IP Library › Granted Patent US 11,884,295
Granted Patent B2
US 11,884,295 · App. 17/074,993 · Granted Jan 30, 2024

Apparatus and method for controlling autonomous driving of vehicle

Inventors: Ki Cheol Shin (Seongnam-si, KR); Hyun Kyu Kim (Seoul, KR)
Assignees: HYUNDAI MOTOR COMPANY; KIA MOTORS CORPORATION
B60W60/0015B60W30/09B60W30/0953B60W30/0956B60W30/16B60W40/10B60W2554/4044B60W2720/106
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,884,295
App. No.
17/074,993
Granted
Jan 30, 2024
Kind
B2
Abstract

A method of controlling autonomous driving of a vehicle includes: selecting a target object ahead of the vehicle based on driving information, generating a velocity profile for maintaining a desired distance to the target object, calculating a desired acceleration based on the velocity profile and a delay time of the vehicle, and controlling an actuator of the vehicle based on the desired acceleration.

Claims (58)

1. A method of controlling autonomous driving of a vehicle, the method comprising:

selecting, by a driving environment recognizer, a target object ahead of the vehicle based on driving information;

generating, by a velocity profile generator, a velocity profile for maintaining a desired distance to the target object from the vehicle;

calculating, by an acceleration calculator, a desired acceleration based on the velocity profile and a delay time of the vehicle;

setting, by the acceleration calculator, the desired acceleration to be less than an initial inclination of a longitudinal acceleration and deceleration profile based on the delay time of the vehicle; and

controlling, by a vehicle controller, an actuator of the vehicle based on the desired acceleration,

wherein generating the velocity profile includes:

calculating, by a driving information processor, a target velocity of the vehicle based on a velocity limit of a road on which the vehicle travels and a velocity and a heading direction of the target object; and

applying, by the driving information processor, a predetermined weight to a time to collision (TTC) between the vehicle and the target object to calculate a target convergence time,

wherein the velocity profile is classified into an acceleration and deceleration section and a constant velocity section based on the target convergence time,

wherein the target convergence time is a time consumed to converge to the target velocity, and the predetermined weight is a tuning coefficient of a time to collision and variably adjusted in a range of zero (0) to 1 based on characteristics of a vehicle and a behavior of the target object in real time,

wherein the desired distance is set in consideration of driver driving tendency as well as a minimum safety distance with the target object, and

wherein the desired distance is set by learning the driver driving tendency during autonomous driving or is determined by applying a degree of risk to the target object.

2. The method of claim 1 , wherein generating the velocity profile includes:

generating the longitudinal acceleration and deceleration profile in a curve form based on a third order polynomial based on a current velocity, the target velocity, and the target convergence time of the vehicle.

3. The method of claim 2 , wherein generating the velocity profile includes:

determining the initial inclination of the longitudinal acceleration and deceleration profile using both a velocity error between the current velocity and the target velocity of the vehicle and a distance error between a relative distance and the desired distance to the target object.

4. The method of claim 2 , wherein generating the velocity profile includes:

calculating coefficients for respective degree-terms of the third order polynomial based on a preset constraint condition,

wherein the preset constraint condition includes a condition that a velocity at the target convergence time is the target velocity and a velocity inclination at the target convergence time is zero (0).

5. The method of claim 2 , wherein calculating the desired acceleration includes:

extracting a reaction velocity corresponding to the delay time based on the longitudinal acceleration and deceleration profile; and

calculating the desired acceleration using a vehicle velocity variation between the reaction velocity and the current velocity for the delay time.

6. The method of claim 1 , wherein controlling the actuator includes:

after the target convergence time, maintaining a constant velocity of the vehicle depending on the target velocity.

7. The method of claim 1 , wherein the target convergence time is variably adjusted based on a driving environment of the vehicle.

