专利摘要:
The invention relates to a method and a device (100) for testing a driver assistance system for a vehicle in a test environment (6). Traffic scenario descriptions (12) are determined, each of which characterize a specific traffic scenario and have at least one parameter by means of which the respective traffic scenario can be adapted to boundary conditions. The traffic scenario descriptions (12) are stored in a traffic scenario file in which the at least one parameter is stored in a predetermined format. At least one traffic scenario description (12) is selected on the basis of an input by a user and / or on the basis of predetermined criteria. In addition, a test case is generated on the basis of the at least one selected traffic scenario description (12) and at least one predefined value for the at least one parameter, the test case having a concrete implementation of the one characterized by the at least one selected traffic scenario description (12) Traffic scenarios in relation to the at least one predetermined value of the at least one parameter correspond and are suitable for generating a test environment (6) in which a driver assistance system can be subjected to a test run. A test run can be carried out on the basis of the test case created.
公开号:AT521607A4
申请号:T50922/2018
申请日:2018-10-24
公开日:2020-03-15
发明作者:Emre Kaplan Dr;Ing Dr Andrea Leitner Dipl;Ahmetcan Erdogan PHD;Dipl Ing Markus Nager Ma
申请人:Avl List Gmbh;
IPC主号:
专利说明:

Summary
The present invention relates to a method and a device for testing a driver assistance system for a vehicle in a test environment. Traffic scenario descriptions are determined, each of which characterize a particular traffic scenario and have at least one parameter by means of which the respective traffic scenario can be adapted to boundary conditions. The traffic scenario descriptions are stored in a traffic scenario file in which the at least one parameter is stored in a predetermined format. At least one traffic scenario description is selected on the basis of an input from a user and / or based on predefined criteria. In addition, a test case is generated on the basis of the at least one selected traffic scenario description and at least one predefined value for the at least one parameter, the test case with a concrete realization of the traffic scenario characterized by the at least one selected traffic scenario description in relation to the at least one a predetermined value of the at least one parameter corresponds and is suitable for generating a test environment in which a driver assistance system can be subjected to a test run. A test run can be carried out on the basis of the test case created.
Fig. 2/27
PI32126AT
AVL List GmbH
METHOD AND DEVICE FOR TESTING A DRIVER ASSISTANCE SYSTEM
The present invention relates to a method and a device for testing a driver assistance system for a vehicle in a test environment.
Modern vehicles are increasingly equipped with advanced driver assistance systems (ADAS), which support the driver in certain driving situations. The support ranges from the simple display of possibly relevant information (e.g. issuing a warning by a lane change assistant) to semi-autonomous interventions (e.g. regulation of the torque applied to the wheel axles by an anti-lock braking system) to fully autonomous interventions in the control of the vehicle (e.g. adaptive cruise control by one Adaptive cruise control (ACC).
The basis for such driver assistance systems is usually formed by sensor data, for example provided signals from ultrasound sensors, radar sensors or cameras, which can be used to determine the current driving situation and in response to this the function of the respective driver assistance system can be carried out. In particular in the case of driver assistance systems which (autonomously) intervene in the control of the vehicle, the current driving situation must be able to be classified in a highly reliable manner on the basis of the sensor data.
In general, certain rules or criteria assigned to a driving situation are set up, and if they are fulfilled, it can be concluded that a known driving situation exists. The fulfillment of the rule or criteria is effective e.g. as a trigger for an action by the driver assistance system. For example, a traffic scenario in which a neighboring vehicle in front of the vehicle equipped with the driver assistance system (EGO vehicle) can cut into the same lane can be recognized in that a sensor-detected transverse distance decreases perpendicular to the direction of travel to the neighboring vehicle and finally, at least in Essentially, assumes the value 0 if the neighboring vehicle is immediately in front of the EGO vehicle.
/ 27
PI32126AT
AVL List GmbH
In order to test such driver assistance systems, in particular their reaction in already known traffic scenarios, classified sensor data are generally provided with respect to a known traffic scenario and the driver assistance system to be tested is fed with these classified sensor data. In order to reliably test the driver assistance system, a large number of sensor data, which may also characterize slight variations in the traffic scenario, are generally required.
For this purpose, WO 2017/210222 A1 discloses the automatic generation of simulation scenarios for validating a driver assistance system. A large number of such simulation scenarios can be generated in particular by varying recorded scenarios, the variations being based on a data stream which is generated by isolating differences between similar recorded scenarios.
It is an object of the present invention to further improve the testing of driver assistance systems, in particular to simplify them and / or to make them more flexible.
This object is achieved by a method and a device for testing a driver assistance system for a vehicle in a test environment in accordance with the independent claims. Advantageous embodiments of the invention are the subject of the dependent claims.
