Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multiple target type oriented mechanical arm self-adaptive grabbing method

A robotic arm, multi-target technology, applied in the field of intelligent robots, can solve problems such as manual intervention, inability to meet changes in the type of target objects, and inability to adjust the type of target objects adaptively, so as to reduce the cost of debugging and modification.

Active Publication Date: 2019-07-09
EFORT INTELLIGENT EQUIP CO LTD
View PDF10 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Therefore, the existing robotic arm grasping method cannot be adaptively adjusted when there are too many types of target objects. The problem of multiple and rapidly changing characteristics

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
  • Multiple target type oriented mechanical arm self-adaptive grabbing method
  • Multiple target type oriented mechanical arm self-adaptive grabbing method
  • Multiple target type oriented mechanical arm self-adaptive grabbing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] In order to make the technical means, creative features, goals and effects achieved by the present invention easy to understand, the present invention will be further elaborated below in conjunction with the accompanying drawings and embodiments.

[0051] Such as Figure 1 to Figure 4 As shown, a method for adaptive grasping of a robotic arm for multi-target types includes the following steps:

[0052] (1) Image acquisition and image preprocessing are carried out first.

[0053] Specifically, the RGBD camera or depth camera fixed at the end of the robot arm is used to obtain the depth image and color image in the scene at a distance of about 0.7m from the object. The depth image contains the spatial state information of the object to be captured in the scene, The pixel value corresponding to each pixel in the depth image represents the distance between the sensor and the object to be captured, and the color image contains surface color information and texture informati...

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 relates to a multiple target type oriented mechanical arm self-adaptive grabbing method. According to the method, based on the prior art, firstly candidate grabbing points are randomly sampled, the legality of the candidate grabbing points is judged, then an RGBD image with legal grabbing point information is generated, a constructed grabbing success rate prediction neural network isused for predicting the grabbing success rate of each legal grabbing point, the grabbing point with the highest grabbing success rate not less than 85% is selected, and finally a clamping jaw is driven by a mechanical arm to conduct grabbing. The method avoids training the neural network repeatedly or adjusting a threshold value manually, and can be used for self-adaptively grabbing most objectswith moderate weight and shapes matched with that a fixture, so that the adaptability of a robot grabbing system in scenes where the types of to-be-grabbed objects are various and change is quick is significantly increased, and moreover, compared with the prior art, the method can greatly reduce the debugging and changing cost of users in the using process.

Description

technical field [0001] The invention relates to the field of intelligent robots, in particular to a multi-object-oriented mechanical arm self-adaptive grasping method. Background technique [0002] The standard process in the existing robotic arm grasping method is to obtain scene image information through an RGBD depth camera, and then generally use two methods to identify and segment the position of the object to be grasped, and finally guide the robotic arm to complete the grasping action. [0003] One of them is a geometric method, and the patent publication number is CN108247635A "A method for grasping objects by a manipulator with depth vision", which uses European clustering, LCCP and CPC segmentation to segment the scene and select the region of interest to capture method, which mainly uses geometric methods to grab objects, but the accuracy and accuracy of segmentation of this method are not ideal when there are many types of targets. The main limitation is that the...

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): B25J9/16
CPCB25J9/1661B25J9/1612B25J9/161
Inventor 易廷昊翟昱代夷帆姜宇帆张云涛马英
Owner EFORT INTELLIGENT EQUIP CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com