Workpiece pose rapid high-precision estimation method and apparatusbased on point cloud data

Abstract

The invention discloses a workpiece pose estimation method based on point cloud, which is mainly used for solving the problem of workpiece pose estimation in the field of automatic assembly, especially in the field of small part assembly. The method comprises the steps of point cloud data preprocessing, point cloud virtual view extraction and pose estimation. Wherein the pose estimation step further comprises the steps of performing iterative operation by adopting a particle filter algorithm based on a dynamic model of an iterative closest point algorithm, outputting the pose of the effectiveparticle in a weighted mean mode if an iterative stop condition is met, and calculating the pose of the target workpiece relative to the camera coordinate system through inversion operation. The invention also relates to an apparatus comprising a memory and a processor implementing the above method steps when the processor executes a program stored in the memory.

Description

Technical field [0001] The invention relates to the technical field of machine vision object pose estimation, in particular to a method and device for fast and high-precision estimation of the pose of a workpiece based on point cloud data. Background technique [0002] With the development of industrial robot technology, more and more automated production lines adopt robot operations. In the fields of automatic robot sorting and automatic assembly, vision-guided robot operations are becoming more and more important. Traditional vision guidance is based on 2D images. In recent years, three-dimensional scanning equipment (such as three-dimensional laser scanners, structured light cameras, etc.) has been used to obtain three-dimensional point cloud data on the surface of the workpiece (ie, the workpiece point cloud), and the workpiece point cloud and the workpiece The template point cloud sampled by the CAD model is registered to obtain the rigid transformation between the two, so a...

AI Technical Summary

Problems solved by technology

However, the method based on deep learning needs to use a large amount of data for training. The current method of using deep learning to do pose estimation based on point cloud mainly uses the data in the public data set, mainly for some situations in life scenes. The pose estimation of the item, its pose estimation accuracy is too low to meet the robot grasping and assembly accuracy requirements in industrial scenarios

At the same time, the method of deep learning needs to consume more time for training, and the price of its computing equipment is extremely expensive, and it is not popular in the industry at present.

Images