Steering risk decision system and method for driving narrow roads

• US 9,522,701 B2
• Filed: 05/15/2014
• Issued: 12/20/2016
• Est. Priority Date: 11/15/2013
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Original Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Inventors: Shin, Ki Cheol, Lee, Chang Jae, Jung, Ee Suk
• Primary Examiner(s): Do, Truc M
• Application Number:
  US14/278,518
• Publication Number:
  US 20150142299A1
• Time in Patent Office: 950 Days
• US Class Current: 1/1
• CPC Class Codes: B62D 15/0295 by overlaying a vehicle path based on present steering angle over an image without processing that image
• CPC Class Codes: G06T 11/20 Drawing from basic elements, e.g. lines or circles
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads

Abstract

The present invention provides a steering risk decision system and method that determine and provide a steering risk of a vehicle to a driver. The system includes an obstacle sensor that senses an obstacle to generate first sensor data and a driving state sensor senses a driving state of a vehicle to generate second sensor data. In addition, a processor extracts feature points from first sensor data to indicate the obstacle in point and line shapes and predicts a driving region of the vehicle using second sensor data. Further, the processor calculates a relationship between the vehicle and the obstacle using information for the obstacle indicated in the point and line shapes and information for the driving region to determine a steering risk of the vehicle based on the calculated result.

Claims

1. A steering risk decision system, comprising:

an obstacle sensor configured to sense an obstacle to generate first sensor data;

a driving state sensor configured to sense a driving state of a vehicle to generate second sensor data; and

a processor configured to;

extract feature points from the first sensor data to indicate the obstacle in point and line shapes;

predict a driving region of the vehicle using the second sensor data;

calculate a relationship between the vehicle and the obstacle using information for the obstacle indicated in the point and line shapes and information for the driving region;

determine a steering risk of the vehicle based on the calculated results;

wherein the processor is configured to set a region between two circular arcs formed by a trace generated by an inner wheel of a rotational direction of the vehicle and a trace generated by an outer wheel front corner of the rotational direction to the risk region;

wherein the processor is configured to;

classify front and side regions of the vehicle into a risk region, a warning region, and a safety region using information for the driving region; and

compare the classified regions and information for the obstacle to determine a steering risk; and

wherein the processor is configured to;

divide the risk region and the warning region into a left region and a right region based on the center of a rear wheel shaft of the vehicle; and

compare the divided regions and information for the obstacle to determine the steering risk for each of the left and right regions of the vehicle.

2. The steering risk decision system according to claim 1, wherein the processor is further configured to:

cluster the first sensor data and find feature points from the clustered first sensor data to cluster the feature points in the point and line shapes; and

arrange the clustered feature points on a two-dimensional plane.

3. The steering risk decision system according to claim 1, wherein the processor is configured to predict the driving region using a kinematics model of the vehicle.

4. The steering risk decision system according to claim 1, wherein the processor is configured to set a region surrounding the risk region while being spaced apart from a boundary line of the risk region by a predetermined distance to the warning region.

5. The steering risk decision system according to claim 1, wherein the processor is configured to set a region surrounding the risk region in a form in which the region is gradually widened toward a side as a distance from the vehicle increases to the warning region.

6. The steering risk decision system according to claim 5, wherein the processor is configured to set a region surrounding the risk region in a form in which an outer side thereof has a larger radius than a side boundary circular arc of the risk region and an inner side thereof has a smaller radius than the side boundary circular arc of the risk region to the warning region.

7. A steering risk decision method of a vehicle, the method comprising:

extracting, by a processor, feature points of an obstacle to indicate the obstacle in point and line shapes;

sensing, by a sensor, a driving state of the vehicle to predict a driving region of the vehicle;

calculating, by the processor, a relationship between the vehicle and the obstacle using information for the obstacle indicated in the point and line shapes and information for the driving region and determining a steering risk of the vehicle based on the calculated result;

setting, by the processor, the risk region between two circular arcs formed by a trace generated by an inner wheel of a rotational direction of the vehicle and a trace generated by an outer wheel front corner of the rotational direction;

wherein in the calculating of the relationship between the vehicle and the obstacle, front and side regions of the vehicle are classified, by the processor, into a risk region, a warning region, and a safety region to determine whether the obstacle is positioned in any region of the classified regions; and

wherein in the calculating of the relationship between the vehicle and the obstacle, the risk region and the warning region are divided, by the processor, into a left region and a right region based on the center of a rear wheel shaft of the vehicle to determine whether the obstacle is positioned in any region of the left region and the right region.

8. The steering risk decision method according to claim 7, further comprising:

setting, by the processor, the warning region to a region surrounding the risk region while being spaced apart from a boundary line of the risk region by a predetermined distance.

9. The steering risk decision method according to claim 7, further comprising:

setting, by the processor, the warning region to a region surrounding the risk region in a form in which the region is gradually widened toward a side as a distance from the vehicle increases.

10. The steering risk decision method according to claim 7, further comprising:

setting, by the processor, the warning region to a region surrounding the risk region in a form in which an outer side thereof has a larger radius than a side boundary circular arc of the risk region and an inner side thereof has a smaller radius than the side boundary circular arc of the risk region.

11. A non-transitory computer readable medium containing program instructions executed by a processor, the computer readable medium comprising:

program instructions that extract feature points of an obstacle to indicate the obstacle in point and line shapes;

program instructions that control a sensor to sense a driving state of the vehicle to predict a driving region of the vehicle;

program instructions that calculate a relationship between the vehicle and the obstacle using information for the obstacle indicated in the point and line shapes and information for the driving region and determining a steering risk of the vehicle based on the calculated result;

program instructions that set the risk region between two circular arcs formed by a trace generated by an inner wheel of a rotational direction of the vehicle and a trace generated by an outer wheel front corner of the rotational direction;

program instructions that classify front and side regions of the vehicle into a risk region, a warning region, and a safety region to determine whether the obstacle is positioned in any region of the classified regions; and

program instructions that divide the risk region and the warning region into a left region and a right region based on the center of a rear wheel shaft of the vehicle to determine whether the obstacle is positioned in any region of the left region and the right region.