ADAPTIVE CRUISE CONTROL SYSTEM AND METHOD FOR VEHICLE

• US 20140012479A1
• Filed: 12/30/2010
• Published: 01/09/2014
• Est. Priority Date: 12/30/2010
• Status: Active Grant

• Current Assignee: Institute Of Automation Chinese Academy Of Sciences (Chinese Academy of Sciences)
• Original Assignee: Institute Of Automation Chinese Academy Of Sciences (Chinese Academy of Sciences)
• Inventors: Zhao, Dongbin
• Granted Patent: US 9,266,533 B2
• Time in Patent Office: Days
• US Class Current: 701/96
• CPC Class Codes: B60K 31/0008 including means for detecting potential obstacles in vehicle path
• CPC Class Codes: B60W 10/04 including control of propulsion units
• CPC Class Codes: B60W 10/06 including control of combustion engines
• CPC Class Codes: B60W 10/18 including control of braking systems
• CPC Class Codes: B60W 10/184 with wheel brakes
• CPC Class Codes: B60W 2050/0029 Mathematical model of the driver
• CPC Class Codes: B60W 2050/0062 Adapting control system settings
• CPC Class Codes: B60W 2556/00 Input parameters relating to data
• CPC Class Codes: B60W 2556/10 Historical data
• CPC Class Codes: B60W 2556/45 External transmission of data to or from the vehicle
• CPC Class Codes: B60W 30/143 Speed control B60W30/16 takes precedence
• CPC Class Codes: B60W 30/16 Control of distance between vehicles, e.g. keeping a distance to preceding vehicle

Abstract

A vehicle adaptive cruise control system and method are provided. The adaptive cruise control system, comprising an adaptive cruise mode selection unit configured to select adaptive cruise modes to control speeds and relative distances for a host vehicle in different modes; a data acquisition unit configured to acquire a vehicle state variable x(t); a control unit configured to generate a vehicle control signal u(t) based on the vehicle state variable x(t); a critic unit configured to evaluate a control performance according to the vehicle state variable x(t) and the vehicle control signal u(t), if a result of evaluation indicates that the control performance does not comply with a requirement, then the control unit and the critic unit perform an online leaning; a gas pedal unit and a brake unit configured to be controlled respectively by using the vehicle control signal u(t) output from the is control unit and data provided from a the vehicle inverse dynamics. According to the system, the safety and personality is improved.

Claims

1. An adaptive cruise control system, comprising:

an adaptive cruise mode selection unit configured to select adaptive cruise modes to control speeds and relative distances for a host vehicle in different modes;

a data acquisition unit configured to acquire a vehicle state variable x(t);

a control unit configured to generate a vehicle control signal u(t) based on the vehicle state variable x(t);

a critic unit configured to evaluate a control performance according to the vehicle state variable x(t) and the vehicle control signal u(t), if a result of evaluation indicates that the control performance does not comply with a requirement, then the control unit and the critic unit perform an online leaning;

a gas pedal unit and a brake unit configured to be controlled respectively by using the vehicle control signal u(t) output from the control unit and data provided from a the vehicle inverse dynamics.

2. The system according to claim 1, wherein the adaptive cruise modes comprise a safety mode, an agility mode and a comfort mode.

3. The system according to claim 2, wherein the adaptive cruise mode selection unit comprises at least one of a button, a menu, a joy sticker, a touch screen and a remote controller.

4. The system according to claim 3, wherein the data acquisition unit comprises a range sensor or a speed sensor, the vehicle state variable x(t) including a relative distance and a relative speed (Δ

d(t),Δ

v(t)), and the vehicle control signal u(t) generated by the control unit including the acceleration of the vehicle.

5. The system according to claim 1, wherein the critic unit is configured to output an approximate performance index for determining whether the control performance complies with the requirement;

if so, the critic unit is configured to continue the control, otherwise, the critic unit and the control unit are configured to execute an online training process; and

the control unit is configured to turn off the adaptive cruise control system to switch to a manual control mode by stamping the gas unit or the brake pedal unit so as to execute the control of the online training process.

