Speed planning guidance line for mild slow down

Patent metadata

Field	Value
Publication number	US-2021200231-A1
Application number	US-201916730181-A
Country	US
Kind code	A1
Filing date	Dec 30, 2019
Priority date	Dec 30, 2019
Publication date	Jul 1, 2021
Grant date	—

Abstract

A method, apparatus, and system for planning a deceleration trajectory based on a natural deceleration profile for an autonomous driving vehicle (ADV) is disclosed. In one embodiment, in response to a request for driving in a natural deceleration mode, a current speed of the ADV is determined. A speed guideline is generated based on a predetermined natural deceleration profile associated with the ADV in view of the current speed of the ADV. A speed planning operation is performed by optimizing a total cost function based on the speed guideline to determine speeds of a plurality of trajectory points along a trajectory planned to drive the ADV. A number of control commands are generated based on the speed planning operation to control the ADV with the planned speeds along the trajectory, such that the ADV naturally slows down according to the predetermined natural deceleration profile.

First claim

What is claimed is:

1 . A computer-implemented method for operating an autonomous driving vehicle (ADV), the method comprising:
in response to a request for driving in a natural deceleration mode, determining a current speed of the ADV; generating a speed guideline based on a predetermined natural deceleration profile associated with the ADV in view of the current speed of the ADV; performing a speed planning operation by optimizing a total cost function based on the speed guideline to determine speeds of a plurality of trajectory points along a trajectory planned to drive the ADV; and generating a plurality of control commands based on the speed planning operation to control the ADV with the planned speeds along the trajectory, such that the ADV naturally slows down according to the predetermined natural deceleration profile.

2 . The method of claim 1 , wherein the predetermined natural deceleration profile was generated by allowing a sample vehicle that is of a same type as the ADV to naturally decelerate under neutral road conditions from a maximum speed to a full stop without engaging either an accelerator or a brake, and measuring and recording a time-speed relationship during the natural deceleration.

3 . The method of claim 2 , wherein the predetermined natural deceleration profile comprises a reference line that approximately represents the recorded time-speed relationship during the natural deceleration.

4 . The method of claim 1 , wherein the total cost function comprises at least a total speed cost function having at least a deviation-from-natural-deceleration cost term and an obstacle cost term when the ADV is operated in the natural deceleration mode.

5 . The method of claim 1 , wherein optimizing the total cost function comprises using Quadratic programming (QP) to minimize the total cost function.

6 . The method of claim 1 , wherein the total cost function further comprises a total path cost function to determine a total path cost for the planned trajectory.

7 . The method of claim 1 , wherein the total speed cost function comprising at least an acceleration cost term, a jerk cost term, and an obstacle cost term when the ADV is planned to be in a speed-up state.

8 . A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations of operating an autonomous driving vehicle (ADV), the operations comprising:
in response to a request for driving in a natural deceleration mode, determining a current speed of the ADV; generating a speed guideline based on a predetermined natural deceleration profile associated with the ADV in view of the current speed of the ADV; performing a speed planning operation by optimizing a total cost function based on the speed guideline to determine speeds of a plurality of trajectory points along a trajectory planned to drive the ADV; and generating a plurality of control commands based on the speed planning operation to control the ADV with the planned speeds along the trajectory, such that the ADV naturally slows down according to the predetermined natural deceleration profile.

9 . The machine-readable medium of claim 8 , wherein the predetermined natural deceleration profile was generated by allowing a sample vehicle that is of a same type as the ADV to naturally decelerate under neutral road conditions from a maximum speed to a full stop without engaging either an accelerator or a brake, and measuring and recording a time-speed relationship during the natural deceleration.

10 . The machine-readable medium of claim 9 , wherein the predetermined natural deceleration profile comprises a reference line that approximately represents the recorded time-speed relationship during the natural deceleration.

11 . The machine-readable medium of claim 8 , wherein the total cost function comprises at least a total speed cost function having at least a deviation-from-natural-deceleration cost term and an obstacle cost term when the ADV is operated in the natural deceleration mode.

12 . The machine-readable medium of claim 9 , wherein optimizing the total cost function comprises using Quadratic programming (QP) to minimize the total cost function.

13 . The machine-readable medium of claim 9 , wherein the total cost function further comprises a total path cost function to determine a total path cost for the planned trajectory.

14 . The machine-readable medium of claim 8 , wherein the total speed cost function comprising at least an acceleration cost term, a jerk cost term, and an obstacle cost term when the ADV is planned to be in a speed-up state.

15 . 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 of operating an autonomous driving vehicle (ADV), the operations including
in response to a request for driving in a natural deceleration mode, determining a current speed of the ADV,
generating a speed guideline based on a predetermined natural deceleration profile associated with the ADV in view of the current speed of the ADV,
performing a speed planning operation by optimizing a total cost function based on the speed guideline to determine speeds of a plurality of trajectory points along a trajectory planned to drive the ADV, and
generating a plurality of control commands based on the speed planning operation to control the ADV with the planned speeds along the trajectory, such that the ADV naturally slows down according to the predetermined natural deceleration profile.

16 . The system of claim 15 , wherein the predetermined natural deceleration profile was generated by allowing a sample vehicle that is of a same type as the ADV to naturally decelerate under neutral road conditions from a maximum speed to a full stop without engaging either an accelerator or a brake, and measuring and recording a time-speed relationship during the natural deceleration.

17 . The system of claim 16 , wherein the predetermined natural deceleration profile comprises a reference line that approximately represents the recorded time-speed relationship during the natural deceleration.

18 . The system of claim 15 , wherein the total cost function comprises at least a total speed cost function having at least a deviation-from-natural-deceleration cost term and an obstacle cost term when the ADV is operated in the natural deceleration mode.

19 . The system of claim 15 , wherein optimizing the total cost function comprises using Quadratic programming (QP) to minimize the total cost function.

20 . The system of claim 15 , wherein the total cost function further comprises a total path cost function to determine a total path cost for the planned trajectory.

Assignees

• Baidu Usa Llc

Inventors

• Zhu Fan

Classifications

• B60W2710/20

  Steering systems · CPC title

• B60W2520/10

  Longitudinal speed · CPC title

• B60W40/105

  Speed · CPC title

• B60W10/18

  including control of braking systems · CPC title

• B60W60/001

  Planning or execution of driving tasks · CPC title