A first aspect of the invention relates to a, in particular computer-based, method for testing a driver assistance system for a vehicle in a test environment, comprising the following working steps: (i) determining traffic scenario descriptions, each of which describes a specific traffic scenario, in particular a cut-in maneuver or a Cut-out maneuvers, characterize and have at least one parameter by means of which the respective traffic scenario can be adapted to boundary conditions, the traffic scenario descriptions preferably, in particular in each case, being stored in a traffic scenario file in which the at least one parameter is stored in one predetermined, in particular generic, format is stored; (ii) Selection of at least one traffic scenario description based on an input by a user, in particular an indication of the at least one parameter or at least one value entered by the user or / 27
PI32126AT
AVL List GmbH
Range of values for the at least one parameter and / or predetermined criteria; and (iii) generating a test case on the basis of the at least one selected traffic scenario description and at least one predetermined value, in particular entered by the user, for the at least one parameter and preferably further traffic scenario descriptions, the test case with a concrete implementation of the the at least one selected traffic scenario description characterizes traffic scenarios and preferably further traffic scenarios in relation to the at least one predetermined value of the at least one parameter and is suitable for generating a test environment in which a driver assistance system can be subjected to a test run.
A boundary condition in the sense of the invention is, in particular, a traffic situation, a weather, an initial speed of the vehicle with the driver assistance system to be tested (hereinafter: test vehicle) and / or other road users, a road geometry or a road course, a distance of the test vehicle to or several other road users, a configuration of the test vehicle and / or other road users such as a load, for example a trailer, and / or the like. A boundary condition can in particular be any conceivable factor that influences the control of the vehicle equipped with the driver assistance system by the driver assistance system.
A test case in the sense of the invention is in particular a script, e.g. a sequence of actions by road users, which enables a driver assistance system to be checked. A test case can be, for example, a script, on the basis of which a simulation for testing the driver assistance system can be carried out.
A test environment in the sense of the invention is in particular the content of a simulation that generates a concrete (virtual) implementation of a traffic scenario. In other words, a test environment can be, for example, a simulated environment of the test vehicle, in which at least other road users, possibly also the test vehicle itself, move in a predefined manner, in particular carry out predetermined actions.
/ 27
PI32126AT
AVL List GmbH
A predetermined format in the sense of the invention is in particular a predefined (data) structure. A predetermined format can, for example, follow a certain scheme, e.g. correspond to a specific arrangement or sequence of several parameters and / or a specific coding of the at least one parameter in the traffic scenario file. It is conceivable, for example, that several parameters are stored in a table, in particular a two- or three-dimensional, possibly also multidimensional, matrix.
Determining traffic scenario descriptions within the meaning of the invention is in particular capturing, e.g. when performing real or simulated tests. Determining traffic scenario descriptions can also be reading in, e.g. from databases and / or the like.
The invention is based in particular on the approach of preferably selecting at least one traffic scenario description from a plurality of traffic scenario descriptions, each of which characterizes a specific traffic scenario and is preferably in a predetermined, in particular generic, format, and on the basis of which to generate at least one test case a test environment that is suitable for testing a driver assistance system. The traffic scenarios characterized by the traffic scenario descriptions preferably correspond to specific traffic scenarios such as cut-in maneuvers (one-maneuvers) or a cut-out maneuvers (out-maneuvers). However, the traffic scenario descriptions preferably describe the respective traffic scenario in a general, generic form, without the traffic scenario descriptions specifying a specific execution of these maneuvers. The test case, on the other hand, preferably corresponds to a concrete implementation of the traffic scenario, which is characterized by the at least one selected traffic scenario description.
Both the at least one traffic scenario description can be selected on the basis of a user input, for example by specifying at least one parameter or entered values or value ranges for one or more parameters which adapt, in particular, define boundary conditions of the traffic scenarios, as well as the at least one test case from the at least one out
PI32126AT
AVL List GmbH chose traffic scenario description. The parameters can serve as variables in the traffic scenarios, for example.
For example, the user can input that the test vehicle, i.e. the vehicle equipped with the driver assistance system, drives straight ahead in a first lane at a speed selected by the user and is overtaken by another vehicle in an adjacent second lane, the other vehicle being in the first lane at a distance selected by the user from the test vehicle reverts. Based on these entries, a database with traffic scenario files stored therein, which contain the traffic scenario descriptions in the specified format, can be searched in order to select traffic scenario descriptions with which the specific traffic scenario characterized by the user input can be implemented. The parameters and / or boundary conditions entered by the user can then, like values in a mathematical function, be inserted into the at least one selected traffic scenario description in order to generate at least one test case with which a simulation can be carried out and the driver assistance system can thereby be tested.
As a result of the user input being able to select at least one traffic scenario description, in particular from a large number of traffic scenario descriptions, it is possible to dispense with a possibly complex, scenario- or maneuver-specific preparation of data records for generating test environments. According to the invention, test runs for testing a driver assistance system can therefore be carried out particularly easily and quickly and / or in large numbers. In particular, because the traffic scenario descriptions can be stored in a predetermined, preferably generic, format, access to a wide range of traffic scenarios is made possible.
Overall, the invention makes it possible to further improve the testing of driver assistance systems, in particular to simplify them and / or to make them more flexible.
Preferred embodiments of the invention and their developments are described below, each, unless this is expressly excluded, / 27
PI32126AT
AVL List GmbH can be combined as desired with one another and with the aspects of the invention described below.
In a preferred embodiment, the method further comprises the following step: performing a test run using the test case generated. As a result, the driver assistance system can be tested in a reliable manner, in particular on the basis of a specifically adapted traffic scenario.
