Overhead line robot obstacle crossing method, device and equipment based on AI visual identification

A visual recognition and robotics technology, applied in the field of robotics, can solve the problems of easily damaged collision sensors and inability to successfully overcome obstacles.

Active Publication Date: 2021-04-20
中科开创(广州)智能科技发展有限公司
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The main purpose of this application is to provide an obstacle surmounting method for overhead line robots based on AI visual recognition, aiming to solve the technical problems that the collision sensors of existing robots are easily damaged, and the collision sensors cannot be successfully surmounted after the collision sensors are easily damaged.

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
  • Overhead line robot obstacle crossing method, device and equipment based on AI visual identification
  • Overhead line robot obstacle crossing method, device and equipment based on AI visual identification
  • Overhead line robot obstacle crossing method, device and equipment based on AI visual identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0053] refer to figure 1 , an embodiment of the present application based on the AI ​​visual recognition method for the overhead line robot obstacle, including:

[0054] S1: Obtain the route information of the overhead line in the forward direction of the robot collected through AI visual recognition, wherein the route information includes the type of obstacles set on the overhead line;

[0055] S2: According to the route information, it is judged whether there is a designated obstacle within a first preset distance in the forward direction;

[0056] S3: If yes, then con...

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 the field of robots, and discloses an overhead line robot obstacle crossing method based on AI visual recognition, and the method comprises the steps: obtaining the route information, collected through vision, of an overhead line in the advancing direction of a robot, wherein the route information comprises the type of an obstacle disposed on the overhead line; according to the route information, judging whether a specified obstacle exists within a first preset distance in the advancing direction or not; if yes, controlling the forward speed of the robot to be reduced from the first speed to a second speed; starting a collision sensor and an obstacle crossing algorithm corresponding to the obstacle type of the specified obstacle; controlling the robot to cross a specified obstacle through a collision sensor and an obstacle crossing algorithm. The speed change of the robot in the inspection process is controlled through the AI visual recognition analysis and acquisition device for matching and recognizing the obstacle type and the obstacle distance, the failure probability of high-speed collision of the collision sensor is reduced, obstacle crossing can still be conducted smoothly when the collision sensor fails, the line inspection efficiency of the overhead line robot is improved, and the service life of the overhead line robot is prolonged.

Description

technical field [0001] The present application relates to the field of robotics, in particular to an obstacle-surmounting method, device and equipment for an overhead line robot based on AI visual recognition. Background technique [0002] It is the future development trend for robots to replace manual labor to carry out dangerous and heavy inspection work, and it is in line with the corresponding national policies. Now the same type of robot on the market mainly detects whether there is an obstacle through the collision sensor carried on the robot body, and controls the robot to cross the obstacle to complete the inspection work, but the robot will not slow down until it touches the obstacle. It is easy to be damaged. After the collision sensor is damaged, obstacles cannot be detected, and the robot cannot cross obstacles so that the inspection task fails. If the set training speed is very slow, the inspection efficiency will be low, which seriously affects the actual use e...

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): G05D1/02
Inventor 王齐欧阳开一邱文锋夏永晓
Owner 中科开创(广州)智能科技发展有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap