WO2021018448A1

WO2021018448A1 - Method and device for creating a map and for operating a vehicle

Info

Publication number: WO2021018448A1
Application number: PCT/EP2020/065801
Authority: WO
Inventors: Jan Rohde; Christian Passmann; Daniel Zaum
Original assignee: Robert Bosch Gmbh
Priority date: 2019-07-26
Filing date: 2020-06-08
Publication date: 2021-02-04
Also published as: DE102019211137A1

Abstract

The invention relates to a method (300) for creating (340) an attribute map, comprising a step of providing (310) a positioning map, a step of determining (320) selected regions on the positioning map, a step of determining (330) attributes, and a step of creating (340) the attribute map on the basis of the positioning map. The invention further relates to a method (400) for operating (450) a vehicle, comprising a step of providing (410) an attribute map, which has been created according to a method (300) for creating an attribute map, a step of detecting (420) the surroundings of the vehicle, a step of determining (430) a position of the vehicle, a step of determining (440) at least one attribute, depending on the position of the vehicle, and a step of operating (450) the vehicle, depending on the at least one attribute.

Description

description

title

Method and device for creating a map and for operating a vehicle

The present invention relates, inter alia, to a method for creating an attribute map and a method for operating a vehicle, depending on this attribute map.

Disclosure of the invention

The method according to the invention for creating an attribute map comprises a step of providing a localization map, the localization map

Comprises localization features, and a step of determining selected areas in the localization map such that each area is uniquely determined depending on the localization features. The method further comprises a step of determining attributes depending on a respective configuration of each individual area, with each individual area being assigned at least one attribute, and a step of creating the attribute map based on the location map, the attribute map comprising the assigned attributes .

A localization map is to be understood as meaning, for example, a digital map that is present in the form of (map) data values on a storage medium. The map is designed, for example, in such a way that one or more map layers are included, one map layer showing, for example, a map from a bird's eye view (course and position of roads, buildings, landscape features, etc.). This corresponds, for example, to a map of a navigation system. Another

Map layer comprises, for example, a radar map, wherein the

Localization features, which are covered by the radar map, with a

Radar signature are stored. Another map layer comprises, for example, a lidar map, the localization features which are included in the lidar map being stored with a lidar signature. The map is designed in particular in such a way that it can be used for navigation of a

Vehicle, in particular an automated vehicle, is suitable. For this purpose, the individual map layers include, for example, localization features with a GPS position, this position being known with high accuracy. A highly precise position is to be understood as a position which is within a predetermined

Coordinate system, for example WGS84 coordinates, is so precise that this position does not exceed a maximum permissible blurring. In this case, the maximum fuzziness can depend, for example, on the surroundings - or the number and / or configuration of the localization features. Furthermore, the maximum uncertainty can depend, for example, on whether the vehicle is operated manually or partially, highly or fully automated (corresponding to one of SAE levels 1 to 5).

In principle, the maximum fuzziness is so low that, in particular, safe operation of the (automated) vehicle is guaranteed. For a fully automated operation of an automated vehicle, the maximum blurring is, for example, of the order of about 10 centimeters. A vehicle is to be understood as meaning, for example, an automated vehicle that is designed in accordance with one of SAE levels 1 to 5 (see standard SAE J3016), or a manually operated vehicle, in accordance with SAE level 0.

A localization feature is, for example, an object (traffic sign, infrastructure features [guardrail, curve course, tunnel, bridges, etc.], building, etc.) which can be detected and / or classified or assigned by means of a vehicle's environment sensor system. In one embodiment, a localization feature additionally or alternatively includes, for example, a course of the road (number of lanes, curve radius, etc.) and / or a pattern of several - for example repeating - objects (for example a characteristic sequence of

Traffic signs, etc.).

A selected area is to be understood as meaning, for example, an area on the map which corresponds to a street section (for example between two intersections and / or between two entrances and exits, etc.) and / or a region (for example a certain urban area, etc.) assigned. Several selected areas are to be understood in particular as areas which do not overlap and / or which are unmistakable. Non-overlapping areas are areas to which each point on the map can be clearly assigned. Areas that cannot be confused are to be understood as areas which, for example can be detected and unambiguously recognized by means of a vehicle environment sensor system (for example, in that each selected area includes a unique arrangement of localization features).

