Category: News

𝗧𝗶𝘁𝗹𝗲: 𝗔 𝗧𝗿𝗮𝗻𝘀𝗲𝗻𝗱𝗼𝘀𝗰𝗼𝗽𝗶𝗰 𝗧𝗲𝗹𝗲𝗿𝗼𝗯𝗼𝘁𝗶𝗰 𝗦𝘆𝘀𝘁𝗲𝗺 𝗨𝘀𝗶𝗻𝗴 𝗛𝗲𝘁𝗲𝗿𝗼𝗴𝗲𝗻𝗲𝗼𝘂𝘀 𝗙𝗹𝗲𝘅𝗶𝗯𝗹𝗲 𝗠𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗼𝗿𝘀 𝗳𝗼𝗿 𝗕𝗶𝗺𝗮𝗻𝘂𝗮𝗹 𝗘𝗻𝗱𝗼𝘀𝗰𝗼𝗽𝗶𝗰 𝗦𝘂𝗯𝗺𝘂𝗰𝗼𝘀𝗮𝗹 𝗗𝗶𝘀𝘀𝗲𝗰𝘁𝗶𝗼𝗻

🔍 𝗕𝗮𝗰𝗸𝗴𝗿𝗼𝘂𝗻𝗱:

Endoscopic submucosal dissection (ESD) is a key technique for early GI cancer treatment, requiring high dexterity and precision.

🛠 𝗪𝗵𝗮𝘁 𝘄𝗲 𝗱𝗶𝗱:

We developed the first 𝗵𝗲𝘁𝗲𝗿𝗼𝗴𝗲𝗻𝗲𝗼𝘂𝘀 𝗳𝗹𝗲𝘅𝗶𝗯𝗹𝗲 𝗺𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗼𝗿𝘀 (𝗛𝗙𝗠𝘀) for bimanual ESD, integrating:

🤖 𝗦𝗲𝗿𝗶𝗮𝗹 𝗔𝗿𝘁𝗶𝗰𝘂𝗹𝗮𝘁𝗲𝗱 𝗠𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗼𝗿 (𝗦𝗔𝗠) – for stable, multidirectional tissue traction

🔬 𝗣𝗮𝗿𝗮𝗹𝗹𝗲𝗹 𝗖𝗼𝗻𝘁𝗶𝗻𝘂𝘂𝗺 𝗪𝗿𝗶𝘀𝘁 (𝗣𝗖𝗪) – for accurate tissue dissection

📐 𝗞𝗲𝘆 𝗰𝗼𝗻𝘁𝗿𝗶𝗯𝘂𝘁𝗶𝗼𝗻𝘀:

✔ Kinematic modeling using Denavit–Hartenberg & Cosserat rod methods

✔ Workspace & dexterity analysis via simulation

✔ Validation through 16 ex vivo ESD tests

💡 This work demonstrates a novel strategy for surgical robotics—leveraging heterogeneous structures to enhance flexibility, stiffness, and accuracy in minimally invasive procedures.

👏 Kudos to our amazing team and collaborators from CUHK (Prof. Huxin Gao, Tao Zhang, Prof. Hongliang Ren), Qilu Hospital (Xiaoxiao Yang, Prof. 左秀丽, Prof. Yanqing Li), Southern University of Science and Technology (Xiao Xiao, Prof. Qinghu Meng), and Beijing Institute of Technology (Prof. Changsheng Li)!

📖 Stay tuned for the full article in IEEE RAM!

🏆 Paper: Contact-Aided Navigation of Flexible Robotic Endoscope Using Deep Reinforcement Learning in Dynamic Stomach

👩‍🔬 Authors: Chi Kit Ng, Huxin Gao, Tianao Ren, Prof. Jiewen Lai, and Prof. Hongliang Ren

🔍 𝗪𝗵𝘆 𝗶𝘁 𝗺𝗮𝘁𝘁𝗲𝗿𝘀:

Navigating flexible robotic endoscopes in the dynamic, deformable stomach environment is a grand challenge. Our proposed Contact-Aided Navigation (CAN) strategy, powered by deep reinforcement learning and force-feedback, achieved:

• 100% success rate in both static and dynamic simulated stomach environments

• Average navigation error of just 𝟭.𝟲 𝗺𝗺

• Robust generalization even under strong external disturbances

This work highlights how 𝗲𝗺𝗯𝗼𝗱𝗶𝗲𝗱 𝗔𝗜 𝗮𝗻𝗱 𝗯𝗶𝗼𝗺𝗲𝗰𝗵𝗮𝗻𝗶𝗰𝘀-𝗶𝗻𝘀𝗽𝗶𝗿𝗲𝗱 𝘀𝘁𝗿𝗮𝘁𝗲𝗴𝗶𝗲𝘀 can transform surgical robotics, enabling safer and more precise navigation in complex clinical environments.

Check the paper at https://lnkd.in/g6KgZTdD

🙏 Huge thanks to the team, collaborators, and the broader robotics community for the support and inspiration.

