# US 11,442,913 B2 · Method and device for creating a localization map

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,442,913 B2
- Document ID: US11442913B2
- Status: Granted
- Kind: B2
- Application number: 16/983,756
- Filed: 2020-08-03
- Published: 2021-03-25
- Granted: 2022-09-13
- Earliest claimed: 2019-09-24
- Assignees: Robert Bosch GmbH
- Applicants: Robert Bosch GmbH
- Inventors: Carsten Hasberg; Jan Rohde
- Web page: https://patentgrep.com/patent/US11442913B2

## CPC

- G06F 16/2237: {Vectors, bitmaps or matrices}
- G06F 16/29: Geographical information databases
- G01C 21/3833: {characterised by the source of data}
- G01C 21/387: {Organisation of map data, e.g. version management or database structures}
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method and device for creating a localization map, including a step of receiving environmental data values, a step of dividing the environmental data values into at least two separate data records, a step of creating a plurality of partial maps, a step of creating the localization map and a step of making the localization map available.

## Claims

### Claim 1

A method for creating a localization map, the method comprising:
receiving environmental data values which represent an environment of at least one vehicle, wherein the environmental data values are acquired utilizing a driving environment sensor system of a vehicle, and subsequently transmitted for reception, and wherein the environment of the at least one vehicle includes at least a partially overlapping area of subareas, each of the subareas corresponding to an environment of one vehicle;
dividing the environmental data values into at least two separate data records;
creating a plurality of partial maps, based on the at least two separate data records;
creating the localization map, based on the plurality of partial maps, depending upon a consistency check of the plurality of partial maps; and
making the localization map available;
wherein the creating of the plurality of partial maps includes inserting environmental features, which are included in a surrounding area, into a basemap,
wherein the creating of the plurality of partial maps includes starting from the at least two separate data records, in which at least two partial maps are created which represent different aspects, including at least two of: different sensors, different times of acquisition, different weather conditions, different traffic conditions and/or traffic densities, of the environment,
wherein the consistency check of the at least two partial maps includes a check of whether the at least two partial maps are merge-able to form the localization map, and wherein it is checked whether the at least two partial maps, based on individual environmental features, are congruent within predetermined tolerance ranges and/or are able to be made congruent,
wherein a result of the consistency check is evaluated to identify errors in the creating of the plurality of partial maps, and when the consistency check fails, an error in the mapping is inferred.

### Claim 2 (depends on 1)

The method as recited in claim 1, wherein the dividing is carried out as a function of at least one division criterion, the at least one division criterion being selected as a function of environmental properties of a surrounding area.

### Claim 3 (depends on 2)

The method as recited in claim 2, wherein the at least one division criterion is selected as a function of a weighting of the environmental properties, the weighting being based on predetermined criteria and/or on a machine learning approach.

### Claim 4 (depends on 1)

The method as recited in claim 1, wherein the consistency check is carried out using a similarity metric and an identification, based on the similarity metric, and minimization of an effect of mapping errors.

### Claim 5

An apparatus for creating a localization map, comprising:
an the arithmetic logic unit configured to perform the following:
receiving environmental data values which represent an environment of at least one vehicle, wherein the environmental data values are acquired utilizing a driving environment sensor system of a vehicle, and subsequently transmitted for reception, and wherein the environment of the at least one vehicle includes at least a partially overlapping area of subareas, each of the subareas corresponding to an environment of one vehicle;
dividing the environmental data values into at least two separate data records;
creating a plurality of partial maps, based on the at least two separate data records;
creating the localization map, based on the plurality of partial maps, depending upon a consistency check of the plurality of partial maps; and
making the localization map available;
wherein the creating of the plurality of partial maps includes inserting environmental features, which are included in a surrounding area, into a basemap,
wherein the creating of the plurality of partial maps includes starting from the at least two separate data records, in which at least two partial maps are created which represent different aspects, including at least two of: different sensors, different times of acquisition, different weather conditions, different traffic conditions and/or traffic densities, of the environment,
wherein the consistency check of the at least two partial maps includes a check of whether the at least two partial maps are merge-able to form the localization map, and wherein it is checked whether the at least two partial maps, based on individual environmental features, are congruent within predetermined tolerance ranges and/or are able to be made congruent,
wherein a result of the consistency check is evaluated to identify errors in the creating of the plurality of partial maps, and when the consistency check fails, an error in the mapping is inferred.

### Claim 6

A non-transitory machine-readable storage medium on which is stored a computer program, which is executable by a processor, comprising:
a program code arrangement for creating a localization map, by performing the following:
receiving environmental data values which represent an environment of at least one vehicle, wherein the environmental data values are acquired utilizing a driving environment sensor system of a vehicle, and subsequently transmitted for reception, and wherein the environment of the at least one vehicle includes at least a partially overlapping area of subareas, each of the subareas corresponding to an environment of one vehicle;
dividing the environmental data values into at least two separate data records;
creating a plurality of partial maps, based on the at least two separate data records;
creating the localization map, based on the plurality of partial maps, depending upon a consistency check of the plurality of partial maps; and
making the localization map available;
wherein the creating of the plurality of partial maps includes inserting environmental features, which are included in a surrounding area, into a basemap, wherein the creating of the plurality of partial maps includes starting from the at least two separate data records, in which at least two partial maps are created which represent different aspects, including at least two of: different sensors, different times of acquisition, different weather conditions, different traffic conditions and/or traffic densities, of the environment,
wherein the consistency check of the at least two partial maps includes a check of whether the at least two partial maps are merge-able to form the localization map, and wherein it is checked whether the at least two partial maps, based on individual environmental features, are congruent within predetermined tolerance ranges and/or are able to be made congruent,
wherein a result of the consistency check is evaluated to identify errors in the creating of the plurality of partial maps, and when the consistency check fails, an error in the mapping is inferred.