基于多智能体蚁群强化学习的多无人机目标探索与跟踪方法及系统

By improving the ant colony algorithm and the multi-agent proximal policy optimization algorithm, and combining exploration and tracking pheromones, the problem of low efficiency in multi-target exploration and tracking by UAVs in unknown areas is solved, and efficient target discovery and tracking results are achieved.

CN119596981BActive Publication Date: 2026-07-17LANZHOU UNIVERSITY OF TECHNOLOGY
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
LANZHOU UNIVERSITY OF TECHNOLOGY
Filing Date
2024-12-04
Publication Date
2026-07-17

Smart Images

  • Figure CN119596981B_ABST
    Figure CN119596981B_ABST
Patent Text Reader

Abstract

本发明基于多智能体蚁群强化学习的多无人机目标探索与跟踪方法及系统，包括以下步骤：将无人机进行目标跟踪的实际环境划分为网格单元；基于网格单元，进行目标状态初始化，获得无人机的初始观测位置；基于蚁群算法以及无人机的初始观测位置，计算无人机在各网格单元间的转移概率；基于转移概率以及网格单元，建立奖励函数；基于奖励函数以及现有探索信息和跟踪信息，利用多智能体近端策略优化算法对多无人机进行集中训练，获得最优联合决策；基于最优联合决策，使得无人机完成对待探索的多目标的探索与跟踪。本发明技术方案增加了无人机在未知区域中发现目标的可能性，还能够有效的跟随目标。
Need to check novelty before this filing date? Find Prior Art