EP4028890A2 - Computerimplementiertes verfahren zur terminierung eines szenario-basierten testprozesses eines fahrassistenzsystems - Google Patents
Computerimplementiertes verfahren zur terminierung eines szenario-basierten testprozesses eines fahrassistenzsystemsInfo
- Publication number
- EP4028890A2 EP4028890A2 EP21749586.0A EP21749586A EP4028890A2 EP 4028890 A2 EP4028890 A2 EP 4028890A2 EP 21749586 A EP21749586 A EP 21749586A EP 4028890 A2 EP4028890 A2 EP 4028890A2
- Authority
- EP
- European Patent Office
- Prior art keywords
- distance
- test
- critical
- test cases
- cycle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012360 testing method Methods 0.000 title claims description 108
- 238000000034 method Methods 0.000 title claims description 106
- 230000008569 process Effects 0.000 title claims description 34
- 238000013461 design Methods 0.000 claims description 68
- 238000011156 evaluation Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 5
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 238000006467 substitution reaction Methods 0.000 claims 1
- 238000004088 simulation Methods 0.000 description 12
- 230000001133 acceleration Effects 0.000 description 7
- 238000005094 computer simulation Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000010998 test method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- IXUZXIMQZIMPSQ-ZBRNBAAYSA-N [(4s)-4-amino-4-carboxybutyl]azanium;(2s)-2-amino-4-hydroxy-4-oxobutanoate Chemical compound OC(=O)[C@@H](N)CCC[NH3+].[O-]C(=O)[C@@H](N)CC(O)=O IXUZXIMQZIMPSQ-ZBRNBAAYSA-N 0.000 description 2
- 238000012938 design process Methods 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000036461 convulsion Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
- B60W50/0225—Failure correction strategy
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3688—Test management for test execution, e.g. scheduling of test suites
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
- B60W50/0205—Diagnosing or detecting failures; Failure detection models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
- B60W50/023—Avoiding failures by using redundant parts
Definitions
- the invention relates to a computer-implemented method for terminating a scenario-based test process of a driver assistance system according to the preamble of patent claim 1.
- Driving assistance systems such as an adaptive cruise control and/or functions for highly automated driving can be verified or validated using various verification methods.
- hardware-in-the-loop methods software-in-the-loop methods, simulations and/or test drives can be used.
- DE 10 2017 200 180 A1 specifies a method for verifying and/or validating a vehicle function, which is provided for driving a vehicle autonomously in the longitudinal and/or transverse direction.
- the method includes determining, on the basis of environmental data relating to an area surrounding the vehicle, a test control instruction to an actuator of the vehicle in order to implement a vehicle function, the test control instruction not being implemented by the actuator.
- the method also includes simulating, on the basis of environment data and using a road user model with respect to at least one road user in the area surrounding the vehicle, a fictitious traffic situation that would exist if the test control instruction had been implemented.
- the method also includes providing test data relating to the fictitious traffic situation. In this case, the vehicle function is operated passively in the vehicle in order to determine the test control instruction.
- a disadvantage of this method is that verification and/or validation of the vehicle function requires actual operation of the vehicle to determine the required data.
- the object is achieved according to the invention by a computer-implemented method for terminating a scenario-based test process of a driver assistance system according to patent claim 1, a computer program according to patent claim 14 and a computer-readable storage medium according to patent claim 15.
- the invention relates to a method for terminating a scenario-based test process of a driver assistance system, critical test cases being indicated by parameter combinations leading to critical driving situations, for example a vehicle collision or a near-vehicle collision, of specific driving situation parameters spanning a metric parameter space.
- the method also includes a cyclic test process that includes the determination of critical test cases and uses a distance metric for termination, ie as a condition for terminating the cycle.
- the method includes the following steps: after each iteration n of the cycle, at least one test of the driver assistance system is carried out and a number of critical test cases are determined, • Based on this, a distance in the parameter space between a first set of critical test cases in iteration n and a second set of critical test cases from iteration n-1 or a previously defined set of critical test cases is determined and
- the cycle of the testing process is terminated or continued such that the testing process is cyclically repeated.
- scenarios are defined which can be described as an abstraction of a traffic situation.
