CN109522673A - A kind of test method, device, equipment and storage medium - Google Patents
A kind of test method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN109522673A CN109522673A CN201811459787.2A CN201811459787A CN109522673A CN 109522673 A CN109522673 A CN 109522673A CN 201811459787 A CN201811459787 A CN 201811459787A CN 109522673 A CN109522673 A CN 109522673A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- parameter
- model
- test
- module
- 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.)
- Granted
Links
- 238000010998 test method Methods 0.000 title claims abstract description 23
- 238000012360 testing method Methods 0.000 claims abstract description 121
- 238000000034 method Methods 0.000 claims abstract description 44
- 230000008569 process Effects 0.000 claims abstract description 25
- 238000004088 simulation Methods 0.000 claims description 34
- 230000001133 acceleration Effects 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 7
- 241000208340 Araliaceae Species 0.000 description 6
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 6
- 235000003140 Panax quinquefolius Nutrition 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 235000008434 ginseng Nutrition 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000005291 magnetic effect Effects 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000008447 perception Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003447 ipsilateral effect Effects 0.000 description 1
- 238000005511 kinetic theory Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011056 performance test Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Automation & Control Theory (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a kind of test method, device, equipment and storage mediums.This method comprises: constructing whole vehicle model according to the property parameters of vehicle；According to relationship of the vehicle between the vehicle actual operation parameters acquired in real road operational process, the whole vehicle model is calibrated；It is tested using the whole vehicle model after calibration.The technical solution of the embodiment of the present invention can fully consider the output valve error of module to be tested caused by the parameters such as dynamics and the kinematics of vehicle during the test, and then improve the accuracy of test.
Description
Technical field
The present embodiments relate to automatic Pilot technologies more particularly to a kind of test method, device, equipment and storage to be situated between
Matter.
Background technique
During automatic driving vehicle road test, the scene of barrier and road is all non-quantitation, uncontrollable, because
And in order to guarantee the driving safety of automatic driving vehicle, it is very necessary for carrying out test to each module of automatic driving vehicle.
Currently, automatic driving vehicle acquires perception data, state of motion of vehicle data during road actual travel, with
And vehicle actual path data.Each module of vehicle is emulated according to the perception data of acquisition and state of motion of vehicle data
Test, obtains the offline track data of automatic driving vehicle during emulation testing.And to the actual path of automatic driving vehicle
Data and offline track data carry out recurrence comparison, to complete the test to each module of automatic driving vehicle.
But during automatic driving vehicle actual travel, due to the influence of the parameters such as dynamics of vehicle and kinematics,
There can be error between the control data values and actual travel data value of automatic driving vehicle, to affect to automatic Pilot vehicle
The accuracy of each model measurement.
Summary of the invention
The embodiment of the invention provides a kind of test method, device, equipment and storage mediums, can fill during the test
Point consider the output valve error of module to be tested caused by dynamics of vehicle and kinematics parameters, and then improves the accurate of test
Degree.
In a first aspect, the embodiment of the invention provides a kind of test methods, this method comprises:
Whole vehicle model is constructed according to the property parameters of vehicle；
According to relationship of the vehicle between the vehicle actual operation parameters acquired in real road operational process, to institute
Whole vehicle model is stated to be calibrated；
It is tested using the whole vehicle model after calibration.
Second aspect, the embodiment of the invention also provides a kind of test device, which includes:
Model construction module, for constructing whole vehicle model according to the property parameters of vehicle；
Model calibration module, the vehicle actual motion ginseng for being acquired in real road operational process according to the vehicle
Relationship between number calibrates the whole vehicle model；
Test module, for being tested using the whole vehicle model after calibration.
The third aspect, the embodiment of the invention also provides a kind of equipment, comprising:
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes the test method as described in any embodiment of that present invention.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program realizes the test method as described in any embodiment of that present invention when the program is executed by processor.
The scheme of the embodiment of the present invention, by constructing whole vehicle model, according to the actual operation parameters in vehicle operation
Between relationship the whole vehicle model of building is calibrated after, tested, can tested using the whole vehicle model after calibration
The output valve error of module to be tested caused by the dynamics and kinematics parameters of vehicle is fully considered in the process, and then is improved
The accuracy of test.
