Multi-layer multi-granularity cluster task planning method based on sequential distribution

Abstract

The invention discloses a multilayer multi-granularity cluster task planning method based on sequential distribution. The method comprises multi-layer dimension reduction belief information representation, an interlayer information interaction model and sequential distribution of online prediction functions. The multi-layer dimensionality reduction belief information is expressed as establishmentof a unified patrol model, the granularity of information concerned by each layer of unmanned aerial vehicle in the interlayer information interaction model is different but has a certain corresponding relationship, and the corresponding relationship between each layer of unmanned aerial vehicles mainly comprises belief information transmission from bottom to top and command information transmission from top to bottom; the sequential distribution of the online prediction functions is based on a myopia scheduling algorithm, and the myopia scheduling algorithm comprises single unmanned aerial vehicle patrol based on a heuristic function, subgroup patrol based on a sequential distribution technology and centralized scheduling of cluster patrol. The unmanned aerial vehicle cluster continuous reconnaissance task planning method can better realize task planning of unmanned aerial vehicle cluster continuous reconnaissance under complex conditions, and is beneficial to popularization and application.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicle cluster control, in particular to a multi-layer and multi-granularity cluster task planning method based on sequential allocation. Background technique [0002] UAV swarms have developed rapidly in recent years, especially UAV swarms with reconnaissance capabilities are becoming a common means of situational awareness. We consider a scenario where a swarm of drones continuously scouts an area, collecting as much situational information as possible. This is very common in reality, such as searching for missing tourists in mountainous areas, scouting the battlefield environment, obtaining disaster information, patrolling plant protection, and so on. In these areas, the environment is dynamic and uncertain, and each UAV can only obtain local information at the current moment. In other words, the environment is partially observable. Therefore, the difficulty lies in how to carry out...

AI Technical Summary

Problems solved by technology

However, as the number of drones increases, the number of possible actions increases exponentially, and some baseline algorithms, such as Partially Observable Monte Carlo schemes, struggle to solve our problem

Images