Evaluating locating measurements of a surroundings sensor for a motor vehicle

Patent metadata

Field	Value
Publication number	US-12024178-B2
Application number	US-201917279336-A
Country	US
Kind code	B2
Filing date	Oct 1, 2019
Priority date	Dec 20, 2018
Publication date	Jul 2, 2024
Grant date	Jul 2, 2024

Abstract

A method for evaluating locating measurements of a surroundings sensor for a motor vehicle. The method includes: associating locating measurements with an object described by an estimated object state, for the locating measurements in each case an association probability being determined for the association of the locating measurement with the object; estimating instantaneous state parameters of the object, including an adaptation of the state parameters to the locating measurements associated with the object, weightings of the locating measurements associated with the object being taken into consideration during the adaptation, for the locating measurements in each case the weighting being dependent on the determined association probability for the association of the particular locating measurement with the object; and transferring the estimated instantaneous state parameters of the object to a state estimator for updating the estimated state of the object. A sensor system is also described.

First claim

The invention claimed is:

1. A method for a surroundings sensor for a motor vehicle, the comprising the following steps:
using a predefined model to initialize an identification of presence of an object with a set of object parameters that defines a state of the object;
subsequent to the initialization:
obtaining from the surroundings sensor a plurality of locating measurements that each indicates a presence at a respective location;
associating a subset of the obtained locating measurements with the object whose presence was previously identified with the initialization using the predefined model; and
assigning to each of the locating measurements of the subset a respective association probability that represents a respective likelihood of the association of the respective locating measurement with the object whose presence was previously identified with the initialization using the predefined model; and

based on the associating, updating the state of the object defined by the set of object parameters of the object based on the subset of the obtained locating measurements, wherein:
for each of the subset of the obtained locating measurements, a respective effect of the respective obtained locating measurement on the update is weighted according to the respective association probability assigned to the respective locating measurement so that different ones of the subset of the obtained locating measurements are differently weighted than one another; and
the updating of the state of the object includes updating at least one of an identification of a shape of the object and an identification of a size of the object.

2. The method as recited in claim 1 , wherein the association probability is a probability that a location of the locating measurement is a location of a real object that corresponds to the object whose presence was previously identified with the initialization using the predefined model.

3. The method as recited in claim 1 , wherein the assigning of the association probability is based on a measuring uncertainty of the locating measurement.

4. The method as recited in claim 1 , wherein the assigning of the association probability is based on an uncertainty of the object parameters of the object.

5. The method as recited in claim 1 , wherein the assigning of the association probability is based on an uncertainty of the predefined model used for the initialization in which initial settings of the object parameters of the object are set.

6. The method as recited in claim 1 , the method further comprising the following steps:
obtaining measuring uncertainties of the locating measurements from the surroundings sensor;
estimating uncertainties of a current state of the object parameters of the object based on the obtained measuring uncertainties of the locating measurements associated with the object, wherein the updating is performed based on the current state of the object parameters and the estimated uncertainties of the object parameters.

7. The method as recited in claim 6 , wherein the estimation of uncertainties is carried out using an unscented transform, the locating measurements associated with the object and the obtained measuring uncertainties of the locating measurements associated with the object being used as input variables of the unscented transform.

8. The method as recited in claim 7 , wherein the estimation of uncertainties includes performing the following steps:
calculating sigma points of the unscented transform using:
a vector, which includes the locating measurements associated with the object, as a mean value estimation for a distribution of the sigma points; and
a matrix, which includes the measuring uncertainties of the locating measurements associated with the object as a covariance matrix for the distribution of the sigma points;

estimating updated object parameters for each of the sigma points of the unscented transform, including an adaptation of the object parameters to the respective sigma point; and
determining a variance of a distribution of the updated object parameters of the object, estimated for the sigma points, as the estimation of the uncertainties.

9. The method as recited in claim 1 , wherein the updating includes the updating of the recorded shape.

10. The method as recited in claim 1 , wherein the updating includes the updating of the recorded size.

11. The method as recited in claim 1 , wherein the assigning of the respective association probability is based on an uncertainty of the locating measurement.

12. The method as recited in claim 1 , wherein the assigning of the respective association probability is based on an uncertainty of the set of object parameters.

13. The method as recited in claim 1 , wherein the assigning of the respective association probability is based on an expected deviation from the predefined model used for the initialization of the presence of the object parameters.

14. A sensor system for a motor vehicle, comprising:
a surroundings sensor; and
a processor configured to:
use a predefined model to initialize an identification of presence of an object with a set of object parameters that defines a state of the object;
subsequent to the initialization:
obtain from the surroundings sensor a plurality of locating measurements that each indicates a presence at a respective location;
associate a subset of the obtained locating measurements with the object whose presence was previously identified with the initialization using the predefined model; and
assign to each of the locating measurements of the subset a respective association probability that represents a respective likelihood of the association of the respective locating measurement with the object whose presence was previously identified with the initialization using the predefined model; and

based on the association, update the state of the object defined by the set of object parameters of the object based on the subset of the obtained locating measurements;

wherein:
for each of the subset of the obtained locating measurements, a respective effect of the respective obtained locating measurement on the update is weighted according to the respective association probability assigned to the respective locating measurement so that different ones of the subset of the obtained locating measurements are differently weighted than one another; and
the update of the state of the object includes updating at least one of an identification of a shape of the object and an identification of a size of the object.

Assignees

• Bosch Gmbh Robert

Inventors

• Lang Stefan
• Gussner Thomas

Classifications

• B60W40/08

  related to drivers or passengers · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• B60W2554/4049

  Relationship among other objects, e.g. converging dynamic objects · CPC title

• B60W40/12 Primary

  related to parameters of the vehicle itself {, e.g. tyre models} · CPC title

• G01S13/88

  Radar or analogous systems specially adapted for specific applications (electromagnetic prospecting or detecting of objects, e.g. near-field detection, G01V3/00) · CPC title