For example, under an embodiment of each individual area is one

Understand area-specific characterization. For example, a selected area can be understood to mean a road section, with the

Embodiment then indicates whether it is a country road or a motorway, etc. In one embodiment, the configuration describes, for example, the number of lanes per direction of travel and / or the specified maximum speed and / or a number of curves in this area and / or an indication of the radii of the curves in this area, etc. In a further embodiment For example, the design describes a condition of the road surface (wet, dry, smooth, coefficient of friction, etc.)

An environment sensor system is to be understood as at least one video and / or at least one radar and / or at least one lidar and / or at least one ultrasound and / or at least one further sensor which is designed to detect the surroundings of a vehicle, with this environment includes, in particular, localization features to be recorded in the form of environment data values.

Attributes are, for example, information about the activation release for a specific driver assistance function (also called driving function here).

A motorway assistance function is considered as an example below. The

Activation of this driving function is permitted on all motorways. As a result, the attribute map contains the value "Activation permitted" at all coordinates that can be assigned to a motorway. Be in an advantageous form

Activation attributes for several driver assistance and AD functions (general:

Driving functions) stored in the attribute card. This means that it can be used for several or different driving functions.

In a further advantageous embodiment, information about the uniqueness of the feature combinations contained in the localization map is stored in the attribute map. An unambiguous combination of features is characterized by the fact that, within a given radius (eg 1 km) around this feature arrangement, none, within a predefined permitted deviation, the same combination of characteristics is available. This uniqueness attribute is determined according to the claims mentioned.

Creating the attribute map based on the localization map, the attribute map comprising the assigned attributes, is to be understood, for example, as adding precisely these attributes to the localization map so that the corresponding attribute can be called up depending on a position of a vehicle . Thus, an attribute map is to be understood, for example, as a localization map to which attributes have been added at least partially (for example in certain areas).

The method according to the invention advantageously solves the problem of providing a method for creating an attribute map. This card enables a quick and cost-efficient option, for example for a driver assistance system

Vehicle to decide whether or when and to what extent the corresponding function is or can be performed. This object is achieved by means of the method according to the invention by using an already existing

Localization map is subdivided into selected areas, with the corresponding attributes being assigned to the respective areas. This advantageously enables a reduction of all parameters to be considered, which

may need to be checked before such an example

Driver assistance system is executed, and thus allows a quick and reliable decision as to whether or which driving function needs to be activated or deactivated.

The device according to the invention, in particular a computing unit, is set up to carry out all steps of the method of creating an attribute map.

A computing unit is to be understood as meaning, for example, a single server and / or a network of servers (cloud), which is designed to use one or more cards with a vehicle, for example by radio and / or cable connection

(Localization map, attribute map, etc.) in the form of data values.

For this purpose, the computing unit includes, for example, a processor, main memory, a hard disk and a suitable program for carrying out the method. Furthermore, the computing unit includes, for example, a transmitting and / or receiving unit, which is designed to exchange data values - in particular with an external server or a cloud and / or an infrastructure unit and / or a vehicle.

This also shows the advantage that a large part of the computational effort for carrying out a method for creating an attribute map is not carried out in a vehicle, which often has very little computing capacity, but on a server or in a cloud.

The method according to the invention for operating a vehicle comprises a step of providing an attribute map, this attribute map being created in accordance with the method according to the invention for creating an attribute map, and a step of detecting the surroundings of the vehicle, the surroundings comprising at least one localization feature. The method further comprises a step of determining a position of the vehicle, depending on a comparison of the captured environment with the attribute map (for example with a map level of the attribute map which corresponds to a localization map or comprises the localization map), a step of determining at least one attribute, depending on the position of the vehicle, and a step of operating the vehicle depending on the at least one attribute.

The vehicle is to be understood as meaning, for example, an automated vehicle that is designed in accordance with one of SAE levels 1 to 5 (see standard SAE J3016), or a manually operated vehicle, in accordance with SAE level 0.

