US20220138575A1 - Computer implemented method and test unit for approximating test results and a method for providing a trained, artificial neural network - Google Patents

Computer implemented method and test unit for approximating test results and a method for providing a trained, artificial neural network Download PDF

Info

Publication number
US20220138575A1
US20220138575A1 US17/559,716 US202117559716A US2022138575A1 US 20220138575 A1 US20220138575 A1 US 20220138575A1 US 202117559716 A US202117559716 A US 202117559716A US 2022138575 A1 US2022138575 A1 US 2022138575A1
Authority
US
United States
Prior art keywords
motor vehicle
driving situation
target function
definition
parameters
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
Application number
US17/559,716
Inventor
Sebastian BANNENBERG
Fabian Lorenz
Rainer Rasche
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dspace GmbH
Original Assignee
Dspace GmbH
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Priority claimed from EP19192743.3A external-priority patent/EP3783452A1/en
Priority claimed from EP19192741.7A external-priority patent/EP3783446B1/en
Application filed by Dspace GmbH filed Critical Dspace GmbH
Assigned to DSPACE GMBH reassignment DSPACE GMBH ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: RASCHE, RAINER, LORENZ, Fabian, BANNENBERG, Sebastian
Publication of US20220138575A1 publication Critical patent/US20220138575A1/en
Assigned to DSPACE GMBH reassignment DSPACE GMBH CHANGE OF NAME (SEE DOCUMENT FOR DETAILS). Assignors: DSPACE DIGITAL SIGNAL PROCESSING AND CONTROL ENGINEERING GMBH
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/088—Non-supervised learning, e.g. competitive learning
    • 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
    • B60W50/06—Improving the dynamic response of the control system, e.g. improving the speed of regulation or avoiding hunting or overshoot
    • 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
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
    • 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
    • G06F11/3664—Environments for testing or debugging software
    • 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
    • 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
    • G06F11/3692—Test management for test results analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/047—Probabilistic or stochastic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections

Definitions

  • the present invention relates to a computer-implemented method for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • the present invention further relates to a computer-implemented method for providing a trained, artificial neural network for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • the invention also further relates to a test unit for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • the present invention further relates to a computer program and a computer-readable data carrier.
  • Driver assistance systems such as adaptive cruise control and/or highly automated driving functions can be verified and validated using a variety of verification methods.
  • hardware-in-the-loop methods software-in-the-loop methods, simulations and/or test drives can be used.
  • the overhead, in particular the time and/or cost, for testing such vehicle functions using the above-mentioned verification methods is typically very high, since a large number of potentially possible driving situations must be tested.
  • DE 10 2017 200 180 A1 specifies a method for verifying and/or validating a vehicle function, which is intended to autonomously guide a vehicle in the longitudinal and/or transverse direction.
  • the method includes determining a test control instruction of the vehicle function to an actuator of the vehicle, wherein the test control instruction is not implemented by the actuator.
  • the method further includes simulating a fictitious traffic situation that would be present if the test control instruction had been implemented.
  • the method further comprises the provision of test data relating to the fictitious traffic situation.
  • the vehicle function is operated passively in the vehicle to determine the test control instruction.
  • a disadvantage of this method is that the actual operation of the vehicle is required for the verification and/or validation of the vehicle function in order to be able to determine the required data.
  • test cases can be efficiently determined in scenario-based testing of systems and system components in highly automated driving.
  • the object is achieved by a computer-implemented method for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle, a computer-implemented method for providing a trained, artificial neural network for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle, a test unit for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle, a computer program and a computer-readable data carrier.
  • the invention relates to a computer-implemented method for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • the method comprises receiving a first data set comprising a plurality of driving situation parameters formed of environment parameters describing the environment of the motor vehicle and EGO parameters describing the state of the motor vehicle, wherein each driving situation parameter has a predetermined domain of definition.
  • the method further comprises approximating a numerical value range of a target function for the domain of definition of at least one driving situation parameter using a trained, artificial neural network which is applied to the plurality of driving situation parameters, wherein the target function represents a driving maneuver of a motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition.
  • the method further comprises providing a second data set including the numerical value range of the target function and the associated domain of definition of the at least one driving situation parameter.
  • the present invention is thus advantageously able to replace the simulation of driving situations and/or driving situation parameters by means of an artificial neural network.
  • test results are test results of interest, which are the subject of virtual tests of a device, such as a control device, for the autonomous guidance of a motor vehicle.
  • scenarios are defined which can be described as the abstraction of a traffic situation.
  • a logical scenario here is the abstraction of a traffic situation with the road, the driving behavior and the surrounding traffic without concrete parameter values.
  • the logical scenario becomes a concrete scenario.
  • Such a concrete scenario corresponds to a particular traffic situation.
  • An autonomous driving function is realized by a system, for example a control unit.
  • the control unit is conventionally tested in the real vehicle in real traffic situations or, alternatively, validated by virtual tests.
  • the present method approximates test results or traffic situations of interest within a predetermined domain of definition of the driving situation parameters used.
  • the domain of definition of the driving situation parameters is chosen such that it covers, for example, safety-related driving situations such as, for example, collisions or near-collisions of involved vehicles.
  • test results approximated in this way can then be advantageously validated in the context of virtual tests of the control unit, so that an efficient virtual validation of control units for the autonomous guidance of motor vehicles is possible using the method according to the invention.
  • the method according to the invention further comprises that the EGO parameters include a speed of the motor vehicle and the environment parameters include a speed of a further motor vehicle and a distance between the motor vehicle and the further motor vehicle.
  • the cut-in scenario can be described as a traffic situation in which a highly automated or autonomous vehicle drives in a predetermined lane and another vehicle merges into the lane of the EGO vehicle from another lane, at a certain distance and at a reduced speed as compared to the speed of the EGO vehicle.
  • the speed of the EGO vehicle and the further vehicle which is also referred to as a FELLOW vehicle, is constant. Since the speed of the EGO vehicle is higher than that of the FELLOW, the EGO vehicle must be braked to avoid a collision of the two vehicles.
  • the method according to the invention further comprises that the target function is a safety target function having a numerical value, which has a minimum value at a safety distance between the motor vehicle and the further motor vehicle of ⁇ V FELLOW ⁇ 0.55, has a maximum value in a collision between the motor vehicle and the further motor vehicle, and at a safety distance between the motor vehicle and the further motor vehicle of ⁇ V FELLOW ⁇ 0.55, has a value which is greater than the minimum value.
  • the safety target 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 functional value of the safety target function is 0.
  • the safety distance can be defined as a distance at which, as a function of a speed difference between the EGO vehicle and the FELLOW vehicle and the distance between the EGO vehicle and the FELLOW vehicle, safe braking of the EGO vehicle is always possible without the occurrence of a collision with the FELLOW vehicle.
  • Such a distance is defined in the present example by a value in meters which corresponds to the velocity V FELLOW ⁇ 0.55.
  • the target function value more and more approaches the value of 1. Accordingly, 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 0 and the target function value is 1.
  • the method according to the invention also can comprise that the target function is a comfort target function or an energy consumption target function having a numerical value which has a minimum value if there is no change in the acceleration of the motor vehicle, has a maximum value in the event of a collision between the motor vehicle and the further motor vehicle, and in a change in the acceleration of the motor vehicle as a function of the amount of change in the acceleration, has a value between the minimum value and the maximum value.
  • the target function is a comfort target function or an energy consumption target function having a numerical value which has a minimum value if there is no change in the acceleration of the motor vehicle, has a maximum value in the event of a collision between the motor vehicle and the further motor vehicle, and in a change in the acceleration of the motor vehicle as a function of the amount of change in the acceleration, has a value between the minimum value and the maximum value.
  • the changes in acceleration are called jerks.
  • the driving situation is the more comfortable, the smaller the calculated value of the comfort target function.
  • energy consumption is a fixed maximum value. The reason for this is that in a motor vehicle with an internal combustion engine and/or a traction battery in an electrically operated vehicle or hybrid vehicle, the tank of gas can generally no longer be used in the event of an accident.
  • possible safety-relevant test cases may lie between collision and non-collision cases, which can be defined on the basis of the respective target functions, i.e., the safety target function, the comfort target function and the energy consumption target function.
  • the method according to the invention furthermore can comprise that the plurality of driving situation parameters, in particular the speed of the motor vehicle and the speed of the further motor vehicle, are generated within the predetermined domain of definition by a random algorithm.
  • the plurality of driving situation parameters constituting the data set that is used to approximate the test results can be easily and time efficiently generated.
  • the method according to the invention can further comprise that a separate artificial neural network is used for approximating the numerical value range of each target function, wherein individual hyperparameters of each artificial neural network are stored in a database.
  • the artificial neural network used in each case can be trained specifically for the best possible approximation of the relevant target function and is thus advantageously able to produce a more accurate approximation result as compared to an artificial neural network which approximates a plurality of target functions by means of a common algorithm.
  • the method according to the invention can further comprise that as a function of the target function, the artificial neural network uses between 2 to 15 layers, between 6 and 2048 neurons per layer, and ReLU, LeakyReLU or ELU as the activation function. This way, the best possible approximation results can be achieved in the present configuration.
  • the second data set comprising the numerical value range of the target function and the assigned domain of definition of the at least one driving situation parameter can be graphically represented two-dimensionally or three-dimensionally as a function of a number of driving situation parameters.
  • a functional course of the approximated numerical value range of the target function for the given domain of definition of the driving situation parameters used can be represented graphically. This allows for the graphical representation of non-collision cases, collision cases and a boundary between non-collision cases and collision cases.
  • the invention further relates to a computer-implemented method for providing a trained, artificial neural network for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • the method comprises receiving a first set of input training data comprising a plurality of driving situation parameters including environment parameters describing the surroundings of the motor vehicle and EGO parameters describing the state of the motor vehicle, wherein each driving situation parameter has a predetermined domain of definition.
  • the method further comprises receiving a second set of output training data formed of the numerical value range of the target function and the associated domain of definition of the at least one driving situation parameter, wherein the output training data is associated with the input training data.
  • the method comprises training the artificial neural network to approximate a numerical value range of the target function for the domain of definition of at least one driving situation parameter, wherein the target function represents a driving maneuver of the motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition, based on the input training data and the output training data with a training calculation unit.
  • the method comprises the provision of the trained, artificial neural network for approximating test results of the virtual test of the device for the at least partially autonomous guidance of the motor vehicle.
  • the thus trained, artificial neural network is therefore advantageously able to attain an exact approximation result of the target function to be approximated.
  • the plurality of driving situation parameters in particular the speed of the motor vehicle and the speed of the further motor vehicle, can be generated within the predetermined domain of definition by a random algorithm and/or by a simulation.
  • the parameter sets of driving situation parameters can thus be generated in a simple manner, for example when using an artificial neural network by applying a random function within a predetermined domain of definition.
  • the method can also further comprise training the artificial neural network by weight settings of a plurality of data sets of driving situation parameters using a gradient descent backpropagation, in particular using the Adam optimization method.
  • a comparison is made between the actual output and the desired target output in order to determine an error.
  • error detection is made between the actual output and the desired target output in order to determine an error.
  • the target output is specified by the data set and is called the target value.
  • the error can be determined by the absolute value of the discrepancy between the actual value and the target value. This is called an absolute error. If several data sets are considered, the mean absolute error can be used. For this, the individual absolute errors are summed up and divided by the number of data records being considered.
  • the accuracy is usually the percentage value of how often the output matches the target value.
  • the error can be traced through the entire network to the input layer. Since the goal is to minimize the error, the gradient descent method can be used to update the weights towards a local minimum. This is called a backward pass.
  • the procedure of forward pass, error detection and backward pass is called backpropagation.
  • a single backpropagation sequence is called a training step.
  • the Adam optimization method uses different learning rates for different parameters. These can also increase. In addition, these learning rates are influenced by a momentum. This means that successive weight updates in the same gradient direction result in a higher learning rate. In comparison, the learning rate is decreased if the gradient direction changes with successive updates.
  • the invention further relates to a test unit for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • the test unit comprises an input for receiving a first data set comprising a plurality of driving situation parameters including environment parameters describing the surroundings of the motor vehicle and EGO parameters describing the state of the motor vehicle, wherein each driving situation parameter has a predetermined domain of definition.
  • test unit can approximate a numerical value range of a target function for the domain of definition of at least one driving situation parameter using a trained, artificial neural network which is applied to the plurality of driving situation parameters, wherein the target function represents a driving maneuver of the motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition.
  • the test unit further comprises an output for providing a second data set including the numerical value range of the target function and the associated domain of definition of the at least one driving situation parameter.
