US-12617427-B2 - Autonomous driving control apparatus and method for generating driving path thereof

Abstract

An autonomous driving control apparatus and a method for generating a driving path thereof are provided. The autonomous driving control apparatus includes a processor that receives a driving path from a navigation device. The processor is configured to determine whether there is a turn section on the driving path, determines a turn path, a curvature of which continuously changes in response to determining that there is the turn section on the driving path, and outputs the turn path.

Inventors

• Sung Woo Choi
• Sung Kwan Kim

Assignees

• HYUNDAI MOTOR COMPANY
• KIA CORPORATION

Dates

Publication Date

20260505

Application Date

20240403

Priority Date

20230719

Claims (18)

1. 1 . An autonomous driving control apparatus, comprising: a processor configured to receive a driving path from a navigation device operatively connected to the processor, wherein the processor is configured to: identify a turn section included in the driving path; obtain, based on information related to the turn section and an identification of the turn section, a start point of the turn section, an end point of the turn section and a target vehicle heading deflection; generate, based on the end point of the turn section and the target vehicle heading deflection, a turn path, wherein a curvature of the turn path is continuously changed; output the turn path; and control a vehicle to drive along the turn path, wherein the driving path includes the information related to the turn section.
2. 2 . The autonomous driving control apparatus of claim 1 , wherein the processor is further configured for estimating a maximum curvature and a maximum steering angular speed based on the end point of the turn section and the target vehicle heading deflection, and wherein the turn path is generated based on the maximum curvature and the maximum steering angular speed.
3. 3 . The autonomous driving control apparatus of claim 2 , wherein the processor is further configured for estimating the maximum curvature and the maximum steering angular speed using a deep neural network (DNN).
4. 4 . The autonomous driving control apparatus of claim 2 , wherein the processor is further configured to determine an end point of a first clothoid curve and a vehicle heading and a curvature at the end point of the first clothoid curve based on the maximum curvature and the maximum steering angular speed.
5. 5 . The autonomous driving control apparatus of claim 4 , wherein the processor is further configured to determine a clothoid length based on the maximum curvature and the maximum steering angular speed.
6. 6 . The autonomous driving control apparatus of claim 5 , wherein the processor is further configured to determine a vehicle heading deflection in a clothoid section based on the maximum curvature and the maximum steering angular speed.
7. 7 . The autonomous driving control apparatus of claim 6 , wherein the processor is further configured to: determine a rotational center point based on the end point of the first clothoid curve, the vehicle heading at the end point of the first clothoid curve, and the maximum curvature; and determine a circle curve based on the end point of the first clothoid curve, the target vehicle heading deflection, the vehicle heading deflection in the clothoid section, and the rotational center point.
8. 8 . The autonomous driving control apparatus of claim 7 , wherein the processor is further configured to determine a second clothoid curve based on the target vehicle heading deflection and the rotational center point.
9. 9 . The autonomous driving control apparatus of claim 8 , wherein the processor is further configured to determine the turn path using the first clothoid curve, the circle curve, and the second clothoid curve.
10. 10 . A method for generating a driving path of an autonomous driving control apparatus, the method comprising: receiving, by a processor, a driving path from a navigation device; identifying, by the processor, a turn section included in the driving path; obtaining, based on information related to the turn section and an identification of the turn section, a start point of the turn section, an end point of the turn section and a target vehicle heading deflection; generating, by the processor, based on the end point of the turn section and the target vehicle heading deflection, a turn path, wherein a curvature of the turn path is continuously changed; outputting, by the processor, the turn path; and controlling, by the processor, a vehicle to drive along the turn path, wherein the driving path includes the information related to the turn section.
11. 11 . The method of claim 10 , wherein the determining of the turn path further includes: estimating a maximum curvature and a maximum steering angular speed based on the end point of the turn section and the target vehicle heading deflection, and wherein the turn path is generated based on the maximum curvature and the maximum steering angular speed.
12. 12 . The method of claim 11 , wherein the estimating of the maximum curvature and the maximum steering angular speed includes: estimating the maximum curvature and the maximum steering angular speed using a deep neural network (DNN).
13. 13 . The method of claim 11 , wherein the determining of the turn path further includes: determining an end point of a first clothoid curve and a vehicle heading and a curvature at the end point of the first clothoid curve based on the maximum curvature and the maximum steering angular speed.
14. 14 . The method of claim 13 , wherein the determining of the turn path further includes: determining a clothoid length based on the maximum curvature and the maximum steering angular speed.
15. 15 . The method of claim 14 , wherein the determining of the turn path further includes: determining a vehicle heading deflection in a clothoid section based on the maximum curvature and the maximum steering angular speed.
16. 16 . The method of claim 15 , wherein the determining of the turn path further includes: determining a rotational center point based on the end point of the first clothoid curve, the vehicle heading at the end point of the first clothoid curve, and the maximum curvature; and determining a circle curve based on the end point of the first clothoid curve, the target vehicle heading deflection, the vehicle heading deflection in the clothoid section, and the rotational center point.
17. 17 . The method of claim 16 , wherein the determining of the turn path further includes: determining a second clothoid curve based on the target vehicle heading deflection and the rotational center point.
18. 18 . The method of claim 17 , wherein the determining of the turn path further includes: determining the turn path using the first clothoid curve, the circle curve, and the second clothoid curve.

