CMR Surgical has joined an NVIDIA-led initiative centred on advancing the artificial intelligence (AI) capabilities of surgical robots.
The British surgical robotics company announced that it is contributing the ‘majority’ of surgical data used to create Nvidia’s Open-H – an open source large language model (LLM) dataset for healthcare robotics. It is hoped that this will act as a data repository for training the next generation of intelligent surgical systems.
Open-H is comprised of real-world surgical video, robotic telemetry and multimodal data from healthcare and robotics organisations. According to CMR, the company has contributed almost 500 hours of anonymised surgical data from its Versius surgical robot, representing the largest share of surgical data a part of the initiative.
Open‑H underpins Isaac GR00T‑H, an open vision‑language‑action model, a type of AI foundation model that combines computer vision, natural language processing, and robotic control into a single, open-source system. Nvidia says the technology is designed to enable robotic systems to “better interpret complex surgical environments and tasks". The tech giant believes the platform can accelerate the development of intelligent robotic systems while maintaining safety and regulatory standards.
CMR Surgical’s chief technology officer, Chris Fryer, commented: “Surgical robotics generates a rich understanding of how procedures are performed. By contributing real‑world surgical data to collaborative initiatives like Open‑H, we are helping build the foundations for the next generation of intelligent surgical systems.
“Our focus is on technologies that support surgeons and expand access to minimally invasive surgery. Combining clinical data with advances in AI and simulation creates a powerful opportunity to accelerate innovation responsibly.”
Nvidia’s plans for AI and robotics
Nvidia’s CEO, Jensen Huang, announced the Open-H initiative, which also features participation from companies including Hexagon Robotics, KUKA, and Medtronic, at the tech giant’s Nvidia GTC conference, taking place in California from 16 to 19 March.
“Physical AI has arrived – every industrial company will become a robotics company,” Huang said. During his presentation, Huang revealed that Nvidia has other initiatives in motion for the advancement of robotics in other fields such in ‘humanoid’ robots that perform packing and sorting functions in factories and warehouses.
Robotics, alongside medical imaging, remains one of the key application areas for AI in healthcare. According to a report by GlobalData, the combined AI market across healthcare was valued at $11.9bn in 2024 and is expected to reach a valuation of $57.4bn in 2029.
Huang’s remarks around AI’s application in surgical robotics strike a similar tone to previous comments he made on the tech’s impact in the medical imaging space.
Speaking at the 2024 J.P. Morgan Healthcare conference, Huang said: “Ultrasound systems, computed tomography (CT) scan systems, all kinds of instruments – they’re always going to be a device plus a whole bunch of AIs.”
