Dynamic model with actuation latency

Patent metadata

Field	Value
Publication number	US-11738771-B2
Application number	US-201916627257-A
Country	US
Kind code	B2
Filing date	Dec 20, 2019
Priority date	Dec 20, 2019
Publication date	Aug 29, 2023
Grant date	Aug 29, 2023

Abstract

A simulation of an autonomous driving vehicle (ADV) includes capturing first data that includes a control command output by an autonomous vehicle controller of the ADV, and capturing second data that includes the control command being implemented at a control unit of the ADV. The control command, for example, a steering command, a braking command, or a throttle command, is implemented by the ADV to affect movement of the ADV. A latency model is determined based on comparing the first data with the second data, where the latency model defines time delay and/or amplitude difference between the first data and the second data. The latency model is applied in a virtual driving environment.

First claim

What is claimed is:

1. A method for simulating driving of an autonomous driving vehicle (ADV), comprising:
capturing first data that includes a control command output by an autonomous vehicle controller of the ADV and timing of outputting the control command, wherein the control command was generated using an autonomous driving algorithm;
capturing second data that includes the control command being implemented at a control unit of the ADV and timing of the implementation, the control command being implemented to affect movement of the ADV; and
determining a latency model based on comparing at least timing of the first data with the second data, the latency model defining time delay between the first data and the second data and the latency model defining an amplitude difference between the first data and the second data, wherein the latency model is utilized to simulate the autonomous driving algorithm in a virtual driving environment.

2. The method of claim 1 , further comprising:
obtaining a control command from a communication bus of the ADV;
applying the latency model to the control command to generate a simulated control response of the ADV;
obtaining a sensed ADV response to the control command from the communication bus of the ADV;
determining latency adjustment based on a difference between the simulated control response and the sensed ADV response to the control command; and
updating the latency model according to the latency adjustment.

3. The method of claim 1 , wherein generating the virtual driving environment includes
generating a virtual control command to simulate movement of a virtual ADV; and
applying the latency model to the virtual control command to affect a virtual latency in the simulated movement of the virtual ADV.

4. The method of claim 1 , wherein the latency model includes one or more of the following: a curve, an equation, an equation that defines a curve, one or more coefficients, an impulse response, or a transfer function that, when applied to the first data, results in an approximation of the second data.

5. The method of claim 1 , wherein the control command is a steering command.

6. The method of claim 1 , wherein the control command is a brake command.

7. The method of claim 1 , wherein the control command is a throttle command.

8. The method of claim 1 , wherein the control unit is a steering unit, a brake unit, a throttle unit, or a motor controller.

9. The method of claim 1 , wherein capturing the second data having the control command being implemented at the control unit includes sensing an action of the control unit.

10. The method of claim 1 , wherein capturing the second data having the control command being implemented at the control unit includes recording data on a communication bus of the ADV that facilitates communication to the control unit.

11. A data processing system, comprising:
one or more processors; and
memory coupled to the one or more processors to store instructions, which when executed by the one or more processors, cause the one or more processors to perform operations comprising:
capturing first data that includes a control command output by an autonomous vehicle controller of an autonomous driving vehicle (ADV) and timing of outputting the control command, wherein the control command was generated using an autonomous driving algorithm;
capturing second data that includes the control command being implemented at a control unit of the ADV and timing of the implementation, the control command being implemented to affect movement of the ADV; and
determining a latency model based on comparing at least timing of the first data with the second data, the latency model defining time delay between the first data and the second data and the latency model defining an amplitude difference between the first data and the second data, wherein the latency model is utilized to simulate the autonomous driving algorithm in a virtual driving environment.

12. The data processing system of claim 11 , further comprising:
obtaining a control command from a communication bus of the ADV;
applying the latency model to the control command to generate a simulated control response of the ADV;
obtaining a sensed ADV response to the control command from the communication bus of the ADV;
determining latency adjustment based on a difference between the simulated control response and the sensed ADV response to the control command; and
updating the latency model according to the latency adjustment.

13. The data processing system of claim 11 , wherein generating the virtual driving environment includes
generating a virtual control command to simulate movement of a virtual ADV; and
applying the latency model to the virtual control command to affect a virtual latency in the simulated movement of the virtual ADV.

14. The data processing system of claim 11 , wherein the latency model includes one or more of the following: a curve, an equation, an equation that defines a curve, one or more coefficients, an impulse response, or a transfer function that, when applied to the first data, results in an approximation of the second data.

15. The data processing system of claim 11 , wherein capturing the second data having the control command being implemented at the control unit includes recording data on a communication bus of the ADV that facilitates communication to the control unit.

16. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations comprising:
capturing first data that includes a control command output by an autonomous vehicle controller of an autonomous driving vehicle (ADV) and timing of outputting the control command, wherein the control command was generated using an autonomous driving algorithm;
capturing second data that includes the control command being implemented at a control unit of the ADV and timing of the implementation, the control command being implemented to affect movement of the ADV; and
determining a latency model based on comparing at least timing of the first data with the second data, the latency model defining time delay between the first data and the second data and the latency model defining an amplitude difference between the first data and the second data, wherein the latency model is utilized to simulate the autonomous driving algorithm in a virtual driving environment.

17. The non-transitory machine-readable medium of claim 16 , further comprising:
obtaining a control command from a communication bus of the ADV;
applying the latency model to the control command to generate a simulated control response of the ADV;
obtaining a sensed ADV response to the control command from the communication bus of the ADV;
determining latency adjustment based on a difference between the simulated control response and the sensed ADV response to the control command; and
updating the latency model according to the latency adjustment.

18. The non-transitory machine-readable medium of claim 16 , wherein generating the virtual driving environment includes
generating a virtual control command to simulate movement of a virtual ADV; and
applying the latency model to the virtual control command to affect a virtual latency in the simulated movement of the virtual ADV.

19. The non-transitory machine-readable medium of claim 16 , wherein the latency model includes one or more of the following: a curve, an equation, an equation that defines a curve, one or more coeffici

Assignees

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

Inventors

• Jiang Shu
• Luo Qi
• Miao Jinghao
• Hu Jiangtao
• Wang Yu
• Xu Jiaxuan
• Zhou Jinyun
• Hu Kuang
• Ma Chao

Classifications

• B60W60/0011 Primary

  involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles · CPC title

• B60W10/06

  including control of combustion engines · CPC title

• B60W10/18

  including control of braking systems · CPC title

• B60W10/20

  including control of steering systems · CPC title

• G06F30/15 Primary

  Vehicle, aircraft or watercraft design · CPC title