This work introduces a comprehensive dataset designed to advance AI-driven surgical robotics and medical imaging. By capturing detailed 𝗮𝗻𝗮𝘁𝗼𝗺𝗶𝗰𝗮𝗹 𝗹𝗮𝗻𝗱𝗺𝗮𝗿𝗸𝘀 𝗼𝗳 𝘁𝗵𝗲 𝘂𝗽𝗽𝗲𝗿 𝗮𝗶𝗿𝘄𝗮𝘆, we aim to support safer, more accurate 𝗯𝗿𝗼𝗻𝗰𝗵𝗼𝘀𝗰𝗼𝗽𝘆 𝗮𝗻𝗱 𝗶𝗻𝘁𝘂𝗯𝗮𝘁𝗶𝗼𝗻 procedures — paving the way for improved patient outcomes and robust benchmarking in clinical AI.

🔑 𝗛𝗶𝗴𝗵𝗹𝗶𝗴𝗵𝘁𝘀:

– First-of-its-kind dataset focused on airway anatomical landmarks

– Enables benchmarking for automated navigation and intubation tasks

– Openly available to foster collaboration across robotics, AI, and healthcare communities

We hope this resource will accelerate innovation in 𝗲𝗺𝗯𝗼𝗱𝗶𝗲𝗱 𝗶𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲 𝗳𝗼𝗿 𝗵𝗲𝗮𝗹𝘁𝗵𝗰𝗮𝗿𝗲 and inspire new interdisciplinary collaborations.

👉 Read the full paper: https://rdcu.be/eS0d5

Grateful to all co-authors and collaborators from The Chinese University of Hong Kong (Ruoyi Hao, Zhiqing Tang, Catherine Po Ling Chan, Jason Ying Kuen Chan, Prof. Hongliang Ren), Hubei University of Technology (Zhang Yang), Huazhong University of Science and Technology (Yang Zhou), National University of Singapore (Lalithkumar Seenivasan), and Singapore General Hospital (Shuhui 

Xu, Neville Wei Yang Teo, Kaijun Tay, Vanessa Yee Jueen Tan, Jiun Fong Thong, Kimberley Liqin Kiong, Shaun Loh, Song Tar Toh, and Prof. Chwee Ming Lim), for making this possible. Excited to see how others build upon this foundation!

💡This work introduces 𝗩𝗟-𝗦𝘂𝗿𝗴𝗣𝗧, the first large-scale multimodal dataset that 𝘪𝘯𝘵𝘦𝘨𝘳𝘢𝘵𝘦𝘴 𝘷𝘪𝘴𝘶𝘢𝘭 𝘵𝘳𝘢𝘫𝘦𝘤𝘵𝘰𝘳𝘪𝘦𝘴 𝘸𝘪𝘵𝘩 𝘴𝘦𝘮𝘢𝘯𝘵𝘪𝘤 𝘱𝘰𝘪𝘯𝘵 𝘴𝘵𝘢𝘵𝘶𝘴 𝘥𝘦𝘴𝘤𝘳𝘪𝘱𝘵𝘪𝘰𝘯𝘴 in surgical environments.

🔍Alongside the dataset, we propose 𝗧𝗚-𝗦𝘂𝗿𝗴𝗣𝗧, a text-guided point tracking method that consistently outperforms vision-only approaches, especially under challenging intraoperative conditions such as smoke, occlusion, and tissue deformation.

🙏 We are deeply grateful to all coauthors and especially our clinical collaborators at Shenzhen People’s Hospital for their invaluable contributions. Looking forward to engaging with the community at AAAI in Singapore and advancing the conversation on multimodal surgical AI!

Check the paper at https://lnkd.in/grfE5iVi

Project Page: https://lnkd.in/gscM_ciV

🎉 Excited to share that the 3rd C4SR+ Workshop: 𝘾𝙤𝙣𝙩𝙞𝙣𝙪𝙪𝙢, 𝘾𝙤𝙢𝙥𝙡𝙞𝙖𝙣𝙩, 𝘾𝙤𝙤𝙥𝙚𝙧𝙖𝙩𝙞𝙫𝙚, 𝘾𝙤𝙜𝙣𝙞𝙩𝙞𝙫𝙚 𝙎𝙪𝙧𝙜𝙞𝙘𝙖𝙡 𝙍𝙤𝙗𝙤𝙩𝙞𝙘 𝙎𝙮𝙨𝙩𝙚𝙢𝙨 𝙞𝙣 𝙩𝙝𝙚 𝙀𝙢𝙗𝙤𝙙𝙞𝙚𝙙 𝘼𝙄 𝙀𝙧𝙖 took place during #IROS2025 in Hangzhou, China.

This year’s workshop attracted 𝗼𝘃𝗲𝗿 𝗼𝗻𝗲 𝗵𝘂𝗻𝗱𝗿𝗲𝗱 𝗽𝗮𝗿𝘁𝗶𝗰𝗶𝗽𝗮𝗻𝘁𝘀 𝗳𝗿𝗼𝗺 𝗮𝗰𝗿𝗼𝘀𝘀 𝘁𝗵𝗲 𝗴𝗹𝗼𝗯𝗲 — a fantastic turnout that reflects the growing momentum in 𝘀𝘂𝗿𝗴𝗶𝗰𝗮𝗹 𝗿𝗼𝗯𝗼𝘁𝗶𝗰𝘀 𝗮𝗻𝗱 𝗲𝗺𝗯𝗼𝗱𝗶𝗲𝗱 𝗔𝗜.

