Industrial digital twins are helping shape the future of physical AI in manufacturing.🏭 At #NVIDIAGTC# Berlin, hear from the leaders bringing simulation, agentic AI, robotics, and autonomous systems from concept to the factory floor. Don't miss: 👉 Building Europe’s Industrial Future with NVIDIA’s Open Physical AI Platform 👉 Automation Meets Autonomy: Europe’s Next Era of Robotics - Agile Robots, @dexoryHQ, @wandelbots 👉 Building the Automotive Physical AI Playbook: Factory Robotics and Autonomous Vehicles - @MercedesBenz 🔗

From Digital Twins to Data Engine: Cutting the Real-Data Burden with Sim-Powered Robot Learning Teaching a robot a new task could take hundreds of teleoperated demonstrations. For foundation models, adapting to an entirely new robot can cost orders of magnitude more — dedicated hardware, trained operators, months of engineering. On @boosterobotics' dual-arm robot, we studied this at two levels: ✱ Specialist: Can task-aligned simulation mixed with a small set of real demonstrations reduce the real-data burden? ✅ Yes. With only 10 real demos, the policy made no contact at all in physical rollouts (0/20). Adding 50 simulated trajectories brought contact to 17/20. ✱ Foundation: Can data accumulated across tasks build a reusable starting point (a Booster-specific model prior)? ✅ Yes. After full-parameter continued pretraining, a model adapted with just 30 demonstrations per task beat the original given twice as many: 14/16 vs 10/16 in simulated evaluation. Before any task-specific adaptation, in zero-shot simulation, it was already roughly 3× closer to the target (17.27 cm → 5.78 cm). This work runs on Axis Suite, our Physical AI solution across different robot embodiments. Distributed contributors generate task-aligned sim data on Axis Hub at scale, reducing real-data needs for specialist adaptation while powering cross-embodiment generalist training. Read the full blog:

Simulating Humanity: 85% accurate digital twins, behavioral foundation models, social physics, & 8 billion agents @simile_ai CEO @joon_s_pk explains how AI can move from predicting what people will do to simulating how to shape outcomes, why today’s frontier models still miss how humans actually behave, how digital twins reproduced people with 85% accuracy, why human biases and mistakes have to be learned rather than optimized away, and what it would take to eventually simulate all 8 billion people on Earth.

CATERPILLAR PARTNERS WITH FIELDAI ON PHYSICAL AI $CAT is working with FieldAI to bring AI-powered autonomy and robotics into jobsites and factories, using Caterpillar’s operational data, FieldAI’s robot foundation models and NVIDIA technologies. Early applications include autonomous inspections, real-time digital twins, risk detection and AI-driven optimization of equipment and facility operations.

We asked HPE experts for their take on some of the hottest trends in tech. 🔥 From quantum to digital twins, here's one expert's take on what these technologies mean for the future of enterprise AI.

What if doctors could spot your next sports injury before it happens? Orthopedic Surgeon Dr. Andrew D. Pearle says digital twins, virtual models created from a patient's body, are starting to change orthopedic care. By simulating real-life movements, surgeons can compare treatment options and study how stress affects a patient's joints. Researchers believe the technology could eventually identify athletes who are more likely to suffer an ACL tear, giving doctors a chance to intervene before an injury even happens. @MorningsMaria @MariaBartiromo

.@SASsoftware is celebrating half a century of data and analytics leadership, trusted by 90%+ of the Fortune 500. With agentic AI, digital twins, and quantum computing ahead, the next 50 years look even brighter. Read the full @Nasdaq story here:

Lewis Hamilton recently pointed to a mismatch between simulation and reality as a major factor behind a challenging race weekend. It's a problem every systems engineer recognizes: how do you simulate a system operating at the edge of chaos? In our latest blog, we explore how Unconventional AI builds digital twins that faithfully model hardware operating in these highly sensitive regimes, capturing the physical and numerical effects that can significantly influence real-world performance. Read the full post: