Deploying human-driven vehicles for autonomous vehicle routing and localization map updating

• US 10,186,156 B2
• Filed: 05/25/2017
• Issued: 01/22/2019
• Est. Priority Date: 05/25/2017
• Status: Active Grant

• Current Assignee: Uatc, LLC (Uber Technologies, Inc.)
• Original Assignee: Uber Technologies, Inc.
• Inventors: Sweeney, Matthew, Levandowski, Anthony
• Primary Examiner(s): Lee, Tyler J
• Application Number:
  US15/604,979
• Publication Number:
  US 20180342165A1
• Time in Patent Office: 607 Days
• CPC Class Codes: G01C 21/3407 specially adapted for specific applications
• CPC Class Codes: G06Q 10/06311 Scheduling, planning or task assignment for a person or group
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0133 for classifying traffic situation
• CPC Class Codes: G08G 1/096725 where the received information generates an automatic action on the vehicle control
• CPC Class Codes: G08G 1/096775 where the origin of the information is a central station
• CPC Class Codes: G08G 1/096827 where the route is computed onboard
• CPC Class Codes: G08G 1/202 Dispatching vehicles on the basis of a location, e.g. taxi dispatching

Abstract

An on-demand transport system can manage an on-demand transportation service for a given region by matching requesting users with drivers and the AVs, where the AVs utilize localization maps and live sensor data to autonomously operate throughout the given region. The transport system can identify a local anomaly within the given region that affects AV performance. The transport system can transmit a routing invitation a driver to provide feedback corresponding to the local anomaly. Based on feedback data received from the driver, the transport system can transmit an update to AVs intersecting the local anomaly to enable the intersecting AVs to resolve the local anomaly.

Claims

1. An on-demand transport facilitation system comprising:

one or more processors;

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

manage an on-demand transportation service for a given region by matching requesting users with drivers and autonomous vehicles (AVs), the AVs utilizing localization maps and live sensor data to autonomously operate throughout the given region;

identify a local anomaly within the given region, the local anomaly affecting AV performance;

transmit a routing invitation to one or more of the drivers, via an executing driver application on a computing device of each of the one or more drivers, to provide feedback corresponding to the local anomaly;

receive an acceptance to the routing invitation from a selected driver of the one or more drivers;

receive feedback data from the selected driver to resolve the local anomaly; and

based on the feedback data, transmit an update to AVs intersecting the local anomaly to enable the intersecting AVs to resolve the local anomaly.

2. The on-demand transport facilitation system of claim 1, wherein the feedback data comprises recorded sensor data from the selected driver, and wherein the executed instructions further cause the one or more processors to:

determine, from the recorded sensor data, that a localization map corresponding to the local anomaly comprises stale data; and

update the localization map with the recorded sensor data;

wherein the update transmitted to the intersecting AVs comprises the updated localization map.

3. The on-demand transport facilitation system of claim 2, wherein the executed instructions cause the one or more processors to update the localization map by extracting new data from the recorded sensor data and patching the stale data of the localization map with the new data.

4. The on-demand transport facilitation system of claim 3, wherein the new data comprises a new static object.

5. The on-demand transport facilitation system of claim 2, wherein the stale data in the localization map corresponds to at least one of a road construction zone, a road hazard, or an occlusion.

6. The on-demand transport facilitation system of claim 1, wherein the executed instructions further cause the one or more processors to:

receive telemetry data from the AVs operating throughout the given region, the telemetry data indicating the local anomaly.

7. The on-demand transport facilitation system of claim 1, wherein the executed instructions further cause the one or more processors to:

receive teleassistance requests from AVs encountering the local anomaly, the teleassistance requests indicating stuck states for the encountering AVs due to the local anomaly;

wherein the executed instructions cause the one or more processors to identify the local anomaly based on the received teleassistance requests.

8. The on-demand transport facilitation system of claim 1, wherein the executed instructions further cause the one or more processors to:

store a driver profile for each of the drivers, the driver profile indicating sensor resources possessed by the driver.

