上海航天（中英文）2024，Vol.41Issue(1)：108-115,8.DOI:10.19328/j.cnki.2096-8655.2024.01.014
基于多智能体深度强化学习的多星观测任务分配方法
Multi-Satellite Observation Task Allocation Method Based on Multi-Agent Deep Reinforcement Learning
王桢朗 1何慧群 2周军 1金云飞1
作者信息
- 1. 上海卫星工程研究所,上海 201109
- 2. 上海航天技术研究院,上海 201109
- 折叠
摘要
Abstract
To address the task allocation scenario under complex and constrained conditions in a multi-satellite environment,a multi-satellite autonomous decision-making observation task allocation algorithm is proposed.The algorithm uses a multi-agent deep reinforcement learning algorithm based on centralized training and distributed execution.The satellite agents trained by this algorithm have certain autonomous collaboration capabilities and the ability to independently achieve the efficient allocation of multi-satellite observation tasks even if there is no central decision-making node or communication restriction.关键词
多智能体系统/深度强化学习/多星系统/多智能体深度确定性策略梯度算法/任务规划Key words
multi-agent system/deep reinforcement learning/multi-satellite system/multi-agent deep deterministic policy gradient(MADDPG)/mission planning分类
信息技术与安全科学引用本文复制引用
王桢朗,何慧群,周军,金云飞..基于多智能体深度强化学习的多星观测任务分配方法[J].上海航天（中英文）,2024,41(1):108-115,8.
