Cooperative path planning is an important area in fixed-wing UAV swarm.However,avoiding multiple timevarying obstacles and avoiding local optimum are two challenges for existing approaches in a dynamic environment.Fir...Cooperative path planning is an important area in fixed-wing UAV swarm.However,avoiding multiple timevarying obstacles and avoiding local optimum are two challenges for existing approaches in a dynamic environment.Firstly,a normalized artificial potential field optimization is proposed by reconstructing a novel function with anisotropy in each dimension,which can make the flight speed of a fixed UAV swarm independent of the repulsive/attractive gain coefficient and avoid trapping into local optimization and local oscillation.Then,taking into account minimum velocity and turning angular velocity of fixed-wing UAV swarm,a strategy of decomposing target vector to avoid moving obstacles and pop-up threats is proposed.Finally,several simulations are carried out to illustrate superiority and effectiveness.展开更多
A novel method was designed to solve reinforcement learning problems with artificial potential field.Firstly a reinforcement learning problem was transferred to a path planning problem by using artificial potential fi...A novel method was designed to solve reinforcement learning problems with artificial potential field.Firstly a reinforcement learning problem was transferred to a path planning problem by using artificial potential field(APF),which was a very appropriate method to model a reinforcement learning problem.Secondly,a new APF algorithm was proposed to overcome the local minimum problem in the potential field methods with a virtual water-flow concept.The performance of this new method was tested by a gridworld problem named as key and door maze.The experimental results show that within 45 trials,good and deterministic policies are found in almost all simulations.In comparison with WIERING's HQ-learning system which needs 20 000 trials for stable solution,the proposed new method can obtain optimal and stable policy far more quickly than HQ-learning.Therefore,the new method is simple and effective to give an optimal solution to the reinforcement learning problem.展开更多
With applying the information technology to the military field, the advantages and importance of the networked combat are more and more obvious. In order to make full use of limited battlefield resources and maximally...With applying the information technology to the military field, the advantages and importance of the networked combat are more and more obvious. In order to make full use of limited battlefield resources and maximally destroy enemy targets from arbitrary angle in a limited time, the research on firepower nodes dynamic deployment becomes a key problem of command and control. Considering a variety of tactical indexes and actual constraints in air defense, a mathematical model is formulated to minimize the enemy target penetration probability. Based on characteristics of the mathematical model and demands of the deployment problems, an assistance-based algorithm is put forward which combines the artificial potential field （APF） method with a memetic algorithm. The APF method is employed to solve the constraint handling problem and generate feasible solutions. The constrained optimization problem transforms into an optimization problem of APF parameters adjustment, and the dimension of the problem is reduced greatly. The dynamic deployment is accomplished by generation and refinement of feasible solutions. The simulation results show that the proposed algorithm is effective and feasible in dynamic situation.展开更多
In the cloud era, the control objects are becoming larger and the information processing is more complex, and it is difficult for traditional control systems to process massive data in a timely manner. In view of the ...In the cloud era, the control objects are becoming larger and the information processing is more complex, and it is difficult for traditional control systems to process massive data in a timely manner. In view of the difficulty of data processing in the cloud era, it is extremely important to perform massive data operations through cloud servers. Unmanned aeriel vehicle(UAV) control is the representative of the intelligent field. Based on the ant colony algorithm and incorporating the potential field method, an improved potential field ant colony algorithm is designed. To deal with the path planning problem of UAVs, the potential field ant colony algorithm shortens the optimal path distance by 6.7%, increases the algorithm running time by39.3%, and increases the maximum distance by 24.1% compared with the previous improvement. The cloud server is used to process the path problem of the UAV and feedback the calculation results in real time. Simulation experiments verify the effectiveness of the new algorithm in the cloud environment.展开更多
A new vision-based approach was presented for predicting the behavior of the ball carrier—shooting, passing and dribbling in basketball matches. It was proposed to recognize the ball carrier’s head pose by classifyi...A new vision-based approach was presented for predicting the behavior of the ball carrier—shooting, passing and dribbling in basketball matches. It was proposed to recognize the ball carrier’s head pose by classifying its yaw angle to determine his vision range and the court situation of the sportsman within his vision range can be further learned. In basketball match videos characterized by cluttered background, fast motion of the sportsmen and low resolution of their head images, and the covariance descriptor, were adopted to fuse multiple visual features of the head region, which can be seen as a point on the Riemannian manifold and then mapped to the tangent space. Then, the classification of head yaw angle was directly completed in this space through the trained multiclass LogitBoost. In order to describe the court situation of all sportsmen within the ball carrier’s vision range, artificial potential field (APF)-based information was introduced. Finally, the behavior of the ball carrier—shooting, passing and dribbling, was predicted using radial basis function (RBF) neural network as the classifier. Experimental results show that the average prediction accuracy of the proposed method can reach 80% on the video recorded in basketball matches, which validates its effectiveness.展开更多