Detailed description of the invention
Fig. 1 is a kind of flow chart for test method that the embodiment of the present invention one provides；
Fig. 2 is a kind of flow chart of test method provided by Embodiment 2 of the present invention；
Fig. 3 is a kind of flow chart for test method that the embodiment of the present invention three provides；
Fig. 4 is a kind of structural schematic diagram for test device that the embodiment of the present invention four provides；
Fig. 5 is a kind of structural schematic diagram for equipment that the embodiment of the present invention five provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is the flow chart for the test method that the embodiment of the present invention one provides, and the present embodiment is applicable to automatic Pilot
The case where each module of vehicle is tested for the property, for example, the decision rule control module to automatic driving vehicle carries out performance
The case where test.This method can be executed by test device provided in an embodiment of the present invention or equipment, which can be used firmly
The mode of part and/or software is realized.As shown in Figure 1, specifically comprising the following steps:
S101 constructs whole vehicle model according to the property parameters of vehicle.
Wherein, the property parameters of vehicle, which can be, causes decision rule controlling value and vehicle driving real output value to there is mistake
The preset parameter that the vehicle of difference itself carries.It may include static property parameters and dynamic property parameters.For example, static belong to
Property parameter may include vehicle empty mass, car gage and vehicle wheelbase etc..Vehicle empty mass can be vehicle and not hold
When carrying any object, the quality of vehicle itself；The wheelspan of vehicle can be on vehicle between symmetrically arranged left and right two-wheeled away from
From；The wheelbase of vehicle can be ipsilateral the distance between the front and back two-wheeled of vehicle；Dynamic attribute parameter may include: object in sky
Between position, speed, acceleration etc..Whole vehicle model can refer to for describing vehicle attribute parameter, service ability and mechanics
The model applied to vehicle emulation testing of the performances such as characteristic.Optionally, whole vehicle model can include but is not limited to: vehicle power
Learn model, vehicle kinematics model and centroid simplified model etc..Specifically, Full Vehicle Dynamics model can be as research effect
In stress condition and vehicle movement on vehicle relationship and the model established, may include 1/4 model of 2DOF, 7 freedom degrees
1/2 model and 15 freedom degree whole vehicle models etc..Full Vehicle Dynamics model can be reaction vehicle location, speed, acceleration etc.
The model established with the relationship of time.Centroid simplified model can be the centroid of reaction vehicle and the relationship of stress condition and build
Vertical simplified model.
Optionally, Full Vehicle Dynamics model, the vehicle kinematics mould in whole vehicle model are constructed according to the property parameters of vehicle
The process of type or centroid simplified model is similar.The following embodiment of the present invention is constructed with structure according to the property parameters of vehicle whole
It is described in detail for vehicle dynamics model.
Illustratively, when constructing Full Vehicle Dynamics model according to the property parameters of vehicle, can be analysis leads to vehicle
Controlling value and real output value the reason of there are errors, so that it is determined which freedom degree to set about the property parameters according to vehicle from,
Building meets the Full Vehicle Dynamics model of current automatic driving vehicle；It is also possible to using existing in existing kinetic theory
Full Vehicle Dynamics model (such as 1/4 model of 2DOF, 7 freedom degree, 1/2 model or 15 freedom degree whole vehicle models), in conjunction with current
The property parameters of automatic driving vehicle, construct the Full Vehicle Dynamics model of current automatic driving vehicle, for example, can will acquire
The property parameters of vehicle import in third party's dynamics software, and software can construct the vehicle of the automatic driving vehicle automatically
Kinetic model.
Optionally, when constructing whole vehicle model according to the property parameters of vehicle, it can be and class is constituted to same model or vehicle
As a kind of automatic driving vehicle construct a kind of whole vehicle model.
S102 is right according to relationship of the vehicle between the vehicle actual operation parameters acquired in real road operational process
Whole vehicle model is calibrated.
Wherein, vehicle actual operation parameters can refer to the ginseng that automatic driving vehicle exports in road actual moving process
Number, may include: acceleration, speed, throttle, brake, rotary inertia of steering wheel, the torque, frictional force system of automatic driving vehicle
Number, front wheel angle, rear-wheel corner, full-vehicle steering error etc..
The whole vehicle model of S101 building leads to the ginseng of whole vehicle model due to measurement error or running environment difference in order to prevent
The situations of number inaccuracy occur, and in based on whole vehicle model test automatic driving vehicle before the performance of module to be tested, need elder generation
The whole vehicle model of building is calibrated, the error because of whole vehicle model is avoided to lead to the inaccuracy of module performance test to be tested
Situation.
