Systems and methods for personalizing adaptive cruise control in a vehicle

Patent metadata

Field	Value
Publication number	US-11787404-B2
Application number	US-202117387045-A
Country	US
Kind code	B2
Filing date	Jul 28, 2021
Priority date	Jul 28, 2021
Publication date	Oct 17, 2023
Grant date	Oct 17, 2023

Abstract

Systems and methods for personalizing adaptive cruise control in a vehicle are disclosed herein. One embodiment collects vehicle-following-behavior data associated with a particular driver; trains a Gaussian Process (GP) Regression model using the collected vehicle-following-behavior data to produce a set of adaptive-cruise-control (ACC) parameters pertaining to the particular driver, the set of ACC parameters modeling learned vehicle-following behavior of the particular driver; generates an acceleration command for the vehicle based, at least in part, on the set of ACC parameters; applies a predictive safety filter to the acceleration command to produce a certified acceleration command that has been vetted for safety; and controls acceleration of the vehicle automatically in accordance with the certified acceleration command to regulate a following distance between a lead vehicle and the vehicle in accordance with the learned vehicle-following behavior of the particular driver.

First claim

What is claimed is:

1. A system for personalizing adaptive cruise control in a vehicle, the system comprising:
one or more processors; and
at least one memory communicably coupled to at least one of the one or more processors and storing:
a data collection module including instructions that when executed by the one or more processors cause the one or more processors to collect vehicle-following-behavior data associated with a particular driver;
a training module including instructions that when executed by the one or more processors cause the one or more processors to train, employing nonlinear output-error (NOE) to improve training accuracy, a Gaussian Process (GP) Regression model using the collected vehicle-following-behavior data to produce a set of adaptive-cruise-control (ACC) parameters pertaining to the particular driver, the set of ACC parameters modeling learned vehicle-following behavior of the particular driver;
an ACC module including instructions that when executed by the one or more processors cause the one or more processors to:
generate an acceleration command for the vehicle based, at least in part, on the set of ACC parameters;
apply a predictive safety filter to the acceleration command to produce a certified acceleration command that has been vetted for safety; and
control acceleration of the vehicle automatically in accordance with the certified acceleration command to regulate a following distance between a lead vehicle and the vehicle in accordance with the learned vehicle-following behavior of the particular driver.

2. The system of claim 1 , wherein the vehicle-following-behavior data associated with the particular driver includes space gap, ego-vehicle speed, and lead-vehicle speed.

3. The system of claim 1 , wherein the data collection module and the training module are stored in a memory among the at least one memory that resides in one of a cloud server and an edge server and the training module includes further instructions that when executed by the one or more processors cause the one or more processors to transmit the set of ACC parameters from one of the cloud server and the edge server to the vehicle.

4. The system of claim 1 , wherein the data collection module and the training module are stored in a memory among the at least one memory that resides in an ACC system installed in the vehicle.

5. The system of claim 1 , wherein the training module includes further instructions that when executed by the one or more processors cause the one or more processors to update the set of ACC parameters pertaining to the particular driver by further training the GP Regression model based on additional collected vehicle-following-behavior data associated with the particular driver.

6. The system of claim 1 , wherein the vehicle is steered by the particular driver.

7. The system of claim 1 , wherein the vehicle is operating in an autonomous driving mode.

8. A non-transitory computer-readable medium for personalizing adaptive cruise control in a vehicle and storing instructions that when executed by one or more processors cause the one or more processors to:
collect vehicle-following-behavior data associated with a particular driver;
train, employing nonlinear output-error (NOE) to improve training accuracy, a Gaussian Process (GP) Regression model using the collected vehicle-following-behavior data to produce a set of adaptive-cruise-control (ACC) parameters pertaining to the particular driver, the set of ACC parameters modeling learned vehicle-following behavior of the particular driver;
generate an acceleration command for the vehicle based, at least in part, on the set of ACC parameters;
apply a predictive safety filter to the acceleration command to produce a certified acceleration command that has been vetted for safety; and
control acceleration of the vehicle automatically in accordance with the certified acceleration command to regulate a following distance between a lead vehicle and the vehicle in accordance with the learned vehicle-following behavior of the particular driver.

9. The non-transitory computer-readable medium of claim 8 , wherein the vehicle-following-behavior data associated with the particular driver includes space gap, ego-vehicle speed, and lead-vehicle speed.

10. The non-transitory computer-readable medium of claim 8 , wherein the instructions include further instructions to update the set of ACC parameters pertaining to the particular driver by further training the GP Regression model based on additional collected vehicle-following-behavior data associated with the particular driver.

11. A method of personalizing adaptive cruise control in a vehicle, the method comprising:
collecting vehicle-following-behavior data associated with a particular driver;
training, employing nonlinear output-error (NOE) to improve training accuracy, a Gaussian Process (GP) Regression model using the collected vehicle-following-behavior data to produce a set of adaptive-cruise-control (ACC) parameters pertaining to the particular driver, the set of ACC parameters modeling learned vehicle-following behavior of the particular driver;
generating an acceleration command for the vehicle based, at least in part, on the set of ACC parameters;
applying a predictive safety filter to the acceleration command to produce a certified acceleration command that has been vetted for safety; and
controlling acceleration of the vehicle automatically in accordance with the certified acceleration command to regulate a following distance between a lead vehicle and the vehicle in accordance with the learned vehicle-following behavior of the particular driver.

12. The method of claim 11 , wherein the vehicle-following-behavior data associated with the particular driver includes space gap, ego-vehicle speed, and lead-vehicle speed.

13. The method of claim 11 , wherein the collecting the vehicle-following-behavior data associated with the particular driver and the training the GP Regression model are performed by one of a cloud server and an edge server and the method further comprises transmitting the set of ACC parameters from one of the cloud server and the edge server to the vehicle.

14. The method of claim 11 , wherein the collecting the vehicle-following-behavior data associated with the particular driver and the training the GP Regression model are performed by an ACC system installed in the vehicle.

15. The method of claim 11 , further comprising updating the set of ACC parameters pertaining to the particular driver by further training the GP Regression model based on additional collected vehicle-following-behavior data associated with the particular driver.

16. The method of claim 13 , wherein the vehicle is steered by the particular driver.

17. The method of claim 11 , wherein the vehicle is operating in an autonomous driving mode.

Assignees

• Toyota Eng & Mfg North America

Inventors

• Wang Yanbing
• Wang Ziran
• Han Kyungtae
• Gupta Rohit
• Tiwari Prashant

Classifications

• B60W30/162 Primary

  Speed limiting therefor · CPC title

• B60W50/0097

  Predicting future conditions · CPC title

• B60W50/0098

  Details of control systems ensuring comfort, safety or stability not otherwise provided for · CPC title

• B60W60/001

  Planning or execution of driving tasks · CPC title

• B60W2050/0029

  Mathematical model of the driver · CPC title