Robot grasp pose estimation method based on object recognition depth learning model

Abstract

The invention discloses a robot grasping pose estimation method based on an object recognition depth learning model, which relates to the technical field of computer vision. The method is based on anRGBD camera and depth learning. The method comprises the following steps: S1, camera parameter calibration and hand-eye calibration being carried out; S2, training an object detection object model; S3, establishing a three-dimensional point cloud template library of the target object; 4, identifying the types and position of each article in the area to be grasped; 5, fusing two-dimensional and three-dimensional vision information and obtaining a point cloud of a specific target object; 6, completing the pose estimation of the target object; S7: adopting an error avoidance algorithm based on sample accumulation to avoid errors; S8: Steps S4 to S7 being continuously repeated by the vision system in the process of moving the robot end toward the target object, so as to realize iterative optimization of the pose estimation of the target object. The algorithm of the invention utilizes a target detection YOLO model to carry out early-stage fast target detection, reduces the calculation amount of three-dimensional point cloud segmentation and matching, and improves the operation efficiency and accuracy.

Description

Technical field [0001] The present invention relates to the technical field of computer vision, in particular to a robot grasping pose estimation method based on an object recognition deep learning model. Background technique [0002] In recent years, with the continuous development of the computer vision field, machine vision technology has been widely used in various fields of manufacturing and service industries. The combination of machine vision technology and other traditional disciplines has also become increasingly close. It has had a significant impact in the fields of civil engineering, agriculture, medical treatment, and transportation. The application of machine vision in the mechanical field is particularly extensive. Among them, the robot grasping based on vision has also become This is a current research hotspot. [0003] The vision field can be divided into monocular vision, binocular vision and depth vision according to different sensors. Monocular vision is mainly...

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is to overcome the complex algorithm in the prior art and the time-consuming problem of obtaining high-precision three-dimensional information, and improve the accuracy of information acquisition and the efficiency of grasping

Images