The method according to the invention advantageously solves the problem of providing a method for operating a vehicle. Under one operation is included

for example, the execution of safety-related functions and / or the execution of so-called driver assistance functions, such as the execution of a

To understand lane departure warning and / or the execution of an emergency stopping process, etc. This object is achieved by means of the method according to the invention in that the vehicle is operated as a function of at least one attribute, this at least one attribute being taken from a so-called attribute map as a function of a position of the vehicle. This enables a simple, quick and safe possibility to advantageously execute a corresponding (above) function or to decide whether or when such a corresponding function is to be carried out. The at least one attribute is preferably determined by determining a selected area in the attribute map as a function of the position and providing the at least one attribute as a function of the selected area.

The vehicle is preferably operated by activating or not activating or deactivating a driving function as a function of the at least one attribute.

A driving function is, for example, dependent on the design of the

Vehicle (e.g. SAE level, etc.) to understand that an automated lateral and / or longitudinal control is being carried out and / or that a warning is issued to a driver and / or occupant of the vehicle and / or that driver assistance functions (motorway assistant or -pilot, etc.), etc. Activation or non-activation is understood to mean that the corresponding driving function was deactivated beforehand and a corresponding selection is now taking place, that is, an - at least temporary - activation takes place, if this is in accordance with Attribute is possible, or a non-activation (the driving function remains deactivated) takes place if a

Activation according to attribute is not possible. A deactivation is to be understood as meaning that a driving function activated beforehand, depending on a corresponding attribute, should no longer be activated.

The device according to the invention, in particular a control unit, is set up to carry out all steps of the method according to one of the method claims for operating a vehicle.

The device is designed, for example, as a control unit of the vehicle and comprises a computing unit (processor, main memory, hard disk) and suitable software to carry out the method according to one of the method claims for operating the vehicle. In one embodiment, the device comprises a transmitting and / or receiving unit which is designed to exchange data values - in particular with an external server or a cloud and / or an infrastructure unit. In a further embodiment the device comprises

for example, additionally or alternatively, a data interface for exchanging data values with a transmitting and / or receiving unit of the vehicle. Furthermore, the device comprises, for example, a data interface for requesting and / or

Receiving an input signal. Furthermore, a computer program is claimed, comprising instructions which, when the computer program is executed by a computer, cause the computer to execute a method according to one of the method claims for operating a vehicle. In one embodiment, the computer program corresponds to the software comprised by the device.

Furthermore, a machine-readable storage medium on which the computer program is stored is claimed.

All feature definitions or explanations of individual terms, features, etc. are valid both for the method for creating an attribute map and for the method for operating a vehicle and are used uniformly - unless this is clearly indicated.

Advantageous developments of the invention are given in the subclaims and listed in the description.

drawings

Exemplary embodiments of the invention are shown in the drawings and are explained in more detail in the following descriptions. Show it:

Figure 1 shows an embodiment of the method according to the invention;

FIG. 2 shows an exemplary embodiment of the method according to the invention for creating an attribute map in the form of a flow chart; and

FIG. 3 shows an exemplary embodiment of the method according to the invention for operating a vehicle in the form of a flow chart

Embodiments of the invention

Figure 1 shows an embodiment. A vehicle 200 is located in an area which, for example, corresponds to a selected area 230 of an attribute map. This area or the corresponding selected area 230 is pure here shown as an example of a motorway section. The vehicle 200 comprises a device 210, in particular a control device, which is set up to carry out all the steps of a method 400 for operating a vehicle 200.

In a first step, an attribute map is provided, this being encompassed and loaded, for example, by the device 210, retrieved from a memory source external to the device 210 or requested and / or received from an external server. In one possible embodiment, the external server corresponds, for example, to a device 110 which is set up to carry out all steps of a method 300 for creating 340 an attribute map. In a

In an advantageous embodiment, for creating 340 the attribute map, for example, features of the surroundings detected by a vehicle are received by the device 110 and used to determine the position of this vehicle. This has the advantage that the localization map does not have to be transmitted at all and the attribute map only partially has to be transmitted, which leads to a lower communication effort or a lower data transmission rate.

In a subsequent step, surroundings 220 of vehicle 200 are recorded, surroundings 220 including at least one localization feature 221.