- a logical scenario here is the abstraction of a traffic situation with the road, driving behavior and the surrounding traffic without concrete parameter values.
- the logical scenario becomes a concrete scenario.
- Such a concrete scenario corresponds to an individual traffic situation.
- the cut-in scenario can be described as a traffic situation in which a highly automated or autonomous vehicle drives in a specified lane and another vehicle moves from another lane into the lane of the ego vehicle at a reduced speed compared to the ego vehicle certain distance.
- the ego vehicle refers here to the vehicle to be tested.
- a parameter set of a scenario can consist of scenery parameters and driving situation parameters, with all parameters having a predefined definition range.
- driving situation parameters can be determined by the number and type of road users. Driving situation parameters thus reflect moving objects in the scenario, such as the number of road users, type of road users, number of lane changes and/or maneuvers carried out by the road users.
- the procedural test process includes an extended replacement model creation process in order to be able to efficiently specify an approximation of the described scenario.
- the extended replacement model creation process in order to be able to efficiently specify an approximation of the described scenario.
- Substitute modeling process includes a cycle of at least a design phase, a modeling phase and a test phase including the determination of critical test cases.
- a distance metric is determined after each cycle.
- the definition of a predetermined limit or threshold value controls the termination of the substitute model formation, that is to say of the cycle.
- surrogate models can be employed to speed up the testing process, as indicated by the method of the present invention.
- Surrogate models are simplified mathematical functions that predict the rating of a simulated test drive for at least a given set of parameters. As a rule, fewer simulations are required to create a substitute model than to identify critical test cases using other methods. If no simulations are then carried out when identifying critical test cases, but the Using surrogate model predictions saves time in the testing process.
- the method according to the invention first runs through a design phase and a modeling phase for the formation of the replacement model.
- the substitute modeling method is determined by a design and a modeling method.
- the set S Q X of points from the domain for which evaluations are carried out is called the design.
- the elements x e S are design points.
- the f(s) e Y values are the associated evaluations of the computer model.
- the term computer model is used because the functions studied in surrogate modeling cannot be written as a simple formula and a computer is required to efficiently determine an output.
- the evaluation of computer models is also referred to as simulation.
- a design can be created either sequentially or non-sequentially.
- the design points are chosen in one step.
- a design is sequential if the design points are chosen one after the other. Only one or more new design points can be selected in each step.
- Sequential methods require a non-sequential starting design. This serves as a starting point for selecting new design points.
- termination conditions can be formulated so that not too many design points are evaluated. Since computer models, i.e. simulations, have long evaluation times, this is an advantage. If no more evaluations are carried out than necessary, this accelerates the creation of substitute models. In addition, the step width between the steps or iterations of the selection of new design points can be varied.
- Voronoi design An example of a design process is the Voronoi design. It is a sequential design and requires a starting design to gain new points Select. It is a sequential, space-filling design, so areas need to be identified where few dots are distributed. A description of these areas follows with the eponymous Voronoi diagram.
- a Voronoi diagram is a decomposition of space into regions that are determined by a given set of points in space, referred to here as centers. Each region is determined by exactly one center and includes all points in space that are closer to the center of the region than to any other center in terms of the Euclidean metric.
- Voronoi design An extension of the Voronoi design is the LOLA-Voronoi design.
- the LOLA-Voronoi theme is sequential and requires a starting theme.
- the design uses two evaluations of the previous design points to identify areas where new design points are chosen. One rating for exploration and one rating for exploitation.
- the LOI_A algorithm is used for the exploitation.
- LOLA stands for local linear approximation.
- the LOLA algorithm selects new design points at points where the system deviates the most from a locally linear approximation.
- Modeling processes form a substitute model from an existing design and the associated evaluations of the computer model/simulation.
- An example method of modeling is the radial basis function.
- the substitute model consists of a linear combination of basis functions. If the design has n points with evaluations / simulations, the linear combination consists of n basis functions. Radial basis functions are often used to model computer models.
- test results can be approximated and, in particular, critical test cases can also be determined.
- a termination condition is necessary to terminate the cyclical test process consisting of a design phase, a modeling phase and a test phase, including the determination of critical test cases, as efficiently as possible.
- a big advantage of sequential designs is the possibility to formulate termination conditions.
