Systems and methods for generating flight plans for use by a ride sharing network

Abstract

To provide a system and method for generating a flight plan used by a suitable ride-sharing network.SOLUTION: The present disclosure provides systems and methods for systems and methods for generating potential flight plans for use by a ride sharing network, including dynamic and / or automated changes to flight plans being arranged for passengers based on real-time information. In particular, the systems and methods of the present disclosure can operate to generate a fleet-level set of potential flight plans that complies with one or more constraints regarding a fleet of aircraft. The potential flight plan can be exposed into and used by the ride share network to provide transportation to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims priority to and the benefit of U.S. Provisional Patent Application No. 62 / 994,320, filed March 25, 2020, which is incorporated herein by reference in its entirety.

[0002] The present disclosure relates generally to facilitating ride-sharing of aircraft flights. More specifically, the present disclosure relates to systems and methods for planning flights for use by ride-sharing networks, including dynamic changes to flight plans based on real-time information. [Background technology]

[0003] Transportation services exist that allow individual users to request transportation on demand. For example, transportation services currently exist to allow operators of land-based vehicles (e.g., "cars") to provide transportation services for potential passengers and deliver luggage, goods, and / or prepared food.

[0004] However, as metropolitan areas become increasingly dense, land-based infrastructure such as roads become increasingly constrained and congested, and as a result, land-based transportation may not adequately serve the transportation needs of a significant number of users. Summary of the Invention [Means for solving the problem]

[0005] Aspects and advantages of embodiments of the present disclosure will be set forth in part in the description that follows, or may be learned from the description, or may be learned through practice of the embodiments.

[0006] One exemplary aspect of the present disclosure is directed to a computing system configured to generate flight plans for a rideshare network. The computing system includes one or more processors and one or more non-transitory computer-readable media storing instructions that, collectively, when executed by the one or more processors, cause the computing system to perform operations. The operations include receiving input data describing a fleet of aircraft, one or more constraints, and a flight plan duration. The operations include generating a set of potential flight plans for the fleet of aircraft and the flight plan duration based, at least in part, on the input data. The operations include exposing the set of potential flight plans to the rideshare network. The operations include receiving, from the rideshare network, one or more additions of one or more passengers to one or more of the potential flight plans and generating one or more dispatched flight plans.

[0007] Other aspects of the present disclosure are directed to various systems, apparatus, non-transitory computer-readable media, user interfaces, and electronic devices.

[0008] These and other features, aspects, and advantages of various embodiments of the present disclosure will become better understood with reference to the following description and appended claims. The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain relevant principles. The present invention provides, for example, the following. (Item 1) 1. A computing system configured to generate a flight plan for a rideshare network, the computing system comprising: one or more processors; One or more non-transitory computer-readable media collectively storing instructions that, when executed by the one or more processors, cause the computing system to perform operations, including: receiving input data describing a fleet of aircraft, one or more constraints, and a flight plan duration; generating a set of potential flight plans for the fleet of aircraft and the flight plan horizon based at least in part on the input data; exposing the set of potential flight plans to the rideshare network; receiving from the rideshare network one or more additions of one or more passengers to one or more of the set of potential flight plans to generate one or more arranged flight plans; one or more non-transitory computer-readable media, A computing system comprising: (Item 2) Item 1. The computing system of item 1, wherein the input data includes expected demand data describing expected demand for individual flights at different individual times and locations, the expected demand data being based, at least in part, on the rideshare network. (Item 3) 10. The computing system of claim 1, wherein the input data includes expected supply data describing expected supply of land-based transportation providers at different individual times and transportation locations, the expected supply data being based, at least in part, on the rideshare network. (Item 4) The operation further comprises: monitoring compliance of said fleet of aircraft with said arranged flight plans; Detecting one or more deviations from the dispatched flight plan of the fleet of aircraft or the one or more passengers; adjusting one or both of said arranged flight plans or said set of potential flight plans to take into account said one or more deviations; 2. The computing system of any preceding claim, comprising: (Item 5) Monitoring compliance of the fleet of aircraft with the arranged flight plans includes: location data associated with one or more aircraft in said fleet of aircraft; or location data associated with one or more of said one or more passengers; Item 5. The computing system of item 4, comprising tracking one or both of: (Item 6) Tracking the location data associated with one or more of the one or more passengers includes: receiving passenger location data associated with an individual passenger from a land vehicle device assigned to the individual passenger for providing ground transportation to the individual passenger prior to an individual arranged flight plan for the passenger; Item 6. The computing system of item 5, comprising: (Item 7) 7. The computing system of claim 4, wherein each arranged flight plan is associated with one or more assigned passengers of the one or more passengers, a scheduled takeoff time, a scheduled landing time, and a buffer period, the buffer period indicating a delay from the scheduled takeoff time. (Item 8) generating a dispatched flight plan for the one or more dispatched flight plans includes: determining the buffer period for the dispatched flight plan based, at least in part, on the one or more assigned passengers of the dispatched flight plan; 8. The computing system of claim 7, comprising: (Item 9) 9. The computing system of claim 8, wherein each of the one or more assigned passengers is associated with a multi-leg journey, one leg of the multi-leg journey being the arranged flight plan, and the buffer period is determined for each of the one or more assigned passengers based at least in part on the multi-leg journey. (Item 10) 10. The computing system of claim 9, wherein the multi-leg journey is associated with a total estimated travel time for assigned passengers, and the buffer period is determined based, at least in part, on an aggregated duration for the multi-leg journey for each of the one or more assigned passengers as a result of delaying the dispatched flight plan by one or more different durations. (Item 11) 11. The computing system of claim 9, wherein the buffer period is determined, at least in part, based on a number of the one or more assigned passengers who would have changes to their multi-leg travel leg as a result of delaying the arranged flight plan by one or more different periods. (Item 12) adjusting one or both of the one or more dispatched flight plans or the set of potential flight plans to account for the one or more deviations; determining that the deviation is due to a late assigned passenger on the arranged flight plan; determining an estimated arrival time for the late assigned passenger; determining an adjustment to the dispatched flight plan based, at least in part, on the estimated arrival time for the late assigned passenger; applying said adjustment to said dispatched flight plan; 12. The computing system of claim 7-11, comprising: (Item 13) Determining the adjustment to the dispatched flight plan comprises: adding the late assigned passenger to one or more of the set of potential flight plans in response to determining that the estimated arrival time for the late assigned passenger is after the scheduled takeoff time by more than the buffer period; in response to determining that the estimated arrival time for the late passenger is after the scheduled takeoff time and within the buffer period, delaying the scheduled takeoff time for the dispatched flight plan to accommodate the late assigned passenger; automatically transmitting a notification to one or more of said late assigned passengers, flight personnel, or aircraft operators; Item 13. The computing system of item 12, comprising: (Item 14) 1. A computer-implemented method for generating a flight plan for a rideshare network, the method comprising: receiving, by a computing system comprising one or more computing devices, input data describing a fleet of aircraft, one or more constraints, and a flight plan horizon; generating, by the computing system, a set of potential flight plans for the fleet of aircraft and the flight planning horizon based at least in part on the input data; exposing, by the computing system, the set of potential flight plans to the rideshare network; receiving, by the computing system, one or more additions of one or more passengers from the rideshare network to one or more of the set of potential flight plans and generating one or more arranged flight plans; A method comprising: (Item 15) Item 15. The computer-implemented method of item 14, wherein generating the set of potential flight plans for the fleet of aircraft includes generating the set of potential flight plans for the fleet of aircraft that optimizes an objective function. (Item 16) The objective function is: the number of sets of potential flight plans; the proportion of said set of potential flight plans expected to be arranged by passengers; the number of sets of potential flight plans expected to operate at maximum passenger capacity; the number of passengers expected to be served by said set of potential flight plans; the number or percentage of passengers on said set of potential flight plans that are expected to arrive at their respective destinations in advance of their desired arrival times; or an estimated period of time that passengers on the set of potential flight plans are expected to be late beyond the desired arrival time; Item 16. The computer-implemented method of item 15, wherein the set of potential flight plans is evaluated according to one or more metrics including: (Item 17) The method further comprises: learning updated values ​​for the set of weights of the objective function based at least in part on observed outcome data. Item 17. The computer-implemented method of items 15-16. (Item 18) Generating the set of potential flight plans for the fleet of aircraft includes: sorting a plurality of periods contained within the flight plan period into two or more priority hierarchies; iteratively generating the set of potential flight plans for the time period within each priority stratum, starting with the highest priority stratum; Including, The potential flight plans generated for the higher priority hierarchies are used to generate constraints to be satisfied by the potential flight plans generated for the lower priority hierarchies. Item 14-17. The computer-implemented method of any one of items 14-17. (Item 19) detecting, by the computing system, one or more deviations of the fleet of aircraft or the one or more passengers from the dispatched flight plan; determining, by the computing system, an adjustment to at least one of the dispatched flight plan or the set of potential flight plans to accommodate the one or more deviations; comparing, by the computing system, the adjustment to pre-approval criteria for the operator of at least one of the set of dispatched flight plans or the set of potential flight plans; adjusting, by the computing system, at least one of the dispatched flight plan or the set of potential flight plans in response to determining that the adjustment achieves the pre-approval criteria; transmitting, by the computing system, data indicative of the adjustment to human mitigation personnel in response to a determination that the adjustment does not achieve the pre-approval criteria; and 19. The computer-implemented method of items 14-18, further comprising: (Item 20) One or more non-transitory computer-readable media comprising instructions that, when executed by one or more computing devices, cause the one or more computing devices to: receiving input data describing a fleet of aircraft, one or more constraints, and a flight plan duration; generating a set of potential flight plans for the fleet of aircraft and the flight plan horizon based at least in part on the input data; exposing the set of potential flight plans to a rideshare network; receiving from the rideshare network one or more additions of one or more passengers to one or more of the set of potential flight plans to generate one or more arranged flight plans; One or more non-transitory computer-readable media for performing operations including: [Brief explanation of the drawings]

[0009] A detailed discussion of the embodiments, directed to those skilled in the art, is set forth in the specification, which refers to the accompanying figures.

[0010] [Figure 1] FIG. 1 depicts a block diagram of an exemplary computing system according to an exemplary embodiment of the present disclosure.

[0011] [Figure 2] FIG. 2 depicts a pictorial representation of an exemplary set of flight paths between an exemplary set of transportation nodes, according to an exemplary embodiment of the present disclosure.

[0012] [Figure 3] FIG. 3 depicts a pictorial diagram of an exemplary transportation node, according to an exemplary embodiment of the present disclosure.

[0013] [Figure 4] FIG. 4 depicts a flowchart diagram of an example method for generating and using a set of flight plans in a rideshare network, according to an exemplary embodiment of the present disclosure.

[0014] [Figure 5] FIG. 5 depicts a flowchart diagram of an example method for generating a set of potential flight plans on a per-aircraft basis, according to an example embodiment of the present disclosure.

[0015] [Figure 6]FIG. 6 depicts a flowchart diagram of an example method for generating a set of potential flight plans based on a priority hierarchy, according to an example embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0016] Detailed Description Exemplary aspects of the present disclosure are directed to systems and methods for generating potential flight plans for use by a rideshare network, including, in some implementations, dynamic and / or automated changes to the flight plans based on real-time information. In particular, the systems and methods of the present disclosure can operate to generate a fleet-level set of potential flight plans that conform to one or more constraints on the aircraft fleet. The potential flight plans can be introduced into and used by the rideshare network to provide transportation services to users. For example, the rideshare network can add passengers to the potential flight plans and dispatch the flight plans (e.g., operate the flight plans). Flights associated with the dispatched flight plans may be offered as standalone transportation services or may be part of a larger, multi-leg transportation service itinerary that utilizes multiple transportation modes, such as a mix of car and aircraft transportation. Additionally, the systems and methods of the present disclosure provide manual and / or automated tools for flight plan adjustments, for example, to handle and mitigate delays or other real-time effects that cause the aircraft fleet to deviate from the set of flight plans.

