Determining Portions of a Roadway Model Requiring Updating

• US 20160343179A1
• Filed: 08/04/2016
• Published: 11/24/2016
• 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
• Granted Patent: US 10,049,507 B2
• Time in Patent Office: Days
• 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; and

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.

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 1, 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; and

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.

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.

15. A computer-implemented method for providing data for use in determining which portions of a roadway model representing a real-world roadway require updating, the method comprising:

storing, by a data storage device carried by a self-driving road vehicle traveling on the roadway, a copy of at least part of the roadway model corresponding to a part of the roadway on which the self-driving road vehicle is travelling;

the roadway model being sufficient to enable autonomous driverless operation of the self-driving road vehicle;

obtaining, while the self-driving road vehicle is traveling on the roadway, sensor data from at least one sensor carried by the self-driving road vehicle, the sensor data portraying at least one feature of the roadway at a known position on the roadway and corresponding to a model feature in the roadway model; and

a processor carried by the self-driving road vehicle and coupled to the data storage device using the sensor data to determine discrepancy data at known positions on the roadway; and

transmitting the discrepancy data for analysis.

16. The method of claim 15, wherein using the sensor data to determine discrepancy data at known positions on the roadway comprises identifying positions on the roadway where the self-driving road vehicle experienced underperformance.

17. The method of claim 15, wherein using the sensor data to determine discrepancy data at known positions on the roadway comprises comparing the sensor data to the copy of at least part of the roadway model to determine discrepancies between the sensor data and the roadway model.

18. The method of claim 15, 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.