Aircraft flight path noise reduction

Abstract

A method for generating flight paths for an aircraft includes: at a computing system, receiving, for a plurality of waypoints in a geographic region, a predicted aircraft noise level at each of the multiple waypoints, the predicted aircraft noise level being predicted at least in part based on multiple flight parameters of the aircraft. The predicted aircraft noise level is input to a flight path prediction system configured to generate candidate flight paths for the aircraft through the geographic region based at least in part on the predicted aircraft noise level. The candidate flight paths are output from the flight path prediction system, wherein the candidate flight paths are predicted to result in less ground level noise when followed by the aircraft, compared to alternative flight paths through the geographic region.

Description

Technical Field

[0001] This disclosure pertains to the technical field of reducing noise experienced on the ground due to overhead aircraft. Background Technology

[0002] Arriving and departing aircraft at airports generate noise levels that can disrupt communities surrounding the airport. While aircraft-induced noise has been significantly reduced over the past few decades, advancements in navigation technology have led to aircraft flying over some communities at an increased frequency. This change has resulted in complaints from communities located on departure and arrival flight tracks.

[0003] In response to these complaints, many countries have enacted regulations to control aircraft noise. For example, the U.S. Federal Aviation Administration (FAA) sets maximum noise levels that individual civil aircraft can generate during takeoff and landing, as well as near airports. Air navigation service providers (ANSPs) around the world are working to enforce noise reduction procedures for arrivals and departures and penalize airlines for flights that generate noise exceeding mandatory thresholds. Summary of the Invention

[0004] This invention is not a broad summary of the specification. It is not intended to identify key or essential elements of the specification, nor to outline any scope of embodiments specific to the specification or any scope of the claims. Its sole purpose is to present some concepts of the specification in a simplified form as a prelude to the more detailed description presented in this disclosure.

[0005] A method for generating an aircraft flight path includes: at a computing system, receiving, for a plurality of waypoints in a geographic region, a predicted aircraft noise level at each waypoint, the predicted aircraft noise level being predicted at least in part based on a plurality of flight parameters of the aircraft. The predicted aircraft noise level is input to a flight path prediction system configured to generate candidate flight paths for the aircraft through the geographic region based at least in part on the predicted aircraft noise level. The candidate flight paths are output from the flight path prediction system, wherein the predicted candidate flight paths result in less ground-level noise when followed by the aircraft compared to alternative flight paths through the geographic region.

[0006] The features, functions, and advantages already discussed can be implemented independently in various embodiments or combined in other embodiments, further details of which can be seen in the following description and figures. Attached Figure Description

[0007] Figure 1A and Figure 1B An aerial view schematically illustrates an example geographic area that includes multiple waypoints at which aircraft noise levels are predicted.

[0008] Figure 2 An example method for generating flight paths for aircraft is shown.

[0009] Figure 3 An example computational system for implementing a flight path prediction system is illustrated schematically.

[0010] Figure 4 The illustration schematically shows the collection of historical measurement noise levels.

[0011] Figure 5 A virtual grid overlaid on a geographic area is illustrated schematically, where the size of the virtual grid is configurable.

[0012] Figures 6A-6C The diagram illustrates how to generate flight paths by connecting multiple cells to cell segments between grid cells of a virtual grid.

[0013] Figures 7A-7C The diagram illustrates the generation of flight paths as a sequence of waypoints selected via a weighted graph-based algorithm.

[0014] Figure 8 An example computing system is illustrated schematically. Detailed Implementation

[0015] This disclosure considers a system for generating flight paths of aircraft through geographical areas to reduce accumulated aircraft noise. First, refer to... Figure 1A The image shows a map of geographic region 100. Aircraft 102 is flying through this geographic region along flight path 104. The operation of the aircraft generates noise, which can be audible and potentially disruptive on the ground. The amount of noise experienced at any given point along the ground depends on the specific flight path taken by the aircraft, with some potentially producing a greater level of perceived noise (compared to other flight paths).

[0016] Therefore, the flight path generation technology described herein can be used to generate flight paths for aircraft, reducing disturbance to surrounding communities and enabling aircraft operators to improve operations and mitigate the risk of penalties for exceeding mandatory noise thresholds. The system is applicable to addressing any suitable noise-related metric, such as maximum sound pressure level (Lamax), sound exposure level (SEL), etc. Furthermore, while a specific discussion has been given in the context of airport arrivals / departures, it is understood that this discussion applies to any environment near an aircraft that creates noise levels based on the aircraft's path relative to the location experiencing the noise.

[0017] As will be described in more detail below, flight paths can be generated based on predicted noise levels at multiple different waypoints distributed throughout the geographic area (e.g., an assessment of the noise levels that would occur if the aircraft's path would pass through or approach a given waypoint). Using the predicted noise in conjunction with other considerations, waypoints can be sequentially connected stepwise to create a flight path that optimally reduces noise. As used herein, "optimal" does not imply that the selected waypoints will produce the lowest possible noise—other factors may influence path selection. Therefore, "optimal" will generally refer to the minimum noise path that satisfies a set of relevant constraints. In other words, "optimal" may generally refer to a reduced noise level (compared to other path options).

