Grip Force Estimation of Laparoscope Surgical Robot based on Neural Network Optimized by Genetic Algorithm

Abstract

In this paper, we described a method of sensorless grip force estimation based on Neural Network (NN) optimized by Genetic Algorithm (GA) to address the gripping force estimation problem of laparoscope surgical robots. The gripping force estimation problem is the key of haptic feedback in Robotic Minimally Invasive Surgeries (RMIS). We verified the proposed method and compared with the grip force estimated by dynamic model. The number of units of hidden layer was optimized so that it made a better fitting performance. The experimental results demonstrated that the proposed method had a good performance for the sensorless grip force estimation, which is well applied to our surgical robots.