DE102016212774A1 - Method and device for generating an environment map and for locating a vehicle - Google Patents

Abstract

A method for generating an environment map for the purpose of localizing a vehicle in its surroundings and a corresponding device performs the following steps: cyclically creating images of the surroundings of the vehicle by means of at least one camera, extracting landmarks from the cyclic images of the camera, wherein within an image only a predetermined field of view for evaluation with respect to the landmarks is taken into account, - creating an environment map from the extracted landmarks, wherein the predetermined field of view for evaluating the cyclic images is a function of the prevailing weather conditions. By fusing the resulting environment map and a digital map, a precise localization of the vehicle is achieved.

Description

The invention relates to a method for generating an environment map for the purpose of localization of a vehicle in its environment according to the preamble of claim 1, a corresponding device according to the preamble of claim 6, a method for locating an autonomous vehicle in its environment according to the preamble of the claim 9 and a corresponding device with the features of claim 10.

Automatic or autonomous driving requires a highly accurate localization of the vehicle in its environment. Since automated vehicles do not have to move in "good-natured" environments, but in the real world and are thus directly exposed to atmospheric disturbances, such as seasons, weather changes and lighting effects, localization procedures must be robust and localization guaranteed in every situation these atmospheric disturbances can affect the localization.

When talking about localization in the context of automatic driving, localization consists of a two-part approach. In the first step, a map is generated from observations during one or more test drives. In the next step you will try to locate yourself with observations of a subsequent trip on the previously created maps. In both steps, the observations for localization are of crucial importance. However, these observations depend on the sensors used and the situation surrounding the vehicle. For example, observations from a laser scanner behave differently in rain than in drought. A camera also provides different observations in rain, moisture and drought.

• – Sammlung von Beobachtungen in unterschiedlichen Situationen, wie beispielsweise bei Trockenheit, Regen, Nässe, etc., zur Erstellung von Karten, die weitestgehend unabhängig von atmosphärischen Gegebenheit sind. Live-Beobachtungen können so allerdings nicht beeinflusst werden.
• – Anpassung der Sensor-Detektion der Beobachtungen. Dabei wird der Detektionsalgorithmus für jede atmosphärische Störung trainiert, um beispielsweise die Detektion von Bildobjekten in den jeweiligen Situationen zu verbessern.

The above problem has hitherto been attempted to be solved by the following approaches:

• - Collection of observations in different situations, such as drought, rain, wet, etc., to create maps that are largely independent of atmospheric conditions. However, live observations can not be influenced.
• - Adjustment of the sensor detection of the observations. In this case, the detection algorithm is trained for each atmospheric disturbance, for example in order to improve the detection of image objects in the respective situations.

• – Werden die Karten aus unterschiedlichen Beobachtungen in unterschiedlichen Situationen erstellt, so bedeutet dies nicht, dass während der Lokalisierung in einer bestimmten Situation, wie beispielsweise Regen, die Beobachtungen gut zur Karte korrespondieren. Eine Robustheit der Lokalisierung gegen atmosphärische Störungen ist deshalb nicht zwingend gegeben.
• – Durch die reine Anpassung der Sensor-Detektion der Beobachtungen werden die Ausgaben des Sensors zwar direkt für jede Situation verbessert, ob dies jedoch direkt eine Verbesserung der Lokalisierung mit sich bringt ist bislang offen.

These approaches have two inherent disadvantages:

• - If the maps are created from different observations in different situations, this does not mean that during localization in a given situation, such as rain, the observations correspond well to the map. A robustness of the localization against atmospheric disturbances is therefore not necessarily given.
• - The mere adaptation of the sensor detection of the observations, although the outputs of the sensor directly improved for each situation, but whether this directly brings an improvement in localization is so far open.

Overall, this leads to the fact that the adjustments of map and observations without consideration of the localization results were not necessarily chosen sensibly for a localization optimization.