The region coverage control problem of multiple stratospheric airships system is firstly addressed in this paper.Towards it,we propose a two-layer control framework with the artificial potential field(APF)-based regio...The region coverage control problem of multiple stratospheric airships system is firstly addressed in this paper.Towards it,we propose a two-layer control framework with the artificial potential field(APF)-based region coverage control law and the adaptive tracking control law.The APF-based region coverage control law ensures the coverage task is achieved until every single stratospheric airship ends up performing station keeping where near the respective global minimum point,in which an innovative solution to the local minimum problem is put forward.The adaptive tracking control law is designed to realize motion control using tracking the desired velocity and angular velocity given by coverage control law,with the consideration of several practical control problems as unknown individual differences and external disturbances.To save resources,the combined self-/event-triggered mechanism designed therein significantly reduces the times of state information transmission and control law calculation.The effectiveness of the proposed control framework is verified through simulations.展开更多
Analysis and design techniques for cooperative flocking of nonholonomic multi-robot systems with connectivity maintenance on directed graphs are presented. First, a set of bounded and smoothly distributed control prot...Analysis and design techniques for cooperative flocking of nonholonomic multi-robot systems with connectivity maintenance on directed graphs are presented. First, a set of bounded and smoothly distributed control protocols are devised via carefully designing a class of bounded artificial potential fields （APF） which could guarantee the connectivity maintenance, col ision avoidance and distance stabilization simultaneously during the system evolution. The connectivity of the underlying network can be preserved, and the desired stable flocking behavior can be achieved provided that the initial communication topology is strongly connected rather than undirected or balanced, which relaxes the constraints for group topology and extends the previous work to more generalized directed graphs. Furthermore, the proposed control algorithm is extended to solve the flocking problem with a virtual leader. In this case, it is shown that al robots can asymptotically move with the desired velocity and orientation even if there is only one informed robot in the team. Finally, nontrivial simulations and experiments are conducted to verify the effectiveness of the proposed algorithm.展开更多
Path planning is a key technique of autonomous navigation for robots,and the velocity field is an important part.Constructing velocity field in a complex workspace is still challenging.In this paper,an inner normal gu...Path planning is a key technique of autonomous navigation for robots,and the velocity field is an important part.Constructing velocity field in a complex workspace is still challenging.In this paper,an inner normal guided segmentation algorithm in a complex polygon is proposed to decompose the complex workspace in this paper.The artificial potential field model based on probability theory is then used to calculate the potential field of the decomposed workspace,and the velocity field is obtained by utilizing the potential field of this workspace.Path optimization is implemented by curve evolution,during which the internal force generated in the smoothing process of the initial path by a mean filter and the external force is obtained from the gradient of the workspace potential field.The parameter selection principle is deduced by analyzing the influence of several parameters on the path length and smoothness.Simulation results show that the designed polygon decomposition algorithm can effectively segment complex workspace and that the path optimization algorithm can shorten and smoothen paths.展开更多
A self-organized integrated air-ground detection swarmis tentatively applied to achieve reentry vehicle landing detection,such as searching and rescuing a manned spaceship. The detectionswarm consists of multiple unma...A self-organized integrated air-ground detection swarmis tentatively applied to achieve reentry vehicle landing detection,such as searching and rescuing a manned spaceship. The detectionswarm consists of multiple unmanned aerial vehicles （UAVs）and unmanned ground vehicles （UGVs）. The UAVs can accessa detected object quickly for high mobility, while the UGVs cancomprehensively investigate the object due to the variety of carriedequipment. In addition, the integrated air-ground detectionswarm is capable of detecting from the ground and the air simultaneously.To accomplish the coordination of the UGVs andUAVs, they are all regarded as individuals of the artificial swarm.Those individuals make control decisions independently of othersbased on the self-organizing strategy. The overall requirements forthe detection swarm are analyzed, and the theoretical model ofthe self-organizing strategy based on a combined individual andenvironmental virtual function is established. The numerical investigationproves that the self-organizing strategy is suitable andscalable to control the detection swarm. To further inspect the engineeringreliability, an experiment set is established in laboratory,and the experimental demonstration shows that the self-organizingstrategy drives the detection swarm forming a close range and multiangularsurveillance configuration of a landing spot.展开更多
文摘Cooperative path planning is an important area in fixed-wing UAV swarm.However,avoiding multiple timevarying obstacles and avoiding local optimum are two challenges for existing approaches in a dynamic environment.Firstly,a normalized artificial potential field optimization is proposed by reconstructing a novel function with anisotropy in each dimension,which can make the flight speed of a fixed UAV swarm independent of the repulsive/attractive gain coefficient and avoid trapping into local optimization and local oscillation.Then,taking into account minimum velocity and turning angular velocity of fixed-wing UAV swarm,a strategy of decomposing target vector to avoid moving obstacles and pop-up threats is proposed.Finally,several simulations are carried out to illustrate superiority and effectiveness.
