Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Underwater robot optimization decision-making method for non-wide area target search task

An underwater robot and target search technology, applied in the field of optimal decision-making of underwater robots, can solve problems such as increasing the complexity of problems, no search value, lack of quantitative analysis and optimization strategy guidance, etc.

Active Publication Date: 2020-08-28
OCEAN UNIV OF CHINA
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the optimization problem of non-wide-area environment, most of the existing technical solutions are underwater robots to conduct full-coverage search along the non-wide area, or directly adopt greedy strategies to detect discrete suspicious points, lacking relevant quantitative analysis and optimization strategy guidance
Compared with the traditional wide-area environment, the geographical conditions of the non-wide-area environment will limit the movement of the robot to a certain extent, making most of the heading selections worthless and increasing the complexity of the problem.

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
  • Underwater robot optimization decision-making method for non-wide area target search task
  • Underwater robot optimization decision-making method for non-wide area target search task
  • Underwater robot optimization decision-making method for non-wide area target search task

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] Hereinafter, specific embodiments of the present invention will be further described in conjunction with the accompanying drawings.

[0065] The present invention takes underwater oil pipeline inspection as an example, such as figure 1 As shown, when the underwater robot is navigating above the oil pipeline, the camera on the robot scans the pipeline downwards to search for leakage targets. Since the field of view of the camera is often wider than the width of the pipeline, the oil pipeline can be approximately regarded as a series of continuous two-dimensional line or curve. In order to distinguish it from traditional broad areas, special narrow and long areas such as oil pipelines, coastlines, and island reef lines are called non-wide areas.

[0066] In many cases, the non-wide-area environment can be described as a collection of straight lines or curves. At this time, the information of the two-dimensional search map can be further simplified into a one-dimensional ...

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 an underwater robot optimization decision-making method for a non-wide area target search task. The method comprises the steps: abstracting a non-wide area into a series of continuous two-dimensional straight lines or curves, and determining a one-dimensional expression form of the two-dimensional straight lines or curves; expanding the prior discrete data set, and estimating a target probability graph in a non-wide area environment; adjusting the target probability graph, and extracting high-value sub-regions meeting task time constraints; determining an access sequence of the underwater robot to each high-value sub-region according to a given evaluation index; and guiding the underwater robot to reach each high-value sub-region by utilizing the corrected Dubins field, and then scanning each high-value sub-region by the robot in a covering manner until a target search task is completed. Based on a prior discrete data set, a target probability graph with continuous distribution characteristics in a non-wide-area environment can be estimated more accurately, and the feasibility of sub-region extraction is ensured; and a Dubins field correction method is provided to guide the underwater robot to safely and quickly reach each sub-region.

Description

technical field [0001] The invention belongs to the technical field of navigation, guidance and control of underwater robots, and in particular relates to an optimal decision-making method for underwater robots facing non-wide-area target search tasks. Background technique [0002] In recent years, with the continuous development and utilization of the ocean, the use of underwater robots to search for targets in complex sea areas has gradually become a research hotspot in the fields of marine environment monitoring, pipeline inspection, and sea rescue. Research on the optimal decision-making method of underwater robots for target search tasks can provide new research ideas and solutions for marine target search problems, and further improve the autonomous navigation capabilities and environmental adaptability of underwater robots. [0003] The optimal decision-making problem of underwater robots for target search tasks mainly includes two parts: search graph modeling and mot...

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): G05D1/06
CPCG05D1/0692
Inventor 姚鹏王琨魏欣邱立艳刘玉会
Owner OCEAN UNIV OF CHINA
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
Eureka Blog
Learn More
PatSnap group products