In a further preferred embodiment, the method further comprises the following work steps: (i) determining at least one data record which characterizes at least one, in particular real, traffic scenario; and (ii) identifying at least one parameter in the at least one determined data set, by means of which the respective traffic scenario can be adapted to boundary conditions, in particular an initial speed of an EGO vehicle to which the traffic scenario relates. An EGO vehicle in the sense of the invention is in particular a vehicle from the point of view of which the, in particular real, traffic scenario is running.
The identification of at least one parameter in the at least one data record makes it possible in a particularly reliable manner to subsequently select at least one traffic scenario description from a multiplicity of traffic scenario descriptions based on the user input. In particular, at least one traffic scenario can thus be selected based on the identified parameter, e.g. all traffic scenario descriptions that characterize a traffic scenario corresponding to a determined data set and therefore also have the identified parameter. In other words, the number of possible traffic scenarios relevant for testing the driver assistance system can be increased in this way.
The at least one data record is preferably determined on the basis of a sensor data stream, which is generated, for example, by a sensor device for detecting the (real) vehicle environment of the EGO vehicle, in particular extracted from the sensor data stream. The sensor data stream can be processed, for example, in such a way that the vehicle environment of the EGO vehicle is classified, e.g. Objects such as other road users, traffic signs, obstacles and / or the like are recognized and labeled. The at least one data record can then be generated from the processed sensor data stream. With / 27
PI32126AT
AVL List GmbH, in other words, the at least one determined data record is preferably based on processed sensor data that were generated when a real vehicle environment was recorded and the additional meta information, i.e. information derived from raw data and therefore going beyond the pure physical information contained in the sensor data stream. In particular, this meta-information allows the identification of the at least one parameter, by means of which the respective traffic scenario can be adapted to boundary conditions.
In a further preferred embodiment, the identification of the at least one parameter is carried out by comparing a classified vehicle environment in chronologically successive scenes of the at least one traffic scenario characterized by the at least one determined data record. A classified vehicle environment in the sense of the invention is in particular a description of the vehicle environment of a vehicle that goes beyond pure physical information. The classified vehicle environment, which is preferably characterized by the data set provided, can in particular contain meta information which makes the classified vehicle environment comparable at different times. The classified vehicle environment preferably contains meta information, on the basis of which individual objects of the at least one traffic scenario characterized and characterized by the at least one determined data record can be identified and labeled (e.g. labeled) and e.g. their positions, their speeds, their configuration and / or the like can be compared with one another in the successive scenes. As a result, the at least one parameter can be identified in a particularly reliable and / or automated manner.
Preferably, the states of the elements of the vehicle environment, i.e. the status of the elements of the vehicle environment, are in each scene of the at least one traffic scenario characterized by the at least one determined data set. e.g. the objects identified in the vehicle environment, such as other road users, derived and compared, in particular subtracted, from one another in successive scenes. A state of an element of the vehicle environment in the sense of the invention contains in particular at least one physical quantity that characterizes the element, in particular relative to the EGO vehicle, e.g. the speed of the element, the position of the element, the configuration of the element and / or the like.
/ 27
PI32126AT
AVL List GmbH
If the state of an element changes in the successive scenes, the at least one parameter is preferably identified as the physical variable that causes the change in the state. This allows at least one
Parameters can be identified particularly easily.
For example, the speed and the size of another road user can be taken from the classified vehicle environment in a first scene and compared with the speed or size of this road user in a subsequent second scene. The speed of the road user will usually change in the course of the traffic scenario and can therefore be identified as a parameter. In contrast, the size of the road user usually does not change and is therefore not identified as a parameter.
In a further preferred embodiment, the method further comprises the following work step: generating at least one traffic scenario description on the basis of the determined data record or the determined data records, the traffic scenario description characterizing the determined traffic scenario and the at least one identified parameter in the predetermined format is filed. The storage of the at least one identified parameter in the specific format, in particular in a traffic scenario file, corresponds in a preferred manner to the generation of a standardized format or a standardized traffic scenario description. In other words, by storing the at least one identified parameter in the specific format, a standardized definition of the at least one corresponding traffic scenario, which is characterized by the at least one determined data record, is stored. The at least one data record extracted from a sensor data stream can thereby be provided in a generic form in particular as a description of the traffic scenario and subsequently selected to generate at least one test case.
In a further preferred embodiment, the method also has the following work step: storing the generated traffic scenario description, in particular the traffic scenario file, in a traffic scenario database, further traffic scenario files also being stored in the traffic scenario database. This traffic scenario database is preferably set up as a No-SQL database and contains a standardized definition of the at least one Ver / 27
PI32126AT
AVL List GmbH reverse scenarios that is characterized by the at least one determined data set. By storing the generated traffic scenario description in the database, the generation of test cases can be based on a large number of, in particular real, traffic scenarios.
In a further preferred embodiment, the method further comprises at least one of the following work steps: (i) determining the predetermined values from a test run database; and / or (ii) determining the predetermined values from a user input, in particular via a user interface. For example, at least one value or range of values for the at least one parameter, which e.g. has proven to be useful in previous tests of a driver assistance system, read from the test run database and used to generate the at least one test case. Alternatively or additionally, a user can specify at least one value or range of values for the at least one parameter when entering a user, in particular when entering to select at least one traffic scenario description. As a result, test cases can be generated automatically and quickly and / or the user can be given a high degree of control over the generation of the test cases and thus over the checking of the driver assistance system.
