DE102016224042A1 - Method and device for checking high-precision map data for driver assistance functions of a motor vehicle - Google Patents

Abstract

The invention relates to a method for checking high-precision HD map data for carrying out driver assistance functions in motor vehicles, comprising the following steps: providing HD map dataperforming a simulation in which a vehicle is virtually moved over one or more routes defined by the HD map data , Checking vehicle parameters during the simulation based on given test conditions; and detecting bad HD map data depending on whether the test conditions are met.

Description

Technical area

The invention relates to map data provided with high accuracy and used for operating autonomous driving functions. Furthermore, the present invention relates to the generation and the provision of the highly accurate map data.

Technical background

For semi-autonomous or fully autonomous driving, motor vehicles must be provided with navigational map data that has higher accuracy and resolution than the map data used for route planning and driver navigation. Since such highly accurate map data (HD map data) can indicate resolutions of the under-1-meter lanes, peripheral structures, signage, and the like, and lanes may change due to construction work and the like, frequent update cycles of the HD map data are required. These are therefore very frequently, for example daily, updated and made available to the motor vehicles for performing the semi-automatic and fully automated driving.

Since automated driving is safety-critical, the provided HD map data must be absolutely correct and must not lead in connection with the function of semi-automated / fully automated driving to an undesired behavior of the motor vehicle or even to accidents. Usually, HD map data is backed up on the basis of field tests and tests in the motor vehicle and only released after successful verification. This process usually takes much longer than the required update cycles.

It is therefore an object to provide a means by which HD map data can be checked or made more plausible faster.

Disclosure of the invention

This object is solved by the method for checking HD map data for performing semi-autonomous / fully autonomous driving functions according to claim 1 and by a device according to the independent claim.

Further embodiments are specified in the dependent claims.

• - Bereitstellen von HD-Kartendaten;
• - Durchführen einer Simulation, bei der ein Fahrzeug virtuell über eine oder mehrere durch die HD-Kartendaten definierten Fahrstrecken bewegt wird,
• - Überprüfen von Fahrzeugparameter während der Simulation anhand von vorgegebenen Testbedingungen; und
• - Erkennen von fehlerhaften HD-Kartendaten abhängig davon, ob die Testbedingungen erfüllt sind.

According to a first aspect, a method for checking high-precision HD map data for carrying out driver assistance functions in motor vehicles is provided, comprising the following steps:

• - providing HD map data;
• Performing a simulation in which a vehicle is virtually moved over one or more routes defined by the HD map data,
• - checking vehicle parameters during the simulation based on given test conditions; and
• - Detecting bad HD map data depending on whether the test conditions are met.

One idea of the above method is to subject the HD map data to be tested to a test in a virtual simulation environment. In this case, one or more of the driver assistance functions, in particular functions of semi-autonomous / fully autonomous driving, which depend directly on the correctness and the plausibility of the HD map data, can be simulated. Within the framework of a simulation in a virtual test environment, it is possible to identify errors in the HD map data which can lead to undesirable behavior of the driver assistance function and thus confirm the suitability of the HD map data for use in real motor vehicles.

For the test in the virtual environment, a selected area, in particular a map tile, is selected from HD map data and a drive of a virtual motor vehicle is simulated. The selected area represents real itineraries in a geographical area. The virtual ride passes along virtual routes included in the HD map data, which are composed of contiguous route sections. In this case, a journey of a virtual motor vehicle is guided in accordance with average speeds indicated for the virtual route sections, so that all possible virtual travel routes of the area of the HD map data are simulated. In this case, adjusting driving state data parameters for the virtual journey are monitored and, if one or more of the driving state parameters deviates from predetermined normal ranges, an error of the HD map data at a specific position or for a specific virtual route section is detected.

The fully automated testing and simulation of HD map data can provide feedback to the card supplier more quickly as to whether the HD map data is correct and useful for the desired driver assistance functions. Furthermore, it is possible to use HD map data in to release short update cycles for use in real motor vehicles and to prevent the delivery of faulty HD map data.

It can be provided that the simulation is carried out with varying environmental parameters and / or varying operating parameters.

In particular, the varying environmental parameters may include a varying lane condition and varying weather conditions, wherein the varying operating parameters include varying vehicle speeds.

• - eine Fahrzeuggeschwindigkeit;
• - einen Lenkwinkel;
• - eine Längs- und Querbeschleunigung (positiv/negativ)
• - ein Ereignis einer Über-/Untersteuerung; und
• - einen Reibwert bzw. eine Reifenbeschaffenheit.

