Underwater robot cooperative target searching method based on global information transmission mechanism

Abstract

The invention relates to an underwater robot cooperative target searching method based on a global information transmission mechanism. The method comprises the steps: preliminarily calculating an activity value of each grid in a to-be-searched task region according to prior probability distribution and obstacle distribution of a target, and enabling the activity values to serve as the prior searchgraph information of the region; in combination with ocean current field distribution in the area, calculating robot navigation time between every two adjacent grids, and determining the connection weight between every two adjacent grids; mutually transmitting active values between the adjacent grids at a certain weight; extracting a high-value sub-region by adopting a Gaussian mixture model, andtransmitting the expected income of the high-value sub-region to each grid to realize global sharing and updating of region search graph information; and enabling each robot to independently maintainand iteratively update the respective region search graph and determine a next behavior until the target search task is completed. The method is simple and feasible, the path is smooth, the efficiency is high, and multi-robot cooperative target search is realized.

Description

technical field [0001] The invention belongs to the technical field of navigation, guidance and control of underwater robots, and in particular relates to a collaborative target search method for underwater robots based on a global information transmission mechanism. Background technique [0002] Compared with the traditional manual search mode, the use of high-tech means such as underwater robots to search for targets has the advantages of flexibility, convenience, and high safety. Therefore, it is gradually being applied to large-scale, long-term search tasks in complex marine environments. Generally speaking, the underwater robot sails according to the established route, and detects the mission area through the equipped high-definition camera or side-scan sonar and other equipment, in order to find the target as soon as possible, or reduce the environmental uncertainty as much as possible, or as much as possible Collect environmental information. In addition, compared wi...

AI Technical Summary

Problems solved by technology

The random method can guide the underwater robot to navigate randomly in the mission area, such as Levy flight, Brownian motion, etc. As time accumulates, the underwater robot will gradually cover the area and search for the target, although this method does not require precise positioning and complex The optimization process, but the search efficiency is still low, and it is not suitable for long-term search tasks in large-scale and complex sea areas

The heuristic method is based on the search map information of the region, and adopts various heuristic strategies such as model predictive control, gradient method, neural network, etc. to determine the future search behavior of the underwater robot. This type of method is more flexible and has high search efficiency. The distribution of graph information is complex, and the robot is easy to fall into the local optimal area and cannot detect other high-value areas.

[0004] Through the above analysis, it can be seen that when the search map information in the task area is known, various heuristic methods are more effective, but they often have local optimal problems and lack of global consideration of future information in distant areas

Images