🎤 Distinguished Speakers

We were honored to host leading experts who shared their groundbreaking research and perspectives, including Prof. Nassir Navab from Technical University of Munich, Prof. Leonardo Mattos from Italian Institute of Technology, Prof. Mingchuan Zhou from Zhejiang University, Prof. Dandan Zhang from Imperial College London, Prof. Yunjie Yang from University of Edinburgh, and Prof. Guoying Gu from Shanghai Jiao Tong University.

🔑 Key Themes Discussed

• Embodied AI in surgery and intelligent operating rooms

• Soft & continuum robotics for minimally invasive procedures

• Human–robot collaboration in clinical practice

• Cognitive surgical systems and decision-making

🏆 Workshop Contributions

– 9 oral and 9 poster paper presentations from emerging researchers

– Best Paper & Best Presentation Awards recognizing outstanding contributions

🙏 A heartfelt thank you to all speakers, participants, and organizers who made this workshop such a success. The discussions and collaborations will continue to shape the future of surgical robotics.

🔗 Learn more about the workshop and its highlights on the official page: https://lnkd.in/gswzMFAy

The work couples a VLM backbone with a dual-phase training recipe (SFT → RFT) to turn language prompts into robust tracking and motor commands for a continuum endoscope.

A highlight was a meeting with Prof. Ken Goldberg—especially meaningful since Prof. Ren previously served as a postdoc at UC Berkeley, keeping our CUHK↔︎UCB connection strong.

🤝 Huge thanks to collaborators and everyone who stopped by the poster!

Authors: Chi Kit Ng*, Long Bai*, Guankun Wang*, Yupeng Wang, Huxin Gao, Kun Yuan, Chenhan Jin, Tieyong Zeng, Hongliang Ren
Affiliations: CUHK, TUM

His keynote, “Robotic Endoscopy & Surgical Foundation Models,” dived deep into intelligent minimally invasive surgical robots. Specifically, he highlighted how advanced flexible surgical motion generation and perception capabilities are set to transform procedures with surgical foundation models.

A big thank you to all organizers, speakers, and participants for fostering such a vibrant exchange of ideas at the forefront of medical robotics. The collaboration and innovation underscore the immense potential of AI and robotics to improve patient outcomes and empower surgeons.

For workshop details: https://lnkd.in/gvCREK2m

👏 Huge congratulations to YIMING HUANG, Long Bai, Beilei Cui, and our amazing co-authors Kun Yuan, Guankun Wang, Mobarak I. Hoque, Nicolas Padoy, Nassir Navab, and Hongliang Ren for their outstanding contributions.

🤝 Beyond the award, it’s been a wonderful gathering of our lab members and alumni—celebrating collaboration, innovation, and the friendships that fuel our research.

His talk, “𝗘𝗻𝗱𝗼𝗹𝘂𝗺𝗶𝗻𝗮𝗹 𝗥𝗼𝗯𝗼𝘁𝗶𝗰𝘀 & 𝗘𝗺𝗯𝗼𝗱𝗶𝗲𝗱 𝗔𝗜 𝗶𝗻 𝘃𝗶𝘃𝗼,” shed light on how robotics and embodied intelligence are reshaping the future of minimally invasive interventions. The vision he shared opens exciting pathways for smarter, safer, and more adaptive medical technologies.

Grateful to the #EMA4MICCAI team for creating such a vibrant platform for exchanging ideas at the intersection of medical imaging, AI, and robotics.

In this study, we introduce 𝗦𝘂𝗿𝗴𝗧𝗣𝗚𝗦, a novel framework that enables real-time, text-promptable 3D semantic querying in surgical environments. By integrating 𝘃𝗶𝘀𝗶𝗼𝗻-𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗺𝗼𝗱𝗲𝗹𝘀 with 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗦𝗽𝗹𝗮𝘁𝘁𝗶𝗻𝗴 𝗮𝗻𝗱 𝘀𝗲𝗺𝗮𝗻𝘁𝗶𝗰-𝗮𝘄𝗮𝗿𝗲 𝗱𝗲𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻 𝘁𝗿𝗮𝗰𝗸𝗶𝗻𝗴, our method significantly improves the precision and efficiency of robotic-assisted surgery.

📌 Key Contributions:

• First text-promptable Gaussian Splatting for 3D surgical scenes

• Semantic-aware deformation tracking for dynamic anatomy

• Region-aware optimization for sharper segmentation and smoother reconstruction

• State-of-the-art results on CholecSeg8K and EndoVis18 datasets

Paving the way for smarter, safer surgical systems. Check out the full paper: https://lnkd.in/euGHFma5

Thanks and congrats to the amazing author team:

YIMING HUANG, Long Bai, Beilei Cui, Guankun Wang, Hongliang Ren (CUHK); Kun Yuan (Unistra, TUM), Nicolas Padoy (Unistra), Nassir Navab (TUM), and Mobarak I. Hoque (UCL).