Description

CROSS-REFERENCE TO RELATED APPLICATION The present application claims priority to Korean Patent Application No. 10-2023-0094094, filed on Jul. 19, 2023, the entire contents of which is incorporated herein for all purposes by this reference. BACKGROUND OF THE PRESENT DISCLOSURE Field of the Present Disclosure The present disclosure relates to an autonomous driving control apparatus and a method for generating a driving path thereof. DESCRIPTION OF RELATED ART When a path with a discontinuous curvature is generated when a driving path of a vehicle is generated, there is an inconvenience of having to adjust a steering angle of the vehicle to suit the discontinuous curvature after the vehicle stops. However, when following a continuous curvature path, the vehicle may follow a path, a curvature of which changes, without stopping. A conventional method for generating a continuous curvature path configures the continuous curvature path using a clothoid for increasing curvature, a circle for maintaining the increased curvature and changing a heading, and a clothoid for decreasing the curvature to “0” again. However, when a path ends at the end portion of the clothoid, where the end point will occur may be determined only after all the calculations are finished, it is difficult to place the end point at a position desired by a user. It is essential to use two continuous curvature turn path, each of which includes two clothoids and one circle, and a segment element connecting the respective continuous curvature turn paths. One turn path is configured with respect to a start point and one turn path is configured with respect to an end point, and end clothoid portions of the two turn paths are connected by a straight line. However, in the instant case, the path becomes very long. It is impossible to use the path in a narrow section such as a U-turn section. The information included in this Background in this Background of the present disclosure is only for enhancement of understanding of the general background of the present disclosure and may not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art. BRIEF SUMMARY Various aspects of the present disclosure are directed to providing an autonomous driving control apparatus and a method for generating a driving path thereof to generate a continuous curvature path for a narrow turn section, such as a U-turn section, when generating the driving path of the vehicle. The technical problems to be solved by the present disclosure are not limited to the aforementioned problems, and any other technical problems not mentioned herein will be clearly understood from the following description by those skilled in the art to which the present disclosure pertains. According to an aspect of the present disclosure, an autonomous driving control apparatus may include a processor that receives a driving path from a navigation device. The processor is configured to determine whether there is a turn section on the driving path, may be configured to determine a turn path, a curvature of which continuously changes in response to determining that there is the turn section on the driving path, and may outputs the turn path. The processor is configured to determine a start point and an end point of the turn section and a target vehicle heading deflection based on the driving path. The processor may estimate a maximum curvature and a maximum steering angular speed based on the end point of the turn section and the target vehicle heading deflection. The processor may estimate the maximum curvature and the maximum steering angular speed using a deep neural network (DNN). The processor is configured to determine an end point of a first clothoid curve and a vehicle heading and a curvature at the end point of the first clothoid curve based on the maximum curvature and the maximum steering angular speed. The processor is configured to determine a clothoid length based on the maximum curvature and the maximum steering angular speed. The processor is configured to determine a vehicle heading deflection in a clothoid section based on the maximum curvature and the maximum steering angular speed. The processor is configured to determine a rotational center point based on the end point of the first clothoid curve, the vehicle heading at the end point of the first clothoid curve, and the maximum curvature and may be configured to determine a circle curve based on the end point of the first clothoid curve, the target vehicle heading deflection, the vehicle heading deflection in the clothoid section, and the rotational center point. The processor is configured to determine a second clothoid curve based on the target vehicle heading deflection and the rotational center point. The processor is configured to determine the turn path using the first clothoid curve, the circle curve, and the second clothoid curve. According to ano