Data-Driven vs. Model-Based Approaches in Medical Robotics: Choosing One or Embracing Both?

In today's landscape, the increasing availability of data and rapid progress in computing hardware such as GPUs have spurred the expansion of artificial intelligence, deep learning, and data-driven approaches in the field of medical robotics, resulting in a surge of academic publications. Concurrently, skepticism about these methods has emerged, highlighting concerns over their "black-box" nature and the ethical dilemmas they may engender. Amidst this backdrop, many researchers remain committed to exploring traditional analytical methods. This ongoing debate and controversy underscore the relevance of examining whether data-driven approaches, model-based methods, or a synergy of both, should be pursued in medical robotics, motivating the need for this Research Topic.



This Research Topic aims to explore the critical dialogue between data-driven and model-based approaches in medical robotics, inviting contributions that either compare these methods or highlight their integration. By focusing on the comparative analysis and potential synergy of these approaches, we intend to shed light on their respective advantages and the scenarios in which they excel. This initiative seeks to equip the research community with insights and evidence-based guidance on selecting or combining these strategies for specific challenges in medical robotics. Through a curated collection of innovative studies and recent advancements, this topic will serve as a valuable resource for navigating the decision-making process in the deployment of medical robotics technologies, fostering informed choices and promoting a balanced perspective on the future direction of the field.



This Research Topic welcomes submissions on the following topics, but is not limited to:

1. Advances in model-based and model-free control strategies for surgical, rehabilitation, and soft robotics;

2. Analytical modeling applications in surgical procedures and rehabilitation therapy;

3. Integrating data-driven insights with model-based techniques in medical robotics;

4. The role of AI and machine learning in enhancing surgical robot technologies;

5. Innovations in sensing and actuation towards more responsive surgical and rehabilitation robots;

6. Ethical considerations and transparency in the use of AI within surgical and rehabilitation robotics;

7. A comparative study of data-driven and model-based methods in actuation and control in surgical and rehabilitation robotics.



This Research Topic invites submission of Original Research, Systematic Review, Methods, Review, Policy and Practice Reviews, Hypothesis & Theory, Clinical Trial, Registered Report, Technology and Code.

Keywords: Artificial Intelligence; Medical Robotics; Data-driven method; Model-based approach; Machine learning; Deep learning; Surgery; Interventions; Reinforcement Learning

Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.