Air Traffic Management Problem Research Articles

How will banning motorcycles affect the preferred mode choice of motorcyclists in Hanoi, Vietnam?

In rapidly urbanizing regions of low- and middle-income countries as found in Asia, transportation management faces significant challenges, particularly with the popularity of two-wheeled vehicles. While these vehicles offer convenience in Asian megacities, their increasing prevalence has led to many urban traffic issues, including air pollution and traffic management problems. Consequently, several countries have contemplated or implemented bans on motorized two-wheeled vehicles in urban areas. With a forthcoming ban on motorcycles in 2030, this study investigates potential switches in transportation travel modes among motorcyclists. Analyzing factors influencing choices between electric bicycles (e-bikes) and buses, the results indicate a probable widespread adoption of e-bikes over buses post-ban. Income, place of residence, and access to bus stops emerge as key determinants.

General real-time three-dimensional multi-aircraft conflict resolution method using multi-agent reinforcement learning

Reinforcement learning (RL) techniques have been studied for solving the conflict resolution (CR) problem in air traffic management, leveraging their potential for computation and ability to handle uncertainty. However, challenges remain that impede the application of RL methods to CR in practice, including three-dimensional manoeuvres, generalisation, trajectory recovery, and success rate. This paper proposes a general multi-agent reinforcement learning approach for real-time three-dimensional multi-aircraft conflict resolution, in which agents share a neural network and are deployed on each aircraft to form a distributed decision-making system. To address the challenges, several technologies are introduced, including a partial observation model based on imminent threats for generalisation, a safety separation relaxation model for multiple flight levels for three-dimensional manoeuvres, an adaptive manoeuvre strategy for trajectory recovery, and a conflict buffer model for success rate. The Rainbow Deep Q-learning Network (DQN) is used to enhance the efficiency of the RL process. A simulation environment that considers flight uncertainty (resulting from mechanical and navigation errors and wind) is constructed to train and evaluate the proposed approach. The experimental results demonstrate that the proposed method can resolve conflicts in scenarios with much higher traffic density than in today’s real-world situations.

General multi-agent reinforcement learning integrating heuristic-based delay priority strategy for demand and capacity balancing

Reinforcement learning (RL) techniques have been studied for solving the demand and capacity balancing (DCB) problem in air traffic management to exploit their full computational potential. Due to the lack of generalisation and the seemingly reduced optimisation performance affected by the training scenarios, it is challenging for existing RL-based DCB methods to be effectively applied in practice. This paper proposes a general multi-agent reinforcement learning (MARL) method that integrates a heuristic-based delay priority strategy to improve the efficiency of the solution and the generalisation of the model. The delay priority strategy is used to reduce the potential learning task and thus training difficulty. This study explores what features of the delay priority strategy are better suited to the MARL method. A long short-term memory (LSTM) network is integrated into a deep q-learning network (DQN) to ensure the model compatible with arbitrary DCB instances and to facilitate agents to identify key sectors. This study is conducted as a part of a large-scale European DCB research project, where real data from French and Spanish airspace are used for experimentation. Results suggest that the proposed method has advantages in generalisation, optimisation performance and computational performance over state-of-the-art RL-based DCB methods.

Air-traffic controller and autopilot joint control of aircraft as mixed integer quadratic problem

One of the traditional problems in air-traffic management is optimal safe scheduling aircraft at a point of air-routes join. However, this problem implies another one, namely, the problem of guiding the aircraft to the prescribed point of its route at the necessary instant. The latter problem is studied much less attentively. Change of the arrival instant can be provided by alternating the aircraft motion trajectory on the basis of near-airport air-routes scheme or by alternating its velocity. Such a control can be worked out as automatically by the aircraft autopilot as manually by an air-traffic controller. But it can be difficult to an air-traffic controller to construct such a control especially during rush hours in loaded airports. In this paper, the authors suggest an optimizational formalization of the problem of automatic directions generation for such a guiding. The criterion to be minimized in this formalization is the number of controller-pilot interactions, because each such an interaction is a long, difficult process liable to linguistic, technical, psychological, and other errors. Since the criterion and other processes are of discrete kind, the formalization is done in the framework of mixed integer quadratic programming. The obtained problems are solved numerically by means of MIQP-solver provided by the Gurobi library. Each subproblem is solved quite fast within 0.1-0.5 seconds. So, solution of the entire problem (which includes enumeration of trajectories and choice of the optimal velocity regime for each of them) takes one-two seconds. Thus, the problem for the entire group of aircraft can be solved during a time acceptable for a real time application.