[0017] More specifically, a flight planning system implemented by one or more computing devices can receive a set of input data describing a fleet of aircraft, one or more flight plan constraints, and a flight plan duration. The input data can be provided by a user and / or can be automatically captured (e.g., periodically, such as daily). For example, in some implementations, heterogeneous aircraft owners / operators can interact with the computing system (e.g., applications implemented thereby) and provide information regarding the availability of their aircraft for participation in a rideshare network. The provided information can then be accessed by the flight planning system. In other implementations, information about the fleet of available aircraft originates from a single, centralized source that oversees all aircraft operations.

[0018] A fleet of aircraft can include any number of aircraft of the same or different models owned and / or operated by one or more different air operators. Exemplary aircraft that may be included in a fleet include helicopters or other vertical takeoff and landing aircraft (VTOL), such as electric vertical takeoff and landing aircraft (eVTOL). In some implementations, a fleet of aircraft can include aircraft corresponding to varying levels of autonomous flight / movement, including non-autonomous aircraft, semi-autonomous aircraft, and fully autonomous aircraft. Each aircraft can be owned, maintained, and / or operated by one or more different air vehicle operators. By way of example, an air vehicle operator can include any entity with operational control (e.g., ownership, licensing, etc.) of one or more air vehicles. Each air vehicle operator can make one or more air vehicles available during a flight planning period.

[0019] A flight planning period may define the overall start and end dates and times for which the flight planning system should generate potential flight plans for a fleet of aircraft. Exemplary flight planning periods include periods of 3 hours, 24 hours, 1 week, etc. A flight planning period may be continuous or may include discrete periods.

[0020] The constraints described by the set of input data may include, by way of example, any number of different constraints associated with each aircraft, such as individual origin locations for each aircraft, individual destination locations for each aircraft, individual times when each aircraft is available or unavailable, individual starting fuel or charge levels for each aircraft, individual capabilities or attributes of each aircraft, such as the number of available passenger seats, maximum continuous operating time, maximum or minimum flight range, maximum or minimum flight altitude, noise level, etc., associated with an aircraft operation.

[0021] The constraints described by the set of input data may also describe a fixed infrastructure that a fleet of aircraft must utilize. More specifically, in some implementations, aircraft may operate according to or within a fixed infrastructure in which the ability of passengers to board and deplane from the aircraft is constrained to a defined set of transportation nodes. As an example, aircraft may be constrained to board and deplane passengers only at a defined set of physical takeoff and / or landing areas, which in some cases may be referred to as airports. To provide an example, a metropolitan area may have dozens of transportation nodes located at various locations within the metropolitan area. Each transportation node may include one or more takeoff and / or arrival points and / or other infrastructure to enable passengers to safely board or deplane from aircraft. A transportation node may also include charging equipment, refueling equipment, and / or other infrastructure to enable aircraft operation. The takeoff and / or arrival points of a transportation node may be located at ground level and / or elevated above ground level (e.g., on a building). Thus, input data to the flight planning system may also provide various constraints associated with each individual transportation node, such as, by way of example, location, types of aircraft that are allowed to take off / land at the transportation node, number of takeoff and / or arrival points at the transportation node, number of refueling or charging structures at the transportation node, minimum turnaround preparation time for an aircraft to land and then take off from the transportation node, frequency (e.g., throughput) at which aircraft may arrive at and depart from the transportation node, airspace access requirements, and / or other descriptors of different transportation nodes.

[0022] In some implementations, the constraints described by the set of input data may also describe the availability of other resources, such as a particular aircraft operator ("pilot"), operational personnel, and physical resources available at a transportation node (e.g., machinery, fuel, maintenance capacity for safe passenger embarkation). In some implementations, a particular pilot may be linked to a particular aircraft and treated as a single resource, while in other implementations, they may be treated as separate resources.

[0023] In some implementations, input data to a flight planning system can include other additional data, such as forecasted demand, supply, or weather data. For example, forecasted demand data can be provided as input to the flight planning system. The forecasted demand data can describe the forecasted demand for air transportation at various times and locations over the flight planning period. The data can describe the expected origin and destination of the demand, or can simply forecast the origin of the demand.

[0024] The expected demand data can be based, at least in part, on a rideshare network. The rideshare network can include, for example, a multi-modal rideshare network configured to provide transportation services for multiple different users of the network (e.g., to be carried out by aircraft, land vehicles, etc.). For example, the rideshare network can receive a request for transportation between two locations (e.g., an origin location and a desired location), determine one or more optimal modes (e.g., aircraft, land vehicles, etc.) for facilitating the transportation, assign service providers associated with the one or more optimal modes, and provide the transportation. The rideshare network can determine the expected demand data by utilizing a number of real-time requests and / or historical data indicating the number of requests received from multiple different users of the network. In this manner, the expected demand data can be determined, at least in part, based on the rideshare network. As an example, the expected demand data can include historical and / or real-time requests from passengers of the rideshare network and / or data determined, at least in part, based on historical and / or real-time requests from passengers of the rideshare network and provided to a flight planning system. In this manner, the set of potential flights generated by the flight planning system may shift throughout the operational period based, at least in part, on information from the rideshare network.

[0025] As another example, expected supply data can be provided as input to a flight planning system. The expected supply data can describe the expected supply of ground-based transportation providers at different individual times and transportation locations over a flight planning period. The expected supply data can be based, at least in part, on a rideshare network. For example, a rideshare network can include multiple service providers (e.g., drivers, aircraft operators, etc.) and / or be associated with multiple rideshare assets (e.g., vehicles, etc.). The expected supply data can identify the number of service providers and / or assets available (e.g., opted in, etc.) to provide transportation services at multiple different times and / or locations over the flight planning period. In this manner, the expected supply data can be determined, at least in part, based on the rideshare network. As an example, the expected supply data can include historical and / or real-time information identifying the availability of service providers and / or number of assets in the rideshare network and / or data determined, at least in part, based on the historical and / or real-time availability of service providers and / or number of assets in the rideshare network and provided to the flight planning system. In some implementations, the set of potential flights generated by the flight planning system can be provided as expected supply data for the rideshare network. In such cases, the rideshare network may facilitate the availability of a number of service providers and / or assets in the rideshare network based, at least in part, on the set of potential flights (e.g., by encouraging commitments from drivers, operators, and / or asset owners).

[0026] As yet another example, the additional data may include forecasted weather data, available flight routes between infrastructure nodes, airspace availability throughout the planning horizon, and / or other aeronautical information that may be provided as input data to a flight planning system.

[0027] According to one aspect of the present disclosure, in response to input data, the flight planning system can generate a set of potential flight plans for a fleet of aircraft over a flight planning period, where each potential flight plan can include various types of information, such as, by way of example, an aircraft identification, a pilot identification (if required), an origin location, a destination location, a rough indication of the flight path, an estimated departure time, an estimated arrival time, and / or various other information regarding the potential operation of the aircraft.

[0028] More specifically, the flight planning system can generate a set of potential flight plans that maximizes the satisfaction of a combination of one or more objectives while also adhering to all of the constraints (e.g., not violating any of the constraints). By way of example, objectives considered by the flight planning system can include maximizing the number of potential flights generated, maximizing the proportion of potential flight plans that are dispatched, operating at maximum passenger capacity, maximizing the number of dispatched flights, flights operating on time, maximizing the number of passengers, arriving at their destinations on time, maximizing the number of passengers, minimizing the cumulative period passengers are delayed beyond their desired arrival time, and / or various other objectives. In some implementations, the flight planning system can use a fleet-level objective function (e.g., using a set of weights) that balances some or all of the different objectives described above. The set of weights can be manually adjusted and / or automatically adjusted (e.g., learned).

[0029] The flight planning system can implement one or more of a variety of different algorithms to generate a set of potential flight plans. For example, in some implementations, the flight planning system can iteratively analyze a fleet of aircraft on an aircraft-by-aircraft basis, thus generating an optimal set of potential flight plans for each aircraft. For example, an optimal set of potential flight plans for an aircraft can be generated by optimizing an aircraft-level objective function (e.g., using a set of weights) that balances any combination of the objectives described above for that aircraft. The set of weights in the aircraft-level objective function can be manually adjusted and / or automatically adjusted (e.g., learned). In some implementations, the aircraft-level objective function and the fleet-level objective function can be the same function and have the same weights. In some implementations, the fleet-level objective function can be equal to the sum of the aircraft-level objective functions as each applied to all aircraft in the fleet.

[0030] In particular, in one example, the flight planning system can generate a set of flight plans for a particular aircraft by starting at the beginning of the flight planning horizon and sequentially generating / adding flight plans for the aircraft until the end of the flight planning horizon is reached. As one example, in each instance in which the flight planning system attempts to generate a new flight plan for an aircraft, the flight planning system can generate multiple candidate flight plans, score each candidate flight plan according to an aircraft-level objective function, and then select and add the highest-scoring flight plan for that aircraft.

[0031] As described above, the aircraft-level objective function may, by way of example, balance any number of different objectives, including various objectives that are functions of demand for the generated flight plans (e.g., total number of passengers served, total number of flights arranged, total number of flights with all available seats filled, etc.). To evaluate such objective functions, including objectives that are functions of demand, the flight planning system may query a demand model to obtain forecasted demand and / or supply information that can be used to evaluate such objectives. In another example, the aircraft-level objective function may focus on maximizing the total number of generated flight plans (e.g., including as the sole objective).

[0032] In some implementations, the objective function can evaluate a set of flight plans based, at least in part, on the final journey for a plurality of potential passengers. For example, the objective can include a function to reduce the total travel time for a plurality of passengers. As an example, the demand data (e.g., received and / or based on a ride-sharing service) can include expected demand for a transportation service. Sometimes, the transportation service can include a multi-modal transportation service. In such cases, an air flight segment, such as one of the set of potential flight plans, can include one of a plurality of destinations for a passenger before the passenger reaches the final destination. The objective function can evaluate a set of flight plans based, at least in part, on the total estimated travel time for a plurality of passengers. For example, the flight planning system can identify infrastructure, traffic, weather, and / or other factors that may affect subsequent ground transportation segments and optimize the set of potential flight plans to reduce the total estimated travel time for users of the ride-sharing network.

[0033] As an example, a flight planning system can consider ground-based transportation information when generating a set of flight plans. For example, the expected supply availability of the last leg can be used as an input to an aircraft-level objective function to reward (e.g., increase the objective score associated with) flights that deliver passengers to their destinations and have a robust supply of ground-based transportation services, and penalize (e.g., decrease the objective score associated with) flights that deliver passengers to their destinations and do not have a robust supply of ground-based transportation services. Similarly, the expected supply availability of the first leg can be used as an input to an aircraft-level objective function to reward (e.g., increase the objective score associated with) flights that collect passengers from departure nodes and have a robust supply of ground-based transportation services, and penalize (e.g., decrease the objective score associated with) flights that collect passengers from departure nodes and do not have a robust supply of ground-based transportation services. In other implementations, such information regarding the supply of transportation services according to other means can also be assumed to be included in the expected demand data.

[0034] The flight planning system (e.g., an objective function, etc.) can evaluate a set of potential flight plans based, at least in part, on the proximity with which the set of potential flight plans can transport potential passengers (e.g., anticipated based on anticipated demand data, etc.) to their anticipated final destinations. For example, the anticipated demand data can include anticipated final destinations for each of a plurality of anticipated passengers. The flight planning system can generate a set of potential flight plans to facilitate transportation of the plurality of anticipated passengers to locations (e.g., transportation nodes) closest to their anticipated final destinations.

[0035] In some implementations, the location (e.g., transportation node) closest to the expected final destination may not be the most efficient and / or timely route for transporting the multiple expected passengers. For example, subsequent ground transportation from the closest location may be affected by traffic and / or other roadway delays. Additionally, in some implementations, the flight plan to the closest location may be affected by weather or other airspace delays. In such cases, the flight planning system (e.g., objective function, etc.) can generate / evaluate a set of flight plans to facilitate transportation of the multiple expected passengers to the location (e.g., transportation node) closest in time to the expected final destination such that factors affecting subsequent transportation to the final destination are taken into account.

