Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A multi-UAV task decision-making method based on maddpg

A multi-UAV and decision-making method technology, applied in the field of flight control, can solve the problems of increased environmental complexity, unstable environment, and increased variance, and achieve the effect of increasing the level of intelligence, improving combat capabilities, and ensuring survivability

Active Publication Date: 2022-07-15
NORTHWESTERN POLYTECHNICAL UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in a multi-UAV environment, it is difficult for traditional reinforcement learning methods to play a role, because in a multi-UAV environment, each UAV is constantly changing, and the environment is no longer stable, and for traditional reinforcement learning algorithms For the strategy gradient method in , as the number of drones increases, the complexity of the environment also increases, which leads to the optimization method of estimating the gradient by sampling, the variance increases sharply, and it is difficult to calculate the final result

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A multi-UAV task decision-making method based on maddpg
  • A multi-UAV task decision-making method based on maddpg
  • A multi-UAV task decision-making method based on maddpg

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0149] In this example, the final network structure is designed as: Actor network structure is fully connected neural network [56; 56; 2], Critic network structure is fully connected neural network [118; 78; 36; 1], two neural networks The hidden layers all use the RELU function as the activation function, such as Image 6 shown. During training, the mini-batch size is 1024, the maximum learning step size (maxepisode) is 30000, the update rate of the auxiliary network is τ=0.01, the learning rate of the critical network is 0.01, and the learning rate of the actor network is 0.001. The AdamOptimizer optimizer is used for learning. The size of the experience pool is 1,000,000. Once the data in the experience pool exceeds the maximum value, the original experience data will be lost, and the constructed multi-UAV task decision-making network will achieve optimal performance.

[0150] The invention initializes the positions of three unmanned aerial vehicles in a designated area in...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a multi-UAV task decision-making method based on MADDPG. The MADDPG algorithm is introduced into the multi-UAV task assignment. First, according to the actual combat environment of the multi-UAV, a two-dimensional combat required for deep reinforcement learning is established. The environment model, secondly, establishes the mathematical description of various threats such as air defense missiles in the multi-UAV combat environment, and finally takes the trajectory, distance of the multi-UAV and the defense threat of the battlefield as constraints, conducts learning and training, and then obtains Multi-UAV mission decision model. This method adopts the experience pool and dual network structure, which greatly improves the operation and convergence speed of the entire network. In the process of high-speed flight of the UAV, the results can be obtained faster, and the purpose of autonomous decision-making of multiple UAVs can be realized. , it can also ensure the efficiency of its mission decision-making in the unknown combat environment.

Description

technical field [0001] The invention belongs to the field of flight control, and particularly relates to a method for multi-unmanned aerial vehicle task decision-making. Background technique [0002] For the military of various countries, drones will become one of the indispensable weapons in the future battlefield. UAVs are likely to become the target of attacks and counterattacks by multiple combat platforms, becoming the most common and deadly "sword" in air combat. Although the existing multi-UAV system can complete some complex combat tasks, as a large fleet cooperative system, the traditional multi-UAV mission decision-making is generally carried out under the conditions of the known battlefield environment. If the set combat plan cannot meet the actual combat environment, it is difficult to make a timely response plan. Therefore, finding a method that can quickly and efficiently assign tasks to multiple UAVs in an unknown combat environment is particularly important...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G05D1/10
CPCG05D1/104
Inventor 李波甘志刚越凯强高晓光万开方高佩忻
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products