Granted Patent B2

US 12,319,281 · App. 18/155,089 · Granted Jun 3, 2025

Inventor: Alan M. Cordeiro (Farmington Hills, MI)

Assignee: Magna Electronics Inc.

B60W30/12B60W30/18163B60W2420/403B60W2420/408B60W2552/53

Abstract

Claims (54)

1. A vehicular sensing system, the vehicular sensing system comprising:

a camera disposed at a vehicle equipped with the vehicular sensing system and viewing exterior of the vehicle, the camera capturing image data;

a radar sensor disposed at the vehicle and sensing exterior of the vehicle, the radar sensor capturing radar data;

wherein the camera comprises a CMOS imaging array, and wherein the CMOS imaging array comprises at least one million photosensors arranged in rows and columns;

an electronic control unit (ECU) comprising electronic circuitry and associated software;

wherein the electronic circuitry of the ECU comprises at least one data processor;

wherein image data captured by the camera and radar data captured by the radar sensor is processed at the ECU;

wherein the vehicular sensing system, responsive to processing at the ECU of radar data captured by the radar sensor, determines an edge of a road along which the vehicle is traveling;

wherein the vehicular sensing system, responsive to processing at the ECU of image data captured by the camera, determines location of a lane marking of a traffic lane of the road along which the vehicle is traveling;

wherein the vehicular sensing system, after determining location of the lane marking of the traffic lane of the road along with the vehicle is traveling, and responsive to failing to determine a location of a subsequent lane marking of the traffic lane on the road along which the vehicle is traveling via processing at the ECU of the image data captured by the camera, predicts the location of the subsequent lane marking of the road based on the determined edge of the road along which the vehicle is traveling and the location of the lane marking determined prior to failing to determine the location of the subsequent lane marking; and

wherein the vehicle is controlled based at least in part on the predicted location of the lane marking of the road.

2. The vehicular sensing system of claim 1 , wherein the camera views at least forward of the vehicle with a field of view greater than 90 degrees.

3. The vehicular sensing system of claim 1 , wherein the radar sensor comprises a front center radar sensor with a field of sensing greater than 90 degrees.

4. The vehicular sensing system of claim 3 , further comprising at least one corner radar sensor with a field of sensing that at least partially overlaps the field of sensing of the front center radar sensor.

5. The vehicular sensing system of claim 4 , wherein the at least one corner radar sensor comprises a left front corner radar sensor and a right front corner radar sensor.

6. The vehicular sensing system of claim 1 , wherein the vehicular sensing system, responsive to processing by the ECU of image data captured by the camera, estimates a curvature of the road along which the vehicle is traveling.

7. The vehicular sensing system of claim 1 , wherein the vehicular sensing system, responsive to processing by the ECU of radar data captured by the radar sensor, estimates a curvature of the road along which the vehicle is traveling.

8. The vehicular sensing system of claim 7 , wherein the vehicular sensing system estimates the curvature of the road the vehicle is traveling along based on determining the edge of the road along which the vehicle is traveling at a plurality of different distances in front of the vehicle.

9. The vehicular sensing system of claim 1 , wherein the vehicular sensing system halts controlling the vehicle after the vehicle has been controlled for a threshold period of time based at least in part on the predicted location of the lane marking of the road.

10. The vehicular sensing system of claim 1 , wherein the vehicular sensing system halts controlling the vehicle after the vehicle has been controlled for a threshold distance based at least in part on the predicted location of the lane marking of the road.

11. The vehicular sensing system of claim 1 , wherein the vehicular sensing system determines a rolling average of distance between a center of the traffic lane of the road along which the vehicle is traveling and the determined edge of the traffic lane, and wherein the vehicular sensing system predicts the location of the lane marking of the traffic lane of the road based on the determined rolling average.

12. The vehicular sensing system of claim 11 , wherein the vehicular sensing system temporarily ceases determining the rolling average of distance between the center of the traffic lane of the road along which the vehicle is traveling and the determined edge of the traffic lane responsive at least in part to determination of a temporary widening of the traffic lane at an exit ramp or an entry ramp.

13. The vehicular sensing system of claim 1 , wherein the vehicular sensing system predicts the location of the lane marking of the road using a model.

14. The vehicular sensing system of claim 13 , wherein the model is trained using the determined location of the lane marking.

