With the rapid growth of flight flow,the workload of controllers is increasing daily,and handling flight conflicts is the main workload.Therefore,it is necessary to provide more efficient conflict resolution decision-...With the rapid growth of flight flow,the workload of controllers is increasing daily,and handling flight conflicts is the main workload.Therefore,it is necessary to provide more efficient conflict resolution decision-making support for controllers.Due to the limitations of existing methods,they have not been widely used.In this paper,a Deep Reinforcement Learning(DRL)algorithm is proposed to resolve multi-aircraft flight conflict with high solving efficiency.First,the characteristics of multi-aircraft flight conflict problem are analyzed and the problem is modeled based on Markov decision process.Thus,the Independent Deep Q Network(IDQN)algorithm is used to solve the model.Simultaneously,a’downward-compatible’framework that supports dynamic expansion of the number of conflicting aircraft is designed.The model ultimately shows convergence through adequate training.Finally,the test conflict scenarios and indicators were used to verify the validity.In 700 scenarios,85.71%of conflicts were successfully resolved,and 71.51%of aircraft can reach destinations within 150 s around original arrival times.By contrast,conflict resolution algorithm based on DRL has great advantages in solution speed.The method proposed offers the possibility of decision-making support for controllers and reduce workload of controllers in future high-density airspace environment.展开更多
In order to grasp the evolution of flight conflict amount accurately and to forecast the amount, chaos in flight conflicts is studied. Firstly, a fault tree of flight conflicts is established based on the man-machine-...In order to grasp the evolution of flight conflict amount accurately and to forecast the amount, chaos in flight conflicts is studied. Firstly, a fault tree of flight conflicts is established based on the man-machine-environ- ment system engineering theory. The chaotic characteristics of flight conflict are analyzed from the qualitative point of view. Secondly, an improved chaotic algorithm for the largest Lyapunov exponent is proposed based on the small-data method and the wavelet de-noising theory. Chaos in flight conflict time series is identified by the improved chaotic algorithm from the quantitative point of view. Finally, a case study by the chaos forecasting al- gorithm is performed and the results are evaluated by the gray error checking ： Correlative value of posterior error is 0. 220 9〈0. 35, and micro-error probability is 0. 985 3〉0.95. Such results show the chaos forecasting algo- rithm is effective, thus it is feasible to analyze and forecast flight conflict by chaotic theory.展开更多
Describing spatial safety status is crucial for high-density air traffic involving multiple unmanned aerial vehicles （UAVs） in a complex environment. A probabilistic approach is proposed to measure safety situation ...Describing spatial safety status is crucial for high-density air traffic involving multiple unmanned aerial vehicles （UAVs） in a complex environment. A probabilistic approach is proposed to measure safety situation in congested airspace. The occupancy distribution of the airspace is represented with conflict probability between spatial positions and UAV. The concept of a safety envelope related to flight performance and response time is presented first instead of the conventional fixed-size protected zones around aircraft. Consequently, the conflict probability is performance-dependent, and effects of various UAVs on safety can be distinguished. The uncertainty of a UAV future position is explicitly accounted for as Brownian motion. An analytic approximate algorithm for the conflict probability is developed to decrease the computational consumption. The relationship between safety and flight performance are discussed for different response times and prediction intervals. To illustrate the applications of the approach, an experiment of three UAVs in formation flight is performed. In addition, an example of trajectory planning is simulated for one UAV flying over airspace where five UAVs exist. The validation of the approach shows its potential in guaranteeing flight safety in highly dynamic environment.展开更多
In order to improve the accuracy of free flight conflict detection and reduce the false alarm rate, an improved flight conflict detection algorithm is proposed based on Gauss-Hermite particle filter（GHPF）. The algor...In order to improve the accuracy of free flight conflict detection and reduce the false alarm rate, an improved flight conflict detection algorithm is proposed based on Gauss-Hermite particle filter（GHPF）. The algorithm improves the traditional flight conflict detection method in two aspects：（i） New observation data are integrated into system state transition probability, and Gauss-Hermite Filter（GHF） is used for generating the importance density function.（ii） GHPF is used for flight trajectory prediction and flight conflict probability calculation. The experimental results show that the accuracy of conflict detection and tracing with GHPF is better than that with standard particle filter. The detected conflict probability is more precise with GHPF, and GHPF is suitable for early free flight conflict detection.展开更多
