Individualized risk routing for human drivers

• US 10,697,789 B2
• Filed: 05/23/2017
• Issued: 06/30/2020
• Est. Priority Date: 05/23/2017
• Status: Active Grant

• Current Assignee: Uber Technologies, Inc.
• Original Assignee: Uatc, LLC (Uber Technologies, Inc.)
• Inventors: Kislovskiy, Dima, Bradley, David McAllister
• Primary Examiner(s): Kan, Yuri
• Application Number:
  US15/602,375
• Publication Number:
  US 20180340790A1
• Time in Patent Office: 1,134 Days
• CPC Class Codes: G01C 21/3484 Personalized, e.g. from learned user behaviour or user-defined profiles
• CPC Class Codes: G01C 21/3629 Guidance using speech or audio output, e.g. text-to-speech text to speech systems per se G10L13/00

Abstract

A transportation management system can maintain a set of driver logs for drivers operating throughout a given region, where each driver log indicates driving characteristics of a respective driver. The system can determine a destination for the respective driver operating a vehicle from an initial location to the destination, and determine a set of routes between the initial location and the destination. Based at least in part on the driving characteristics of the respective driver, the system can determine an individualized risk value for the respective driver for each route of the set of routes, and select an optimal route from the set of routes based, at least in part, on the individualized risk value for each route.

Claims

1. A transportation management system for a given region, comprising:

one more processors; and

one or more memory resources storing instructions that, when executed by the one or more processors, cause the transportation management system to;

maintain a set of driver logs for drivers operating throughout the given region, each driver log indicating driving characteristics of a respective driver;

receive a transport request from a rider;

select a human-driven vehicle type for servicing the transport request from a variety of vehicle types including the human-driven vehicle type and an autonomous vehicle type, wherein the human-driven vehicle type is selected based on respective expected usage costs associated with each variety of the vehicle types;

determine a destination for the respective driver operating a vehicle from an initial location to the destination based on the transport request from the rider;

determine a set of routes between the initial location and the destination;

based at least on the driving characteristics of the respective driver, determine respective individualized risk values for the respective driver for each route of the set of routes, wherein the driving characteristics of the respective driver include ride-share data associated with the respective driver; and

select an optimal route from the set of routes based at least on the respective individualized risk value and respective expected usage costs for each route.

2. The transportation management system of claim 1, wherein the executed instructions further cause the transportation management system to:

determine a generalized risk value for each route of the set of routes;

wherein the executed instructions cause the transportation management system to further select the optimal route from the set of routes based on the generalized risk value for each route.

3. The transportation management system of claim 1, wherein the respective driver comprises an operator of at least one of aerial vehicles, surface vehicles, remotely operated vehicles, or submersible vehicles, and wherein the driver log for the respective driver indicates the driving characteristics of the respective driver corresponds to each of the at least one of the aerial vehicles, surface vehicles, remotely operated vehicles, or submersible vehicles.

4. The transportation management system of claim 1, wherein the executed instructions further cause the transportation management system to:

provide turn-by-turn directions to the destination along the optimal route to a driver device of the respective driver.

5. The transportation management system of claim 1, wherein each of the set of driver logs further indicates at least one of an on-duty time, a driver safety ranking, a driver reaction time indicator, and data corresponding to a vehicle of the respective driver.

6. The transportation management system of claim 5, wherein at least one of the driver safety ranking or the driver reaction time indicator is determined by receiving sensor data from a driver device of the respective driver.

7. The transportation management system of claim 6, wherein the sensor data comprises at least one of image data, audio data, or inertial data from the driver device.

8. The transportation management system of claim 5, wherein the data corresponding to the vehicle of the respective driver indicates an amount of time since the vehicle of the respective driver was last serviced.

9. The transportation management system of claim 5, wherein the data corresponding to the vehicle of the respective driver indicates at least one of a make, a model, a manufacture year, an options package, or a safety rating of the vehicle of the respective driver.

