Modeling and Evaluation for Robot-Assisted Surgical Training and Intuitive Teleoperation

With the advance of teleoperated robotic platforms, such as the da Vinci surgical systems (Intuitive Surgical Inc., Sunnyvale, CA), robot-assisted surgery (RAS) has revolutionized a wide range of surgical interventions towards a safe, reliable, and minimally invasive approach. The objective of this PhD research is to design and develop computational techniques that are capable of automatically measuring a surgeon’s technical skills, interpreting the inherent difficulty demand of complex human motor control tasks, and providing efficient teleoperation evaluation with regard to the human operator. Specifically, the dissertation aims to (1) develop a human-centric analytical approach to objectively evaluate robot-assisted teleoperation, (2) develop machine learning based approaches for automated surgical skill assessment in basic surgical training tasks while improving the interpretability of the assessment to support efficient acquisition of skills, and (3) develop methods for an transferrable and task independent assessment of the operative difficulty demand and surgical skills by extending analysis to broader scenarios of robotic surgical teleoperation. Based on novel techniques of computational intelligence and human-centric analysis, this PhD research highlights the potential to improve surgical training and intuitive design of teleoperation systems for high performing robot-assisted surgery.