Optionally, usually there is certain corresponding relationships between collected vehicle actual operation parameters, for example, accelerating
Degree and the relationship between the relationship between speed, throttle, rotary inertia of steering wheel and front wheel angle, rear-wheel corner etc..At this
In inventive embodiments, can by the relationship between the operating parameter that is exported in automatic driving vehicle real road driving process,
The whole vehicle model of building is calibrated, for example, can be according to the relationship between acceleration and speed, throttle, to the whole of building
Model formation parameter relevant with acceleration, speed, throttle is adjusted in vehicle model.Automatic driving vehicle reality can also be passed through
Between the relationship between operating parameter that exports during the road driving of border and the operating parameter planned by the whole vehicle model
Relationship, to be calibrated to the whole vehicle model of building.Specifically, can be according between actual operation parameters relationship and rule
The relationship between operating parameter drawn is compared, and adjusts the parameter value in whole vehicle model, and then complete the vehicle mould to building
The calibration of type；It is also possible to the pass between the operating parameter obtained according to the relationship between actual operation parameters and emulation testing
System constructs cost function, acquires corresponding whole vehicle model parameters of formula when error minimum, and then complete the whole vehicle model to building
Calibration；It can also be based on neural network model, it will be between the operating parameter of relationship and planning between actual operation parameters
Relationship input neural network model, the neural network model can according to training when sample data and corresponding algorithm analyze
The corresponding optimal value of the parameter of the whole vehicle model is exported, to complete the calibration to the whole vehicle model of building.
It should be noted that the embodiment of the present invention can also use other modes according to vehicle in real road operational process
Relationship between the vehicle actual operation parameters of middle acquisition, calibrates whole vehicle model, to this present embodiment without limiting.
S103 is tested using the whole vehicle model after calibration.
Optionally, after to the whole vehicle model calibration of the automatic driving vehicle, vehicle is carried out using the whole vehicle model after calibration
In each module to be tested test when, can be and different test scene is set (such as two lane highways crossroad, three lanes have obstacle
The crossing of object vehicle doubling, narrow hill path turning road etc.), each module to be tested in vehicle is tested, to guarantee
The accuracy of test result.
Optionally, the process tested using the whole vehicle model after calibration model to be tested each in vehicle is similar.It connects
The embodiment of the present invention of getting off is for testing the decision rule Controlling model in vehicle using the whole vehicle model after calibration
It describes in detail.
Illustratively, when decision rule control module is tested in vehicle, control automatic driving vehicle is by obtaining
The current driving data for taking perception data and vehicle are exported by decision rule control module and are controlled based on the whole vehicle model after calibration
The planning operation data of automatic driving vehicle processed, so that the automatic driving vehicle is in current scene downward driving.It can be and obtain at this time
The actual operating data for taking automatic driving vehicle to export, by comparing the rule of decision rule control module control automatic driving vehicle
Operation data and the vehicle are drawn in the error under current scene between actual operating data, to judge that decision rule controls in vehicle
The performance of module.It can also be the actual travel track for obtaining automatic driving vehicle, by comparing decision rule control module control
Departure degree between the ideal trajectory and actual path of automatic driving vehicle operation processed, to judge that decision rule controls in vehicle
The performance of module.
Optionally, due to the property parameters of vehicle under different scenes can it is different, using calibration after vehicle
When learning the test of each module to be tested in model progress vehicle, it can be for whole after the different corresponding calibrations of test scene
Vehicle model carries out the test of each module to be tested in vehicle.To guarantee the accuracy of test result.
A kind of test method is present embodiments provided, by constructing whole vehicle model, according to the reality in vehicle operation
After relationship between operating parameter calibrates the whole vehicle model of building, tested using the whole vehicle model after calibration, energy
It is enough to fully consider the output valve error to be tested touched caused by the dynamics and kinematics parameters of vehicle during the test, in turn
Improve the accuracy of test.
Embodiment two
Fig. 2 is a kind of flow chart of test method provided by Embodiment 2 of the present invention, base of this method in above-described embodiment
Further optimize on plinth, specifically give the vehicle actual operation parameters that are acquired in real road operational process according to vehicle it
Between relationship, the concrete condition introduction that whole vehicle model is calibrated.As shown in Fig. 2, this method comprises:
S201 constructs whole vehicle model according to the property parameters of vehicle.
S202, at least one dimension in the vehicle actual operation parameters that vehicle is acquired in real road operational process
Operating parameter is fitted actual relationship curve as output parameter as input parameter, the operating parameter of other dimensions.