A position of the vehicle 200 is then determined as a function of a comparison of the captured surroundings 220 with the attribute map and / or localization map. A comparison is to be understood here, for example, that a position of the

Vehicle 200 relative to the at least one localization feature 221 - for example in the form of a distance and / or an orientation (for example as an angle between a first theoretical line between localization feature 221 and vehicle 200 and a second theoretical line that represents the current

Direction of travel of vehicle 200 represents) is determined. Then the actual position of the vehicle 200 is then dependent on the position of the at least one stored in the attribute map and / or localization map

Localization feature 221 - for example by means of vector addition - determined.

In a subsequent step, at least one attribute is determined as a function of the position of the vehicle 200 in that the at least one attribute is read out from the attribute map in relation to the position of the vehicle 200. The vehicle 200 is then operated as a function of the at least one attribute.

FIG. 2 shows an exemplary embodiment of a method 300 for creating 340 an attribute map.

The method 300 begins in step 301.

In step 310 a localization map is provided, the localization map comprising localization features.

In step 320, selected areas are determined in the localization map in such a way that each area is uniquely determined as a function of the localization features. In step 330, attributes are determined depending on a particular configuration of each individual area, with at least one attribute being assigned to each individual area.

In step 340, the attribute map is created on the basis of the localization map, the attribute map comprising the assigned attributes.

The method 300 ends in step 350.

FIG. 3 shows an exemplary embodiment of a method 400 for operating 450 a vehicle 200.

The method 400 begins in step 401.

In step 410, an attribute map is provided which was created according to a method 300 for creating 340 an attribute map.

In step 420, surroundings 220 of vehicle 200 are recorded, surroundings 220 including at least one localization feature 221.

In step 430, a position of the vehicle 200 is determined as a function of a comparison of the captured surroundings 220 with the attribute map.

In step 440, at least one attribute is determined as a function of the position of the vehicle 200.

In step 450, the vehicle 200 is operated depending on the at least one attribute.

The method 400 ends in step 460.

In an alternative embodiment, step 420 takes place first, an environment 220 of the vehicle 200 being recorded, the environment 220 at least one

Localization feature 221 includes. The environment 220 is then transmitted in the form of environment data values to a server, which for example corresponds to the device 110, so that a position of the vehicle 200 is determined by means of the server. This is followed by step 410, with only a section of the attribute map that is relevant - depending on the position of the vehicle 200 - being provided in such a way that the vehicle 200 can receive this relevant section. In this embodiment, step 430 is omitted and steps 440 and 450 then follow as described above. The server-side position determination takes place here

for example, by comparing the environmental data values with a digital positioning map (which corresponds to the localization map, for example) on the server side.

Claims

Expectations

A method (300) for creating (340) an attribute map, comprising:

- Providing (310) a localization map, wherein the localization map

Includes localization features;

- Determination (320) of selected areas in the localization map in such a way that each area is uniquely determined as a function of the localization features;

- Determination (330) of attributes depending on a respective configuration of each individual area, with at least one attribute being assigned to each individual area; and

- Creation (340) of the attribute map, starting from the localization map, the attribute map comprising the assigned attributes.

2. Device (110), in particular a computing unit, which is set up to carry out all steps of a method (300) according to claim 1.

3. Method (400) for operating (450) a vehicle (200); full:

- providing (410) an attribute map which was created according to a method (300) for creating an attribute map according to claim 1;

- Detecting (420) an environment (220) of the vehicle (200), the environment (220) comprising at least one localization feature (221);

- Determining (430) a position of the vehicle (200), depending on one

Comparison of the captured environment (220) with the attribute map;

- Determining (440) at least one attribute, depending on the position of the

Vehicle (200); and

- Operating (450) the vehicle (200) depending on the at least one

Attribute.

4. The method (400) according to claim 3, characterized in that the at least one attribute is determined by determining a selected area (230) in the attribute map as a function of the position and providing the at least one attribute as a function of the selected area (230) becomes.

5. The method (400) according to claim 3, characterized in that the vehicle (200) is operated by activating or not activating or deactivating a driving function depending on the at least one attribute.

6. Device (210), in particular a control device, which is set up to carry out all the steps of the

Method (400) according to one of claims 3 to 5 to be carried out.

7. Computer program, comprising instructions that are used in the execution of the

Computer program causing a computer to carry out a method (400) according to one of claims 3 to 5.

8. Machine-readable storage medium on which the computer program is based

Claim 7 is saved.