Review on artificial intelligence techniques for improving representative air traffic management capability

The use of artificial intelligence(AI)has increased since the middle of the 20th century,as evidenced by its applications to a wide range of engineering and science problems.Air traffic management(ATM)is becoming increasingly automated and autonomous,making it lucrative for AI applications.This paper presents a systematic review of studies that employ AI techniques for improving ATM capability.A brief account of the history,structure,and advantages of these methods is provided,followed by the description of their applications to several representative ATM tasks,such as air traffic services(ATS),airspace management(AM),air traffic flow management(ATFM),and flight operations(FO).The major contribution of the current review is the professional survey of the AI application to ATM alongside with the description of their specific advantages:(i)these methods provide alternative approaches to conventional physical modeling techniques,(ii)these methods do not require knowing relevant internal system parameters,(iii)these methods are computationally more efficient,and(iv)these methods offer compact solutions to multivariable problems.In addition,this review offers a fresh outlook on future research.One is providing a clear rationale for the model type and structure selection for a given ATM mission.Another is to understand what makes a specific architecture or algorithm effective for a given ATM mission.These are among the most important issues that will continue to attract the attention of the AI research community and ATM work teams in the future.

Dynamic Air Route Open-Close Problem for Airspace Management

Dynamic airspace management plans and assigns airspace resources to airspace users on demand to increase airspace capacity. Although many studies of air traffic flow management （ATFM） have sought to optimally allocate air traffic to get the best use of given airspace resources, few studies have focused on how to build an efficient air traffic network or how to adjust the current network in real time. This paper presents an integer program model named the dynamic air route open-close problem （DROP）. DROP has a cost-based objective function which takes into account constraints such as the shortest occupancy time of routes, which are not considered in ATFM models. The aim of DROP is to determine which routes will be opened to a certain user during a given time period. Simulation results show that DROP can facilitate utilization of air routes. DROP, a simplified version of an air traffic network constructing problem, is the first step towards realizing dynamic airspace management. The combination of ATFM and DROP can facilitate decisions toward more reasonable, efficient use of limited airspace resources.

Locally generalised multi-agent reinforcement learning for demand and capacity balancing with customised neural networks

Reinforcement Learning(RL)techniques are being studied to solve the Demand and Capacity Balancing(DCB)problems to fully exploit their computational performance.A locally gen-eralised Multi-Agent Reinforcement Learning(MARL)for real-world DCB problems is proposed.The proposed method can deploy trained agents directly to unseen scenarios in a specific Air Traffic Flow Management(ATFM)region to quickly obtain a satisfactory solution.In this method,agents of all flights in a scenario form a multi-agent decision-making system based on partial observation.The trained agent with the customised neural network can be deployed directly on the corresponding flight,allowing it to solve the DCB problem jointly.A cooperation coefficient is introduced in the reward function,which is used to adjust the agent’s cooperation preference in a multi-agent system,thereby controlling the distribution of flight delay time allocation.A multi-iteration mechanism is designed for the DCB decision-making framework to deal with problems arising from non-stationarity in MARL and to ensure that all hotspots are eliminated.Experiments based on large-scale high-complexity real-world scenarios are conducted to verify the effectiveness and efficiency of the method.From a statis-tical point of view,it is proven that the proposed method is generalised within the scope of the flights and sectors of interest,and its optimisation performance outperforms the standard computer-assisted slot allocation and state-of-the-art RL-based DCB methods.The sensitivity analysis preliminarily reveals the effect of the cooperation coefficient on delay time allocation.

Strategic flight assignment approach based on multi-objective parallel evolution algorithm with dynamic migration interval

The continuous growth of air traffic has led to acute airspace congestion and severe delays, which threatens operation safety and cause enormous economic loss. Flight assignment is an economical and effective strategic plan to reduce the flight delay and airspace congestion by rea- sonably regulating the air traffic flow of China. However, it is a large-scale combinatorial optimiza- tion problem which is difficult to solve. In order to improve the quality of solutions, an effective multi-objective parallel evolution algorithm （MPEA） framework with dynamic migration interval strategy is presented in this work. Firstly, multiple evolution populations are constructed to solve the problem simultaneously to enhance the optimization capability. Then a new strategy is pro- posed to dynamically change the migration interval among different evolution populations to improve the efficiency of the cooperation of populations. Finally, the cooperative co-evolution （CC） algorithm combined with non-dominated sorting genetic algorithm II （NSGA-II） is intro- duced for each population. Empirical studies using the real air traffic data of the Chinese air route network and daily flight plans show that our method outperforms the existing approaches, multi- objective genetic algorithm （MOGA）, multi-objective evolutionary algorithm based on decom- position （MOEA/D）, CC-based multi-objective algorithm （CCMA） as well as other two MPEAs with different migration interval strategies.

A multi-objective multi-memetic algorithm for network-wide conflict-free 4D flight trajectories planning

Under the demand of strategic air traffic flow management and the concept of trajectory based operations（TBO）,the network-wide 4D flight trajectories planning（N4DFTP） problem has been investigated with the purpose of safely and efficiently allocating 4D trajectories（4DTs）（3D position and time） for all the flights in the whole airway network.Considering that the introduction of large-scale 4DTs inevitably increases the problem complexity,an efficient model for strategiclevel conflict management is developed in this paper.Specifically,a bi-objective N4 DFTP problem that aims to minimize both potential conflicts and the trajectory cost is formulated.In consideration of the large-scale,high-complexity,and multi-objective characteristics of the N4DFTP problem,a multi-objective multi-memetic algorithm（MOMMA） that incorporates an evolutionary global search framework together with three problem-specific local search operators is implemented.It is capable of rapidly and effectively allocating 4DTs via rerouting,target time controlling,and flight level changing.Additionally,to balance the ability of exploitation and exploration of the algorithm,a special hybridization scheme is adopted for the integration of local and global search.Empirical studies using real air traffic data in China with different network complexities show that the proposed MOMMA is effective to solve the N4 DFTP problem.The solutions achieved are competitive for elaborate decision support under a TBO environment.