[0036] In some implementations, the flight planning system can implement a tiered approach to generate flight plans. In particular, the flight planning period can be divided into several different periods, and each period can be assigned to one of multiple priority tiers. There can be any number of priority tiers, including, for example, two tiers. More specifically, the tiered approach recognizes that certain periods throughout the day or week may be of higher priority due to increased levels of demand by passengers. As one example, periods corresponding to "busy hours" or typical commute times may be considered higher priority than other periods. As another example, periods including the occurrence of popular events (e.g., sporting events, music festivals, and / or the like) may be recognized as higher priority periods. In yet another example, periods can be sorted into different priority tiers based on expected demand data.

[0037] In a multi-tiered approach, the flight planning system can iteratively generate flight plans for time periods within each priority tier, starting with the highest priority tier. Thus, after determining the flight plan for the time period in the highest priority tier, the flight planning system can then determine the flight plan for the time period in the next highest priority tier. In particular, each tier of time periods can use the generated flight plan for the previous tier as a constraint for the scheduling process. For example, if the generated flight plan for the 4:00 PM to 7:00 PM period requires a given aircraft to depart from a particular transportation node with a particular fuel / charge level, when generating a flight plan for the 1:00 PM to 4:00 PM period, the flight planning system can handle as a constraint the fact that the aircraft needs to arrive at the particular transportation node with a particular fuel / charge level during the 1:00 PM to 4:00 PM period. In such a manner, the flight plan can be specifically optimized for the highest priority period, for example, when the largest number of passengers need to be served.

[0038] Additionally, in some implementations, the flight planning algorithm can include a greedy refueling component. The greedy refueling component can greedily assign aircraft to participate in refueling and / or recharging whenever the aircraft is not in flight (e.g., above a minimum amount of time) and refueling / recharging infrastructure is available at the aircraft's current location. The greedy refueling component can be applied after flight plan generation or can be used as part of the generation process itself. In such a manner, refueling / recharging infrastructure usage can be optimized.

[0039] In some implementations, the flight planning system can perform or participate in an iterative learning process for the weighting of the planning objective function. For example, an initial set of weights for the objective function can be manually adjusted. The flight planning system can operate with the initial set of weights to generate any number of flight plans over any number of flight planning periods. Performance associated with the generated flight plans can be observed and measured according to various metrics. The set of weights can be readjusted (e.g., automatically and / or manually) based on the observed performance. For example, various learning techniques, such as gradient descent, can be applied to learn the set of weights. For example, gradient descent can be applied to the weights of the fleet-level objective function or the aircraft-level objective function. More generally, the flight planning system can collect any data describing the performance of certain manually controlled settings, actions, weights, decisions, and / or the like and can apply machine learning techniques to such data to learn updated or optimized versions of such settings, actions, weights, decisions, and / or the like.

[0040] In this manner, the flight planning system can automatically generate a set of potential flight plans for a fleet of aircraft owned and / or operated by one or more different air operators. In some implementations, each flight plan can be approved by an individual air vehicle operator. For example, each air vehicle operator can be associated with a pre-approval rule set. The pre-approval rule set can, for example, outline one or more acceptable flight plans for air vehicles under the operational control of the individual air vehicle operator (e.g., from / to / between one or more approved locations, within an approved time period, etc.). In some implementations, the set of potential flight plans can include only approved flight plans. Additionally or alternatively, the set of potential flight plans can include unapproved flight plans. In such cases, the unapproved flight plans can be provided to the individual air vehicle operator for manual approval (e.g., escalation approval). The flight planning system can modify and / or regenerate any flight plans that are not manually and / or pre-approved by the individual air vehicle operator.

[0041] After the flight planning system generates a set of potential flight plans for a fleet and a flight planning period, the set of potential flight plans can be exposed to the rideshare network. In particular, a matching system of the rideshare network matches one or more passengers in the network with a particular flight plan according to a matching process, thereby dispatching the flight plan for operation. In some implementations, the matching system can implement a passenger pool in which multiple requests for service are collected from users over a period of time, and the matching service collectively analyzes the requests and identifies opportunities to pool passengers together. While aspects of the present disclosure focus on providing air transportation services to human passengers, the systems and methods of the present disclosure are equally applicable to determining flight plans for air transportation services for non-human payloads, such as luggage, prepared food, pet transportation, and / or the like.

[0042] In some implementations, a set of potential flight plans can be exposed to a rideshare network with minimal detail. For example, a potential flight plan can be described by data indicating the number of passengers and / or routes that can be served between, between, and / or to segment times at multiple locations. Passengers on the rideshare network can reserve a route by booking air transportation for a segment time. The reserved segment time can be used by the rideshare network to match passengers to flights from the potential set of flights.

[0043] As an example, passengers in a rideshare network can reserve a route (e.g., generally, flight details, etc.) for a certain segment time. The segment time can describe a time slot container and can be used as input to generate a dispatched flight plan. The rideshare network can receive multiple requests, group the multiple requests into one or more time slot containers, and organize flights around the time slot containers. Passengers are given a price estimate but may not be billed until after the flight has occurred. Prior to the flight's occurrence, passengers can be provided with information such as the aircraft type assigned to perform the flight, the time slot associated with the flight, and / or any other information associated with the dispatched flight.

[0044] In this manner, a dispatched flight plan can be generated by adding passengers to a potential flight plan of a set of potential flight plans. Thus, a dispatched flight plan can include a potential flight plan with one or more assigned passengers. For example, each dispatched flight plan can be associated with one or more assigned passengers associated with the rideshare network. Additionally, a dispatched flight plan can include a scheduled takeoff time, a scheduled landing time, and a buffer period. The buffer period can indicate a delay from the scheduled takeoff time. This can be, for example, a period of time that is perceived as acceptable by the passenger. The acceptability can be based on feedback data provided by the passenger through a software application running on the user device. For example, the software application can provide prompts and collect feedback from the passenger regarding their experience, including, for example, the passenger's level of satisfaction or dissatisfaction with the delay. The feedback data from a specific passenger may be stored for a determination of acceptability for the particular passenger (e.g., if they are included on a later flight) and / or aggregated with feedback data from one or more other passengers to determine whether the period would represent an acceptable delay for other passengers. In some implementations, the aggregated data may be utilized to determine whether the delay is acceptable for passengers who previously provided feedback data. The buffer period may be determined, at least in part, based on the input data, one or more constraints (e.g., weather, traffic, deviations, etc.), and / or the period. For example, a dispatched flight plan may form a user-centric flight schedule with an adjustable takeoff time based, at least in part, on the assigned passengers associated with the dispatched flight plan. The adjustable user-centric takeoff time may be represented by a buffer period.

[0045] More specifically, the dispatched flight plan may include a buffer period determined based on a comprehensive input centered on passenger convenience. As an example, the flight planning system may generate the dispatched flight plan based, at least in part, on one or more assigned passengers (e.g., added by a rideshare network). The flight planning system may determine a buffer period for the dispatched flight plan based, at least in part, on the one or more assigned passengers of the dispatched flight plan.

[0046] For example, one or more assigned passengers can each be associated with a multi-leg journey. A multi-leg journey can include multiple legs, e.g., via one or more different modes. For example, one leg of a multi-leg journey can include a dispatched flight plan. An additional leg can include ground transportation to an origin location of the dispatched flight plan, another ground transportation from a destination location of the dispatched flight plan, and / or one or more additional flight legs preceding and / or following the dispatched flight plan.

[0047] In some implementations, the flight planning system may determine a buffer period for each one or more assigned passengers based at least in part on the multi-leg journey. For example, the multi-leg journey may be associated with a total estimated travel time for the assigned passengers. In such a case, the buffer period may be determined at least in part based on an aggregated delay period for each multi-leg journey of the one or more assigned passengers as a result of delaying the dispatched flight plan by one or more different periods. The buffer period may be determined, for example, to ensure that the aggregated delay period is less than a threshold time (one hour or more, 30 minutes, 10 minutes, etc.). In some cases, the threshold time may include a period less than the duration of the dispatched flight. As one example, the flight planning system may predict higher traffic volume for ground transportation in a first period after the dispatched flight. In such a case, the flight planning system may determine a buffer period that is less than the first period to prevent affected passengers from being further delayed by the predictable traffic volume.

[0048] Additionally or alternatively, the buffer period may be determined based, at least in part, on the number of one or more assigned passengers who would have changes to their multi-leg journey as a result of delaying the dispatched flight plan by one or more different periods. For example, the buffer period may be determined to prevent one or more assigned passengers from missing a subsequent flight.

[0049] A computing system, including a flight planning system, can continuously monitor the success / feasibility of each arranged flight plan. For example, the computing system can monitor real-time data, such as aircraft location data (e.g., received from an aircraft's GPS system), aircraft sensor data (e.g., fuel / charge levels, etc.), passenger location data (e.g., received from passenger computing devices with authorization), weather data, ground-based transportation data, and / or other forms of data, to detect current or likely deviations from the arranged flight plans of the aircraft fleet and / or passengers. In particular, the computing system can monitor and evaluate estimated arrival times versus planned arrival times for some or all passengers, estimated arrival times versus planned arrival times for some or all aircraft, and / or other measures of flight plan success.

[0050] Thus, the computing system may continually assess whether a flight will successfully depart and / or arrive at its scheduled time, including tracking whether an assigned passenger will be able to physically travel through the transportation node and successfully arrive at the departure transportation node in sufficient time to board the aircraft. In particular, in some implementations, the estimated arrival time may be for the passenger and may be based on a first leg of a multi-leg journey. For example, a user may arrive at a transportation node using ground-based transportation (e.g., a ride-share vehicle), and thus the computing system may track the user's progress along the ground-based transportation leg and assess whether the user will arrive in sufficient time to avoid delaying their associated flight (e.g., which may be the second leg of a multi-leg journey).

[0051] The computing system can track user location, for example, by receiving location data associated with one or more of the one or more passengers. For example, the computing system can interact with a rideshare network and receive updates to the passenger's location. As an example, the computing system can receive passenger location data associated with an individual passenger from a ground vehicle device assigned to the individual passenger for providing ground transportation to the individual passenger ahead of an individual arranged flight plan for the passenger. The location data can be received in real time, periodically, or during the course of the passenger's journey from an origin location to the first transportation node. Additionally, or alternatively, the location data can be received in response to a detected deviation from an original estimated arrival time. For example, the location data for a passenger may indicate a later or earlier estimated arrival time for the passenger. In some implementations, the location data can include traffic information, driver information, flight information, and / or any other information associated with the transportation of the passenger to the first transportation node of the arranged flight.

[0052] The computing system can implement real-time mitigation measures and re-planning when a particular flight plan is significantly delayed or canceled / failed. Typically, the computing system can attempt to delay re-planning activities until it believes, with a significant probability, that it will be impossible to successfully complete the arranged flight plan.

[0053] Additionally or alternatively, the computing system may implement real-time mitigation measures and re-planning based, at least in part, on one or more deviations for one or more passengers. For example, the computing system may reoptimize a set of potential flight plans and / or one or more dispatched flight plans based, at least in part, on minimizing inconvenience to passengers. As an example, the computing system may determine a mitigation measure (e.g., delaying a flight, reassigning one or more passengers to a different dispatched flight, etc.) in response to one or more deviations for the aircraft fleet and / or passengers. For each available mitigation measure, the computing system may determine a portion of passengers that will be affected as a result of the mitigation measure. As an example, the computing system may determine a portion of passengers that will not arrive on time as a result of the mitigation measure, a total duration (e.g., one or more hours, minutes, etc.) that will be added to transportation service for all passengers as a result of the mitigation measure, and / or other metrics. In this manner, the computing system can adjust one or both of the dispatched flight plan and / or the set of potential flight plans to account for one or more deviations without adversely affecting the convenience of dispatched passengers in the on-demand transportation service.