It, can will wherein specifically, vehicle collected actual operation parameters in real road driving process have very much
At least one dimension as input parameter, others be used as output parameter, be fitted vehicle actual operation parameters between reality
Relation curve.It optionally, can will be in speed, acceleration in vehicle operating parameters and control instruction value at least one dimension
Parameter is as input parameter；It will laterally compensate, turn in vehicle operating parameters, the brake of longitudinal compensation, error, throttle, torque, rubbing
Parameter in wiping force coefficient, wheel steering angle, full-vehicle steering and error at least one dimension is as output parameter.
Optionally, the relation curve of fitting can be the corresponding one or more output parameters of an input parameter, it is also possible to
It is the corresponding one or more output parameters of multiple input parameters, the actual relationship curve of fitting can be one (i.e. by one
Actual relationship curve reflects multiple practical corresponding relationships output and input between parameter), it is also possible to a plurality of (i.e. by a plurality of
Actual relationship curve reflects the practical corresponding relationship between different input/output arguments).For example, it may be by a period of time
Actual acceleration value is as output parameter, and using the practical throttle changing value in the period as output parameter, fitting is practical to be added
The relation curve of velocity amplitude and throttle.It is also possible to the Servo Control instruction in practical a period of time be input parameter, by this
Actual wheel corner and full-vehicle steering error in period are fitted practical Servo Control instruction and turn with wheel as output parameter
Relation curve between angle and full-vehicle steering error.
Optionally, it is known that input and output parameter when being fitted actual curve, can be input parameter and output ginseng
Number is input in curve fitting software, is obtained corresponding fit correlation curve, is also possible to input and output parameter band
Enter fitting formula, solve the design parameter of fitting formula, and then draw fit correlation curve etc., in this regard, the embodiment of the present invention is not
It is defined.
S203 treats test module using operating parameter and the vehicle model of at least one dimension and makees emulation testing.
Optionally, emulation testing is made to the module to be tested of vehicle, can be logical to the operating parameter of at least one dimension
Cross whole vehicle model processing after, by module to be tested according to related algorithm determines and the dimension operating parameter have corresponding relationship other
Operating parameter in dimension can be through whole vehicle model to adding for example, if the decision rule module to vehicle is tested
After the operating parameter of speed dimension is handled, the control of corresponding decision rule is based on by the decision rule control module of vehicle and is calculated
Method (such as Model Predictive Control (Model Predictive Control, MPC) algorithm, proportional-integral-differential
(Proportion-Integral-Differential, PID) algorithm etc.) output planning throttle dimension operating parameter.
Optionally, the tool that test module makees emulation testing is treated using the operating parameter of at least one dimension and whole vehicle model
Body process, can be using the operating parameter of at least one dimension as the input of whole vehicle model, using the output of whole vehicle model as
The input of module to be tested treats test module and carries out emulation testing, obtains other dimensions of modular simulation output to be tested
Operating parameter.For example, can be if the decision rule module to vehicle is tested and input the operating parameter of acceleration dimension
Whole vehicle model, by the decision rule control module of the acceleration value input vehicle after treatment of whole vehicle model output, decision
Planning control module is according to vehicle dynamic model output treated acceleration value, according to pre- decision rule control algolithm
Cook up the operating parameter of the throttle dimension of control automatic driving vehicle traveling.
Optionally, whole vehicle model handles the operating parameter of at least one dimension of input, can be at least one
The operating parameter of a dimension is brought into the whole vehicle model formula, thus the operational parameter value for the dimension that obtains that treated.The fortune
Row parameter value considers error caused by dynamics of vehicle and kinematics parameters, by the operating parameter decision rule go out other
The operational parameter value of dimension is more accurate.
S204, using the operating parameter of at least one dimension as input parameter, the simulation results are intended as output parameter
Close simulation relation curve.
Optionally, the mode of Curve fitting simulation relation curve is similar with the fitting mode of actual relationship curve, only corresponding
Output parameter is different, in Curve fitting simulation relation curve using the test result of S203 module to be tested as output parameter, input
Parameter is to make the operating parameter of at least one dimension of emulation testing to the module to be tested of vehicle.
It should be noted that the operating parameter of at least one dimension in S202, S203 and S204 is all consistent, because
Just there is comparativity only to fit the simulation relation curve come with the operating parameter of dimension, and then just can be based in S203
Actual relationship curve and S204 in simulation relation curve vehicle dynamic model is calibrated.
