检索结果-南通市图书馆

cooperative multi-target hunting by unmanned surface vehicles based on multi-agent reinforcement learning

Defence Technology（防务技术） 2023年第11期29卷 80-94页

作者： Jiawei Xia Yasong Luo Zhikun Liu Yalun Zhang Haoran Shi Zhong Liu College of Weaponry Engineering Naval University of EngineeringWuhan430033China Institute of Vibration and Noise Naval University of EngineeringWuhan430033China

To solve the problem of multi-target hunting by an unmanned surface vehicle(USV)fleet,a hunting algorithm based on multi-agent reinforcement learning is proposed.Firstly,the hunting environment and kinematic model without boundary constraints are built,and the criteria for successful target capture are given.Then,the cooperative hunting problem of a USV fleet is modeled as a decentralized partially observable Markov decision process(Dec-POMDP),and a distributed partially observable multitarget hunting Proximal Policy Optimization(DPOMH-PPO)algorithm applicable to USVs is proposed.In addition,an observation model,a reward function and the action space applicable to multi-target hunting tasks are designed.To deal with the dynamic change of observational feature dimension input by partially observable systems,a feature embedding block is proposed.By combining the two feature compression methods of column-wise max pooling(CMP)and column-wise average-pooling(CAP),observational feature encoding is established.Finally,the centralized training and decentralized execution framework is adopted to complete the training of hunting strategy.Each USV in the fleet shares the same policy and perform actions independently.Simulation experiments have verified the effectiveness of the DPOMH-PPO algorithm in the test scenarios with different numbers of USVs.Moreover,the advantages of the proposed model are comprehensively analyzed from the aspects of algorithm performance,migration effect in task scenarios and self-organization capability after being damaged,the potential deployment and application of DPOMH-PPO in the real environment is verified.

关键词： Unmanned surface vehicles Multi-agent deep reinforcement learning cooperative hunting Feature embedding Proximal policy optimization

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

cooperative hunting in a discrete predator-prey system

引用

International Journal of Biomathematics 2020年第7期13卷 133-158页

作者： Yunshyong Chow Sophia R-J.Jang Hua-Ming Wang Institute of Mathematics Academia Sinica Taipei 10617Taiwan Department of Mathematics and Statistics Texas Tech University LubbockTX 79409USA Department of Statistics Anhui Normal University Wuhu 241003AnhuiP.R.China

We propose and investigate a discrete-time predator-prey system with cooperative hunting in the predator population.The model is constructed from the classical Nicholson-Bailey host-parasitoid system with density dependent growth rate.A sufficient condition based on the model parameters for which both populations can coexist is derived,namely that the predator’s maximal reproductive number exceeds one.We study existence of interior steady states and their stability in certain parameter regimes.It is shown that the system behaves asymptotically similar to the model with no cooperative hunting if the degree of cooperation is small.Large cooperative hunting,however,may promote persistence of the predator for which the predator would otherwise go extinct if there were no cooperation.

关键词： cooperative hunting discrete predator-prey system predator persistence Neimark-Sacker bifurcation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Multi-UAV cooperative hunting in Cluttered Environments Considering Downwash E®ects

引用

Guidance, Navigation and Control 2023年第1期3卷 61-84页

作者： Shichen Fan Hugh H.-T.Liu Institute for Aerospace Studies University of Toronto 4925 Du®erin Street North YorkOntarioCanada M3H 5T6

This paper presents a novel solution to the three-dimensional (3D) cooperative hunting ofmultiple drones that deals with surrounding a target simultaneously while navigating aroundobstacles in the cluttered dynamic 3D environment. Meanwhile, drones avoid the air°owdownwash force created by the spinning propellers on unmanned aerial vehicles (UAVs) andtheir e®ect on the other UAVs. This solution consists of a 3D Simultaneous Encirclementstrategy, the cooperative hunting objective with a novel revised particle swarm optimization(PSO*) path planning algorithm, a °ocking theory-inspired obstacle avoidance algorithm, and acascade PI controller. Simulation results with varying conditions were carried out to validatethe e®ectiveness of the proposed solution by successfully taking care of the downwash e®ects,and having multiple hunter UAVs hunt and encircle a moving or stationary target in a dynamicor static obstacle-rich cluttered environment.

关键词： cooperative hunting downwash e®ect UAS.

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

cooperative hunting Control for Multi-Underactuated Surface Vehicles

Cooperative Hunting Control for Multi-Underactuated Surface ...

引用

第37届中国控制会议

作者： Binbin Hu Bin Liu Hai-Tao Zhang School of Automation and the State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology

In this study, a control scheme based on the distance and angle between the hunters and invader is designed for the cooperative hunting behavior of the underactuated surface vehicles, in presence of small uncertain disturbance. Based on the Lyapunov synthesis, it is proven that the cooperative hunting error asymptotically converges to zero when the desired immediate control signal of the hunter vehicle is realized. Then, a PID controller is performed to achieve immediate control signal of the hunter vehicle. Several simulation results demonstrate the effectiveness of the controller.

