Hybrid trip planning for autonomous vehicles

• US 10,438,493 B2
• Filed: 03/06/2017
• Issued: 10/08/2019
• Est. Priority Date: 08/24/2016
• Status: Active Grant

• Current Assignee: Uatc, LLC (Uber Technologies, Inc.)
• Original Assignee: Uber Technologies, Inc.
• Inventors: Bavar, Brett, Bartel, Emily, Zhang, Xiaodong, Nix, Molly, Sweeney, Matthew, Nagy, Bryan
• Primary Examiner(s): Black, Thomas G
• Assistant Examiner(s): Smith-Stewart, Demetra R
• Application Number:
  US15/450,268
• Publication Number:
  US 20180061242A1
• Time in Patent Office: 946 Days
• Field of Search: None
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 50/082 Selecting or switching between different modes of propelling
• CPC Class Codes: G01C 21/3407 specially adapted for specific applications
• CPC Class Codes: G01C 21/3461 Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types, segments such as motorways, toll roads, ferries
• CPC Class Codes: G01S 19/13 Receivers
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G08G 1/202 Dispatching vehicles on the basis of a location, e.g. taxi dispatching

Abstract

A hybrid trip planning system can receive transport requests from requesting users, determine pick-up and/or drop off locations from the transport request, and select available autonomous vehicles (AV) to service the transport requests. For each transport request, the planning system can identify a plurality of entry points from the pick-up location to an autonomy grid on which the AVs operate, and a plurality of exit points from the autonomy grid to the drop-off location. The planning system may determine optimal entry and/or exit points and transmit transport data to the selected AV. The transport data can provide optimal routing for a human safety driver to drive the selected AV in manual segments that are off grid, and switch the AV into an autonomous driving mode within the autonomy grid.

Claims

1. A hybrid trip planning 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 one or more processors to;

receive a transport request from a requesting user;

determine a pick-up location from the transport request;

select an autonomous vehicle (AV) to service the transport request;

identify a plurality of entry points from the pick-up location to an autonomy grid on which AVs operate;

determine a most optimal entry point from the plurality of entry points; and

transmit transport data to the selected AV, the transport data providing a first optimal route for a human safety driver to drive the selected AV in a manual mode from the pick-up location to the most optimal entry point, at which the selected AV switches into an autonomous driving mode.

2. The hybrid trip planning system of claim 1, wherein the executed instructions further cause the one or more processors to:

based on receiving the transport request, identify a set of candidate AVs within a predetermined proximity of the pick-up location;

wherein the executed instructions cause the one or more processors to select the AV to service the transport request from the set of candidate AVs.

3. The hybrid trip planning system of claim 1, wherein the transport data is executable by the selected AV to cause mapping and routing information to be generated on an interior user interface of the selected AV, the mapping and routing information providing the human safety driver with the first optimal route from the pick-up location to the most optimal entry point.

4. The hybrid trip planning system of claim 1, wherein the executed instructions further cause the one or more processors to:

determine a drop-off location from the transport request;

determine a plurality of exit points from the autonomy grid to the drop-off location; and

determine a most optimal exit point from the plurality of exit points.

5. The hybrid trip planning system of claim 4, wherein the transport data further provides a second optimal route for the human safety driver to drive the selected AV from the most optimal exit point, at which the human safety driver is to switch the AV to the manual mode to manually drive the AV to the drop-off location.

6. The hybrid trip planning system of claim 5, wherein the transport data is executable by the selected AV to cause mapping and routing information to be generated on an interior user interface of the selected AV, the mapping and routing information providing the human safety driver with the second optimal route from the most optimal exit point to the drop-off location.

7. The hybrid trip planning system of claim 5, wherein the executed instructions cause the one or more processors to determine the most optimal entry point and the most optimal exit point based on distance optimizations using a road network map.

8. The hybrid trip planning system of claim 5, wherein the executed instructions cause the one or more processors to determine the most optimal entry point and the most optimal exit point based on time optimizations using a live traffic map.