[0018] Figure 1B Geographic region 100 is shown again, comprising multiple waypoints indicated by markers distributed throughout the region. Five of these waypoints are marked as waypoints 106A-106E and are located along the flight path 104 of aircraft 102. These waypoint indications can be used to predict the orientation of aircraft noise levels. For example, ground-based sound sensing equipment can be used to measure the noise generated by various different aircraft during multiple previous flights. Based on these ground-based measurements, it is possible to predict the amount of noise a given aircraft will cause when passing through different waypoints in the region.

[0019] In some examples, the techniques described herein can be applied to airspace areas associated with major airports—for example, locations near city centers with significant air traffic. However, it should be understood that the techniques described herein can be applied to any suitable geographical area of ​​size and location. Any suitable number of different waypoints can be defined within a given geographical area, and such waypoints can have any suitable regular or irregular distribution. In some examples, waypoints have a three-dimensional distribution throughout the geographical area. For example, in some examples, waypoints are distributed throughout the entire airspace of the geographical area. In some examples, the geographical area may include one or more ground-level waypoints—for example, located at or near an airport runway. Furthermore, any suitable equipment or sensors can be distributed throughout the geographical area for measuring ground-level noise.

[0020] In any case, the ground noise level measured by appropriate ground-based sensing equipment can be used to predict the noise level at different waypoints along potential future flight paths. Furthermore, this predicted noise level can be used to generate candidate flight paths for aircraft, reducing the perceptible noise caused by the aircraft. Figure 2 An example method 200 for generating flight paths for an aircraft is illustrated. The steps of method 200 can be started, terminated, and / or repeated at any suitable time and in response to any suitable conditions. Method 200 can be implemented by any suitable computing system with one or more computing devices. Any computing device implementing the steps of method 200 can have any suitable capabilities, hardware configuration, and form factor. In some examples, method 200 can be implemented as follows regarding... Figure 8 The computing system described is 800.

[0021] In method 202, method 200 includes receiving predicted aircraft noise levels at each of the multiple waypoints in a geographic region. The predicted aircraft noise levels are predicted based on at least multiple flight parameters of the aircraft.

[0022] about Figure 3 Method 200 is described in more detail. Specifically, Figure 3 An example computing system 300 is schematically illustrated. As mentioned above, the computing system 300 can have any suitable configuration and capabilities. In some examples, aspects of the computing system 300 can be distributed among two or more different computing devices. In some examples, the computing system 300 is implemented as follows regarding... Figure 8 The computing system described is 800.

[0023] exist Figure 3In this system, computing system 300 implements flight path prediction system 302. The flight path prediction system has received a set of predicted noise levels 304 corresponding to multiple different waypoints within a geographic area. In this example, the predicted noise levels are predicted by noise prediction system 306 of the computing system. The noise prediction system implements machine learning model 308, which is configured to predict the noise levels based at least in part on a set of flight parameters 310 received by the computing system.

[0024] The flight path prediction system 302 and the noise prediction system 306 can each be implemented as any suitable combination of computer software, hardware, and / or firmware components. In some examples, the flight path prediction system and the noise prediction system are separate software applications running on the same computing device or on different computing devices communicatively coupled to each other. As will be described in more detail below, each of the flight path prediction system and the noise prediction system can implement any suitable model and / or algorithm to generate output data based on suitable input data. In some examples, suitable machine learning (ML) and / or artificial intelligence (AI) techniques may be used.

[0025] For example, machine learning model 308 is used to predict the predicted noise level 304 based at least in part on the set of flight parameters 310. In some cases, the noise prediction system may include two or more different machine learning models for predicting noise levels—for example, corresponding to different geographical regions (e.g., different airport areas), different aircraft types, different types of flight paths (e.g., arrival or departure), etc. Any suitable underlying ML technique can be used. As an example, the ML model can be selected from at least one of the following: linear machine learning models, nonlinear machine learning models, ensemble machine learning model systems, neural network models, transformer models, and / or other suitable types of machine learning models.

[0026] Furthermore, machine learning models can be trained in any suitable manner. Figure 3 In the example, the predicted noise level is based at least in part on multiple historical noise levels 312 measured throughout the geographic area. Historical noise levels (albeit measured by ground-based equipment) can be used to predict the amount of noise experienced at various waypoints. This is about Figure 4The diagram schematically illustrates, again showing geographic region 100 and multiple waypoints distributed throughout the region. In this example, multiple previous flight paths are shown throughout the geographic region, one of which is labeled as previous flight path 400. During these previous aircraft flights, sound levels were measured at ground-based sensing equipment. The locations of several ground sensors (e.g., microphones) are marked with black squares, including sensor location 401. The noise levels measured by these ground sensors are output as historical measured noise levels 402. It should be understood that multiple different ground sensors may be distributed throughout the geographic region and used to measure the noise levels experienced on the ground while the aircraft is in flight.

[0027] Back Figure 3 The historical measured noise level is associated with multiple historical flight parameters 314 corresponding to multiple previous aircraft flights. In other words, in this example, the predicted aircraft noise level is predicted by a machine learning model trained at least in part on the historical measured noise levels and historical flight parameters of multiple previous aircraft flights. In this way, for a given set of flight parameters corresponding to an upcoming aircraft flight, the noise prediction system can be used to predict the noise level of the upcoming flight at each of multiple waypoints (if the flight passes through or approaches that waypoint).

