Generating non-semantic reference data for determining the position of a motor vehicle

Abstract

Computer-implemented method for generating non-semantic reference data for determining the position of a motor vehicle (6), wherein a set of raw data points (7) is provided which maps a predetermined environmental area (11); characterized in that - for each of the raw data points (7), a predetermined descriptor is determined by means of a computing unit (8), which descriptor characterizes a property of the environmental area (11) at a position of the respective raw data point (7); - at least one point cluster (9a, 9b, 9c, 9d, 9e, 9f) is generated by means of the computing unit (8) by grouping the raw data points (7) depending on their descriptors;- by means of the computing unit (8), a first point cluster of the at least one point cluster (9a, 9b, 9c, 9d, 9e, 9f) is assigned a key figure, which relates to an information gain for determining the position of the motor vehicle (6), depending on the descriptors of the raw data points (7) of the first point cluster, the key figure indicating the influence that the use of the first point cluster for determining the position of the motor vehicle (6) has on the accuracy of the position determination; and - depending on the key figure, feature information of the first point cluster is stored on a storage unit (10) as non-semantic reference data for determining the position.

Claims

[1] Computer-implemented method for generating non-semantic reference data for determining the position of a motor vehicle (6), wherein a set of raw data points (7) is provided which maps a predetermined environmental area (11); characterized by , that - for each of the raw data points (7) a predetermined descriptor is determined by means of a computing unit (8), which descriptor characterizes a property of the surrounding area (11) at a position of the respective raw data point (7); - at least one point cluster (9a, 9b, 9c, 9d, 9e, 9f) is generated by means of the computing unit (8) by grouping the raw data points (7) depending on their descriptors; - by means of the computing unit (8), a first point cluster of the at least one point cluster (9a, 9b, 9c, 9d, 9e, 9f) is assigned a key figure, which relates to an information gain for determining the position of the motor vehicle (6), depending on the descriptors of the raw data points (7) of the first point cluster, wherein the key figure indicates the influence that the use of the first point cluster for determining the position of the motor vehicle (6) has on the accuracy of the position determination; and - depending on the key figure, feature information of the first point cluster is stored as non-semantic reference data for position determination on a storage unit (10). [2] Method according to claim 1, characterized by that by means of the computing unit (8) - a spatial distribution of all point clusters (9a, 9b, 9c, 9d, 9e, 9f) of the at least one point cluster (9a, 9b, 9c, 9d, 9e, 9f) is analyzed; - depending on a result of the analysis of the spatial distribution, a localization characteristic is determined for the first point cluster; and - the key figure is determined depending on the localization key figure. [3] Method according to claim 2, characterized by that by means of the computing unit (8) - a number of point clusters is determined which are located in a predetermined sub-area of the surrounding area (11) in which the first point cluster is located; and - the localization value is determined depending on the number. [4] Method according to one of claims 1 to 3, characterized by that by means of the computing unit (8) - a singularity characteristic value for the first point cluster is determined depending on the descriptors of the raw data points (7) of the first point cluster and on the descriptors of the raw data points (7) of a second point cluster of the at least one point cluster (9a, 9b, 9c, 9d, 9e, 9f); and - the key figure is determined depending on the singularity value. [5] Method according to one of claims 1 to 4, characterized by that by means of the computing unit (8) - at least one descriptor cluster (12a, 12b, 12c) is generated by grouping the raw data points (7) depending on their descriptors and independently of their respective spatial positions; and - the at least one point cluster (9a, 9b, 9c, 9d, 9e, 9f) is generated by spatially grouping the raw data points (7), wherein each descriptor cluster (12a, 12b, 12c) is identical to one of the point clusters or is separated to form at least two of the point clusters. [6] Method according to one of claims 1 to 5, characterized by that by means of the computing unit (8) - depending on the descriptors of the raw data points (7) of the first point cluster, a distinctiveness value is determined for the first point cluster; and - the key figure is determined depending on the distinctiveness value. [7] Method according to claim 6, characterized by that by means of the computing unit (8) - a distribution of the descriptors of the raw data points (7) of the first point cluster is determined; and - the distinctiveness index is determined depending on the distribution. [8] Method according to one of claims 6 or 7, characterized by that the feature information of the first point cluster is stored on the storage unit (10) by means of the computing unit (8) depending on the distinctiveness characteristic value. [9] Method according to one of claims 6 to 8, characterized by that the feature information of the first point cluster is stored on the storage unit (10) by means of the computing unit (8) only if the distinctiveness characteristic value is greater than or equal to a predetermined limit value. [10] Method for determining the position of a motor vehicle (6), wherein - image data of an environment of the motor vehicle (6) are generated by means of an environment sensor (13) of the motor vehicle (6); - by means of a further computing unit (14) of the motor vehicle (6), the image data are compared with predetermined reference data for position determination; and - by means of the further computing unit (14) a position of the motor vehicle (6) is determined depending on a result of the comparison; characterized by that the reference data for position determination were generated by means of a method according to one of claims 1 to 9. [11] Map system for determining the position of a motor vehicle (6), the map system comprising a further memory unit (15), characterized by that reference data for position determination are stored on the further storage unit (15), which were generated by means of a method according to one of claims 1 to 9. [12] Motor vehicle (6) with a map system (15) for determining position according to claim 11. [13] Computer system (16) for generating non-semantic reference data for determining the position of a motor vehicle (6), the computer system (16) comprising a computing unit (8) and a memory unit (10), wherein the computing unit (8) is configured to receive a set of raw data points (7) which maps a predetermined environmental area (11); characterized by that the computing unit (8) is set up to - to determine for each of the raw data points (7) a descriptor which characterizes a property of the surrounding area (11) at a position of the respective raw data point; - to generate at least one point cluster (9a, 9b, 9c, 9d, 9e, 9f) by grouping the raw data points (7) depending on their descriptors; - assigning a key figure to a first point cluster of the at least one point cluster (9a, 9b, 9c, 9d, 9e, 9f) depending on the descriptors of the raw data points (7) of the first point cluster, which key figure relates to an information gain for determining the position of the motor vehicle (6), wherein the key figure indicates the influence that the use of the first point cluster for determining the position of the motor vehicle (6) has on the accuracy of the position determination; and - depending on the key figure, to store feature information of the first point cluster as reference data for position determination on the storage unit (10). [14] Computer program with instructions which, when the computer program is executed by a computer system (16), cause the computer system (16) to carry out a method according to one of claims 1 to 9. [15] A computer-readable storage medium on which a computer program according to claim 14 is stored.

Images