Orientation Matters: 6-DoF Autonomous Camera Movement for Video-based Skill Assessment in Robot-Assisted Surgery*

Video-based surgical skill assessment is one of the main assessment methods in robot-assisted surgery (RAS). Expert assessors watch videos of trainees, recorded from endoscopic camera feeds, and evaluate their performance using well-established assessment questionnaires. A major drawback of this method, however, is the high variability in scores between different assessors, mainly due to the limited visual feedback provided by the recorded videos. To solve this problem, we propose a new method for six-degree-of-freedom (6-DoF) autonomous camera movement for RAS, which, unlike previous methods, takes into account both the position and 3D orientation information from structures in the surgical scene. We developed a simulation environment to test our method on the “wire chaser” surgical training task from validated training curricula in RAS. In a study with N = 30 human subjects, we show that our proposed method leads to at least 21% more accurate skill assessment and at least 31% less variability in assessment scores than when using a fixed camera view, or camera movement method based only on position information. Our preliminary work suggests that there are potential benefits to autonomous camera positioning informed by scene orientation, and this can direct designers of automated endoscopes and surgical robotic systems, especially when using chip-on-tip cameras that can be wristed for 6-DoF motion.