DE102018006231A1 - Validate digital map tracking information - Google Patents

Abstract

The invention relates to a method for validating lane guidance information of a digital map, comprising the steps: - determining (S1) a position of a vehicle (1) when driving on a road section, - assigning (S2) the position of the vehicle (1) to a coordinate in the digital map, - determining (S3) a first lane guidance (10) from the digital map in an area around the coordinate, - detecting (S4) a second lane guidance (20) of the road section by a sensor unit (3) of the vehicle (1) , - Comparing (S5) the first tracking (10) with the second tracking (20) by means of a metric and detecting a deviation between the first tracking (10) and the second tracking (20) based on the metric, the metric at least one comprises the following: a difference in location from the first tracking (10) and the second tracking (20) • a difference from the kinematic data recorded by the sensor unit (3) in the sequence n the second lane guidance (20) by the vehicle (1) and expected kinematic data when following the first lane guidance (10) by the vehicle (1); a folding of the first lane guidance (10) with the second lane guidance (20); • a Multiplication of the first tracking (10) by the second tracking (20).

Description

The invention relates to a method for validating lane guidance information of a digital map, a device for validating lane guidance information of a digital map and a vehicle with such a device.

The object of the invention is to validate in real time the lane guidance of a road stored in a digital map on a road section currently used by a vehicle.

The invention results from the features of the independent claims. Advantageous further developments and refinements are the subject of the dependent claims.

• - Ermitteln einer Position eines Fahrzeugs beim Befahren eines Straßenabschnitts,
• - Zuordnen der Position des Fahrzeugs zu einer Koordinate in der digitalen Karte,
• - Ermitteln einer ersten Spurführung aus der digitalen Karte in einem Bereich um die Koordinate,
• - Erfassen einer zweiten Spurführung des Straßenabschnitts durch eine Sensoreinheit des Fahrzeugs,
• - Vergleichen der ersten Spurführung mit der zweiten Spurführung mittels einer Metrik und Detektieren einer Abweichung zwischen der ersten Spurführung und der zweiten Spurführung auf Grund der Metrik, wobei die Metrik zumindest eines aus den folgenden umfasst:
  • • Eine Ortsdifferenz aus der ersten Spurführung und der zweiten Spurführung;
  • • Eine Differenz aus von der Sensoreinheit erfassten kinematischen Daten beim Folgen der zweiten Spurführung durch das Fahrzeug und erwarteten kinematischen Daten beim Folgen der ersten Spurführung durch das Fahrzeug;
  • • Eine Faltung der ersten Spurführung mit der zweiten Spurführung;
  • • Eine Multiplikation der ersten Spurführung mit der zweiten Spurführung.

A first aspect of the invention relates to a method for validating tracking information of a digital map, comprising the steps:

• Determining a position of a vehicle when driving on a section of road,
• Assigning the position of the vehicle to a coordinate in the digital map,
• Determining a first lane guidance from the digital map in an area around the coordinate,
• Detection of a second lane guidance of the road section by a sensor unit of the vehicle,
• Comparing the first guidance with the second guidance by means of a metric and detecting a deviation between the first guidance and the second guidance based on the metric, the metric comprising at least one of the following:
  • • A difference in location from the first guidance and the second guidance;
  • • A difference between the kinematic data recorded by the sensor unit when the vehicle follows the second lane guidance and the expected kinematic data when the vehicle follows the first lane guidance;
  • • A folding of the first guidance with the second guidance;
  • • A multiplication of the first guidance by the second guidance.

The digital map has tracking information, that is, the map provides respective tracking information for a plurality of areas on the map, so that a first tracking can be extracted from the digital map for the area of interest. Thus, in the first step of the method, a position of the vehicle when driving on a road section is preferably detected by satellite positioning and in the second step this position is assigned to a coordinate of the digital map. After these steps, the position of the vehicle that can be assigned to a coordinate of the map is thus detected, and the first lane information associated with the position of the vehicle can be read from the digital map from the coordinate.

