IP Library › Granted Patent US 12,633,220
Granted Patent B2
US 12,633,220 · App. 18/781,615 · Granted May 19, 2026

Method and apparatus for generating a memory parking assist path

Inventor: Jin Han Jeong (Seongnam-si, KR)
Assignees: HYUNDAI MOTOR COMPANY; KIA CORPORATION
G08G1/168B60W30/06G06T7/70G06V20/586
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 12,633,220
App. No.
18/781,615
Granted
May 19, 2026
Kind
B2
Abstract

A method and an apparatus for generating a safe Memory Parking Assist path by considering perception and positioning errors due to distortion of an SVM wide-angle camera are disclosed. The method for generating a parking path includes obtaining images around a vehicle by cameras; obtaining position of the vehicle and obstacles around the vehicle by using images; activating a Memory Parking Assist (MPA) in response to a determination that the vehicle approaches a memory path; predicting whether the vehicle collides with any of the obstacles if the vehicle tracks the memory path; determining whether the obstacles are avoidable in response to a determination that the vehicle is predicted to collide with the obstacle; and generating an avoidance path for the vehicle to avoid the obstacle and a convergence path for the vehicle to converge to the memory path.

Claims (50)

1 . A method for generating a parking path, the method comprising:

obtaining images around a vehicle by cameras;

obtaining position of the vehicle and obstacles around the vehicle using the images;

activating a Memory Parking Assist (MPA) in response to a determination that the vehicle approaches a memory path;

predicting whether the vehicle collides with any of the obstacles if the vehicle tracks the memory path;

determining whether the obstacles are avoidable in response to a determination that the vehicle is predicted to collide with the obstacle;

generating an avoidance path for the vehicle to avoid the obstacle;

updating the position of the vehicle periodically by using current environment around a parking lot;

determining whether the vehicle tracks the memory path by using the updated position of the vehicle; and

generating a convergence path for the vehicle to converge to the memory path when the vehicle deviates the memory path.

2 . The method of claim 1 , further comprising:

updating the memory path to the avoidance path and the convergence path; and

repeatedly predicting whether the vehicle collides with any of the obstacles and repeatedly determining whether the obstacles are avoidable by using the updated memory path.

3 . The method of claim 1 , wherein a polygon-shaped vehicle margin is applied for predicting whether the vehicle collides with any of the obstacles, determining whether the obstacles are avoidable, generating the avoidance path, and generating the convergence path.

4 . The method of claim 3 , wherein an area of the vehicle margin increases or decreases according to a distance between the obstacle and the vehicle.

5 . The method of claim 2 , wherein repeatedly predicting whether the vehicle collides with any of the obstacles and repeatedly determining whether the obstacles are avoidable by using the updated memory path comprises:

applying a decreased vehicle margin compared to the vehicle margin before updating the memory path.

6 . The method of claim 1 , wherein the avoidance path and the convergence path are clothoid paths.

7 . A system for generating a parking path, the system comprising:

a memory device; and

a processing device, communicatively coupled to the memory device and configured to:

obtain images around a vehicle by cameras,

obtain position of the vehicle and obstacles around the vehicle by using images,

activate a Memory Parking Assist (MPA) in response to a determination that the vehicle approaches a memory path,

predict whether the vehicle collides with any of the obstacles if the vehicle tracks the memory path,

determine whether the obstacles are avoidable in response to a determination that the vehicle is predicted to collide with the obstacle,

generate an avoidance path for the vehicle to avoid the obstacle,

update the position of the vehicle periodically by using current environment around a parking lot,

determine whether the vehicle tracks the memory path by using the updated position of the vehicle, and

generate a convergence path for the vehicle to converge to the memory path when the vehicle deviates the memory path.

8 . The system of claim 7 , wherein the processing device is further configured to:

update the memory path to the avoidance path and the convergence path; and

repeatedly predict whether the vehicle collides with any of the obstacles and repeatedly determine whether the obstacles are avoidable by using the updated memory path.

9 . The system of claim 7 , wherein a polygon-shaped vehicle margin is applied for predicting whether the vehicle collides with any of the obstacles, determining whether the obstacles are avoidable, generating the avoidance path, and generating the convergence path.

10 . The system of claim 9 , wherein an area of the vehicle margin increases or decreases according to a distance between the obstacle and the vehicle.

11 . The system of claim 8 , wherein, when whether the vehicle collides with any of the obstacles is repeatedly predicted and whether the obstacles are avoidable is repeatedly determined by using the updated memory path, decreased vehicle margin compared to the vehicle margin before update of the memory path is applied.

12 . The system of claim 7 , wherein the avoidance path and the convergence path are clothoid paths.

13 . A system for generating a parking path, the system comprising:

a memory device; and

a processing device, communicatively coupled to the memory device and configured to:

obtain images around a vehicle by cameras,

obtain position of the vehicle and obstacles around the vehicle by using images,

activate a Memory Parking Assist (MPA) in response to a determination that the vehicle approaches a memory path,

predict whether the vehicle collides with any of the obstacles if the vehicle tracks the memory path,

determine whether the obstacles are avoidable in response to a determination that the vehicle is predicted to collide with the obstacle,

generate an avoidance path for the vehicle to avoid the obstacle,

generate a convergence path for the vehicle to converge to the memory path,

update the memory path to the avoidance path and the convergence path, and

repeatedly predict whether the vehicle collides with any of the obstacles and repeatedly determine whether the obstacles are avoidable by using the updated memory path,

wherein, when whether the vehicle collides with any of the obstacles is repeatedly predicted and whether the obstacles are avoidable is repeatedly determined by using the updated memory path, decreased vehicle margin compared to the vehicle margin before update of the memory path is applied.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 25, 2024
From: JEONG, JIN HAN
To: HYUNDAI MOTOR COMPANY; KIA CORPORATION
Reel/Frame 068084/0507 →
Priority Claims (1)
KR 10-2023-0188998 · Dec 21, 2023 · national
Continuity (1)
Related Publication 20250209919A1 · Jun 26, 2025
References Cited (6)
US 20180312169A1 · Harai · 2018 [cited by examiner]
US 20200130696A1 · Xiao · 2020 [cited by examiner]
US 20210370917A1 · Ishinoda · 2021 [cited by examiner]
KR 101581286B1 · 2015 [cited by applicant]
KR 102387603B1 · 2022 [cited by applicant]
KR 20230081749A · 2023 [cited by applicant]