基金Projects(30270496,60075019,60575012)supported by the National Natural Science Foundation of China
文摘A novel method was designed to solve reinforcement learning problems with artificial potential field.Firstly a reinforcement learning problem was transferred to a path planning problem by using artificial potential field(APF),which was a very appropriate method to model a reinforcement learning problem.Secondly,a new APF algorithm was proposed to overcome the local minimum problem in the potential field methods with a virtual water-flow concept.The performance of this new method was tested by a gridworld problem named as key and door maze.The experimental results show that within 45 trials,good and deterministic policies are found in almost all simulations.In comparison with WIERING's HQ-learning system which needs 20 000 trials for stable solution,the proposed new method can obtain optimal and stable policy far more quickly than HQ-learning.Therefore,the new method is simple and effective to give an optimal solution to the reinforcement learning problem.
基金supported by the National Outstanding Youth Science Foundation (60925011)the National Natural Science Foundation of China (61203181)
文摘With applying the information technology to the military field, the advantages and importance of the networked combat are more and more obvious. In order to make full use of limited battlefield resources and maximally destroy enemy targets from arbitrary angle in a limited time, the research on firepower nodes dynamic deployment becomes a key problem of command and control. Considering a variety of tactical indexes and actual constraints in air defense, a mathematical model is formulated to minimize the enemy target penetration probability. Based on characteristics of the mathematical model and demands of the deployment problems, an assistance-based algorithm is put forward which combines the artificial potential field （APF） method with a memetic algorithm. The APF method is employed to solve the constraint handling problem and generate feasible solutions. The constrained optimization problem transforms into an optimization problem of APF parameters adjustment, and the dimension of the problem is reduced greatly. The dynamic deployment is accomplished by generation and refinement of feasible solutions. The simulation results show that the proposed algorithm is effective and feasible in dynamic situation.
基金supported by the Natural Science Foundation of Heilongjiang Province (LH2021E045)。
文摘In the cloud era, the control objects are becoming larger and the information processing is more complex, and it is difficult for traditional control systems to process massive data in a timely manner. In view of the difficulty of data processing in the cloud era, it is extremely important to perform massive data operations through cloud servers. Unmanned aeriel vehicle(UAV) control is the representative of the intelligent field. Based on the ant colony algorithm and incorporating the potential field method, an improved potential field ant colony algorithm is designed. To deal with the path planning problem of UAVs, the potential field ant colony algorithm shortens the optimal path distance by 6.7%, increases the algorithm running time by39.3%, and increases the maximum distance by 24.1% compared with the previous improvement. The cloud server is used to process the path problem of the UAV and feedback the calculation results in real time. Simulation experiments verify the effectiveness of the new algorithm in the cloud environment.
基金Project(50808025) supported by the National Natural Science Foundation of ChinaProject(20090162110057) supported by the Doctoral Fund of Ministry of Education, China
文摘A new vision-based approach was presented for predicting the behavior of the ball carrier—shooting, passing and dribbling in basketball matches. It was proposed to recognize the ball carrier’s head pose by classifying its yaw angle to determine his vision range and the court situation of the sportsman within his vision range can be further learned. In basketball match videos characterized by cluttered background, fast motion of the sportsmen and low resolution of their head images, and the covariance descriptor, were adopted to fuse multiple visual features of the head region, which can be seen as a point on the Riemannian manifold and then mapped to the tangent space. Then, the classification of head yaw angle was directly completed in this space through the trained multiclass LogitBoost. In order to describe the court situation of all sportsmen within the ball carrier’s vision range, artificial potential field (APF)-based information was introduced. Finally, the behavior of the ball carrier—shooting, passing and dribbling, was predicted using radial basis function (RBF) neural network as the classifier. Experimental results show that the average prediction accuracy of the proposed method can reach 80% on the video recorded in basketball matches, which validates its effectiveness.