The term “lane guidance” is to be understood in particular to mean information about the number and the location of the lanes on the road section currently being traveled by the vehicle, the location of the lanes naturally having an extent in at least one dimension, and therefore the location of the lanes is preferred as a set of points, as a parameterized curve, as a polynomial model or in another data form. If the lane guidance is determined from the digital map using the known position of the vehicle, this information is briefly referred to as the first lane guidance. If, on the other hand, the lane guidance is determined by means of the sensor unit of the vehicle map, this information about the number and the location of the lanes on the road section currently used by the vehicle is briefly referred to as “second lane guidance”. Both the first lane guidance and the second lane guidance are particularly suitable and preferably recorded and ascertained with sufficient accuracy that a driver assistance system is able to carry out automatically performed driving maneuvers such as keeping lanes or changing lanes by means of this respective information.

A possible metric is a difference between the kinematic data recorded by the sensor unit when the vehicle follows the second lane guidance and the expected kinematic data when the vehicle follows the first lane guidance; A lateral acceleration of the vehicle or also a vehicle speed together with a steering angle of the vehicle, a yaw angle of the vehicle or also a yaw rate or also a yaw acceleration are preferably used as kinematic data.

A difference in location between the first guidance compared to the second guidance is, in particular, the sum of discrete distances between a location of the first guidance and a location of the second guidance. As stated above, the respective location has a certain extent in at least one dimension and is preferably to be understood as a curve in the mathematical sense. Alternatively, a maximum distance between the first tracking compared to the second tracking can be defined as the location difference between the first tracking compared to the second tracking.

A convolution of the first guidance with the second guidance is to be understood as a convolution in the mathematical sense, the location of the first guidance indicating the first function and the location of the second guidance indicating the second function, with both functions resulting in a third function as a result of the Convolution is determined. In this way, a convolution, also called convolution, that is, the resultant superimposition of the first function with a mirrored and shifted version of the second function, can in particular be used to determine a moving average between the functions.

A multiplication of the first guidance by the second guidance is in this sense a multiplication of the above. to understand the first function with the second function.

The vehicle can in particular be a car, truck, bus, or a work vehicle.

It is an advantageous effect of the invention that the vehicle receives data about the validity of the lane guidance stored in the digital map for this road section while driving on a road section. No other vehicles are required for this. Furthermore, the result of the detection of a deviation between the first lane guidance and the second lane guidance can be used in almost real time in order to inform a driver assistance system of the vehicle accordingly, in particular if the driver assistance system of the vehicle uses information about the lane guidance of the road section currently being driven on.

According to an advantageous embodiment, the sensor unit comprises one of the following elements: camera, lidar, odometry unit, steering angle sensor, angular acceleration sensor, translational acceleration sensor, position angle sensor.

The odometry unit is designed in particular to determine a distance covered by counting the rolled circumference of the wheel. By deriving it in time, a speed of the vehicle in a respective wheel circumferential direction is also achieved, and by deriving it again an associated acceleration.

The position angle sensor is in particular designed to detect a yaw angle of the vehicle. The yaw angle of the vehicle is in particular an angle of the vehicle about a vertical axis of the vehicle, preferably with respect to the north.

In general, the first tracking and the second tracking always differ at least somewhat from one another, since they have different sources. When a deviation between the first tracking and the second tracking due to the metric is detected, small deviations are therefore preferably ignored, and only larger tendencies in the differences from the metric are detected as a real deviation. Possible solutions are the application of a low-pass filter or the application of a limit value to the metric or, preferably, to the respective tracking, as shown in the following embodiments.

According to a further advantageous embodiment, the first tracking and / or the second tracking are low-pass filtered before comparing the first tracking with the second tracking.

Sensor errors and other uncertainties are thus advantageously compensated for more easily by combining the metrics.

According to a further advantageous embodiment, the deviation between the first tracking and the second tracking is detected when the metric exceeds a predefined limit value.

The two preceding embodiments advantageously prevent, as explained above, that smaller measurement inaccuracies such as sensor noise or map inaccuracies lead to a detection of a deviation of the first tracking from the second tracking.

