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 wit...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.展开更多
In order to qualify shock resistance performance of shipboard equipments and simulate real underwater explosion environment,a novel dual-pulse shock test machine is proposed.The new machine will increase testing capab...In order to qualify shock resistance performance of shipboard equipments and simulate real underwater explosion environment,a novel dual-pulse shock test machine is proposed.The new machine will increase testing capability and meet special shock testing requirement.Two key parts of the machine,the velocity generator and the shock pulse regulator,play an important role in producing the positive acceleration pulse and the succeeding negative acceleration pulse,respectively.The generated dual-pulse shock for test articles is in conformity with an anti-shock test specification.Based on the impact theory,a nonlinear dynamic model of the hydraulically-actuated test machine is established with thorough analysis on its mechanism that involves conversion of gas potential energy and dissipation of kinetic energy.Simulation results have demonstrated that the proposed machine is able to produce a double-pulse acceleration shock in the time domain or a desired shock response spectrum in the frequency domain,which sets up a base for the construction of the machine.展开更多
基金financial support from National Natural Science Foundation of China(Grant No.61601491)Natural Science Foundation of Hubei Province,China(Grant No.2018CFC865)Military Research Project of China(-Grant No.YJ2020B117)。
文摘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.
文摘In order to qualify shock resistance performance of shipboard equipments and simulate real underwater explosion environment,a novel dual-pulse shock test machine is proposed.The new machine will increase testing capability and meet special shock testing requirement.Two key parts of the machine,the velocity generator and the shock pulse regulator,play an important role in producing the positive acceleration pulse and the succeeding negative acceleration pulse,respectively.The generated dual-pulse shock for test articles is in conformity with an anti-shock test specification.Based on the impact theory,a nonlinear dynamic model of the hydraulically-actuated test machine is established with thorough analysis on its mechanism that involves conversion of gas potential energy and dissipation of kinetic energy.Simulation results have demonstrated that the proposed machine is able to produce a double-pulse acceleration shock in the time domain or a desired shock response spectrum in the frequency domain,which sets up a base for the construction of the machine.
