Side collision avoidance system and method for vehicle

• US 9,937,905 B2
• Filed: 06/15/2016
• Issued: 04/10/2018
• Est. Priority Date: 03/22/2016
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Original Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Inventors: Kim, Jun Soo, Yoo, Jeong Jae, Park, Jin Ho, Lim, Hyung Jun
• Primary Examiner(s): CHEUNG, CALVIN K
• Application Number:
  US15/182,641
• Publication Number:
  US 20170274876A1
• Time in Patent Office: 664 Days
• Field of Search: None
• CPC Class Codes: B60T 2201/022 Collision avoidance systems
• CPC Class Codes: B60T 7/22 initiated by contact of vehicle, e.g. bumper, with an external object, e.g. another vehicle , or by means of contactless obstacle detectors mounted on the vehicle
• CPC Class Codes: B60W 10/18 including control of braking systems
• CPC Class Codes: B60W 2050/143 Alarm means
• CPC Class Codes: B60W 2420/408 Radar; Laser, e.g. lidar
• CPC Class Codes: B60W 2420/54 Audio sensitive means, e.g. ultrasound
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: B60W 30/08 Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
• CPC Class Codes: B60W 30/095 Predicting travel path or likelihood of collision
• CPC Class Codes: B60W 30/0953 the prediction being responsive to vehicle dynamic parameters
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 50/14 Means for informing the driver, warning the driver or prompting a driver intervention
• CPC Class Codes: G01S 13/862 Combination of radar systems with sonar systems
• CPC Class Codes: G01S 13/87 Combinations of radar systems, e.g. primary radar and secondary radar
• CPC Class Codes: G01S 13/931 of land vehicles
• CPC Class Codes: G01S 15/87 Combinations of sonar systems
• CPC Class Codes: G01S 15/931 of land vehicles
• CPC Class Codes: G01S 2013/9315 Monitoring blind spots
• CPC Class Codes: G01S 2013/93185 Controlling the brakes
• CPC Class Codes: G01S 2013/93271 in the front of the vehicles
• CPC Class Codes: G01S 2013/93272 : in the back of the vehicles
• CPC Class Codes: G01S 2015/937 : sensor installation details

Abstract

A side collision avoidance system and method for a vehicle combines data from radar sensors mounted on front and rear surfaces of the vehicle with data from ultrasonic sensors mounted on side surfaces of the vehicle, and detects obstacles on the basis of the combined data, so as to increase accuracy in the detection of obstacles and predict the probability of collisions with obstacles with high accuracy. The system includes: radar sensors detecting an obstacle around the vehicle; ultrasonic sensors detecting the obstacle around the vehicle; a controller combining sensor data from the radar sensors with sensor data from the ultrasonic sensors to generate combined data, detecting the obstacle on the basis of the combined data, and predicting collision or non-collision with the detected obstacle on the basis of the combined data; and a brake driver braking the vehicle when the collision is predicted.

Claims

1. A side collision avoidance system for a vehicle, comprising:

a plurality of radar sensors configured to detect an obstacle around the vehicle;

a plurality of ultrasonic sensors configured to detect the obstacle around the vehicle;

a controller configured to;

combine radar sensor data from the radar sensors with ultrasonic sensor data from the ultrasonic sensors to generate combined data;

detect the obstacle on the basis of the combined data; and

predict collision or non-collision with the detected obstacle on the basis of the combined data; and

a brake driver configured to brake the vehicle when the collision is predicted,

wherein the controller generates covariance of the radar sensor data, covariance of the ultrasonic sensor data, and covariance of the combined data on the basis of cross-covariance of the ultrasonic sensor data and the radar sensor data.

2. The side collision avoidance system according to claim 1, further comprising a warning unit outputting an alarm when the collision is predicted.

3. The side collision avoidance system according to claim 1, wherein the controller calculates a collision probability with the obstacle in consideration of a standard deviation of the covariance of the combined data, and predicts the collision or non-collision with the detected obstacle on the basis of the calculated collision probability.