S205 compares actual relationship curve and simulation relation curve, and is calibrated according to comparison result to whole vehicle model.
Optionally, compare actual relationship curve and simulation relation curve, can be the registration for calculating two curves, it can also be with
It is the mean error calculated between two curves, can also be while the registration of calculation amount curve and mean error etc., thus
Judge whether to need to calibrate the vehicle dynamic model, for example, if the registration of two curves is less than default registration threshold
When value and/or mean error are less than default error threshold, just the whole vehicle model is calibrated.
Optionally, it when being calibrated according to comparison result to whole vehicle model, can be based on acquisition vehicle actual motion ginseng
The planning operation parameter of several and module to be tested control automatic driving vehicle, calibrates whole vehicle model, for example, if to vehicle
Decision rule module tested, then can be acquisition have corresponding relationship practical various dimensions operating parameter and planning operation
Parameter is led to using the operating parameter of the throttle dimension in practical various dimensions operating parameter as the output of decision rule control module
Decision rule control algolithm is crossed, reversely calculates the corresponding module input parameter value of the output parameter value, the input extrapolated is joined
Output of the numerical value as whole vehicle model, using the operating parameter of the throttle dimension in corresponding planning various dimensions operating parameter as whole
The input of vehicle model carries it into whole vehicle model formula, to adjust the size of the parameter value in the model formation, and then completes
Calibration to vehicle model.Can also using neural network model or construction cost function by the way of or other modes carry out it is whole
The calibration of vehicle model, to this present embodiment without limiting.
S206 is tested using the whole vehicle model after calibration.
A kind of test method is present embodiments provided, by constructing whole vehicle model, is fitted the pass of vehicle actual operation parameters
It is the relation curve of the operating parameter of curve and emulation testing, the whole vehicle model of building is calibrated, using whole after calibration
Vehicle model is tested, and can be improved the accuracy of whole vehicle model calibration, and then improve the accuracy of test.
Embodiment three
Fig. 3 is a kind of flow chart for test method that the embodiment of the present invention three provides, base of this method in above-described embodiment
Further optimize on plinth, gives the concrete condition using module testing to be tested in the whole vehicle model progress vehicle after calibration
It introduces, shows in particular the specific feelings tested using the decision rule control module that the whole vehicle model after calibration carries out vehicle
Condition introduction.
Decision rule control module is the nucleus module of automatic driving vehicle, for being worked as according to real road situation and vehicle
Preceding operating parameter generates traveling strategy, and according to the strategic planning operating parameter, then controls according to the operating parameter of planning
Automatic driving vehicle is in safe on-road travel.For example, obtaining environment road conditions, hair by camera or radar laser equipment
Existing front needs to turn, and the straight-line travelling that vehicle is current, then the decision instruction of turning can be generated, then according to the decision of turning
The operating parameter (e.g., the rotary inertia of steering wheel, front wheel angle, rear-wheel corner, speed etc.) of instruction planning turning, finally controls
Automatic driving vehicle is executed according to the operating parameter perfection of planning.But due to the influence of dynamics of vehicle and kinematics parameters,
The operating parameter that perfect Execution plan comes out, it may appear that there is the case where error in the actual operating parameter of vehicle and planning, for example,
Front wheel angle in the operating parameter of perfect Execution plan is 30 degree, and reality is due to the influence of frictional resistance, the front-wheel of output
Corner only has 25 degree, just will appear front wheel angle error at this time.It therefore, can be based on whole vehicle model come planning operation parameter, so
It controls automatic driving vehicle again afterwards to travel according to the operating parameter of planning, to reduce decision rule controlling value and real output value
Between error.The test of the Vehicle Decision Method planning control module of the present embodiment is exactly to go out to based on whole vehicle model decision rule
The consistency of driving parameters and the driving parameters of vehicle final output carries out assessment test.
As shown in figure 3, this method comprises:
S301 constructs whole vehicle model according to the property parameters of vehicle.
S302, at least one dimension in the vehicle actual operation parameters that vehicle is acquired in real road operational process
Operating parameter is fitted actual relationship curve as output parameter as input parameter, the operating parameter of other dimensions.
S303 treats test module using the operating parameter and whole vehicle model of at least one dimension and makees emulation testing.
S304, using the operating parameter of at least one dimension as input parameter, the simulation results are intended as output parameter
Close simulation relation curve.
S305 compares actual relationship curve and simulation relation curve, and is calibrated according to comparison result to whole vehicle model.