[0054] In some implementations, the mitigation process can include delaying the flight based on a buffer period in the dispatched flight plan. For example, the buffer period can indicate a period of time before and / or after scheduled takeoff that is acceptable for the aircraft. For example, consideration can be given to accommodating late and / or early passengers based, at least in part, on the user's (e.g., location) and the perception of other pooled users associated with the dispatched flight. For example, the buffer period can be determined based on a collective inconvenience factor and / or trickle-down impact of the delayed takeoff time. The computing system can determine that the deviation is due to a late assigned passenger for the dispatched flight plan. The computing system can determine an estimated arrival time for the late assigned passenger and determine an adjustment for the dispatched flight plan based, at least in part, on the estimated arrival time and the buffer period for the late assigned passenger. The computing system can apply the adjustment to the dispatched flight plan.

[0055] As an example, in response to determining that the estimated arrival time for the late assigned passenger is after the scheduled takeoff time by a period that exceeds the buffer period, the computing system can add the late assigned passenger to one or more of the set of potential flight plans (and / or dispatched flight plans with space for the late assigned passenger). Additionally, or alternatively, in response to determining that the estimated arrival time for the late passenger is after the scheduled takeoff time that is within the buffer period, the computing system can delay the scheduled takeoff time for the dispatched flight plan to accommodate the late assigned passenger. In some implementations, the computing system can automatically transmit a notification to one or more of the late assigned passenger (e.g., via a user device), operations personnel (e.g., via an operations device), and / or the aircraft operator (e.g., via an aircraft device).

[0056] In some implementations, the mitigation process can include manual input by human mitigation personnel. For example, the need to implement mitigation can be automatically detected, and as a result, the computing system can provide an alert and a mitigation user interface to the human mitigation personnel. For example, the mitigation user interface can include a graphical user interface that shows potential alternative flight plans and / or modifications thereto for a flight plan currently experiencing a delay / cancellation. As one example, the human personnel can interact with the interface and adjust various parameters of one or more flight plans. For example, the human personnel can modify flight departure times, modify buffer times associated with passenger physical passage through transportation nodes and / or vehicle boarding / deboarding, add or remove passengers from flights, move passengers between flights, change pilots, and / or take other actions to manually modify the set of flight plans. In some implementations, any downstream impacts on the flight plans from manual modifications can be automatically calculated and propagated through the set of flight plans.

[0057] In some implementations, the user interface may provide warnings or other indications of the extent to which a mitigation activity or potential action may affect other users of the system and / or violate certain initial input constraints. For example, if mitigation personnel attempt to delay a flight plan that has not yet departed to wait for the delayed user, the user interface may inform the mitigation personnel that such an action will affect one or more other travelers (e.g., three other travelers). The warnings / indications provided within the user interface may provide impact information according to various metrics, including, for each available option / action, the number of users that will be affected as a result of the option / action, the number of users that will miss their arrival time as a result of the option / action, the total duration that will be added to transportation service for all users as a result of the option / action, and / or other metrics. Generally, preference may be given to mitigation strategies that have the least impact on other passengers. Additionally, some constraints (e.g., final aircraft destination at the end of a flight plan period) can be manually violated, while other constraints (e.g., safety constraints such as maximum weight on board the aircraft) cannot be manually violated.

[0058] In another example, a human personnel can modify one or more constraints and then revert the flight planning process. For example, if extreme weather makes a subset of transportation nodes unavailable for a period of time, a human personnel can adjust the constraints, mark the subset of transportation nodes as unavailable for that period of time, and then revert the flight planning process. Thus, some adjustments can be made directly to individual flight plans, while other adjustments may require system-wide readjustment or replanning.

[0059] In some implementations, the mitigation process can be automated (e.g., with the ability for manual override). As an example, a computing system can continuously generate contingency flight plans. For example, contingency flight plans can be generated using a process as described above, but taking into account potential or actual delays in a flight plan. When it is detected that a mitigation intervention should be implemented, the computing system can automatically select the best available contingency flight plan and indicate the selected flight plan to each aircraft and other system components. For example, automatic updates and alerts can be sent to passengers, aircraft providers, operations personnel, and / or other integrated systems. For each potential set of updated flight plans, the contingency flight plans can be ranked based on various metrics, including the number of passengers that would be affected as a result of the option / action, the number of passengers that would miss their arrival time as a result of the option / action, the total duration that would be added to transportation service for all passengers as a result of the option / action, and / or other metrics. Alternatively, or in addition, the objective function can be used to score contingency flight plans and / or replans for some or all of the fleet of aircraft. Thus, in some instances, dynamic contingency generation can be viewed as a sustained fleet-wide re-optimization of flight plans based on real-time conditions.

[0060] In some implementations, the mitigation process can be automated and implemented within the boundaries of pre-approval criteria established by one or more aircraft operators. For example, a computing system can detect one or more deviations of a fleet of aircraft and / or one or more passengers from a dispatched flight plan. The computing system can determine adjustments for at least one of the dispatched flight plan and / or set of potential flight plans to accommodate the one or more deviations. The computing system can compare the adjustments to pre-approval criteria for at least one of the dispatched flight plan or set of potential flight plans. In response to determining that the adjustments achieve the pre-approval criteria, the computing system can automatically adjust at least one of the dispatched flight plan and / or set of potential flight plans. In response to determining that the adjustments do not achieve the pre-approval criteria, the computing system can transmit data indicating the adjustments to human mitigation personnel.

[0061] Thus, in some implementations, the systems and methods of the present disclosure can generate potential flight plans for use by a rideshare network that include dynamic and / or automated changes to the flight plans based on real-time information. In particular, the systems and methods of the present disclosure can operate to generate a fleet level set of potential flight plans that comply with one or more constraints for the fleet of aircraft, and can provide manual and / or automated tools for flight plan adjustments, for example, to handle and mitigate delays or other real-time effects that cause the fleet of aircraft to deviate from the set of flight plans.

[0062] Referring now to the figures, exemplary embodiments of the present disclosure will be discussed in further detail. Exemplary Devices and Systems

[0063] 1 depicts a block diagram of an exemplary computing system 100 according to an exemplary embodiment of the present disclosure. The computing system 100 includes a cloud services system 102 that may operate to plan and fulfill transportation services.

[0064] The cloud services system 102 may be communicatively connected via a network 180 to one or more passenger computing devices 140, one or more service provider computing devices 150 for a first vehicle, one or more service provider computing devices 160 for a second vehicle, one or more service provider computing devices 170 for an Nth vehicle, and one or more infrastructure and operation computing devices 190.

[0065] Each of computing devices 140, 150, 160, 170, 190 may include any type of computing device, such as a smartphone, tablet, handheld computing device, wearable computing device, embedded computing device, navigation computing device, vehicle computing device, etc. The computing devices may include one or more processors and memory (e.g., similar to that which will be discussed with reference to processor 112 and memory 114). While service provider devices are shown for N different transportation means, any number of different transportation means may be used, including, for example, fewer than the three illustrated means (e.g., two means may be used). The service provider may include a human operator of the vehicle or the vehicle itself.

[0066] The cloud service system 102 includes one or more processors 112 and memory 114. The one or more processors 112 can be any suitable processing device (e.g., a processor core, a microprocessor, an ASIC, an FPGA, a controller, a microcontroller, etc.) and can be a single processor or multiple operatively connected processors. The memory 114 can include one or more non-transitory computer-readable storage media such as RAM, ROM, EEPROM, EPROM, one or more memory devices, flash memory devices, etc., and combinations thereof.

[0067] The memory 114 may store information that may be accessed by one or more processors 112. For example, the memory 114 (e.g., one or more non-transitory computer-readable storage media, memory devices) may store data 116 that may be retrieved, received, accessed, written, manipulated, created, and / or stored. In some implementations, the cloud service system 102 may retrieve data from one or more memory devices that are remote from the system 102.

[0068] The memory 114 may also store computer-readable instructions 118 that may be executed by the one or more processors 112. The instructions 118 may be software written in any suitable programming language or may be implemented in hardware. Additionally, or alternatively, the instructions 118 may be executed, logically and / or virtually, within separate threads on the processors 112. For example, the memory 114 may store instructions 118 that, when executed by the one or more processors 112, cause the one or more processors 112 to perform any of the operations and / or functions described herein. As an example, the memory 114 may include instructions 118 that, when executed by the one or more processors 112, cause the one or more processors 112 to perform operations of the flight planning system described herein.

[0069] Cloud services system 102 can include several different systems, such as a state of the world system 126, a forecasting system 128, an optimization / planning system 130, and a matching and fulfillment system 132. Matching and fulfillment system 132 can include a different matching system for each vehicle 134 and a monitoring and mitigation system 136. Each of systems 126-136 can be implemented in software, firmware, and / or hardware, including as software that, when executed by processor 112, causes cloud services system 102 to perform desired operations. Systems 126-136 can cooperate and interoperate (e.g., including feeding information to each other).

[0070] World state system 126 may operate to maintain data describing the current state of the world. For example, world state system 126 may generate, collect, and / or maintain data describing projected passenger demand, projected service provider supply, projected weather conditions, planned itineraries, predetermined transportation plans (e.g., flight plans) and assignments, current demand, current ground transportation service providers, current transportation node operating status (e.g., including recharging or refueling capabilities), current aircraft status (e.g., including current fuel or battery levels), current aircraft pilot status, current flight state and trajectory, current airspace information, current weather conditions, current communication system behavior / protocols, and / or the like. World state system 126 may obtain such world state information through communication with some or all of devices 140, 150, 160, 170, 190. For example, device 140 may provide current information about passengers, while devices 150, 160, and 170 may provide current information about service providers. The device 190 can provide current information about the status of the infrastructure and associated operations / management.

[0071] The forecasting system 128 may generate forecasts of supply and demand for transportation services at or between various locations over time. The forecasting system 128 may also generate or provide weather forecasts. The forecasts made by the system 128 may be generated based on historical data and / or through supply and demand modeling. In some instances, the forecasting system 128 may be referred to as an RMR system, where RMR stands for "routing, matching, and recharging." The RMR system may be capable of simulating the daily behavior of activity across multiple rideshare networks.

[0072] The optimization / planning system 130 may generate transportation plans for various transportation assets and / or generate itineraries for passengers. For example, the optimization / planning system 130 may perform flight planning for a fleet of aircraft (e.g., through implementation of any of the methods described herein, including methods 400, 500, and 600 of FIGS. 4, 5, and 6). As another example, the optimization / planning system 130 may plan or manage / optimize a journey, which includes interactions between passengers and service providers across multiple transportation modes.

[0073] The matching and fulfillment system 132 can match passengers with service providers for different modes of transportation. For example, each individual matching system 134 can communicate with a corresponding service provider computing device 150, 160, 170 via one or more APIs or connections. Each matching system 134 can communicate trajectories and / or assignments to a corresponding service provider. Thus, the matching and fulfillment system 132 can perform or address assignments of ground transportation, flight trajectories, takeoff / landing, etc.

[0074] The monitoring and mitigation system 136 can monitor a user's journey and can implement mitigation measures when the journey experiences significant delays (e.g., one of the legs fails to complete). Thus, the monitoring and mitigation system 136 can provide situational awareness, advisories, adjustments, and the like. The monitoring and mitigation system 136 can trigger alerts and actions that are sent to devices 140, 150, 160, 170, and 190. For example, passengers, service providers, and / or operations personnel can be alerted when a transportation plan is modified and provided with an updated plan / course of action. Thus, the monitoring and mitigation system 136 can have additional control over the movements of aircraft, ground vehicles, pilots, and passengers.

[0075] In some implementations, the cloud service system 102 may also store or include one or more machine-learned models. For example, the models may be or otherwise include various machine-learned models, such as support vector machines, neural networks (e.g., deep neural networks), decision tree-based models (e.g., random forests), or other multi-layer nonlinear models. Exemplary neural networks include feedforward neural networks, recurrent neural networks (e.g., long short-term memory recurrent neural networks), convolutional neural networks, or other forms of neural networks.

[0076] In some instances, the service provider computing devices 150, 160, 170 may be associated with an autonomous vehicle. Thus, the service provider computing devices 150, 160, 170 may provide communication between the cloud service system 102 and the autonomous vehicle's autonomy stack, which autonomously controls the movement of the autonomous vehicle.