  • an artificial neural network is advantageously used which has the object of approximating test results as a function of the predetermined domain of definition of the driving situation parameters of interest.
  • test results approximated in this way can then be advantageously validated in the context of virtual tests of the device, so that an efficient virtual validation of the device for the autonomous guidance of motor vehicles is possible by means of the test unit according to the invention.
  • a driving situation which underlies the approximation of the test results of the virtual test of the device, formed in particular as a control unit, is a lane change of another motor vehicle into the traffic lane of the motor vehicle employing the plurality of driving situation parameters.
  • the test unit is thus advantageously able to approximate corresponding test results of the virtual test with regard to, for example, a cut-in scenario.
  • the invention further relates to a computer program with program code for carrying out the approximation method according to the invention when the computer program is executed on a computer. Moreover, the invention relates to a computer-readable data carrier with program code of a computer program in order to execute the approximation method according to the invention when the computer program is executed on a computer.
  • test unit is designed to test a plurality of different devices or control units of, for example, automobiles, utility vehicles and/or commercial vehicles, ships or aircraft in terms of an approximation of test results.
  • FIG. 1 is a flow chart of a method for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle according to an example embodiment of the invention
  • FIG. 2 is a three-dimensional illustration of a target function according to the invention according to an example embodiment of the invention
  • FIG. 3 is a three-dimensional illustration of a further target function according to the invention according to an example embodiment of the invention.
  • FIG. 4 is a three-dimensional illustration of a further target function according to the invention according to an example embodiment of the invention.
  • FIG. 5 is a flow chart of the method for approximating the subset of test results of the virtual test of the device for the at least partially autonomous guidance of the motor vehicle according to an example embodiment of the invention
  • FIG. 6 is a flow chart of the method for approximating the subset of test results of the virtual test of the device for the at least partially autonomous guidance of the motor vehicle according to an example embodiment of the invention
  • FIG. 7 is a flow chart of a method for providing a trained, artificial neural network for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle;
  • FIG. 8 is a test unit for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • FIG. 1 shows a flow chart of a method for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle according to a preferred embodiment of the invention.
  • the method comprises receiving S 1 a first data set DS 1 a, DS 1 b, DS 1 c comprising a plurality of driving situation parameters including environment parameters FP 1 , FP 2 describing the environment of the motor vehicle and EGO parameters FP 3 describing the state of the motor vehicle.
  • Each driving situation parameter has a predetermined domain of definition.
  • the method further comprises approximating S 2 a numerical value range WB 1 , WB 2 , WB 3 of a target function F 1 , F 2 , F 3 for the domain of definition of at least one driving situation parameter using a trained, artificial neural network K 1 .
  • the artificial neural network K 1 is applied to the plurality of driving situation parameters.
  • the target function F 1 , F 2 , F 3 represents a driving maneuver of the motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition.
  • the method comprises providing a second data set DS 2 a, DS 2 b, DS 2 c including the numerical value range WB 1 , WB 2 , WB 3 of the target function F 1 , F 2 , F 3 and the associated domain of definition of the at least one driving situation parameter.
  • the one or more EGO parameters FP 3 include a speed V EGO of the motor vehicle, and the environment parameters FP 1 , FP 2 include a speed V FELLOW of another motor vehicle and a distance d SPUR between the motor vehicle and the further motor vehicle.
  • the plurality of driving situation parameters in particular the speed V EGO of the motor vehicle and the speed V FELLOW of the further motor vehicle are generated within the predetermined domain of definition by a random algorithm.
  • the artificial neural network K 1 uses between 2 to 15 layers, between 6 and 2048 neurons per layer, and ReLU as the activation function.
  • ReLU ReLU
  • LeakyReLU or ELU can be used as the activation function.
  • the second data set DS 2 a including the numerical value range of the target function F 1 and the associated domain of definition of the at least one driving situation parameter.
  • the above-mentioned range of values can be graphically represented, for example, two-dimensionally or three-dimensionally.
  • FIG. 2 shows a three-dimensional illustration of a target function according to the invention according to the preferred embodiment of the invention.
  • the illustrated target function F 1 is a safety target function.
  • the safety target function has a numerical value or function value approximated by the artificial neural network K 1 (shown in FIG. 1 ).
  • the function value has a minimum value at a safety distance between the motor vehicle and the further motor vehicle of ⁇ V FELLOW ⁇ 0.55. Furthermore, the function value has a maximum value in the event of a collision between the motor vehicle and the further motor vehicle. In addition, at a safety distance between the motor vehicle and the further motor vehicle of ⁇ V FELLOW ⁇ 0.55, the function value has a value which is greater than the minimum value.
  • the value range WB 1 of the second data set DS 2 a illustrated in FIG. 2 is shown three-dimensionally in the present representation.
  • individual approximation results of respective parameter combinations of the driving situation parameters used can thus be very well recognized with the aid of the respective dots.
  • a boundary between collision and non-collision cases can be read on the basis of the illustrated function profile.
  • FIG. 3 shows a three-dimensional image of a further target function according to the invention according to the preferred embodiment of the invention.
  • the target function F 2 shown in FIG. 3 is a comfort target function which has a numerical value which has a minimum value if there is no change in the acceleration of the motor vehicle, a maximum value in a collision between the motor vehicle and the further motor vehicle, and a value between the minimum value and the maximum value if the acceleration of the motor vehicle is modified as a function of an amount of change in the acceleration.
  • the numerical value range of the comfort target function from 0 to 140 shown in FIG. 3 is arbitrarily selected and in the alternative may have a different value range.
  • FIG. 4 shows a three-dimensional image of a further target function according to the invention according to the preferred embodiment of the invention.
  • the target function F 3 shown in FIG. 4 is an energy consumption target function having a numerical value which has a minimum value if there is no change in the acceleration of the motor vehicle, a maximum value in a collision between the motor vehicle and the another motor vehicle, and a value between the minimum value and the maximum value in case the acceleration of the motor vehicle is modified as a function of an amount of change in the acceleration.
  • the numerical value range of the comfort target function of 0.1 to 0.2 shown in FIG. 4 is arbitrarily selected and in the alternative may have a different value range.
  • FIG. 5 shows a flow chart of the method for approximating the subset of test results of the virtual test of the device for the at least partially autonomous guidance of the motor vehicle according to a further preferred embodiment of the invention
  • the artificial neural network K 1 shown in FIG. 5 has an input layer L 1 , a plurality of hidden layers L 2 , and an output layer L 3 .
  • the output of the artificial neural network K 1 is a first function value F 1 , a second function value F 2 and a third function value F 3 .
  • the first function value F 1 relates to a safety target function
  • the second function value F 2 relates to a comfort target function
  • the third function value F 3 relates to an energy consumption target function.
  • the artificial neural network K 1 is thus able to approximate the function value F 1 based on a first data set DS 1 a of the safety target function.
  • the second data set DS 2 a can then be generated, i.e., a graphical representation of the numerical value range WB 1 of the safety target function can be realized.
  • the artificial neural network K 1 receives a first data set DS 1 a relating to the safety target function, a second data set DS 2 a relating to the comfort target function and a third data set relating to the energy consumption target function.
  • the data sets DS 1 a, DS 1 b, DS 1 c each have a plurality of driving situation parameters including environment parameters describing the surroundings of the motor vehicle FP 1 , FP 2 and EGO parameters FP 3 describing the state of the motor vehicle.
  • a second data set DS 2 a, DS 2 b, DS 2 c including the numerical value range WB 1 , WB 2 , WB 3 of the target function F 1 , F 2 , F 3 and the assigned domain of definition of the at least one driving situation parameter can subsequently be generated.
  • FIG. 6 shows a flow chart of the method for approximating the subset of test results of the virtual test of the device for the at least partially autonomous guidance of the motor vehicle according to a further preferred embodiment of the invention.
  • a separate artificial neural network K 1 , K 2 , K 3 is used for approximating the numerical value range WB 1 , WB 2 , WB 3 of each target function F 1 , F 2 , F 3 .
  • Individual hyperparameters of each artificial neural network K 1 , K 2 , K 3 are stored in a database.
  • the first neural network K 1 has an input layer L 1 a, a plurality of hidden layers L 2 a and an output layer L 3 a, which outputs the function value of the safety target function F 1 .
  • the first artificial neural network K 1 also receives the first data set DS 1 a. On the basis of the approximated function value of the first artificial neural network K 1 , the second data set DS 2 a can then be created, which includes the numerical value range of the target function F 1 and the associated domain of definition of the at least one driving situation parameter.
  • the second neural network K 2 has an input layer L 1 b, a plurality of hidden layers L 2 b, and an output layer L 3 b, which outputs the function value of the safety target function F 2 .
  • the second artificial neural network K 2 also receives the second data set DS 1 b. On the basis of the approximated function value of the second artificial neural network K 2 , the second data set DS 2 b can then be created, which includes the numerical value range of the target function F 2 and the associated domain of definition of the at least one driving situation parameter.
  • the third neural network K 3 has an input layer L 1 c, a plurality of hidden layers L 2 c and an output layer L 3 c, which outputs the function value of the safety target function F 3 .
  • the third artificial neural network K 3 also receives the third data set DS 1 c. On the basis of the approximated function value of the third artificial neural network K 3 , the second data set DS 2 c can then be created, which includes the numerical value range of the target function F 3 and the associated domain of definition of the at least one driving situation parameter.
  • FIG. 7 shows a flow chart of a method for providing a trained, artificial neural network for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • the method comprises receiving S 1 ′ a first data set DS 1 a ′, DS 1 b ′, DS 1 c ′ of input training data comprising a plurality of driving situation parameters including environment parameters FP 1 , FP 2 describing the surroundings of the motor vehicle and EGO parameters FP 3 describing the state of the motor vehicle.
  • Each driving situation parameter has a predetermined domain of definition.
  • the method comprises receiving S 2 ′ of a second data set DS 2 a ′, DS 2 b ′, DS 2 c ′ of output training data including the numerical value range WB 1 , WB 2 , WB 3 of the target function F 1 , F 2 , F 3 and the associated domain of definition of the at least one driving situation parameter.
  • the output training data is related to the input training data.
  • the method has the step of training S 3 ′ of the artificial neural network for approximating a numerical value range WB 1 , WB 2 , WB 3 of the target function F 1 , F 2 , F 3 for the domain of definition of at least one driving situation parameter.
  • the target function F 1 , F 2 , F 3 represents a driving maneuver of the motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition based on the input training data and the output training data.
  • the approximation is done with a training calculation unit 20 .
  • the method comprises providing S 4 ′ the trained, artificial neural network K 1 , K 2 , K 3 for approximating test results of the virtual test of the device for the at least partially autonomous guidance of the motor vehicle.
  • the plurality of driving situation parameters in particular the speed V EGO of the motor vehicle and the speed V FELLOW of the further motor vehicle are generated within the predetermined domain of definition by a random algorithm. Alternatively, these can be generated, for example, by a simulation.
  • the artificial neural network K 1 , K 2 , K 3 is trained by weight settings of a plurality of data sets of driving situation parameters using a gradient descent backpropagation S 3 a ′, in particular using the Adam optimization method.
  • FIG. 8 shows a test unit for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • the test unit comprises an input 10 for receiving a first data set DS 1 a, DS 1 b, DS 1 c comprising a plurality of driving situation parameters including environment parameters describing the surroundings of the motor vehicle and EGO parameters describing the state of the motor vehicle.
  • Each driving situation parameter in this case has a predefined domain of definition.
  • test unit 1 has a processor 12 for approximating a numerical value range WB 1 , WB 2 , WB 3 of a target function F 1 , F 2 , F 3 for the domain of definition of at least one driving situation parameter using a trained, artificial neural network K 1 , K 2 , K 3 .
  • the artificial neural network is applied to the plurality of driving situation parameters.
  • the target function F 1 , F 2 , F 3 represents a driving maneuver of the motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition.
  • the test unit 1 has an output 14 for providing a second data set DS 2 a, DS 2 b, DS 2 c including the numerical value range WB 1 , WB 2 , WB 3 of the target function F 1 , F 2 , F 3 and the associated domain of definition of the at least one driving situation parameter.
  • a driving situation underlying the approximation of the test results of the virtual test of the device is a lane change of another motor vehicle into the lane of the motor vehicle employing the plurality of driving situation parameters.
  • an underlying driving situation may be another driving situation such as approaching a traffic light with and/or without a lane change or with one or more vehicles involved.