According to a further advantageous embodiment, several of the possible metrics are added to a combined metric and the combination metric is used to detect the deviation between the first tracking and the second tracking.

The individual metrics are preferably multiplied by a respective weighting and the weighted metrics are added to a combined metric.

According to a further advantageous embodiment, the deviation between the first lane guidance and the second lane guidance is detected when the metric has a value that increases monotonously over the passage of the road section for a predefined period of time.

According to a further advantageous embodiment, the method further comprises the step: updating the digital map if a deviation is found when comparing the first guidance with the second guidance.

This advantageously updates the second lane guidance provided by the digital map almost in real time.

According to a further advantageous embodiment, the method further comprises the step of: configuring a driver assistance system of the vehicle depending on the result of the comparison of the first lane guidance with the second lane guidance.

This embodiment advantageously makes it possible for a driver assistance system to receive, in addition to the first lane guidance from the digital map, a second lane guidance determined by the measurement of the sensor unit, and therefore not to perform any erroneous driving maneuvers due to errors in the first lane guidance from the digital map.

• · Eine Ortsdifferenz aus der ersten Spurführung und der zweiten Spurführung;
• · Eine Differenz aus von der Sensoreinheit erfassten kinematischen Daten beim Folgen der zweiten Spurführung durch das Fahrzeug und erwarteten kinematischen Daten beim Folgen der ersten Spurführung durch das Fahrzeug;
• · Eine Faltung der ersten Spurführung mit der zweiten Spurführung;
• · Eine Multiplikation der ersten Spurführung mit der zweiten Spurführung.

A further aspect of the invention relates to a device for validating lane guidance information of a digital map, comprising a locating unit that is designed to determine a position of a vehicle when driving on a road section, and has a computing unit that is used to assign the position of the vehicle to a coordinate in the digital map, for determining a first guidance from the digital map in an area around the coordinate, for detecting a second guidance of the road section by a sensor unit of the vehicle, for comparing the first guidance with the second guidance using a metric and for detecting a deviation between the first tracking and the second tracking based on the metric, the metric comprising at least one of the following:

• · A difference in location from the first guidance and the second guidance;
• · A difference between the kinematic data recorded by the sensor unit when the vehicle follows the second lane guidance and the expected kinematic data when the vehicle follows the first lane guidance;
• · Folding the first lane with the second lane;
• · A multiplication of the first guidance by the second guidance.

Advantages and preferred developments of the proposed device result from an analog and analogous transmission of the statements made above in connection with the proposed method.

Another aspect of the invention relates to a vehicle with a device as described above and below.

Further advantages, features and details result from the following description, in which - if necessary with reference to the drawing - at least one exemplary embodiment is described in detail. Identical, similar and / or functionally identical parts are provided with the same reference symbols.

• 1 ein Verfahren zum Validieren einer Spurführungsinformation einer digitalen Karte gemäß einem Ausführungsbeispiel der Erfindung,
• 2 einen Vergleich der ersten Spurführung mit der zweiten Spurführung gemäß einem weiteren Ausführungsbeispiel der Erfindung,
• 3 einen Vergleich der ersten Spurführung mit der zweiten Spurführung gemäß einem weiteren Ausführungsbeispiel der Erfindung,
• 4 einen Vergleich der ersten Spurführung mit der zweiten Spurführung gemäß einem weiteren Ausführungsbeispiel der Erfindung, und
• 5 ein Fahrzeug mit einer Vorrichtung zum Validieren einer Spurführungsinformation einer digitalen Karte gemäß einem weiteren Ausführungsbeispiel der Erfindung.

Show it:

• 1 a method for validating a tracking information of a digital map according to an embodiment of the invention,
• 2 a comparison of the first tracking with the second tracking according to a further embodiment of the invention,
• 3 a comparison of the first tracking with the second tracking according to a further embodiment of the invention,
• 4 a comparison of the first tracking with the second tracking according to a further embodiment of the invention, and
• 5 a vehicle with a device for validating tracking information of a digital map according to a further exemplary embodiment of the invention.

The representations in the figures are schematic and not to scale.

• - Ermitteln S1 einer Position eines Fahrzeugs 1 mittels einer Ortungseinheit 5, nämlich einer Satellitenortungseinheit, beim Befahren eines Straßenabschnitts einer Autobahn,
• - Zuordnen S2 der Position des Fahrzeugs 1 zu einer Koordinate in der digitalen Karte,
• - Ermitteln S3 einer ersten Spurführung 10 aus der digitalen Karte in einem Bereich von fünfhundert Metern in Fahrtrichtung des Fahrzeugs 1 ausgehend von der Koordinate,
• - Erfassen S4 einer zweiten Spurführung 20 des Straßenabschnitts durch eine Sensoreinheit 3 des Fahrzeugs 1, wobei die Sensoreinheit 3 zumindest eine Kameraeinheit und einen Seitenbeschleunigungsmesser umfasst,
• - Vergleichen S5 der ersten Spurführung 10 mit der zweiten Spurführung 20 mittels einer kombinierten Metrik und Detektieren einer Abweichung zwischen der ersten Spurführung 10 und der zweiten Spurführung 20 auf Grund der kombinierten Metrik, wobei zur Ermittlung der kombinierten Metrik die folgenden Metriken addiert werden:
  • • Eine Ortsdifferenz aus der ersten Spurführung 10 und der zweiten Spurführung 20;
  • • Eine Differenz aus von der Sensoreinheit 3 erfassten kinematischen Daten beim Folgen der zweiten Spurführung 20 durch das Fahrzeug 1 und erwarteten kinematischen Daten beim Folgen der ersten Spurführung 10 durch das Fahrzeug 1;
  • • Eine Faltung der ersten Spurführung 10 mit der zweiten Spurführung 20;

Hierbei wird die zweite Spurführung 20 vor dem Vergleichen der ersten Spurführung 10 mit der zweiten Spurführung 20 tiefpassgefiltert. Eine Abweichung zwischen der ersten Spurführung 10 und der zweiten Spurführung 20 wird dann detektiert, wenn die Metrik einen vordefinierten Grenzwert überschreitet. Anschließend erfolgen die Schritte:

• - Aktualisieren S6 der digitalen Karte, wenn beim Vergleichen der ersten Spurführung 10 mit der zweiten Spurführung 20 eine Abweichung festgestellt wird, und
• - Konfigurieren S7 eines Fahrerassistenzsystems des Fahrzeugs 1 abhängig vom Ergebnis des Vergleichens der ersten Spurführung 10 mit der zweiten Spurführung 20.

1 shows a method for validating tracking information of a digital map. The process has the following steps:

• - Determine S1 a position of a vehicle 1 by means of a locating unit 5 , namely a satellite location unit, when driving on a section of a highway,
• - Assign S2 the position of the vehicle 1 to a coordinate in the digital map,
• - Determine S3 a first guidance 10 from the digital map in a range of five hundred meters in the direction of travel of the vehicle 1 starting from the coordinate,
• - To capture S4 a second lane guidance 20 of the road section by a sensor unit 3 of the vehicle 1 , the sensor unit 3 comprises at least one camera unit and a lateral accelerometer,
• - To compare S5 the first lane 10 with the second lane guidance 20 using a combined metric and detecting a deviation between the first tracking 10 and the second tracking 20 based on the combined metric, whereby the following metrics are added to determine the combined metric:
  • • A location difference from the first lane 10 and the second tracking 20 ;
  • • A difference from the sensor unit 3 captured kinematic data when following the second lane guidance 20 through the vehicle 1 and expected kinematic data when following the first lane guidance 10 through the vehicle 1 ;
  • • A fold of the first lane guidance 10 with the second lane guidance 20 ;

This is the second guidance 20 before comparing the first guidance 10 with the second lane guidance 20 low-pass filtered. A deviation between the first lane guidance 10 and the second tracking 20 is then detected when the metric exceeds a predefined limit. Then follow the steps:

