Method for determining the course of the road for a motor vehicle
First Claim
1. A method of determining a course of a driving lane along a road ahead of a vehicle that is driving on the driving lane, comprising steps:
- a) providing a lane model, which models the driving lane, and which includes at least one lane course parameter that models the course of the driving lane;
b) with at least one sensor system of the vehicle, acquiring sensor data regarding surroundings ahead of the vehicle;
c) evaluating at least a portion of the sensor data, comprising;
detecting, from the sensor data, plural candidate structures in the surroundings ahead of the vehicle,for each respective one of the candidate structures, determining a respective tangent line that is a straight line tangent to the respective candidate structure at a selected point thereon, andamong the plural candidate structures, selecting a pair of structures of which the respective tangent lines are parallel to one another;
d) determining an orientation value of the tangent lines of the pair of structures;
e) determining a respective updated value of the at least one lane course parameter and updating the lane model with the respective updated value by adopting the determined orientation value of the tangent lines of the pair of structures as a predicted orientation value of the course of the lane at a point at a first distance in an x-direction ahead of the vehicle; and
f) using the lane model with the respective updated value of the at least one lane course parameter to predictively determine the course of the driving lane, and operating a driver assistance system of the vehicle dependent thereon and in response thereto, to assist in a driving operation of the vehicle;
wherein the steps d) and e) are performed without use of a lateral distance, transversely to the x-direction, of the pair of structures from the course of the driving lane.
1 Assignment
0 Petitions
Accused Products
Abstract
A method for determining the course of the road for a moving motor vehicle having a surroundings sensor system. Sensor data generated by the surroundings sensor system are evaluated to detect lane-relevant features. A lane model having at least one lane model parameter that determines the course of the lane is generated for the road, structures of at least one distance range that are parallel to the road are detected in the sensor data, the tangential direction of at least the one structure that is parallel to the road is determined, and the value of the tangential direction of the structure that is parallel to the road is adopted as the value of the direction of the tangent line at the point of contact with the structure that is parallel to the road to determine at least the one lane model parameter by predictive estimation in the lane model.
42 Citations
24 Claims
-
1. A method of determining a course of a driving lane along a road ahead of a vehicle that is driving on the driving lane, comprising steps:
-
a) providing a lane model, which models the driving lane, and which includes at least one lane course parameter that models the course of the driving lane; b) with at least one sensor system of the vehicle, acquiring sensor data regarding surroundings ahead of the vehicle; c) evaluating at least a portion of the sensor data, comprising; detecting, from the sensor data, plural candidate structures in the surroundings ahead of the vehicle, for each respective one of the candidate structures, determining a respective tangent line that is a straight line tangent to the respective candidate structure at a selected point thereon, and among the plural candidate structures, selecting a pair of structures of which the respective tangent lines are parallel to one another; d) determining an orientation value of the tangent lines of the pair of structures; e) determining a respective updated value of the at least one lane course parameter and updating the lane model with the respective updated value by adopting the determined orientation value of the tangent lines of the pair of structures as a predicted orientation value of the course of the lane at a point at a first distance in an x-direction ahead of the vehicle; and f) using the lane model with the respective updated value of the at least one lane course parameter to predictively determine the course of the driving lane, and operating a driver assistance system of the vehicle dependent thereon and in response thereto, to assist in a driving operation of the vehicle; wherein the steps d) and e) are performed without use of a lateral distance, transversely to the x-direction, of the pair of structures from the course of the driving lane.