9. The hybrid trip planning system of claim 5, wherein the executed instructions further cause the one or more processors to:

perform a first optimization to determine an autonomy route for the AV through the autonomy grid from the most optimal entry point to the most optimal exit point; and

transmit route data to the selected AV, the route data being executable by a control system of the selected AV, the route data indicating the optimized autonomy route from the most optimal entry point to the most optimal exit point.

10. The hybrid trip planning system of claim 9, wherein the executed instructions further cause the one or more processors to:

detect a trigger corresponding to the human safety driver entering the autonomy grid at an alternate entry point that is different from the most optimal entry point; and

in response to the trigger, perform a second optimization to determine a new autonomy route from the alternate entry point to the most optimal exit point; and

transmit route data indicating the new autonomy route to the selected AV for execution.

11. The hybrid trip planning system of claim 4, wherein the executed instructions cause the one or more processors to establish each of the most optimal entry and exit points after a respective intersection to facilitate safe transitions between the manual mode and the autonomy mode.

12. The hybrid trip planning system of claim 1, wherein the executed instructions further cause the one or more processors to:

based on the pick-up location, determine a set of candidate vehicles to service the transport request, the set of candidate vehicle comprising a blend of non-autonomous vehicles and AVs;

wherein the executed instructions cause the one or more processors to select the selected AV to service the transport request based on the pick-up location and a drop-off location identified in the transport request fulfilling a set of criteria which enable availability of autonomous transport services.

13. The hybrid trip planning system of claim 12, wherein the set of criteria includes an autonomy distance threshold comprising a minimum distance percentage in which the selected AV must be in the autonomous mode between the pick-up location and the drop off location.

14. The hybrid trip planning system of claim 12, wherein the set of criteria includes an autonomy time threshold comprising a minimum time percentage in which the selected AV must be in the autonomous mode between the pick-up location and the drop off location.

15. The hybrid trip planning system of claim 12, wherein the set of criteria includes a manual distance threshold comprising a maximum distance percentage in which the selected AV can operate in the manual mode between the pick-up location and the drop off location.

16. The hybrid trip planning system of claim 12, wherein the set of criteria includes a manual time threshold comprising a maximum time percentage in which the selected AV can operate in the manual mode between the pick-up location and the drop off location.

17. A computer-implemented method of hybrid trip planning, the method being performed by one or more processors and comprising:

receiving a transport request from a requesting user;

determining a pick-up location from the transport request;

selecting an autonomous vehicle (AV) to service the transport request;

identifying a plurality of entry points from the pick-up location to an autonomy grid on which AVs operate;

determining a most optimal entry point from the plurality of entry points; and

transmitting transport data to the selected AV, the transport data providing a first optimal route for a human safety driver to drive the selected AV in a manual mode from the pick-up location to the most optimal entry point, at which the selected AV switches into an autonomous driving mode.

18. The method of claim 17, further comprising:

based on receiving the transport request, identifying a set of candidate AVs within a predetermined proximity of the pick-up location;

wherein the one or more processors select the AV to service the transport request from the set of candidate AVs.

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

receive a transport request from a requesting user;

determine a pick-up location from the transport request;

select an autonomous vehicle (AV) to service the transport request;

identify a plurality of entry points from the pick-up location to an autonomy grid on which AVs operate;

determine a most optimal entry point from the plurality of entry points; and

transmit transport data to the selected AV, the transport data providing a first optimal route for a human safety driver to drive the selected AV in a manual mode from the pick-up location to the most optimal entry point, at which the selected AV switches into an autonomous driving mode.

20. The non-transitory computer readable medium of claim 19, wherein the executed instructions further cause the one or more processors to:

based on receiving the transport request, identify a set of candidate AVs within a predetermined proximity of the pick-up location;

wherein the executed instructions cause the one or more processors to select the AV to service the transport request from the set of candidate AVs.