Method for assessing an affiliation of a sensing point to an object in a surrounding area of motor vehicle, and driver assistance system

Patent metadata

Field	Value
Publication number	US-10643082-B2
Application number	US-201615563171-A
Country	US
Kind code	B2
Filing date	Mar 22, 2016
Priority date	Mar 31, 2015
Publication date	May 5, 2020
Grant date	May 5, 2020

Abstract

The invention relates to a method for assessing an affiliation of a sensing point (12, 13, 19, 20) to an object in a surrounding area (7, 8) of a motor vehicle (1), in which the sensing point (12, 13, 19, 20) is sensed using a first sensor device (4) of the motor vehicle (1), and a fuzziness zone (14, 15) characterizing a positional fuzziness of the sensing point (12, 13, 19, 20) is formed around the sensing point (12, 13, 19, 20), wherein the assessment of the affiliation of the sensing point (12, 13, 19, 20) to the object takes into consideration at least one position of a further sensing point (12, 13, 19, 20) of the object, wherein an overall fuzziness zone (16) is formed on the basis of the fuzziness zone (14, 15) of the sensing point (12, 13, 19, 20), and the affiliation of the sensing point (12, 13, 19, 20) to the object is acknowledged if the sensing point (12, 13, 19, 20) and the further sensing point (12, 13, 19, 20) are situated in an area formed by the overall fuzziness zone (16). The invention also relates to a driver assistance system (2) and a motor vehicle (1).

First claim

The invention claimed is:

1. The method for assessing an affiliation of a sensing point to an object in a surrounding area of a motor vehicle, comprising:
sensing the sensing point using a first sensor device of the motor vehicle; and
forming a fuzziness zone characterizing a positional fuzziness of the sensing point around the sensing point,
forming an overall fuzziness zone based on the fuzziness zone of the sensing point; and
assessing whether the sensing point is affiliated to the object by taking into consideration at least one position of a further sensing point,
wherein the sensing point is determined to be affiliated to the object when the sensing point and the further sensing point are both situated in an area formed by the overall fuzziness zone, and
wherein the further sensing point is a reference point that is affiliated to the object,
wherein the fuzziness zone of the sensing point is produced as a two-dimensionally elliptical fuzziness zone,
wherein the two-dimensionally elliptical fuzziness zone indicates a weighting for a probability of the positional fuzziness for each direction of axes of the elliptical fuzziness zone.

2. The method according to claim 1 , wherein a further fuzziness zone is formed around the further sensing point, and the overall fuzziness zone is formed by summing the fuzziness zone and the further fuzziness zone to increase a statement probability of the detected object.

3. The method according to claim 2 , wherein the further fuzziness zone is produced as a two-dimensionally elliptical fuzziness zone.

4. The method according to claim 1 , wherein the fuzziness zone and/or a further fuzziness zone produced around the further sensing point have their shape adapted on the basis of the location of the sensing points in relation to the overall fuzziness zone.

5. The method according to claim 4 , wherein the adaptation is performed according to at least one first affiliation statement.

6. The method according to claim 4 , wherein the affiliation of the sensing point to the object is assessed by virtue of a covariance matrix being formed on the basis of a distance between the sensing points and a Mahalanobis distance being produced on the basis of the covariance matrix.

7. The method according to claim 6 , wherein a check is performed to determine whether the Mahalanobis distance is less than a prescribed gate value of 1, and, in the event of the Mahalanobis distance being less than the prescribed gate value, and the two sensing points being situated within the overall fuzziness zone, the sensing point is assessed as being affiliated to the object.

8. The method according to claim 7 , wherein at least one fuzziness zone has its shape and/or orientation adapted if the Mahalanobis distance of an affiliation assessment is greater than the prescribed gate value.

9. The method according to claim 8 , wherein at least one fuzziness zone is adapted if, in one assessment scenario, a number N of affiliation assessments for sensing points with respect to an object is greater than a threshold value, which number N has respectively been assessed with a Mahalanobis distance greater than the prescribed gate value.

10. The method according to claim 7 , wherein the surrounding area is sensed using a second sensor device that is functionally different from the first sensor device, and sensing points of the second sensor device are assessed on the basis of the affiliation assessment taken as a basis for the first sensor device.

11. The method according to claim 10 , wherein the affiliation assessments of the two sensor devices are compared and a statement accuracy of at least one sensor device is rated on the basis thereof.

12. The method according to claim 6 , wherein a check is performed to determine whether the Mahalanobis distance is less than a prescribed gate value of 1, and, in the event of the Mahalanobis distance being less than the prescribed gate value, the covariance matrix is reduced.

13. The method according to claim 1 , wherein the sensing point and the further sensing point are associated to form a fused sensing point if the two sensing points are situated in the area of the overall fuzziness zone.

14. The method according to claim 1 , wherein the object characterized by affiliated sensing points is entered into a map of the surrounding area.

15. A driver assistance system having at least one first sensor device and an evaluation unit that is configured to carry out the method according to claim 1 .

Assignees

• Valeo Schalter & Sensoren Gmbh

Inventors

• Bariant Jean-Francois
• Heimberger Markus

Classifications

• G08G1/166

  for active traffic, e.g. moving vehicles, pedestrians, bikes · CPC title

• G08G1/168

  Driving aids for parking, e.g. acoustic or visual feedback on parking space · CPC title

• G05D1/0238

  using obstacle or wall sensors (G05D1/0246 and G05D1/0289 take precedence; lidar systems designed for anti-collision purposes G01S17/93) · CPC title

• G08G1/165 Primary

  for passive traffic, e.g. including static obstacles, trees · CPC title

• G06K9/00805

  Physics · mapped topic