Method and system for determining road frictions of autonomous driving vehicles using learning-based model predictive control

Patent metadata

Field	Value
Publication number	US-10407076-B2
Application number	US-201715327036-A
Country	US
Kind code	B2
Filing date	Jan 13, 2017
Priority date	Jan 13, 2017
Publication date	Sep 10, 2019
Grant date	Sep 10, 2019

Abstract

In one embodiment, planning data is received, for example, from a planning module, to drive an autonomous driving vehicle (ADV) from a starting location and a destination location. In response, a series of control commands are generated based on the planning data, where the control commands are to be applied at different points in time from the starting location to the destination location. A cost is calculated by applying a cost function to the control commands, a first road friction to be estimated in a current trip, and a second road friction estimated during a prior trip from the starting location to the destination location. The first road friction of the current trip is estimated using the cost function in view of a prior termination cost of the prior trip, such that the cost reaches minimum.

First claim

What is claimed is:

1. A computer-implemented method for operating an autonomous driving vehicle, the method comprising:
receiving planning data to drive an autonomous driving vehicle (ADV) from a starting location to a destination location;
generating a series of control commands based on the planning data, the control commands to be applied at a plurality of points in time from the starting location to the destination location;
calculating a cost by applying a cost function to the control commands, a first road friction to be estimated in a current trip from the starting location to the destination location, and a second road friction estimated during a prior trip from the starting location to the destination location; and
estimating the first road friction of the current trip using the cost function in view of a prior termination cost of the prior trip, such that the cost reaches minimum.

2. The method of claim 1 , wherein the prior termination cost comprises a prior cost calculated at the destination location of the prior trip using the cost function.

3. The method of claim 1 , further comprising:
calculating a current termination cost for the current trip when the ADV reaches the destination location;
comparing the prior termination cost of the prior trip and the current termination cost of the current trip to determine whether a difference between the prior and current termination costs is below a predetermined threshold; and
iteratively performing generating a series of control commands and calculating a cost by applying a cost function to the control commands for a new trip from the starting location to the destination location, in response to determining that the difference is above the predetermined threshold.

4. The method of claim 3 , further comprising designating the first road friction of the current trip as a final road friction between the starting location and the destination location, in response to determining that the difference is below the predetermined threshold.

5. The method of claim 4 , wherein the final road friction is utilized to determine subsequent control commands for the ADV in a subsequent trip from the starting location to the destination location.

6. The method of claim 1 , wherein estimating the first road friction comprises:
estimating a plurality of first road segment frictions of a plurality of road segments corresponding to the plurality of points in time between the starting location and the destination location; and
determining differences between the first road segment frictions with a plurality of second road segment frictions that were estimated for corresponding points in time during the prior trip, wherein the cost is calculated based on the differences between the first road segment frictions and the second road segment frictions.

7. The method of claim 6 , wherein the cost is calculated based on a sum of the differences between the first road segment frictions and the second road segment frictions.

8. The method of claim 6 , wherein each of the first road segment frictions is estimated based on a location of the ADV and a speed of the ADV in response to a control command issued at a point in time of a corresponding road segment.

9. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising:
receiving planning data to drive an autonomous driving vehicle (ADV) from a starting location to a destination location;
generating a series of control commands based on the planning data, the control commands to be applied at a plurality of points in time from the starting location to the destination location;
calculating a cost by applying a cost function to the control commands, a first road friction to be estimated in a current trip from the starting location to the destination location, and a second road friction estimated during a prior trip from the starting location to the destination location; and
estimating the first road friction of the current trip using the cost function in view of a prior termination cost of the prior trip, such that the cost reaches minimum.

10. The machine-readable medium of claim 9 , wherein the prior termination cost comprises a prior cost calculated at the destination location of the prior trip using the cost function.

11. The machine-readable medium of claim 9 , wherein the operations further comprise:
calculating a current termination cost for the current trip when the ADV reaches the destination location;
comparing the prior termination cost of the prior trip and the current termination cost of the current trip to determine whether a difference between the prior and current termination costs is below a predetermined threshold; and
iteratively performing generating a series of control commands and calculating a cost by applying a cost function to the control commands for a new trip from the starting location to the destination location, in response to determining that the difference is above the predetermined threshold.

12. The machine-readable medium of claim 11 , wherein the operations further comprise designating the first road friction of the current trip as a final road friction between the starting location and the destination location, in response to determining that the difference is below the predetermined threshold.

13. The machine-readable medium of claim 12 , wherein the final road friction is utilized to determine subsequent control commands for the ADV in a subsequent trip from the starting location to the destination location.

14. The machine-readable medium of claim 9 , wherein estimating the first road friction comprises:
estimating a plurality of first road segment frictions of a plurality of road segments corresponding to the plurality of points in time between the starting location and the destination location; and
determining differences between the first road segment frictions with a plurality of second road segment frictions that were estimated for corresponding points in time during the prior trip, wherein the cost is calculated based on the differences between the first road segment frictions and the second road segment frictions.

15. The machine-readable medium of claim 14 , wherein the cost is calculated based on a sum of the differences between the first road segment frictions and the second road segment frictions.

16. The machine-readable medium of claim 14 , wherein each of the first road segment frictions is estimated based on a location of the ADV and a speed of the ADV in response to a control command issued at a point in time of a corresponding road segment.

17. A data processing system, comprising:
a processor; and
a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations including
receiving planning data to drive an autonomous driving vehicle (ADV) from a starting location to a destination location,
generating a series of control commands based on the planning data, the control commands to be applied at a plurality of points in time from the starting location to the destination location,
calculating a cost by applying a cost function to the control commands, a first road friction to be estimated in a current trip from the starting location to the destination location, and a second road friction estimated during a prior trip from the starting location to the destination location, and
estimating the first road friction of the current t

Assignees

• Baidu Usa Llc
• Baidu Com Times Tech Beijing Co Ltd

Inventors

• Luo Qi
• Zhu Fan
• Hu Sen
• Kong Qi
• Yu Xiang
• Zhu Zhenguang
• Pan Yuchang
• Yang Wenli
• Yang Guang

Classifications

• B60W2050/0088

  Adaptive recalibration · CPC title

• B60W2050/0028

  Mathematical models, e.g. for simulation · CPC title

• B60W2050/0024

  Variable gains · CPC title

• B60W2552/40

  Coefficient of friction · CPC title

• G01C21/3407

  specially adapted for specific applications · CPC title