US-20260127969-A1 - REAL-TIME DYNAMIC 4D TRAJECTORY OPTIMIZATION FOR AVIATION

Abstract

Systems, devices, methods, and computer-readable media provide improved flight path selections. A system includes a graph representation operator configured to generate a graph of potential flight paths and actual obstacles in the potential flight paths, the potential flight paths extending from a takeoff location to a destination location, a predictive analysis model configured to receive the graph and environmental data and generate predictions of future environmental conditions based on the graph and the environmental data, a cost function and heuristic estimate operator configured to determine costs associated with flight paths of the potential flight paths based on the future environmental conditions, and a predictive pathfinding model configured to identify a flight path of the potential paths based on the costs, aircraft specific performance data, air traffic control constraints, current environmental conditions, and the future environmental conditions.

Inventors

• Vishnu Balachandran
• Jerrin Xavier

Assignees

• ARINC INCORPORATED

Dates

Publication Date

20260507

Application Date

20250609

Priority Date

20240625

Claims (20)

1. 1 . A flight plan optimization system comprising: a graph representation operator configured to generate a graph of potential flight paths and actual obstacles in the potential flight paths, the potential flight paths extending from a takeoff location to a destination location; a predictive analysis model configured to receive the graph and environmental data and generate predictions of future environmental conditions based on the graph and the environmental data; a cost function and heuristic estimate operator configured to determine costs associated with flight paths of the potential flight paths based on the future environmental conditions; and a predictive pathfinding model configured to identify a flight path of the potential paths based on the costs, aircraft specific performance data, air traffic control constraints, current environmental conditions, and the future environmental conditions.
2. 2 . The flight plan optimization system of claim 1 , wherein the costs include emissions and fuel efficiency.
3. 3 . The flight plan optimization system of claim 1 , wherein the predictive analysis model is implemented as a Mamba model.
4. 4 . The flight plan optimization system of claim 3 , wherein the predictive pathfinding model is implemented as a D* algorithm.
5. 5 . The flight plan optimization system of claim 1 , further comprising a graph update operator configured to generate updates to the graph based on the graph and the future environmental conditions from the predictive analysis model and provide the updates to the graph to the graph representation operator and the cost function and heuristic estimate operator.
6. 6 . The flight plan optimization system of claim 1 , further comprising a feedback operator configured to provide the identified flight path to the predictive analysis model.
7. 7 . The flight plan optimization system of claim 1 , further comprising a reactive standard instrument departures (SIDS)/standard instrument arrivals (STARS) operator configured to adjust SIDS and STARS data based on ATC data and the future environmental data and provide the adjusted SIDS and STARS data to the predictive analysis model.
8. 8 . A method comprising: generating, by a graph representation operator, a graph of potential flight paths and actual obstacles in the potential flight paths, the potential flight paths extending from a takeoff location to a destination location; receiving, by a predictive analysis model, the graph and environmental data; generating, by the predictive analysis model, predictions of future environmental conditions based on the graph and the environmental data; determining, by a cost function and heuristic estimate operator, costs associated with flight paths of the potential flight paths based on the future environmental conditions; and identifying, by a predictive pathfinding model, a flight path of the potential paths based on the costs, aircraft specific performance data, air traffic control constraints, current environmental conditions, and the future environmental conditions.
9. 9 . The method of claim 8 , wherein the costs include emissions and fuel efficiency.
10. 10 . The method of claim 8 , wherein the predictive analysis model is implemented as a Mamba model.
11. 11 . The method of claim 10 , wherein the predictive pathfinding model is implemented as a D* algorithm.
12. 12 . The method of claim 8 , further comprising: generating, by a graph update operator, updates to the graph based on the graph and the future environmental conditions from the predictive analysis model; and providing, by the graph update operator, the updates to the graph to the graph representation operator and the cost function and heuristic estimate operator.
13. 13 . The method of claim 8 , further comprising providing, by a feedback operator, the identified flight path to the predictive analysis model.
14. 14 . The method of claim 8 , further comprising adjusting, by a reactive standard instrument departures (SIDS)/standard instrument arrivals (STARS) operator, SIDS and STARS data based on ATC data and the future environmental data and provide the adjusted SIDS and STARS data to the predictive analysis model.
15. 15 . A non-transitory machine-readable medium including instructions that, when executed by a machine, cause the machine to perform operations for flight plan optimization, the operations comprising: generating, by a graph representation operator, a graph of potential flight paths and actual obstacles in the potential flight paths, the potential flight paths extending from a takeoff location to a destination location; receiving, by a predictive analysis model, the graph and environmental data; generating, by the predictive analysis model, predictions of future environmental conditions based on the graph and the environmental data; determining, by a cost function and heuristic estimate operator, costs associated with flight paths of the potential flight paths based on the future environmental conditions; and identifying, by a predictive pathfinding model, a flight path of the potential paths based on the costs, aircraft specific performance data, air traffic control constraints, current environmental conditions, and the future environmental conditions.
16. 16 . The non-transitory machine-readable medium of claim 15 , wherein the costs include emissions and fuel efficiency.
17. 17 . The non-transitory machine-readable medium of claim 15 , wherein the predictive analysis model is implemented as a Mamba model.
18. 18 . The non-transitory machine-readable medium of claim 17 , wherein the predictive pathfinding model is implemented as a D* algorithm.
19. 19 . The non-transitory machine-readable medium of claim 15 , wherein the operations further comprise: generating, by a graph update operator, updates to the graph based on the graph and the future environmental conditions from the predictive analysis model; and providing, by the graph update operator, the updates to the graph to the graph representation operator and the cost function and heuristic estimate operator.
20. 20 . The non-transitory machine-readable medium of claim 15 , wherein the operations further comprise providing, by a feedback operator, the identified flight path to the predictive analysis model.

