Method for Satellite-Based Determination of a Vehicle Position

Abstract

The disclosure relates to a method for satellite-based determination of a vehicle position, comprising the following steps: a) receiving GNSS satellite data; b) determining a vehicle's position with the GNSS satellite data received in step a); c) providing input variables that can have an effect on the accuracy of the vehicle position determined in step b); d) determining a positional accuracy of the vehicle position determined in step b) using an algorithm that assigns a positional accuracy to a vehicle position; and e) adapting the algorithm.

Claims

1. A method for satellite-based determination of a vehicle position, the method comprising: a) receiving GNSS satellite data; b) determining a vehicle position of a vehicle with the received GNSS satellite data; c) providing input variables that effect an accuracy of the determined vehicle position; d) determining a positional accuracy of the determined vehicle position using an algorithm that assigns a positional accuracy to the vehicle position; and e) adapting the algorithm.

2. The method according to claim 1, wherein the steps a) to e) are carried out on a vehicle side.

3. The method according to claim 1, wherein at least step e) is carried out externally to the vehicle and at least one information item for adapting the algorithm stored on the vehicle is provided to at least one vehicle.

4. The method according to claim 1, wherein the algorithm determines the positional accuracy as based on the detected vehicle position and at least one of the input variables.

5. A method for improving the accuracy estimation of a satellite-based determination of a vehicle position, the method comprising: i) detecting a GNSS-based vehicle position of the vehicle; ii) receiving input variables that effect an accuracy of the detected GNSS-based vehicle position; iii) detecting a reference position for the detected GNSS-based vehicle position; and iv) adapting an algorithm that assigns a positional accuracy to the detected GNSS-based vehicle position based on at least one of a comparison between the detected GNSS-based vehicle position and the detected reference position and a comparison between the detected GNSS-based vehicle position and at least one of the received input variables.

6. The method according to claim 5, wherein the steps i) to iv) are carried out externally to the vehicle.

7. The method according to claim 5, wherein the steps i) to iv) are carried out on a vehicle side.

8. The method according to claim 5, wherein the adaptation of the algorithm is carried out automatically.

9. The method according to claim 5, wherein the algorithm is a neural network having at least one of weights and threshold values.

10. The method according to claim 9, wherein, in step iv), the at least one of the weights and the threshold values of the algorithm are adjusted.

11. The method according to claim 5, wherein the adapting of the algorithm is carried out one of while the vehicle is stopped and after the vehicle is stopped.

12. The method according to claim 1, wherein the adapting the algorithm further comprises: i) detecting a GNSS-based vehicle position of the vehicle; ii) receiving input variables that effect an accuracy of the detected GNSS-based vehicle position; iii) detecting a reference position for the detected GNSS-based vehicle position; and iv) adapting an algorithm that assigns a positional accuracy to the detected GNSS-based vehicle position based on at least one of a comparison between the detected GNSS-based vehicle position and the detected reference position and a comparison between the detected GNSS-based vehicle position and at least one of the received input variables.

13. The method according to claim 1, wherein the method is carried out by a computer program.

14. The method according to claim 1, wherein the computer program is stored on a machine-readable storage medium.

15. A motion and position sensor configured to carry out a method for satellite-based determination of a vehicle position, the method comprising: a) receiving GNSS satellite data; b) determining a vehicle position of a vehicle with the received GNSS satellite data; c) providing input variables that effect an accuracy of the determined vehicle position; d) determining a positional accuracy of the determined vehicle position using an algorithm that assigns a positional accuracy to the vehicle position; and e) adapting the algorithm.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The solution presented here as well as its technical background will be explained in more detail below on the basis of the figures. It should be noted that the disclosure is not intended to be limited by the exemplary embodiments. In particular, unless explicitly indicated otherwise, it is also possible to extract partial aspects of the facts explained in the figures and to combine them with other components and/or information from other figures and/or the present description. They show schematically:

[0067] FIG. 1: a sequence of a method presented here for satellite-based determination of a vehicle position for a normal operating process, and

[0068] FIG. 2: a sequence of a method presented here for improving the accuracy estimation of a satellite-based determination of a vehicle position for a normal operating process.

DETAILED DESCRIPTION

[0069] FIG. 1 shows a schematic representation of a sequence of a method presented here for satellite-based determination of a vehicle position for a normal operating process. The displayed sequence of method steps a), b), c), d) and e) with the blocks 110, 120, 130, 140, and 150 is provided purely as an example. In block 110, a reception of GNSS satellite data takes place. In block 120 a vehicle position is determined with the GNSS satellite data received in step a). In block 130 input variables are provided that can have an effect on the accuracy of the vehicle position determined in step b). In block 140, a positional accuracy of the vehicle position calculated in step b) is determined using an algorithm which assigns a positional accuracy to a vehicle position. In block 150 an adaptation of the algorithm takes place.

[0070] In particular, the method steps a) and c) or b) and c) may also be executed at least partially in parallel or simultaneously.

[0071] FIG. 2 shows a schematic drawing of a sequence of a method presented here for improving the accuracy estimation of a satellite-based determination of a vehicle position for a normal operating process. The displayed sequence of the method steps i), ii), iii), and iv) with the blocks 210, 220, 230, and 240 is provided purely as an example. In block 210 a GNSS-based vehicle position is detected. In block 220 input variables are received that can affect the accuracy of the vehicle position determined in step i). In block 230 a reference position is detected for the vehicle position detected in step i). In block 240 an adaptation is carried out of an algorithm that assigns a positional accuracy to a vehicle position, taking into account at least one comparison between the vehicle position detected in step i) and the reference position acquired in step iii) and/or at least one of the input variables received in step ii).

[0072] In particular, the method steps i), ii) and iii) may also be executed at least partially in parallel or simultaneously.

[0073] In particular, the solution presented here allows one or more of the following advantages: [0074] By the introduction of an AI system or neural network for learning a function for determining a positional accuracy, memory can be saved on the motion and position sensor. [0075] This new AI system can calculate a positional accuracy within a motion and position sensor more accurately on the basis of existing scenarios. [0076] The memory required for this within the motion and position sensor tends to be significantly smaller than the use of a lookup table. [0077] The use of a reference position system within an autonomous vehicle for training the AI system (deviation of the satellite-based position determination relative to the reference positioning system) provides a means of continuously improving the AI system for the positional accuracy on the motion and position sensor on the basis of new scenarios of vehicles already existing in the field. [0078] The more accurate computation of the positional accuracy, or the output of this improved positional accuracy from the motion and position sensor, leads to an increase in traffic safety in vehicles which use a motion and position sensor, since the other control units know exactly whether or not they can currently trust the position delivered by the motion and position sensor.