Method for determining a lane change indication of a vehicle

1. A method for determining a lane change indication of a vehicle, comprising:

loading a lane change model and position data of the vehicle, wherein

the position data indicate a distance between the vehicle and a lane center of a lane of a roadway on which the vehicle is currently located, and

the lane change model is configured as a convolutional neural network; and

determining a lane change indication, wherein

the determination is performed using the position data and the lane change model, and

the determination comprises detecting a point of discontinuity in the distance between the vehicle and the lane center of the lane of the roadway.

2. The method according to claim 1 , wherein

the position data comprise at least two data points, and

each data point indicates the distance between a vehicle reference point of the vehicle and a lane center of a roadway at a particular time.

3. The method according to claim 1 , wherein

the point of discontinuity is a change of sign.

4. The method according to claim 1 , further comprising:

calculating a two-dimensional projection using a surroundings model, wherein the determination is also performed taking into consideration the surroundings model and/or the two-dimensional projection.

5. The method according to claim 4 , wherein

the two-dimensional projection is formed by an image section of a rear view or front view with respect to the vehicle.

6. The method according to claim 5 , wherein

the two-dimensional projection at least partly indicates a roadway marking and the vehicle.

7. The method according to claim 4 , wherein

the two-dimensional projection at least partly indicates a roadway marking and the vehicle.

8. The method according to claim 5 , wherein

the surroundings model is formed by camera data, distance sensor data, a road model and/or map data, by way of sensor fusion.

9. The method according to claim 4 , wherein

the surroundings model is formed by camera data, distance sensor data, a road model and/or map data, by way of sensor fusion.

10. The method according to claim 9 , wherein

the road model comprises at least one indication about a road surface, a rolling resistance and/or a number of lanes of a roadway.

11. The method according to claim 1 , wherein

the position data form an input for the lane change model, and

the lane change indication indicates whether the vehicle is performing, will perform, or has performed a lane change.

12. The method according to claim 1 , further comprising:

training a classifier using a multiplicity of lane change indications.

13. The method according to claim 12 , wherein

the classifier is a neural network.

14. A computer product comprising a non-transitory computer-readable storage medium having stored thereon program code that, when executed by a processor, carries out the acts of:

loading a lane change model and position data of a vehicle, wherein

the position data indicate a distance between the vehicle and a lane center of a lane of a roadway on which the vehicle is currently located;

determining a lane change indication, wherein

the determination is performed using the position data and the lane change model; and

training a classifier using a multiplicity of lane change indications, wherein

the multiplicity of lane change indications comprises:

detecting a point of discontinuity in the distance between the vehicle and the lane center of the lane of the roadway; and

calculating a two-dimensional projection using a surroundings model, wherein the surroundings model comprises one or more of:

camera data;

distance sensor data;

a road model; and/or

map data.

15. A vehicle, comprising:

a computer-product according to claim 14 ; and

a vehicle computing apparatus having the processor configured to execute the program code stored on the storage medium.

16. A vehicle, comprising:

a computing apparatus that is designed to control the vehicle at least partly using a neural network, that is trained with a multiplicity of lane change indications, wherein

the multiplicity of lane change indications is determined by:

loading a lane change model and position data of the vehicle, wherein

the position data indicate a distance between the vehicle and a lane center of a lane of a roadway on which the vehicle is currently located;

determining a lane change indication by detecting a point of discontinuity in the distance between the vehicle and the lane center of the lane of the roadway; and

calculating a two-dimensional projection using a surroundings model, wherein

the determination is also performed taking into consideration the surroundings model and/or

the two-dimensional projection, and

the two-dimensional projection at least partly indicates a roadway marking and indicates the vehicle.

17. The vehicle according to claim 16 , wherein the vehicle is a self-driving vehicle.