基金supported by Safety Ability Project of Civil Aviation Administration of China(No.TM 2018-5-1/2)the Open Foundation project of The Graduate Student Innovation Base,China(Laboratory)of Nanjing University of Aeronautics and Astronautics,China(No.kfjj20190720)。
文摘With the rapid growth of flight flow,the workload of controllers is increasing daily,and handling flight conflicts is the main workload.Therefore,it is necessary to provide more efficient conflict resolution decision-making support for controllers.Due to the limitations of existing methods,they have not been widely used.In this paper,a Deep Reinforcement Learning(DRL)algorithm is proposed to resolve multi-aircraft flight conflict with high solving efficiency.First,the characteristics of multi-aircraft flight conflict problem are analyzed and the problem is modeled based on Markov decision process.Thus,the Independent Deep Q Network(IDQN)algorithm is used to solve the model.Simultaneously,a’downward-compatible’framework that supports dynamic expansion of the number of conflicting aircraft is designed.The model ultimately shows convergence through adequate training.Finally,the test conflict scenarios and indicators were used to verify the validity.In 700 scenarios,85.71%of conflicts were successfully resolved,and 71.51%of aircraft can reach destinations within 150 s around original arrival times.By contrast,conflict resolution algorithm based on DRL has great advantages in solution speed.The method proposed offers the possibility of decision-making support for controllers and reduce workload of controllers in future high-density airspace environment.
基金Supported by the Joint Funds of National Natural Science Foundation of China(61039001)~~
文摘In order to grasp the evolution of flight conflict amount accurately and to forecast the amount, chaos in flight conflicts is studied. Firstly, a fault tree of flight conflicts is established based on the man-machine-environ- ment system engineering theory. The chaotic characteristics of flight conflict are analyzed from the qualitative point of view. Secondly, an improved chaotic algorithm for the largest Lyapunov exponent is proposed based on the small-data method and the wavelet de-noising theory. Chaos in flight conflict time series is identified by the improved chaotic algorithm from the quantitative point of view. Finally, a case study by the chaos forecasting al- gorithm is performed and the results are evaluated by the gray error checking ： Correlative value of posterior error is 0. 220 9〈0. 35, and micro-error probability is 0. 985 3〉0.95. Such results show the chaos forecasting algo- rithm is effective, thus it is feasible to analyze and forecast flight conflict by chaotic theory.
基金supported by the National Basic Research Program of China (No.2011CB707002)
文摘Describing spatial safety status is crucial for high-density air traffic involving multiple unmanned aerial vehicles （UAVs） in a complex environment. A probabilistic approach is proposed to measure safety situation in congested airspace. The occupancy distribution of the airspace is represented with conflict probability between spatial positions and UAV. The concept of a safety envelope related to flight performance and response time is presented first instead of the conventional fixed-size protected zones around aircraft. Consequently, the conflict probability is performance-dependent, and effects of various UAVs on safety can be distinguished. The uncertainty of a UAV future position is explicitly accounted for as Brownian motion. An analytic approximate algorithm for the conflict probability is developed to decrease the computational consumption. The relationship between safety and flight performance are discussed for different response times and prediction intervals. To illustrate the applications of the approach, an experiment of three UAVs in formation flight is performed. In addition, an example of trajectory planning is simulated for one UAV flying over airspace where five UAVs exist. The validation of the approach shows its potential in guaranteeing flight safety in highly dynamic environment.
基金Supported by the Joint Project of National Natural Science Foundation of ChinaCivil Aviation Administration of China(U1333116)
文摘In order to improve the accuracy of free flight conflict detection and reduce the false alarm rate, an improved flight conflict detection algorithm is proposed based on Gauss-Hermite particle filter（GHPF）. The algorithm improves the traditional flight conflict detection method in two aspects：（i） New observation data are integrated into system state transition probability, and Gauss-Hermite Filter（GHF） is used for generating the importance density function.（ii） GHPF is used for flight trajectory prediction and flight conflict probability calculation. The experimental results show that the accuracy of conflict detection and tracing with GHPF is better than that with standard particle filter. The detected conflict probability is more precise with GHPF, and GHPF is suitable for early free flight conflict detection.
