Digital-analog hybrid unmanned cluster brain swarm intelligence cooperative navigation method

By employing a hybrid digital-analog unmanned swarm brain-like collaborative navigation method, combining motion models and deep reinforcement learning, a local obstacle map is constructed, solving the navigation problem in unknown dynamic environments and achieving precise navigation and obstacle avoidance.

CN118643858BActive Publication Date: 2026-06-02NANJING UNIV OF POSTS & TELECOMM
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410574776.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-10
Publication Date
2026-06-02
Estimated Expiration
2044-05-10

AI Technical Summary

Technical Problem

Traditional global path planning algorithms cannot handle obstacles in unknown or dynamic environments in unmanned combat scenarios, resulting in inaccurate navigation and failure to achieve optimal path planning.

Method used

A brain-like collaborative navigation method for unmanned swarms, combining digital and analog models, is adopted. This method integrates the motion model of unmanned intelligent agents with deep reinforcement learning, processes state information through long short-term memory networks, designs a dynamic reward mechanism, and utilizes swarm intelligence collaboration technology to construct a local obstacle map and dynamically integrate navigation algorithms.

Benefits of technology

The performance of the navigation algorithm has been improved, enabling accurate navigation in unknown dynamic environments, avoiding obstacles and reaching the target point.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118643858B_ABST
    Figure CN118643858B_ABST
Patent Text Reader

Abstract

This invention discloses a hybrid mathematical-analog unmanned swarm brain-like collaborative navigation method, comprising: Step 1: establishing a motion model and a perception model for the unmanned intelligent agent swarm; Step 2: constructing a navigation algorithm based on a mathematical model using a dynamic window algorithm; Step 3: constructing a dual-delay deep deterministic gradient network with temporal correlation by combining a long short-term memory network; Step 4: obtaining the coordinates of the nearest obstacles for each intelligent agent in the unmanned swarm and performing density clustering on the coordinate set; Step 5: calculating the obstacle density ρ based on a local information map. obs Combined with intelligent agent S i Step 6: Calculate the dynamic fusion weights based on the closest distance to the obstacle. i This invention employs a hybrid fusion of mathematical model-based methods and deep reinforcement learning to improve decision-making speed. It dynamically fuses the two navigation algorithms based on environmental complexity, further enhancing the performance of deep reinforcement learning-based navigation algorithms.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Unmanned cluster collaborative crowd-sourcing target search method based on distributed reinforcement learning

    CN116935058A

  • Evolved environment information transmission method and device between cooperative targets

    CN117519226A