In recent years,the concept of digital human has attracted widespread attention from all walks of life,and the modelling of high-fidelity human bodies,heads,and hands has been intensively studied.This paper focuses on...In recent years,the concept of digital human has attracted widespread attention from all walks of life,and the modelling of high-fidelity human bodies,heads,and hands has been intensively studied.This paper focuses on head modelling and proposes a generic head parametric model based on neural radiance fields.Specifically,we first use face recognition networks and 3D facial expression database FaceWarehouse to parameterize identity and expression semantics,respectively,and use both as conditional inputs to build a neural radiance field for the human head,thereby improving the head model’s representation ability while ensuring editing capabilities for the identity and expression of the rendered results;then,through a combination of volume rendering and neural rendering,the 3D representation of the head is rapidly rendered into the 2D plane,producing a high-fidelity image of the human head.Thanks to the well-designed loss functions and good implicit representation of the neural radiance field,our model can not only edit the identity and expression independently,but also freely modify the virtual camera position of the rendering results.It has excellent multi-view consistency,and has many applications in novel view synthesis,pose driving and more.展开更多
System upgrades in unmanned systems have made Unmanned Aerial Vehicle(UAV)-based patrolling and monitoring a preferred solution for ocean surveillance.However,dynamic environments and large-scale deployments pose sign...System upgrades in unmanned systems have made Unmanned Aerial Vehicle(UAV)-based patrolling and monitoring a preferred solution for ocean surveillance.However,dynamic environments and large-scale deployments pose significant challenges for efficient decision-making,necessitating a modular multiagent control system.Deep Reinforcement Learning(DRL)and Decision Tree(DT)have been utilized for these complex decision-making tasks,but each has its limitations:DRL is highly adaptive but lacks interpretability,while DT is inherently interpretable but has limited adaptability.To overcome these challenges,we propose the Adaptive Interpretable Decision Tree(AIDT),an evolutionary-based algorithm that is both adaptable to diverse environmental settings and highly interpretable in its decision-making processes.We first construct a Markov decision process(MDP)-based simulation environment using the Cooperative Submarine Search task as a representative scenario for training and testing the proposed method.Specifically,we use the heat map as a state variable to address the issue of multi-agent input state proliferation.Next,we introduce the curiosity-guiding intrinsic reward to encourage comprehensive exploration and enhance algorithm performance.Additionally,we incorporate decision tree size as an influence factor in the adaptation process to balance task completion with computational efficiency.To further improve the generalization capability of the decision tree,we apply a normalization method to ensure consistent processing of input states.Finally,we validate the proposed algorithm in different environmental settings,and the results demonstrate both its adaptability and interpretability.展开更多
A formation model of manned/unmanned aerial vehicle(MAV/UAV) collaborative combat can qualitatively and quantitatively analyze the synergistic effects.However,there is currently no effective and appropriate model cons...A formation model of manned/unmanned aerial vehicle(MAV/UAV) collaborative combat can qualitatively and quantitatively analyze the synergistic effects.However,there is currently no effective and appropriate model construction method or theory,and research in the field of collaborative capability evaluation is basically nonexistent.According to the actual conditions of cooperative operations,a new MAV/UAV collaborative combat network model construction method based on a complex network is presented.By analyzing the characteristic parameters of the abstract network,the index system and complex network are combined.Then,a method for evaluating the synergistic effect of the cooperative combat network is developed.This method provides assistance for the verification and evaluation of MAV/UAV collaborative combat.展开更多
The close-in weapon system(CIWS)is a combat system that faces a complex environment full of dynamic and unknown challenges,whose construction and planning require a systematic design method.Multiliving agent(MLA)theor...The close-in weapon system(CIWS)is a combat system that faces a complex environment full of dynamic and unknown challenges,whose construction and planning require a systematic design method.Multiliving agent(MLA)theory is a methodology for the combat system design,which uses the livelihood degree to evaluate the multi-dimensional long-term operational effectiveness of the system;whereas,there is still no uniform quantization framework for the livelihood degree,and the adjustment methods of livelihood degree need to be further improved.In this paper,we propose the uniform quantization framework for the livelihood degree and detailed discuss the methods of livelihood adjustment.Based on the MLA theory,the multi-dimensional operational effectiveness of the missile-gun integrated weapon system(MGIWS)is analyzed,and the long-term combat effectiveness against the saturation attack is assessed.Furthermore,the planning problem of the equipment deployment and configuration is investigated.Two objectives,including the overall livelihood degree and cost-effectiveness(CE),are proposed,and the optimization method based on genetic algorithm(GA)is studied for the planning problem.展开更多