Furthermore, the test conditions may define validity ranges of driving state parameters and their courses, wherein the driving state parameters may include one or more of the following values:

• a vehicle speed;
• a steering angle;
• - a longitudinal and lateral acceleration (positive / negative)
• an event of oversteer / understeer; and
• - A coefficient of friction or a tire condition.

• - ein Beschleunigungswert und/oder ein Verzögerungswert liegen innerhalb vorgegebener Grenzen, die ein komfortables Fahrverhalten definieren;
• - ein Kurvenradius unterschreitet einen vorgegebenen maximalen Kurvenradius, die ein Kraftfahrzeug bei einer simulierten Geschwindigkeit durchfahren kann,
• - eine Querbeschleunigung unterschreitet eine maximale Querbeschleunigung, ab der das Kraftfahrzeug zum Ausbrechen neigt; und
• - andere Fahrzeugparameter liegen innerhalb eines vorbestimmten Wertebereichs, der sich aus fahrzeugspezifischen bzw. funktionsspezifischen Vorgaben ergibt.

According to one embodiment, the test conditions may not be satisfied if at least one of the following conditions is not met:

• an acceleration value and / or a deceleration value are within predefined limits which define a comfortable driving behavior;
• a curve radius falls below a predetermined maximum curve radius which a motor vehicle can drive through at a simulated speed,
• - A lateral acceleration is less than a maximum lateral acceleration, from which the motor vehicle tends to break out; and
• - Other vehicle parameters are within a predetermined range of values resulting from vehicle-specific or function-specific specifications.

• - fehlerhafte Geometrien, wobei sich zulässige Werte durch die spezifische Funktionsausprägung der betreffenden Fahrerassistenzfunktion, halbautomatisiertes Fahren, reine Warnungsfunktion ohne aktive Eingriffe und dergleichen, ergeben;
• - Verdeckungen von Landmarken zur Lokalisierung des Kraftfahrzeugs, wobei überprüft wird, ob von jeder Fahrzeugposition immer eine Mindestzahl an Landmarkenobjekten erkennbar ist oder ob es potentiell zu Verdeckungen kommt;
• - ausreichende Informationsdichte in den HD-Kartendaten, wobei für jeden Streckenabschnitt überprüft wird, ob die Informationsdichte ausreichend ist, um für jede Fahrzeugposition eine bestimmte Anzahl von Landmarkenobjekten erkennen zu können.

Furthermore, the test conditions may take into account one or more of the following predetermined aspects:

• - erroneous geometries, with permissible values resulting from the specific function characteristic of the relevant driver assistance function, semi-automated driving, pure warning function without active intervention and the like;
• - Concealment of landmarks for localization of the motor vehicle, being checked whether from each vehicle position always a minimum number of landmark objects is recognizable or if it potentially comes to coverages;
• Sufficient information density in the HD map data, wherein it is checked for each route section, whether the information density is sufficient to be able to recognize a certain number of landmark objects for each vehicle position.

It may be provided that the simulation is performed with respect to one or more driver assistance functions.

According to a further aspect, an apparatus for checking high-precision HD map data for carrying out driver assistance functions in motor vehicles is provided, wherein the device is designed to perform a simulation in which a vehicle virtually moves over one or more routes defined by HD map data is used to check vehicle parameters during simulation based on given test conditions and to detect bad HD map data depending on whether the test conditions are met.

list of figures

• 1 eine schematische Darstellung eines Systems mit einer Zentralstelle, die HD-Kartendaten bereitstellt und Kraftfahrzeugen die Fahrerassistenzfunktionen und eine Funktion zum halbautonomen/vollautonomen Fahren aufweisen; und
• 2 ein Flussdiagramm zur Veranschaulichung eines Verfahrens zum Überprüfen von HD-Kartendaten.

Embodiments are explained below with reference to the accompanying drawings. Show it:

• 1 a schematic representation of a system with a central office that provides HD map data and motor vehicles have the driver assistance functions and a function for semi-autonomous / fully autonomous driving; and
• 2 a flowchart illustrating a method for checking HD map data.

Description of embodiments

1 schematically shows a system 1 with a central office 2 , the HD map data for retrieval and transmission to motor vehicles 3 provides. In the system 1 of the 1 the HD card data is from a central office 2 provided. The transmission of the HD card data takes place via a wireless communication link 4 , in particular a radio link to the motor vehicles 3 who are to use the HD map data.

