Unmanned vehicle search path planning method and device and unmanned vehicle

Abstract

The invention discloses a path planning method and device for searching of an unmanned aircraft and the unmanned aircraft, and belongs to the technical field of intelligent search and rescue on the sea. The method comprises the following steps: S1, analyzing marine accident information by adopting a Monte Carlo random particle simulation method to establish a particle initial distribution diagram, and performing clustering analysis on the initial distribution of the particles by using a Gaussian mixture model (GMM), and further determining a target search area corresponding to the optimal particle inclusion probability based on a confidence ellipse algorithm of corrosion expansion; s2, establishing an under-actuated unmanned vehicle steering mathematical model adaptive to boundary characteristics, and determining a steering non-working path; s3, optimizing the global search discovery probability and the search total path based on a dual-normalization multi-target search planning algorithm to obtain an area coverage optimal path planning strategy. According to the invention, a search area determination method is provided, a classic parallel line sea sweeping search strategy is improved to realize area search planning, and the search success probability of persons in distress is improved on the premise of invested limited search power.

Description

technical field [0001] The invention belongs to the technical field of maritime intelligent search and rescue, and more particularly relates to a path planning method and device for unmanned aerial vehicle search, and the unmanned aerial vehicle. Background technique [0002] Existing search forces have certain deficiencies in the emergency response and search requirements of maritime emergencies, and manned search forces are not competent for large-area, long-term, and dangerous environment search tasks. In recent years, with the rapid development of unmanned aerial vehicles represented by unmanned boats, this type of unmanned aerial vehicles usually has long-distance autonomous navigation capabilities, strong adaptability to harsh sea conditions and shoal waters, and is an efficient search belt for maritime targets. Here comes a new opportunity. [0003] In the event of a maritime accident, in order to minimize the loss of life and property, it is necessary to accurately ...

AI Technical Summary

Problems solved by technology

Patent CN102167038B optimizes the path of automatic driving of tractors in field operations, and realizes high efficiency and full area coverage of farmland operation plots by automatic driving tractor units; Or traverse sequentially, just simply analyze the relationship between the steering radius and the working width to select the steering mode

At present, in the field of unmanned boats, it focuses on point-to-point path planning and path optimization. For example, CN110442135B focuses on improving the genetic operation process of genetic algorithms to realize the path optimization of multi-way points of unmanned vehicles, which belongs to point-to-point in essence. The scope of path planning cannot be simply transplanted for path optimization of area coverage problems

[0005] To sum up, it can be seen that the search area determination and search path planning in the prior art are generally inefficient, which affects the search success rate

Images