[0077] Infrastructure and operations computing devices 190 can be any form of computing device used by or in infrastructure or operations personnel, including, for example, devices configured to perform passenger security checks, baggage check-in / out, recharging / refueling, safety briefings, vehicle check-in / out, and / or the like.

[0078] Network 180 can be any type of network or combination of networks that enables communication between devices. In some embodiments, the network can include one or more of a local area network, a wide area network, the Internet, a secure network, a cellular network, a mesh network, a peer-to-peer communication link, and / or some combination thereof, and can include any number of wired or wireless links. Communication over network 180 can be accomplished using any type of protocol, protection scheme, encoding, formatting, packaging, etc., via, for example, a network interface. Exemplary Fixed Infrastructure

[0079] FIG. 2 depicts a pictorial representation of an example set of flight plans between an example set of transportation nodes, according to an exemplary embodiment of the present disclosure. In particular, FIG. 2 provides a simplified illustration of an example fixed infrastructure associated with flight-based transportation in an example metropolitan area. As shown in FIG. 2, there are four transportation nodes, which may be referred to as "skyports" (e.g., vertiports, vertihubs). For example, a first transportation node 202 is located within a first vicinity of the metropolitan area, a second transportation node 204 is located within a second vicinity, a third transportation node 206 is located within a third vicinity, and a fourth transportation node 208 is located within a fourth vicinity. The locations and number of transportation nodes are provided by way of example only. Any number of transportation nodes in any different locations may be used.

[0080] Flights are available (e.g., may be pre-planned) between certain pairs of transportation nodes. For example, flight path 210 exists between first transportation node 202 and fourth transportation node 208. Similarly, flight path 212 exists between fourth transportation node 208 and third transportation node 206.

[0081] 3 depicts a pictorial representation of an example transportation node 300, according to an example embodiment of the present disclosure. Example transportation node 300 includes several take-off / arrival points, such as points 302 and 304. Example transportation node 300 also includes several vehicle parking locations, such as parking locations 306 and 308. For example, refueling or recharging infrastructure may be accessible at each parking location.

[0082] Flight trajectories into and out of transportation node 300 may be defined, configured, assigned, communicated, etc. Figure 3 illustrates several flight trajectories, including, for example, trajectories 310 and 312. The trajectories can be fixed or dynamically calculated. The trajectories can be calculated by the aircraft or can be centrally calculated and then assigned and communicated to the aircraft. As an example, Figure 3 illustrates helicopter 314 taking off from point 304 following trajectory 312. Exemplary Methods

[0083] FIG. 4 depicts a flowchart diagram of an example method 400 for generating and using a set of flight plans within a rideshare network, according to an exemplary embodiment of the present disclosure. One or more portions of method 400 can be implemented by a computing system, including, for example, one or more computing devices, such as the computing systems described with reference to other figures (e.g., flight planning system, computing system 100, cloud services system 102, world state system 126, forecasting system 128, optimization / planning system 130, matching and fulfillment system 132, etc.). Each individual portion of method 400 can be performed by any (or any combination of) one or more computing devices. Furthermore, one or more portions of method 400 can be implemented as an algorithm on a hardware component of a device described herein (e.g., as in FIGS. 1-3, etc.), e.g., to generate a set of flight plans. FIG. 4 depicts elements that are performed in a particular order for purposes of illustration and discussion. Those skilled in the art, using the disclosure provided herein, will understand that elements of any of the methods discussed herein can be adapted, rearranged, extended, omitted, combined, and / or modified in various ways without departing from the scope of the disclosure. Figure 4 is described with reference to elements / terminology described with respect to other systems and figures for exemplary illustrative purposes and is not meant to be limiting. One or more portions of method 400 can additionally or alternatively be performed by other systems.

[0084] At (402), method 400 may include receiving data describing a fleet of aircraft and one or more flight plan constraints for a flight planning horizon. For example, a computing system (e.g., computing system 100, cloud services system 102, world state system 126, forecasting system 128, optimization / planning system 130, matching and fulfillment system 132) may receive data describing a fleet of aircraft and one or more flight plan constraints for a flight planning horizon. A computing system (e.g., optimization and planning system 130, etc.) may receive a set of input data describing the fleet of aircraft, the one or more flight plan constraints, and / or the flight planning horizon. The input data may be provided by one or more systems and / or devices of the rideshare environment. For example, the input data may include passenger data received via one or more passenger computing devices 140 of FIG. 1, service provider data received from one or more service provider devices 150, 160, 170 of FIG. 1, infrastructure data received from one or more infrastructure and operations computing devices 190, world state data received from one or more world state systems 126, forecast data received from one or more forecast systems 128, and / or any other information associated with the rideshare network.

[0085] User-input data can be manually entered by a user (e.g., passenger, pilot, driver, operations personnel, etc.) and / or can be automatically captured (e.g., periodically, such as daily). For example, in some implementations, heterogeneous aircraft owners / operators can interact with a computing system (e.g., an application implemented thereby) (e.g., via service provider devices 150, 160, 170, etc.) and provide information regarding the availability of their aircraft for participation in the rideshare network. The provided information can then be accessed by the computing system (e.g., optimization / planning system 130). In other implementations, information about the fleet of available aircraft originates from a single, centralized source that oversees all aircraft operations.

[0086] A fleet of aircraft can include any number of aircraft of the same or different models owned and / or operated by one or more different air operators. Exemplary aircraft that may be included in a fleet include helicopters or other vertical takeoff and landing aircraft (VTOL), such as electric vertical takeoff and landing aircraft (eVTOL). In some implementations, a fleet of aircraft can include aircraft corresponding to varying levels of autonomous flight / movement, including non-autonomous aircraft, semi-autonomous aircraft, and fully autonomous aircraft. Each aircraft can be owned, maintained, and / or operated by one or more different air vehicle operators. By way of example, an air vehicle operator can include any entity with operational control (e.g., ownership, licensing, etc.) of one or more air vehicles. Each air vehicle operator can make one or more air vehicles available during a flight planning period.

[0087] A flight planning period may define the overall start and end dates and times for which the flight planning system should generate potential flight plans for a fleet of aircraft. Exemplary flight planning periods include periods of 3 hours, 24 hours, 1 week, etc. A flight planning period may be continuous or may include discrete periods.

[0088] The constraints described by the set of input data may include, by way of example, any number of different constraints associated with each aircraft, such as individual origin locations for each aircraft, individual destination locations for each aircraft, individual times when each aircraft is available or unavailable, individual starting fuel or charge levels for each aircraft, individual capabilities or attributes of each aircraft, such as the number of available passenger seats, maximum continuous operating time, maximum or minimum flight range, maximum or minimum flight altitude, noise level, etc., associated with an aircraft operation.

[0089] The constraints described by the set of input data may also describe fixed infrastructure (e.g., fixed infrastructure 300 in Figures 2-3) that a fleet of aircraft must utilize. In some implementations, the constraints described by the set of input data may also describe the availability of other resources, such as specific aircraft operators ("pilots"), operational personnel, and physical resources available at transportation nodes (e.g., machinery, fuel, maintenance capacity for safe passenger embarkation). In some implementations, a specific pilot may be linked to a specific aircraft and treated as a single resource, while in other implementations, they may be treated as separate resources.

[0090] In some implementations, input data to a computing system (e.g., optimization / planning system 130) may include world state and / or forecasted data (e.g., as determined / forecasted by world state system 126 and / or forecasting system 128). For example, the input data may include forecasted demand data that may describe the expected demand for air transportation at various times and locations over a flight planning period. The data may describe the expected origin and destination for the demand, or may simply forecast the origin of the demand.

[0091] The predicted demand data can be based, at least in part, on the rideshare network. The rideshare network (e.g., one or more devices 102, 140, 150, 160, 170, 190 thereof) can determine the predicted demand data by utilizing a number of real-time requests and / or historical data indicating the number of requests received from a plurality of different users of the network (e.g., drivers, service providers, pilots, dispatchers, etc.). In this manner, the predicted demand data can be determined, at least in part, based on the rideshare network. As an example, the predicted demand data can include historical and / or real-time requests from passengers of the rideshare network and / or data determined, at least in part, based on the historical and / or real-time requests from passengers of the rideshare network and provided to a computing system (e.g., forecasting system 128).

[0092] As another example, the input data may include expected supply data that may describe the expected supply of ground-based transportation providers at different individual times and transportation locations over a flight planning horizon. The expected supply data may be based, at least in part, on the rideshare network. For example, the rideshare network (e.g., its one or more devices 102, 140, 150, 160, 170, 190) may determine the expected supply data by identifying the number of service providers and / or assets available (e.g., opted in, etc.) to provide transportation services at multiple different times and / or locations over the flight planning horizon. In this manner, the expected supply data may be determined (e.g., by the forecasting system 128). As an example, the expected supply data may include historical and / or real-time information identifying the availability of the number of service providers and / or assets of the rideshare network and / or data determined and provided to a computing system (e.g., the optimization / planning system 130) based, at least in part, on the historical and / or real-time availability of the number of service providers and / or assets of the rideshare network.

[0093] At (404), method 400 may include generating a set of potential flight plans for the fleet of aircraft. For example, a computing system (e.g., computing system 100, cloud services system 102, world state system 126, forecasting system 128, optimization / planning system 130, matching and fulfillment system 132) may generate the set of potential flight plans for the fleet of aircraft. For example, in response to input data, a computing system (e.g., optimization / planning system 130, etc.) may generate the set of potential flight plans for the fleet of aircraft over a flight planning period. Each potential flight plan may include various types of information, such as, by way of example, an aircraft identification, a pilot identification (if required), an origin location, a destination location, a rough indication of the flight path, an estimated departure time, an estimated arrival time, and / or various other information regarding the potential operation of the aircraft.

[0094] A computing system (e.g., optimization / planning system 130, etc.) can generate a set of potential flight plans that maximizes the satisfaction of one or more combinations of objectives while also adhering to all of the constraints (e.g., not violating any of the constraints). As examples, objectives considered by a computing system (e.g., optimization / planning system 130, etc.) can include maximizing the number of potential flights generated, maximizing the proportion of potential flight plans that are dispatched, operating at maximum passenger capacity, maximizing the number of dispatched flights, flights operating on time, maximizing the number of passengers, arriving at their destinations on time, maximizing the number of passengers, minimizing the cumulative period passengers are delayed beyond their desired arrival time, and / or various other objectives. In some implementations, a computing system (e.g., optimization / planning system 130, etc.) can use a fleet-level objective function (e.g., using a set of weights) that balances some or all of the different objectives described above. The set of weights can be manually adjusted and / or automatically adjusted (e.g., learned).

[0095] A computing system (e.g., optimization / planning system 130, etc.) can implement one or more of a variety of different algorithms to generate a set of potential flight plans. For example, in some implementations, a computing system (e.g., optimization / planning system 130, etc.) can iteratively analyze a fleet of aircraft on an aircraft-by-aircraft basis, thereby generating an optimal set of potential flight plans for each aircraft. For example, an optimal set of potential flight plans for an aircraft can be generated by optimizing an aircraft-level objective function (e.g., using a set of weights) that balances any combination of the objectives described above for that aircraft. The set of weights in the aircraft-level objective function can be manually adjusted and / or automatically adjusted (e.g., learned). In some implementations, the aircraft-level objective function and the fleet-level objective function can be the same function and have the same weights. In some implementations, the fleet-level objective function can be equal to the sum of the aircraft-level objective functions as applied to all aircraft in the fleet.

[0096] For example, FIG. 5 depicts a flowchart diagram of an example method 500 for generating a set of potential flight plans on a per-aircraft basis, according to an exemplary embodiment of the present disclosure. One or more portions of method 500 can be implemented by a computing system, including, for example, one or more computing devices, such as the computing systems described with reference to other figures (e.g., flight planning system, computing system 100, cloud services system 102, world state system 126, forecasting system 128, optimization / planning system 130, matching and fulfillment system 132, etc.). Each individual portion of method 500 can be performed by any (or any combination of) one or more computing devices. Furthermore, one or more portions of method 500 can be implemented as an algorithm on a hardware component of a device described herein (e.g., as in FIGS. 1-3, etc.), e.g., to generate a set of flight plans on a per-aircraft basis. FIG. 5 depicts elements that are performed in a particular order for purposes of illustration and discussion. Those skilled in the art, using the disclosure provided herein, will understand that elements of any of the methods discussed herein can be adapted, rearranged, extended, omitted, combined, and / or modified in various ways without departing from the scope of the disclosure. Figure 5 is described with reference to elements / terminology described with respect to other systems and figures for exemplary illustrative purposes and is not meant to be limiting. One or more portions of method 500 can additionally or alternatively be performed by other systems.