[0028] It should be understood that "flight parameters" can include a wide variety of different types of information relating to a particular aircraft and / or current environmental conditions. As a non-limiting example, flight parameters may include aircraft type (e.g., manufacturer, model, size, aerodynamic characteristics), engine type (e.g., turbojet, turbofan, turboprop), engine thrust settings (e.g., takeoff, climb, cruise, approach, and landing may each have different thrust settings, producing different noise levels), aircraft speed, altitude, time of day, weight and load, atmospheric conditions (e.g., weather conditions, temperature, humidity, air pressure, wind speed, wind direction), ground terrain (e.g., urban areas, bodies of water, forests), etc. Flight parameters 310 may include any or all such information for an upcoming aircraft flight, while historical flight parameters may include any or all such information from each of several previous aircraft flights. Furthermore, flight parameters may include any additional or alternative information from the examples discussed herein.

[0029] It should be understood that flight parameters can be received from any suitable source. For example, flight parameters can be loaded from a database, received via a computer network, loaded from removable storage devices, or manually entered by human workers. Some flight parameters can be collected from devices or sensors located at waypoints distributed throughout the geographic area, from devices or sensors located far from waypoints, and / or from any other suitable source.

[0030] In any case, based on this set of flight parameters, the noise prediction system outputs the predicted noise levels for multiple waypoints. These noise predictions can be made at any suitable level of granularity to take into account aircraft type, speed, altitude, atmospheric conditions, or any other appropriate parameters. The cumulative noise level can then be predicted for a potential flight path constructed from the multiple waypoints.

[0031] Therefore, we will temporarily return to Figure 2 In step 204, method 200 includes inputting a predicted aircraft noise level into a flight path prediction system, which is configured to generate candidate flight paths for the aircraft through a geographic area. The candidate flight paths may be generated at least in part based on the predicted aircraft noise level and multiple flight path constraints. Figure 3 In the example, the flight path prediction system generates candidate flight paths 318 based on the predicted noise level 304 and multiple route constraints 316.

[0032] Generally, flight path prediction systems generate candidate flight paths that are predicted to cause less ground-level noise when followed by an aircraft, compared to alternative flight paths through a geographic area. In other words, the candidate flight paths generated by the flight path prediction system are predicted to cause less perceptible ground-level noise compared to naive flight paths generated without respect to noise reduction. In some examples, the flight path prediction system aims to predict flight paths that minimize the amount of ground-level noise—for example, the minimum noise-probable flight path through a geographic area. Alternatively, in some examples, the flight path prediction system aims to generate flight paths that are predicted to cause less ground-level noise at ground locations within the geographic area than a predefined noise target—for example, a maximum sound level imposed by applicable regulations—without necessarily generating the minimum noise-probable flight path.

[0033] Multiple route constraints include any suitable information relating to the aircraft's ability to move throughout a geographic area—for example, any constraints on waypoints within a geographic area through which the aircraft can fly or approach. As a non-limiting example, multiple route constraints may include one or more of the following: the aircraft's turning radius, coordinates of restricted airspace within the geographic area (e.g., no-fly zones, special-purpose airspace), weather conditions within the geographic area (e.g., locations affected by convective weather), and departure and arrival procedures applied to the geographic area (e.g., Standard Instrument Departure Line (SID) and / or Standard Arrival Line (STAR)). Route constraints can be received from any suitable source—e.g., loaded from one or more databases, received via a suitable computer network (e.g., accessed via the Internet through an API), manually entered by human workers, etc. Furthermore, in some examples, one or more route constraints can be dynamically updated over time. For example, as weather conditions change, weather-related route constraints can be dynamically transmitted to a flight path prediction system and used to generate candidate flight paths for the future.

[0034] Various methods can be employed to select candidate flight paths to optimally reduce noise impact. In some examples, generating candidate flight paths includes a grid-based approach involving overlaying a virtual grid onto a geographic region, such that for each grid cell of the virtual grid, a grid-related predicted noise level for that grid cell is interpolated from one or more predicted aircraft noise levels from one or more waypoints falling within the grid cell. Candidate flight paths can then be generated as multiple cell-to-cell segments between the grid cells of the virtual grid, where each cell-to-cell segment is selected at least in part based on the grid-related predicted noise levels of the grid cells connected by the cell-to-cell segments. For example, this can be performed using a dynamic grid-based Viterbi algorithm to generate candidate flight paths. Figure 3 In the example, the flight path prediction system implements the Viterbi algorithm 320, which can be used to generate candidate flight paths.

[0035] Figure 5 An example grid-based method is depicted, where a virtual grid 500 is overlaid on a geographic region 100. The virtual grid comprises multiple grid cells, three of which are labeled as grid cells 502A, 502B, and 502C. It should be understood that... Figure 5 The size of the virtual grid relative to the geographic region 100 is not limited. Typically, the size of each cell in the virtual grid can be set such that the geographic region is represented by two or more grid cells. In some examples, the virtual grid may include dozens, hundreds, or thousands of grid cells representing different parts of the geographic region.