A second aspect of the invention relates to a device for testing a driver assistance system for a vehicle in a test environment, which has a means for determining traffic scenario descriptions, wherein the traffic scenario descriptions preferably each have a specific traffic scenario, in particular a cut-in maneuver or a cut. Out-maneuvers, characterize and have at least one parameter by means of which the respective traffic scenario can be adapted to boundary conditions. The means for determining traffic scenario descriptions is also preferably set up to store the traffic scenario descriptions, in particular in each case, in a traffic scenario file in which the at least one parameter is stored in a predetermined, in particular generic, format. The means for determining traffic scenario descriptions can in particular be set up as an interface or sensor device. In addition, the device preferably has a means for selecting at least one traffic scenario description based on input from a user and / or predefined criteria, the means for selecting at least one traffic scenario description in particular as a first module / 27
PI32126AT
AVL List GmbH a data processing device, e.g. can be designed as appropriate software. In addition, the device preferably has a means for generating a test case on the basis of the at least one selected traffic scenario description and at least one predetermined value for the at least one parameter and preferably further traffic scenario descriptions, the test case with a concrete realization of the by the at least one selected traffic scenario description characterizes traffic scenarios and preferably further traffic scenarios in relation to the at least one predetermined value of the at least one parameter and is suitable for generating a test environment in which a driver assistance system can be subjected to a test run. The means for generating the test case can in particular be used as a second module of the data processing device, e.g. as appropriate software can be set up.
A means in the sense of the present invention can be designed in terms of hardware and / or software, in particular one that is data or signal-connected, preferably digital, processing, in particular microprocessor unit (CPU) or a module of a, preferably with a memory and / or bus system have such and / or one or more programs or program modules. The CPU can be designed to process commands that are implemented as a program stored in a memory system, to acquire input signals from a data bus and / or to output signals to a data bus. A storage system can have one or more, in particular different, storage media, in particular optical, magnetic, solid-state and / or other non-volatile media. The program can be designed in such a way that it embodies or is capable of executing the methods described here, so that the CPU can execute the steps of such methods and thus in particular can control and / or monitor a reciprocating piston machine.
In a preferred embodiment, the device has a traffic scenario database in which traffic scenario descriptions are or are stored in the form of traffic scenario files, each of which has at least one parameter available in a predetermined, in particular generic, format, by means of which a parameter is described by the respective traffic scenario description characterized traffic scenario can be adapted to boundary conditions.
/ 27
PI32126AT
AVL List GmbH
In a further preferred embodiment, the device also has an input device by means of which a user can make an input for selecting at least one traffic scenario description, in particular from traffic scenario descriptions stored in the traffic scenario database.
In a further preferred embodiment, the device has a simulation device which is set up to carry out a test run using the test case generated. For this purpose, the simulation device can have, for example, a simulation environment such as MATLAB / Simulink, IPG CarMaker, PreScan, SUMO SCANer or Virtual Test Drive (VTD).
The features and advantages described in relation to the first aspect of the invention and its advantageous embodiment also apply, at least where it makes technical sense, to the second aspect of the invention and its advantageous embodiment, and vice versa.
Further features, advantages and possible uses of the invention result from the following description in connection with the figures, in which the same reference numerals are used throughout for the same or corresponding elements of the invention. At least partially, they show schematically:
1 shows a preferred embodiment of a device according to the invention;
2 shows a preferred embodiment of a method according to the invention; and
3 shows an example of a traffic scenario description.
FIG. 1 shows a preferred embodiment of a device 100 according to the invention for testing a driver assistance system for a vehicle in a test environment. The device 100 has a traffic scenario database 2 with traffic scenario descriptions stored therein, each of which characterizes a specific traffic scenario, an input device 3 for selecting at least one of the traffic scenario descriptions stored in the traffic scenario database 2, a data processing device 4 for creating a test case, the one with a concrete realization of the traffic scenario selected by the at least one / 27
PI32126AT
AVL List GmbH
Description characterized traffic scenarios corresponds, based on the at least one selected traffic scenario description and a simulation device 5 for performing a test run using the test case generated, in particular a test environment generated based on the test case.
The traffic scenario descriptions preferably characterize in a generic manner a specific traffic scenario, for example a cut-in maneuver or a cut-out maneuver. In other words, the traffic scenario descriptions preferably each represent a traffic scenario, in particular at least one concrete driving maneuver of a vehicle involved in the traffic scenario, in an abstract form.
The traffic scenario descriptions are preferably stored in the traffic scenario database 2 in the form of traffic scenario files. Because of the preferred generic character of the traffic scenario descriptions, the traffic scenario files can be stored in a predetermined, in particular generic, format, regardless of the (specific) traffic scenario characterized in each case. This enables or at least simplifies, for example, identification and / or parameterization of the traffic scenario characterized by the respective traffic scenario description.