[0097] At 502, method 500 can include receiving data describing a fleet of aircraft and one or more flight plan constraints for a flight duration. For example, a computing system (e.g., a flight planning system, computing system 100, cloud services system 102, world state system 126, forecasting system 128, optimization / planning system 130, matching and fulfillment system 132, etc.) can receive the data describing the fleet of aircraft and one or more flight plan constraints for a flight duration in a manner described herein (e.g., with reference to FIG. 4).

[0098] At 504, method 500 can include considering the next aircraft in the fleet. For example, a computing system (e.g., optimization / planning system 130, etc.) can consider the next aircraft in the fleet. At 506, method 500 can include generating a set of potential flight plans for the currently considered aircraft over the planning horizon. For example, a computing system (e.g., optimization / planning system 130, etc.) can generate a set of potential flight plans for the currently considered aircraft over the planning horizon. In particular, the set of potential flight plans can be flight plans that optimize an aircraft-level objective function.

[0099] For example, a computing system (e.g., optimization / planning system 130, etc.) may generate a set of flight plans for a particular aircraft by sequentially generating / adding flight plans for the aircraft starting from the beginning of the flight planning horizon and until the end of the flight planning horizon is reached. As an example, in each instance in which a computing system (e.g., optimization / planning system 130, etc.) attempts to generate a new flight plan for an aircraft, the computing system (e.g., optimization / planning system 130, etc.) may generate multiple candidate flight plans, score each candidate flight plan according to an aircraft-level objective function, and then select and add the highest-scoring flight plan for the aircraft.

[0100] As described herein, the aircraft-level objective function may, by way of example, balance any number of different objectives, including various objectives that are functions of demand for generated flight plans (e.g., total number of passengers served, total number of flights arranged, total number of flights with all available seats filled, etc.). To evaluate such objective functions, including objectives that are functions of demand, the system (e.g., optimization / planning system 130, etc.) may query a demand model (e.g., world state / forecasting system 126, 128, etc.) to obtain forecasted demand and / or supply information that can be used to evaluate such objectives. In another example, the aircraft-level objective function may focus (e.g., including as the sole objective) on maximizing the total number of generated flight plans.

[0101] In some implementations, the objective function may evaluate a set of flight plans based, at least in part, on the final journeys for multiple potential passengers. For example, the objective may include a function for reducing the total travel time for multiple passengers. As an example, the demand data (e.g., from the world state / forecasting system 126, 128, etc.) may include expected demand for the transportation service (e.g., expected demand data determined by the forecasting system 128, etc.). At times, the transportation service may include a multi-modal transportation service. In such cases, an air flight segment, such as one of the set of potential flight plans, may include one of multiple destinations for a passenger before the passenger reaches their final destination. The objective function may evaluate a set of flight plans based, at least in part, on the total estimated travel time for multiple passengers. For example, a computing system (e.g., the optimization / planning system 130, etc.) may identify infrastructure, traffic, weather, and / or other factors that may affect subsequent ground transportation segments and optimize the set of potential flight plans to reduce the total estimated travel time for users of the rideshare network.

[0102] As an example, a computing system (e.g., optimization / planning system 130, etc.) can consider ground-based transportation information (e.g., provided by world conditions, forecasting systems 126, 128, service provider computing devices 150, 160, 170, infrastructure and operations computing device 190, etc.) when generating a set of flight plans. For example, the expected last-leg supply availability can be used as an input to an aircraft-level objective function to reward (e.g., increase the objective score associated with) flights that deliver passengers to their destinations and have a robust supply of ground-based transportation services, and penalize (e.g., decrease the objective score associated with) flights that deliver passengers to their destinations and do not have a robust supply of ground-based transportation services. Similarly, the expected supply availability of the first leg may also be used as an input to the aircraft-level objective function to reward (e.g., increase the objective score associated with) flights that collect passengers from departure nodes that have a robust supply of ground-based transportation services and penalize (e.g., decrease the objective score associated with) flights that collect passengers from departure nodes that do not have a robust supply of ground-based transportation services. In other implementations, such information regarding the supply of transportation services according to other means may also be assumed to be included in the expected demand data.

[0103] A computing system (e.g., optimization / planning system 130, etc.) can evaluate a set of potential flight plans based, at least in part, on the proximity with which the set of potential flight plans can transport potential passengers (e.g., expected based on expected demand data, etc.) to their expected final destinations. For example, the expected demand data may include expected final destinations for each of a plurality of expected passengers. The computing system (e.g., optimization / planning system 130, etc.) can generate a set of potential flight plans to facilitate transporting the plurality of expected passengers to locations (e.g., transportation nodes) closest to their expected final destinations.

[0104] In some implementations, the location (e.g., transportation node) closest to the expected final destination may not be the most efficient and / or timely route for transporting the multiple expected passengers. For example, subsequent ground transportation from the closest location may be affected by traffic and / or other roadway delays. Additionally, in some implementations, the flight plan to the closest location may be affected by weather or other airspace delays. In such cases, a computing system (e.g., optimization / planning system 130, etc.) can generate / evaluate a set of flight plans to facilitate transportation of the multiple expected passengers to the location (e.g., transportation node) closest in time to the expected final destination such that factors affecting subsequent transportation to the final destination are taken into account.

[0105] In some implementations, a computing system (e.g., optimization / planning system 130, etc.) can include a greedy refueling component. The greedy refueling component can greedily assign aircraft to engage in refueling and / or recharging whenever the aircraft is not in flight (e.g., above a minimum amount of time) and refueling / recharging infrastructure is available at the aircraft's current location (e.g., as indicated by infrastructure and operations computing device 190, etc.). The greedy refueling component can be applied after flight plan generation or can be used as part of the generation process itself. In such a manner, refueling / recharging infrastructure usage can be optimized.

[0106] In some implementations, a computing system (e.g., optimization / planning system 130, etc.) can perform or participate in an iterative learning process for the weighting of the planning objective function. For example, an initial set of weights for the objective function can be manually adjusted. The computing system (e.g., optimization / planning system 130, etc.) can operate with the initial set of weights to generate any number of flight plans over any number of flight planning periods. Performance associated with the generated flight plans can be observed and measured according to various metrics. The set of weights can be readjusted (e.g., automatically and / or manually) based on the observed performance. For example, various learning techniques, such as gradient descent, can be applied to learn the set of weights. For example, gradient descent can be applied to the weightings of the fleet-level objective function or the aircraft-level objective function. More generally, a computing system (e.g., optimization / planning system 130, etc.) can collect any data describing the performance of certain manually controlled settings, actions, weights, decisions, and / or the like, and can apply machine learning techniques to such data to learn updated or optimized versions of such settings, actions, weights, decisions, and / or the like.

[0107] In this manner, a computing system (e.g., optimization / planning system 130, etc.) can automatically generate a set of potential flight plans for a fleet of aircraft owned and / or operated by one or more different air operators. In some implementations, each flight plan can be approved by an individual air vehicle operator (e.g., via service provider computing devices 150, 160, 170, etc.). For example, each air vehicle operator can be associated with a pre-approval rule set. The pre-approval rule set can, for example, outline one or more acceptable flight plans for air vehicles under the operational control of the individual air vehicle operator (e.g., from / to / between one or more approved locations, within an approved time period, etc.). In some implementations, the set of potential flight plans can include only approved flight plans. Additionally or alternatively, the set of potential flight plans can include unapproved flight plans. In such cases, the unapproved flight plans can be provided to the individual air vehicle operator for manual approval (e.g., staged approval). A computing system (e.g., optimization / planning system 130, etc.) can modify and / or regenerate any flight plan that is not manually and / or pre-approved by an individual air vehicle operator.

[0108] At 508, the method 500 may include determining whether additional aircraft remain in the fleet. For example, a computing system (e.g., the optimization / planning system 130, etc.) may determine whether additional aircraft remain in the fleet.

[0109] If additional aircraft remain, method 500 may return to (504) to consider the next aircraft in the fleet. However, if at (508) it is determined that all aircraft in the fleet have been considered, method 500 may proceed to (510).

[0110] At 510, method 500 may include determining whether additional optimization iterations should be performed. For example, a computing system (e.g., optimization / planning system 130, etc.) may determine whether additional optimization iterations should be performed. Any number of iterations may be performed to allow flight plans to be generated for different aircraft and balanced and reordered relative to one another. For example, aircraft may be considered in a different sequence in each iteration. The iterations may be performed until one or more stopping criteria are met. The stopping criteria may include a loop counter meeting a threshold, a change in the objective function score over the iterations being below a threshold, a raw objective function score exceeding a threshold, and / or other criteria. However, in some cases, only a single iteration is performed.

[0111] If at 510 it is determined that additional iterations should be performed, method 500 may return to block 504 to perform another iteration of plan generation for some or all of the fleet. However, if at 510 it is determined that additional iterations should not be performed, method 500 may proceed to 512.

[0112] At 512, method 500 may include providing a set of potential flights as an output. For example, a computing system (e.g., optimization / planning system 130, etc.) may provide the set of potential flights as an output. As an example, the set of potential flights may be output to a matching and fulfillment system (e.g., matching and fulfillment system 132 of FIG. 1 ) configured to add passengers to one or more of the sets of potential flights to generate one or more arranged flights.

[0113] As another example, FIG. 6 depicts a flowchart diagram of an example method 600 for generating a set of potential flight plans based on a priority hierarchy, according to an exemplary embodiment of the present disclosure. One or more portions of method 600 can be implemented by a computing system, including, for example, one or more computing devices, such as the computing systems described with reference to other figures (e.g., flight planning system, computing system 100, cloud services system 102, world state system 126, forecasting system 128, optimization / planning system 130, matching and fulfillment system 132, etc.). Each individual portion of method 600 can be performed by any (or any combination of) one or more computing devices. Furthermore, one or more portions of method 600 can be implemented as an algorithm on a hardware component of a device described herein (e.g., as in FIGS. 1-3, etc.) to generate a set of flight plans, for example, based on a priority hierarchy. FIG. 6 depicts elements being performed in a particular order for purposes of illustration and discussion. Those skilled in the art, using the disclosure provided herein, will understand that elements of any of the methods discussed herein can be adapted, rearranged, extended, omitted, combined, and / or modified in various ways without departing from the scope of the disclosure. Figure 6 is described with reference to elements / terminology described with respect to other systems and figures for exemplary illustrative purposes and is not meant to be limiting. One or more portions of method 600 can additionally or alternatively be performed by other systems.

[0114] At 602, method 600 may include receiving data describing a fleet of aircraft and one or more flight plan constraints for a flight period. For example, a computing system (e.g., a flight planning system, computing system 100, cloud services system 102, world state system 126, forecasting system 128, optimization / planning system 130, matching and fulfillment system 132, etc.) may receive data describing a fleet of aircraft and one or more flight plan constraints for a flight period in a manner described herein (e.g., with reference to FIG. 4).

[0115] At 602, the method 600 may include sorting time periods within a flight plan period into two or more priority hierarchies. For example, a computing system (e.g., optimization / planning computing system 130, etc.) may sort multiple time periods within a flight plan period into two or more priority hierarchies.

[0116] At 606, method 600 may include considering the next priority tier of the time period. For example, the computing system (e.g., the optimization / planning computing system 130, etc.) may consider the next priority tier of the time period. For example, in the first instance of 606, the computing system (e.g., the optimization / planning computing system 130, etc.) may consider the highest priority tier of the time period. As an example, in a multi-tier approach, the computing system (e.g., the optimization / planning computing system 130, etc.) may first start with the highest priority tier and iteratively consider the time periods within each priority tier (e.g., by generating a flight plan, etc.). Thus, after considering the time period in the highest priority tier, the computing system (e.g., the optimization / planning computing system 130, etc.) may then consider the time period in the next highest priority tier.