- the Hausdorff distance of the sets of critical test cases as a distance metric can be used as a termination condition.
- critical test cases are determined by parameter combinations of specific, one metric parameter space leading to critical driving situations, for example a vehicle collision or a near vehicle collision spanning driving situation parameters specified. It is therefore relevant to identify exactly these parameter combinations and to integrate them into the formation of a substitute model.
- the Hausdorff distance is used to determine a distance in the parameter space between a first set of critical test cases in iteration n and a second set of critical test cases from iteration n-1 or a previously defined set of critical test cases and based on the difference in the distance in metric space between the first set and the second set and a predetermined limit, the cycle of the testing process is terminated or continued.
- a better surrogate model is formed as the number of design points increases, so that critical test cases can be better approximated with the surrogate model. If the Hausdorff distance between the set of critical test cases in the current iteration and the set of critical test cases from the previous iteration is small, there are enough design points and a good approximation of critical test cases is still achieved.
- a better quality of the substitute model can thus be determined over a number of cycles with a consistently small distance metric such as in particular the Hausdorff distance between the considered sets of critical test cases.
- Various evaluation functions of highly automated vehicles can be used as a basis for the approximation of critical test cases.
- the method also includes that the evaluation function is a safety objective function which has a numerical value which has a minimum value at a distance between the motor vehicle and the other motor vehicle of >FELLOW X 0.55 a collision between the motor vehicle and the further motor vehicle has a maximum value, and at a distance between the motor vehicle and the further motor vehicle of ⁇ FELLOW X 0.55 has a numerical value which is greater than the minimum value.
- the evaluation function is a safety objective function which has a numerical value which has a minimum value at a distance between the motor vehicle and the other motor vehicle of >FELLOW X 0.55 a collision between the motor vehicle and the further motor vehicle has a maximum value, and at a distance between the motor vehicle and the further motor vehicle of ⁇ FELLOW X 0.55 has a numerical value which is greater than the minimum value.
- the safety objective function indicates how safe the traffic situation is for the ego vehicle. It is specified as follows: If the distance between the ego vehicle and the fellow vehicle is always greater than or equal to the safety distance, the function value of the safety objective function is 0.
- the safety distance can be defined as a distance at which, depending on a speed difference between the ego vehicle and the fellow vehicle and the distance between the ego vehicle and the fellow vehicle, the ego vehicle can always be braked safely without a collision occurring the Fellow vehicle is possible.
- Such a distance is defined in the present example by a value in meters which corresponds to the speed VFELLOW X 0.55.
- the objective function value approaches the value 1 more and more. Consequently, if there is a collision of the ego vehicle and the fellow vehicle, the distance between the ego vehicle and the fellow vehicle is less than or equal to zero and the objective function value is 1.
- the method according to the invention also has that the evaluation function is a comfort target function or an energy consumption target function which has a numerical value which has a minimum value in the case of no change in the acceleration of the motor vehicle in the event of a collision between the motor vehicle and the further motor vehicle has a maximum value, and when the acceleration of the motor vehicle changes depending on the amount of change in the acceleration, has a numerical value between the minimum value and the maximum value.
- the evaluation function is a comfort target function or an energy consumption target function which has a numerical value which has a minimum value in the case of no change in the acceleration of the motor vehicle in the event of a collision between the motor vehicle and the further motor vehicle has a maximum value, and when the acceleration of the motor vehicle changes depending on the amount of change in the acceleration, has a numerical value between the minimum value and the maximum value.
- the changes in acceleration are called jerks.
- the driving situation is all the more comfortable the smaller the calculated value of the comfort target function is.
- the fuel consumption in the event of a collision between the ego vehicle and the fellow vehicle is 1, i.e. the fuel consumption is set to a specified maximum value.
- the reason for this is that the tank filling of a vehicle can no longer be used in the event of an accident.
- the object of the invention is to specify a method that develops the prior art.
