Robotic learning of motion using demonstrations and statistical models for surgical simulation

Conclusions:    Surgical tasks can be modeled using Gaussian Mixture Model and motion primitives identified by adaptive mean shift method with minimum user intervention. Generic motion trajectory has been successfully reconstructed based on the motion model. Investigation on the effectiveness of this method and generic model for surgical training is ongoing.

Methods:    The generic model was developed from twenty-two sets of motion trajectories of soft tissue division with laparoscopic scissors collected from a robotic laparoscopic surgical training system. Adaptive mean shift method with initial bandwidth determined by the plug-in-rule method was used to identify the primitives in the motion trajectories. Gaussian Mixture Model was applied to model the underlying motion structure. Gaussian Mixture Regression was then applied to reconstruct a generic motion trajectory for the task.

Results: The generic model and proposed method were investigated in experiments. Motion trajectory of tissue division was model and reconstructed. The motion model which was trained based on primitives determined by adaptive mean shift method produced RMS error of 3.05° and 3.08° with respect to the demonstrated trajectories of left and right instruments, respectively. The RMS error was smaller than that of k-means method and fixed bandwidth mean shift method. The dexterous features in the demonstrations were also preserved.

Purpose:    In robotic-assisted surgical training, the expertise of surgeons in maneuvering surgical instruments may be utilized to provide the motion trajectories for teaching. However, the motion primitives for trajectory planning are not known until the motion trajectory is generalized. We hypothesize that a generic model that encodes surgical skills using demonstrations and statistical models can be used by the surgical training robot to determine the motion primitive base on the motion trajectory.