Abstract

A computer-implemented method for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle. The invention further relates to a computer-implemented method for providing a trained, artificial neural network, a test unit, a computer program and a computer-readable data carrier.

Description

  • This nonprovisional application is a continuation of International Application No. PCT/EP2020/073057, filed on Aug. 18, 2020, which claims priority under 35 U.S.C. § 119(a) to European Patent Application No. 19192743.3, which was filed in Europe on Aug. 21, 2019, and which are both herein incorporated by reference.
    • BACKGROUND OF THE INVENTION Field of the Invention
  • The present invention relates to a computer-implemented method for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • The present invention further relates to a computer-implemented method for providing a trained, artificial neural network for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • The invention also further relates to a test unit for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle. The present invention further relates to a computer program and a computer-readable data carrier.
    • Description of the Background Art
  • Driver assistance systems such as adaptive cruise control and/or highly automated driving functions can be verified and validated using a variety of verification methods. In particular, hardware-in-the-loop methods, software-in-the-loop methods, simulations and/or test drives can be used.
  • The overhead, in particular the time and/or cost, for testing such vehicle functions using the above-mentioned verification methods is typically very high, since a large number of potentially possible driving situations must be tested.
  • This can lead in particular to a high expenditure for test drives as well as for simulations. DE 10 2017 200 180 A1 specifies a method for verifying and/or validating a vehicle function, which is intended to autonomously guide a vehicle in the longitudinal and/or transverse direction.
  • Based on environmental data relating to an environment of the vehicle, the method includes determining a test control instruction of the vehicle function to an actuator of the vehicle, wherein the test control instruction is not implemented by the actuator.
  • Based on environmental data and using a road user model with respect to at least one road user in the vicinity of the vehicle, the method further includes simulating a fictitious traffic situation that would be present if the test control instruction had been implemented.
  • The method further comprises the provision of test data relating to the fictitious traffic situation. The vehicle function is operated passively in the vehicle to determine the test control instruction.
  • A disadvantage of this method is that the actual operation of the vehicle is required for the verification and/or validation of the vehicle function in order to be able to determine the required data.
  • Accordingly, there is a need to improve existing methods and test equipment such that so-called test cases can be efficiently determined in scenario-based testing of systems and system components in highly automated driving.
    • SUMMARY OF THE INVENTION
  • It is therefore an object of the invention to provide a method, a test unit, a computer program and a computer-readable data carrier, which can determine test cases in the context of a scenario-based testing for systems and system components in highly automated driving in an efficient manner.
  • The object is achieved by a computer-implemented method for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle, a computer-implemented method for providing a trained, artificial neural network for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle, a test unit for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle, a computer program and a computer-readable data carrier.
  • The invention relates to a computer-implemented method for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • The method comprises receiving a first data set comprising a plurality of driving situation parameters formed of environment parameters describing the environment of the motor vehicle and EGO parameters describing the state of the motor vehicle, wherein each driving situation parameter has a predetermined domain of definition.
  • The method further comprises approximating a numerical value range of a target function for the domain of definition of at least one driving situation parameter using a trained, artificial neural network which is applied to the plurality of driving situation parameters, wherein the target function represents a driving maneuver of a motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition. The method further comprises providing a second data set including the numerical value range of the target function and the associated domain of definition of the at least one driving situation parameter.
  • The present invention is thus advantageously able to replace the simulation of driving situations and/or driving situation parameters by means of an artificial neural network.
  • In the context of the present method, therefore, an artificial neural network is advantageously used, which has the object of approximating test results. These test results are test results of interest, which are the subject of virtual tests of a device, such as a control device, for the autonomous guidance of a motor vehicle.
  • In scenario-based testing of systems and system components for the autonomous guidance of a motor vehicle, scenarios are defined which can be described as the abstraction of a traffic situation. A logical scenario here is the abstraction of a traffic situation with the road, the driving behavior and the surrounding traffic without concrete parameter values.
  • By choosing concrete parameter values, the logical scenario becomes a concrete scenario. Such a concrete scenario corresponds to a particular traffic situation.
  • An autonomous driving function is realized by a system, for example a control unit. The control unit is conventionally tested in the real vehicle in real traffic situations or, alternatively, validated by virtual tests.
  • In this context, the present method approximates test results or traffic situations of interest within a predetermined domain of definition of the driving situation parameters used. The domain of definition of the driving situation parameters is chosen such that it covers, for example, safety-related driving situations such as, for example, collisions or near-collisions of involved vehicles.
  • The test results approximated in this way can then be advantageously validated in the context of virtual tests of the control unit, so that an efficient virtual validation of control units for the autonomous guidance of motor vehicles is possible using the method according to the invention.
  • According to one aspect of the invention, the method according to the invention further comprises that the EGO parameters include a speed of the motor vehicle and the environment parameters include a speed of a further motor vehicle and a distance between the motor vehicle and the further motor vehicle.
  • Using these parameters, a so-called cut-in scenario can thus be advantageously approximated. The cut-in scenario can be described as a traffic situation in which a highly automated or autonomous vehicle drives in a predetermined lane and another vehicle merges into the lane of the EGO vehicle from another lane, at a certain distance and at a reduced speed as compared to the speed of the EGO vehicle.
  • The speed of the EGO vehicle and the further vehicle, which is also referred to as a FELLOW vehicle, is constant. Since the speed of the EGO vehicle is higher than that of the FELLOW, the EGO vehicle must be braked to avoid a collision of the two vehicles.
  • On the basis of the above-mentioned EGO parameters and environment parameters, it is thus possible to approximate traffic situations by the method according to the invention that are relevant in the given domain of definition of the above-mentioned parameters.
  • The method according to the invention further comprises that the target function is a safety target function having a numerical value, which has a minimum value at a safety distance between the motor vehicle and the further motor vehicle of ≥VFELLOW×0.55, has a maximum value in a collision between the motor vehicle and the further motor vehicle, and at a safety distance between the motor vehicle and the further motor vehicle of ≤VFELLOW×0.55, has a value which is greater than the minimum value.
  • The safety target 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 functional value of the safety target function is 0.
  • The safety distance can be defined as a distance at which, as a function of a speed difference between the EGO vehicle and the FELLOW vehicle and the distance between the EGO vehicle and the FELLOW vehicle, safe braking of the EGO vehicle is always possible without the occurrence of a collision with the FELLOW vehicle.
  • Such a distance is defined in the present example by a value in meters which corresponds to the velocity VFELLOW×0.55.
  • The smaller the distance between the EGO vehicle and the FELLOW vehicle or starting from the point when the safety distance is undershot, the target function value more and more approaches the value of 1. Accordingly, 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 0 and the target function value is 1.
  • The method according to the invention also can comprise that the target function is a comfort target function or an energy consumption target function having a numerical value which has a minimum value if there is no change in the acceleration of the motor vehicle, has a maximum value in the event of a collision between the motor vehicle and the further motor vehicle, and in a change in the acceleration of the motor vehicle as a function of the amount of change in the acceleration, has a value between the minimum value and the maximum value.
  • With the aid of the comfort target function, statements can be made as to how pleasant a driving maneuver is for the driver of the EGO vehicle. Great acceleration or deceleration and frequent repetition of these operations is considered to be not comfortable.
  • The changes in acceleration are called jerks. The driving situation is the more comfortable, the smaller the calculated value of the comfort target function. In the event of a collision between the EGO vehicle and the FELLOW vehicle, energy consumption is a fixed maximum value. The reason for this is that in a motor vehicle with an internal combustion engine and/or a traction battery in an electrically operated vehicle or hybrid vehicle, the tank of gas can generally no longer be used in the event of an accident.
  • In respect of the cut-in scenario, thus, possible safety-relevant test cases may lie between collision and non-collision cases, which can be defined on the basis of the respective target functions, i.e., the safety target function, the comfort target function and the energy consumption target function.
  • The method according to the invention furthermore can comprise that the plurality of driving situation parameters, in particular the speed of the motor vehicle and the speed of the further motor vehicle, are generated within the predetermined domain of definition by a random algorithm.
  • Thus, the plurality of driving situation parameters constituting the data set that is used to approximate the test results can be easily and time efficiently generated.
  • The method according to the invention can further comprise that a separate artificial neural network is used for approximating the numerical value range of each target function, wherein individual hyperparameters of each artificial neural network are stored in a database.
  • By using a separate artificial neural network for the approximation of each target function, the artificial neural network used in each case can be trained specifically for the best possible approximation of the relevant target function and is thus advantageously able to produce a more accurate approximation result as compared to an artificial neural network which approximates a plurality of target functions by means of a common algorithm.
  • The method according to the invention can further comprise that as a function of the target function, the artificial neural network uses between 2 to 15 layers, between 6 and 2048 neurons per layer, and ReLU, LeakyReLU or ELU as the activation function. This way, the best possible approximation results can be achieved in the present configuration.
