Unmanned underwater vehicle IVFH (intelligent vector field histogram) collision avoidance method

Abstract

The invention relates to an unmanned underwater vehicle IVFH (intelligent vector field histogram) collision avoidance method, in particular, an unmanned underwater vehicle two-dimensional IVFH (intelligent vector field histogram) collision avoidance method. With the method adopted, an unmanned underwater vehicle can obtain the location information of an obstacle through processing sensor data in a navigation process, so that the unmanned underwater vehicle can focus on security and rapidity, and the unmanned underwater vehicle can have a certain intelligence like human beings; and reasonable collision avoidance actions can be decided based on factors such as the distance of the obstacle, the distance of a target point, free grid percentage and known field of vision percentage, for example, course and navigational speed instructions can be determined, so that the unmanned underwater vehicle can avoid the obstacle so as to prevent danger. The method of the invention is suitable for collision avoidance conditions of unmanned underwater vehicles.

Description

technical field [0001] The invention relates to a collision avoidance method for an unmanned underwater vehicle. Background technique [0002] Unmanned underwater vehicle is an effective means to assist human beings to complete ocean development. Due to the complexity, uncertainty, and non-structural nature of the marine environment, unmanned underwater vehicles need to sense the surrounding environmental information in real time on the basis of global path planning during navigation, using sonar as the main detection method. The local environment makes a reasonable action response to avoid risks and obstacles that are beyond the prior knowledge and not predicted by the global path planning. The ability to avoid collisions is a concentrated expression of the intelligence level of unmanned underwater vehicles, and it is of great significance for them to realize true autonomy. [0003] Collision avoidance methods commonly used for unmanned underwater vehicles include artific...

AI Technical Summary

Problems solved by technology

Intelligent computing methods represented by neural networks, genetic algorithms, and particle swarm optimization provide online learning and online optimization solutions for collision avoidance problems, but often require large storage space and running time during the calculation process, which is difficult to meet real-time requirements, which may lead to collisions of unmanned underwater vehicles before they can make collision avoidance decisions in the future

Since the VFH method was proposed and widely used in 1991, on the one hand, it has effectively proved its practicability, and on the other hand, it has gradually exposed the shortcomings of the method, such as sensitivity to thresholds and lack of consideration of robot kinematics and dynamics characteristics. However, a series of improved VFH methods have been proposed one after another: the VFH+ method takes into account the width and trajectory of the robot, so that it can gradually turn to the predetermined heading and meet the constraints of robot kinematics and dynamics, but this method is only a pure local obstacle avoidance algorithm. It is easy to get lost in multiple obstacles; the VFH* method adds a prediction mechanism on the basis of the VFH+ method, that is, predicts the relationship between the position of the robot and the surrounding environment in the following cycles, and optimizes the selection among several possible angles, so that the robot A better motion direction can be found in a local area, but this method is still a local obstacle avoidance algorithm in essence, and this method does not take into account the speed of surrounding obstacles, and the motion direction it selects may not be optimal , and there is a contradiction between execution time and prediction accuracy when using this algorithm; the VFH# algorithm first predicts the local environment, re-determines the static dynamic grid, and provides accurate parameters for the subsequent optimal selection. This algorithm is no longer The obstacle avoidance algorithm in a static environment is an obstacle avoidance algorithm in a local dynamic environment. Using this method, the robot can choose a better direction of travel in a local dynamic environment

Images