Mathematical modeling and optimization analysis of multi agent collaborative space allocation scheme for ships
孔令彦 1郑小琪 2蒋楠1
扫码查看
点击上方二维码区域，可以放大扫码查看
作者信息
1. 上海工程技术大学高等职业技术学院,上海 200437
2. 上海交通大学,上海 200437
折叠
摘要
为保证各舰船之间的协同占位或位置协调,确定各舰船需要占据的位置或区域,提出舰船多智能体协同占位方案数学建模优化方法.以舰船多智能体运动数学模型为基础,分析各个舰船智能体的运动和航行状态,判断各个智能体的航行领域,并确定舰船智能体的最近会遇距离;采用MADDPG(Multi-Agent Deep Deterministic Policy Gradient)算法结合该距离构建舰船多智能体多元组,以此获取舰船多智能体最佳的占位决策结果;在此基础上,引入同结构变换优化舰船多智能体占位编队结构,保证每个个体的精准占位以及位姿状态的一致性.测试结果表明,该方法能够有效完成各个智能体的位置决策,保证编队位姿状态的一致性,整个舰船智能体编队位置和理想位置之间的误差均低于(5,5)m.
Abstract
To ensure collaborative occupancy or position coordination among ships,determine the positions or areas that each ship needs to occupy,and propose a mathematical modeling optimization method for ship multi-agent collaborat-ive occupancy scheme.Based on the mathematical model of ship multi-agent motion,analyze the motion and navigation status of each ship intelligent agent,determine the navigation domain of each intelligent agent,and determine the nearest en-counter distance of the ship intelligent agent.Using the MADDPG(Multi Agent Deep Determining Policy gradient)al-gorithm combined with this distance to construct a multi-agent multi group for ships,in order to obtain the optimal occu-pancy decision results for ship multi-agent systems.On this basis,the same structure transformation is introduced to optim-ize the formation structure of ship multi-agent occupancy,ensuring accurate occupancy and consistency of pose state for each individual.The test results show that this method can effectively complete the position decision-making of various intel-ligent agents,ensure the consistency of the formation pose state,and the error between the position of the entire ship intelli-gent agent formation and the ideal position is less than(5,5)m.
关键词
舰船多智能体/协同占位方案/数学建模优化/位姿状态
Key words
multi-intelligent agents for ships/collaborative occupancy plan/mathematical modeling optimization/pose state
维普
万方数据