Needle Target-Insertion Trajectory Planning based on Reforcement Learning Expert's skill

this paper proposes a new robot needle insertion trajectory planning method based on learning expert's skill. Through reforcement learning, the system can imitate the expert's behavior in planning optimal needle insertion policy. After learning two experts' skill and experience, the needle insertion optimal policy shows that each one can catch the main characters of the expert's own behavior. Through experimental verification, this paper also presents an approach on improving system learning speed. This makes it possible for robot needle trajectory real time enforcement learning and target insertion in complicate surgical operating conditions.