Multi-class out-of-order workpiece robot grabbing pose estimation method based on deep learning

A technology of deep learning and pose estimation, applied in neural learning methods, instruments, calculations, etc., can solve the problems of long cycle, low efficiency, and limited expressive ability of complex functions, and achieve the effect of long cycle and low efficiency
CN110428464AActive Publication Date: 2019-11-08ZHEJIANG UNIV
6 Cites 7 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Current Assignee / Owner
ZHEJIANG UNIV
Publication Date
2019-11-08

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a multi-class out-of-order workpiece robot grabbing pose estimation method based on deep learning. The method comprises steps of adopting independent point cloud classificationnetwork, position generation network and attitude generation network; inputting the point cloud information into the point cloud classification network, and classifying the input point cloud information by the point cloud classification network to obtain the category of the point cloud information; synthesizing the category of the point cloud information and the point cloud information into similar point cloud information, inputting the similar point cloud information into a position generation network and an attitude generation network respectively, processing and predicting the similar point cloud information by the position generation network and the attitude generation network respectively to obtain position information and attitude information, and synthesizing to obtain the pose ofthe robot. According to the method, grabbing pose estimation of multiple types of out-of-order workpieces can be achieved, the method is a brand-new end-to-end implementation method based on deep learning, grabbing programming of specific workpieces can be rapidly achieved only by providing few sets of training data, and the requirements of industrial production can be met.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to a method for estimating the pose of a robot grasping belonging to artificial intelligence, in particular to a method for estimating the pose of a robot grasping a multi-category out-of-sequence workpiece based on deep learning. Background technique

[0002] As one of the world's top five industrial robot consumers, China's installation volume increased to 36.0% of the world in 2018. A total of 138,000 industrial robots were installed, a year-on-year increase of 59%. The consumption volume has exceeded the sum of Europe and the United States. Intelligent manufacturing is the main direction of Made in China 2025, and there is a huge demand for intelligent industrial robots. The application of robots for handling and loading and unloading accounts for more than two-thirds, and the added value brought by intelligent upgrading is obvious.

[0003] With the development of artificial intelligence, some scholars have begun to study th...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More