9. The on-demand transport facilitation system of claim 8, wherein the executed instructions cause the on-demand transport facilitation system to transmit the routing invitation to the one or more drivers based on (i) at least one of distance or time from a current location of each of the one or more drivers to local anomaly, and (ii) the sensor resources of each of the one or more drivers as indicating by the driver profiles.

10. The on-demand transport facilitation system of claim 8, wherein the sensor resources included in each of the driver profiles indicates whether a corresponding driver possesses sensor data recording equipment comprising at least one of a LIDAR sensor or a stereoscopic camera.

11. The on-demand transport facilitation system of claim 1, wherein the executed instructions further cause the one or more processors to:

transmit a status query to the selected driver, the status query to determine whether a road segment corresponding to the local anomaly is passable;

wherein the received feedback data comprises a query response from the driver indicating whether the road segment is passable.

12. The on-demand transport facilitation system of claim 1, wherein the executed instructions further cause the one or more processors to:

access a third party resource indicating planned road projects for the given region;

wherein the executed instructions cause the one or more processors to identify the local anomaly based on the planned road projects for the given region.

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

manage an on-demand transportation service for a given region by matching requesting users with drivers and autonomous vehicles (AVs), the AVs utilizing localization maps and live sensor data to autonomously operate throughout the given region;

identify a local anomaly within the given region, the local anomaly affecting AV performance;

transmit a routing invitation to one or more of the drivers, via an executing driver application on a computing device of each the one or more drivers, to provide feedback corresponding to the local anomaly;

receive an acceptance to the routing invitation from a selected driver of the one or more drivers;

receive feedback data from the selected driver to resolve the local anomaly; and

based on the feedback data, transmit an update to AVs intersecting the local anomaly to enable the intersecting AVs to resolve the local anomaly.

14. The non-transitory computer readable medium of claim 13, wherein the feedback data comprises recorded sensor data from the selected driver, wherein the executed instructions further cause the one or more processors to:

determine, from the recorded sensor data, that a localization map corresponding to the local anomaly comprises stale data; and

update the localization map with the recorded sensor data; and

wherein the update transmitted to the intersecting AVs comprises the updated localization map.

15. The non-transitory computer readable medium of claim 14, wherein the executed instructions cause the one or more processors to update the localization map by extracting new data from the recorded sensor data and patching the stale data of the localization map with the new data.

16. The non-transitory computer readable medium of claim 15, wherein the new data comprises a new static object.

17. The non-transitory computer readable medium of claim 14, wherein the stale data in the localization map corresponds to at least one of a road construction zone, a road hazard, or an occlusion.

18. A computer-implemented method of facilitating transportation by autonomous vehicles (AVs), the method being performed by one or more processors and comprising:

managing an on-demand transportation service for a given region by matching requesting users with drivers and the AVs, the AVs utilizing localization maps and live sensor data to autonomously operate throughout the given region;

identifying a local anomaly within the given region, the local anomaly affecting AV performance;

transmitting a routing invitation to one or more of the drivers, via an executing driver application on a computing device of each of the one or more drivers, to provide feedback corresponding to the local anomaly;

receiving an acceptance to the routing invitation from a selected driver of the one or more drivers;

receiving feedback data from the selected driver to resolve the local anomaly; and

based on the feedback data, transmitting an update to AVs intersecting the local anomaly to enable the intersecting AVs to resolve the local anomaly.

19. The method of claim 18, wherein the feedback data comprises recorded sensor data from the selected driver, the method further comprising:

determining, from the recorded sensor data, that a localization map corresponding to the local anomaly comprises stale data; and

updating the localization map with the recorded sensor data; and

wherein the update transmitted to the intersecting AVs comprises the updated localization map.

20. The method of claim 19, wherein updating the localization map comprises extracting new data from the recorded sensor data and patching the stale data of the localization map with the new data.