Multi-living agent system （MLAS） is a new concept in the field of complex system research, which is peculiarly suitable for the design and analysis of a complex information system in a serious confrontation and tigh...Multi-living agent system （MLAS） is a new concept in the field of complex system research, which is peculiarly suitable for the design and analysis of a complex information system in a serious confrontation and tight constraint environment. However, the universal method to quantitatively measure the living degree of an MLAS remains uncertain, which is critical to the self-organizing process. Therefore, a novel analytic hierarchy process （AHP） based method with dependent pairwise comparison matrix （PCM） for the evaluation of living degree of the MLAS is proposed, which eliminates the shortcoming of fixed PCM in traditional process. Furthermore, to avoid the annoying procedure of the consistency validation, the PCMs are appropriately reconstructed. Through an illustration of the netted radar system, the calculation detail is explicitly presented. Altogether, the advanced evaluation method successfully accomplishes the preset objective and promotes the development of the MLAS theory and AHP as well.展开更多
This paper realizes the full-domain collaborative deployment of multiple interference sources of the global satellite navigation system(GNSS)and evaluates the deployment effect to enhance the ability to disturb the at...This paper realizes the full-domain collaborative deployment of multiple interference sources of the global satellite navigation system(GNSS)and evaluates the deployment effect to enhance the ability to disturb the attacker and the capability to defend the GNSS during navigation countermeasures.Key evaluation indicators for the jamming effect of GNSS suppressive and deceptive jamming sources are first created,their evaluation models are built,and their detection procedures are sorted out,as the basis for determining the deployment principles.The principles for collaboratively deploying multi-jamming sources are developed to obtain the deployment structures(including the required number,structures in demand,and corresponding positions)of three single interference sources required by collaboratively deploying.Accordingly,simulation and hardware-in-loop testing results are presented to determine a rational configuration of the collaborative deployment of multi-jamming sources in the set situation and further realize the full-domain deployment of an interference network from ground,air to space.Varied evaluation indices for the deployment effect are finally developed to evaluate the deployment effect of the proposed configuration and further verify its reliability and rationality.展开更多
文摘In recent years,the concept of digital human has attracted widespread attention from all walks of life,and the modelling of high-fidelity human bodies,heads,and hands has been intensively studied.This paper focuses on head modelling and proposes a generic head parametric model based on neural radiance fields.Specifically,we first use face recognition networks and 3D facial expression database FaceWarehouse to parameterize identity and expression semantics,respectively,and use both as conditional inputs to build a neural radiance field for the human head,thereby improving the head model’s representation ability while ensuring editing capabilities for the identity and expression of the rendered results;then,through a combination of volume rendering and neural rendering,the 3D representation of the head is rapidly rendered into the 2D plane,producing a high-fidelity image of the human head.Thanks to the well-designed loss functions and good implicit representation of the neural radiance field,our model can not only edit the identity and expression independently,but also freely modify the virtual camera position of the rendering results.It has excellent multi-view consistency,and has many applications in novel view synthesis,pose driving and more.
文摘System upgrades in unmanned systems have made Unmanned Aerial Vehicle(UAV)-based patrolling and monitoring a preferred solution for ocean surveillance.However,dynamic environments and large-scale deployments pose significant challenges for efficient decision-making,necessitating a modular multiagent control system.Deep Reinforcement Learning(DRL)and Decision Tree(DT)have been utilized for these complex decision-making tasks,but each has its limitations:DRL is highly adaptive but lacks interpretability,while DT is inherently interpretable but has limited adaptability.To overcome these challenges,we propose the Adaptive Interpretable Decision Tree(AIDT),an evolutionary-based algorithm that is both adaptable to diverse environmental settings and highly interpretable in its decision-making processes.We first construct a Markov decision process(MDP)-based simulation environment using the Cooperative Submarine Search task as a representative scenario for training and testing the proposed method.Specifically,we use the heat map as a state variable to address the issue of multi-agent input state proliferation.Next,we introduce the curiosity-guiding intrinsic reward to encourage comprehensive exploration and enhance algorithm performance.Additionally,we incorporate decision tree size as an influence factor in the adaptation process to balance task completion with computational efficiency.To further improve the generalization capability of the decision tree,we apply a normalization method to ensure consistent processing of input states.Finally,we validate the proposed algorithm in different environmental settings,and the results demonstrate both its adaptability and interpretability.
