Multi-unmanned aerial vehicle task decision-making method based on MADDPG
A multi-UAV and decision-making technology, applied in the field of flight control, can solve problems such as increased environmental complexity, increased variance, and unstable environment
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0149] In this example, the final network structure is designed as: Actor network structure is [56; 56; 2] fully connected neural network, critic network structure is [118; 78; 36; 1] fully connected neural network, two neural networks The hidden layer uses the RELU function as the activation function, such as Figure 6 shown. The mini-batch size during training 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 Critic network is 0.01, and the learning rate of the Actor network is 0.001. Both networks are The AdamOptimizer optimizer is used for learning, and 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 performance of the multi-UAV task decision-making network constructed is optimal.
[0150] The present invention initializes the positions of three unmanned aerial vehicles in...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com