Task planning method for autonomous cooperation of unmanned aerial vehicle cluster

Abstract

The invention discloses a task planning method for autonomous cooperation of an unmanned aerial vehicle cluster. The method comprises the steps of obtaining and distributing a task request; selectinga single Agent task; broadcasting a selection result and a target satisfaction value to the outside; acquiring broadcast information of other Agents; carrying out multi-Agent conflict elimination; broadcasting task planning results. According to the method, the electromagnetic space environment of actual flight of the unmanned aerial vehicle is fully considered, distribution autonomous planning isprovided, compared with the prior art, the method has higher reliability and stronger robustness, no central computing node exists, the system does not only depend on any node, and when the node breaks down, the overall function of the system cannot be affected; the method has the advantages of short communication time delay and low calculation complexity, and each Agent can realize autonomous planning and control by only needing part of information and own states of other Agents, so that the calculation complexity is greatly reduced, and quick response to battlefield environment change can be realized.

Description

technical field [0001] The invention belongs to the field of intelligent planning and scheduling, and in particular relates to a task planning method for autonomous coordination of drone clusters. Background technique [0002] In the existing research on UAV swarm mission planning, according to the different information perspectives and control methods of mission planning, it can be mainly divided into two methods, centralized global planning and distributed autonomous planning. [0003] Centralized global planning means that a central node collects and summarizes all global battlefield information and UAV status information, establishes a unified mission planning and scheduling model, and obtains each UAV’s status after solving the model. The task is assigned a sequence, and the result is sent to the corresponding node in the form of a command for execution. [0004] The advantage of the centralized global planning method is very obvious. Since the global information is co...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a task planning method for autonomous coordination of UAV clusters, which is used to solve the problems of high information quality requirements, poor system invulnerability, high computational complexity and long time-consuming planning process in the prior art. Improving the Robustness, Invulnerability and Reliability of Mission Machine Cluster Mission Planning

Images