  • The second data set comprising the numerical value range of the target function and the assigned domain of definition of the at least one driving situation parameter can be graphically represented two-dimensionally or three-dimensionally as a function of a number of driving situation parameters.
  • Thus, advantageously, a functional course of the approximated numerical value range of the target function for the given domain of definition of the driving situation parameters used can be represented graphically. This allows for the graphical representation of non-collision cases, collision cases and a boundary between non-collision cases and collision cases.
  • The invention further relates to a computer-implemented method for providing a trained, artificial neural network for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • The method comprises receiving a first set of input training data comprising a plurality of driving situation parameters including environment parameters describing the surroundings of the motor vehicle and EGO parameters describing the state of the motor vehicle, wherein each driving situation parameter has a predetermined domain of definition.
  • The method further comprises receiving a second set of output training data formed of the numerical value range of the target function and the associated domain of definition of the at least one driving situation parameter, wherein the output training data is associated with the input training data.
  • Moreover, the method comprises training the artificial neural network to approximate a numerical value range of the target function for the domain of definition of at least one driving situation parameter, wherein the target function represents a driving maneuver of the motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition, based on the input training data and the output training data with a training calculation unit.
  • Furthermore, the method comprises the provision of the trained, artificial neural network for approximating test results of the virtual test of the device for the at least partially autonomous guidance of the motor vehicle.
  • As a function of a number of used training data sets and/or training episodes and the optimization performed, the thus trained, artificial neural network is therefore advantageously able to attain an exact approximation result of the target function to be approximated.
  • The plurality of driving situation parameters, in particular the speed of the motor vehicle and the speed of the further motor vehicle, can be generated within the predetermined domain of definition by a random algorithm and/or by a simulation. The parameter sets of driving situation parameters can thus be generated in a simple manner, for example when using an artificial neural network by applying a random function within a predetermined domain of definition.
  • The method can also further comprise training the artificial neural network by weight settings of a plurality of data sets of driving situation parameters using a gradient descent backpropagation, in particular using the Adam optimization method.
  • When values are input to an artificial neural network, the outputs of the neurons are calculated layer by layer and forwarded until they reach the end of the output layer. This is called a forward pass.
  • A comparison is made between the actual output and the desired target output in order to determine an error. This is called error detection. The target output is specified by the data set and is called the target value. In the simplest case, the error can be determined by the absolute value of the discrepancy between the actual value and the target value. This is called an absolute error. If several data sets are considered, the mean absolute error can be used. For this, the individual absolute errors are summed up and divided by the number of data records being considered.
  • In classifications, the accuracy is usually the percentage value of how often the output matches the target value.
  • The error can be traced through the entire network to the input layer. Since the goal is to minimize the error, the gradient descent method can be used to update the weights towards a local minimum. This is called a backward pass.
  • By adjusting the weights, it is possible for the neural network to solve the specific problem better and better and to improve its accuracy of the predictions. The procedure of forward pass, error detection and backward pass is called backpropagation. A single backpropagation sequence is called a training step.
  • The Adam optimization method uses different learning rates for different parameters. These can also increase. In addition, these learning rates are influenced by a momentum. This means that successive weight updates in the same gradient direction result in a higher learning rate. In comparison, the learning rate is decreased if the gradient direction changes with successive updates.
  • The invention further relates to a test unit for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • The test unit comprises an input for receiving a first data set comprising a plurality of driving situation parameters including environment parameters describing the surroundings of the motor vehicle and EGO parameters describing the state of the motor vehicle, wherein each driving situation parameter has a predetermined domain of definition.
  • Furthermore, the test unit can approximate a numerical value range of a target function for the domain of definition of at least one driving situation parameter using a trained, artificial neural network which is applied to the plurality of driving situation parameters, wherein the target function represents a driving maneuver of the motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition.
  • The test unit further comprises an output for providing a second data set including the numerical value range of the target function and the associated domain of definition of the at least one driving situation parameter.
  • In the context of the present test unit, therefore, an artificial neural network is advantageously used which has the object of approximating test results as a function of the predetermined domain of definition of the driving situation parameters of interest.
  • The test results approximated in this way can then be advantageously validated in the context of virtual tests of the device, so that an efficient virtual validation of the device for the autonomous guidance of motor vehicles is possible by means of the test unit according to the invention.
  • In accordance with a further aspect of the invention, it is provided that a driving situation which underlies the approximation of the test results of the virtual test of the device, formed in particular as a control unit, is a lane change of another motor vehicle into the traffic lane of the motor vehicle employing the plurality of driving situation parameters.
  • The test unit is thus advantageously able to approximate corresponding test results of the virtual test with regard to, for example, a cut-in scenario.
  • The invention further relates to a computer program with program code for carrying out the approximation method according to the invention when the computer program is executed on a computer. Moreover, the invention relates to a computer-readable data carrier with program code of a computer program in order to execute the approximation method according to the invention when the computer program is executed on a computer.
  • The features of the method described herein can be used for approximating test results of a variety of different scenarios or driving situations. Likewise, the test unit according to the invention is designed to test a plurality of different devices or control units of, for example, automobiles, utility vehicles and/or commercial vehicles, ships or aircraft in terms of an approximation of test results.
  • Further scope of applicability of the present invention will become apparent from the detailed description given hereinafter. However, it should be understood that the detailed description and specific examples, while indicating preferred embodiments of the invention, are given by way of illustration only, since various changes and modifications within the spirit and scope of the invention will become apparent to those skilled in the art from this detailed description.
    • BRIEF DESCRIPTION OF THE DRAWINGS
  • The present invention will become more fully understood from the detailed description given hereinbelow and the accompanying drawings which are given by way of illustration only, and thus, are not limitive of the present invention, and wherein:
  • FIG. 1 is a flow chart of a method for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle according to an example embodiment of the invention;
  • FIG. 2 is a three-dimensional illustration of a target function according to the invention according to an example embodiment of the invention;
  • FIG. 3 is a three-dimensional illustration of a further target function according to the invention according to an example embodiment of the invention;
  • FIG. 4 is a three-dimensional illustration of a further target function according to the invention according to an example embodiment of the invention;
  • FIG. 5 is a flow chart of the method for approximating the subset of test results of the virtual test of the device for the at least partially autonomous guidance of the motor vehicle according to an example embodiment of the invention;
  • FIG. 6 is a flow chart of the method for approximating the subset of test results of the virtual test of the device for the at least partially autonomous guidance of the motor vehicle according to an example embodiment of the invention;
  • FIG. 7 is a flow chart of a method for providing a trained, artificial neural network for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle; and
  • FIG. 8 is a test unit for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
    •  DETAILED DESCRIPTION
  • FIG. 1 shows a flow chart of a method for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle according to a preferred embodiment of the invention.
  • The method comprises receiving S1 a first data set DS1 a, DS1 b, DS1 c comprising a plurality of driving situation parameters including environment parameters FP1, FP2 describing the environment of the motor vehicle and EGO parameters FP3 describing the state of the motor vehicle.
  • Each driving situation parameter has a predetermined domain of definition. The method further comprises approximating S2 a numerical value range WB1, WB2, WB3 of a target function F1, F2, F3 for the domain of definition of at least one driving situation parameter using a trained, artificial neural network K1.
  • The artificial neural network K1 is applied to the plurality of driving situation parameters. The target function F1, F2, F3 represents a driving maneuver of the motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition.
  • In addition, the method comprises providing a second data set DS2 a, DS2 b, DS2 c including the numerical value range WB1, WB2, WB3 of the target function F1, F2, F3 and the associated domain of definition of the at least one driving situation parameter.
  • The one or more EGO parameters FP3 include a speed VEGO of the motor vehicle, and the environment parameters FP1, FP2 include a speed VFELLOW of another motor vehicle and a distance dSPUR between the motor vehicle and the further motor vehicle.
  • The plurality of driving situation parameters, in particular the speed VEGO of the motor vehicle and the speed VFELLOW of the further motor vehicle are generated within the predetermined domain of definition by a random algorithm.
  • As a function of the target function F1, the artificial neural network K1 uses between 2 to 15 layers, between 6 and 2048 neurons per layer, and ReLU as the activation function. Alternatively, for example, LeakyReLU or ELU can be used as the activation function.
  • The second data set DS2 a including the numerical value range of the target function F1 and the associated domain of definition of the at least one driving situation parameter. As a function of the number of driving situation parameters, the above-mentioned range of values can be graphically represented, for example, two-dimensionally or three-dimensionally.
  • FIG. 2 shows a three-dimensional illustration of a target function according to the invention according to the preferred embodiment of the invention.