The publication EP 0 913 751 B1 relates to an autonomous vehicle and a method for controlling an autonomous vehicle, comprising an input unit for one or more driving jobs, a route planning device comprising at least one position detection device and a digital road map, means for generating a path, an array of sensors each comprising at least one distance sensor for detecting objects and quality features of the path, a collision avoidance device, a device for detecting the state of the vehicle, a vehicle control device and a device for controlling the vehicle actuation as a function of the signals generated by the vehicle control device. The arrangement of sensors comprises at least the following sensors: two substantially horizontally oriented distance sensors arranged in the front region of the vehicle, at least one distance sensor arranged in the front region of the vehicle, at least one distance sensor arranged in the rear region of the vehicle, at least one on the roof of the vehicle Vehicle arranged on the roadway facing distance sensor with trackable scanning angle, arranged on the respective sides of the vehicle ultrasonic sensors or microwave radar sensors and at least one each arranged in the front and rear of the vehicle camera.

The publication DE 10 2008 034 923 A1 discloses a method for controlling the climatic conditions of a building containing a heating and / or an air conditioning system with at least one outside the building, the detection of the temperature serving sensor, using distributed over a data channel weather data of a location of the building enclosing predicted large-scale weather situation and using the physical quantity sensed by the sensor by computing a minimum weather condition prognosis relating to the location of the building, the forecast being for controlling the heating or air conditioning.

Fully autonomous vehicles require precise localization of the vehicle in its environment, i. on the road or the road, which is under certain circumstances due to weather conditions, such as rain, snow, fog, etc. is not sufficiently guaranteed.

The invention is therefore based on the object to improve the generation of an environment map for the purpose of localization of a vehicle in its environment and the localization of a vehicle in its environment.

This object is achieved by a method for generating an environment map with the features of claim 1, by a corresponding device with the features of claim 6, by a method for locating a vehicle with the features of claim 9 and by a corresponding device having the features of Claim 10 solved. Preferred embodiments of the invention are subject of the dependent claims.

• – zyklisches Erstellen von Bilder des Umfelds des Fahrzeugs mittels mindestens einer bilderzeugenden Einrichtung,
• – Extrahieren von Landmarken aus den zyklischen Bildern der bilderzeugenden Einrichtung und Erstellen eines Messdatensatzes für jedes Bild,
• – Ermitteln der Fahrzeugposition und der Fahrzeugeigenbewegung,
• – Erstellen einer Umfeldkarte aus dem Messdatensatz sowie der Fahrzeugposition und der Fahrzeugeigenbewegung, wobei innerhalb des Messdatensatzes nur ein vorgegebenes Sichtfeld berücksichtigt wird, wobei das vorgegebene Sichtfeld zur Auswertung der zyklischen Messdatensätze eine Funktion der aktuellen Wetterbedingung ist.

The inventive method for generating an environment map for the purpose of localizing a vehicle in its environment comprises the following steps:

• - Cyclic creation of images of the environment of the vehicle by means of at least one image-forming device,
• Extract landmarks from the cyclic images of the imaging device and create a measurement dataset for each image;
• Determining the vehicle position and the vehicle's own movement,
• - Creating an environment map from the measurement data set and the vehicle position and the vehicle's own motion, wherein within the measurement data set only a predetermined field of view is taken into account, wherein the predetermined field of view for evaluating the cyclic measurement data sets is a function of the current weather condition.

By coupling between field of view and prevailing weather conditions, the environment map is optimized.

Preferably, the predetermined field of view is parameterized by a set of parameters, the parameter set being a function of the weather condition. The parameterization of the field of view enables the description and handling of the field of view in the course of the algorithm.

More preferably, the weather condition is classified into a predetermined number of weather classes. In other words, the currently prevailing weather condition is assigned to a class such as "dry," "wet," or "rain," and these three classes are meant to be exemplary only, as a consistent description of weather conditions is hardly possible.

More preferably, the landmarks are formed by the road markings, the environment by the roadway in front of the vehicle and the field of view by a trapezoid on the road, the trapezoid is indeed used only within the measurement data set and is "imaginary", so to speak.

Preferably, the predetermined field of view for a weather condition is determined by a predetermined number of test runs for that weather condition, wherein the optimization of the field of view is performed by performing a localization of the vehicle for each test run and comparing each location thus determined with a reference location. By carrying out a large number of test drives for different weather conditions and different parameter sets for the field of view, it is possible to determine optimum parameter values for the individual weather classes, which are then used in the determination and optimization of the local environment map.

