A Surgeon Preference-Guided Autonomous Instrument Tracking Method With a Robotic Flexible Endoscope Based on dVRK Platform

In minimally invasive surgery, endoscopes serve as the eyes of surgeon. To avoid fatigue in manual endoscope steering, robotic endoscope holders have been developed. Unfortunately, existing robotic endoscope holders are not widely adopted due to the poor surgeon-robot cooperation. In this work, we developed an intelligent flexible endoscope system based on the da Vinci Research Kit. In the system, surgical instruments are detected and classified in real time with an oriented bounding box-based object detection method. A custom dataset of 6243 images is established to train the detection neural network. Then, a surgeon’s preference guided visual servoing control method is proposed for automatically tracking the detected instruments during minimally invasive surgery. In order to realize 3-degree of freedom control on the image plane, an image moment-based visual servoing control method is adopted. To improve the dynamic performance of the system control, a modified genetic algorithm is developed to select the optimal gains of the robot controller. Both simulation and experimental results show the feasibility of the proposed intelligent flexible endoscope system.