For this purpose, the traffic scenario descriptions stored in the traffic scenario database 2 can have, for example, at least one parameter, such as speeds and / or positions of the road users contained in the traffic scenario, with which the respective traffic scenario can be adapted to boundary conditions. The at least one parameter is preferably contained in the traffic scenario files. In particular, the predefined format of the traffic scenario files can correspond to the predefined format of the at least one parameter with which the at least one parameter is stored in the traffic scenario file. In other words, the predetermined format of the traffic scenario files can be predetermined or formed by the structure with which the at least one parameter is stored in the traffic scenario database 2. This enables the parameterization of the traffic scenarios.
/ 27
PI32126AT
AVL List GmbH
At least one traffic scenario description can also be selected via the at least one parameter contained in the traffic scenario files. For example, a user can use the input device 3 to specify or specify at least one parameter which is to be taken into account when creating test cases. In particular, it is conceivable for the user to enter at least one value or range of values for the at least one parameter via the input device 3, so that those traffic scenario descriptions can be selected in the database which have the corresponding parameter or in which the corresponding parameter describes the entered value or range of values.
For this purpose, the input device 3 can have, for example, a graphical user interface, in which the user can provide information on the selection of the at least one traffic scenario description, in particular the at least one parameter. The input device 3 thus preferably serves as a user interface.
The data processing device 4 is preferably set up to take into account at least one predetermined value for the at least one parameter for generating the test case on the basis of the at least one selected traffic scenario description, wherein the at least one predetermined value can be provided, for example, by the input device 3. By specifying at least one value for the at least one parameter, the traffic scenario characterized by the selected, preferably generic or abstract, traffic scenario description can be concretized, so that the test case preferably corresponds to a specific implementation of the traffic scenario.
Based on the test case generated by the data processing device 4, the simulation device 5 can preferably generate a test environment in which a driver assistance system can be subjected to a test run. For example, on the basis of the test case generated, the simulation device 5 can simulate a virtual, in particular dynamic, vehicle environment in which the reaction of the driver assistance system is tested in the traffic scenario specified by the test case. The parameterization of the traffic scenarios, each of which is characterized by a description of the traffic scenario, allows the driver to be tested accordingly
PI32126AT
AVL List GmbH sistance systems under various conditions, e.g. in different weather conditions, on different road segments, at different vehicle speeds, with or without a trailer and / or the like.
FIG. 2 shows a preferred embodiment of a method 1 according to the invention for testing a driver assistance system for a vehicle in a test environment 6. In a method step S1, a sensor data stream 7 generated when a real vehicle environment is detected by means of a sensor device is preferably processed. The sensor data stream 7 can in particular be prepared in such a way that parameterizable data records, each characterizing at least one traffic scenario, can be generated and stored in a database 2 as, in particular, generic traffic scenario descriptions. These traffic scenario descriptions serve as the basis for generating at least one test case, with which the test environment 6 can be generated for testing the driver assistance system.
The sensor data stream 7 is preferably processed in method step S1, in particular analyzed, e.g. by classifying the vehicle environment represented by the sensor data stream 7. For example, elements of the vehicle environment can be identified and labeled in individual snapshots of the vehicle environment obtained by sensor data fusion, which correspond to individual scenes of a real (specific) traffic scenario. Thus, so-called meta information, which goes beyond the pure physical information due to the sensory detection of the vehicle environment, is preferably generated. For example, object lists of objects recognized in the vehicle environment, such as other road users or traffic signs, can be generated in this frame. Such processing of the sensor data stream 7 can be implemented, for example, by a rule-based approach in which predetermined events are recognized and marked.
In other words, an environment model is preferably generated on the basis of the sensor data stream 7, which, for example, represents the objects around the EGO vehicle equipped with the sensor device.
In a further method step S2a, on the basis of the sensor data stream 7 processed in this way, in particular from the meta information generated in the process, such as an object list, at least one data record which is at least one by the sensor device 27
PI32126AT
AVL List GmbH characterized, determined traffic scenario. E.g. processed sensor data corresponding to individual traffic scenarios, which are identified, for example, by recognized predetermined events, can be selectively extracted from the sensor data stream 7. This can also be called scenario mining.
In a further method step S2b, at least one parameter is preferably identified for the at least one determined data set, by means of which the at least one traffic scenario characterized by the at least one determined data set is adapted to boundary conditions, such as weather conditions, a speed of the EGO vehicle and / or the like can. In other words, the at least one traffic scenario characterized by the at least one determined data record can be parameterized.
The identification of the at least one parameter can be achieved, for example, by using the classified vehicle environment, i.e. the at least one data record, the states of elements of the vehicle environment, for example of recognized objects such as other road users, are determined and compared with one another in successive scenes of the traffic scenario characterized by the at least one data record. In this case, a state of an element of the vehicle environment can be defined, for example, by physical variables such as a speed, position, configuration and / or the like. In a preferred manner, at least one parameter is identified in particular when a change in a state of an element occurs in the temporally successive scenes of the traffic scenario, for example a change in speed or position.
Since the traffic scenario description is preferably defined by the data record determined in method step S2a and the at least one parameter identified in method step S2b, method steps S2a and S2b can also be understood as determining traffic scenario descriptions and summarized in a method step S2c. As an alternative or in addition, such traffic scenario descriptions can also be determined in some other way, for example from other databases such as NCAP, DVP and / or accident databases (not shown).
