Reiley Carol E, Plaku Erion, Hager Gregory D
Department of Computer Science, Johns Hopkins University, 3400 N. Charles Street, Baltimore, MD 21218, USA.
Annu Int Conf IEEE Eng Med Biol Soc. 2010;2010:967-70. doi: 10.1109/IEMBS.2010.5627594.
Robotic surgical assistants offer the possibility of automating portions of a task that are time consuming and tedious in order to reduce the cognitive workload of a surgeon. This paper proposes using programming by demonstration to build generative models and generate smooth trajectories that capture the underlying structure of the motion data recorded from expert demonstrations. Specifically, motion data from Intuitive Surgical's da Vinci Surgical System of a panel of expert surgeons performing three surgical tasks are recorded. The trials are decomposed into subtasks or surgemes, which are then temporally aligned through dynamic time warping. Next, a Gaussian Mixture Model (GMM) encodes the experts' underlying motion structure. Gaussian Mixture Regression (GMR) is then used to extract a smooth reference trajectory to reproduce a trajectory of the task. The approach is evaluated through an automated skill assessment measurement. Results suggest that this paper presents a means to (i) extract important features of the task, (ii) create a metric to evaluate robot imitative performance (iii) generate smoother trajectories for reproduction of three common medical tasks.
机器人手术助手提供了将部分耗时且繁琐的任务自动化的可能性，以减轻外科医生的认知工作量。本文提出使用示范编程来构建生成模型，并生成能够捕捉从专家示范中记录的运动数据潜在结构的平滑轨迹。具体而言，记录了直观外科公司的达芬奇手术系统中一组专家外科医生执行三项手术任务时的运动数据。这些试验被分解为子任务或手术步骤，然后通过动态时间规整在时间上进行对齐。接下来，高斯混合模型（GMM）对专家的潜在运动结构进行编码。然后使用高斯混合回归（GMR）来提取平滑的参考轨迹，以再现任务的轨迹。该方法通过自动技能评估测量进行评估。结果表明，本文提出了一种方法，可（i）提取任务的重要特征，（ii）创建一个评估机器人模仿性能的指标，（iii）生成更平滑的轨迹以再现三项常见医疗任务。
