Non-trip risk matching and routing for on-demand transportation services
An on-demand transportation management system can receive transport requests in connection with an on-demand transportation service, each transport request indicating a start location and a destination. The system can determine a set of candidate vehicles to service each transport request, and can further determine a non-trip risk value for servicing the transport request. The system may then select an optimal vehicle in the set of candidate vehicles based at least in part on the non-trip risk value.
1. An on-demand transportation management system comprising:
one or more processors; and
one or more memory resources storing instructions that, when executed by the one or more processors, cause the on-demand transportation management system to perform operations comprising:
receiving a transport request in connection with an on-demand transportation service, the transport request indicating a start location and a destination;
determining a set of candidate vehicles available to service the transport request, wherein the set of candidate vehicles comprises one or more autonomous vehicles;
determining a non-trip risk value for servicing the transport request based at least in part on a type of the start location or a type of the destination, wherein the non-trip risk value is indicative of an impact that the type of the start location or the type of the destination has on the autonomous performance of an autonomous vehicle of the one or more autonomous vehicles;
selecting an optimal vehicle in the set of candidate vehicles based at least in part on the non-trip risk value; and
outputting data instructing the optimal vehicle to service the transport request, the data indicating at least the start location associated with the transport request, wherein the optimal vehicle is an autonomous vehicle configured to autonomously travel to the start location associated with the transport request.
2. The on-demand transportation management system of claim 1 , wherein the operations further comprise:
collecting historical non-trip risk data corresponding to vehicles operating within a given region;
wherein the non-trip risk value is based at least in part on the historical non-trip risk data.
3. The on-demand transportation management system of claim 2 , wherein the historical non-trip risk data identify harmful events affecting requesting users in connection with the on-demand transportation service, but external to actual trips servicing the requesting users between pick-up locations and destinations.
4. The on-demand transportation management system of claim 3 , wherein the historical non-trip risk data further correlates wait time by requesting users in changing conditions.
5. The on-demand transportation management system of claim 4 , wherein the changing conditions correspond to at least one of inclement weather, a current event, or a predicted event.
6. The on-demand transportation management system of claim 1 , wherein the impact that the type of the start location or the type of the destination has on the autonomous performance of the autonomous vehicle comprises an affect on a time to reach the destination by the autonomous vehicle.
7. The on-demand transportation management system of claim 1 , wherein:
the autonomous vehicle is a first candidate vehicle;
the non-trip risk value is a first non-trip risk value; and
the operations further comprise determining a second non-trip risk value for servicing the transport request based at least in part on the type of the start location or the type of the destination, the second non-trip risk value being indicative of an impact that the type of the start location or the type of the destination has on at least one of:
the ability of a second candidate vehicle of the set of candidate vehicles to service the transport request, or
a time to reach the destination by the second candidate vehicle.
8. The on-demand transportation management system of claim 7 , wherein selecting the optimal vehicle in the set of candidate vehicles based at least in part on the non-trip risk value comprises comparing the first non-trip risk value and the second non-trip risk value.
9. The on-demand transportation management system of claim 8 , wherein the second candidate vehicle is a human-driven vehicle.
10. The on-demand transportation management system of claim 1 , wherein determining the non-trip risk value comprises determining an inferred risk for a trip based at least in part on freight to be transported.
11. A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
receiving a transport request in connection with an on-demand transportation service, the transport request indicating a start location and a destination;
determining a set of candidate vehicles available to service the transport request, wherein the set of candidate vehicles comprises one or more autonomous vehicles;
determining a non-trip risk value for servicing the transport request based at least in part on a type of the start location or a type of the destination, wherein the non-trip risk value is indicative of an impact that the type of the start location or the type of the destination has on the autonomous performance of an autonomous vehicle of the one or more autonomous vehicles;
selecting an optimal vehicle in the set of candidate vehicles based at least in part on the non-trip risk value; and
outputting data instructing the optimal vehicle to service the transport request, the data indicating at least the start location associated with the transport request, wherein the optimal vehicle is an autonomous vehicle configured to autonomously travel to the start location associated with the transport request.
12. The non-transitory computer readable medium of claim 11 , wherein the operations further comprise:
collecting historical non-trip risk data corresponding to vehicles operating within a given region;
wherein the non-trip risk value is based at least in part on the historical non-trip risk data.
13. The non-transitory computer readable medium of claim 12 , wherein the historical non-trip risk data identify harmful events affecting requesting users in connection with the on-demand transportation service, but external to actual trips servicing the requesting users between pick-up locations and destinations.
14. The non-transitory computer readable medium of claim 13 , wherein the historical non-trip risk data further correlates wait time by requesting users in changing conditions.
15. The non-transitory computer readable medium of claim 14 , wherein the changing conditions correspond to at least one of inclement weather, a current event, or a predicted event.
16. The non-transitory computer readable medium of claim 11 , wherein the impact that the type of the start location or the type of the destination has on the autonomous performance of the autonomous vehicle comprises an affect on a time to reach the destination by the autonomous vehicle.
17. The non-transitory computer readable medium of claim 11 , wherein:
the autonomous vehicle is a first candidate vehicle;
the non-trip risk value is a first non-trip risk value; and
the operations further comprise determining a second non-trip risk value for servicing the transport request based at least in part on the type of the start location or the type of the destination, the second non-trip risk value being indicative of an impact that the type of the start location or the type of the destination has on at least one of:
the ability of a second candidate vehicle of the set of candidate vehicles to service the transport request, or
a time to reach the destination by the second candidate vehicle.
18. The non-transitory computer readable medium of claim 17 , wherein selecting the optimal vehicle in the set of candidate vehicles based at least in part on the non-trip risk value comprises comparing the first non-trip risk value and the second non-trip risk value.
19. The non-transitory computer readable medium of claim 18 , wherein the second candidate vehicle is a human-driven vehicle.
20. A computer-implemented method of facilitating an on-demand transportation service, the method being performed by one or more processors and comprising:
receiving a transport request in connection with an on-demand transportation service, the transport request indicating a start location and a destination;
determining a set of candidate vehicles available to service the transport request, wherein the set of candidate vehicles comprises one or more autonomous vehicles;
determining a non-trip risk value for servicing the transport request based at least in part on a type of the start location or a type of the destination, wherein the non-trip risk value is indicative of an impact that the type of the start location or the type of the destination has on the autonomous performance of an autonomous vehicle of the one or more autonomous vehicles;
selecting an optimal vehicle in the set of candidate vehicles based at least in part on the non-trip risk value; and
outputting data instructing the optimal vehicle to service the transport request, the data indicating at least the start location associated with the transport request, wherein the optimal vehicle is an autonomous vehicle configured to autonomously travel to the start location associated with the transport request.
21. The computer-implemented method of claim 20 , wherein:
the autonomous vehicle is a first candidate vehicle;
the non-trip risk value is a first non-trip risk value; and
the operations further comprise determining a second non-trip risk value for servicing the transport request based at least in part on the type of the start location or the type of the destination, the second non-trip risk value being indicative of an impact that the type of the start location or the type of the destination has on at least one of:
the ability of a second candidate vehicle of the set of candidate vehicles to service the transport request, or
a time to reach the destination by the second candidate vehicle.
22. The computer-implemented method of claim 20 , wherein the type of start location or destination location comprises a hospital location.