8. A non-transitory computer-readable recording medium having a program recorded thereon, the program to direct a processor to perform acts of:

selecting, by a driving environment recognizer, a target object ahead of a vehicle based on driving information;

generating, by a velocity profile generator, a velocity profile for maintaining a desired distance to the target object from the vehicle;

calculating, by an acceleration calculator, a desired acceleration based on the velocity profile and a delay time of the vehicle;

setting, by the acceleration calculator, the desired acceleration to be less than an initial inclination of a longitudinal acceleration and deceleration profile based on the delay time of the vehicle; and

controlling, by a vehicle controller, an actuator of the vehicle based on the desired acceleration,

wherein generating the velocity profile includes:

calculating, by a driving information processor, a target velocity of the vehicle based on a velocity limit of a road on which the vehicle travels and a velocity and a heading direction of the target object; and

applying, by the driving information processor, a predetermined weight to a time to collision (TTC) between the vehicle and the target object to calculate a target convergence time,

wherein the velocity profile is classified into an acceleration and deceleration section and a constant velocity section based on the target convergence time,

wherein the target convergence time is a time consumed to converge to the target velocity, and the predetermined weight is a tuning coefficient of a time to collision and variably adjusted in a range of zero (0) to 1 based on characteristics of a vehicle and a behavior of the target object in real time,

wherein the desired distance is set in consideration of driver driving tendency as well as a minimum safety distance with the target object, and

wherein the desired distance is set by learning the driver driving tendency during autonomous driving or is determined by applying a degree of risk to the target object.

9. An apparatus for controlling autonomous driving of a vehicle, the apparatus comprising a processor configured to:

select a target object ahead of the vehicle based on driving information;

generate a velocity profile for maintaining a desired distance to the target object from the vehicle;

calculate a desired acceleration based on the velocity profile and a delay time of the vehicle;

set the desired acceleration to be less than an initial inclination of a longitudinal acceleration and deceleration profile based on the delay time of the vehicle;

control an actuator of the vehicle based on the desired acceleration;

calculate a target velocity of the vehicle based on a velocity limit of a road on which the vehicle travels, and a velocity and a heading direction of the target object; and

apply a predetermined weight to a time to collision (TTC) between the vehicle and the target object to calculate a target convergence time,

wherein the velocity profile is classified into an acceleration and deceleration section and a constant velocity section based on the target convergence time,

wherein the target convergence time is a time consumed to converge to the target velocity, and the predetermined weight is a tuning coefficient of a time to collision and variably adjusted in a range of zero (0) to 1 based on characteristics of the vehicle and a behavior of the target object in real time,

wherein the velocity profile generator processor is configured to set the desired distance in consideration of driver driving tendency as well as a minimum safety distance with the target object, and

wherein the desired distance is set by learning the driver driving tendency during autonomous driving or is determined by applying a degree of risk to the target object.

10. The apparatus of claim 9 , wherein the processor is configured to generate the longitudinal acceleration and deceleration profile in a curve form based on a third order polynomial based on a current velocity, the target velocity, and the target convergence time of the vehicle.

11. The apparatus of claim 10 , wherein the processor is configured to determine the initial inclination of the longitudinal acceleration and deceleration profile using both a velocity error between the current velocity and the target velocity of the vehicle and a distance error between a relative distance and the desired distance to the target object.

12. The apparatus of claim 10 , wherein the processor is configured to calculate coefficients for respective degree-terms of the third order polynomial based on a preset constraint condition, and

wherein the preset constraint condition includes a condition that a velocity at the target convergence time is the target velocity and a velocity inclination at the target convergence time is zero (0).

13. The apparatus of claim 10 , wherein the processor is configured to extract a reaction velocity corresponding to the delay time based on the longitudinal acceleration and deceleration profile and calculate the desired acceleration using a vehicle velocity variation between the reaction velocity and the current velocity for the delay time.

14. The apparatus of claim 9 , wherein the processor is configured to maintain a constant velocity of the vehicle based on the target velocity after the target convergence time.

15. The apparatus of claim 9 , wherein the target convergence time is variably adjusted based on a driving environment of the vehicle.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 28, 2022
From: CHOI, SEUNGMOK; IM, HYUK; KIM, JINNAM; CHAE, YOUNGWAN
To: HYUNDAI MOTOR COMPANY; KIA CORPORATION
Reel/Frame 061583/0664 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 12, 2021
From: SHIN, KI CHEOL; KIM, HYUN KYU
To: HYUNDAI MOTOR COMPANY; KIA MOTORS CORPORATION
Reel/Frame 055243/0382 →
Priority Claims (1)
KR 10-2019-0169289 · Dec 17, 2019 · national
Continuity (1)
Related Publication 20210179143A1 · Jun 17, 2021
Cited By (2)
US 12,274,572 US 12,409,842