- FIG. 1 shows a schematic view of different traffic scenarios with different driving maneuvers of an ego vehicle and a varying number of Fellow vehicles
- Figure 2 is a schematic view showing a boundary between critical and non-critical test results
- FIG. 3 shows a Voronoi diagram as an example of a design method
- Figure 4 schematically the determination of a Hausdorff distance
- FIG. 5 schematic view of the previous test method using a substitute model
- FIG. 6 shows a schematic view of the test method according to the invention using a substitute model
- FIG. 7 shows a schematic representation of a course of Hausdorff distances over a number of evaluations/simulations
- FIG. 1 shows a schematic representation for distinguishing between scenarios (Si to S n ) according to the invention.
- the scenarios Si and S2 can be completely different in relation to the subset of their parameter set, have overlapping parameters or also be the same in relation to the subset of their respective parameter set.
- critical test cases are performed by parameter combinations of specific, one metric leading to critical driving situations, for example a vehicle collision or a near vehicle collision Parameter space spanning driving situation parameters specified. Therefore, these parameter combinations must be identified in a scenario.
- FIG. 1 A scenario is shown on the left-hand side of FIG. 1, which shows a turning maneuver and has an Ego vehicle and four Fellow vehicles. The same intersection area is shown on the right-hand side of FIG. 1, but without a turning maneuver with only one ego vehicle.
- FIG. 1 Various scenarios are shown in FIG. 1, which allow different combinations of parameters and also allow different critical test cases.
- FIG. 2 shows the cut-in scenario using the driving situation parameters EGO, i.e. a speed of the ego vehicle, and on the vertical axis VFELLOW, i.e. the speed of the fellow vehicle driving ahead.
- EGO driving situation parameters
- VFELLOW vertical axis
- the function shown in FIG. 2 forms the boundary between critical and non-critical test results (Crit_TF).
- the points shown are approximate test results. Alternatively, the points shown can be simulated test results, for example.
- the evaluation function (BF) shown is the safety target function, which has a numerical value that has a minimum value at a safety distance between the motor vehicle and the other motor vehicle of >VFELLOW ⁇ 0.55 in the event of a collision between the motor vehicle and the further motor vehicle has a maximum value, and with a safety distance between the motor vehicle and the further motor vehicle of ⁇ VFELLOW X 0.55 has a numerical value which is greater than the minimum value.
- a comfort target function or an efficiency target function can be approximated, for example, which has a numerical value that has a minimum value if there is no change in the acceleration of the motor vehicle and a maximum value in the event of a collision between the motor vehicle and the other motor vehicle has, and with a change in the acceleration of the Motor vehicle depending on the amount of change in acceleration has a numerical value between the minimum value and the maximum value.
- a Voronoi diagram is shown in FIG. 3 as an example of a design method in the design phase (D).
- D design phase
- the corresponding Voronoi cell is drawn around each of the points. Cells are smaller in areas with multiple design points. In the figure this is visible in the middle of the definition area.
- the sequential Voronoi design consists of three steps:
- the sizes of the cells are approximated in relation to the size of the domain in order to save time and computing effort. For this purpose, a number of random points in the domain of definition are chosen. For each randomly selected point, the design point that is closest is determined.
- Each design point is assigned the number of random points that are closest to the design point.
- the size of a Voronoi cell associated with a design point is equal to the number of random points closest to the design point divided by the total number of random points chosen.
- FIG. 4 shows a schematic representation of a determination of a Hausdorff distance as an example of a distance metric (AM) between two sets.
- the Hausdorff distance between sets of critical test cases (Crit_TF) as a distance metric (AM) can be used according to the invention as a termination condition.
- a distance in the parameter space between a first set of critical test cases (Krit_TF, tn) in iteration n and a second set of critical test cases (Krit_TF, tn-1) from iteration n-1 or a previously defined set becomes more critical Test cases (Krit_TF) are determined and the cycle (Z) of the test process (TP) is terminated or continued on the basis of the difference in the distance in metric space between the first set and the second set and a previously defined limit.
- Figure 4 shows how the Hausdorff distance of two sets results.
- the figure shows two compact subsets B and A.
- the point a e A is marked, whose distance B(a,B) to the set B is maximum.
- the distance is marked with a black line.
- B is marked with maximum distance B(4,ö).
- FIG. 5 shows a schematic view of the previous test method using an equivalent model (EM).
- the substitute modeling process (EBV) consists of a design phase (D) and a modeling phase (M).