• – eine bilderzeugende Einrichtung zur Erzeugung zyklischer Bilder des Umfelds des Fahrzeugs,
• – eine Einrichtung zum Extrahieren von Landmarken aus den zyklischen Bildern der bilderzeugenden Einrichtung und zum Erstellen eines Messdatensatzes für jedes Bild,
• – eine Einrichtung zum Ermitteln der Fahrzeugposition und der Fahrzeugeigenbewegung,
• – eine Einrichtung zum Erstellen einer Umfeldkarte aus dem Messdatensatz sowie der Fahrzeugposition und der Fahrzeugeigenbewegung, wobei innerhalb des Messdatensatzes nur ein vorgegebenes Sichtfeld berücksichtigt wird, und
• – eine Einrichtung zur Bestimmung der aktuellen Wetterbedingung, wobei das vorgegebene Sichtfeld eine Funktion der aktuellen Wetterbedingung ist.

The device according to the invention for generating an environment map for the purpose of localizing a vehicle in its environment, wherein the device is set up and designed for carrying out the method explained above

• An image-forming device for generating cyclic images of the surroundings of the vehicle,
• A device for extracting landmarks from the cyclic images of the image-forming device and for generating a measurement data set for each image,
• A device for determining the vehicle position and the vehicle's own movement,
• A device for creating an environment map from the measured data set as well as the vehicle position and the vehicle own motion, wherein within the measurement data set only a predetermined field of view is taken into account, and
• - A device for determining the current weather condition, wherein the predetermined field of view is a function of the current weather condition.

More preferably, the means for determining the current weather condition performs a classification of the weather condition into a predetermined number of weather classes.

Preferably, exactly one field of view is stored per weather class, which is determined by measuring trips for the respective weather class.

• – Erzeugen einer Umfeldkarte des aktuellen Umfelds des Fahrzeugs, wobei die Umfeldkarte mit dem oben erläuterten Verfahren zur Erzeugung einer Umfeldkarte erzeugt wird,
• – Bereitstellen einer digitalen Karte des aktuellen Umfelds des Fahrzeugs, wobei die digitale Karte die Landmarken des aktuellen Umfelds aufweist, und
• – Fusionieren der Umfeldkarte und der digitalen Karte zum Erzeugen einer Lokalisierung des Fahrzeugs in seinem Umfeld.

The method according to the invention for locating a vehicle in its environment carries out the following steps:

• Generating an environment map of the current environment of the vehicle, wherein the environment map is generated with the above-described method for generating an environment map,
• Providing a digital map of the current environment of the vehicle, the digital map having the landmarks of the current environment, and
• - Fusion of the environment map and the digital map to create a localization of the vehicle in its environment.

• – eine Einrichtung zum Erzeugen einer Umfeldkarte des aktuellen Umfelds des Fahrzeugs, wobei eine oben erläuterte Vorrichtung zur Erzeugung einer Umfeldkarte verwendet wird,
• – eine Einrichtung zum Bereitstellen einer digitalen Karte des aktuellen Umfelds des Fahrzeugs, wobei die digitale Karte die Landmarken des aktuellen Umfelds aufweist, und
• – eine Einrichtung zum Fusionieren der Umfeldkarte und der digitalen Karte zum Erzeugen einer Lokalisierung des Fahrzeugs in seinem Umfeld,

The device according to the invention for locating a vehicle in its surroundings, wherein the device is set up and designed to carry out the method for localizing a vehicle explained above

• A device for generating an environment map of the current environment of the vehicle, wherein an above-described device is used to generate an environment map,
• A device for providing a digital map of the current environment of the vehicle, the digital map having the landmarks of the current environment, and
• A means for merging the environment map and the digital map to create a location of the vehicle in its environment,

Thus, there is an extension of the landmark-based localization to an adaptive adaptation to the external atmospheric conditions. The method described above describes how parameters for localization in certain weather situations, such as fog, rain and drought, can be determined.

• – Durchführen von Messfahrten für die jeweiligen Klassen, wie beispielsweise Regen, Nässe und Trockenheit. Die Messfahrten sollen alle Daten für die Lokalisierung enthalten und zudem muss eine Referenzeinheit zur Referenzlokalisierung mitaufgezeichnet werden.
• – Einteilen der Fahrten in die jeweiligen Klassen – diese Datengrundlage kann als Trainingsset bezeichnet werden.
• – Innerhalb jeder Klasse werden jetzt die Parameter optimiert. Hier sei dies am Beispiel des Sichtbereichs der Kamera erläutert. Es werden die minimalen und maximalen Parameterwerte sowie die Schrittweite festgelegt. Für jede Fahrt des Trainingssets werden nun alle Parameterkombinationen durchgetestet. Dabei können unterschiedliche zusätzliche Bedingungen an die Parameterkombinationen festgelegt werden. Als Güte-Maß zu Bewertung einer Parameterkombination wird die Referenzlokalisierung herangezogen. Über ein festgelegtes Distanzmaß, wie beispielsweise das euklidisch Abstandsmaß, kann so der Fehler zwischen Referenzlokalisierung und Parameterkombination ermittelt werden. Nachdem alle Fahrten mit allen Kombinationen durchgetestet wurden, wird die beste Fahrt herangezogen. Da Witterung nicht diskret einteilbar ist, wird versucht das Rauschen der besten Fahrt zu bestimmen. Dies geschieht, indem die Abstände der Lokalisierung zur Referenzlokalisierung der besten Fahrt diskretisiert werden. Über diese diskreten Abstände wird die Standardabweichung gebildet. Alle weiteren getesteten Fahrten werden nur weiter betrachtet, wenn sie innerhalb von 2 Standardabweichungen zur besten Fahrt der Klasse liegen. Anschließend können die Parameterwerte aller betrachteten Fahrten gemittelt werden. Sie gelten als optimale Parameterwerte für die Lokalisierung der jeweiligen Klasse.

To determine these parameters, proceed as follows:

• - Carry out test drives for the respective classes, such as rain, wet and dry conditions. The test drives should contain all data for the localization and also a reference unit for reference localization must be recorded.
• - Divide the trips into the respective classes - this data base can be called a training set.
• Within each class, the parameters are now optimized. Here, this is explained using the example of the field of view of the camera. The minimum and maximum parameter values as well as the step size are defined. For each trip of the training set, all parameter combinations are now tested. Different additional conditions can be specified for the parameter combinations. As a quality measure for the evaluation of a parameter combination, the reference localization is used. Over a fixed distance measure, as for example the Euclidean distance measure, so the error between reference localization and parameter combination can be determined. After all the rides with all combinations have been tested, the best ride is used. Since weather is not discretely divisible, it tries to determine the noise of the best ride. This is done by discretizing the distances of the localization to the reference location of the best trip. About this discreet Distances, the standard deviation is formed. All other tested rides will only be considered further if they are within 2 standard deviations from the best ride in the class. Subsequently, the parameter values of all considered journeys can be averaged. They are considered optimal parameter values for the localization of the respective class.

• – Es wird nicht nur ein Parameterset für alle Wetterbedingungen verwendet, sondern für jede Witterung wird ein spezielles Parameterset ermittelt und eingesetzt,
• – durch die ermittelten witterungsspezifischen Parametersets kann die Lokalisierung an die jeweilige Situation adaptiv auf Robustheit angepasst werden, um Fehllokalisierungen zu vermieden.

The presented method provides robust accurate localization with the following events:

• - Not only is a parameter set used for all weather conditions, but a special parameter set is determined and used for each weather,
• - By the determined weather-specific parameter sets, the localization can be adaptively adapted to the particular situation to robustness, to avoid mislocalizations.

A preferred embodiment of the invention will be explained below with reference to the drawings. It shows

1 a schematic representation of the localization problem with reference to a traffic situation,

2 a field of view of a camera of a vehicle,

3 Definition of the field of view,

4 different fields of view as a function of the class of the environmental condition, and

5 a schematic representation of the device for precise localization.

As already mentioned above, an autonomously driving vehicle requires a precise localization in its traffic environment. In other words, the position of the vehicle on the road must be as accurate as possible, i. within a few inches, be known.

So shows 1 a traffic situation at an intersection 1 coming from the two streets 2 and 3 is formed. It moves a first vehicle 4 on one street 3 go straight over the intersection 1 and one on the other street 2 located second vehicle 5 wants to turn left and crosses the driveway of the vehicle driving straight ahead 4 , Both vehicles 4 . 5 have a satellite-based location system, such as a GPS system.

The inaccuracies caused by the GPS location are in 1 as uncertainty circles 6 . 8th around the respective vehicles 4 . 5 shown. So GPS can be the first vehicle 4 only within the GPS uncertainty circle 6 and the second vehicle 5 only within the GPS uncertainty circle 8th be located. The GPS uncertainty circles 6 . 8th in the localization of the two vehicles 4 . 5 lead through the respective vehicle movement to overlapping GPS uncertainty areas 7 and 9 wherein the hatched area of overlap represents the GPS collision area 10 forms. In other words, due to the inaccuracies in the GPS localizations of the two vehicles 4 . 5 results in a large potential GPS collision area 10 , what the safety of autonomously moving vehicles 4 . 5 is insufficient.

A precise localization of the two vehicles 4 . 5 on the streets 2 . 3 leads to much smaller uncertainty circles 11 and 13 around the vehicles 4 . 5 , so that the uncertainty caused by the vehicle movements uncertainty 12 and 14 in terms of precise localization in a much smaller collision area 15 cut, which is shown in two dashed lines. So it is necessary for an autonomous driving a precise localization of the vehicles 4 . 5 in the environment, here the crossing area 1 to provide.

For precise localization, therefore, the position of the vehicle on the road is determined for example on the basis of the lane markings and other features by means of a suitable sensor system, in which case a monocular camera is used in the example case. The results of the evaluation of the sensor data are fused with a digital map and the GPS position in order to arrive at a precise localization. Since automatic vehicles, i. autonomous vehicles, moving around in the real world and having to deal with real world events, the precise localization is influenced by lane markings due to weather conditions. So it is obvious that the visibility of the lane markings for different weather conditions such as drought, rain, snow or fog is different. In other words, precise location by means of lane markings or environment objects such as traffic lights, etc., recorded in the digital map depends on the weather conditions.

2 shows the view from a vehicle 25 on a roadway 20 with different lanes 21 . 22 . 23 . 24 , where the trapezoidal field of view 26 a camera (not shown) of the vehicle 25 the area of the camera is that for detecting markings of the roadway 20 serves. In 2 are the already recognized markers 27 . 28 . 29 Shown as black bars, due to the forward movement of the vehicle within the over the lane 20 away moving field of view 26 have occurred or are currently occurring.

In 3 will that be in the 2 perspective trapezoidal field of view 26 formally defined more precisely. This is the field of view 26 a camera arranged on the front of a vehicle 30 defined by the aperture angles α and β, it being assumed for further discussion that α = β. If the field of view 26 is not arranged symmetrically in front of the vehicle, α ≠ β. The total height h of the in 3 shown triangle is composed of a fixed height h _F and the height of the trapezoid h _T , ie: h = h _F + h _T.

Here is the fixed height h _F by mounting the camera 30 conditioned on the vehicle and therefore given. Variable is the height h _{T of} the trapezoid 26 and thus its upper width w, which is composed of the left width w ₁ and the right width w ₂ . Consequently: w = w ₁ + w ₂ , where for α = β w ₁ = w ₂ . It can therefore the height h _T and the width w of the trapezoid 26 varies and as variable parameters of the field of view 26 the camera 30 to be viewed as.

4 shows the result for fields of view 26 in front of a vehicle 25 as a function of the weather class, in the present example the three weather classes "Dry", "Wet" and "Rain" (Rain) are used. It is obvious that more weather classes can be defined, for example the class "rain" could be differentiated into "light rain", "medium rain" and "heavy rain". Furthermore, classes such as "fog" and "snowfall" could be defined, which are differentiable into further subclasses.

It turns out that for each of the weather classes "dry", "wet" and "rain" to form the respective fields of vision 26 different parameters are used for optimal recognition of the lane markings. These different parameters for the height h, which is composed of the trapezoid height h _T and the fixed height h _F , and the width w of the field of view 26 lead to different trapezoids, namely the trapezoid T _R for the weather class "rain", the trapezoid T _D for the weather class "dry" and the trapezoid T _W for the weather class "wet". In the example, the three weather classes are self-explanatory. So "dry" stands for a dry road, "wet" for a wet road without rain and "rain" for a road in the current rain. The weather classes can be derived, for example, from the data of a suitable sensor, for example a rain sensor in combination with other sensors.

In order to determine the parameters, training runs are carried out in the classified weather conditions and the lane markings are determined, the parameter height of the trapezoid h _T and the width w of the trapezoid being varied within predefined limits in order to evaluate the measurements. In other words, the lane markings in the given weather class are measured for a predetermined number of training runs, the measured data are evaluated with predetermined parameter sets for the field of view, and the localization of the vehicle is determined for the respective parameter set and compared with reference values. From the deviation of the localization and the reference values, a localization quality for the parameter set used in the respective weather class can then be determined, wherein, for example, the absolute Euclidean distance with subsequent averaging can be used. From the multiplicity of training runs, mean values of the localization quantities for the different parameter sets can be determined so that an optimal parameter set can be determined for a given weather class.

The following Table 1 shows by way of example the parameter values "width w" and "total height h" determined by training runs for the weather categories "dry", "rain" and "wet" used here: class Width w (m) Height h (m) Area (m ² ) rain 7.3 16.1 99.82 Wet 10 16.4 123.82 Dry 9.7 15.5 113.96 Table 1

5 shows a schematic representation of the device for precise localization of a vehicle in its environment, ie on the road. A mono camera 30 creates cyclic images of the road or the environment in front of the moving vehicle. The image data of the camera 30 become an institution 31 for extracting the lane markings, which extracts the lane markings from the camera images and passes them as measurement data. In this case, the extraction of the lane markings from the camera images usually takes place by means of suitable image processing methods. These measurement data become an evaluation unit 34 which filters the data to reduce the measurement noise, and stores. From the data, a current map of the environment of the vehicle is created, which is continuously supplemented with the new data, ie it is a tracking and merging of the new data with the previous data, ie the environment map performed.

To the environment map in the evaluation 34 to be able to create, are from the data of a sensor 32 comprising various vehicle sensors, such as ESP and ABS for providing odometrical data and a GPS device, by means of a subsequent device 33 determines the vehicle position and the vehicle's own motion. This information is the evaluation device 34 supplied to create the environment map. Further, the information of the facility 33 for determining the vehicle's own motion an electronic horizon 36 supplied, which provides a digital map of the corresponding environment of the vehicle due to the vehicle position, wherein the digital map includes the lane markings. The electronic card can thereby via a mobile radio interface from the electronic horizon 36 be requested and provided.

In the evaluation unit 34 The lane markings can be optimally localized and tracked so that an optimal creation of the environment map of the evaluation unit 34 is possible, the evaluation unit, the weather conditions, ie the weather class, be known, so depending on the weather class, the appropriate parameter set for the field of view of the camera can be selected for evaluation. The weather class is determined by a corresponding device 35 , which clarifies by means of various existing sensors in the vehicle, which weather conditions prevail in the environment of the vehicle. For this purpose, information of the rain sensor, the air conditioning, the time, the lighting system of the vehicle, or other suitable environment sensors, can be used. From the information, the prevailing weather is determined and classified into weather classes. The result of the classification, ie the weather class, becomes the evaluation device 34 supplied for use in locating the lane markers to create the environment map.

The of the evaluation device 34 created environment map and that of the electronic horizon 36 provided digital map are in a fusion device 37 fused and carried out a precise localization of the vehicle in his environment. For this purpose, the detected lane markings of the environment map are compared with the lane markings of the digital map and the position of the vehicle is determined again. The thus-determined location of the vehicle becomes an output device 38 supplied for further use.

LIST OF REFERENCE NUMBERS

1

 crossing

2

 Street

3

 Street

4

 first vehicle

5

 second vehicle

6

 GPS uncertainty circle first vehicle

7

 GPS uncertainty area first vehicle

8th

 GPS uncertainty circle second vehicle

9

 GPS uncertainty area second vehicle

10

 GPS-hit area

11

 Uncertainty circle precise localization first vehicle

12

 Uncertainty area precise localization first vehicle

13

 Uncertainty circle precise localization second vehicle

14

 Uncertainty area precise localization second vehicle

15

 Collision area precise localization

20

 roadway

21

 lane

22

 lane

23

 lane

24

 lane

25

 vehicle

26

 Field of view camera

27

 recognized mark

28

 recognized mark

29

 recognized mark

30

 camera

31

 Extraction of the markers

32

 Vehicle sensors, GPS

33

 Determination of the absolute vehicle position and vehicle movement

34

 Evaluate the lane markings, create a measured environment map

35

 Environment sensors for determining the weather class

36

 Electronic horizon (digital environment map)

37

 Fusion of digital map and environment map

38

 Output of precise localization

H

 total height

h _F

 fixed height

h _T

 Height of trapeze

w

 Overall width trapezoid

w ₁

 left width trapeze

w ₂

 right width trapezoid

α

 angle

β

 angle

F

 vehicle

T _R

 Trapeze for class "Rain" (Rain)

T _D

 Trapeze for class "Dry" (Dry)

T _W

 Trapeze for class "Wet" (Wet)

QUOTES INCLUDE IN THE DESCRIPTION

This list of the documents listed by the applicant has been generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Cited patent literature

• EP 0913751 B1 [0007]
• DE 102008034923 A1 [0008]

Claims (10)

Method for generating an environment map for the purpose of locating a vehicle ( 4 . 5 . 25 ) in its environment with the steps: - Cyclic creation of images of the environment of the vehicle ( 4 . 5 . 25 ) by means of at least one image-forming device ( 30 ), - Extract landmarks ( 27 . 28 . 29 ) from the cyclic images of the image-forming device and generating a measurement data set for each image, - determining the vehicle position and the vehicle-own motion, - creating an environment map from the measurement data set, wherein within the measurement data set only a predetermined field of view ( 26 ), as well as the vehicle position and the vehicle's own movement, characterized in that the predetermined field of view ( 26 ) is a function of the current weather condition for evaluating the cyclic measurement data sets. A method according to claim 1, characterized in that the predetermined field of view ( 26 ) is parameterized by a set of parameters (h, w), the parameter set being a function of the weather condition. A method according to claim 2, characterized in that a classification of the weather condition takes place in a predetermined number of weather classes. Method according to one of the preceding claims, characterized in that the landmarks by the lane markings ( 27 . 28 . 29 ), the environment by the roadway in front of the vehicle ( 4 . 5 . 25 ) and the field of view ( 26 ) through a trapezoid ( 26 ) on the road ( 20 ) are formed. Method according to one of the preceding claims, characterized in that predetermined field of view for a weather condition is determined by a predetermined number of test runs for the respective weather condition, wherein the optimization of the field of view ( 26 ) by performing a localization of the vehicle ( 4 . 5 . 25 ) for each test drive and comparison of each localization determined with a reference localization. Device for generating an environment map for the purpose of locating a vehicle ( 4 . 5 . 25 ) in its environment, wherein the device for carrying out the method according to one of the preceding claims is set up and designed, comprising: an image-forming device ( 30 ) for generating cyclic images of the environment of the vehicle ( 4 . 5 . 25 ), - An institution ( 31 ) for extracting landmarks ( 27 . 28 . 29 ) from the cyclic images of the image forming device ( 30 ) and creating a measurement dataset for each image, - a device ( 33 ) for determining the vehicle position and the vehicle own movement, - a device ( 34 ) for creating an environment map from the measurement data set, wherein within the measurement data set only a predetermined field of view ( 26 ), as well as the vehicle position and the vehicle's own movement, characterized by - a device ( 35 ) for determining the current weather condition, wherein the predetermined field of view ( 26 ) is a function of the current weather condition. Device according to claim 6, characterized in that the device ( 35 ) performs a classification of the weather condition into a predetermined number of weather classes to determine the current weather condition. Apparatus according to claim 7, characterized in that per weather class exactly one field of view ( 26 ), which is determined by measuring trips for the respective weather class. Method for locating a vehicle ( 4 . 5 . 25 ) in its environment with the steps: - generating an environment map of the current environment of the vehicle ( 4 . 5 . 25 ), - providing a digital map of the current environment of the vehicle, the digital map displaying the landmarks ( 27 . 28 . 29 ) of the current environment, - merging the environment map and the digital map to generate a localization of the vehicle ( 4 . 5 . 25 ) in its environment, characterized in that the environment map with a method according to one of claims 1 to 5 is generated. Device for locating a vehicle ( 4 . 5 . 25 ) in its environment, wherein the device for carrying out the method according to claim 9 is set up and designed, comprising - a device ( 34 ) for generating an environment map of the current environment of the vehicle ( 4 . 5 . 25 ), - An institution ( 36 ) for providing a digital map of the current environment of the vehicle ( 4 . 5 . 25 ), where the digital map displays the landmarks ( 27 . 28 . 29 ) of the current environment, - an institution ( 37 ) for fusing the environment map and the digital map to generate a location of the vehicle ( 4 . 5 . 25 ) in its environment, characterized by a device for generating an environment map according to one of claims 6 to 8.

Images