A Self-evolution Hybrid Robot for Dental Implant Surgery

Dental implant surgery is an effective method for remediating the loss of teeth. A novel custom-built hybrid robot, combining the advantages of serial manipulator and parallel manipulator, was proposed for assisting the dental implant surgery. The hybrid robot is comprised of 3 DOF translation joints, 2 DOF revolute joints and a Stewart manipulator. The translation joints are used for initial position adjustment, making the Stewart manipulator near the target position. The revolute joints are used for assisting the Stewart manipulator in initial orientation adjustment. The procedure of robot-assisted dental implant surgery is designed and described. Considering the limited workspace of Stewart manipulator, we set minimizing the joint displacement of the Stewart manipulator as the optimization objective to find an optimal joint configuration during initial orientation adjustment. In order to find the optimal joint configuration quickly, neural network is used to map the relationship between the target orientation and the optimal joint configuration. In addition, a self-evolution strategy is proposed for optimizing the learning model continuously. And the effectiveness of the strategy is validated in the phantom experiment.