[0117] At 608, method 600 may include generating a set of potential flight plans for the fleet of aircraft for each time period within the currently considered priority hierarchy. For example, a computing system (e.g., optimization / planning computing system 130, etc.) may generate a set of potential flight plans for the fleet of aircraft for each time period within the currently considered priority hierarchy. For example, method 500 of FIG. 5 may be performed for each time period within the currently considered priority hierarchy. Each tier of time periods may use the generated flight plans for the previous tier as constraints for the scheduling process. For example, if a generated flight plan for the 4:00 PM to 7:00 PM time period requires a given aircraft to depart from a particular transportation node with a particular fuel / charge level, when generating a flight plan for the 1:00 PM to 4:00 PM time period, the flight planning system may handle as a constraint the fact that the aircraft must arrive at the particular transportation node with a particular fuel / charge level during the 1:00 PM to 4:00 PM time period. In such a manner, flight plans may be specifically optimized for the highest priority time period, for example, when the largest number of passengers need to be served.

[0118] At 610, method 600 may include determining whether additional priority tiers remain. For example, a computing system (e.g., optimization / planning system 130, etc.) may determine whether additional priority tiers remain. If additional priority tiers remain, method 600 may return to 606 and consider the next priority tier for the time period. However, if it is determined at 610 that no additional priority tiers remain, method 600 may proceed to 612. At 612, method 600 may include providing as output a set of potential flight plans for the entire flight planning period. For example, a computing system (e.g., optimization / planning system 130, etc.) may provide as output the set of potential flight plans for the entire flight planning period. As an example, the set of potential flight plans may be output to a matching and fulfillment system (e.g., matching and fulfillment system 132 of FIG. 1 ) configured to add passengers to one or more of the sets of potential flights to generate one or more arranged flights.

[0119] Returning to FIG. 4, method 400 may include generating one or more arranged flights based on the set of potential flight plans and passenger demand for generating and using the set of flight plans within the rideshare network.

[0120] At (406), method 400 may include exposing a set of potential flight plans (e.g., determined according to methods 500, 600, etc.) to a rideshare network and receiving passenger additions to one or more flight plans, thereby transitioning the potential flight plans to dispatched flight plans. For example, a computing system (e.g., optimization / planning computing system 130, matching and fulfillment system 132, etc.) may expose a set of potential flight plans to a rideshare network and receive passenger additions to one or more flight plans, thereby transitioning the potential flight plans to dispatched flight plans.

[0121] As an example, after a computing system (e.g., optimization / planning computing system 130, matching and fulfillment system 132, etc.) generates a set of potential flight plans for a fleet and a flight planning period, the set of potential flight plans can be exposed to a rideshare network. In particular, a matching system (e.g., matching system 134 of FIG. 1, etc.) of the rideshare network can match one or more passengers in the network with a particular flight plan according to a matching process, thereby dispatching the flight plan for operation. In some implementations, the matching system (e.g., matching system 134, etc.) of FIG. 1 can implement a passenger pool in which multiple requests for service are collected from users over a period of time, and the matching service collectively analyzes the requests and identifies opportunities to pool passengers together. While aspects of the present disclosure focus on providing air transportation services to human passengers, the systems and methods of the present disclosure are equally applicable to determining flight plans for air transportation services for non-human payloads, such as luggage, prepared food, pet transportation, and / or the like.

[0122] In some implementations, a set of potential flight plans can be exposed to a rideshare network with minimal detail. For example, a potential flight plan can be described by data indicating the number of passengers and / or routes that can be served between, between, and / or to segment times at multiple locations. Passengers on the rideshare network can reserve a route by booking air transportation for a segment time. The reserved segment time can be used by the rideshare network to match passengers to flights from the potential set of flights.

[0123] As an example, passengers in a rideshare network can reserve a route (e.g., generally, flight details, etc.) for a certain segment time. The segment time can describe a time slot container and can be used as input to generate a dispatched flight plan. A computing system (e.g., matching and fulfillment system 132, etc.) can receive multiple requests, group the multiple requests into one or more time slot containers, and organize flights around the time slot containers. Passengers are given a price estimate but may not be billed until after the flight has occurred. Prior to the flight's occurrence, passengers can be provided with information such as the aircraft type assigned to perform the flight, the time slot associated with the flight, and / or any other information associated with the dispatched flight.

[0124] In this manner, a dispatched flight plan can be generated by adding passengers to a potential flight plan of a set of potential flight plans. Thus, a dispatched flight plan can include a potential flight plan with one or more assigned passengers. For example, each dispatched flight plan can be associated with one or more assigned passengers associated with the rideshare network. Additionally, a dispatched flight plan can include a scheduled takeoff time, a scheduled landing time, and a buffer period. The buffer period can indicate a delay (e.g., an acceptable delay) from the scheduled takeoff time. The buffer period can be determined, at least in part, based on input data, one or more constraints (e.g., weather, traffic, deviations, etc.), and / or a duration. For example, a dispatched flight plan can form a user-centric flight schedule with an adjustable takeoff time based, at least in part, on the assigned passengers associated with the dispatched flight plan. This adjustable user-centric takeoff time can be represented by a buffer period.

[0125] More specifically, the dispatched flight plan may include a buffer period that is determined based on a comprehensive input centered on passenger convenience. As an example, a computing system (e.g., matching and fulfillment system 132, etc.) may generate the dispatched flight plan based, at least in part, on one or more assigned passengers (e.g., added by a rideshare network). The computing system (e.g., matching and fulfillment system 132, etc.) may determine a buffer period for the dispatched flight plan based, at least in part, on the one or more assigned passengers of the dispatched flight plan.

[0126] For example, one or more assigned passengers can each be associated with a multi-leg journey. A multi-leg journey can include multiple legs, e.g., via one or more different modes. For example, one leg of a multi-leg journey can include a dispatched flight plan. An additional leg can include ground transportation to an origin location of the dispatched flight plan, another ground transportation from a destination location of the dispatched flight plan, and / or one or more additional flight legs preceding and / or following the dispatched flight plan.

[0127] In some implementations, a computing system (e.g., matching and fulfillment system 132, etc.) can determine a buffer period for each one or more assigned passengers based, at least in part, on the multi-leg journey. For example, the multi-leg journey can be associated with a total estimated travel time for the assigned passenger. In such a case, the buffer period can be determined, at least in part, based on an aggregated delay period for each multi-leg journey of the one or more assigned passengers as a result of delaying the dispatched flight plan by one or more different periods. The buffer period can be determined, for example, to ensure that the aggregated delay period is less than a threshold time (e.g., 1 hour, 30 minutes, 10 minutes, etc.). In some cases, the threshold time can include a period less than the duration of the dispatched flight. As an example, for illustrative purposes, a computing system (e.g., matching and fulfillment system 132, etc.) may predict higher traffic volume for ground transportation during a first period after the dispatched flight. In such a case, a computing system (e.g., matching and fulfillment system 132, etc.) may determine a buffer period that is less than the first period to prevent affected passengers from being further delayed by predictable traffic.

[0128] Additionally or alternatively, the buffer period may be determined based, at least in part, on the number of one or more assigned passengers who would have changes to their multi-leg journey as a result of delaying the dispatched flight plan by one or more different periods. For example, the buffer period may be determined to prevent one or more assigned passengers from missing a subsequent flight.

[0129] At 408, method 400 may include monitoring compliance of a fleet of aircraft and / or passengers with arranged flight plans. For example, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may monitor compliance of a fleet of aircraft and / or passengers with arranged flight plans.

[0130] More specifically, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may continuously monitor the success / feasibility of each arranged flight plan. For example, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may monitor real-time data, such as aircraft location data (e.g., received from service provider computing devices 150, 160, 170, etc.), aircraft sensor data (e.g., from service provider computing devices 150, 160, 170, infrastructure and operations computing devices 190, etc.), passenger location data (e.g., received, with authorization, from passenger computing devices 140, service provider computing devices 150, 160, 170, etc.), weather data (e.g., from forecasting system 128, etc.), ground-based transportation data (e.g., received from service provider computing devices 150, 160, 170, etc.), and / or other forms of data, to detect current or likely deviations from the arranged flight plans of aircraft fleets and / or passengers. In particular, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may monitor and evaluate estimated versus planned arrival times for some or all passengers, estimated versus planned arrival times for some or all aircraft, and / or other measures of flight plan success.

[0131] Thus, at 408, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) can continuously assess whether a flight will successfully depart and / or arrive at its scheduled time, including tracking whether an assigned passenger will be able to physically progress through the transportation node and successfully arrive at the departure transportation node in sufficient time to board the aircraft. In particular, in some implementations, the estimated arrival time may be for the passenger and may be based on a first leg of a multi-leg journey. For example, a user may arrive at a transportation node using ground-based transportation (e.g., a ride-share vehicle), and thus a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may track the user's progress along the ground-based transportation leg and assess whether the user will arrive in sufficient time to avoid delaying their associated flight (e.g., which may be the second leg of a multi-leg journey).

[0132] A computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) can track user location, for example, by receiving location data associated with one or more of the one or more passengers. For example, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) can interact with a rideshare network (e.g., via one or more service provider devices 150, 160, 170, etc.) to receive updates to passenger locations. As an example, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) can receive passenger location data associated with an individual passenger from a land vehicle device assigned to the individual passenger for providing ground transportation to the individual passenger prior to the passenger's individual arranged flight plan. The location data can be received in real time, periodically, or during the course of the passenger's journey from the passenger's origin location to the first transportation node. Additionally or alternatively, the location data can be received in response to a detected deviation from an original estimated arrival time. For example, location data for a passenger may indicate a later or earlier estimated arrival time for a passenger. In some implementations, location data may include traffic information, driver information, flight information, and / or any other information associated with transporting the passenger to the first transportation node of the arranged flight.

[0133] At (410), method 400 may include detecting one or more deviations from a dispatched flight plan for a fleet of aircraft and / or passengers. For example, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may detect one or more deviations from a dispatched flight plan for a fleet of aircraft and / or passengers. The computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may implement real-time mitigation measures and replanning when a particular flight plan is significantly delayed or canceled / not dispatched. Typically, the computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may attempt to delay replanning activities until it is deemed, with a significant probability, that the dispatched flight plan will not be able to be successfully completed.

[0134] At 412, method 400 may include adjusting the flight plan to account for the deviation. For example, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may adjust the flight plan to account for the deviation. For example, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may implement real-time mitigation measures and re-planning based, at least in part, on one or more deviations for one or more passengers. For example, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may re-optimize the set of potential flight plans and / or one or more dispatched flight plans based, at least in part, on minimizing inconvenience to passengers. As an example, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may determine a mitigation action (e.g., delaying a flight, reassigning one or more passengers to a different scheduled flight, etc.) in response to one or more deviations in the aircraft fleet and / or passengers. For each available mitigation action, the computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may determine a portion of passengers that will be affected as a result of the mitigation action. As an example, the computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may determine a portion of passengers that will not arrive on time as a result of the mitigation action, an aggregate duration that will be added to transportation service for all passengers as a result of the mitigation action, and / or other metrics.In this manner, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) can adjust one or both of the dispatched flight plan and / or the set of potential flight plans to account for one or more deviations without adversely affecting the convenience of dispatched passengers in the on-demand transportation service.

[0135] In some implementations, the mitigation process may include delaying the flight based on a buffer period in the dispatched flight plan. For example, the buffer period may indicate a period of time before and / or after the scheduled takeoff that is acceptable for the aircraft. For example, consideration may be given to accommodating late and / or early passengers based, at least in part, on the user's (e.g., location) and the perception of other pooled users associated with the dispatched flight. For example, the buffer period may be determined based on the collective inconvenience factor and / or trickle-down impact of the delayed takeoff time. A computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may determine that the deviation is due to a late assigned passenger for the dispatched flight plan. The computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may determine an estimated arrival time for the late assigned passenger and determine an adjustment for the dispatched flight plan based, at least in part, on the estimated arrival time and the buffer period for the late assigned passenger. A computing system (eg, matching and fulfillment system 132, monitoring and mitigation system 136, etc.) can apply adjustments to the dispatched flight plan.

