Heterogeneous multi-agent multi-target defense decision control method based on differential game

CN119250199AActive Publication Date: 2025-01-03HANGZHOU INNOVATION RES INST OF BEIJING UNIV OF AERONAUTICS & ASTRONAUTICS
-1 Cites 3 Cited by

Patent Information

Application Number
CN202411278551.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-12
Publication Date
2025-01-03
Estimated Expiration
2044-09-12

Smart Images

  • Figure CN119250199A_ABST
    Figure CN119250199A_ABST
Patent Text Reader

Abstract

The invention discloses a heterogeneous multi-agent multi-target defense decision control method based on differential game. The method comprises the following steps: determining an agent team in a three-dimensional half space, wherein the agent team comprises a defender and an attacker; constructing a multi-target defense game environment model and a heterogeneous multi-agent dynamic model; determining a termination condition and a revenue function of the multi-target attack and defense game; according to the multi-target defense game environment model and the heterogeneous multi-agent dynamic model, constructing a single-to-single attack and defense confrontation optimal control strategy and a corresponding value function based on differential game; and determining multi-agent game scene task allocation according to the revenue function and the value function. According to the method, the success rate of target area defense is improved by utilizing the advantages of air-ground cooperation, strict theoretical derivation and mathematical proof are provided for target defense games of air units and ground units, and the problem of many-to-many target defense with large intelligent agent number scale is solved; the method is practical in practical application of air-ground cooperative combat tasks.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Cooperative autonomous network defense decision-making method based on multi-agent layered reinforcement learning

    CN118573415A

  • Method and device for defending against an attacking missile

    EP2482025A2

  • Optimal Strategies in Security Games

    US20130273514A1

  • Method for resource allocation in mission planning

    US20150199623A1

  • Method, defence drone, and defence system for defence against a foreign drone

    WO2023135017A1

Cited By

  • Defense allocation method and device for multi-agent confrontation game and electronic equipment

    CN120725155A

  • Two-vehicle target defense intelligent game playing method based on reachable set

    CN121069999A

  • Defense satellite cooperative game distributed model prediction control method

    CN121523355A