The HD map data correspond to highly accurate map data, which is particularly suitable for carrying out certain driver assistance functions, in particular for the function of the semi-autonomous / Fully autonomous driving (HAF / VAF) are suitable or required. The driver assistance functions are used in motor vehicles 3 provided and use the most current HD map data. Especially for security-relevant functions, such as HAF / VAF, the timeliness of the HD map data used is important. Therefore, map data providers provide HD map data in fast update cycles. However, before the HD map data are released, they must be checked, which is usually driven the specified by the HD map data routes with a real test vehicle and the HD map data according to environmental data, which are detected by an environment detection sensor technology of the test vehicle become. This process is tedious and usually takes up to several weeks.

To check and release the HD cards from the central office 2 a method is provided, as can be seen from the flow chart of 2 evident.

In step S1, HD map data is provided by the map supplier.

In step S2, an area of the HD map data is selected for review. The area can map a geographical area and correspond to a tile in which virtual distances defined by the HD map data are located. The virtual routes have interconnected virtual road sections in a route network, each of which is provided with parameters such as information on the topology, for example, gradient and gradient, road condition, roadway width, edge development, signage and the like. The HD map data describe the routes very detailed and have a high spatial resolution, in particular a resolution of less than 1 m.

In a simulation environment, a virtual motor vehicle is now moved along the virtual driving route in step S3. This is done with typical operating parameters for the motor vehicle, such as a predetermined by the average speed for each section section speed. In this case, driving state parameters for each route section are determined for the virtual vehicle.

In a simulation environment, the interplay of all in-vehicle sensors and functions with a simulated reality and predefined boundary conditions (weather, road sections, road conditions) is readjusted and corresponding results generated.

The virtual links describing the HD map data are associated with route parameters that have usually been checked for plausibility prior to deployment by the map provider, in particular prior to performing that ride. For this purpose, the individual route parameters can be checked to see whether their information is within predetermined validity ranges. The simulation also provides information on how the interaction of the plurality of route parameters affects the behavior of a virtual motor vehicle when it is moved along the virtual routes of the area of the HD map data. In the simulation, for example, a motor vehicle can be guided at a predetermined speed for the HAF / VAF along the routes of the map data. The driving condition parameters are monitored.

In step S4, it is checked whether an error can be detected on the basis of the driving state parameters. If this is the case (alternative: yes), faulty HD card data are signaled in step S5, otherwise (alternative no), the HD card data are marked as error-free in step S6 and transmitted to the motor vehicles 3 Approved. For the driving state parameters, test conditions are defined that must be fulfilled for a release of the HD map data. The test conditions may indicate, for example, validity ranges for the driving state parameters.

• - Beschleunigungswerte und Verzögerungswerte liegen innerhalb vorgegebener Grenzen, die ein komfortables Fahrverhalten definieren.
• - Ein Kurvenradius unterschreitet einen vorgegebenen maximalen Kurvenradius, die ein Kraftfahrzeug bei einer simulierten Geschwindigkeit durchfahren kann,
• - eine Querbeschleunigung unterschreitet eine maximale Querbeschleunigung, ab der das Kraftfahrzeug zum Ausbrechen neigt.
• - Andere Fahrzeugparameter liegen innerhalb eines vorbestimmten Wertebereichs, der sich aus fahrzeugspezifischen bzw. funktionsspezifischen Vorgaben ergibt.

Such an error is detected if at least one of predetermined test conditions is not met. These test conditions may include:

• - Acceleration values and deceleration values are within predefined limits, which define a comfortable driving behavior.
• A curve radius is less than a predefined maximum curve radius that a motor vehicle can drive through at a simulated speed,
• - A lateral acceleration falls below a maximum lateral acceleration, from which the motor vehicle tends to break out.
• - Other vehicle parameters are within a predetermined range of values resulting from vehicle-specific or function-specific specifications.

• - fehlerhafte Geometrien, wobei sich zulässige Werte durch die spezifische Funktionsausprägung der betreffenden Fahrerassistenzfunktion, halbautomatisiertes Fahren, reine Warnungsfunktion ohne aktive Eingriffe und dergleichen, ergeben;
• - Verdeckungen von Landmarken zur Lokalisierung des Kraftfahrzeugs, wobei überprüft wird, ob von jeder Fahrzeugposition immer eine Mindestzahl an Landmarkenobjekten erkennbar ist oder ob es potentiell zu Verdeckungen kommt;
• - gesamthafter Systemtest im FAS-Verbund. Dabei wird die Karte im Zusammenspiel mit sämtlichen FAS-Systemen und Komponenten innerhalb eines Prüfstandes evaluiert;
• - ausreichende Informationsdichte in den HD-Kartendaten, wobei für jeden Streckenabschnitt überprüft wird, ob die Informationsdichte ausreichend ist, um für jede Fahrzeugposition eine bestimmte Anzahl von Landmarkenobjekten erkennen zu können.