In a further method step S3, the at least one data record with the at least one traffic scenario parameterized in this way is /, in particular generic, / 27
PI32126AT
AVL List GmbH
Traffic scenario description stored in a traffic scenario file and in the
Traffic scenario database 2 saved. In particular, the at least one identified parameter can be stored in a predetermined, in particular generic, format in the traffic scenario file.
In a further method step S4, at least one of the traffic scenario descriptions determined and stored in the traffic scenario database 2 can then be selected by inputting a user, for example via an input device 3. E.g. the user can specify at least one parameter with which the traffic scenarios characterized by the traffic scenario descriptions can be adapted to boundary conditions.
The at least one traffic scenario description relevant or selected with respect to the user input is made available to a data processing device which, based on this traffic scenario description and at least one value, in particular by the user input, for the at least one parameter in at least one parameter in a further method step S6 Generates a test case which corresponds to a concrete realization of the traffic scenario characterized by the at least one selected traffic scenario description. The at least one test case generated can be used to generate a test environment for testing the driver assistance system.
The user can influence, in particular configure, the test of the driver assistance system via his input, for example by specifying boundary conditions for the traffic scenario characterized by the at least one traffic scenario description, in particular the course of the traffic scenario, e.g. resolving a traffic situation, specified. For this, the user can e.g. select appropriate parameters on the basis of which the at least one test case is created. It is particularly conceivable that the user directly selects relevant traffic scenario descriptions and, e.g. by specifying at least one value or range of values of a corresponding parameter.
Such modified traffic scenario descriptions can be carried out in a further method step S5, possibly together with generated test cases, in the traffic / 27
PI32126AT
AVL List GmbH scenario database, where you can be selected at a later point in time to generate test cases, especially faster ones.
In a further method step S7, a simulation environment 5 for testing a driver assistance system, for example a virtual vehicle environment, is generated from the at least one test case generated. For this purpose, the simulation device 5 can have a simulation environment, for example MATLAB / Simulink, IPG CarMaker, PreScan, SUMO SCANer or Virtual Test Drive (VTD). The test environment 6 can be generated independently of the simulation environment used, since the traffic scenario descriptions in the traffic scenario database 2 are stored as traffic scenario files in a predetermined, in particular generic, format and, accordingly, the test cases in a standardized format, e.g. the OpenSCENARIO format.
It is pointed out that the exemplary embodiments are merely examples which are not intended to restrict the scope of protection, the applications and the structure in any way. Rather, the person skilled in the art is given a guideline for the implementation of at least one exemplary embodiment by the preceding description, wherein various changes, in particular with regard to the function and arrangement of the described components, can be carried out without leaving the scope of protection as it results from the Claims and these equivalent combinations of features.
FIG. 3 shows an example of a traffic scenario description 11 in a schematic illustration. Preferably, the traffic scenario description 12 shown corresponds to a general description of a specific traffic scenario, in particular a driving maneuver such as a cut-in maneuver in the example shown, in which an EGO vehicle 8, to which the traffic scenario relates, is one first lane 9a into a second, adjacent lane 9b behind a preceding vehicle 10, as indicated by the arrow. Based on a corresponding traffic scenario description 12, e.g. a driver assistance system, e.g. adaptive cruise control (ACC) to be tested for its reaction during and / or after reeving.
/ 27
PI32126AT
AVL List GmbH
Such a traffic scenario description 12 characterizing a traffic scenario can be determined in different ways. For example, traffic scenario descriptions can be loaded from NCAP, DVP and / or accident databases. As an alternative or in addition, sensor data can be collected that characterize the traffic scenario, for example by carrying out corresponding simulations or the EGO vehicle 8 equipped with a sensor device for detecting the vehicle environment is taking a test drive and a section that is generated by the sensor device and that is associated with the Traffic scenario corresponds when sensor data is extracted.
With regard to the cut-in maneuver, the sensor data stream is distinguished, for example, by the fact that the vehicle 10 driving ahead is suddenly detected in the middle of a detection area 11 of a sensor unit of the sensor device, for example a LIDAR sensor, when the lanes 9a, 9b change. This event can therefore be understood as a trigger for the cut-in maneuver and, preferably together with other corresponding triggers, can be used to extract the sensor data from the sensor data stream.
On the basis of the sensor data extracted in this way, parameters that define boundary conditions of the traffic scenario, for example the speed of the first-person vehicle 8 and the preceding vehicle 10, the distance of the first-person vehicle 8 from the preceding vehicle 10 at the beginning and / or at the end of the vehicle are preferably identified below Cut-in maneuvers, the lanes 9a, 9b and / or the like used by the vehicles 8, 10. The parameters identified in this way preferably determine how the cut-in maneuver proceeds.
The parameters can in particular be identified by comparing, in particular subtracting, different states of the two vehicles 8, 10, which are defined by the parameters and which occur during the course of the traffic scenario, in particular at the beginning and at the end of the traffic scenario. will.