- D design phase
- M modeling phase
- a cycle between the design (D) and modeling phase (M) can be run through 1 to n times, depending on the methods used or termination criteria.
- the test process can start using the substitute model.
- tests are carried out and evaluated in the course of identifying critical test cases (Krit_TF).
- Krit_TF critical test cases
- FIG. 6 shows the computer-implemented method according to the invention.
- an equivalent model (EM) is created using a method (EBMV) including a design phase (D) and a modeling phase (M).
- the replacement model creation method (EBV) also includes the test process (TP).
- a termination is based on a distance metric (AM) such as the Hausdoff distance, in the parameter space between a first set of critical test cases (Krit_TF, tn) in iteration n and a second set of critical test cases (Krit_TF, tn-1) from iteration n-1 or a previously defined set of critical test cases (Krit_TF).
- AM distance metric
- Z new cycle n + 1 is started with the design phase (D).
- FIG. 7 shows a schematic representation of a course of distance metrics (AM) using the example of the Hausdorff distance over a number of evaluations/simulations.
- the Hausdorff distances are shown in the vertical axis in FIG.
- a sequential design is preferably used in the design phase (D), such as for example LOLA-Voronoi.
- the design process uses a starting design and determines new design points in each iteration. After each iteration, the scenario used is simulated and the respective evaluation function (BF) is evaluated, for example a safety target function.
- BF evaluation function
- a termination (Ter) or termination condition is based on the Hausdorff distance of critical test cases (Crit_TF). With this, a sequential replacement model creation method (EBV) will terminate if no or only minor changes in the approximation of critical test cases (Crit_TF) take place in a step.
- EBV sequential replacement model creation method
- the Hausdorff distances of two successive approximations of the critical test cases (Crit_TF) are considered. This is not yet possible in the first run and new points are added to the design with the sequential design. With the second iteration, the pairwise comparison of the Hausdorff distances between the approximations of the critical test cases (Crit_TF) can be determined.
- FIG. 7 shows the development of the Hausdorff distances between the iterations. If this value of the respective Hausdorff distance is smaller than a previously specified limit, the termination (Ter) or termination condition is met. Otherwise, new design points are chosen in the design phase (D) and the process is repeated until termination (Ter).
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Human Computer Interaction (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Computer Hardware Design (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102020120500.7A DE102020120500A1 (de) | 2020-08-04 | 2020-08-04 | Computerimplementiertes Verfahren zur Terminierung eines szenario-basierten Testprozesses eines Fahrassistenzsystems |
PCT/EP2021/070809 WO2022028934A2 (de) | 2020-08-04 | 2021-07-26 | Computerimplementiertes verfahren zur terminierung eines szenario-basierten testprozesses eines fahrassistenzsystems |
Publications (1)
Publication Number | Publication Date |
---|---|
EP4028890A2 true EP4028890A2 (de) | 2022-07-20 |
Family
ID=77179998
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP21749586.0A Pending EP4028890A2 (de) | 2020-08-04 | 2021-07-26 | Computerimplementiertes verfahren zur terminierung eines szenario-basierten testprozesses eines fahrassistenzsystems |
Country Status (5)
Country | Link |
---|---|
US (1) | US20240010210A1 (de) |
EP (1) | EP4028890A2 (de) |
CN (1) | CN115735197A (de) |
DE (1) | DE102020120500A1 (de) |
WO (1) | WO2022028934A2 (de) |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102017200180A1 (de) | 2017-01-09 | 2018-07-12 | Bayerische Motoren Werke Aktiengesellschaft | Verfahren und Testeinheit zur Bewegungsprognose von Verkehrsteilnehmern bei einer passiv betriebenen Fahrzeugfunktion |
-
2020
