NVIDIA and Partners Drive Smart City Innovation with Advanced Physical AI Across Global Urban Centers

As global urban populations are projected to swell by 2.5 billion people by 2050, the urgent demand for sustainable urban planning and enhanced public services has never been greater. Artificial intelligence (AI) is emerging as a critical tool to meet these needs, with the smart traffic management market alone expected to reach $20 billion by 2027.

This week, at the Smart City Expo World Congress (SCEWC) in Barcelona, NVIDIA and its expanding ecosystem of partners—including Bentley Systems, Deloitte, Esri, Linker Vision, and Milestone Systems—are showcasing their latest advancements in physical AI. These innovations are designed to enhance public spaces, transit systems, and city operations across several global cities.

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

This streamlined workflow facilitates rapid simulation of real-world urban conditions, extensive sensor integration, and real-time vision AI. Recent enhancements to the blueprint include new NVIDIA Cosmos world foundation models and VLMs, which generate photorealistic synthetic data and provide physical reasoning capabilities. Additionally, the latest version of the VSS blueprint—a component of the NVIDIA Metropolis platform—is accelerating the development of vision AI agents and applications. Developers can now access step-by-step intelligent traffic system workflows and technical recipes through new cookbooks for NVIDIA Cosmos Predict, NVIDIA Cosmos Transfer, and NVIDIA Cosmos Reason.

Solving the complex challenges of urban growth, from traffic and climate resilience to real-time safety, demands a seamless fusion of next-generation AI, cloud, edge computing, ultrafast networking, and open data platforms. NVIDIA's global partner ecosystem is rising to this challenge, bringing scalable AI solutions to fruition.

Mapping and spatial analytics leader Esri is collaborating with NVIDIA to develop an AI agent for the City of Raleigh, North Carolina. This agent ingests, analyzes, and visualizes vast amounts of camera data, generating real-time alerts and insights displayed on an interactive geospatial map. This empowers city operators to swiftly respond to issues, optimize traffic flows, and refine infrastructure design, ultimately boosting urban mobility and reducing carbon emissions.

Milestone Systems is integrating generative AI into its XProtect video management platform, leveraging NVIDIA Cosmos Reason VLMs post-trained with 75,000 hours of compliant traffic video. This enables users to effortlessly extract valuable insights from video streams, review alerts, and automatically generate reports. Milestone will also offer these specialized VLMs-as-a-service, with general availability expected later this year, promising to reduce operator alarm fatigue by up to 30% in cities like Dubuque, Iowa, and Genoa, Italy.

Linker Vision is a frontrunner in deploying the end-to-end NVIDIA Blueprint for smart city AI in Ho Chi Minh City and Danang, Vietnam. Building on its success in Kaohsiung City, Taiwan, where its vision AI platform reduced incident response times by up to 80%, Linker Vision is using AVES Reality’s simulation-ready 3D digital twins, powered by NVIDIA Omniverse, to simulate and monitor traffic and construction activities, ensuring projects stay on schedule and improving urban efficiency.

Ireland’s Smart Dublin organization is leveraging Cesium, Bentley Systems’ 3D geospatial platform, and NVIDIA Omniverse for real-time data visualization and analysis of micromobility (walking, cycling, scooters) across the city. Additionally, AI transportation technology company VivaCity utilizes NVIDIA Jetson and Metropolis platforms on its AI-powered computer vision sensors to provide Dublin with highly accurate multimodal data on road users. This data helps understand traffic patterns, identify dangerous sites, and improve road safety. Future plans include integrating AI agents into a digital twin for faster insights, such as natural language search capabilities. Bentley's AI technology Blyncsy also uses NVIDIA Cosmos and Metropolis to generate synthetic data for analyzing road conditions and improving maintenance.

Deloitte is applying AI to automate street inspections for city transportation departments, focusing on protecting vulnerable roadway users. Using Cosmos Predict, Deloitte converts static intersection images into photorealistic, physically accurate videos. Cosmos Transfer then generates videos across various real-world scenarios, including fog, rain, snow, and low light. Finally, Cosmos Reason helps evaluate these videos to identify potential areas for improvement, making the inspection process insightful and dynamic.

The widespread adoption of these smart city deployments is supported by NVIDIA's extensive ecosystem of hardware and software partners, including AAEON, Advantech, Aetina, Dell Technologies, HPE, OpenZeka, and YUAN High Technologies. Many of these partners are showcasing physical AI demos running on NVIDIA RTX PRO Servers, NVIDIA DGX Spark, and NVIDIA Jetson Thor modules at SCEWC.

Further innovations 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, which utilizes NVIDIA Cosmos Reason and the VSS blueprint to optimize roadway safety, traffic, and waste management. These advancements underscore a collective commitment to building smarter, safer, and more sustainable cities for the future.