The parameters identified in this way are preferably stored at least as part of the traffic scenario description 12 in a traffic scenario file, which together with other traffic scenario files, e.g. from NCAP, DVP and / or accident
PI32126AT
AVL List GmbH
Databases that forms a traffic scenario database. The traffic scenario file is preferably provided with a marker (tag) which identifies the traffic scenario description 12 stored in the traffic scenario as corresponding to a cut-in maneuver.
To generate a test case, on the basis of which a test environment can be generated in which the driver assistance system of the EGO vehicle 8 (hereinafter referred to as the test vehicle, since it is equipped with the driver assistance system to be tested) can be tested Traffic scenario description 12 of the CutIn maneuver, which was determined as described above, can be selected, eg by user input, by means of which all traffic scenario descriptions 12 identified with the corresponding marking are called up. Values for the parameters of the selected traffic scenario description 12 can e.g. can also be specified by user input or by calling up from a parameter database. The cut-in maneuver characterized by the selected traffic scenario description 12 is then preferably matched to the parameters defined by the parameters and / or further, e.g. Boundary conditions defined by the user input and criteria defined are adapted.
For example, a value can be specified for the, in particular lateral, speed of the test vehicle 8 which is lower than when the real cut-in maneuver is recorded. Accordingly, the implementation of the cut-in maneuver characterized by the test case proceeds more slowly or takes longer. In this way, at least one value or range of values can also be specified for other parameters in order to generate one or more implementations of the cut-in maneuver. Correspondingly, several different test cases can be generated easily and without great effort on the basis of the one traffic scenario description 12.
/ 27
AVL List GmbH
Reference list
method
Procedural steps
Traffic scenario database
Input device
Data processing device
Simulation device
Test environment
Sensor data stream
EGO vehicle or test vehicle
Lane other vehicle
Detection area
Traffic scenario description
contraption
权利要求:
Claims (8)
[1]
1. A method (1) for testing a driver assistance system for a vehicle in a test environment (6), comprising the following work steps:
- Determination (S2c) of traffic scenario descriptions (12), each of which characterize a specific traffic scenario, in particular a cut-in maneuver or a cut-out maneuver, and which have at least one parameter by means of which the respective traffic scenario is adapted to boundary conditions can, the traffic scenario descriptions (12) preferably, in particular in each case, being stored in a traffic scenario file in which the at least one parameter is stored in a predetermined, in particular generic, format;
- selecting (S4) at least one traffic scenario description (12) on the basis of an input from a user and / or based on predetermined criteria; and
- Generating (S6) a test case on the basis of the at least one selected traffic scenario description (12) and at least one predetermined value for the at least one parameter and preferably further traffic scenario descriptions, the test case with a concrete realization of the by the at least one selected traffic scenario description (12) characterized traffic scenarios and preferably further traffic scenarios in relation to the at least one predetermined value of the at least one parameter and is suitable for generating a test environment (6) in which a driver assistance system can be subjected to a test run.
[2]
2. The method of claim 1, further comprising the following step:
- Carrying out (S7) a test run using the generated test case.
[3]
3. The method (1) according to claim 1 or 2, further comprising the following steps:
22/27
PI32126AT
AVL List GmbH
- Determining (S2a) at least one data record which characterizes at least one, in particular real, traffic scenario; and
- Identifying (S2b) at least one parameter in the at least one determined data set, by means of which the respective traffic scenario can be adapted to boundary conditions, in particular an initial speed of a first-person vehicle, to which the traffic scenario relates.
[4]
4. The method according to claim 3, wherein the identification of the at least one parameter is carried out by means of a comparison of a classified vehicle environment in chronologically successive scenes of the at least one traffic scenario characterized by the at least one determined data record.
[5]
5. The method according to claim 3 or 4, further comprising the step:
- Generating at least one traffic scenario description (12) on the basis of the determined data record or the determined data records, wherein the traffic scenario description (12) characterizes the determined traffic scenario and wherein the at least one identified parameter is stored in the predetermined format.
[6]
6. The method according to any one of claims 1 to 5, further comprising the step:
Filing (S3) of the generated traffic scenario description (12), in particular the traffic scenario file, in a traffic scenario database (2), further traffic scenario files also being stored in the traffic scenario database (2).
[7]
7. The method according to any one of claims 1 to 6, further comprising at least one of the following steps:
- Determining the specified values from a test run database; and or
23/27
PI32126AT
AVL List GmbH
- Determining the specified values from a user input, in particular via a user interface.
[8]
8. Device (100) for testing a driver assistance system for a vehicle in a test environment (6), comprising:
- Means, in particular an interface or sensor device, for determining traffic scenario descriptions (12), each of which characterize a specific traffic scenario, in particular a cut-in maneuver or a cut-out maneuver, and have at least one parameter by means of which the respective Traffic scenario can be adapted to boundary conditions, and preferably for storing the traffic scenario descriptions (12), in particular in each case, in a traffic scenario file in which the at least one parameter is stored in a predetermined, in particular generic, format;
- Means, in particular a first module of a data processing device, for selecting at least one traffic scenario description (12) on the basis of an input from a user and / or predefined criteria; and
- Means, in particular a second module of a data processing device, for generating a test case on the basis of the at least one selected traffic scenario description (12) and at least one predefined value for the at least one parameter and preferably further traffic scenario descriptions, the test case having a specific one Realization of the traffic scenario characterized by the at least one selected traffic scenario description and preferably further traffic scenarios in relation to the at least one predetermined value of the at least one parameter corresponds and is suitable for generating a test environment (6) in which a driver assistance system can be subjected to a test run.