- 2020-08-04 DE DE102020120500.7A patent/DE102020120500A1/de active Pending
-
2021
- 2021-07-26 WO PCT/EP2021/070809 patent/WO2022028934A2/de active Application Filing
- 2021-07-26 EP EP21749586.0A patent/EP4028890A2/de active Pending
- 2021-07-26 US US18/004,071 patent/US20240010210A1/en active Pending
- 2021-07-26 CN CN202180046192.8A patent/CN115735197A/zh active Pending
Also Published As
Publication number | Publication date |
---|---|
US20240010210A1 (en) | 2024-01-11 |
CN115735197A (zh) | 2023-03-03 |
DE102020120500A1 (de) | 2022-02-10 |
WO2022028934A2 (de) | 2022-02-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2999998B1 (de) | Methode zur ermittlung eines modells einer ausgangsgrösse eines technischen systems | |
DE102019124018A1 (de) | Verfahren zum Optimieren von Tests von Regelsystemen für automatisierte Fahrdynamiksysteme | |
EP3785177A1 (de) | Verfahren und vorrichtung zum ermitteln einer netzkonfiguration eines neurona-len netzes | |
WO2022028935A1 (de) | Computerimplementiertes verfahren zum bereitstellen eines test-verlaufs zu testender verkehrsszenarien | |
WO2021058223A1 (de) | Verfahren zur effizienten, simulativen applikation automatisierter fahrfunktionen | |
DE102017218851A1 (de) | Verfahren, Vorrichtung und Computerprogramm zur Erstellung eines tiefen neuronalen Netzes | |
DE102018128890A1 (de) | Verfahren und Testvorrichtung zum Testen eines Fahrassistenzsystems für ein Kraftfahrzeug | |
EP3783446B1 (de) | Computerimplementiertes verfahren und testeinheit zum approximieren einer teilmenge von testergebnissen | |
DE102019134053A1 (de) | Verfahren zur kontinuierlichen Absicherung im Fahrversuch applizierter automatisierter Fahrfunktionen | |
WO2020207789A1 (de) | Verfahren und vorrichtung zum ansteuern einer technischen einrichtung | |
EP4028890A2 (de) | Computerimplementiertes verfahren zur terminierung eines szenario-basierten testprozesses eines fahrassistenzsystems | |
EP4105811A1 (de) | Computerimplementiertes verfahren zum szenariobasierten testen und/oder homologation von zu testenden zumindest teilweise autonomen fahrfunktionen durch key performance indicators (kpi) | |
WO2016050553A1 (de) | Ein trajektorien-planungsverfahren zur ermittlung eines steuerprofils für ein kraftfahrzeug | |
AT524932B1 (de) | Verfahren und System zum Testen eines Fahrerassistenzsystems für ein Fahrzeug | |
EP0813986B1 (de) | Verfahren zur Abstandsregelung für ein Fahrzeug | |
EP3871052B1 (de) | Verfahren zur kalibirierung eines technischen systems | |
WO2022077042A1 (de) | Verfahren und ein system zum testen eines fahrerassistenzsystems für ein fahrzeug | |
EP4027245A1 (de) | Computerimplementiertes verfahren zur bestimmung von ähnlichkeitswerten von verkehrsszenarien | |
WO2021089499A1 (de) | Verfahren und system zum prüfen einer automatisierten fahrfunktion durch reinforcement-learning | |
EP3783452A1 (de) | Computerimplementiertes verfahren und testeinheit zum approximieren von testergebnissen und verfahren zum bereitstellen eines trainierten, künstlichen neuronalen netzes | |
DE102022002916A1 (de) | Verfahren zum Ermitteln einer Schaltstrategie für ein Schaltgetriebe eines Fahrzeugs, sowie Verfahren zum Trainieren eines lernfähigen Systems zur Prädiktion einer Schaltstrategie und Fahrerassistenzsystem | |
DE102022129009A1 (de) | Verfahren zum Testen von automatisierten Fahrzeugfunktionen | |
DE102022132181A1 (de) | Verfahren für eine dynamische Modellauswahl bei einer ADAS/ADS-Simulation | |
DE102022117839A1 (de) | Computerimplementiertes Verfahren zur Optimierung von Parametern eines Fahrerassistenzsystems eines Kraftfahrzeugs | |
DE102021123597A1 (de) | Verfahren und Steuergerät zur automatisierten Applikation von Fahrerassistenzsystemen im Serienbetrieb |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION HAS BEEN PUBLISHED |
|
AK | Designated contracting states |
Kind code of ref document: A2 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20220810 |
|
RBV | Designated contracting states (corrected) |
Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
DAV | Request for validation of the european patent (deleted) | ||
DAX | Request for extension of the european patent (deleted) |