Speed control parameter estimation method for autonomous driving vehicles

Patent metadata

Field	Value
Publication number	US-10442435-B2
Application number	US-201615379345-A
Country	US
Kind code	B2
Filing date	Dec 14, 2016
Priority date	Dec 14, 2016
Publication date	Oct 15, 2019
Grant date	Oct 15, 2019

Abstract

In one embodiment, when speed control command (e.g., throttle, brake commands) is issued based on a target speed, a first feedback parameters is determined based on an expected speed and an actual speed of the ADV in response to the speed control command. A second feedback parameter is determined by applying a speed control parameter adjustment (SCPA) model to a set of input parameters that are captured or measured at the point in time. The set of input parameters represents a driving environment of the ADV at the point in time. One or more control parameters of a speed controller of the ADV is adjusted based on the first feedback parameter and the second feedback parameter, where the speed controller is configured to generate and issue speed control commands. Subsequent speed control commands can be generated based on the adjusted speed control parameters of the speed controller.

First claim

What is claimed is:

1. A computer-implemented method for operating an autonomous driving vehicle (ADV), the method comprising:
issuing, by a speed controller, a speed control command in response to receiving a first target speed;
determining a first feedback parameter as a difference between an expected speed and an actual speed of the ADV in response to the speed control command, wherein the expected speed is calculated by a powertrain reference model based on the first target speed, wherein the powertrain reference model is created offline based on a plurality of design characteristics of the ADV;
determining a second feedback parameter by applying a machine learning model trained offline based on driving statistics captured from a variety of vehicles to a set of input parameters that are obtained in real-time, the set of input parameters representing a driving environment of the ADV at a point in time;
dynamically adjusting a control parameter of the speed controller based on the first feedback parameter, the second feedback parameter, and the speed control command as a third feedback parameter, wherein each of the first feedback parameter, the second feedback parameter, and the third feedback parameter is associated with an individual weight factor; and
generating a subsequent speed control command based on the adjusted control parameter of the speed controller for a subsequent command cycle in response to receiving a second target speed.

2. The method of claim 1 wherein the speed control command comprises a throttle percentage of a maximum throttle command value.

3. The method of claim 1 , wherein the plurality of design characteristics of the ADV includes engine, transmission, and driveline parameters associated with the ADV.

4. The method of claim 1 , wherein the set of input parameters comprises at least one of a weather condition, road condition, wind resistance, map location, vehicle weight, or tire pressure measured at the point in time.

5. The method of claim 4 , wherein the set of input parameters further comprises a user driving preference of a passenger riding in the ADV at the point in time.

6. 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:
issuing, by a speed controller, a speed control command in response to receiving a first target speed;
determining a first feedback parameter as a difference between an expected speed and an actual speed of the ADV in response to the speed control command, wherein the expected speed is calculated by a powertrain reference model based on the first target speed, wherein the powertrain reference model is created offline based on a plurality of design characteristics of the ADV;
determining a second feedback parameter by applying a machine learning model trained offline based on driving statistics captured from a variety of vehicles to a set of input parameters that are obtained in real-time, the set of input parameters representing a driving environment of the ADV at a point in time;
dynamically adjusting a control parameter of the speed controller based on the first feedback parameter, the second feedback parameter, and the speed control command as a third feedback parameter, wherein each of the first feedback parameter, the second feedback parameter, and the third feedback parameter is associated with an individual weight factor; and
generating a subsequent speed control command based on the adjusted control parameter of the speed controller for a subsequent command cycle in response to receiving a second target speed.

7. The machine-readable medium of claim 6 wherein the speed control command comprises a throttle percentage of a maximum throttle command value.

8. The machine-readable medium of claim 6 , wherein the plurality of design characteristics of the ADV includes engine, transmission, and driveline parameters associated with the ADV.

9. The machine-readable medium of claim 6 , wherein the set of input parameters comprises at least one of a weather condition, road condition, wind resistance, map location, vehicle weight, or tire pressure measured at the point in time.

10. The machine-readable medium of claim 9 , wherein the set of input parameters further comprises a user driving preference of a passenger riding in the ADV at the point in time.

11. 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 issuing, by a speed controller, a speed control command in response to
receiving a first target speed;
determining a first feedback parameter as a difference between an expected speed and an actual speed of the ADV in response to the speed control command, wherein the expected speed is calculated by a powertrain reference model based on the first target speed, wherein the powertrain reference model is created offline based on a plurality of design characteristics of the ADV;
determining a second feedback parameter by applying a machine learning model trained offline based on driving statistics captured from a variety of vehicles to a set of input parameters that are obtained in real-time, the set of input parameters representing a driving environment of the ADV at a point in time;
dynamically adjusting a control parameter of the speed controller based on the first feedback parameter, the second feedback parameter, and the speed control command as a third feedback parameter, wherein each of the first feedback parameter, the second feedback parameter, and the third feedback parameter is associated with an individual weight factor; and
generating a subsequent speed control command based on the adjusted control parameter of the speed controller for a subsequent command cycle in response to receiving a second target speed.

12. The system of claim 11 , wherein the speed control command comprises a throttle percentage of a maximum throttle command value.

13. The system of claim 11 , wherein the plurality of design characteristics of the ADV includes engine, transmission, and driveline parameters associated with the ADV.

14. The system of claim 11 , wherein the set of input parameters comprises at least one of a weather condition, road condition, wind resistance, map location, vehicle weight, or tire pressure measured at the point in time.

15. The system of claim 14 , wherein the set of input parameters further comprises a user driving preference of a passenger riding in the ADV at the point in time.

16. The system of claim 11 , wherein the adjusted control parameter is one of a plurality of control parameters of the speed controller, wherein the plurality of control parameters are configured offline based on empirical driving statistics including vehicle speeds, vehicle accelerations, and road friction captured at different points in time and under various driving conditions, and wherein the plurality of control parameters include a proportional coefficient, an integral coefficient, and a derivative coefficient of the speed controller.

17. The system of claim 11 , wherein the trained machine learning module is to adjust the speed controller to adapt to differences of the ADV from the variety of vehicles and to adapt to deterioration of the ADV based on the input parameters captured at real-time.

18. The method of claim 1 , wherein the adjusted control parameter is one of a plurality of control parameter

Assignees

• Baidu Usa Llc

Inventors

• Luo Qi
• Zhu Fan
• Hu Sen
• Kong Qi
• Yu Xiang
• Yang Guang

Classifications

• B60W2555/20

  Ambient conditions, e.g. wind or rain · CPC title

• B60W2554/00

  Input parameters relating to objects · CPC title

• B60W2552/00

  Input parameters relating to infrastructure · CPC title

• B60W2540/043

  Identity of occupants · CPC title

• B60W2556/50

  of positioning data, e.g. GPS [Global Positioning System] data · CPC title