-
-
2. A method of determining a course of a lane of a road, on which lane a motor vehicle is driving, wherein the motor vehicle has at least one surroundings sensor system directed toward the road, wherein sensor data generated by the surroundings sensor system are evaluated to detect a plurality of lane-relevant features,
the method comprising: -
generating a lane model having at least one lane model parameter that determines the course of the lane; acquiring the sensor data with the surroundings sensor system; partitioning the sensor data into a near range and a far range relative to the vehicle; in the near range of the sensor data and not in the far range of the sensor data, determining a lane width of the lane of the road, a deviation of the motor vehicle from a middle of the lane, and a yaw angle of the motor vehicle; in the sensor data, detecting a plurality of structures that are parallel to the road, the detecting including; determining whether a detected first structure is parallel to any detected second structure among the plurality of structures at a same distance ahead of the motor vehicle; and precluding the detected first structure from the plurality of structures if the detected first structure is not parallel to any detected second structure at the same distance ahead of the motor vehicle; determining, as a value of a slope of a tangent, a tangential direction of at least one of the plurality of structures that is not precluded and that is parallel to the road; using the value of the slope of the tangent of the at least one of the plurality of structures, and not using a lateral distance for each of the at least one of the plurality of structures in a lateral direction of the motor vehicle, to calculate the at least one lane model parameter in the lane model by a predictive estimation, wherein the at least one lane model parameter represents a curvature of the lane at a distance of the at least one of the plurality of structures; and using the lane model having the lane width of the lane of the road, the deviation of the motor vehicle from the middle of the lane, the yaw angle of the motor vehicle, and the at least one lane model parameter, in a driver assistance system of the motor vehicle to assist a driver of the motor vehicle.
-
-
3. A vehicle with a driver assistance system, configured to carry out a method of determining a course of a lane of a road, on which lane the motor vehicle is driving, wherein the motor vehicle has at least one surroundings sensor system directed toward the road, wherein the surroundings sensor system is configured to generate sensor data, the driver assistance system is configured to evaluate the sensor data to detect a plurality of lane-relevant features, and the driver assistance system is configured:
-
to generate a lane model having at least one lane model parameter that determines the course of the lane; to acquire the sensor data with the surroundings sensor system; to partition the sensor data into a near range and a far range relative to the vehicle; in the near range of the sensor data and not in the far range of the sensor data, to determine a lane width of the lane of the road, a deviation of the motor vehicle from a middle of the lane, and a yaw angle of the motor vehicle; in the sensor data, to detect a plurality of structures that are parallel to the road, by; determining whether a detected first structure is parallel to any detected second structure among the plurality of structures at a same distance ahead of the motor vehicle; and precluding the detected first structure from the plurality of structures if the detected first structure is not parallel to any detected second structure at the same distance ahead of the motor vehicle; to determine, as a value of a slope of a tangent, a tangential direction of at least one of the plurality of structures that is not precluded and that is parallel to the road; to use the value of the slope of the tangent of the at least one of the plurality of structures, and not use a lateral distance for each of the at least one of the plurality of structures in a lateral direction of the motor vehicle, to calculate the at least one lane model parameter in the lane model by a predictive estimation, wherein the at least one lane model parameter represents a curvature of the lane at a distance of the at least one of the plurality of structures; and to use the lane model having the lane width of the lane of the road, the deviation of the motor vehicle from the middle of the lane, the yaw angle of the motor vehicle, and the at least one lane model parameter, in the driver assistance system to assist a driver of the motor vehicle.
-
-
4. A method of determining a course of a driving lane along a road ahead of a vehicle that is driving on the driving lane, comprising steps:
-
a) providing a lane model, which models the driving lane, and which includes at least one lane course parameter that models the course of the driving lane, wherein the lane model includes and is partitioned into a near range lane model and a far range lane model; b) with at least one sensor system of the vehicle, acquiring sensor data regarding surroundings ahead of the vehicle, wherein the sensor data includes and is partitioned into near range sensor data regarding a near range of the surroundings ahead of the vehicle and far range sensor data regarding a far range of the surroundings ahead of the vehicle, wherein the far range is located farther ahead of the vehicle than the near range; c) evaluating at least the far range sensor data, comprising; detecting, from the far range sensor data, plural candidate structures in the far range of the surroundings ahead of the vehicle, for each respective one of the candidate structures, determining a respective tangent line that is a straight line tangent to the respective candidate structure at a selected point thereon, and among the plural candidate structures, selecting a pair of structures of which the respective tangent lines are parallel to one another; d) determining an orientation of the tangent lines of the pair of