A Large Neighborhood Search Algorithm with Simulated Annealing and Time Decomposition Strategy for the Aircraft Runway Scheduling Problem

The runway system is more likely to be a bottleneck area for airport operations because it serves as a link between the air routes and airport ground traffic. As a key problem of air traffic flow management, the aircraft runway scheduling problem (ARSP) is of great significance to improve the utilization of runways and reduce aircraft delays. This paper proposes a large neighborhood search algorithm combined with simulated annealing and the receding horizon control strategy (RHC-SALNS) which is used to solve the ARSP. In the framework of simulated annealing, the large neighborhood search process is embedded, including the breaking, reorganization and local search processes. The large neighborhood search process could expand the range of the neighborhood building in the solution space. A receding horizon control strategy is used to divide the original problem into several subproblems to further improve the solving efficiency. The proposed RHC-SALNS algorithm solves the ARSP instances taken from the actual operation data of Wuhan Tianhe Airport. The key parameters of the algorithm were determined by parametric sensitivity analysis. Moreover, the proposed RHC-SALNS is compared with existing algorithms with excellent performance in solving large-scale ARSP, showing that the proposed model and algorithm are correct and efficient. The algorithm achieves better optimization results in solving large-scale problems.

Methods of Air Traffic Management Using Artificial Intelligence in India

Artificial intelligence (AI) has been recognised as having a broad potential to reduce human workload or increase human capabilities in complex scenarios; however, it is now clear that AI also plays an important role in transforming our lives by promoting more efficient existing services or completely new services. AI is already assisting managers (airlines/airports managers, air traffic management) and operators in a wide range of aviation and air traffic system applications (pilots, air traffic controllers, airport operators, flow controllers). The aviation and air traffic management (ATM) sectors are now confronted with new interconnected challenges: energy transition, increased environmental protection, increased capacity flexibility, integration of new components into air traffic (drones), and system resilience to large traffic perturbations (economic crises, pandemics). AI should help to discover effective solutions to all of these problems. The capacity and safety of the airspace system are heavily reliant on the competent coordination of air traffic control System (ATCS) and flight desk employees. This indicates that aviation traffic will expand at an exponential pace, causing substantial congestion, flight delays, and pollution. Maintaining safe spacing between aircrafts, directing them during takeoff and landing from airports, guiding them around adverse weather, and ensuring that traffic moves smoothly with minimum delays. The goal of this Research Topic is to develop and apply new AI techniques to solve new aircraft operations and air traffic management problems, with the goal of making air transportation operations (including air traffic) more efficient and safe than they are today, while new aviation technologies and new airspace organisation concepts are introduced, and the main goal of this research is to provide automatic communication between the airport and the aircraft. The Problem of manually checking climatic conditions, runway parameters, air traffic, and various other information can be solved by using GSM technology. To reduce the manual efforts and human errors. Before landing, the arrival time of the aircraft is announced automatically.

On the binary formulation of air traffic flow management problems

We discuss a widely used air traffic flow management formulation. We show that this formulation can lead to a solution where air delays are assigned to flights during their take-off which is prohibited in practice. Although air delay is more expensive than ground delay, the model may assign air delay to a few flights during their take-off to save more on not having as much ground delay. We present a modified formulation and verify its functionality in avoiding incorrect solutions.

