Current advances in medical robotics research have enabled the performance of complex procedures through the development of compliant surgical platforms designed to seamlessly interact with the user. As a result, recent medical robotics research is investigating novel approaches to provide cooperative control between the surgeon and the robot. Techniques such as shared control, active constraints/virtual fixtures, gaze-contingent motor channeling and learning from demonstration have the potential to significantly improve surgical robotics by creating a greater synergy between the surgeon and their tools. In addition, many of these techniques also provide a framework for a sophisticated surgical skills evaluation and skill transfer. To this end, the robot must be able to sense changes in the dynamic surgical environment and adapt its actions accordingly, always keeping the human in the control loop. Robot-surgeon cooperation is critical for overcoming the potential legal and ethical issues and promoting the wider uptake of robotic surgery. The focus of this research topic is on current approaches in the development of cooperative control techniques for medical robotics. Authors are particularly encouraged to submit papers on the use of open platforms for surgical robotics such as the KUKA lightweight robot, the RAVEN II robot and the Da Vinci Research Kit (DVRK), and their potential for improving the performance of challenging techniques through collaborative execution of complex surgical tasks.
Topics to be covered include but are not limited to:
• Shared control
• Supervisory control
• Virtual fixtures and active constraints
• Haptic, tactile and other perceptual feedback mechanisms
• Cooperative robotic control through perceptual docking
• Real-time surgical workflow monitoring and learning from demonstration
• Visual servoing and gaze contingent control
• Collaborative control of open platforms for surgical robotics
• Cognitive factors influencing human-robot interaction
• Image-constrained biomechanical modeling and prediction of tissue deformation
Current advances in medical robotics research have enabled the performance of complex procedures through the development of compliant surgical platforms designed to seamlessly interact with the user. As a result, recent medical robotics research is investigating novel approaches to provide cooperative control between the surgeon and the robot. Techniques such as shared control, active constraints/virtual fixtures, gaze-contingent motor channeling and learning from demonstration have the potential to significantly improve surgical robotics by creating a greater synergy between the surgeon and their tools. In addition, many of these techniques also provide a framework for a sophisticated surgical skills evaluation and skill transfer. To this end, the robot must be able to sense changes in the dynamic surgical environment and adapt its actions accordingly, always keeping the human in the control loop. Robot-surgeon cooperation is critical for overcoming the potential legal and ethical issues and promoting the wider uptake of robotic surgery. The focus of this research topic is on current approaches in the development of cooperative control techniques for medical robotics. Authors are particularly encouraged to submit papers on the use of open platforms for surgical robotics such as the KUKA lightweight robot, the RAVEN II robot and the Da Vinci Research Kit (DVRK), and their potential for improving the performance of challenging techniques through collaborative execution of complex surgical tasks.
Topics to be covered include but are not limited to:
• Shared control
• Supervisory control
• Virtual fixtures and active constraints
• Haptic, tactile and other perceptual feedback mechanisms
• Cooperative robotic control through perceptual docking
• Real-time surgical workflow monitoring and learning from demonstration
• Visual servoing and gaze contingent control
• Collaborative control of open platforms for surgical robotics
• Cognitive factors influencing human-robot interaction
• Image-constrained biomechanical modeling and prediction of tissue deformation
