Description

Artificial Intelligence and medical robotics are revolutionizing the surgical domain. The potential impact of AI and robot autonomy is significant. However, the design and control of robots for such unpredictable environments is still a critical issue, and safety is of paramount importance. To balance automation and human intervention, there is growing interest in combining machine learning and shared control approaches to promote solutions that keep humans in the loop. This approach can improve safety, comfort, robustness, and flexibility and enhance the overall decision-making performance. There are several approaches to this, such as involving humans in the planning process, using control theory to monitor humans as they perform tasks, and using unsupervised reinforcement learning or supervised machine learning to learn behaviors or motions.

To implement these control strategies, several areas of robotics and artificial intelligence research need to come together, including robot design and control, vision/sensing, haptics, explainable artificial intelligence, human-in-the-loop machine learning, learning and reasoning, and decision making under uncertainty. In order to move this field forward, there is a need for interdisciplinary events where researchers from these areas can come together to share their perspectives and insights, and to explore the implications of different aspects related to rehabilitation, surgical and healthcare robotics. The workshop will be a full-day event with multiple invited keynote speakers, including a poster session where participants can contribute to the workshop by presenting and discussing their latest results. There will be breaks between sessions to provide networking opportunities for researchers to interact with speakers and panelists.

Call for Extended Abstracts for the Poster Sessions

We would like to invite submissions of extended abstracts to the “Hybrid Human-Machine Interaction in Surgery” workshop at the Hymlin Symposium on Medical Robotic HSMR 2024. The workshop aims to bring together researchers from computer science, AI/ML, robotics, and surgery to explore future research directions in supervised control, shared control, and machine learning in surgical AI and robotics. Key outcomes include discussing clinical needs for surgical robots, analyzing human-machine interaction strategies, identifying hybrid learning approaches, ensuring ethical decision-making, and exploring AI applications for vision and robot control. To implement these strategies effectively, research fields such as robot design, vision/sensing, haptics, explainable AI, and decision-making must converge. Interdisciplinary gatherings facilitate the exchange of insights and exploration of implications in rehabilitation, surgical, and healthcare robotics.

Submission Guidelines

Extended abstracts, including references and up to one figure, must be submitted in the double-column format and must not exceed one page in length. The authors may also submit a two-minute explanatory video along with their submissions. All the abstracts must be uploaded by the submission form. We expect that at least one author of each accepted abstract will register for the symposium and present the work during the workshop. Templates can be found here.

Important Dates

• Submission Deadline: May 19th, 2024
• Notification of Acceptance: May 28th, 2024
• Early bird registration deadline: May 31st, 2024
• Workshop Date: June 28, 2024

Call for submissions is now closed.

Programme

Learning Outcomes

The aim of this workshop is to bring together researchers with different backgrounds including but not limited to computer science, AI/ML, robotics, surgery and expertise to explore the research areas for the future development of supervised control, shared control and machine learning in surgical artificial intelligence and robotics.

The learning outcomes of the workshop are:

• Discussing the clinical needs for the new era of surgical robots;
• Analyzing the strategies and HCI principles that promote rich and diverse interactions between humans and machines;
• Identifying hybrid learning and decision making strategies that can maximize the performance of the human-machine team;
• Identifying potential pitfalls and ensuring that trustworthy and ethical hybrid decision-making systems are developed;
• Understanding how design, materials, and control interfaces can help in realizing effective human supervision of surgical robotic systems in terms of multimodal human-robot interface;
• Highlighting the most recent AI applications for vision and robot control applications for the future generation of surgical robots and how human experience can help to develop new paradigms for supervised control;
• Updating on the state-of-the-art commercial surgical robots and providing insights into their potential future;
• Learning how vision and tactile information, together with AI-based elaboration of the information, learning process, and control strategies