Context‐based automation of critical infrastructure systems for efficiency, stakeholder equity, and resilience

AbstractThere is an urgent need for more efficient and resilient infrastructure systems to support a growing population with increasingly scarce resources worldwide. As the demand for limited natural and man‐made resources grows, improved methods for resolving anticipated and unforeseen conflicts of availability are needed. System automation has broadly been adopted for efficiency optimization and resource deconfliction via preplanned actions and responses to anticipated needs. However, human intervention is still relied upon up to resolve emergent issues for which automation lacks the flexibility and adaptability to resolve. In this research, a context‐based decision model for system automation is presented that uses satisficing heuristics to deconflict shared resources without preplanning or human intervention. Via modeling and simulation, the presented model and existing rule‐based algorithms were applied to an air traffic management problem to compare performance with respect to: (a) system efficiency, (b) standard deviation of efficiency, and (c) system stability as a measure of disruption avoidance. Simulation results demonstrate that the presented model concurrently supports efficiency optimization and disruption avoidance for airspace deconfliction, averaging 9.7% higher system efficiency and a 1.5% lower standard deviation of efficiency than the existing rule‐based standard for aircraft collision avoidance (based on an air traffic density of 45 aircraft per 10 000 square nautical miles). The model presented here is extensible to engineered systems that rely on shared, finite resources for mission execution. This research is relevant to the domains of critical infrastructure management, risk management, distributed control systems, and mission assurance.

Near-Optimal Reactive Synthesis Incorporating Runtime Information.

We consider the problem of optimal reactive synthesis - compute a strategy that satisfies a mission specification in a dynamic environment, and optimizes a performance metric. We incorporate task-critical information, that is only available at runtime, into the strategy synthesis in order to improve performance. Existing approaches to utilising such time-varying information require online re-synthesis, which is not computationally feasible in real-time applications. In this paper, we pre-synthesize a set of strategies corresponding to candidate instantiations (pre-specified representative information scenarios). We then propose a novel switching mechanism to dynamically switch between the strategies at runtime while guaranteeing all safety and liveness goals are met. We also characterize bounds on the performance suboptimality. We demonstrate our approach on two examples - robotic motion planning where the likelihood of the position of the robot's goal is updated in real-time, and an air traffic management problem for urban air mobility.

Context-Driven Autonomy for Enhanced System Resilience in Emergent Operating Environments

As higher degrees of operational autonomy are sought in engineered systems, resilient command and control (C2) capabilities are essential for mitigating performance degradation and disruptions. Autonomous C2 systems typically excel in performance optimization and failure-prevention within known or anticipated environments, but can exhibit poor efficacy given a lack of preemptive knowledge of needs and environments. This paper presents a context-driven decision engine for resilient C2 of engineered systems in emergent operating environments. The solution integrates diagnostic and prognostic heuristics to 1) assess system state of health (SoH) based on operational availability; 2) establish situational awareness; and 3) drive C2 decisions based on scenario-specific constraints and priorities. The solution is applied to an air traffic management problem for autonomous aircraft operations based on a Federal Aviation Administration Next Generation Air Transportation System (NextGen) concept. Agent-based modeling and Monte Carlo simulation are used to evaluate the incident rate ( λ ) and mission reliability ( $R_{M}$ ) of the proposed context-based solution against rule-based and utility-based C2 solutions, including the Radio Technical Commission for Aeronautics DO-185B standard and Dynamic A-star Lite (D* Lite) algorithm. Paired t -tests are used to compare approaches based on λ and $R_{M}$ given identical test cases. Results suggest that the proposed context-based solution can concurrently enhance threat avoidance and adaptation capabilities in emergent environments, whereas unilaterally optimized performance is observed via the rule-based and utility-based C2 solutions.

A Combinatorial model to optimize air traffic flow management problems

In this paper we introduce a new 0–1 mathematical formulation for the Air Traffic Flow Management problem. The model is based on a 4D-graph, which allows us to consider the problem not as general combinatorial one, but as a set of shortest path problems with common capacity constraints, a fact that introduces several neat features. Among the decisions considered in the model are ground and air delays, changes in the speed of the aircraft and alternative routes. The proposed model, in comparison with the current state of the art, is shown to be an easy way to model different real complex situations (e.g., more realistic representation of costs and decisions involved, as well as dynamic sector configuration). The rapidity with which the computations are performed in this model shows the applicability of our proposal to the industry.

