IP Library Granted Patent US 12674682
Granted Patent B2
US 12674682 · App. 18/936,442 · Granted Jul 7, 2026

Method and system for generating a localization map containing at least one unique combination of features

Inventors: Jan Rohde (Stuttgart, DE); Philipp Rasp (Reusten, DE)
Assignee: ROBERT BOSCH GMBH
G01C21/3841G01C21/3815
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12674682
App. No.
18/936,442
Filed
Nov 4, 2024
Granted
Jul 7, 2026
Kind
B2
Art Unit
3661
USPC
701/450
Abstract

A method for generating a localization map for operating an automated and/or assisting vehicle system of a vehicle. Fleet data are collected by traversing a traffic route portion with fleet vehicles. The localization map is generated from the collected fleet data. A unique combination of features is ascertained from the collected fleet data. Based on a result of a comparison of the unique combination of features with fleet data for each individual traversal of the traffic route portion or with a modeling of a sensor detection range of a non-fleet vehicle along the traffic route portion, it is ascertained whether the unique combination of features can be detected by a surrounding area sensor system of the fleet vehicles or the vehicle. The unique combination of features is stored in the preliminary localization map if the unique combination of features can be detected by the surrounding area sensor system.

Claims (23)

1 . A method for generating a localization map, containing at least one unique combination of features, for operating an automated and/or assisting vehicle system of a vehicle, the method comprising the following steps:

collecting fleet data by traversing a traffic route portion, assigned to the localization map, using fleet vehicles of a vehicle fleet;

generating the localization map from the collected fleet data;

ascertaining a unique combination of features from the collected fleet data;

ascertaining, based on a result of a comparison of the unique combination of features either with fleet data for each individual traversal of the traffic route portion or with a modeling of a sensor detection range of a non-fleet vehicle along the traffic route portion, whether or not the unique combination of features can be detected by a surrounding area sensor system of the fleet vehicles or the non-fleet vehicle; and

storing the unique combination of features in the localization map when the unique combination of features can be detected by the surrounding area sensor system;

ascertaining at least one quality value for the unique combination of features;

storing the quality value in the localization map; and

performing a self-localization, by an automated and/or assisting vehicle system of at least one of the fleet vehicles or at least one non-fleet vehicle, using the localization map containing the at least one unique combination of features whose quality value stored in the localization map is above a predefined lower limit value.

2 . The method according to claim 1 , further comprising:

ascertaining, based on the result of the comparison, from which lane or lanes of the traffic route portion the unique combination of features can be detected by the surrounding area sensor system.

3 . The method according to claim 1 , wherein the quality value for the unique combination of features is ascertained using: (i) a detection rate, which is ascertained from the result of the comparison and specific to the unique combination of features, and/or (ii) a visibility of the unique combination of features, which visibility is ascertained from the result of the comparison, from at least two different regions of the traffic route portion, and/or (iii) a currentness of the fleet data.

4 . A system for generating a localization map, containing at least one unique combination of features, for operating an automated and/or assisting vehicle system of a vehicle, comprising:

a plurality of fleet vehicles, each having at least one surrounding area sensor system;

at least one central data processing unit, which can be connected to the fleet vehicles for collecting fleet data obtained by traversing a traffic route portion, assigned to the localization map, with the fleet vehicles, and the central data processing unit being configured to generate the localization map from the collected fleet data and to ascertain a unique combination of features from the collected fleet data, wherein the central data processing unit is configured to ascertain, based on a result of a comparison of the unique combination of features either with fleet data for each individual traversal of the traffic route portion or with a modeling of a sensor detection range of a non-fleet vehicle along the traffic route portion, whether or not the unique combination of features can be detected by the surrounding area sensor system of the fleet vehicles or the bon- or the non-fleet,

to store the unique combination of features in the localization map if the unique combination of features can be detected by the surrounding area sensor system,

to ascertain at least one quality value for the unique combination of features, and to store the quality value in the localization map;

wherein an automated and/or assisting vehicle system of at least one of the fleet vehicles or at least one non-fleet vehicle performs a self-localization using the localization map containing the at least one unique combination of features whose quality va lue stored in the localization map is above a predefined lower limit value.

5 . The system according to claim 4 , wherein the central data processing unit is configured to ascertain, on the basis of the result of the comparison, from which lane or lanes of the traffic route portion the unique combination of features can be detected by the surrounding area sensor system.

6 . The system according to claim 4 , wherein the quality value for the unique combination of features is ascertained using:

(i) a detection rate, which is ascertained from the result of the comparison and specific to the unique combination of features, and/or (ii) a visibility of the unique combination of features, which visibility is ascertained from the result of the comparison, from at least two different regions of the traffic route portion, and/or (iii) a currentness of the fleet data.

7 . The system according to claim 4 , wherein the central data processing unit is configured to generate a separate detection query for each unique combination of features and to send the separate detection query to the fleet vehicles in order to detect the unique combination of features using the surrounding area sensor system of each fleet vehicle during a traversal of the traffic route portion.

8 . The system according to claim 4 , wherein the central data processing unit is configured to ascertain, for the operation of the automated and/or assisting vehicle system, a route and trajectory planning with which unique combinations of features can be detected.