EAGER:TaskDCL: Neuroadaptive Context-Aware Human-Robot Collaboration: Mitigating Surgeons' Mental Overload in Robotic-Assisted Surgery

Robotic-assisted surgery has the potential to offer enhanced overall surgical performance and greater precision compared to traditional surgical methods. However, surgeons’ mental workload remains a concern in robotic-assisted surgery due to increased complexity of operations, leading to unexpected human errors and unsatisfactory surgical outcomes. As robotic-assisted surgery rapidly advances with more complex technology, it is critical to prevent surgeons’ mental overload to ensure surgical task performance and patient safety. Neuro-adaptive technology represents an innovative solution for reducing human mental workload by enabling the context-awareness of robots to offer adaptive interventions within response to variations in human cognitive states. However, the adoption of the neuro-adaptive technology in robotic-assisted surgery remains largely unexplored. This gap highlights a fundamental research opportunity in understanding the advantages and limitations of neuro-adaptive technology to enhance surgical outcomes. This EArly-concept Grant for Exploratory Research (EAGER) grant supports research to design neuro-adaptive technology for robotic-assisted surgery. Introducing such an innovative technology to robotic-assisted surgery has the potential to transform traditional teleoperation into a more collaborative human-robot interaction. This, in turn, has the potential to improve patient health, identify and mitigate cognitively demanding procedures or operative conditions, and to reduce costs associated with adverse patient outcomes. This research aims to design neuro-adaptive robotic-assisted surgery by enabling the robot's awareness of the surgical context, with the aim of understanding: (1) how to monitor different surgeons’ workload levels, (2) how to understand the cause of such workload, and (3) how to perform interventions. An artificial intelligence-powered multi-sensing system will be investigated to monitor workload levels on a personal basis for surgeons with varying skill levels. A context-awareness architecture that synthesizes visual and auditory data will be used to identify the cause of mental overload and initiate proper interventions and a prototype of the researched neuro-adaptive technology will be designed and validated. By leveraging multi-modal sensor data, human factors modeling, and artificial intelligence, the ultimate goal of this project is to refine the implementation of these life-saving remote surgery techniques, ensuring that they are more effective, adaptable, and safe. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.