[0036] At each location on the grid, the predicted noise value of the waypoint falling within each grid cell is used to calculate the noise value of the grid cell. Figure 5 In this example, two distinct waypoints fall within grid cell 502A. The predicted noise values ​​for these waypoints are interpolated to give the grid-level predicted noise level 504 for the grid cell. This can be repeated for any or all grid cells to give the grid-level predicted noise level for any or all grid cells. In some examples, a virtual grid may include one or more grid cells that do not include waypoints for measuring noise levels (e.g., cells representing remote areas, bodies of water, etc.). In such cases, any suitable noise value can be predicted for empty grid cells. For example, the average noise level can be used, interpolated values ​​from neighboring cells can be used, zero values ​​can be used, etc.

[0037] Figures 6A-6C An example grid-based method for flight path generation is shown. Specifically, Figures 6A-6C An example virtual grid 600 is shown, which can be overlaid on a geographic area as described above. Figure 6A In this context, a specific grid location 602A has been identified as the starting point of a flight path. For example, this could correspond to the location of the airport from which the aircraft will depart. Generally, the starting point of a flight path corresponds to the grid location where the aircraft begins its flight through a geographic area. This could correspond to an airport, an airstrip, or another location from which the aircraft takes off (e.g., a body of water in the case of a seaplane), or the location where the aircraft is expected to enter the geographic area from an adjacent area. Figures 6A-6C In the examples, grid locations are shown as intersections between different grid cells, but this is not limiting. Instead, in some examples, flight paths can be generated based on the center of each grid cell, another suitable orientation within each grid cell, or the orientation falling on the boundary between neighboring / orthogonal grid cells.

[0038] exist Figure 6AIn this example, the additional grid positions 602B, 602C, and 602D are candidates for extending the flight path. There are three candidate extensions in this example, but it should be understood that this is not limiting. In other examples, any suitable number of different grid positions can be considered to extend the flight path, depending on the expected direction of flight and any applicable route constraints. This set of candidate flight path extensions available for selection can be determined using any suitable criteria or constraints (including qualified flight paths in the airspace, whether it is practically feasible for the aircraft to maneuver to a specific waypoint, etc.). Any suitable criteria can be used to create a pool of candidate grid positions for path extension. The flight path generation method involves selecting from these candidate flight path extensions based on what produces the minimum accumulated noise and satisfies other relevant constraints (e.g., whether it is feasible / permissible for the aircraft to move through the path) to determine the next grid position in the flight path.

[0039] Figure 6B Reflects the reference Figure 6A The discussion yielded definitive results. Specifically, the assessment reflects the selection of waypoint grid location 602C as an extension of the flight path. Grid locations 602A and 602C are connected by cell-to-cell line segment 604, which defines a portion of the entire flight path. This process is repeated at each established grid location—that is, the predicted noise level assessment at the grid location can be used to further establish the next grid location for the path. Figure 6C A complete computational flight path 606 across a grid is depicted, in which a series of established grid locations define the flight path, which reduces accumulated noise compared to an alternative flight path through a geographic region.

[0040] In the example above, grid-based flight path expansion selection can be achieved by applying a dynamic grid-based Viterbi algorithm. For example, this can model the flight path generation problem as an optimization problem aimed at finding the flight path through a virtual grid that minimizes the cost, where the cost corresponds to the predicted noise. Using the Viterbi algorithm, each cell in the virtual grid can be viewed as a state that the aircraft can occupy: S = { s 1 , s 2 , … , s K} = state space The Viterbi algorithm works by evaluating the most likely sequence of states (grid cells) based on a set of observations. These observations may include the predicted noise level at different grid locations, and / or factors such as weather conditions, airspace constraints, etc.

[0041] Y ={y 1 , y 2 ,…, y T = (Observation sequence) Multiple observation sequences together constitute the observation space. O ={ o 1 , o 2 ,…, o N } If time t The observed value is o i ,but y t = o i .

[0042] The probability is calculated, representing the likelihood of transitioning from one state to another—for example, reflecting the cost or probability of moving from one cell to another. This can be factored in by factors such as the distance between cells, the fuel consumption of the transition, and / or the desirability of the path (e.g., avoiding densely populated areas to reduce noise impact). Π ={π 1 , π 2 ,…, π K } = Initial probability The Viterbi algorithm can then calculate the size as K K The transition matrix A It indicates from the state s i arrive s j The transformation, and calculate the size as K N emission matrix B It indicates from the state s i Observed state o j The algorithm iteratively generates a path based on the calculated values ​​and matrices by selecting a series of interconnected nodes (states) from start to finish, reducing accumulated noise along the selected routes. Specifically, the algorithm generates paths...X ={ x 1 , x 2 ,…, x T This is a state sequence. x n ∈ S = { s 1 , s 2 , … , s K The accumulated noise along the path is minimized or otherwise reduced.

[0043] In another example approach, candidate flight paths are generated as a sequence of waypoints connecting the start waypoint to the end waypoint within a geographic region, selected via a weighted graph-based algorithm implemented through a flight path prediction system. Let's return to... Figure 3 Flight path prediction system implements A Pathfinder Algorithm 322 and D Lite algorithm 324 can be used to generate candidate flight paths, as described in more detail below. It should be understood that the flight path prediction system can use either or both of grid-based methods and weighted graph-based algorithms, and / or another suitable algorithm not explicitly described herein.