10. The transportation management system of claim 2, wherein the executed instructions further cause the transportation management system to:

manage an on-demand transportation service by receiving transport requests from requesting users and matching the requesting users with servicing drivers.

11. The transportation management system of claim 10, wherein the optimal route comprises a route from a pick-up location to a destination for a requesting user of the on-demand transportation service, and wherein the respective driver transports the requesting user in connection with the on-demand transportation service.

12. The transportation management system of claim 10, wherein the executed instructions further cause the transportation management system to:

collect historical data identifying failed rides for the on-demand transportation service, each failed ride corresponding to a determined route and an unplanned detour from the determined route; and

compute an aggregate risk quantity for each respective route of the set of routes by determining a failure probability for the respective route based on the historical data across the respective route.

13. The transportation management system of claim 12, wherein the executed instructions cause the transportation management system to further determine the generalized risk value for the each respective route of the set of routes based on a weighted sum between the failure probability and a set of fractional risk quantities of respective path segments for the respective route.

14. The transportation management system of claim 12, wherein the executed instructions cause the transportation management system to further determine the respective individualized risk values for the respective driver based on a weighted sum between the failure probability and the driver characteristics of the respective driver.

19. The transportation management system or claim 1, wherein the ride-share data comprises at least one of an on-duty time for the respective driver or a ride-share rating for the respective driver from one or more previous passengers.

20. The transportation management system or claim 1, wherein the human-driven vehicle type is selected for servicing the transport request further based on fleet utilization data that correlates geographic areas with respective preferred vehicle types.

15. A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:

maintain a set of driver logs for drivers operating throughout a given region, each driver log indicating driving characteristics of a respective driver;

receive a transport request from a rider;

select a human-driven vehicle type for servicing the transport request from a variety of vehicle types including the human-driven vehicle type and an autonomous vehicle type, wherein the human-driven vehicle type is selected based on respective expected usage costs associated with each variety of the vehicle types;

determine a destination for the respective driver operating a vehicle from an initial location to the destination based on the transport request from the rider;

determine a set of routes between the initial location and the destination;

based at least on the driving characteristics of the respective driver, determine respective individualized risk values for the respective driver for each route of the set of routes, wherein the driving characteristics of the respective driver include ride-share data associated with the respective driver; and

select an optimal route from the set of routes based at least on the respective individualized risk values and respective expected usage costs for each route.

16. The non-transitory computer readable medium of claim 15, wherein the executed instructions further cause the one or more processors to:

determine a generalized risk value for each route of the set of routes;

wherein the executed instructions cause the one or more processors to further select the optimal route from the set of routes based on the generalized risk value for each route.

17. The non-transitory computer readable medium of claim 15, wherein the respective driver comprises an operator of at least one of aerial vehicles, surface vehicles, remotely operated vehicles, or submersible vehicles, and wherein the driver log for the respective driver indicates the driving characteristics of the respective driver corresponds to each of the at least one of the aerial vehicles, surface vehicles, remotely operated vehicles, or submersible vehicles.

18. A computer-implemented method of facilitating an on-demand transportation service, the method being performed by one or more processors and comprising:

maintaining a set of driver logs for drivers operating throughout a given region, each driver log indicating driving characteristics of a respective driver;

receiving a transport request from a rider;

selecting a human-driven vehicle type for servicing the transport request from a variety of vehicle types including the human-driven vehicle type and an autonomous vehicle type, wherein the human-driven vehicle type is selected based on respective expected usage costs associated with each variety of the vehicle types;

determining a destination for the respective driver operating a vehicle from an initial location to the destination based on the transport request from the rider;

determining a set of routes between the initial location and the destination;

based at least in part on the driving characteristics of the respective driver, determining respective individualized risk values for the respective driver for each route of the set of routes, wherein the driving characteristics of the respective driver include ride-share data associated with the respective driver; and

selecting an optimal route from the set of routes based at least on the respective individualized risk values and respective expected usage costs for each route.