Method for satellite-based detection of a vehicle location by means of a motion and location sensor

Patent metadata

Field	Value
Publication number	US-11946746-B2
Application number	US-201916401953-A
Country	US
Kind code	B2
Filing date	May 2, 2019
Priority date	May 3, 2018
Publication date	Apr 2, 2024
Grant date	Apr 2, 2024

Abstract

A method for satellite-based detection of vehicle location uses a motion and location sensor. GNSS data is received as an input variable, at least one further input variable is also received. Weighting factors for the input variable and the at least one further input variable are determined. The input variable and the at least one further input variable are weighted by the weighing factors. The vehicle location is detected via the weighted input variable and the weighted at least one further input variable.

First claim

What is claimed is:

1. A method for satellite-based detection of a vehicle location using a motion and location sensor, the method comprising: receiving, with the motion and location sensor, global navigation satellite system (GNSS) data as an input variable; receiving at least one further input variable; determining weighting factors for the input variable and the at least one further input variable based upon map data; weighting the input variable and the at least one further input variable by the determined weighting factors; calculating the vehicle location using the weighted input variable and the weighted at least one further input variable; and controlling vehicle actuators based upon the calculated vehicle location.

2. The method of claim 1 , wherein the at least one further input variable includes one or more of GNSS correction data, data from acceleration and rotational speed sensors, inertial sensor data, wheel speeds, steering angles, vehicle speed, and direction of travel.

3. The method of claim 1 , further comprising; performing a predictive weighting process.

4. The method of claim 1 , wherein the weighting includes applying a Kalman filter.

5. The method of claim 1 , further comprising: receiving the map data prior to determining the weighting factors.

6. The method of claim 1 , wherein the map data includes at least one of data of a road map and data of a feature map.

7. The method of claim 1 , wherein the map data includes at least one of a position, a size, and a location of further road users within a minimum distance around a vehicle corresponding to the vehicle location to be detected.

8. The method of claim 1 , wherein the map data is provided in a pre-processed form.

9. The method of claim 1 , wherein the determining of the weighting factors is performed by a central processing device or a superordinate processing device.

10. The method of claim 9 , further comprising: transmitting the weighting factors, via a car-to-X communication link, to a vehicle corresponding to the vehicle location to be detected.

11. The method of claim 1 , wherein the weighting weighing of the input variable and the at least one further input variable by the determined weighting factors is performed via application of a Kalman filter.

12. The method of claim 1 , wherein the calculating detecting of the vehicle location is performed via a weighted neural network.

13. The method of claim 1 , wherein the method is performed by executing a computer program.

14. The method of claim 13 , wherein the computer program is stored on a machine-readable storage medium.

15. The method of claim 1 , wherein the determining, the weighting, and the calculating are performed by a computing unit of the motion and location sensor executing program instructions permanently stored in a memory.

Assignees

• Bosch Gmbh Robert

Inventors

• Ewert Marlon Ramon

Classifications

• G06N3/0499

  Feedforward networks · CPC title

• G01C21/30 Primary

  Map- or contour-matching · CPC title

• G01C21/165

  combined with non-inertial navigation instruments · CPC title

• G01S19/49

  whereby the further system is an inertial position system, e.g. loosely-coupled · CPC title

• G06N3/08 Primary

  Learning methods · CPC title