NVIDIA announced Medical Physics Simulation, an open source GPU-accelerated framework that lets healthcare robotics deve
NVIDIA announced today the Medical Physics Simulation framework, a new open source GPU-accelerated capability within NVIDIA Isaac for Healthcare. The framework addresses a critical bottleneck in healthcare robotics development: obtaining the large amounts of varied data needed to train, test and improve robot behavior in real-world scenarios. Medical robotics developers face challenges because anatomy varies, instruments bend and slip, imaging can be incomplete, and rare edge cases do not appear on predictable schedules.
Medical Physics Simulation helps developers model anatomy-device interaction, generate hard-to-capture scenarios, test in silico, and train or evaluate robot policies before conducting hardware-heavy testing. The framework combines anatomy and medical device behavior with sensor simulation and robot learning to create reusable simulation environments instead of requiring developers to rebuild custom scenes for each workflow. This approach saves development time and accelerates time-to-market for innovations.
Open source is especially important in healthcare because teams require transparency into the data, models and weights that shape system behavior. Access to open models and weights enables developers to reproduce results, evaluate performance across different anatomies and scenarios, identify limitations and build evidence for regulatory review. The framework leverages NVIDIA CUDA and is part of Isaac for Healthcare, built on NVIDIA Warp, Newton and Cosmos technologies. It can run hundreds of parallel simulation environments simultaneously, helping teams explore more scenarios and identify failure modes earlier in development. Benchmarks show that eight thousand one hundred ninety-two robot-training environments running in parallel with GPU-native simulation cut training time from over five hours to under two minutes.
The framework combines classical physics simulation with generative AI physics simulation. Classical simulation models known physical rules such as device contact, friction and motion. NVIDIA Cosmos-H Dreams, a real-time generative AI physics simulation capability, helps model visual scene dynamics learned from procedural data. Developers can use these approaches together to build and test healthcare robotics systems in virtual environments before moving to physical prototypes and lab testing.
Medical robotics leaders are already applying simulation-driven development. CMR Surgical and Cambridge Consultants contributed nearly five hundred hours of anonymized clinical data from the Versius Surgical Robotic System to the Open-H Embodiment dataset, supporting procedures including cholecystectomy, prostatectomy, hernia repair and hysterectomy. Chris Fryer, chief technology officer at CMR Surgical, stated: 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.
Johnson and Johnson MedTech is using Medical Physics Simulation and a Cosmos-based foundation model to build digital twins of its endoluminal MONARCH platform for urology. XCath is using Medical Physics Simulation for endovascular autonomy policy training. Inner Logic is accelerating medical technology evolution with synthetic data and in silico evidence for regulatory pathways. Medtronic Structural Heart is exploring Medical Physics Simulation with simulated X-ray sensing for catheter navigation research.
Medical Physics Simulation functions as a modular capability within NVIDIA Isaac for Healthcare and can be used independently or alongside digital twin pipelines, medical sensor simulation, the NVIDIA Isaac Lab open robot-learning framework and NVIDIA open models and policies. Developers can explore the open source framework, review reference workflows and build simulation environments for their own devices, anatomies and healthcare robotics applications.