Description

CLAIM OF PRIORITY This patent application claims the benefit of priority to India Application Serial No. 202411048720, filed Jun. 25, 2024, which is incorporated by reference herein in its entirety. TECHNICAL FIELD Embodiments regard improving path selection for airborne vehicles. Embodiments can include a selective state space neural network (NN) that works with an improved path selection technique to provide improvements over current trajectory optimization techniques. BACKGROUND The unpredictable nature of modern airspace, marked by volatile weather, variable air traffic, and changing navigational restrictions, demands a trajectory optimization system capable of real-time adaptability. Traditional models, often static and rigid, fail to accommodate such fluctuations, leading to inefficient and unsafe routing. Existing air traffic routing solutions frequently fall short in forecasting future airspace conditions with sufficient accuracy, compromising their ability to make preemptive, optimal routing decisions. This deficiency results in trajectories that do not maximize fuel efficiency or operational effectiveness. Many current systems inadequately integrate air traffic control (ATC) constraints into their optimization algorithms, resulting in routes that are less efficient and potentially non-compliant, thereby disrupting effective airspace management. As global attention to climate change intensifies, the aviation sector is under pressure to minimize its environmental footprint. Many existing optimization methods neglect this critical aspect, missing vital opportunities to advance the industry's green avionics initiatives by reducing carbon and other pollutant emissions. An inability of aviation path selection techniques to swiftly adjust to unforeseen developments, such as sudden weather shifts or airspace restrictions, introduces significant operational inflexibility. This limitation can lead to increased fuel usage, delays, and a compromised commitment to environmental goals. Algorithms like A*, widely used in prior art, are computationally demanding and struggle to process and adapt to changes in real-time efficiently. This computational burden limits their applicability in dynamic and complex environments, necessitating a more adaptive and less resource-intensive solution. BRIEF DESCRIPTION OF DRAWINGS FIG. 1 illustrates, by way of example, a diagram of an embodiment of a system for airborne vehicle path selection. FIG. 2 illustrates, by way of example, a diagram of an embodiment of a method for aircraft path selection. FIG. 3 is a block diagram of an example of an environment including a system for neural network (NN) training. FIG. 4 illustrates, by way of example, a block diagram of an embodiment of a machine in the example form of a computer system within which instructions, for causing the machine to perform any one or more of the methods or techniques discussed herein, may be executed. DETAILED DESCRIPTION The following description and the drawings sufficiently illustrate teachings to enable those skilled in the art to practice them. Other embodiments may incorporate structural, logical, electrical, process, and other changes. Portions and features of some examples may be included in, or substituted for, those of other examples. Teachings set forth in the claims encompass all available equivalents of those claims. Embodiments may be implemented in one or a combination of hardware, firmware and software. Embodiments may also be implemented as instructions stored on a computer-readable storage device, which may be read and executed by at least one processor to perform the operations described herein. A computer-readable storage device may include any non-transitory mechanism for storing information in a form readable by a machine (e.g., a computer). For example, a computer-readable storage device may include read-only memory (ROM), random-access memory (RAM), magnetic disk storage media, optical storage media, flash-memory devices, and other storage devices and media. Some embodiments may include one or more processors and may be configured with instructions stored on a computer-readable storage device. In confronting the multifaceted challenges of the aviation industry, the landscape of existing solutions, although extensive, frequently falls short in catering to continuously evolving requirements. The requirements include ensuring operational efficiency, safety, environmental sustainability, and the imperative for dynamic, real-time four-dimensional (4D) trajectory optimization. Instances of flight path optimization services provided herein set a new standard by, in part, leveraging cloud technology, thereby presenting a groundbreaking solution that surpasses the constraints of traditional models. This cloud-based flight management services (FMS) solution adeptly navigates the complexities of modern aviation, delivering a more adaptable, efficient, and environmentally conscious approach to tra