Low delay control algorithm of robot arm for minimally invasive medical surgery

Abstract

Minimally invasive surgical robots have received more and more attention from medical patients because of their higher surgical accuracy and higher safety than doctors. Minimally invasive surgery is rapidly revolutionizing the treatment of traditional surgery. In order to solve the problem that the surgical robot has a redundant degree of freedom, which makes the kinematics solution more complicated, this paper analyzes the kinematics of the coordinate system block. Aiming at the problem that the strategy search algorithm needs to re-learn when the target pose changes, a convolutional neural network control strategy is studied and constructed. By designing the structure of the convolutional neural network visual layer and motor control layer, the loss function and sampling of the training process are established. Aiming at the problem of long training time of convolutional neural network, an effective pre-training method is proposed to shorten the training time of the neural network. At the same time, the effectiveness of the above method and the end-to-end control of the convolutional neural network strategy are verified through simulation experiments. The physical structure of the manipulator body is analyzed, and the forward and inverse kinematic equations of the manipulator are established by the D-H method. Monte Carlo method was used to analyze the working space of the manipulator, and low-latency control and simulation experiments were carried out on the movement trajectory of the manipulator in joint space and Cartesian space. The results show that the low-latency control algorithm in this paper is effective to control the mechanical arm of the minimally invasive medical surgery robot.