• - To update S6 the digital map when comparing the first lane guidance 10 with the second lane guidance 20 a deviation is found, and
• - Configure S7 a driver assistance system of the vehicle 1 depending on the result of comparing the first guidance 10 with the second lane guidance 20 ,

2 shows a first tracking determined from a digital map 10 and one by a sensor unit 3 of the vehicle 1 detected second lane guidance 20 the currently used section of road. Also give the curve A and the curve B in each case a measure of a lateral acceleration of the vehicle 1 , correlating with a steering angle of the vehicle 1 , on, with the curve A to the second lane 20 is related and the curve B on the first lane 10 is related. Comparing S5 the first lane 10 with the second lane guidance 20 takes place by means of a metric from the folding of the lateral acceleration from that of the sensor unit 3 determined current kinematic data when following the second lane guidance 20 through the vehicle 1 and the kinematic data expected by calculation when theoretically following the first lane guidance 10 through the vehicle 1 , A deviation between the first lane guidance 10 and the second tracking 20 is then detected when the metric exceeds a predefined limit.

3 shows a first tracking determined from a digital map 10 and one by a sensor unit 3 of the vehicle 1 detected second lane guidance 20 the currently used section of road. There is also a curve C a measure of a difference from the first guidance 10 and the second tracking 20 on. Comparing S5 the first lane 10 with the second lane guidance 20 is done using a metric based on the difference in location from the first lane guidance 10 and the second tracking 20 ; this in turn becomes the second guidance 20 before comparing the first guidance 10 with the second lane guidance 20 low-pass filtered. A deviation between the first lane guidance 10 and the second tracking 20 is detected because the metric has a monotonically increasing value for a predefined period of time over the passage of the road section.

4 shows a first tracking determined from a digital map 10 and one by a sensor unit 3 of the vehicle 1 detected second lane guidance 20 the currently used section of road. Also give the curve D a measure of a curvature d10 of the first tracking 10 and a measure of curvature d20 the second lane 20 and the curve e a measure of a difference in curvature d10 and the curvature d20 on. Comparing S5 the first lane 10 with the second lane guidance 20 is done using a metric from the difference in curvature d10 and the curvature d20 , with the respective curvature of the second tracking 20 from the sensor unit 3 is determined. A deviation between the first lane guidance 10 and the second tracking 20 is detected because the metric exceeds a predefined limit.

• · Eine Ortsdifferenz aus der ersten Spurführung 10 und der zweiten Spurführung 20;
• · Eine Differenz aus von der Sensoreinheit 3 erfassten kinematischen Daten beim Folgen der zweiten Spurführung 20 durch das Fahrzeug 1 und erwarteten kinematischen Daten beim Folgen der ersten Spurführung 10 durch das Fahrzeug 1;
• · Eine Faltung der ersten Spurführung 10 mit der zweiten Spurführung 20;
• · Eine Multiplikation der ersten Spurführung 10 mit der zweiten Spurführung 20.

5 shows a vehicle 1 with one device 100 for validating a tracking information of a digital map, comprising a locating unit 5 used to determine a position of a vehicle 1 is executed when driving on a road section, and having a computing unit for assigning the position of the vehicle 1 to a coordinate in the digital map, to determine a first lane guidance 10 from the digital map in an area around the coordinate, for recording a second lane guidance 20 of the road section by a sensor unit 3 of the vehicle 1 , to compare the first guidance 10 with the second lane guidance 20 by means of a metric and for detecting a deviation between the first tracking 10 and the second tracking 20 is executed based on the metric, the metric comprising at least one of the following:

• · A location difference from the first lane 10 and the second tracking 20 ;
• · A difference from the sensor unit 3 captured kinematic data when following the second lane guidance 20 through the vehicle 1 and expected kinematic data when following the first lane guidance 10 through the vehicle 1 ;
• · Folding the first track 10 with the second lane guidance 20 ;
• · A multiplication of the first guidance 10 with the second lane guidance 20 ,

Although the invention has been illustrated and explained in detail by means of preferred exemplary embodiments, the invention is not restricted by the disclosed examples and other variations can be derived therefrom by a person skilled in the art without departing from the scope of protection of the invention. It is therefore clear that there are a variety of possible variations. It is also clear that exemplary embodiments are only examples that are not to be interpreted in any way as a limitation of the scope, the possible applications or the configuration of the invention. Rather, the preceding description and the description of the figures enable the person skilled in the art to implement the exemplary embodiments in concrete terms, the person skilled in the art being able to carry out various changes in knowledge of the disclosed inventive concept, for example with regard to the function or the arrangement of individual elements mentioned in an exemplary embodiment, without leaving the scope of protection defined by the claims and their legal equivalents, such as further explanations in the description.