[0044] about Figures 7A-7C The use of the weighted graphical method is illustrated schematically. Figure 7A A graph 700 schematically illustrates multiple example waypoint locations, which can be distributed across geographic regions as described above. Three of these waypoints are labeled waypoints 702A-702C. In this example, each waypoint and its predicted noise value are defined as nodes within the graph. Adjacent nodes are connected to each other in various ways via edges (such as edge 704) to account for the probability that associated waypoints can pass consecutively in the flight path to be established. This results in a directed acyclic graph (DAG).

[0045] Generally, weighted graph-based mechanisms can be used to construct a flight path that optimizes accumulated aircraft noise from a series of waypoints. As in the previous example, the predicted noise values ​​for candidate waypoints are obtained using the machine learning methods cited earlier and / or any other feasible prediction methods. Figures 6A-6CSimilar to the example, the graphical mechanism is used to start from the established bearing (the waypoints already selected for the route) and selectively extend the path to other waypoints in multiple iterations based on constraints and costs (minimizing noise) to achieve the desired route.

[0046] Figure 7B and Figure 7C For reference Figures 6A-6C A similar approach is used with graph 700. Specifically, given established waypoints already selected for the route, a noise minimization mechanism is used to further extend the route to adjacent waypoints. Figure 7B In this process, the initial waypoint 702A has been established, and the path determination mechanism is used to select from multiple adjacent candidate waypoints 702B, 702C, and 702D, which, together with the initial waypoint 702A, can form a feasible flight path. Figure 7C In this process, iterative selection from neighboring candidates has yielded a segment for waypoint 702C to extend the flight path. Figure 6C Similarly, this iterative selection from candidate neighbors is performed iteratively to produce results such as Figure 7C The diagram shows a complete series of waypoints defining flight path 704.

[0047] Combination Figures 7A-7C Examples of this approach can be derived using various graphical methods. Generally, each iteration involves taking the previously established waypoints in the path and determining which waypoint the path should extend to, taking into account the predicted noise of the candidate waypoints. One approach involves accounting for the noise cost of the path segments and an estimate of the cost required to extend the path to a completed state (e.g., through relevant airspace). As an example, a weighted A... The search algorithm determines the path cost within graph 700, but any other suitable graph traversal or cost calculation mechanism can be used to generate a set of waypoints that satisfy the relevant constraints, while reducing / optimizing the accumulated noise of the associated flight paths.

[0048] In some examples, weighted graph-based algorithms also include D The Lite algorithm considers dynamic updates to multiple flight path constraints. This allows for dynamic path updates in response to new data, ensuring that flight paths remain optimized for noise minimization despite changing conditions. For example, as previously mentioned, flight path constraints affecting aircraft navigation (such as convective weather positions) can be dynamically updated as conditions change, and such dynamic updates can be input into D when generating candidate flight paths. Lite algorithm.

[0049] In some cases, grid-based Viterbi methods and weighted A Search algorithms can be used in different situations, and in some cases, they can be used together. It should be understood that the determinism associated with certain flight parameters will vary regarding when the aircraft will fly over areas that will experience noise (e.g., near the airport). For example, as departure / arrival times approach, the uncertainty of various parameter values ​​(air traffic in the terminal area, convective weather, etc.) may increase, thus favoring deterministic methods (i.e., A...). (Algorithm). However, when uncertainty is high (farther from arrival / departure), strategic and stochastic methods (i.e., Viterbi) can be used. Furthermore, since parameter uncertainty can vary over a spectrum, these two algorithms can be run in parallel to optimize performance.

[0050] In any case, use either a grid-based or weighted graph-based method, or both, to generate candidate flight paths. Let's return to the previous point. Figure 2 In step 206, method 200 includes a flight path prediction system outputting candidate flight paths. It should be understood that candidate flight paths can be “output” in any suitable manner—for example, they can be written to a file, stored in a computer storage device, transferred to another computing device, displayed on a computer monitor, etc. In some examples, the flight path prediction system is configured to output multiple potential flight paths, which a human pilot can choose from based on various considerations, such as predicted noise, total distance, fuel consumption, etc. In some cases, candidate flight paths are output to an autonomous flight system configured to guide the aircraft along the flight paths without human intervention.

[0051] The methods and processes described herein can be associated with a computing system of one or more computing devices. In particular, such methods and processes can be implemented as an executable computer application, a network-accessible computing service, an application programming interface (API), a library, or a combination of the above and / or other computing resources.

[0052] Figure 8 A simplified representation of a computing system 800 is schematically shown, which is configured to provide any to all computing functions described herein. The computing system 800 may take the form of one or more network-accessible devices, personal computers, server computers, mobile computing devices, and / or other computing devices.

[0053] The computing system 800 includes a logic subsystem 802 and a storage subsystem 804. The computing system 800 may optionally include a display subsystem 806, an input subsystem 808, a communication subsystem 810, and / or... Figure 8 Other subsystems not shown.

[0054] The logical subsystem 802 includes one or more physical devices configured to execute instructions. For example, the logical subsystem may be configured to execute instructions as part of one or more applications, services, or other logical constructs. The logical subsystem may include one or more hardware processors configured to execute software instructions. Additionally or alternatively, the logical subsystem may include one or more hardware or firmware devices configured to execute hardware or firmware instructions. The processor of the logical subsystem may be single-core or multi-core, and the instructions executed thereon may be configured for sequential, parallel, and / or distributed processing. Individual components of the logical subsystem may optionally be distributed across two or more separate devices that can be remotely located and / or configured for coordinated processing. Aspects of the logical subsystem may be virtualized and executed by remotely accessible, networked computing devices configured in a cloud computing configuration.

