Multi-sensor cooperative search decision method and device based on bayesian stackelberg game

By using a Bayesian Stackelberg game model, the multi-sensor system is treated as the leader and the target object as the follower. Their mutual influence in actual search is simulated, and the sensor heading combination is optimized. This solves the problem of decision accuracy caused by the target object's active avoidance behavior, and achieves higher collaborative search accuracy and robustness.

CN122333145APending Publication Date: 2026-07-03CHINESE PEOPLES LIBERATION ARMY UNIT 91977
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610340384.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-19
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

In existing technologies, multi-sensor collaborative search strategies fail to effectively consider the active avoidance behavior of target objects, resulting in a large discrepancy between mathematical models and actual conditions, which affects the accuracy of decision-making.

Method used

A Bayesian Stackelberg game-based approach is adopted, with the multi-sensor system as the leader and the target object as the follower. A game model is established, and the mutual influence between the two parties during the actual search process is simulated by adjusting the leader and follower strategies. A cooperative detection probability model and payoff function are constructed, and the game equilibrium is solved to optimize the sensor heading combination.

Benefits of technology

It improves the accuracy of multi-sensor collaborative search decision-making, enhances the accuracy of leader hybrid strategies by simulating the active avoidance behavior of target objects, overcomes the problems of initial belief bias and local optima, and improves the robustness and accuracy of decision-making.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122333145A_ABST
    Figure CN122333145A_ABST
Patent Text Reader

Abstract

The application discloses a multi-sensor cooperative search decision method and device based on a Bayesian Stackelberg game, and belongs to the technical field of multi-sensor cooperative control. The method comprises the following steps: acquiring performance parameters of each sensor and characteristic parameters of a target object, and establishing a cooperative detection probability model; regarding a multi-sensor system composed of the sensors as a leader, regarding a heading combination of the sensors as a leader strategy, regarding the target object as a follower, regarding a heading of the target object as a follower strategy, and constructing a first income function of the leader and a first income function of the follower according to the cooperative detection probability model to obtain a game model; respectively adjusting the leader mixed strategy and the follower strategy to interact with the game model, solving a first expected leader mixed strategy when a game equilibrium is reached and determining a first expected heading combination of the sensors to obtain a first cooperative search decision result. The application can improve the accuracy and efficiency of multi-sensor cooperative search.
Need to check novelty before this filing date? Find Prior Art