4. The side collision avoidance system according to claim 1, wherein the controller comprises:

a sensor driver driving a radar sensor and an ultrasonic sensor provided in a direction that is determined according to a left-side or right-side exit mode of the vehicle that is parallel parked;

a sensor data combiner combining the radar sensor data with the ultrasonic sensor data;

an effective obstacle detector detecting a plurality of obstacles on the basis of the combined data and detecting the plurality of obstacles positioned in an interested area among the detected plurality of obstacles as effective obstacles; and

a collision predictor detecting the obstacle positioned in a potential collision area among the effective obstacles detected by the effective obstacle detector as a final obstacle, and calculating a collision probability with the final obstacle to predict collision or non-collision.

5. The side collision avoidance system according to claim 4, wherein the sensor driver determines the left-side or right-side exit mode through at least one of a controller area network (CAN), a local interconnect network (LIN), a FlexRay network, and a media oriented system transport (MOST).

6. The side collision avoidance system according to claim 4, wherein the sensor data combiner generates covariance of the radar sensor data, covariance of the ultrasonic sensor data, and covariance of the combined data on the basis of cross-covariance of the ultrasonic sensor data and the radar sensor data.

7. The side collision avoidance system according to claim 4, wherein the effective obstacle detector continuously detects whether or not the effective obstacles are out of the interested area, on the basis of mathematical models of obstacle state changes.

8. The side collision avoidance system according to claim 4, wherein the collision predictor calculates the collision probability with the obstacle in consideration of a standard deviation of the covariance of the combined data, and predicts the collision or non-collision with the obstacle on the basis of the calculated collision probability.

9. The side collision avoidance system according to claim 8, wherein the collision predictor calculates the collision probability (D) with the obstacle on the basis of the standard deviation of the covariance of the combined data by using the following equation:

10. A side collision avoidance method for a vehicle, comprising the steps of:

generating, by a controller, combined data by combining sensor data from radar sensors with sensor data from ultrasonic sensors;

detecting, by the controller, an obstacle on the basis of the combined data;

predicting, by the controller, collision or non-collision with the detected obstacle on the basis of the combined data; and

braking, by a brake driver, the vehicle when the collision is predicted,

wherein the step of generating the combined data further comprises generating covariance of the radar sensor data, covariance of the ultrasonic sensor data, and covariance of the combined data on the basis of cross-covariance of the ultrasonic sensor data and the radar sensor data.

11. The side collision avoidance method according to claim 10, further comprising the step of:

outputting an alarm when the collision is predicted.

12. The side collision avoidance method according to claim 10, further comprising driving, by the controller, one of the radar sensors and one of the ultrasonic sensors provided in a direction that is determined according to a left-side or right-side exit mode of the vehicle that is parallel parked, before the step of generating the combined data.

13. The side collision avoidance method according to claim 10, wherein the step of detecting the obstacle comprises detecting a plurality of obstacles on the basis of the combined data, and detecting the plurality of obstacles positioned in an interested area among the detected obstacles as effective obstacles.

14. The side collision avoidance method according to claim 13, wherein the step of detecting the obstacle comprises continuously detecting whether or not the effective obstacles are out of the interested area, on the basis of mathematical models of obstacle state changes.

15. The side collision avoidance method according to claim 13, wherein the step of predicting the collision or non-collision comprises detecting an obstacle positioned in a potential collision area among the effective obstacles as a final obstacle, and calculating a collision probability with the final obstacle to predict collision or non-collision.

16. The side collision avoidance method according to claim 15, wherein the step of predicting the collision or non-collision comprises calculating the collision probability with the final obstacle in consideration of a standard deviation of the covariance of the combined data.

17. The side collision avoidance method according to claim 16, wherein the step of predicting the collision or non-collision comprises calculating the collision probability (D) with the final obstacle on the basis of the standard deviation of the covariance of the combined data by using the following equation: