What is Open-H-Embodiment?<\/h2>\n\n\n\n
Open-H-Embodiment<\/strong> is a community-driven initiative focused on building a shared, open dataset for training and evaluating AI models in medical robotics. The project centers on so-called Physical AI\u2014intelligent systems that can act in real-world environments, for example by supporting surgical robots or ultrasound systems.<\/p>\n\n\n\n The initiative was launched through collaboration between leading experts: Prof. Axel Krieger<\/strong> (Johns Hopkins University), Prof. Nassir Navab<\/strong> (Technical University of Munich), and Dr. Mahdi Azizian<\/strong> (NVIDIA). It has since expanded to include 35 international organizations spanning academia, industry, and healthcare.<\/p>\n\n\n\n Participating institutions include Balgrist, CMR Surgical, The Chinese University of Hong Kong, Great Bay University, Hong Kong Baptist University, Hamlyn, ImFusion, Johns Hopkins University, University of Leeds, Mohamed bin Zayed University of Artificial Intelligence, Moon Surgical, NVIDIA, Northwell Health, \u00d3buda University, The Hong Kong Polytechnic University, Qilu Hospital of Shandong University, Rob Surgical, Sano \u2013 Centre for Computational Personalised Medicine International Research Foundation, Surgical Data Science Collective, Semaphor Surgical, Stanford University, TU Dresden, Technical University of Munich, Tuodao, University of Turin, University of British Columbia, UC Berkeley, UC San Diego, University of Illinois Chicago, University of Tennessee, University of Texas, Vanderbilt University, and Virtual Incision.<\/p>\n\n\n\n Together, the consortium has compiled over 770 hours of CC-BY-4.0 healthcare robotics training data\u2014primarily from surgical robotics, but also including ultrasound and colonoscopy autonomy\u2014making it one of the largest datasets of its kind worldwide.<\/p>\n\n\n\n Source: NVIDIA via Hugging Face, \u201cPhysical AI for healthcare robotics\u201d, huggingface.co\/blog\/nvidia\/physical-ai-for-healthcare-robotics<\/a><\/p>\n\n\n\n The collected data enabled the development of two breakthrough AI models:<\/p>\n\n\n This marks an important step toward building foundation models for medical robotics\u2014general-purpose AI systems that can be adapted to a wide range of clinical applications.<\/p>\n\n\n\n On Sano\u2019s side, the project involved Sabina Martyniak<\/a>, Mateusz W\u00f3jcikowski<\/a>, and Micha\u0142 Naskr\u0119t<\/a> from the Medical Imaging and Robotics team led by Dr. Przemys\u0142aw Korzeniowski<\/a>.<\/p>\n\n\n\n Their main responsibility was to prepare and standardize data generated with a simulator developed at Sano. The dataset includes recordings of both expert and non-expert users performing robotic cholecystectomy in a VR-simulated environment. It captures not only successful procedures but also errors and recovery attempts, and is enriched with multiple camera perspectives, variable lighting conditions, different levels of anatomical realism, and additional modalities such as depth maps, segmentation masks, approximate surface normals, and optical flow for each view. The data were generated in collaboration with Filippo Filicori, Aditya Amit Godbole, and their team at Northwell Health, as well as Dr Maria Clara Morais, and were subsequently processed for compatibility with the Open-H-Embodiment framework, making them part of the global dataset used to train AI models.<\/p>\n\n\n\n![\"\"](\"https:\/\/sano.science\/wp-content\/uploads\/2026\/03\/Open-H-Embodiment-Sample-data-1024x768.jpg\")
From Data to AI Models<\/h2>\n\n\n\n
\n
Sano\u2019s Role in Building Open-H-Embodiment<\/h2>\n\n\n\n