[0055] Storage subsystem 804 includes one or more physical devices configured to temporarily and / or permanently store computer information, such as data and instructions executable by the logical subsystem. When the storage subsystem includes two or more devices, these devices may be co-located and / or remotely positioned. Storage subsystem 804 may include volatile, non-volatile, dynamic, static, read / write, read-only, random access, sequential access, location-addressable, file-addressable, and / or content-addressable devices. Storage subsystem 804 may include removable and / or built-in devices. The state of storage subsystem 804 can be changed when the logical subsystem executes instructions—for example, to store different data.

[0056] Various aspects of the logic subsystem 802 and the storage subsystem 804 can be integrated together into one or more hardware logic components. For example, such hardware logic components may include program-specific integrated circuits and application-specific integrated circuits (PASIC / ASIC), program-specific standard products and application-specific standard products (PSSP / ASSP), system-on-a-chip (SOC), and complex programmable logic devices (CPLD).

[0057] The logic subsystem and storage subsystem can collaborate to instantiate one or more logic machines. As used herein, the term "machine" is used collectively to refer to a combination of hardware, firmware, software, instructions, and / or any other components that collaborate to provide computer functionality. In other words, "machine" is never an abstract concept and always has a tangible form. A machine can be instantiated by a single computing device, or a machine can include two or more sub-components instantiated by two or more different computing devices. In some implementations, a machine includes local components (e.g., software applications executed by a computer processor) that collaborate with remote components (e.g., cloud computing services provided by a network of server computers). The software and / or other instructions that give a particular machine its functionality can optionally be stored as one or more unexecuted modules on one or more suitable storage devices.

[0058] When included, display subsystem 806 can be used to present a visual representation of the data stored in storage subsystem 804. This visual representation may take the form of a graphical user interface (GUI). Display subsystem 806 may include one or more display devices utilizing virtually any type of technology. In some embodiments, display subsystem may include one or more virtual, augmented, or mixed reality displays.

[0059] When included, the input subsystem 808 may include or interface with one or more input devices. Input devices may include sensor devices or user input devices. Examples of user input devices include a keyboard, mouse, touchscreen, or game controller. In some embodiments, the input subsystem may include or interface with a selected Natural User Input (NUI) component. Such a component may be integrated or peripheral, and the transduction and / or processing of input actions may be handled on-board or off-board. Example NUI components may include a microphone for voice and / or sound recognition; an infrared, color, stereo, and / or depth camera for machine vision and / or gesture recognition; and a head tracker, eye tracker, accelerometer, and / or gyroscope for motion detection and / or intent recognition.

[0060] When included, the communication subsystem 810 can be configured to communicatively couple the computing system 800 to one or more other computing devices. The communication subsystem 810 may include wired and / or wireless communication devices compatible with one or more different communication protocols. The communication subsystem can be configured to communicate via personal, local area, and / or wide area networks.

[0061] This disclosure is presented by way of example and with reference to the accompanying drawings. Components, process steps, and other elements that may be substantially the same in one or more drawings are identified in a coordinated manner and described with minimal repetition. However, it should be noted that the elements identified in a coordinated manner may also differ to some extent. It should also be noted that some drawings may be schematic and not drawn to scale. Various drawing scales, aspect ratios, and numbers of parts shown in the drawings may be intentionally distorted to make certain features or relationships easier to see.

[0062] In addition, this disclosure includes configurations based on the following examples.

[0063] Example 1. A method for generating flight paths for an aircraft, the method comprising: at a computing system, receiving, for a plurality of waypoints in a geographic region, predicted aircraft noise levels at each of the plurality of waypoints, the predicted aircraft noise levels being predicted at least in part based on a plurality of flight parameters of the aircraft; inputting the predicted aircraft noise levels into a flight path prediction system configured to generate candidate flight paths for the aircraft through the geographic region based at least in part on the predicted aircraft noise levels; and outputting the candidate flight paths from the flight path prediction system, wherein the candidate flight paths are predicted to result in less ground level noise when followed by the aircraft, compared to alternative flight paths through the geographic region.

[0064] Example 2. According to the method of Example 1, generating the candidate flight path includes overlaying a virtual grid onto the geographic region, such that for grid cells of the virtual grid, the grid-related predicted noise level of the grid cell is interpolated from one or more predicted aircraft noise levels from one or more waypoints falling within the grid cell.

[0065] Example 3. According to the method of Example 2, the candidate flight path is generated as a plurality of cell-to-cell segments between grid cells of the virtual grid, wherein each cell-to-cell segment is selected at least in part based on the noise level of a grid-related prediction of the grid cells connected by the cell-to-cell segment.

[0066] Example 4. According to the method of Example 3, wherein the flight path prediction system implements a dynamic grid-based Viterbi algorithm to generate the candidate flight paths.

[0067] Example 5. According to the method of Example 1, the candidate flight path is generated as a sequence of waypoints connecting the start waypoint to the end waypoint within the geographic region, the waypoint sequence being selected via a weighted graph-based algorithm implemented by the flight path prediction system.

