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

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...

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.

Images