关键词： cooperative hunting Lyapunov synthesis undercatuated surface vehicle

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

A multi-AUVs cooperative hunting Algorithm for Environment with Ocean Current

A multi-AUVs Cooperative Hunting Algorithm for Environment w...

引用

第37届中国控制会议

作者： Qingqin Liu Bing Sun Daqi Zhu Laboratory of Underwater Vehicles and Intelligent Systems Shanghai Maritime University

Multi-AUV cooperative hunting is a very challenging research area,a novel multi-AUVs bio-inspired cooperative hunting algorithm is presented.Firstly,a bio-inspired Neural Network model（BINN） is established to represent the AUV underwater working environment.Each point in the grid map corresponds to the activity of a neural activity in the BINN,and the next target point of the hunting AUV can be planned autonomously according to the neuron activity of the neurons in the BINN.Secondly,the direction decision algorithm is embedded into the BINN hunting model for the ocean current environment,and the four hunting AUVs all move from the left side of the map,with the rhombic formation to hunt the evader AUV.And the integrated algorithm proposed is compared with the hunting method without direction decision.Finally,simulation results are presented to demonstrate that the proposed algorithm is effective for cooperative hunting mission.

关键词： Autonomous underwater vehicle cooperative hunting direction decision algorithm bio-inspired neural network

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Impact of time delay and cooperation strategy on the stability of a predator-prey model with Holling type III functional response

引用

International Journal of Biomathematics 2023年第3期16卷 165-193页

作者： I.Benamara A.El Abdllaouit J.Mikramt Laboratory of Mathematics Computer Science&Applications-Security of Information Department of Mathematics Faculty of Sciences Mohammed V University in RabatMorocco

In this paper,we propose and analyze a delayed predator-prey model with Holling type III functional response taking into account cooperation behavior in predators.The time delay is introduced in the attack rate to represent the time necessary to trigger the attack.Each analytical result is followed by an ecological interpretation.We investigate the effect of hunting cooperation on both the number and the level of positive steady states.We observe that the level of the positive equilibrium decreases when increasing the hunting cooperation parameter.Then,we study the impact of the delay as well as the cooperation in hunting on the dynamics of the system.We prove that the presence of delay in the attack rate induces stability switches around the coexisting equilibrium when predators cooperate.In addition,we consider the discrete delay as a bifurcation parameter and prove that the model undergoes a Hopf-bifurcation at the coexisting equilibrium when the delay crosses some critical values.Numerical simulations are presented to confirm our analytical findings.

关键词： Predator-prey system Holling type III discrete delay cooperative hunting Hopf-bifurcation switch of stability

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A PE game with one superior hunter and multi-pursuer against an evader

A PE game with one superior hunter and multi-pursuer against...

引用

第40届中国控制会议

作者： Hao Tang Weidong Zhang Min Sun Bin Lin Zhihuan Hu Shanghai Jiao Tong University

In this paper, we consider a pursuit-evasion（PE） game with multi-pursuer and one hunter against an evader where the evader has a speed that is higher than the speed of each pursuer but is lower than the speed of the hunter. We are concerned with the problem how multi-pursuer and one hunter cooperate to capture the evader successfully. We present strategy of dynamic alliance to make sure the multi-pursuer are not redundant. The proposed algorithm uses the well-known Apollonius circle mechanism to define the capture region of the agents based on the locations and the speeds. A chase-following algorithm based on predicting intercept points is proposed. The evader’s escape strategy based on improved artificial potential field method are also studied. The results obtained from numerous simulations demonstrate the validity of the cooperative hunting control and the evader’s escape strategy.

关键词： Pursuit-evasion game cooperative hunting Escape strategy

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Research on multi-robots self-organizing cooperative pursuit algorithm based on Voronoi graph

Research on multi-robots self-organizing cooperative pursuit...

引用

第三十九届中国控制会议

作者： Yan Wang Guohao He Yuedong Ma Guojie Kong Jianwei Gong Intelligent Vehicle Research Center Beijing Institute of Technology North Automatic Control Technology Institute Beijing Special Vehicle Academy

For the problem that the traditional distributed algorithm based on Voronoi graph has a low efficiency and a large standard deviation in capturing random targets, an improved Voronoi graph self-organizing cooperative hunting algorithm is proposed. Through selecting the nearest midpoint of common Voronoi graph boundary, pursuers find their own targets, and become the pursuers alliance for the same target. Each pursuer in the group uses target Voronoi graph area minimization strategy to capture. Simulation results show that the algorithm proposed in this paper can significantly improve the average time and standard deviation of target capture when the targets adopts different escape strategies.

关键词： Multi-robots Self-organizing cooperative hunting Voronoi graph

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：