15. A vehicular sensing system, the vehicular sensing system comprising:

a camera disposed at an in-cabin side of a windshield of a vehicle equipped with the vehicular sensing system and viewing at least forward of the vehicle, the camera capturing image data;

a plurality of radar sensors disposed at the vehicle and sensing at least forward of the vehicle, the plurality of radar sensors capturing radar data, and wherein the plurality of radar sensors comprises a front center radar sensor, a left front corner radar sensor with a field of sensing that at least partially overlaps a field of sensing of the front center radar sensor, and a right front corner radar sensor with a field of sensing that at least partially overlaps the field of sensing of the front center radar sensor;

wherein the camera comprises a CMOS imaging array, and wherein the CMOS imaging array comprises at least one million photosensors arranged in rows and columns;

an electronic control unit (ECU) comprising electronic circuitry and associated software;

wherein the electronic circuitry of the ECU comprises at least one data processor;

wherein image data captured by the camera and radar data captured by the plurality of radar sensors is processed at the ECU;

wherein the vehicular sensing system, responsive to processing at the ECU of radar data captured by the plurality of radar sensors, determines an edge of a road along which the vehicle is traveling;

wherein the vehicular sensing system, responsive to processing at the ECU of image data captured by the camera, determines location of a lane marking of a traffic lane of the road along which the vehicle is traveling;

wherein the vehicular sensing system, responsive to processing by the ECU of image data captured by the camera, estimates a curvature of the road along which the vehicle is traveling;

wherein the vehicular sensing system, after determining location of the lane marking of the traffic lane of the road along with the vehicle is traveling, and responsive to failing to determine a location of a subsequent lane marking of the traffic lane on the road along which the vehicle is traveling via processing at the ECU of the image data captured by the camera, predicts the location of the subsequent lane marking of the road based on (i) the determined edge of the road along which the vehicle is traveling, (ii) the estimated curvature of the road along with the vehicle is traveling and (iii) the location of the lane marking determined prior to failing to determine the location of the subsequent lane marking; and

wherein the vehicle is controlled based at least in part on the predicted location of the lane marking of the road.

16. The vehicular sensing system of claim 15 , wherein the camera views at least forward of the vehicle with a field of view greater than 90 degrees.

17. The vehicular sensing system of claim 15 , wherein the front center radar sensor has a field of sensing greater than 90 degrees.

18. The vehicular sensing system of claim 15 , wherein the vehicular sensing system halts controlling the vehicle after the vehicle has been controlled for a threshold period of time based at least in part on the predicted location of the lane marking of the road.

19. The vehicular sensing system of claim 15 , wherein the vehicular sensing system estimates the curvature of the road the vehicle is traveling along based on determining the edge of the road along which the vehicle is traveling at a plurality of different distances in front of the vehicle.

20. A vehicular sensing system, the vehicular sensing system comprising:

a camera disposed at an in-cabin side of a windshield of a vehicle equipped with the vehicular sensing system and viewing at least forward of the vehicle, the camera capturing image data;

a radar sensor disposed at the vehicle and sensing at least forward of the vehicle, the radar sensor capturing radar data;

wherein the camera comprises a CMOS imaging array, and wherein the CMOS imaging array comprises at least one million photosensors arranged in rows and columns;

an electronic control unit (ECU) comprising electronic circuitry and associated software;

wherein the electronic circuitry of the ECU comprises at least one data processor;

wherein image data captured by the camera and radar data captured by the radar sensor is processed at the ECU;

wherein the vehicular sensing system, responsive to processing at the ECU of radar data captured by the radar sensor, determines an edge of a road along which the vehicle is traveling;

wherein the vehicular sensing system, responsive to processing at the ECU of image data captured by the camera, determines location of a lane marking of a traffic lane of the road along which the vehicle is traveling;

wherein the vehicular sensing system trains a machine learning model based on (i) the edge of the road along with the vehicle is traveling and (ii) the determined location of the lane marking of the traffic lane of the road along which the vehicle is traveling, and wherein the machine learning model comprises a neural network;

wherein the vehicular sensing system, after determining location of the lane marking of the traffic lane of the road along with the vehicle is traveling, and responsive to failing to determine a location of a subsequent lane marking of the traffic lane on the road along which the vehicle is traveling via processing at the ECU of the image data captured by the camera, predicts the location of the subsequent lane marking of the road based at least in part on the trained machine learning model; and

wherein the vehicle is controlled based at least in part on the predicted location of the lane marking of the road.

21. The vehicular sensing system of claim 20 , wherein the vehicular sensing system determines a rolling average of distance between a center of the traffic lane of the road along which the vehicle is traveling and the determined edge of the traffic lane, and wherein the vehicular sensing system predicts the location of the lane marking of the traffic lane of the road based on the determined rolling average.

22. The vehicular sensing system of claim 21 , wherein the vehicular sensing system temporarily ceases determining the rolling average of distance between the center of the traffic lane of the road along which the vehicle is traveling and the determined edge of the traffic lane responsive at least in part to determination of a temporary widening of the traffic lane at an exit ramp or an entry ramp.

Assignments (1)

Continuity (2)

References Cited (32)