Method for ascertaining a description of a lane

Patent metadata

Field	Value
Publication number	US-11062151-B2
Application number	US-201715816807-A
Country	US
Kind code	B2
Filing date	Nov 17, 2017
Priority date	May 20, 2015
Publication date	Jul 13, 2021
Grant date	Jul 13, 2021

Abstract

A method for ascertaining a description of a lane which is in an environment of a vehicle includes ascertaining an assignment function that is set up to assign different values of a feature vector different descriptions of a lane. The method also includes ascertaining environment data of the vehicle, where the environment data includes information about a roadway marking and/or about one or more objects in the environment of the vehicle. In addition, the method includes ascertaining a current value of the feature vector on the basis of the environment data, and determining a description of the lane using the assignment function and using the current value of the feature vector.

First claim

What is claimed is:

1. A method for ascertaining a description of a lane which is in an environment of a vehicle, wherein the method comprises the acts of:
ascertaining an assignment function that is set up to assign different values of a feature vector different descriptions of a lane, wherein the feature vector comprises a multiplicity of features;
ascertaining environment data of the vehicle, wherein the environment data includes information about at least one of a roadway marking and one or more objects in the environment of the vehicle;
ascertaining a current value of the feature vector on the basis of the environment data;
wherein ascertaining the current value of the feature vector further comprises:
detecting a multiplicity of objects in the environment of the vehicle on the basis of the environment data;
ascertaining distances of the multiplicity of objects from the vehicle; and
including the multiplicity of objects in the feature vector in a distance-dependent order based on the ascertained distances of each respective one of the multiplicity of objects; and

determining a description of the lane using the assignment function and using the current value of the feature vector;
wherein the assignment function comprises at least one of:
a neural network having a multiplicity of neurons, wherein a neuron is set up to assign a representative value of the feature vector an applicable description of the lane; and
a multiplicity of clusters having an applicable multiplicity of cluster representatives, wherein the cluster representative of a cluster has an identical dimension to the feature vector, and wherein each of the multiplicity of clusters has an assigned description of the lane;

wherein determining the description of the lane comprises at least one of:
ascertaining a measure of distance between the current value of the feature vector and the representative values of the multiplicity of neurons; and
ascertaining a measure of distance between the current value of the feature vector and the multiplicity of cluster representatives;

wherein the measure of distance comprises a quadratic Euclidean distance; and
one or more weights of the measure of distance is dependent on a number N of objects for which the feature vector has a feature.

Assignees

• Bayerische Motoren Werke Ag

Inventors

• Yamashita Yusaku
• Tanzmeister Georg
• Hofmann Marc

Classifications

• G06V10/82

  using neural networks · CPC title

• B60W2552/30

  Road curve radius · CPC title

• B60W2552/53

  Road markings, e.g. lane marker or crosswalk · CPC title

• B60W60/001

  Planning or execution of driving tasks · CPC title

• B60W2552/10

  Number of lanes · CPC title