Nvidia launches open-source medical robotics simulation framework

Nvidia (NASDAQ: NVDA) has released the Medical Physics Simulation framework, a new open-source, GPU-accelerated capability within its Isaac for Healthcare platform designed to help medical robotics developers train and test robot behavior in virtual environments.

The framework allows developers to simulate anatomy-device interaction, generate synthetic training scenarios, and evaluate robot policies before physical hardware testing. It is built on Nvidia's CUDA, Warp, Newton, and Cosmos technologies and can run up to 8,192 parallel robot-training environments simultaneously. According to Nvidia, benchmarks show this parallel simulation capability reduced training time from over five hours to under two minutes.

The framework combines classical physics simulation with a generative AI physics simulation component called Cosmos-H Dreams, which models visual scene dynamics from procedural data. Because the framework is open source, developers can inspect, adapt, and build on it for their own devices and workflows.

Several medical device companies are already using the framework. CMR Surgical and Cambridge Consultants, part of Capgemini, are using Cosmos-H Dreams to generate patient-specific simulations for soft-tissue surgical procedures. CMR contributed nearly 500 hours of anonymized clinical data from its Versius Surgical Robotic System to the Open-H Embodiment open dataset.

"Open source models allow us to build on shared knowledge, accelerating responsible innovation and, ultimately, gives us the potential to deliver more consistent care and better outcomes for patients worldwide," said Chris Fryer, chief technology officer at CMR Surgical.

Johnson & Johnson MedTech is using the framework to build digital twins of its endoluminal Monarch platform for urology. XCath is applying it for endovascular autonomy policy training. Inner Logic is using it to produce synthetic data and in silico evidence to support regulatory pathways. Medtronic Structural Heart is exploring its use with simulated X-ray sensing for catheter navigation research.

The Medical Physics Simulation framework can be used independently or alongside other components of the Isaac for Healthcare stack, including digital twin pipelines and the Isaac Lab robot-learning framework.

You May Also Be Interested In

• ADARx Pharmaceuticals files for proposed IPO
• Alexander Dennis wins £57m Liverpool bus contract for 207 vehicles
• Novartis pelacarsen trial fails to meet primary endpoint