AUV multi-strategy navigation method based on submarine topography matching

Abstract

The invention discloses an AUV multi-strategy navigation method based on submarine topography matching. The method comprises the steps: constructing a topography adaptive region selection model basedon a machine learning algorithm, wherein the topography adaptive region selection model includes a suitable topography matching region, a topography matching transition region, and an unsuitable topography matching region; during specific navigation, analyzing a type of a navigation area through collected real-time data, and carrying out navigation based on a multi-beam sonar underwater topographyelevation image matching auxiliary method for the suitable topography matching region; for the topography matching transition region, starting a side-scan sonar, and carrying out underwater side-scansonar image matching by using a multi-beam depth finder and the side-scan sonar data to assist ship position calculation for navigation; and for the unsuitable topography matching region, starting the side-scan sonar, and carrying out navigation based on simultaneous localization and a map construction algorithm. The navigation method has better significance and value in practical application.

Description

technical field [0001] The invention relates to the field of AUV autonomous navigation, in particular to an AUV multi-strategy navigation method based on seabed terrain matching. Background technique [0002] With the development of integrated navigation, when underwater vehicles sail on the seabed, due to the lack of GPS navigation, the method based on inertia / dead reckoning is generally adopted, and is equipped with expensive auxiliary equipment, such as attitude heading reference system or Doppler velocity Recorder; however, due to the principle and characteristics of the inertial sensor itself, the inertial navigation system will generate cumulative errors over time, and cannot achieve long-term underwater high-precision navigation. At present, the main solution is to make the AUV float up to receive GPS signals to correct the accumulated errors, but this method is not conducive to the AUV's underwater task execution. [0003] As a geophysical navigation method, Terrain...

AI Technical Summary

Problems solved by technology

[0002] With the development of integrated navigation, when underwater vehicles sail on the seabed, due to the lack of GPS navigation, the method based on inertia / dead reckoning is generally adopted, and is equipped with expensive auxiliary equipment, such as attitude heading reference system or Doppler velocity recorder; however, due to the principle and characteristics of the inertial sensor itself, the inertial navigation system will generate cumulative errors over time, and cannot achieve long-term underwater high-precision navigation

At present, the main solution is to make the AUV float to receive GPS signals to correct the accumulated error, but this method is not conducive to the AUV's underwater task execution

[0003] As a geophysical navigation method, Terrain Adaptive Navigation (TAN) can provide accurate position estimation for AUV's long-range underwater operation. Three-dimensional space path planning method”, however, this method only plans the traditional obstacle avoidance path, and does not consider the navigation ability of the terrain, and the path cannot be modified in real time considering the change of terrain information when the robot executes the path.

Another example is "Path Planning Method for AUV Underwater Terrain Matching Navigation". When executing the path, the path cannot be modified in real time considering the change of terrain information

[0004] Aiming at the defects existing in the existing AUV navigation, the present invention proposes a new multi-strategy navigation algorithm to overcome the defect of floating and correcting position information. Based on the terrain adaptation area selection model of the machine learning algorithm, different strategies are selected according to the characteristics of different regions AUV Navigation

Images