structures; e) determining a respective updated value of the at least one lane course parameter and updating the far range lane model with the respective updated value only for the far range based on using the determined orientation of the tangent lines of the pair of structures as a predicted orientation of the course of the lane in the far range at a point at a first distance in an x-direction ahead of the vehicle; f) evaluating only the near range sensor data to determine therefrom actual detected parameters for the near range including a lane width of the driving lane, a lateral deviation of the vehicle from a virtual center line of the driving lane, and a yaw angle of the vehicle in the near range; g) generating and updating the near range lane model based only on the actual detected parameters for the near range; and h) using the lane model with the respective updated value of the at least one lane course parameter to predictively determine the course of the driving lane, and operating a driver assistance system of the vehicle dependent thereon and in response thereto, to assist in a driving operation of the vehicle. - View Dependent Claims (5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. A method of determining a course of a road on which a vehicle is driving, comprising steps:
-
a) providing a model including at least one course parameter that models the course of the road ahead of the vehicle, wherein the model includes and is partitioned into a near range model and a far range model; b) with a sensor system of the vehicle, acquiring sensor data regarding surroundings ahead of the vehicle, wherein the sensor data includes and is partitioned into near range sensor data regarding a near range of the surroundings ahead of the vehicle and far range sensor data regarding a far range of the surroundings ahead of the vehicle, wherein the far range is located farther ahead of the vehicle than the near range; c) evaluating at least the far range sensor data, comprising; detecting, from the far range sensor data, plural candidate structures in the far range of the surroundings ahead of the vehicle, for each respective one of the candidate structures, determining a respective tangent line that is a straight line tangent to the respective candidate structure at a selected point thereon, and among the plural candidate structures, selecting a pair of structures of which the respective tangent lines are parallel to one another; d) determining an orientation of the tangent lines of the pair of structures; e) adopting the determined orientation of the tangent lines of the pair of structures as a predicted orientation of the course of the road in the far range at a road point at a first distance ahead of the vehicle determined from the selected points on the pair of structures; f) determining a respective updated value of the at least one course parameter and updating the far range model with the respective updated value only for the far range based on the predicted orientation of the course of the road in the far range at the road point at the first distance ahead of the vehicle; g) evaluating only the near range sensor data to determine therefrom actual detected parameters including a lane width of a driving lane on the road, a lateral deviation of the vehicle from a virtual lane center line of the driving lane on the road, and a yaw angle of the vehicle in the near range; h) generating and updating the near range model based only on the actual detected parameters for the near range; and i) using the model with the respective updated value of the at least one course parameter to predictively determine the course of the road, and operating a driver assistance system of the vehicle dependent thereon and in response thereto, to assist in a driving operation of the vehicle. - View Dependent Claims (15, 16, 17, 18, 19)
-
-
20. A method of operating a vehicle that is driving along a driving lane, comprising steps:
-
a) providing a lane model, which includes a model function that models the course of the driving lane, wherein the lane model includes and is partitioned into a near range lane model and a far range lane model; b) with sensors of the vehicle, acquiring sensor data regarding surroundings ahead of the vehicle, wherein the sensor data includes and is partitioned into near range sensor data regarding a near range of the surroundings ahead of the vehicle and far range sensor data regarding a far range of the surroundings ahead of the vehicle, and wherein the far range is located farther ahead of the vehicle than the near range, and in the far range sensor data detecting pertinent elongated structures of structure types that extend longitudinally along a roadway; c) for each respective one of the pertinent elongated structures, determining a respective tangent line that is a straight line tangent to the respective pertinent elongated structure at a selected point thereon, and determining a respective slope value of each respective tangent line in a ground plane of the lane model; d) determining an updated model function only for the far range lane model based on the respective slope values of the tangent lines of the pertinent elongated structures in the far range, such that respective first derivatives of the updated model function at respective x-values in the ground plane are respectively equal to the respective slope values; e) evaluating only the near range sensor data to determine therefrom actual detected parameters for the near range including a lane width of the driving lane, a lateral deviation of the vehicle from a virtual center line of the driving lane, and a yaw angle of the vehicle in the near range; f) generating and updating the near range lane model based only on the actual detected parameters for the near range; and g) using the lane model with the updated model function to predictively determine the course of the driving lane, and operating a driver assistance system of the vehicle dependent thereon and responsive thereto, to assist in a driving operation of the vehicle. - View Dependent Claims (21, 22, 23, 24)
-
Specification