Determining portions of a roadway model requiring updating

• US 9,437,053 B2
• Filed: 01/05/2015
• Issued: 09/06/2016
• Est. Priority Date: 01/06/2014
• Status: Active Grant

• Current Assignee: Dynamic Map Platform North America, Inc. (Dynamic Map Platform Co., Ltd.)
• Original Assignee: GeoDigital International Inc.
• Inventors: Jenkins, Alastair Nigel, Pollock, Richard James
• Primary Examiner(s): TARCZA, THOMAS H
• Assistant Examiner(s): Lee, Tyler J
• Application Number:
  US14/589,616
• Publication Number:
  US 20150193988A1
• Time in Patent Office: 610 Days
• Field of Search: 701/31.5, 701 23- 36
• US Class Current: 1/1
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G09B 29/106 using electronic means

Abstract

A computer-implemented method for determining which portions of a roadway model used by self-driving road vehicles require updating uses discrepancy data derived from the sensors of a plurality of self-driving road vehicles. The discrepancy data may indicate discrepancies between the sensor data and the roadway model, or may indicate portions of the roadway where a self-driving road vehicle underperformed. The discrepancy data is aggregated, and the aggregated discrepancy data is used to identify, as the portions of the roadway model which require updating, those portions of the roadway model corresponding to portions of the roadway for which the aggregated discrepancy data exceeds a threshold.

Claims

1. A computer-implemented method for determining which portions of a roadway model representing a real-world roadway require updating, the method comprising:

maintaining a roadway model of the real-world roadway, the roadway model being sufficient to enable autonomous driverless operation of a self-driving road vehicle;

receiving, from a plurality of self-driving road vehicles on the roadway, discrepancy data for known positions on the roadway;

aggregating the discrepancy data into aggregated discrepancy data, wherein the aggregated discrepancy data comprises, for at least some portions of the roadway, discrepancy data from a plurality of individual self-driving road vehicles;

using the aggregated discrepancy data to identify, as the portions of the roadway model which require updating, those portions of the roadway model corresponding to portions of the roadway for which the aggregated discrepancy data exceeds a threshold; and

responsive to identifying the portions of the roadway model which require updating, doing at least one of;

dispatching one or more survey vehicles to the portions of the roadway for which the aggregated discrepancy data exceeds the threshold; and

modifying an existing plan for updating the roadway model to include the portions of the roadway for which the aggregated discrepancy data exceeds the threshold.

2. The method of claim 1, wherein the discrepancy data identifies positions on the roadway where the self-driving road vehicles experienced underperformance.

3. The method of claim 1, wherein the discrepancy data represents discrepancies, at known positions on the roadway, between information in the roadway model and sensor data from at least one sensor carried by each self-driving road vehicle.

4. The method of claim 3, wherein the sensor data includes at least one of image data, radar data, LIDAR data, GNSS data, INS data, IMU data, accelerometer data, inclinometer data, vibration sensor data, compass data, magnetometer data, color sensor data, weather sensor data and sound data.

5. The method of claim 1, wherein the threshold is a predetermined, fixed threshold.

6. The method of claim 1, wherein the threshold is an adaptive threshold.

7. The method of claim 1, wherein the threshold is generated by applying a statistical model to the discrepancy data.

8. A computer-implemented method for determining which portions of a roadway model representing a real-world roadway require updating, the method comprising:

maintaining a roadway model of the real-world roadway, the roadway model being sufficient to enable autonomous driverless operation of a self-driving road vehicle;

receiving, from a plurality of self-driving road vehicles on the roadway, from at least one sensor carried by each self-driving road vehicle, sensor data associated with known positions on the roadway, the sensor data representing at least one feature of the roadway corresponding to a model feature in the roadway model;

using the sensor data to determine discrepancy data;

aggregating the discrepancy data into aggregated discrepancy data, wherein the aggregated discrepancy data comprises, for at least some portions of the roadway, discrepancy data from a plurality of individual self-driving road vehicles;

using the aggregated discrepancy data to identify, as the portions of the roadway model which require updating, those portions of the roadway model corresponding to portions of the roadway for which the aggregated discrepancy data exceeds a threshold; and

responsive to identifying the portions of the roadway model which require updating, doing at least one of;

dispatching one or more survey vehicles to the portions of the roadway for which the aggregated discrepancy data exceeds the threshold; and

modifying an existing plan for updating the roadway model to include the portions of the roadway for which the aggregated discrepancy data exceeds the threshold.

9. The method of claim 8, wherein the discrepancy data identifies positions on the roadway where the self-driving road vehicles experienced underperformance.

10. The method of claim 8, wherein the discrepancy data represents discrepancies, at known positions on the roadway, between information in the roadway model and sensor data from the at least one sensor carried by each self-driving road vehicle.

11. The method of claim 8, wherein the sensor data includes at least one of image data, radar data, LIDAR data, GNSS data, INS data, IMU data, accelerometer data, inclinometer data, vibration sensor data, compass data, magnetometer data, color sensor data, weather sensor data and sound data.

12. The method of claim 8, wherein the threshold is a predetermined, fixed threshold.

13. The method of claim 8, wherein the threshold is an adaptive threshold.

14. The method of claim 8, wherein the threshold is generated by applying a statistical model to the discrepancy data.