[0136] As an example, in response to determining that the estimated arrival time for a late assigned passenger is after the scheduled takeoff time by a period that exceeds the buffer period, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may add the late assigned passenger to one or more of the set of potential flight plans (and / or dispatched flight plans with space for the late assigned passenger). Additionally or alternatively, in response to determining that the estimated arrival time for a late passenger is after the scheduled takeoff time that is within the buffer period, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may delay the scheduled takeoff time for the dispatched flight plan to accommodate the late assigned passenger. In some implementations, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may automatically transmit notification to one or more of the late assigned passenger (e.g., via individual passenger computing device 140), operations personnel (e.g., via infrastructure and operations computing device 190), and / or aircraft / ground vehicle operator (e.g., via service provider computing devices 150, 160, 170).

[0137] In some implementations, the mitigation process can include manual input by human mitigation personnel. For example, the need to implement mitigation can be automatically detected, and as a result, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) can provide an alert and a mitigation user interface to the human mitigation personnel. For example, the mitigation user interface can include a graphical user interface that shows potential alternative flight plans and / or modifications to a flight plan currently experiencing a delay / cancellation. As one example, the human personnel can interact with the interface and adjust various parameters of one or more flight plans. For example, the human personnel can modify flight departure times, modify buffer times associated with passenger physical passage through transportation nodes and / or vehicle boarding / deboarding, add or remove passengers from flights, move passengers between flights, change pilots, and / or take other actions to manually modify a set of flight plans. In some implementations, any downstream impact on the flight plans from manual changes can be automatically calculated and propagated through the set of flight plans.

[0138] In some implementations, the user interface can provide warnings or other indications of the extent to which a mitigation activity or potential action may affect other users of the system and / or violate certain initial input constraints. For example, if mitigation personnel attempt to delay a flight plan that has not yet departed to wait for the delayed user, the user interface can inform the mitigation personnel that such an action will affect three other travelers. For each available option / action, the warnings / indications provided within the user interface can provide impact information according to various metrics, including the number of users that will be affected as a result of the option / action, the number of users that will miss their arrival time as a result of the option / action, the total duration that will be added to transportation services for all users as a result of the option / action, and / or other metrics. Generally, preference can be given to mitigation strategies that have the least impact on other passengers. Additionally, some constraints (e.g., final aircraft destination at the end of the flight plan horizon) can be manually violated, while other constraints (e.g., safety constraints such as maximum weight on board the aircraft) cannot be manually violated.

[0139] In another example, a human personnel can modify one or more constraints and then revert the flight planning process. For example, if extreme weather makes a subset of transportation nodes unavailable for a period of time, a human personnel can adjust the constraints, mark the subset of transportation nodes as unavailable for that period of time, and then revert the flight planning process. Thus, some adjustments can be made directly to individual flight plans, while other adjustments may require system-wide readjustment or replanning.

[0140] In some implementations, the mitigation process can be automated (e.g., with the ability for manual override). As an example, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) can continuously generate contingency flight plans. For example, contingency flight plans can be generated using a process as described above, but taking into account potential or actual delays in a flight plan. Upon detecting that a mitigation intervention should be implemented, the computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) can automatically select the best available contingency flight plan and present the selected flight plan to each aircraft and other system components. For example, automatic updates and alerts can be sent to passengers, aircraft providers, flight personnel, and / or other integrated systems. For each potential set of updated flight plans, the contingency flight plans can be ranked based on various metrics, including the number of passengers that would be affected as a result of the option / action, the number of passengers that would miss their arrival time as a result of the option / action, the total duration that would be added to transportation service for all passengers as a result of the option / action, and / or other metrics. Alternatively, or in addition, an objective function can be used to score the contingency flight plans and / or replans for some or all of the aircraft fleet. Thus, in some instances, dynamic contingency generation can be viewed as a continuous fleet-wide re-optimization of flight plans based on real-time conditions.

[0141] In some implementations, the mitigation process can be automated and implemented within the boundaries of pre-approval criteria established by one or more aircraft operators. For example, a computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) can detect one or more deviations of a fleet of aircraft and / or one or more passengers from a dispatched flight plan. The computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) can determine adjustments for at least one of the dispatched flight plans and / or the set of potential flight plans to accommodate the one or more deviations. The computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) can compare the adjustments to pre-approval criteria for at least one of the dispatched flight plans or the set of potential flight plans. In response to determining that the adjustment achieves the pre-approval criteria, the computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may automatically adjust at least one of the set of dispatched flight plans and / or potential flight plans. In response to determining that the adjustment does not achieve the pre-approval criteria, the computing system (e.g., matching and fulfillment system 132, monitoring and mitigation system 136, etc.) may transmit data indicative of the adjustment to human mitigation personnel. Additional Disclosures

[0142] The use of a computer-based system allows for a wide variety of possible configurations, combinations, and divisions of tasks and functionality among and among components. Computer-implemented operations can be performed on a single component or across multiple components. Computer-implemented tasks and / or operations can be performed sequentially or in parallel. Data and instructions can be stored in a single memory device or across multiple memory devices.

[0143] While the present subject matter has been described in detail with reference to various specific exemplary embodiments thereof, each example is provided by way of illustration, not limitation, of the present disclosure. Those skilled in the art will be able to readily produce modifications, variations, and equivalents of such embodiments upon attainment of the foregoing understanding. Thus, the present disclosure does not exclude the inclusion of such modifications, variations, and / or additions to the present subject matter that would be readily apparent to one skilled in the art. For example, features illustrated or described as part of one embodiment can be used in combination with another embodiment to yield still a further embodiment. Thus, the present disclosure is intended to cover such modifications, variations, and equivalents.

[0144] 4, 5, and 6 each depict steps performed in a particular order for purposes of illustration and discussion, the methods of the present disclosure are not limited to the order or arrangement shown. Various steps of methods 400, 500, and 600 can be omitted, rearranged, combined, and / or adapted in various ways without departing from the scope of the present disclosure.

Claims

1. A method, the method comprising: a computing system comprising one or more computing devices accessing input data describing a fleet of aircraft; the computing system calculating potential flight plans for aircraft in the fleet of aircraft; the computing system exposing the potential flight plans to a rideshare network via a communications network; generating a dispatched flight plan by the computing system accessing passenger data from the rideshare network indicating one or more passengers to be added to the potential flight plan; the computing system accessing location data associated with the aircraft, the location data being determined by tracking passengers within the aircraft or the one or more passengers; the computing system detecting, based on the location data, a likelihood that the aircraft will not be able to depart from a transportation node at a scheduled time in the dispatched flight plan, the likelihood being associated with arrival at the transportation node by a missed time for the passenger or the aircraft, and the passenger is scheduled to board the aircraft at the transportation node; the computing system calculating a mitigation activity and an impact of the mitigation activity, the impact indicating an effect on the arrival by time of implementing the mitigation activity; the computing system transmitting to a graphical user interface display of a computing device associated with the aircraft the impact of the mitigation activity and a notice associated with the mitigation activity, the notice being displayed on the graphical user interface display to indicate the mitigation activity to mitigate the possibility; A method comprising:

2. The method of claim 1, wherein the computing devices associated with the aircraft include user devices associated with the passengers.

3. The method of claim 1, wherein the computing device associated with the aircraft includes an aircraft device associated with an operator of the aircraft.

4. The method of claim 1, wherein the probability is associated with a buffer period, and arrival by the missed time for the passenger or aircraft exceeds the buffer period.

5. The method of claim 1, wherein the mitigation activity includes reassigning the passenger to another arranged flight plan.

6. The method of claim 1, further comprising: The method of claim 1 , comprising determining a number of passengers among the one or more passengers affected by the mitigation activity.

7. The method of claim 1, wherein the impact of the mitigation activity and the notification associated with the mitigation activity include an indication of the extent to which the mitigation activity affects constraints associated with the arranged flight plan.

8. The method of claim 1, wherein the input data is generated by the rideshare network.

9. A computing system, comprising: one or more processors; one or more non-transitory computer-readable media storing instructions; wherein the instructions are executable by the one or more processors to perform operations, the operations comprising: a computing system comprising one or more computing devices accessing input data describing a fleet of aircraft; the computing system calculating potential flight plans for aircraft in the fleet of aircraft; the computing system exposing the potential flight plans to a rideshare network via a communications network; generating a dispatched flight plan by the computing system accessing passenger data from the rideshare network indicating one or more passengers to be added to the potential flight plan; the computing system accessing location data associated with the aircraft, the location data being determined by tracking passengers within the aircraft or the one or more passengers; the computing system detecting, based on the location data, a likelihood that the aircraft will not be able to depart from a transportation node at a scheduled time in the dispatched flight plan, the likelihood being associated with arrival at the transportation node by a missed time for the passenger or the aircraft, and the passenger is scheduled to board the aircraft at the transportation node; the computing system calculating a mitigation activity and an impact of the mitigation activity, the impact indicating an effect on the arrival by time of implementing the mitigation activity; the computing system transmitting to a graphical user interface display of a computing device associated with the aircraft the impact of the mitigation activity and a notice associated with the mitigation activity, the notice being displayed on the graphical user interface display to indicate the mitigation activity to mitigate the possibility; a computing system including:

10. The computing system of claim 9, wherein the computing devices associated with the aircraft include user devices associated with the passengers.

11. The computing system of claim 9, wherein the computing device associated with the aircraft includes an aircraft device associated with an operator of the aircraft.

12. The computing system of claim 9, wherein the likelihood is associated with a buffer period, and arrival by the missed time for the passenger or aircraft exceeds the buffer period.

13. The computing system of claim 9, wherein the mitigation activity includes reassigning the passenger to another arranged flight plan.

14. The step of calculating the impact of the mitigation activity, comprising: The computing system of claim 9 , further comprising determining a number of passengers among the one or more passengers affected by the mitigation activity.

15. The computing system of claim 9, wherein the impact of the mitigation activity and the notification associated with the mitigation activity include an indication of the extent to which the mitigation activity affects constraints associated with the arranged flight plan.

16. The computing system of claim 9, wherein the input data is generated by the rideshare network.

17. One or more non-transitory computer-readable media storing instructions, the instructions being executable by one or more processors to perform operations, the operations comprising: a computing system comprising one or more computing devices accessing input data describing a fleet of aircraft; the computing system calculating potential flight plans for aircraft in the fleet of aircraft; the computing system exposing the potential flight plans to a rideshare network via a communications network; generating a dispatched flight plan by the computing system accessing passenger data from the rideshare network indicating one or more passengers to be added to the potential flight plan; the computing system accessing location data associated with the aircraft, the location data being determined by tracking passengers within the aircraft or the one or more passengers; the computing system detecting, based on the location data, a likelihood that the aircraft will not be able to depart from a transportation node at a scheduled time in the dispatched flight plan, the likelihood being associated with arrival at the transportation node by a missed time for the passenger or the aircraft, and the passenger is scheduled to board the aircraft at the transportation node; the computing system calculating a mitigation activity and an impact of the mitigation activity, the impact indicating an effect on the arrival by time of implementing the mitigation activity; the computing system transmitting to a graphical user interface display of a computing device associated with the aircraft the impact of the mitigation activity and a notice associated with the mitigation activity, the notice being displayed on the graphical user interface display to indicate the mitigation activity to mitigate the possibility; 1. One or more non-transitory computer-readable media, including:

18. One or more non-transitory computer-readable media as described in claim 17, wherein the computing devices associated with the aircraft include user devices associated with the passengers.

19. One or more non-transitory computer-readable media as described in claim 17, wherein the computing device associated with the aircraft includes an aircraft device associated with an operator of the aircraft.

20. One or more non-transitory computer-readable media as described in claim 17, wherein the likelihood is associated with a buffer period, and arrival by the missed time for the passenger or the aircraft exceeds the buffer period.

Images