COMPLETING FEATURE-BASED LOCALIZATION MAPS

Abstract

A method is provided for creating at least one map of vehicle surroundings with the aid of a control unit. It is checked based on a comparison between received measured data and stored or received map data, whether first features, for example semantic features, are present and complete. First features available in a vehicle surroundings are extracted from the received measured data if no or incomplete map data are present. It is checked whether a localization is possible within the vehicle surroundings with the aid of the first semantic features. If a localization is imprecise or not possible with the aid of the ascertained first features, second features are extracted from the received measured data. A digital map of vehicle surroundings is created based on the ascertained first features and/or the second features. Furthermore, a control unit, a computer program as well as a machine-readable memory medium are provided.

Claims

1. A method for creating at least one digital map of a vehicle surroundings using a control unit, the method comprising the following steps: checking, based on a comparison between received measured data and stored or received map data, whether first features are present and complete; extracting the first features available in a vehicle surroundings from the received measured data when no or incomplete map data are present, it being checked whether a localization is possible within the vehicle surroundings using the first features; extracting, when a localization is imprecise or not possible using the first features, second features from the received measured data; and creating a digital map of the vehicle surroundings based on the first features and/or the second features.

2. The method as recited in claim 1, wherein, when a localization is imprecise or not possible using the ascertained first features, all of the second features are extracted from the received measured data to complete the ascertained map features.

3. The method as recited in claim 1, wherein the digital map is created based at least in part on a fusion of the first features and the second features.

4. The method as recited in claim 1, wherein the first features are produced based on the second features and stored in the digital map.

5. The method as recited in claim 1, wherein the first features are semantic features or geometric features or sensor-specific features of a first vehicle sensor.

6. The method as recited in claim 1, wherein the second features are geometric features or sensor-specific features of a second vehicle sensor.

7. The method as recited in claim 1, wherein the comparison between the received measured data and the stored map data is carried out based on a statistical method, including based on an exceedance of a threshold value of an uncertainty of a localization, or based on a number of available semantic features, or based on a repetition of semantic features.

8. A control unit configured to create at least one digital map of a vehicle surroundings using a control unit, the control unit configured to: check, based on a comparison between received measured data and stored or received map data, whether first features are present and complete; extract the first features available in a vehicle surroundings from the received measured data when no or incomplete map data are present, it being checked whether a localization is possible within the vehicle surroundings using the first features; extract, when a localization is imprecise or not possible using the first features, second features from the received measured data; and create a digital map of the vehicle surroundings based on the first features and/or the second features.

9. A non-transitory machine-readable memory medium on which is stored a computer program for creating at least one digital map of a vehicle surroundings, the computer program, when executed by a computer or control unit, causing the computer or control unit to perform the following steps: checking, based on a comparison between received measured data and stored or received map data, whether first features are present and complete; extracting the first features available in a vehicle surroundings from the received measured data when no or incomplete map data are present, it being checked whether a localization is possible within the vehicle surroundings using the first features; extracting, when a localization is imprecise or not possible using the first features, second features from the received measured data; and creating a digital map of the vehicle surroundings based on the first features and/or the second features.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0029] FIG. 1 shows a schematic top view of a vehicle system according to one specific embodiment of the present invention.

[0030] FIG. 2 shows a schematic flowchart for the purpose of illustrating a method according to the present invention according to one specific embodiment.

DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0031] FIG. 1 shows a schematic top view of a vehicle system 1 according to one specific embodiment. Vehicle system 1 includes at least one vehicle 2 including several vehicle sensors 4, 6.

[0032] In particular, vehicle 2 includes a first vehicle sensor 4, which is designed as a LIDAR sensor by way of example. Furthermore, a second vehicle sensor 6 is provided, which is designed as a radar sensor.

[0033] Vehicle sensors 4, 6 are used to ascertain measured data by scanning vehicle surroundings U. The collected measured data are received by a vehicle-internal control unit 8.

[0034] Control unit 8 may process and, in particular, evaluate the measured data. Moreover, control unit 8 may send the measured data via a wireless communication link 10 to a vehicle-external server unit 12, which is designed as a cloud, for example.

[0035] Vehicle-external server unit 12 may process the measured data to extract landscape features or features 14 and use them to create a digital map 16.

[0036] FIG. 2 shows a schematic flowchart for the purpose of illustrating a method 18 according to the present invention according to one specific embodiment. Method 18 is described based on vehicle system 1 shown in FIG. 1.

[0037] Vehicle 2 travels 20 vehicle surroundings U and decides, whether it should transfer the ascertained measured data to external server unit 12. For this purpose, it is checked 21, whether a map is available.

[0038] If there is no map available for vehicle surroundings U, a digital map is created 22 by vehicle 2 for this area. This takes place by transferring the measured data to external server unit 12 or by control unit 8 in a vehicle-internal manner that processes the measured data in a digital map section.

[0039] If a digital map is available, a check with regard to the quality of this map 23 may be carried out. In the case of a sufficient quality of the available map, no further action 24 is needed, since vehicle 2 is easily able to locate itself within the map.

[0040] If the quality of the map is not sufficient for a localization, the measured data of vehicle sensors 4, 6 are transferred to external server unit 12 to optimize or complete 25 the map.

[0041] It is checked based on a comparison between received measured data and stored or received map data, whether first features, for example semantic features, are present and complete 26.

[0042] First features available in vehicle surroundings U are extracted from the received measured data, if no or incomplete map data are present. It is checked, whether a localization within vehicle surroundings U is possible with the aid of the first semantic features. The corresponding features are sent 27 to external server unit 12, if a localization is possible.

[0043] If a localization is imprecise or not possible with the aid of the ascertained first features, second features are extracted 28 from the received measured data. The second features may be, for example, geometric features. Subsequently, a digital map of vehicle surroundings U is created 29 based on the ascertained first features and/or the second features.

[0044] Control unit 8 of the vehicle is able to decide whether the second features are additionally ascertained. The first features are prioritized in the illustrated exemplary embodiment, since, as semantic features, they are robust and require little memory space.