and summarization (VSS).

This streamlined workflow facilitates rapid simulation of real-world urban conditions, seamless sensor integration, and real-time vision AI capabilities. Recent updates to the blueprint include new NVIDIA Cosmos world foundation models and VLMs, which generate photorealistic synthetic data and provide advanced physical reasoning.

These enhancements, alongside the latest VSS blueprint (part of the NVIDIA Metropolis platform), empower developers to train and build sophisticated vision AI agents and applications. NVIDIA also offers new cookbooks for Cosmos Predict, Cosmos Transfer, and Cosmos Reason, providing step-by-step intelligent traffic system workflows.

Several leading companies are actively implementing NVIDIA technologies to bring secure, scalable physical AI to various global cities, tackling challenges ranging from aging infrastructure to traffic congestion and climate resilience.

Mapping and spatial analytics leader Esri is collaborating with NVIDIA to develop an AI agent for the City of Raleigh, North Carolina. This agent processes vast camera data, generating real-time alerts and insights visualized on an interactive geospatial map.

This system enables city operators to swiftly address issues, optimize traffic flows, and improve infrastructure design, ultimately boosting urban mobility. By leveraging the NVIDIA Blueprint, Raleigh can discover and manipulate data to automate streetlight timing and reduce carbon emissions from traffic congestion.

Milestone Systems is introducing generative AI into its XProtect video management platform. Powered by NVIDIA Cosmos Reason VLMs—trained with 75,000 hours of compliant traffic video—this innovation allows users to easily extract valuable analyses and insights from video streams, review alerts, and automatically generate reports.

These specialized VLMs will also be offered as-a-service to developers, with general availability expected later this year. The new, GDPR-compliant features can reduce operator alarm fatigue by up to 30%, automating video review and filtering out false alarms. Cities like Dubuque, Iowa, and Genoa, Italy, are planning to adopt these advanced video intelligence solutions.

Linker Vision, an early adopter of the end-to-end NVIDIA Blueprint for smart city AI, is deploying physical AI solutions in Ho Chi Minh City and Danang, Vietnam. Building on its success in Kaohsiung City, Taiwan, where its vision AI platform cut incident response times by 80%, Linker Vision is leveraging AVES Reality’s 3D digital twins via NVIDIA Omniverse.

This enables city-scale AI solutions capable of simulating and monitoring traffic and construction activities. The goal is to ensure projects stay on schedule while significantly improving urban mobility and operational efficiency.

Ireland’s Smart Dublin organization is utilizing physical AI to tackle urban challenges, tapping into Cesium, a 3D geospatial platform from Bentley Systems, and NVIDIA Omniverse. This collaboration enables real-time data visualization and analysis for micromobility—such as walking, cycling, and scooter usage—across the city.

Additionally, AI transportation technology company VivaCity uses NVIDIA Jetson and Metropolis platforms on its AI-powered computer vision sensors. These sensors provide Dublin with highly accurate, multimodal data on road users, helping to understand traffic patterns, identify dangerous sites, and improve road safety.

Smart Dublin is also integrating AI agents into a digital twin for faster insights and alerts. Initial steps include visualizing bike route utilization with VivaCity data in a Cesium-powered digital twin, with future plans for natural language search features. Furthermore, Bentley’s AI technology Blyncsy employs NVIDIA Cosmos and Metropolis for generating synthetic data to analyze road conditions and enhance maintenance efforts.

Deloitte is harnessing AI to automate street inspections across thousands of crosswalks for city transportation departments. This initiative aims to bolster protection for vulnerable roadway users, including pedestrians and bikers.

Using Cosmos Predict, Deloitte converts static intersection images into photorealistic, physically accurate videos. Cosmos Transfer then generates videos simulating various real-world scenarios like fog, rain, snow, and low light. Finally, Cosmos Reason evaluates these videos to identify potential areas for improvement, making the inspection process insightful and dynamic.

The extensive NVIDIA ecosystem supporting these smart city deployments includes hardware and software partners such as AAEON, Advantech, Aetina, Dell Technologies, HPE, OpenZeka, and YUAN High Technologies. Many of these partners are exhibiting physical AI demos at SCEWC, running on NVIDIA RTX PRO Servers, NVIDIA DGX Spark (the world’s smallest AI supercomputer), and NVIDIA Jetson Thor modules.

Other notable projects include Akila’s physical AI technologies in Monaco-Monte-Carlo train stations and its digital twin solutions for the University Mohammed VI Polytechnic campus in Morocco. K2K is also demonstrating its real-time analytics solution, leveraging NVIDIA Cosmos Reason and the VSS blueprint to optimize roadway safety, traffic, and waste management.

These innovations highlight the collective effort to bring city-scale AI and urban innovation to life. Interested parties can learn more by joining NVIDIA and its partners at SCEWC and sign up for notifications when the NVIDIA Blueprint for smart city AI becomes broadly available.