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

Method for identifying grabbing stability of manipulator based on deep learning

A recognition method and deep learning technology, applied in the field of robot perception, can solve the problems such as the large difference in the duration of tactile information, the misalignment of valid data parts, and the inability to obtain similarity evaluation, and achieve a robust effect.

Active Publication Date: 2017-07-18
TSINGHUA UNIV
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the dynamic time warping algorithm often cannot obtain accurate similarity evaluation results when the duration of tactile information is large, the valid data is not aligned, and the data contains noise.

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
  • Method for identifying grabbing stability of manipulator based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The manipulator grasping stability identification method based on deep learning proposed by the present invention comprises the following steps:

[0030] (1) Gather the tactile data of the manipulator under different grasping stability, including the following steps:

[0031] (1-1) Assuming that the manipulator has a fingers in total, in one embodiment of the present invention, a=3, and b touch sensors are respectively set on a fingers, in an embodiment of the present invention, b=24, each The b tactile sensors on the finger form a contact array;

[0032](1-2) Control the manipulator to grab the item with random grabbing points and grabbing force, and collect the tactile data during the grabbing process. Let the collected tactile data be T, and the tactile data T is a three-dimensional matrix, and the three dimensions are respectively It is: the number of fingers a of the manipulator, the number of tactile sensors b of a finger, and the number of collections t. Let U b...

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 method for identifying the grabbing stability of a manipulator based on deep learning, and belongs to the technical field of robot perception. The method in the invention comprises the steps of: acquiring tactile data in different grabbing stabilities at first, then, converting time series picture data into a picture, training a deep learning network by utilizing tactile picture data, and finally, identifying the tactile picture data having the unknown stability by utilizing the deep learning network. By means of the method in the invention, training of the deep learning network is carried out based on original data different in time duration, so that the obtained network has the robustness in data duration. The deep learning network in the method is used for updating network parameters based on integrated input data; and influence on the network is very low only when labels of a few data have errors. Thereby, the method has the robustness to noise data.

Description

technical field [0001] The invention relates to a deep learning-based recognition method for grasping stability of a manipulator, which belongs to the technical field of robot perception. Background technique [0002] With the continuous development of technology and the deepening of demand, robot perception technology has become a research hotspot. The primary perception mechanism of robots is vision, but visual information is easily affected by factors such as occlusion and light intensity. Tactile information will not be disturbed by these factors, so tactile information is an important supplement to visual information in certain scenarios. The present invention utilizes the frictional force of the grasping point reflected by the tactile information when the manipulator grasps the object, the elasticity of the object, and the contact between the finger and the object, etc., and uses the tactile information to identify the grasping stability. The invention utilizes the t...

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): G06F17/50B25J9/16G06N99/00
CPCB25J9/163B25J9/1633G06F30/17G06N20/00
Inventor 刘华平覃杰孙富春
Owner TSINGHUA UNIV
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