Method for estimating the quality of localization in the self-localization of a vehicle, device for carrying out the steps of the method, vehicle, and computer program
A method for estimating the quality of localization using sensor detection, wherein the vehicle detects dynamic objects on the road and in the direct surroundings of the road and estimates the dimensions of the objects. The movement of these objects in the near future is estimated. The outer casings of these objects are entered into a map of the surroundings. From the perspective of the sensors used to detect the features in the surroundings, the limitations of the fields of view and the predicted temporal development thereof resulting from the movement of the transportation vehicle and the predicted movements of the objects are entered into the map of the surroundings. The surrounding features that have been entered into the map of the surroundings and which may at visible in the near future are determined. An upper limit for a measure of the quality of localization is estimated.
1. A method for estimating a quality of localization in a self-localization of a transportation vehicle in which a map of a surrounding area is used for the self-localization, the map being used in controlling the transportation vehicle, the method comprising:
the transportation vehicle, when driving on a road, attempting to detect a number of landmarks recorded in the map of the surrounding area using sensors;
determining, by the transportation vehicle, a position of the transportation vehicle from positions of the number of landmarks;
determining, by the transportation vehicle, a future visibility of landmarks by:
detecting obstacles which restrict the visibility of landmarks, wherein detecting the obstacles comprises detecting moving obstacles on the roadway and optionally in the surrounding area of the roadway using sensors;
estimating movement trajectories of the moving obstacles; and
recording projected positions of the moving obstacles in the map of the surrounding area; and
estimating, by the transportation vehicle, the quality of localization in the self-localization of the transportation vehicle based on the visibility of the landmarks.
2. The method of claim 1 , wherein recording the projected positions of the moving obstacles in the map of the surrounding area comprises recording a spatial extent of the moving obstacles.
3. The method of claim 1 , wherein determining the future visibility of landmarks further comprises estimating a future visibility range of a sensor of the transportation vehicle.
4. The method of claim 3 , further comprising determining the landmarks to be observed in future based on the determined future visibility ranges.
5. The method of claim 4 , wherein the quality of localization in the self-localization of the transportation vehicle is determined based on the number of landmarks to be observed in the future.
6. The method of claim 4 , wherein the quality of localization is determined through statistical evaluation of the landmarks to be observed in the future, taking account of the positions of the landmarks in relation to one another.
7. The method of claim 6 , wherein a covariance of the positions of the landmarks which are to be observed in relation to one another is calculated for the statistical evaluation of the landmarks to be observed in the future.
8. A device for estimating a quality of localization in a self-localization of a transportation vehicle in which a map of a surrounding area is used for the self-localization, the map being used in controlling the transportation vehicle, wherein the device comprises:
at least one processor device configured to carry out a method comprising:
while the transportation vehicle is driving on a road, attempting to detect a number of landmarks recorded in the map of the surrounding area using sensors;
determining a position of the transportation vehicle from positions of the number of landmarks;
determining a future visibility of landmarks by:
detecting obstacles which restrict the visibility of landmarks, wherein detecting the obstacles comprises detecting moving obstacles on the roadway and optionally in the surrounding area of the roadway using sensors;
estimating movement trajectories of the moving obstacles; and
recording projected positions of the moving obstacles in the map of the surrounding area; and
estimating the quality of localization in the self-localization of the transportation vehicle based on the visibility of the landmarks.
9. A transportation vehicle, comprising the device of claim 8 .
10. A non-transitory computer readable medium including computer program code which, when executed in a processor device, carries out the method of claim 1 .
11. The device of claim 8 , wherein recording the projected positions of the moving obstacles in the map of the surrounding area comprises recording a spatial extent of the moving obstacles.
12. The device of claim 8 , wherein determining the future visibility of landmarks further comprises estimating a future visibility range of a sensor of the transportation vehicle.
13. The device of claim 12 , wherein the at least one processor is further configured to determine the landmarks to be observed in future based on the determined future visibility ranges.
14. The device of claim 13 , wherein the quality of localization in the self-localization of the transportation vehicle is determined based on the number of landmarks to be observed in the future.
15. The device of claim 13 , wherein the quality of localization is determined through statistical evaluation of the landmarks to be observed in the future, taking account of the positions of the landmarks in relation to one another.
16. The device of claim 15 , wherein a covariance of the positions of the landmarks which are to be observed in relation to one another is calculated for the statistical evaluation of the landmarks to be observed in the future.