文摘A formation model of manned/unmanned aerial vehicle(MAV/UAV) collaborative combat can qualitatively and quantitatively analyze the synergistic effects.However,there is currently no effective and appropriate model construction method or theory,and research in the field of collaborative capability evaluation is basically nonexistent.According to the actual conditions of cooperative operations,a new MAV/UAV collaborative combat network model construction method based on a complex network is presented.By analyzing the characteristic parameters of the abstract network,the index system and complex network are combined.Then,a method for evaluating the synergistic effect of the cooperative combat network is developed.This method provides assistance for the verification and evaluation of MAV/UAV collaborative combat.
基金the Beijing Natural Science Foundation under contract number L191004the National Natural Science Foundation of China under contract number U1833203.
文摘The close-in weapon system(CIWS)is a combat system that faces a complex environment full of dynamic and unknown challenges,whose construction and planning require a systematic design method.Multiliving agent(MLA)theory is a methodology for the combat system design,which uses the livelihood degree to evaluate the multi-dimensional long-term operational effectiveness of the system;whereas,there is still no uniform quantization framework for the livelihood degree,and the adjustment methods of livelihood degree need to be further improved.In this paper,we propose the uniform quantization framework for the livelihood degree and detailed discuss the methods of livelihood adjustment.Based on the MLA theory,the multi-dimensional operational effectiveness of the missile-gun integrated weapon system(MGIWS)is analyzed,and the long-term combat effectiveness against the saturation attack is assessed.Furthermore,the planning problem of the equipment deployment and configuration is investigated.Two objectives,including the overall livelihood degree and cost-effectiveness(CE),are proposed,and the optimization method based on genetic algorithm(GA)is studied for the planning problem.
基金supported by the National Natural Science Foundation of China(61172176)
文摘Multi-living agent system （MLAS） is a new concept in the field of complex system research, which is peculiarly suitable for the design and analysis of a complex information system in a serious confrontation and tight constraint environment. However, the universal method to quantitatively measure the living degree of an MLAS remains uncertain, which is critical to the self-organizing process. Therefore, a novel analytic hierarchy process （AHP） based method with dependent pairwise comparison matrix （PCM） for the evaluation of living degree of the MLAS is proposed, which eliminates the shortcoming of fixed PCM in traditional process. Furthermore, to avoid the annoying procedure of the consistency validation, the PCMs are appropriately reconstructed. Through an illustration of the netted radar system, the calculation detail is explicitly presented. Altogether, the advanced evaluation method successfully accomplishes the preset objective and promotes the development of the MLAS theory and AHP as well.
基金the National Natural Science Foundation of China(Grant No.42174047 and No.42174036)the National Science Foundation Project for Outstanding Youth(No.42104034).
文摘This paper realizes the full-domain collaborative deployment of multiple interference sources of the global satellite navigation system(GNSS)and evaluates the deployment effect to enhance the ability to disturb the attacker and the capability to defend the GNSS during navigation countermeasures.Key evaluation indicators for the jamming effect of GNSS suppressive and deceptive jamming sources are first created,their evaluation models are built,and their detection procedures are sorted out,as the basis for determining the deployment principles.The principles for collaboratively deploying multi-jamming sources are developed to obtain the deployment structures(including the required number,structures in demand,and corresponding positions)of three single interference sources required by collaboratively deploying.Accordingly,simulation and hardware-in-loop testing results are presented to determine a rational configuration of the collaborative deployment of multi-jamming sources in the set situation and further realize the full-domain deployment of an interference network from ground,air to space.Varied evaluation indices for the deployment effect are finally developed to evaluate the deployment effect of the proposed configuration and further verify its reliability and rationality.
基金financial support from NSFC(21635003,21811540027 for Y.Tian,and 22022402,21974051 for L.Zhang)Innovation Program of Shanghai Municipal Education Commission(No.201701070005E00020)for Y.Tian。
