METHOD AND SYSTEM FOR PREDICTING DRIVING PATH OF NEIGHBORING VEHICLE

• US 20170120926A1
• Filed: 07/12/2016
• Published: 05/04/2017
• Est. Priority Date: 10/28/2015
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Original Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Inventors: Yoon, Ji Hyun
• Granted Patent: US 10,793,162 B2
• Time in Patent Office: Days
• CPC Class Codes: B60W 2552/05 Type of road, e.g. motorways, local streets, paved or unpaved roads
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: B60W 2554/4041 Position
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 30/18154 Approaching an intersection
• CPC Class Codes: B60W 40/10 related to vehicle motion
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/041 Abduction
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G08G 1/163 involving continuous checking
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

A method and system for predicting a driving path of a neighboring vehicle which may influence a subject vehicle is provided. The subject vehicle detects a segment adjacent to the neighboring vehicle which is currently driven and searches all segments connected to the segment. The method prevents a collision between the subject vehicle and the neighboring vehicle that occurs due to misrecognition of a position, a driving direction, or velocity of the neighboring vehicle, and more accurately predicts the driving path of the neighboring vehicle. The method includes receiving information of a neighboring road on which a subject vehicle is driven from a detailed map and detecting a segment showing the neighboring vehicle which is being currently driven from the information of the neighboring road. Segments are detected that are connected to the segment and the driving path of the neighboring vehicle is predicted.

Claims

1. A method for predicting a driving path of a neighboring vehicle, comprising:

receiving, by a controller, information regarding a neighboring road on which a subject vehicle is driven using a detailed map;

detecting, by the controller, a segment provided to a position closest to the neighboring vehicle being currently driven from the information regarding the neighboring mad; and

detecting, by the controller, segments connected to the segment and predicting the driving path of the neighboring vehicle using driving paths of the segments.

2. The method according to claim 1, wherein the driving path of the neighboring vehicle is predicted using any one of a most probable path (MPP), a probability estimation path (PEP), and a defensive estimation path (DEP).

3. The method according to claim 1, wherein the detecting of the segment provided to a position of the neighboring vehicle and the position closest to the neighboring vehicle which is being currently driven uses a grid map or quad tree method.

4. The method according to claim 1, wherein in the predicting of the driving path of the neighboring vehicle, a path to which the neighboring vehicle is moved is predicted using velocity, acceleration or a driving direction of the neighboring vehicle.

5. The method according to claim 1, wherein when there is no segment which influences an advancing direction of the subject vehicle, the driving path of the neighboring vehicle is not predicted.

6. The method according to claim 1, wherein when the neighboring vehicle is driven on a same lane as the subject vehicle, or is driven at a rear of the subject vehicle, the driving path of the neighboring vehicle is not predicted.

7. A system for predicting a driving path of a neighboring vehicle, comprising:

a memory configured to store program instructions; and

a processor configured to execute the program instructions, the program instructions when executed configured to;

receive information regarding a neighboring road on which a subject vehicle is driven using a detailed map;

detect a segment provided to a position closest to the neighboring vehicle being currently driven from the information regarding the neighboring road; and

detect segments connected to the segment and predicting the driving path of the neighboring vehicle using driving paths of the segments.

8. The system according to claim 7, wherein the driving path of the neighboring vehicle is predicted using any one of a most probable path (MPP), a probability estimation path (PEP), and a defensive estimation path (DEP).

9. The system according to claim 7, wherein the detecting of the segment provided to a position of the neighboring vehicle and the position closest to the neighboring vehicle which is being currently driven uses a grid map or quad tree method.

10. The system according to claim 7, wherein in the predicting of the driving path of the neighboring vehicle, a path to which the neighboring vehicle is moved is predicted using velocity, acceleration or a driving direction of the neighboring vehicle.

11. The system according to claim 7, wherein when there is no segment which influences an advancing direction of the subject vehicle, the driving path of the neighboring vehicle is not predicted.

12. The system according to claim 7, wherein when the neighboring vehicle is driven on a same lane as the subject vehicle, or is driven at a rear of the subject vehicle, the driving path of the neighboring vehicle is not predicted.