Quantum Annealing Applied to De-Conflicting Optimal Trajectories for Air Traffic Management

We present the mapping of a class of simplified air traffic management problems (strategic conflict resolution) to quadratic unconstrained Boolean optimization problems. The mapping is performed through an original representation of the conflict-resolution problem in terms of a conflict graph, where the nodes of the graph represent flights and the edges represent a potential conflict between flights. The representation allows a natural decomposition of a real-world instance related to wind-optimal trajectories over the Atlantic Ocean into smaller subproblems that can be discretized and are amenable to be programmed in quantum annealers. In this paper, we tested the new programming techniques, and we benchmark the hardness of the instances using both classical solvers and the D-Wave 2X and D-Wave 2000Q quantum chip. The preliminary results show that for reasonable modeling choices, the most challenging subproblems which are programmable in the current devices are solved to optimality with 99% of probability within a second of annealing time.

First Order Hadamard Variation of the Harmonic Navigation Function on a Sphere World

Planning conflict-free trajectories is a long-standing problem in Air Traffic Management. Navigation functions designed specifically to produce flyable trajectories have been previously considered, but lack the robustness to uncertain weather conditions needed for use in an operational context. These uncertainties can be taken into account be modifying the boundary of the domain on which the navigation function is computed. In the following work, we present a method for efficiently taking into account boundary variations, using the Hadamard variation.

Infinite Time Horizon Maximum Causal Entropy Inverse Reinforcement Learning

Inverse reinforcement learning (IRL) attempts to use demonstrations of “expert” decision making in a Markov decision process to infer a corresponding policy that shares the “structured, purposeful” qualities of the expert's actions. In this paper, we extend the maximum causal entropy framework, a notable paradigm in IRL, to the infinite time horizon setting. We consider two formulations (maximum discounted causal entropy and maximum average causal entropy) appropriate for the infinite horizon case and show that both result in optimization programs that can be reformulated as convex optimization problems; thus, admitting efficient computation. We then develop a gradient-based algorithm for the maximum discounted causal entropy formulation that enjoys the desired feature of being model agnostic, a property that is absent in many previous IRL algorithms. We propose the stationary soft Bellman policy, a key building block in the gradient-based algorithm, and study its properties in depth, which not only lead to theoretical insight into its analytical properties, but also help motivate a large toolkit of methods for implementing the gradient-based algorithm. Finally, we select three algorithms of this type and apply them to two problem instances involving demonstration data from a simple controlled queuing network model inspired by problems in air traffic management.

Practical Method for 4-Dimentional Strategic Air Traffic Management Problem With Convective Weather Uncertainty

Strategic air traffic management (SATM) problem, one of the critical tasks in air traffic operations, faces new challenges as the increased concerns on environmental impact and operation efficiency of the air transportation, and the system uncertainty increases due to the time-varying interference, such as the convective weather. To effectively address these challenges, we propose the formulation and solution of a generalized 4-D SATM problem for an air traffic system with convective weather uncertainty. The proposed SATM problem formulation is computationally tractable and the schedule results can realize the avoidance of the convective weather with more than a tolerable risk probability. We provide a solution approach to tackle this problem with complex mathematical basics and illustrate the capabilities of the proposed mixed integer solution approach on the real regional air traffic system operated by the China civil aviation administration. Numerical results demonstrate the effectiveness of the proposed solution approach.

Combination of optimal control approaches for aircraft conflict avoidance via velocity regulation

SummaryThis paper deals with optimal control applied to one of the most crucial and challenging problems in Air Traffic Management that of aircraft conflict avoidance. We propose an optimal control model where aircraft separation is achieved by changing the speeds of aircraft, and the integral over a time window of their squared accelerations is minimized. Pairwise aircraft separation constraints constitute the main difficulties to be handled. We propose an original decomposition of the problem into 3 zones, in such a way that in two of them, no conflict occurs. Then, using the Pontryagin maximum principle, 2 new formulations of the original optimal control problem are proposed and solved via direct shooting methods. Thanks to our decomposition, these numerical methods are applied on subproblems having reduced size with respect to the original one, thus improving the efficiency of the solution process. Thirty problem instances are numerically solved, showing the effectiveness of the proposed approaches.