类似技术:
公开号 | 公开日 | 专利标题
EP3076377A1|2016-10-05|Method for providing information about free space in a region surrounding a motor vehicle as raw sensor data at a communication interface, sensor device, processing device and motor vehicle
EP3438901A1|2019-02-06|Test drive scenario database system for realistic virtual test drive scenarios
EP3526095B1|2020-10-28|Categorization of vehicles in the environment of a motor vehicle
DE102009028451A1|2011-02-17|Collision monitoring for a motor vehicle
AT521607B1|2020-03-15|Method and device for testing a driver assistance system
DE102018206805B3|2019-09-12|A method, apparatus and computer program for predicting a future movement of an object
DE102017204745A1|2017-09-28|Architecture and apparatus for advanced arbitration in integrated controllers
WO2015135688A1|2015-09-17|Apparatus and method for operating a vehicle
DE102018132520A1|2020-06-18|Method and system for controlling a motor vehicle
WO2020048669A1|2020-03-12|Method for determining a lane change indication of a vehicle, computer-readable storage medium, and vehicle
DE102016224291A1|2018-06-07|Method for the computer-aided adaptation of a predetermined semi-automated driving system of a motor vehicle
DE102015010270A1|2017-02-09|Method for operating driver assistance systems in a motor vehicle and motor vehicle
DE102014210752A1|2015-12-17|Method and device for monitoring a target trajectory of a vehicle
AT521724A1|2020-04-15|Method and device for analyzing a sensor data stream and method for driving a vehicle
AT523834B1|2021-12-15|Method and system for testing a driver assistance system
DE102017208692A1|2018-11-29|Method for providing training data for a functional test of a recognition device and database system
DE102016120066A1|2018-04-26|A computer implemented method for controlling an object recognition system
DE102018125712A1|2020-04-23|Driving support method for a vehicle
DE10347187B4|2014-01-09|Method and computer program for iteratively calculating the total mass of a vehicle
DE102015202343A1|2016-08-11|Method and system for performing automated driving maneuvers
EP3789926A1|2021-03-10|Method for detecting an adversarial fault in the input data of a neural network
DE102019213797A1|2021-03-11|Method for evaluating a sequence of representations of at least one scenario
AT521647B1|2020-09-15|Method and system for data processing, for training an artificial neural network and for analyzing sensor data
DE102019127322A1|2021-04-15|Method for detecting objects in a vehicle environment, device for data processing, computer program product and computer-readable data carrier
DE102019213222A1|2021-03-04|Method for predicting a future driving situation of a foreign object, device, vehicle participating in road traffic
同族专利:
公开号 | 公开日
EP3871134A1|2021-09-01|
AT521607B1|2020-03-15|
KR20210078546A|2021-06-28|
JP2022505759A|2022-01-14|
CN113168524A|2021-07-23|
WO2020083996A1|2020-04-30|
US20220048536A1|2022-02-17|
引用文献:
公开号 | 申请日 | 公开日 | 申请人 | 专利标题
DE102011088807A1|2011-12-16|2013-06-20|Bayerische Motoren Werke Aktiengesellschaft|Method for developing and/or testing driver assistance system for motor car, involves determining set of scenarios and characterizing set of scenarios by parameter that is related to driving conditions of car|
US20160280233A1|2013-11-05|2016-09-29|Avl List Gmbh|Virtual test optimization for driver assistance systems|
WO2017210222A1|2016-05-30|2017-12-07|Faraday&Future Inc.|Generating and fusing traffic scenarios for automated driving systems|
CN108646586A|2018-03-20|2018-10-12|重庆邮电大学|A kind of intelligent network connection automobile assemblage on-orbit, test verification System and method for|DE102016220913A1|2015-11-06|2017-05-11|Ford Global Technologies, Llc|Method and device for generating test cases for autonomous vehicles|
AT523834B1|2020-09-15|2021-12-15|Avl List Gmbh|Method and system for testing a driver assistance system|
法律状态:
优先权:
申请号 | 申请日 | 专利标题
ATA50922/2018A|AT521607B1|2018-10-24|2018-10-24|Method and device for testing a driver assistance system|ATA50922/2018A| AT521607B1|2018-10-24|2018-10-24|Method and device for testing a driver assistance system|
JP2021522417A| JP2022505759A|2018-10-24|2019-10-23|Methods and equipment for testing driver assistance systems|
CN201980079143.7A| CN113168524A|2018-10-24|2019-10-23|Method and device for testing a driver assistance system|
PCT/EP2019/078898| WO2020083996A1|2018-10-24|2019-10-23|Method and device for testing a driver assistance system|
EP19797196.3A| EP3871134A1|2018-10-24|2019-10-23|Method and device for testing a driver assistance system|
US17/287,814| US20220048536A1|2018-10-24|2019-10-23|Method and device for testing a driver assistance system|
KR1020217015581A| KR20210078546A|2018-10-24|2019-10-23|Method and apparatus for testing driver assistance systems|
[返回顶部]