[0068] Example 6. According to the method described in Example 5, the weighted graph-based algorithm includes A Pathfinder Algorithm.

[0069] Example 7. According to the method described in Example 6, the weighted graph-based algorithm further includes D. The Lite algorithm is used to take into account dynamic updates of multiple route constraints.

[0070] Example 8. According to the method of Example 1, wherein the candidate flight path is predicted to result in a ground level noise amount less than a predefined noise target at a ground location in the geographic region.

[0071] Example 9. According to the method of Example 1, the candidate flight path is further generated at least in part based on a plurality of route constraints, and the plurality of route constraints include one or more of the following: the turning radius of the aircraft, the coordinates of the restricted airspace within the geographic region, the weather conditions in the geographic region, and departure and arrival procedures applied to the geographic region.

[0072] Example 10. According to the method of Example 1, wherein the predicted aircraft noise level is predicted at least in part based on multiple historical noise levels measured by multiple previous aircraft flying through the geographic area.

[0073] Example 11. According to the method of Example 10, wherein the predicted aircraft noise level is predicted by a machine learning model trained at least in part on the historical measured noise level and historical flight parameters of the plurality of previous aircraft flights.

[0074] Example 12. The method according to Example 11, wherein the historical flight parameters include one or more of the following: aircraft type, aircraft speed, altitude, time of day, and weather conditions of the plurality of previous aircraft flights.

[0075] Example 13. A computing system comprising: a logic subsystem; and a storage subsystem storing instructions executable by the logic subsystem to: receive, for a plurality of waypoints in a geographic region, a predicted aircraft noise level at each of the plurality of waypoints, the predicted aircraft noise level being predicted at least in part based on a plurality of flight parameters of the aircraft; input the predicted aircraft noise level to a flight path prediction system configured to generate, at least in part based on the predicted aircraft noise level, a candidate flight path for the aircraft through the geographic region; and output the candidate flight path from the flight path prediction system, wherein the candidate flight path is predicted to result in less ground level noise when followed by the aircraft, compared to alternative flight paths through the geographic region.

[0076] Example 14. The computing system according to Example 13, wherein generating the candidate flight path includes overlaying a virtual grid onto the geographic region, such that for grid cells of the virtual grid, the grid-related predicted noise level of the grid cell is interpolated from one or more predicted aircraft noise levels from one or more waypoints falling within the grid cell.

[0077] Example 15. The computing system according to Example 14, wherein the candidate flight path is generated as a plurality of cell-to-cell segments between grid cells of the virtual grid, wherein each cell-to-cell segment is selected at least in part based on the noise level of a grid-related prediction of the grid cells connected by the cell-to-cell segment.

[0078] Example 16. The computing system according to Example 13, wherein the candidate flight path is generated as a sequence of waypoints connecting a start waypoint to an end waypoint within the geographic region, the waypoint sequence being selected via a weighted graph-based algorithm implemented by the flight path prediction system.

[0079] Example 17. The computing system according to Example 16, wherein the weighted graph-based algorithm includes A Pathfinder Algorithm.

[0080] Example 18. The computing system according to Example 13, wherein the candidate flight path is predicted to result in a ground level noise amount less than a predefined noise target at a ground location in the geographic region.

[0081] Example 19. According to the computing system of Example 13, the candidate flight path is further generated at least in part based on a plurality of route constraints, and the plurality of route constraints include one or more of the following: the turning radius of the aircraft, the coordinates of the restricted airspace within the geographic region, the weather conditions in the geographic region, and departure and arrival procedures applied to the geographic region.

[0082] Example 20. A method for generating flight paths for an aircraft, the method comprising: at a computing system, receiving, for a plurality of waypoints in a geographic region, predicted aircraft noise levels at each of the plurality of waypoints, the aircraft noise levels being predicted at least in part based on a plurality of flight parameters of the aircraft, the predicted aircraft noise levels being predicted by a machine learning model trained at least in part based on historical measured noise levels and historical flight parameters of a plurality of previous aircraft flights; inputting the predicted aircraft noise levels into a flight path prediction system configured to generate candidate flight paths for the aircraft through the geographic region based at least in part on the predicted aircraft noise levels and a plurality of flight path constraints; and outputting the candidate flight paths from the flight path prediction system, wherein the candidate flight paths are predicted to result in ground level noise amounts less than a predefined noise target at ground locations in the geographic region.

[0083] It should be understood that the configurations and / or methods described herein are exemplary in nature, and these specific embodiments or examples should not be considered in a limiting sense, as many variations are possible. The specific routines or methods described herein may represent one or more of any number of processing strategies. Therefore, the various actions shown and / or described may be performed in the order shown and / or described, in other orders, in parallel, or omitted. Similarly, the order of the above processes may be changed.

[0084] The subject matter of this disclosure includes all novel and non-obvious combinations and sub-combinations of the various processes, systems and configurations disclosed herein, as well as any and all equivalents thereof.

Claims

1. A method for generating a flight path for an aircraft, the method comprising: At the computing system, for multiple waypoints in a geographic region, the predicted aircraft noise level at each of the multiple waypoints is received, the predicted aircraft noise level being predicted at least in part based on multiple flight parameters of the aircraft. The predicted aircraft noise level is input into a flight path prediction system, which is configured to generate candidate flight paths for the aircraft through the geographic region based at least in part on the predicted aircraft noise level; and The candidate flight path is output from the flight path prediction system, wherein the candidate flight path is predicted to cause less ground level noise when followed by the aircraft compared to an alternative flight path through the geographic area.

