Autonomous planning of optimal four-dimensional trajectory for real-time en-route airspace operation with solution space visualisation

Chen, Yutong; Hu, Minghua; Yang, Lei

doi:10.1016/j.trc.2022.103701

Cited by 15 publications

(7 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 outlines the notable real-time 3D CR methods and their characteristics. Further details on these methods can be found in our previous paper (Chen et al, 2022). This paper will provide a comprehensive discussion on the challenges encountered by conventional real-time CR methods.…”

Section: Conventional 3d Real-time Conflict Resolution Methodsmentioning

confidence: 99%

A General Real-Time Three-Dimensional Multi-Aircraft Conflict Resolution Method Using Multi-Agent Reinforcement Learning

CHEN

Yang

et al. 2023

Preprint

View full text Add to dashboard Cite

Section: Conventional 3d Real-time Conflict Resolution Methodsmentioning

confidence: 99%

A General Real-Time Three-Dimensional Multi-Aircraft Conflict Resolution Method Using Multi-Agent Reinforcement Learning

CHEN

Yang

et al. 2023

Preprint

View full text Add to dashboard Cite

“…This approach resorts to the machine learning technique, specifically trajectory clustering, in order to represent the flight segments and construct flight plans [11,12,23,24]. The historical route amendments are adopted as a static foundation and trained to get the prediction model that generates the operationally acceptable flight plan options.…”

Section: Flight Segment Constructionmentioning

confidence: 99%

Sequence‐to‐sequence transfer transformer network for automatic flight plan generation

Yang,

Qian,

Zhang

et al. 2023

IET Intelligent Trans Sys

View full text Add to dashboard Cite

In this work, a machine translation framework is proposed to tackle the flight plan generation in the air transport field. Diverging from the traditional human expert‐based way, a novel sequence‐to‐sequence transfer transformer network to automatic flight plan generation with enhanced operational acceptability is presented. It allows the user to translate the departure and arrival airport pairs denoted as test sentences, into the flyable waypoint sequences denoted as the corresponding source sentences. The approach leverages deep neural networks to autonomously learn air transport specialized knowledge and human expert insights from industry legacy data. Moreover, a multi‐head attention mechanism is adopted to model the complex correlation between airport pairs. Besides, we introduce an innovative waypoint embedding layer to learn effective embeddings for waypoint sequences. Additionally, an extensive flight plan dataset is constructed utilizing real‐world data in China spanning from July to September 2019. Employing the proposed model, rigorous training and testing procedures are conducted on this dataset, yielding remarkably favourable outcomes based on automatic evaluation metrics that are BLEU and METEOR, which outperform other popular approaches. More importantly, the proposed approach achieves high performance in the operational validation and visualization, showing its application potential for real‐world air traffic operation.

show abstract

“…With the shared traffic situation awareness, the alternative solutions are compared and negotiated to achieve the Collaborative Decision‐Making (CDM) in the trajectory planning. The concept of spatio‐temporal reachable space has been proposed in the design of the automation tool for the CD&R [35, 36]. With the introduction of the Space‐time Prism (STP) theory in time geography, the spatio‐temporal reachable space describes the continues variation of spatially reachable space over time of the aircraft under the RTA constraints, based on the information extracted from the flight plan and aircraft performance database.…”

Section: Air‐ground Traffic Situation Awareness Sharingmentioning

confidence: 99%

Autonomous and collaborative trajectory planning for traffic complexity management

Zhou

Yang

et al. 2022

IET Intelligent Trans Sys

Self Cite

View full text Add to dashboard Cite

To accommodate growing air traffic demand, the traffic complexity management plays a crucial role in the capacity improvement of future automated air traffic management. In this paper, an autonomous and collaborative trajectory planning (ACTP) method is presented to facilitate collaborative decision‐making and enhance flexibility of the traffic complexity management in the en route airspace. A nonlinear integer model is formulated for the conflict‐free autonomous trajectory planning by reorganizing the trajectories with the combination of speed adjustment, lateral rerouting and flight level allocation maneuvers. Within the framework of the air‐ground situation awareness sharing, the spatio‐temporal reachable space is defined to describe the feasible solution space under the constraints of aircraft performance and required time of arrival. In addition, both the system‐level and the individual‐level objectives, traffic complexity and flight efficiency, are considered in the model, which are measured through the metric based on linear dynamical systems and the deviation from the user‐preferred trajectory. To balance the optimality and computational efficiency in the multi‐aircraft trajectory planning, a multi‐aircraft clustered and collaborative optimization algorithm is proposed based on the hybrid distributed‐centralized control strategy. The experimental results of the scenario in Western China airspace is presented, which verify the effectiveness of the proposed ACTP method through the comparison of other methods. Furthermore, a multi‐criteria decision‐making problem is discussed to strike a better trade‐off between different objectives in the trajectory planning.

show abstract

Autonomous planning of optimal four-dimensional trajectory for real-time en-route airspace operation with solution space visualisation

Cited by 15 publications

References 46 publications

A General Real-Time Three-Dimensional Multi-Aircraft Conflict Resolution Method Using Multi-Agent Reinforcement Learning

A General Real-Time Three-Dimensional Multi-Aircraft Conflict Resolution Method Using Multi-Agent Reinforcement Learning

Sequence‐to‐sequence transfer transformer network for automatic flight plan generation

Autonomous and collaborative trajectory planning for traffic complexity management

Contact Info

Product

Resources

About