LIST OF REFERENCE NUMBERS

1

vehicle

3

sensor unit

5

locating unit

10

first lane guidance

20

second guidance

100

contraption

S1

Determine

S2

Assign

S3

Determine

S4

To capture

S5

Compare and detect

S6

To update

S7

Configure

Claims (10)

A method for validating a tracking information of a digital map, comprising the steps: - determining (S1) a position of a vehicle (1) when driving on a section of road, Assigning (S2) the position of the vehicle (1) to a coordinate in the digital map, - Determining (S3) a first tracking (10) from the digital map in an area around the coordinate, - Detection (S4) of a second lane guidance (20) of the road section by a sensor unit (3) of the vehicle (1), - Comparing (S5) the first tracking (10) with the second tracking (20) by means of a metric and detecting a deviation between the first tracking (10) and the second tracking (20) based on the metric, the metric being at least one includes the following: • A location difference from the first tracking (10) and the second tracking (20); • A difference between the kinematic data acquired by the sensor unit (3) when the vehicle (1) follows the second lane guidance (20) and the expected kinematic data when the vehicle (1) follows the first lane guidance (10); • A folding of the first tracking (10) with the second tracking (20); • A multiplication of the first tracking (10) with the second tracking (20). Procedure according to Claim 1 , wherein the sensor unit (3) comprises one of the following: camera, lidar, odometry unit, steering angle sensor, angular acceleration sensor, translational acceleration sensor, position angle sensor. Method according to one of the preceding claims, wherein the first tracking (10) and / or the second tracking (20) are low-pass filtered before comparing the first tracking (10) with the second tracking (20). Method according to one of the preceding claims, wherein a plurality of the metrics are combined to form a combined metric and, based on the combined metric, the deviation between the first tracking (10) and the second tracking (20) is detected. Method according to one of the preceding claims, wherein the deviation between the first tracking (10) and the second tracking (20) is detected when the metric exceeds a predefined limit value. Method according to one of the preceding claims, wherein the deviation between the first lane guidance (10) and the second lane guidance (20) is detected when the metric has a monotonically increasing value for a predefined period of time as a result of the driving on the road section. Method according to one of the preceding claims, further comprising the step: Updating (S6) the digital map if a deviation is found when comparing the first tracking (10) with the second tracking (20). Method according to one of the preceding claims, further comprising the step: - Configuring (S7) a driver assistance system of the vehicle (1) depending on the result of comparing the first lane guidance (10) with the second lane guidance (20). Device (100) for validating a lane guidance information of a digital map, comprising a locating unit (5), which is designed to determine a position of a vehicle (1) when driving on a road section, and comprising a computing unit, which is used to assign the position of the vehicle (1 ) to a coordinate in the digital map, for determining a first lane guidance (10) from the digital map in an area around the coordinate, for detecting a second lane guidance (20) of the road section by a sensor unit (3) of the vehicle (1), for comparing the first tracking (10) with the second tracking (20) by means of a metric and for detecting a deviation between the first tracking (10) and the second tracking (20) based on the metric, the metric being at least one includes the following: • A location difference from the first tracking (10) and the second tracking (20); • A difference between the kinematic data acquired by the sensor unit (3) when the vehicle (1) follows the second lane guidance (20) and the expected kinematic data when the vehicle (1) follows the first lane guidance (10); • A folding of the first tracking (10) with the second tracking (20); • A multiplication of the first tracking (10) with the second tracking (20). Vehicle (1) with a device (100) Claim 9 ,

Images