Unlock instant, AI-driven research and patent intelligence for your innovation.

ROS-based non-standard object grabbing method and device

A non-standard, object-based technology, applied in the field of automation, can solve problems such as being unable to grasp unknown and irregular objects

Pending Publication Date: 2021-01-22
JIANGSU UNIV OF SCI & TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The current grasping research on objects is more about establishing a database for grasping in advance when the grasped target is known, and searching for a suitable grasping method by comparing the existing models and states in the database. Grasping planning, which cannot be used to grasp unknown and irregular objects

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • ROS-based non-standard object grabbing method and device
  • ROS-based non-standard object grabbing method and device
  • ROS-based non-standard object grabbing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Such as figure 1 and 3 As shown, a ROS-based non-standard object grabbing method includes the following steps:

[0026] Step 1. Establish a manipulator model and a simulation environment in ROS (Robot Operating System), and input the model and labels of the 3Dnet training set into the built convolutional neural network for in-depth training to obtain a probability prediction model.

[0027] methods for generating predictive models such as figure 2 As shown, the specific steps are:

[0028] Step 1.1, establish the manipulator model and simulation environment in ROS, introduce the 3Dnet training set model, obtain the pictures of the training set model, and extract the edge pixels of the model object, where side a is the outer side of the contour edge line, and side b is side a the opposite direction.

[0029] In step 1.2, use the coordinates of points a and b, the geometric center of the object, and the maximum opening and closing distance of the claw head to calcula...

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

PUM

No PUM Login to View More

Abstract

The invention discloses an ROS-based non-standard object grabbing method and device, and the method comprises the steps: building a mechanical arm model and a simulation environment in an ROS, inputting a model and a label of a 3Dnet training set into a built convolutional neural network for deep training, and obtaining a probability prediction model; placing the object in a working area, and acquiring a depth picture and a color picture of the object by the RGB-D camera; the ROS performs Laplace segmentation processing on the picture, analyzes the edge contour of the picture, and calculates and generates all candidate grabbing postures; calculating a grabbing success probability corresponding to each posture by utilizing a prediction model trained by a neural network and combining the candidate grabbing postures, and selecting the grabbing posture with the highest probability as an optimal grabbing strategy; the grabbing coordinates corresponding to the optimal grabbing strategy are calculated, control data are generated and sent to a mechanical arm hardware system, grabbing of non-standard objects is achieved, accurate modeling is conducted on unknown irregular objects, and the optimal grabbing strategy is rapidly obtained.

Description

technical field [0001] The invention relates to the field of automation, in particular to a ROS-based non-standard object grabbing method and device. Background technique [0002] Under the major national strategies such as "German Industry 4.0" and "Made in China 2025", the industrial manufacturing and robotics industries are undergoing great changes. Although industrial robots have been popularized for a long time, they are limited to fixed programs and fixed occasions. The current world has entered the era of artificial intelligence, and robots need to be combined with deep learning to adapt to new and unfamiliar environments and work autonomously. [0003] The current grasping research on objects is more about establishing a database for grasping in advance when the grasped target is known, and searching for a suitable grasping method by comparing the existing models and states in the database. Grasping planning, this kind of scheme cannot be used to grasp unknown and i...

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

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/20G06T7/00G06T7/13G06N3/04
CPCG06F30/20G06T7/0004G06T7/13G06N3/045
Inventor 姜文刚刘建
Owner JIANGSU UNIV OF SCI & TECH