基金supported by the Postdoctoral Science Foundation of China(Grant No.2020TQ0028)the National Natural Science Foundation of China(No.62173016)Beijing Natural Science Foundation,PRChina(No.4202038)。
文摘The region coverage control problem of multiple stratospheric airships system is firstly addressed in this paper.Towards it,we propose a two-layer control framework with the artificial potential field(APF)-based region coverage control law and the adaptive tracking control law.The APF-based region coverage control law ensures the coverage task is achieved until every single stratospheric airship ends up performing station keeping where near the respective global minimum point,in which an innovative solution to the local minimum problem is put forward.The adaptive tracking control law is designed to realize motion control using tracking the desired velocity and angular velocity given by coverage control law,with the consideration of several practical control problems as unknown individual differences and external disturbances.To save resources,the combined self-/event-triggered mechanism designed therein significantly reduces the times of state information transmission and control law calculation.The effectiveness of the proposed control framework is verified through simulations.
基金supported by the National Natural Science Foundation of China(61175112)the Foundation for Innovative Research Groups of the National Natural Science Foundation of China(G61321002)+3 种基金the Projects of Major International(Regional)Joint Research Program(61120106010)the Beijing Education Committee Cooperation Building Foundationthe Program for Changjiang Scholars and Innovative Research Team in University(IRT1208)the ChangJiang Scholars Program and the Beijing Outstanding Ph.D.Program Mentor Grant(20131000704)
文摘Analysis and design techniques for cooperative flocking of nonholonomic multi-robot systems with connectivity maintenance on directed graphs are presented. First, a set of bounded and smoothly distributed control protocols are devised via carefully designing a class of bounded artificial potential fields （APF） which could guarantee the connectivity maintenance, col ision avoidance and distance stabilization simultaneously during the system evolution. The connectivity of the underlying network can be preserved, and the desired stable flocking behavior can be achieved provided that the initial communication topology is strongly connected rather than undirected or balanced, which relaxes the constraints for group topology and extends the previous work to more generalized directed graphs. Furthermore, the proposed control algorithm is extended to solve the flocking problem with a virtual leader. In this case, it is shown that al robots can asymptotically move with the desired velocity and orientation even if there is only one informed robot in the team. Finally, nontrivial simulations and experiments are conducted to verify the effectiveness of the proposed algorithm.
基金supported by the financial support of the ship segmentation intelligent manufacturing equipment solution and key common technology research,High-tech Ship Research Project of the Chinese Ministry of Science and Technology and the project of Shandong Provincial Key R&D Program(No.2019GGX104035).
文摘Path planning is a key technique of autonomous navigation for robots,and the velocity field is an important part.Constructing velocity field in a complex workspace is still challenging.In this paper,an inner normal guided segmentation algorithm in a complex polygon is proposed to decompose the complex workspace in this paper.The artificial potential field model based on probability theory is then used to calculate the potential field of the decomposed workspace,and the velocity field is obtained by utilizing the potential field of this workspace.Path optimization is implemented by curve evolution,during which the internal force generated in the smoothing process of the initial path by a mean filter and the external force is obtained from the gradient of the workspace potential field.The parameter selection principle is deduced by analyzing the influence of several parameters on the path length and smoothness.Simulation results show that the designed polygon decomposition algorithm can effectively segment complex workspace and that the path optimization algorithm can shorten and smoothen paths.
基金supported by the National Natural Science Foundation of China(11002076)the National High Technology Research and Development Program of China(863 Program)(2014AA7041002)
文摘A self-organized integrated air-ground detection swarmis tentatively applied to achieve reentry vehicle landing detection,such as searching and rescuing a manned spaceship. The detectionswarm consists of multiple unmanned aerial vehicles （UAVs）and unmanned ground vehicles （UGVs）. The UAVs can accessa detected object quickly for high mobility, while the UGVs cancomprehensively investigate the object due to the variety of carriedequipment. In addition, the integrated air-ground detectionswarm is capable of detecting from the ground and the air simultaneously.To accomplish the coordination of the UGVs andUAVs, they are all regarded as individuals of the artificial swarm.Those individuals make control decisions independently of othersbased on the self-organizing strategy. The overall requirements forthe detection swarm are analyzed, and the theoretical model ofthe self-organizing strategy based on a combined individual andenvironmental virtual function is established. The numerical investigationproves that the self-organizing strategy is suitable andscalable to control the detection swarm. To further inspect the engineeringreliability, an experiment set is established in laboratory,and the experimental demonstration shows that the self-organizingstrategy drives the detection swarm forming a close range and multiangularsurveillance configuration of a landing spot.