A branch and cut heuristic for a runway scheduling problem

The paper is focused on one of the major air traffic management problem that consists in sequencing and scheduling airplanes landing and taking off on a runway. This difficult practical task is still carried out by flight controllers manually with little help from decision support systems. In this paper we propose an approach based on a time indexed integer programming formulation. The formulation is solved with a branch and cut method combined with some heuristic rules for dimension reduction. The effectiveness of the proposed approach is illustrated by computational experiments on real-life problem instances for the Milano Linate airport.

Subliminal Speed Control in Air Traffic Management: Optimization and Simulation

We address the conflict resolution problem in air traffic management. It is widely acknowledged that air traffic controllers’ (ATCs) workload is related to the density of flights. ATCs’ main task is to ensure the safety of flights throughout their trips and consists of ensuring the respect of separation standards. Recently, the concept of subliminal control has emerged as a promising conflict resolution technique that could be used to reduce the impact of conflicts on ATCs’ workload. In this research, we present deterministic conflict resolution models adapted to subliminal speed control. The proposed models are formulated as nonlinear optimization problems that seek to minimize indicators related to ATCs’ workload (total conflict duration, total number of conflicts) using only minor speed adjustments. We introduce a linear approximation of the aircraft separation equations to implement the obtained mixed integer programs on a continental size air traffic network. Specifically, we develop a simulation framework aiming at reproducing realistic navigation conditions and evaluate the robustness of our conflict resolution models using a generic uncertainty model. We show that the impact of conflicts on ATCs’ workload can be significantly reduced using only limited resources, i.e., a narrow speed modulation range, even in the presence of perturbations. Further, we demonstrate that a significant share of the potential conflicts can be resolved without inducing important delays to flights. Finally, we report that our model does not require extensive computational resources as most instances can be solved to global optimality in a few seconds.

Exact and Approximate Solving of the Aircraft Collision Resolution Problem via Turn Changes

The aircraft conflict detection and resolution problem in air traffic management consists of deciding the best strategy for an arbitrary aircraft configuration such that all conflicts in the airspace are avoided. A conflict situation occurs if two or more aircraft do not maintain the minimum safety distance during their flight plans. A two-step approach is presented. The first step consists of a nonconvex mixed integer nonlinear optimization (MINLO) model based on geometric constructions. The objective is to minimize the weighted aircraft angle variations to obtain the new flight configuration. The second step consists of a set of unconstrained quadratic optimization models where aircraft are forced to return to their original flight plan as soon as possible once there is no aircraft in conflict with any other. The main results of extensive computation are reported by comparing the performance of state-of-the-art nonconvex MINLO solvers and an approximation by discretizing the possible angles of motion for solving a sequence of integer linear optimization (SILO) models in an iterative way. Minotaur, one of the nonconvex MINLO solvers experimented with, gives better solutions but requires more computation time than the SILO approach, which requires only a short time to obtain a good, feasible solution. Its value in the objective function has a reasonable goodness gap compared with the Minotaur solution. Given the need to solve the problem in almost real time, the approximate SILO approach is favored because of its short computation time and solution quality for the testbeds used in the experiment, which include both small- and real-sized instances. However, Minotaur is useful in this particular case for simulation purposes and for calibrating the SILO approach.

Unified Optimization of Traffic Flows Through Airports

We present a novel integer optimization approach to optimize, in a tractable and unified manner, the airport operations optimization problem. This includes solving the entirety of key air traffic flow management problems faced at an airport: (a) selecting a runway configuration sequence, i.e., determining which runways are open at which times and in which mode they operate; (b) assigning flights to runways and determining the sequence in which flights are processed (i.e., when they take off or land); (c) determining the gate-holding duration of departures; and (d) routing flights to their assigned runway and onward within the terminal area and the near-terminal airspace. The key contribution of this paper is the modeling of these problems, which until present have been studied in isolation, under a framework that is both unified and tractable. This allows the possibility of obtaining system-optimal solutions in a practical amount of time. Furthermore, the approach is implemented on historic data sets from both Boston Logan International and Dallas/Fort Worth International airports. Computational experience indicates that significant reductions in delays, fuel use, and emissions can be achieved from this optimization and that computational tractability is such that real-world instances can be solved within five to 10 minutes.