2. The method of claim 1, wherein generating the candidate flight path comprises overlaying a virtual grid onto the geographic region, such that for grid cells of the virtual grid, the grid-related predicted noise level of the grid cell is interpolated from one or more predicted aircraft noise levels from one or more waypoints falling within the grid cell.

3. The method of claim 2, wherein the candidate flight path is generated as a plurality of cell-to-cell segments between grid cells of the virtual grid, wherein each cell-to-cell segment is selected at least in part based on the noise level of a grid-related prediction of the grid cells connected by the cell-to-cell segments.

4. The method of claim 3, wherein the flight path prediction system implements a dynamic grid-based Viterbi algorithm to generate the candidate flight paths.

5. The method of claim 1, wherein the candidate flight path is generated as a sequence of waypoints connecting a start waypoint to an end waypoint within the geographic region, the waypoint sequence being selected via a weighted graph-based algorithm implemented by the flight path prediction system.

6. The method according to claim 5, wherein the weighted graph-based algorithm includes A Pathfinder Algorithm.

7. The method according to claim 6, wherein the weighted graph-based algorithm further includes D. The Lite algorithm is used to take into account dynamic updates of multiple route constraints.

8. The method of claim 1, wherein the candidate flight path is predicted to result in a ground level noise amount less than a predefined noise target at a ground location in the geographic region.

9. The method of claim 1, wherein the candidate flight path is further generated at least in part based on a plurality of route constraints, and wherein the plurality of route constraints include one or more of the following: the turning radius of the aircraft, the coordinates of the restricted airspace within the geographic region, the weather conditions within the geographic region, and departure and arrival procedures applied to the geographic region.

10. The method of claim 1, wherein the predicted aircraft noise level is predicted at least in part based on multiple historical noise levels measured by multiple previous aircraft flying through the geographic area.

11. The method of claim 10, wherein the predicted aircraft noise level is predicted by a machine learning model trained at least in part on the historical measured noise level and historical flight parameters of the plurality of previous aircraft flights.

12. The method of claim 11, wherein the historical flight parameters include one or more of the aircraft type, aircraft speed, altitude, time of day, and weather conditions of the plurality of previous aircraft flights.

13. A computing system, comprising: Logical subsystem; as well as A storage subsystem that saves instructions, said instructions being executable by the logic subsystem to: For multiple waypoints in a geographic region, the predicted aircraft noise level at each of the multiple waypoints is received, the predicted aircraft noise level being predicted at least in part based on multiple flight parameters of the aircraft. The predicted aircraft noise level is input into a flight path prediction system, which is configured to generate candidate flight paths for the aircraft through the geographic region based at least in part on the predicted aircraft noise level; and The candidate flight path is output from the flight path prediction system, wherein the candidate flight path is predicted to cause less ground level noise when followed by the aircraft compared to an alternative flight path through the geographic area.

14. The computing system of claim 13, wherein generating the candidate flight path comprises overlaying a virtual grid onto the geographic region, such that for grid cells of the virtual grid, the grid-related predicted noise level of the grid cell is interpolated from one or more predicted aircraft noise levels of one or more waypoints falling within the grid cell.

15. The computing system of claim 14, wherein the candidate flight path is generated as a plurality of cell-to-cell segments between grid cells of the virtual mesh, wherein each cell-to-cell segment is selected at least in part based on the noise level of a grid-related prediction of the grid cells connected by the cell-to-cell segment.

16. The computing system of claim 13, wherein the candidate flight path is generated as a sequence of waypoints connecting a start waypoint to an end waypoint within the geographic region, the waypoint sequence being selected via a weighted graph-based algorithm implemented by the flight path prediction system.

17. The computing system of claim 16, wherein the weighted graph-based algorithm includes A Pathfinder Algorithm.

18. The computing system of claim 13, wherein the candidate flight path is predicted to result in a ground level noise amount less than a predefined noise target at a ground location in the geographic region.

19. The computing system of claim 13, wherein the candidate flight path is further generated at least in part based on a plurality of route constraints, and wherein the plurality of route constraints include one or more of the following: the turning radius of the aircraft, the coordinates of the restricted airspace within the geographic region, the weather conditions within the geographic region, and departure and arrival procedures applied to the geographic region.

20. A method for generating a flight path for an aircraft, the method comprising: At the computing system, for multiple waypoints in a geographic region, the predicted aircraft noise level at each of the multiple waypoints is received, the aircraft noise level being predicted at least in part based on multiple flight parameters of the aircraft, the predicted aircraft noise level being predicted by a machine learning model trained at least in part based on historical measured noise levels and historical flight parameters of multiple previous aircraft flights. The predicted aircraft noise level is input into a flight path prediction system, which is configured to generate candidate flight paths for the aircraft through the geographic region based at least in part on the predicted aircraft noise level and multiple route constraints. as well as The candidate flight path is output from the flight path prediction system, wherein the candidate flight path is predicted to result in a ground level noise amount less than a predefined noise target at a ground location in the geographic region.

Images