Pioneering the Future of Endoscopic Robotics
At the third General Assembly on 9 October the IRE team gathered to evaluate the project’s latest milestones — a meeting that showcased how collaboration, innovation, and interdisciplinary expertise are reshaping medical robotics. The path toward safer, more effective, and intelligent robotic colonoscopy is becoming clearer with each iteration of the project.
Key Achievements
The IRE consortium has made achievements across simulation, sensing, and robotic intelligence. Highlights include:
• 435 high-quality, simulation-ready colon meshes, with artifacts removed from the rectum region — enabling precise and realistic modeling for surgical simulation.
• A fully integrated endoscope colon simulator, combining anatomical models with real endoscopic data.
• A novel formulation of forward and differentiable rigid-body dynamics using Lie-algebra rotation derivatives — enabling simulations 4.3× faster than conventional methods while improving optimization for endoscope tip navigation.
• The first theoretical framework for optimal sensor positioning, a foundation for improving robotic perception and accuracy.
• Initial experiments with mechanochromic materials, advancing the tactile sensing capabilities of soft robotic systems.
• Development of intelligent soft robotic platforms for colonoscopy, integrating sensing for improved safety and efficacy.
• Validated prototypes of reinforcement learning environments, supporting adaptive and data-driven robotic control.
• A modular and configurable software interface for streamlined data import and management.
• Proof-of-concept reward design and navigation policy learning, establishing a key basis for autonomous robotic guidance.
Insights from the Keynote
Benedikt Duckworth-Mothes presented inspiring developments, including:
• A survey of current training models and novel methods for model production.
• The first prototype for a colon peristalsis model, simulating realistic organ motion.
• Future directions in sensor integration, essential for enhancing robotic situational awareness and responsiveness.
These advances reflect the team’s dedication to bridging theoretical modeling with tangible MedTech innovation.
Looking Ahead
The next phase of the IRE project aims to transform these advances into clinically viable technologies. Planned initiatives include:
• Creating five colon cases for simulation with varying complexity to refine performance across boundary conditions.
• Designing a novel Eulerian-on-Lagrangian reduced model to accelerate endoscope–tissue interaction simulations.
• Extending the sensor positioning framework for optimized system performance.
• Developing the first iteration of a “sensitive” colon phantom, advancing haptic realism in simulation.
• Validating soft robotic platforms in clinically relevant environments for performance and safety assessment.
• Launching an anthropological study exploring interdisciplinary collaboration within the IRE project.
• Collecting data on insertion forces during colonoscopy, using a custom device developed by AMBU partners.
A Collaborative Effort Across Europe
The progress of the IRE project is made possible through the exceptional collaboration among leading research institutions:
• University of Copenhagen (DIKU) – Kenny Erleben, Martina Finocchiaro, Melanie Ganz-Benjaminsen, Hang Yin, Hans Jacob Teglbjærg Stephensen, Guanglin Ji, and Sune Darkner.
• Universidad Rey Juan Carlos – Christos Koutras, Magí Romanyà, and Miguel A. Otaduy.
• Inria – Jeremie Dequidt, Christian Duriez, Yinoussa Adagolodjo, and Thomas Moupfouma.
• InSimo - Francois Jourdes and Lil Le Crom
• University of Twente – Gijs Krijnen, Giulio Dagnino, Milad Hayati, Momen Abayazid, Venkata Rithwick Puranam, Mostafa A. Atalla, and Islam S. M. Khalil.
• CAMES – Ami Heen, Birgitte Bruun, Johannes van den Heuvel, Kristoffer Mazanti Cold, Lars Konge, and Juana Maria Abdelreda.
• UT – Clemens Lässing and Benedikt Duckworth-Mothes.
• Ambu A/S - Enrique Morales-Orcajo, PhD, Sai Sudhir Chalavadi
The General Assembly, hosted at the Pioneer Centre for AI (P1), deepened ongoing partnerships — propelling the IRE vision of intelligent, autonomous, and patient-safe robotic endoscopy ever closer to clinical reality.