2nd Workshop on Machine Learning in Medical Robotics: Bridging ML Theory and Clinical Frontiers
AIM AND SCOPE
Machine learning (ML), encompassing deep learning and deep reinforcement learning, holds the transformative potential to reshape healthcare robotics. Its applications range from aiding surgeons in intricate procedures to optimizing robot interactions within complex medical environments and delivering personalized patient rehabilitation. Also, the ML landscape is characterized by rapid advancements, with the constant iteration and emergence of cutting-edge algorithms, including Reinforcement Learning, Transfer Learning, Large Language Model (LLM), and generative AI. These innovations contribute to the ever-evolving potential of ML. Despite rapid ML advancements, not all algorithms seamlessly integrate into medical robotics, hindering their full potential. Challenges include the need for a strong robotics background, interdisciplinary collaboration, and ensuring interpretability and safety.
Meanwhile, the ML community researchers are eager to apply the latest developed algorithms to practical applications beyond the computer screen, especially in the field of medical robotics. These advanced machine learning models have great potential to push the boundaries of what’s possible. However, compared to the rapid pace of the iteration of ML models, the integration in the medical robotics field is relatively slow.
At the first edition of our workshop, held at IROS 2022, we primarily focused on discussing the utilization of ML methods in medical robotics research, exploring how to leverage the benefits of ML and mitigate its risks. For the second edition of the workshop, we aim to shift our focus on how to deploy the latest algorithms effectively in medical robotics research, given the recent surge in interest in LLM and generative AI.
Thus, this workshop is designed to serve as a nexus between theoretical ML and clinical frontiers. It aims to facilitate meaningful dialogues among engineers in the field of medical robotics, researchers specializing in ML/robot learning, as well as clinicians. A particular emphasis will be placed on the newest applications utilizing the latest algorithms, such as LLM and generative AI. Moreover, a comprehensive exploration of other ML algorithms is also critical to our agenda.
TOPICS OF INTEREST
This workshop will specifically focus on advancements in ML techniques and the latest developed algorithms for medical robots’ perception, modeling, control, and navigation around the following key themes:
Advancements in autonomous robotics surgery
ML in medical robotics modeling
Learning of surgical skills from demonstrations/videos
Medical robot sensing and localization based on ML
Applications of generative AI and Large Language Models (LLM) in medical robotics
Autonomous (sub-)task learning and execution
Navigation and motion planning for medical robots
Data-driven simulations for surgical training
Solutions on ethical implications, data privacy and security
ORGANIZERS
Di Wu
KU Leuven, Belgium
Jing Guo
Guangdong University of Technology, China
Loris Fichera
Worcester Polytechnic Institute, USA
Farshid Alambeigi
University of Texas at Austin, USA
Yao Zhang
KU Leuven, Belgium
Michael Yip
University of California San Diego, USA
IEEE/RAS TC SUPPORT
This proposed workshop is endorsed by the following IEEE RAS Technical Committees:
● IEEE RAS Technical Committee for Surgical Robotics;
● IEEE RAS Technical Committee for Telerobotics;
● IEEE RAS Technical Committee for Rehabilitation and Assistive Robotics;