  • The illustrated target function F1 is a safety target function. The safety target function has a numerical value or function value approximated by the artificial neural network K1 (shown in FIG. 1).
  • The function value has a minimum value at a safety distance between the motor vehicle and the further motor vehicle of ≥VFELLOW×0.55. Furthermore, the function value has a maximum value in the event of a collision between the motor vehicle and the further motor vehicle. In addition, at a safety distance between the motor vehicle and the further motor vehicle of ≤VFELLOW×0.55, the function value has a value which is greater than the minimum value.
  • The value range WB1 of the second data set DS2 a illustrated in FIG. 2 is shown three-dimensionally in the present representation. In the value range, individual approximation results of respective parameter combinations of the driving situation parameters used can thus be very well recognized with the aid of the respective dots. Likewise, for example, a boundary between collision and non-collision cases can be read on the basis of the illustrated function profile.
  • FIG. 3 shows a three-dimensional image of a further target function according to the invention according to the preferred embodiment of the invention.
  • The target function F2 shown in FIG. 3 is a comfort target function which has a numerical value which has a minimum value if there is no change in the acceleration of the motor vehicle, a maximum value in a collision between the motor vehicle and the further motor vehicle, and a value between the minimum value and the maximum value if the acceleration of the motor vehicle is modified as a function of an amount of change in the acceleration.
  • The numerical value range of the comfort target function from 0 to 140 shown in FIG. 3 is arbitrarily selected and in the alternative may have a different value range.
  • On the basis of the illustrated range of values, it can thus be determined whether the values shown lie in a range in which a collision of the vehicle with the other vehicle occurs, in that no collision occurs between the vehicle and the further vehicle or the numerical function value lies in an intermediate range.
  • FIG. 4 shows a three-dimensional image of a further target function according to the invention according to the preferred embodiment of the invention.
  • The target function F3 shown in FIG. 4 is an energy consumption target function having a numerical value which has a minimum value if there is no change in the acceleration of the motor vehicle, a maximum value in a collision between the motor vehicle and the another motor vehicle, and a value between the minimum value and the maximum value in case the acceleration of the motor vehicle is modified as a function of an amount of change in the acceleration.
  • The numerical value range of the comfort target function of 0.1 to 0.2 shown in FIG. 4 is arbitrarily selected and in the alternative may have a different value range.
  • On the basis of the illustrated range of values, it can thus be determined whether the values shown lie in a range in which a collision of the vehicle with the other vehicle occurs, in that no collision occurs between the vehicle and the further vehicle or the numerical function value lies in an intermediate range.
  • FIG. 5 shows a flow chart of the method for approximating the subset of test results of the virtual test of the device for the at least partially autonomous guidance of the motor vehicle according to a further preferred embodiment of the invention;
  • The artificial neural network K1 shown in FIG. 5 has an input layer L1, a plurality of hidden layers L2, and an output layer L3. The output of the artificial neural network K1 is a first function value F1, a second function value F2 and a third function value F3.
  • The first function value F1 relates to a safety target function, the second function value F2 relates to a comfort target function and the third function value F3 relates to an energy consumption target function.
  • The artificial neural network K1 is thus able to approximate the function value F1 based on a first data set DS1 a of the safety target function. On the basis of the function value of the target function F1, the second data set DS2 a can then be generated, i.e., a graphical representation of the numerical value range WB1 of the safety target function can be realized.
  • The artificial neural network K1 receives a first data set DS1 a relating to the safety target function, a second data set DS2 a relating to the comfort target function and a third data set relating to the energy consumption target function.
  • The data sets DS1 a, DS1 b, DS1 c each have a plurality of driving situation parameters including environment parameters describing the surroundings of the motor vehicle FP1, FP2 and EGO parameters FP3 describing the state of the motor vehicle.
  • On the basis of the functional values K1 approximated by the artificial neural network, a second data set DS2 a, DS2 b, DS2 c including the numerical value range WB1, WB2, WB3 of the target function F1, F2, F3 and the assigned domain of definition of the at least one driving situation parameter can subsequently be generated.
  • FIG. 6 shows a flow chart of the method for approximating the subset of test results of the virtual test of the device for the at least partially autonomous guidance of the motor vehicle according to a further preferred embodiment of the invention.
  • In contrast to the embodiment shown in FIG. 5, in the present embodiment a separate artificial neural network K1, K2, K3 is used for approximating the numerical value range WB1, WB2, WB3 of each target function F1, F2, F3. Individual hyperparameters of each artificial neural network K1, K2, K3 are stored in a database.
  • The first neural network K1 has an input layer L1 a, a plurality of hidden layers L2 a and an output layer L3 a, which outputs the function value of the safety target function F1.
  • The first artificial neural network K1 also receives the first data set DS1 a. On the basis of the approximated function value of the first artificial neural network K1, the second data set DS2 a can then be created, which includes the numerical value range of the target function F1 and the associated domain of definition of the at least one driving situation parameter.
  • The second neural network K2 has an input layer L1 b, a plurality of hidden layers L2 b, and an output layer L3 b, which outputs the function value of the safety target function F2.
  • The second artificial neural network K2 also receives the second data set DS1 b. On the basis of the approximated function value of the second artificial neural network K2, the second data set DS2 b can then be created, which includes the numerical value range of the target function F2 and the associated domain of definition of the at least one driving situation parameter.
  • The third neural network K3 has an input layer L1 c, a plurality of hidden layers L2 c and an output layer L3 c, which outputs the function value of the safety target function F3.
  • The third artificial neural network K3 also receives the third data set DS1 c. On the basis of the approximated function value of the third artificial neural network K3, the second data set DS2 c can then be created, which includes the numerical value range of the target function F3 and the associated domain of definition of the at least one driving situation parameter.
  • FIG. 7 shows a flow chart of a method for providing a trained, artificial neural network for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • The method comprises receiving S1′ a first data set DS1 a′, DS1 b′, DS1 c′ of input training data comprising a plurality of driving situation parameters including environment parameters FP1, FP2 describing the surroundings of the motor vehicle and EGO parameters FP3 describing the state of the motor vehicle. Each driving situation parameter has a predetermined domain of definition.
  • In addition, the method comprises receiving S2′ of a second data set DS2 a′, DS2 b′, DS2 c′ of output training data including the numerical value range WB1, WB2, WB3 of the target function F1, F2, F3 and the associated domain of definition of the at least one driving situation parameter. The output training data is related to the input training data.
  • Furthermore, the method has the step of training S3′ of the artificial neural network for approximating a numerical value range WB1, WB2, WB3 of the target function F1, F2, F3 for the domain of definition of at least one driving situation parameter.
  • The target function F1, F2, F3 represents a driving maneuver of the motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition based on the input training data and the output training data. The approximation is done with a training calculation unit 20.
  • In addition, the method comprises providing S4′ the trained, artificial neural network K1, K2, K3 for approximating test results of the virtual test of the device for the at least partially autonomous guidance of the motor vehicle.
  • The plurality of driving situation parameters, in particular the speed VEGO of the motor vehicle and the speed VFELLOW of the further motor vehicle are generated within the predetermined domain of definition by a random algorithm. Alternatively, these can be generated, for example, by a simulation.
  • The artificial neural network K1, K2, K3 is trained by weight settings of a plurality of data sets of driving situation parameters using a gradient descent backpropagation S3 a′, in particular using the Adam optimization method.
  • FIG. 8 shows a test unit for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle.
  • The test unit comprises an input 10 for receiving a first data set DS1 a, DS1 b, DS1 c comprising a plurality of driving situation parameters including environment parameters describing the surroundings of the motor vehicle and EGO parameters describing the state of the motor vehicle. Each driving situation parameter in this case has a predefined domain of definition.
  • Furthermore, the test unit 1 has a processor 12 for approximating a numerical value range WB1, WB2, WB3 of a target function F1, F2, F3 for the domain of definition of at least one driving situation parameter using a trained, artificial neural network K1, K2, K3. The artificial neural network is applied to the plurality of driving situation parameters.
  • In this case, the target function F1, F2, F3 represents a driving maneuver of the motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition. Furthermore, the test unit 1 has an output 14 for providing a second data set DS2 a, DS2 b, DS2 c including the numerical value range WB1, WB2, WB3 of the target function F1, F2, F3 and the associated domain of definition of the at least one driving situation parameter.
  • In the present embodiment, a driving situation underlying the approximation of the test results of the virtual test of the device, formed in particular as a control unit, is a lane change of another motor vehicle into the lane of the motor vehicle employing the plurality of driving situation parameters.
  • Alternatively, an underlying driving situation may be another driving situation such as approaching a traffic light with and/or without a lane change or with one or more vehicles involved.
  • Although specific embodiments have been illustrated and described herein, it will be understood by those skilled in the art that a variety of alternative and/or equivalent implementations exist. It should be noted that the exemplary embodiment or embodiments are only examples and are not intended to limit the scope, applicability, or configuration in any way.
  • Rather, the above-mentioned summary and detailed description will provide those skilled in the art with a convenient guide to implementing at least one exemplary embodiment, it being understood that various changes in the functionality and arrangement of the elements may be made without departing from the scope of the appended claims and their legal equivalents.
  • In general, this application intends to cover changes or adaptations, or variations of the embodiments presented herein.
  • The invention being thus described, it will be obvious that the same may be varied in many ways. Such variations are not to be regarded as a departure from the spirit and scope of the invention, and all such modifications as would be obvious to one skilled in the art are to be included within the scope of the following claims.

