Probability analysis for grasp planning facing the field of medical robotics

Abstract

Medical surgical robot is a fusion of medical image information matching fusion technology and robotic trajectory control technology. The medical image information matching fusion is to obtain two images of a certain range of the patient’s body by two cameras on the robot, and after matching fusion processing, an image is obtained. At present, surgical robots have been successfully applied in minimally invasive surgery such as pelvic organ prolapse, defects and other basin basement reconstruction operations. Previously, most of the robots used in medical surgery have only one arm, but with the development of robotics related fields, multi-fingered robots with binocular stereo vision become possible in completing complex minimally invasive surgery. This paper aims to promote the further integration of multi-fingered manipulator and medical image detection, focusing on the grasping probability of multi-fingered manipulator. When the three-dimensional information of the object is incomplete, the machine learning method performs better than the hard coding method in the object grasping point planning. At present, most known methods can obtain classification results but could not give the probability of this category. Aiming at the problem of grab point planning, this paper proposes a crawling planning method based on big data Gaussian process classification. In this paper, a planner based on Gaussian process classification is designed, and the hyper constant used in the Gaussian process to judge the probability of capture is calculated. Based on the determined crawling scheme, the feasibility distribution map of the grab points which obtained by the trained Gaussian process classifier is drawn in MATLAB. The results show that the trained Gaussian process classifier is biased towards the center of the object which is the point with high stability. This method can give classification results and corresponding probabilities, which represents the feasibility of grasping points.