6. The system according to claim 5, wherein the online training process for the critic unit is designed using a simple three layered feed-forward neural network;

the critic unit is configured to execute the online training process so as to decrease a learning error objective function for the critic unit to a predefined threshold or a number of performing the online training process reaches a predetermined value.

7. The system according to claim 5, wherein the online training process for the control unit is executed after the online training process for the critic unit converges;

the control unit is configured to the online training process using a simple three layered feed-forward neural network so as to decrease a learning error objective function for the control unit to a predefined threshold or a number of learning reaches a predetermined value.

8. The system according to claim 6, wherein the approximate performance index J(t) is defined as

9. The system according to claim 8, wherein a learning error for the critic unit is defined as

10. The system according to claim 1, wherein the critic unit and the control unit are configured to execute an offline training process which is the same as the online training process on a 3D simulator before driving the vehicle, the 3D simulator comprises a driving wheel, a gas pedal, a brake, a data acquisition unit, a display, a computer, a 3D model of the vehicles, driving simulation module, an embedded longitudinal vehicle dynamics model and an adaptive cruise control algorithm module.

11. An adaptive cruise control method comprising steps of:

selecting an adaptive cruise mode to control speeds and relative distances for a host vehicle;

acquiring a vehicle state variable x(t), as an input to a control unit;

generating, by the control unit, a vehicle control signal u(t) based on the vehicle state variable x(t);

evaluating, by a critic unit, a control performance according to the vehicle state variable x(t) and the vehicle control signal u(t), if a result of evaluation indicates that the control performance does not comply with a requirement, then performing, by the control unit and the critic unit, an online leaning;

if the results of evaluation indicates that the control performance complies with the requirement, controlling a gas pedal unit and a breaking unit respectively by using the vehicle control signal u(t) and data provided from a vehicle dynamics inverse model.

12. The method according to claim 11, wherein the adaptive cruise modes comprise a safety mode, an agility mode and a comfort mode.

13. The method according to claim 12, wherein the adaptive cruise mode is selected with at least one of a button, a menu, a joy sticker, a touch screen and a remote controller.

14. The method according to claim 13, wherein the step of obtaining is performed by a range sensor or a speed sensor, the vehicle state variable x(t) including a relative distance and a relative speed (Δ

d(t),Δ

v(t)), and the vehicle control signal u(t) generated by the control unit including the acceleration of the vehicle.

15. The method according to claim 11, wherein the step of evaluating outputs an approximate performance index for determining whether the control performance complies with the requirement;

if so, executing the sequent control, otherwise, executing an online training process; and

turning off the adaptive cruise control system to switch to a manual control mode by stamping a gas unit or a brake pedal unit so as to execute the control of the online training process.

16. The method according to claim 15, wherein the online training process for the critic unit is designed using a simple three layered feed-forward neural network;

the critic unit is configured to execute the online training process so as to decrease a learning error objective function for the critic unit to a predefined threshold or a number of performing the online training process reaches a predetermined value.

17. The method according to claim 15, wherein the online training process for the control unit is executed after the online training process for the critic unit converges;

the control unit is configured to the online training process using a simple three layered feed-forward neural network so as to decrease a learning error objective function for the control unit to a predefined threshold or a number of learning reaches a predetermined value.

18. The method according to claim 16, wherein the approximate performance index J(t) is defined as

19. The method according to claim 18, wherein a learning error for the critic unit is defined as

20. The method according to claim 11, further comprising steps of executing an offline training process which is the same as the online training process on a 3D simulator before driving the vehicle;

the 3D simulator comprises a driving wheel, a gas pedal, a brake, a data acquisition unit, a display, a computer, a 3D model of the vehicles, driving simulation module, an embedded longitudinal vehicle dynamics model and an adaptive cruise control algorithm module.