Claims (15)

What is claimed is:
1. A computer-implemented method for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle, the method comprising:
receiving a first data set comprising a plurality of driving situation parameters including environment parameters describing the environment of the motor vehicle and EGO parameters describing the state of the motor vehicle, each driving situation parameter having a predetermined domain of definition;
approximating a numerical value range of a target function for the domain of definition of at least one driving situation parameter using a trained, artificial neural network that is applied to the plurality of driving situation parameters, wherein the target function represents a driving maneuver of the motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition; and
providing a second data set including the numerical value range of the target function and the associated domain of definition of the at least one driving situation parameter.
2. The computer-implemented method according to claim 1, wherein the EGO parameters comprise a speed of the motor vehicle, and the environment parameters comprise a speed of another motor vehicle and a distance between the motor vehicle and the further motor vehicle.
3. The computer-implemented method according to claim 2, wherein the target function is a safety target function having a numerical value, which has a minimum value at a safety distance between the motor vehicle and the further motor vehicle of ≥VFELLOW×0.55, has a maximum value in a collision between the motor vehicle and the further motor vehicle, and at a safety distance between the motor vehicle and the further motor vehicle of ≤VFELLOW×0.55, has a value which is greater than the minimum value.
4. The computer-implemented method according to claim 2, wherein the target function is a comfort target function or an energy consumption target function, having a numerical value which has a minimum value if there is no change in the acceleration of the motor vehicle, has a maximum value in a collision between the motor vehicle and the further motor vehicle, and has a value between the minimum value and the maximum value when the acceleration of the motor vehicle changes as a function of an amount of the change in the acceleration.
5. The computer-implemented method according to claim 2, wherein the plurality of driving situation parameters, or the speed of the motor vehicle and the speed of the further motor vehicle, are generated within the predetermined domain of definition by a random algorithm.
6. The computer-implemented method according to claim 1, wherein, for approximating the numerical value range of each target function, a separate artificial neural network is used, and wherein individual hyperparameters of each artificial neural network are stored in a database.
7. The computer-implemented method according to claim 1, wherein, as a function of the target function, the artificial neural network uses between 2 to 15 layers, between 6 and 2048 neurons per layer and ReLU, LeakyReLU or ELU as the activation function.
8. The computer-implemented method according to claim 1, wherein the second data set including the numerical value range of the target function and the associated domain of definition of the at least one driving situation parameter is adapted to be graphically displayed two-dimensionally or three-dimensionally as a function of a number of driving situation parameters.
9. A computer-implemented method for providing a trained, artificial neural network for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle, the method comprising:
receiving a first data set of input training data comprising a plurality of driving situation parameters including environment parameters describing the surroundings of the motor vehicle and EGO parameters describing the state of the motor vehicle, wherein each driving situation parameter has a predetermined domain of definition;
receiving a second data set of output training data including a numerical value range of the target function and the associated domain of definition of the at least one driving situation parameter, wherein the output training data is related to the input training data;
training the artificial neural network for approximating a numerical value range of the target function for the domain of definition of at least one driving situation parameter, wherein the target function represents a driving maneuver of the motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition, based on the input training data and the output training data with a training calculation unit; and
providing the trained, artificial neural network for approximating test results of the virtual test of the device for the at least partially autonomous guidance of the motor vehicle.
10. The computer-implemented method according to claim 9, wherein the plurality of driving situation parameters, or the speed of the motor vehicle and the speed of the further motor vehicle, are generated within the predetermined domain of definition by a random algorithm and/or by a simulation.
11. The computer-implemented method according to claim 9, wherein the artificial neural network is trained by weight settings of a plurality of data sets of driving situation parameters using a gradient descent backpropagation or using the Adam optimization method.
12. A test unit for approximating test results of a virtual test of a device for the at least partially autonomous guidance of a motor vehicle, the test unit comprising:
an input to receive a first data set comprising a plurality of driving situation parameters including environment parameters describing the environment of the motor vehicle and EGO parameters describing the state of the motor vehicle, each driving situation parameter having a predetermined domain of definition;
a processor for approximating a numerical value range of a target function for the domain of definition of at least one driving situation parameter using a trained, artificial neural network, which is applied to the plurality of driving situation parameters, wherein the target function represents a driving maneuver of the motor vehicle in response to a control of the device generated by the plurality of driving situation parameters of the domain of definition; and
an output to provide a second data set including the numerical value range of the target function and the associated domain of definition of the at least one driving situation parameter.
13. The test unit according to claim 12, wherein a driving situation underlying the approximation of the test results of the virtual test of the device, formed in particular as a control unit, is a lane change of another motor vehicle into a lane of the motor vehicle employing the plurality of driving situation parameters.
14. A computer program with program code for carrying out the method according to claim 1, when the computer program is executed on a computer.
15. A computer-readable data carrier with program code of a computer program for carrying out the method according to claim 1, when the computer program is executed on a computer.
US17/559,716 2019-08-21 2021-12-22 Computer implemented method and test unit for approximating test results and a method for providing a trained, artificial neural network Pending US20220138575A1 (en)