Furthermore, the test conditions may take into account one or more of the following predetermined aspects:

• - erroneous geometries, with permissible values resulting from the specific function characteristic of the relevant driver assistance function, semi-automated driving, pure warning function without active intervention and the like;
• - Concealment of landmarks for localization of the motor vehicle, being checked whether from each vehicle position always a minimum number of landmark objects is recognizable or if it potentially comes to coverages;
• - Overall system test in the FAS network. The card is evaluated in interaction with all FAS systems and components within a test bench;
• Sufficient information density in the HD map data, wherein it is checked for each route section, whether the information density is sufficient to be able to recognize a certain number of landmark objects for each vehicle position.

It is possible to simulate the evaluations of map parameters on the driver assistance functions and their behavior and interpretation of the map parameters. This is not possible by a purely static evaluation of the map parameters, since these are evaluated independently of function-specific conditions.

In addition, in a simulation, errors or failures of individual vehicle sensors may be simulated and variable link parameters, such as environmental parameters, such as, e.g. Temperature, road friction values and the like, are simulated by various virtual departures of the virtual routes. As a result, the effects of variable environmental conditions can be taken into account, which would not be possible if the routes were driven down with a real test vehicle.

If the simulation after one or more runs of all routes of the area of the HD map data with a virtual vehicle shows that all driving state parameters from each position of the route sections fulfill the test conditions, then the HD map data can be released. The release is performed by replacing a previously valid area of the HD map data with the checked area of the HD map data in the HD map data sent to the motor vehicle 3 be transmitted to perform the driver assistance functions.

Overall, it is possible to detect errors that would lead to unwanted behavior of the driver assistance functions by simulating the driver assistance functions that require a direct dependency on the HD map data. Thereby, the suitability of the HD map data for providing to the motor vehicles 3 be recognized. When errors occur, the HD map data can be returned early to the card supplier, so that a faster cycle can be achieved for resolving errors in HD map data. All in all, the use of automated tests and simulations can protect daily updated maps or prevent the delivery of faulty HD map data.

LIST OF REFERENCE NUMBERS

1

system

2

central processing unit

3

motor vehicle

4

communication link

Claims (9)

Method for checking high-precision HD map data for performing driver assistance functions in motor vehicles (3), comprising the following steps: - providing (S1) HD map data Performing (S3) a simulation in which a vehicle is virtually moved over one or more routes defined by the HD map data, - checking (S4) vehicle parameters during simulation based on predetermined test conditions; - Detecting bad HD map data depending on whether the test conditions are met. Method according to Claim 1 wherein the simulation is performed with varying environmental parameters and / or varying operating parameters. Method according to Claim 2 wherein the varying environmental parameters include a varying lane condition and varying weather conditions, and wherein the varying operating parameters include varying vehicle speeds. Method according to one of Claims 1 to 3 wherein the test conditions define ranges of validity of driving condition parameters and their histories, wherein driving condition parameters include one or more of the following driving condition parameters: a vehicle speed; a steering angle; a longitudinal and lateral acceleration (positive / negative); an event of oversteer / understeer; and - a friction value or a tire condition specification. Method according to one of Claims 1 to 4 wherein the test conditions are not met if at least one of the following conditions is not met: an acceleration value and / or a deceleration value are within predetermined limits that define a comfortable driving behavior; - A curve radius is less than a predetermined maximum radius of curvature that can pass through a motor vehicle at a simulated speed, - A lateral acceleration falls below a maximum lateral acceleration, from which the motor vehicle tends to break out; and - other vehicle parameters are within a predetermined range of values resulting from vehicle-specific or function-specific specifications. Method according to one of Claims 1 to 5 wherein the test conditions take into account one or more of the following predetermined aspects: - erroneous geometries, permissible values resulting from the specific function characteristic of the relevant driver assistance function, semi-automated driving, pure warning function without active intervention and the like; - Concealment of landmarks for localization of the motor vehicle, being checked whether from each vehicle position always a minimum number of landmark objects is recognizable or if it potentially comes to coverages; Sufficient information density in the HD map data, wherein it is checked for each route section, whether the information density is sufficient to be able to recognize a certain number of landmark objects for each vehicle position. Method according to one of Claims 1 to 6 wherein the simulation is performed with respect to one or more driver assistance functions. Device for checking high-precision HD map data for performing driver assistance functions in motor vehicles (3), the device being designed to perform a simulation in which a vehicle is virtually moved over one or more routes defined by HD map data to vehicle parameters during the simulation to check based on given test conditions and to detect bad HD map data depending on whether the test conditions are met. A computer program product which, when executed on a data processing device, performs a method according to any one of Claims 1 to 7 performs.

Images