Determining VTOL departure time in an aviation transport network for efficient resource management

1. A computer-implemented method comprising:

accessing, over one or more networks, data defining a plurality of requests for transportation services for respective riders, origins, and destinations;

computing assignments of selected ones of the plurality of requests to trip itineraries that include transportation, at least in part, by a vertical take-off and landing (VTOL) aircraft, each of the selected requests being associated with data indicative of a threshold time to arrive at the corresponding destination;

based at least partly on there being unassigned capacity on the VTOL aircraft, accessing demand data associated with the transportation services and the threshold times;

based at least in part on the demand data and the threshold times, computing a VTOL-hold value predictive of whether another request will be received for an additional rider and the additional rider will board the VTOL aircraft within a time period such that each of the riders of selected requests will arrive at their respective destinations prior to the respective threshold times;

computing that, the VTOL aircraft should wait based on the VTOL-hold value exceeding a likelihood threshold; and

after the VTOL aircraft waits in response to the VTOL-hold value, controlling the VIOL aircraft to take-off.

2. The computer-implemented method of claim 1 , further comprising:

transmitting, over the one or more networks to a computing system associated with the VIOL aircraft, information associated with the additional rider.

3. The computer-implemented method of claim 1 , further comprising:

determining that there is the unassigned capacity on the VTOL aircraft based at least in part on one or more signals indicating that one or more other riders have boarded the VTOL aircraft.

4. The computer-implemented method of claim 1 , wherein computing the VTOL-hold value comprises computing the VTOL-hold value based at least in part on a machine-learned model.

5. The computer-implemented method of claim 4 , wherein the machine-learned model is trained by minimizing a loss function, and wherein the machine-learned model is retrained over time with data corresponding to actual transport requests serviced.

6. The computer-implemented method of claim 1 , further comprising

accessing information associated with a state of a battery of the VIOL aircraft.

7. The computer-implemented method of claim 6 , wherein the state of the battery of the VTOL aircraft is indicative of a current state of charge of the battery.

8. The computer-implemented method of claim 1 , further comprising:

transmitting, over the one or more networks, information associated with charging the VIOL aircraft.

9. The computer-implemented method of claim 8 , wherein the information associated with charging the VTOL aircraft is indicative of an amount of time to spend charging before departure.

10. The computer-implemented method of claim 1 , wherein the demand data is indicative of at least one of: (i) a current demand for the transportation services, or (ii) an estimate of future demand for the transportation services.

11. One or more non-transitory computer-readable storage media storing computer program code that is executable by one or more processors to perform operations comprising:

accessing, over one or more networks, data defining a plurality of requests for transportation services for respective riders, origins, and destinations;

computing assignments of selected ones of the plurality of requests to trip itineraries that include transportation, at least in part, by a vertical take-off and landing (VTOL) aircraft, each of the selected requests being associated with data indicative of a threshold time to arrive at the corresponding destination;

based at least partly on there being unassigned capacity on the VIOL aircraft, accessing demand data associated with the transportation services and the threshold times;

based at least in part on the demand data and the threshold times, computing a VTOL-hold value predictive of whether another request will be received for an additional rider and the additional rider will board the VTOL aircraft within a time period such that each of the riders of selected requests will arrive at their respective destinations prior to the respective threshold times;

computing that the VTOL aircraft should wait based on the VTOL-hold value exceeding a likelihood threshold; and

after the VTOL aircraft waits in response to the VTOL-hold value, controlling the VTOL aircraft, to take-off.

12. The one or more non-transitory computer-readable storage media of claim 11 , wherein the operations further comprise:

determining that there is the unassigned capacity on the VTOL aircraft based at least in part on one or more signals indicating that one or more other riders have boarded the VIOL aircraft.

13. The one or more non-transitory computer-readable storage media of claim 11 , further comprising:

adjusting pricing of available seating associated with the unassigned capacity on the VIOL aircraft based at least in part on the demand data.

14. The one or more non-transitory computer-readable storage media of claim 11 , further comprising:

transmitting, over the one or more networks to a client device associated with the additional rider, information associated with the VTOL aircraft.

15. The one or more non-transitory computer-readable storage media of claim 11 , further comprising:

transmitting, over the one or more networks to a computing system associated with the VIOL aircraft, information associated with the additional rider.

16. The one or more non-transitory computer-readable storage media of claim 11 , wherein computing the VTOL-hold value comprises computing the VTOL-hold value based on a machine-learned model.

17. The one or more non-transitory computer-readable storage media of claim 11 , wherein the demand data is indicative of at least one of: (i) a current demand for the transportation services, or (ii) an estimate of future demand for the transportation services.

18. The one or more non-transitory computer-readable storage media of claim 11 , further comprising:

accessing information associated with a state of a battery the VIOL aircraft; and

transmitting, over the one or more networks, information associated with charging the VTOL aircraft.

19. The one or more non-transitory computer-readable storage media of claim 11 , wherein at least one rider of the selected requests is associated with a respective itinerary for the at least one rider, wherein the respective itinerary comprises: (i) at least one transportation leg comprising ground-based transportation for the at least one rider, and (ii) at least one transportation leg comprising aerial transportation via the VTOL aircraft for the at least one rider.

20. A computer system comprising:

one or more processors; and

one or more non-transitory computer-readable storage media storing computer program code that is executable by one or more processors to perform operations comprising:

accessing data defining a plurality of requests for transportation services for respective riders, origins, and destinations;

computing assignments of selected ones of the plurality of requests to trip itineraries that include transportation, at least in part, by a vertical take-off and landing (VTOL) aircraft, each of the selected requests being associated with data indicative of a threshold time to arrive at the corresponding destination;

based at least partly on there being unassigned capacity on the VTOL aircraft, accessing demand data associated with the transportation services and the threshold times;

based at least in part on the demand data and the threshold times, computing a VTOL-hold value predictive of whether another request will be received for an additional rider and the additional rider will board the VTOL aircraft within a time period such that each of the riders of selected requests will arrive at their respective destinations prior to the respective threshold times;

computing that the VTOL aircraft should wait based on the VTOL-hold value exceeding a likelihood threshold; and

after the VTOL aircraft waits in response to the VTOL-hold value, controlling the VIOL aircraft to take-off.