Applications Claiming Priority (7)

Application Number Priority Date Filing Date Title
EP19192743.3A EP3783452A1 (en) 2019-08-21 2019-08-21 Computer-implemented method and test unit for approximizing test results and method for providing a trained, artificial neural network
EP19192741.7 2019-08-21
DE102019122414.4 2019-08-21
EP19192741.7A EP3783446B1 (en) 2019-08-21 2019-08-21 Computer-implemented method and test unit for approximating a subset of test results
EP19192743.3 2019-08-21
DE102019122414 2019-08-21
PCT/EP2020/073057 WO2021032712A1 (en) 2019-08-21 2020-08-18 Computer implemented method and test unit for approximating test results and method for providing a trained artificial neuronal network

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2020/073057 Continuation WO2021032712A1 (en) 2019-08-21 2020-08-18 Computer implemented method and test unit for approximating test results and method for providing a trained artificial neuronal network

Publications (1)

Publication Number Publication Date
US20220138575A1 true US20220138575A1 (en) 2022-05-05

Family

ID=74645737

Family Applications (3)

Application Number Title Priority Date Filing Date
US16/999,533 Pending US20210056432A1 (en) 2019-08-21 2020-08-21 Method for training an artificial neural generator network, method for training an artificial neural discriminator network, and test unit
US17/559,716 Pending US20220138575A1 (en) 2019-08-21 2021-12-22 Computer implemented method and test unit for approximating test results and a method for providing a trained, artificial neural network
US17/559,828 Pending US20220138094A1 (en) 2019-08-21 2021-12-22 Computer-implemented method and test unit for approximating a subset of test results

Family Applications Before (1)

Application Number Title Priority Date Filing Date
US16/999,533 Pending US20210056432A1 (en) 2019-08-21 2020-08-21 Method for training an artificial neural generator network, method for training an artificial neural discriminator network, and test unit

Family Applications After (1)

Application Number Title Priority Date Filing Date
US17/559,828 Pending US20220138094A1 (en) 2019-08-21 2021-12-22 Computer-implemented method and test unit for approximating a subset of test results

Country Status (1)

Country Link
US (3) US20210056432A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11938957B2 (en) 2020-08-24 2024-03-26 Motional Ad Llc Driving scenario sampling for training/tuning machine learning models for vehicles

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9761007B2 (en) * 2015-06-16 2017-09-12 Disney Enterprises, Inc. Method and system for approximating fully calculated image sequence from a subset of calculated image data
DE102017200180A1 (en) * 2017-01-09 2018-07-12 Bayerische Motoren Werke Aktiengesellschaft Method and test unit for the motion prediction of road users in a passively operated vehicle function
US10586310B2 (en) * 2017-04-06 2020-03-10 Pixar Denoising Monte Carlo renderings using generative adversarial neural networks
US20180336439A1 (en) * 2017-05-18 2018-11-22 Intel Corporation Novelty detection using discriminator of generative adversarial network
US11003995B2 (en) * 2017-05-19 2021-05-11 Huawei Technologies Co., Ltd. Semi-supervised regression with generative adversarial networks
US10929722B2 (en) * 2017-05-19 2021-02-23 Nec Corporation Anomaly detection in streaming networks
US11250329B2 (en) * 2017-10-26 2022-02-15 Nvidia Corporation Progressive modification of generative adversarial neural networks
US11132792B2 (en) * 2018-02-22 2021-09-28 Siemens Healthcare Gmbh Cross domain medical image segmentation
US11030744B2 (en) * 2018-06-26 2021-06-08 Astrazeneca Computational Pathology Gmbh Deep learning method for tumor cell scoring on cancer biopsies
US20200134494A1 (en) * 2018-10-26 2020-04-30 Uatc, Llc Systems and Methods for Generating Artificial Scenarios for an Autonomous Vehicle
US11940790B2 (en) * 2018-12-12 2024-03-26 Allstate Insurance Company Safe hand-off between human driver and autonomous driving system

Also Published As

Publication number Publication date
US20210056432A1 (en) 2021-02-25
US20220138094A1 (en) 2022-05-05

Similar Documents

Publication Publication Date Title
JP7064303B2 (en) Autonomous system verification method
Wachenfeld et al. The release of autonomous vehicles
CN109709956B (en) Multi-objective optimized following algorithm for controlling speed of automatic driving vehicle
Ntousakis et al. On microscopic modelling of adaptive cruise control systems
KR20200094641A (en) Method and device for performing multiple agent sensor fusion in cooperative driving based on reinforcement learning
Damerow et al. Risk-aversive behavior planning under multiple situations with uncertainty
CN110686906B (en) Automatic driving test method and device for vehicle
CN111332283A (en) Method and system for controlling a motor vehicle
EP4074566A1 (en) Control method, device and system of intelligent car
CN107364446B (en) Method for operating a motor vehicle
CN111079800B (en) Acceleration method and acceleration system for intelligent driving virtual test
US20220138575A1 (en) Computer implemented method and test unit for approximating test results and a method for providing a trained, artificial neural network
US11354458B1 (en) Automated vehicle safety simulation using safety quotient method
CN108569268B (en) Vehicle anti-collision parameter calibration method and device, vehicle controller and storage medium
CN115735107A (en) Computer-implemented method for providing a test procedure for a traffic scenario to be tested
Zhang et al. A cruise control method for connected vehicle systems considering side vehicles merging behavior
Lee et al. Development of a driving behavior-based collision warning system using a neural network
Hekmatnejad et al. Search-based test-case generation by monitoring responsibility safety rules
CN112784867A (en) Training deep neural networks using synthetic images
CN117242438A (en) Method for testing a driver assistance system of a vehicle
CN114174935A (en) Computer-implemented method and test unit for approximating a subset of test results
Wei et al. A learning-based autonomous driver: emulate human driver's intelligence in low-speed car following
US20220177000A1 (en) Identification of driving maneuvers to inform performance grading and control in autonomous vehicles
CN115176297A (en) Method for training at least one algorithm for a control unit of a motor vehicle, computer program product and motor vehicle
US20230394896A1 (en) Method and a system for testing a driver assistance system for a vehicle

Legal Events

Date Code Title Description
STPP Information on status: patent application and granting procedure in general

Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION

AS Assignment

Owner name: DSPACE GMBH, GERMANY

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:BANNENBERG, SEBASTIAN;LORENZ, FABIAN;RASCHE, RAINER;SIGNING DATES FROM 20211216 TO 20220207;REEL/FRAME:058970/0173

AS Assignment

Owner name: DSPACE GMBH, GERMANY

Free format text: CHANGE OF NAME;ASSIGNOR:DSPACE DIGITAL SIGNAL PROCESSING AND CONTROL ENGINEERING GMBH;REEL/FRAME:062202/0014

Effective date: 20211103