S306 obtains the operation during vehicle testing using test parameter as the input of the vehicle model after calibration
Parameter.
Wherein, test parameter can be the operating parameter of at least one dimension determined based on current test purpose, for example,
The performance for wanting test decision planning control module control automatic driving vehicle to run at high speed, then test data, which can be, ties up speed
The operating parameter of degree and/or acceleration dimension is as test parameter.Operating parameter during vehicle testing, which can be, passes through school
Whole vehicle model after standard treated the corresponding parameter value of test parameter.For example, it may be after bringing test parameter into calibration
Whole vehicle model formula, using the calculated result of formula as the operating parameter during vehicle testing.
Illustratively, it can be and the whole vehicle model after calibration accessed in vehicle emulation tool, i.e., the vehicle after calibration
The input port of the delivery outlet connection decision rule control module of model, test data is input in the whole vehicle model after calibration,
Whole vehicle model will be handled the test parameter, obtain the operating parameter during vehicle testing.
It is imitative to carry out vehicle using the operating parameter during vehicle testing as the input of module to be tested in vehicle by S307
True test, and obtain the simulation track data during vehicle emulation testing.
Illustratively, using the operating parameter during the vehicle testing that S306 is obtained as the defeated of decision rule control module
Enter parameter, carry out the emulation testing of vehicle, specific test process may is that decision rule control module according to the parameter of input
Decision instruction is issued to automatic driving vehicle, the driving parameters of the vehicle are then planned according to the instruction, controls automatic Pilot vehicle
It executes the driving parameters value driving on the road simultaneously, carries out track emulation according to the driving parameters of planning, emulated
Track data.
S308 determines the survey of module to be tested according to the associated actual path data of test parameter and simulation track data
Test result.
Wherein, the associated actual path of test parameter can be control of the automatic driving vehicle based on decision rule control module
System, the track data of actual travel on road.Simulation track data are the traveling ginsengs according to the planning of decision rule control module
Number, by simulation software simulate come track data.The test result of control module can be used to indicate that decision rule control
Molding block controls the whether consistent test result of emulation driving trace of the actual travel track and planning of automatic driving vehicle.
Specifically, the method for determining the test result of control module has according to actual path data and simulation track data
Very much, the present embodiment is to this without limiting.It can be the registration for calculating actual path data and simulation track data, be overlapped
Degree is bigger, illustrates that the performance of decision rule control module is better；It is also possible to calculate actual path data and simulation track data
Average error value, error amount is smaller, illustrates that the performance of decision rule control module is better etc..
It should be noted that the embodiment of the present invention is carried out by taking the decision rule control module for testing automatic driving vehicle as an example
Introduce, but not limited to this, can also be and other modules of automatic driving vehicle are tested, specific implementation procedure with
It is similar to the implementation procedure of decision planning control module, this is no longer repeated.
A kind of test method is present embodiments provided, by constructing vehicle dynamic model, by being fitted the practical fortune of vehicle
The relation curve of the operating parameter of the relation curve and emulation testing of row parameter, calibrates the whole vehicle model of building, will be whole
The output of vehicle model connects the input of module to be tested, and test parameter is inputted whole vehicle model, defeated according to final module to be tested
Simulation track data and actual path data out, treat test module and carry out test assessment.Improve the accuracy of test.
Example IV
Fig. 4 is a kind of structural schematic diagram for test device that the embodiment of the present invention four provides, the executable present invention of the device
Test method provided by any embodiment has the corresponding functional module of execution method and beneficial effect.As shown in figure 4, should
Device includes:
Model construction module 401, for constructing whole vehicle model according to the property parameters of vehicle；
Model calibration module 402, the practical fortune of vehicle for being acquired in real road operational process according to the vehicle
Relationship between row parameter calibrates the whole vehicle model；
Test module 403, for being tested using the whole vehicle model after calibration.
A kind of test device is present embodiments provided, by constructing whole vehicle model, according to the reality in vehicle operation
After relationship between operating parameter calibrates whole vehicle model, using the whole vehicle model after calibration into test, it can test
The output valve error of module to be tested caused by the dynamics and kinematics parameters of vehicle is fully considered in the process, and then is improved
The accuracy of test.
Further, above-mentioned model calibration module 402 includes:
Curve matching unit, the vehicle actual operation parameters for acquiring the vehicle in real road operational process
In at least one dimension operating parameter as input parameter, the operating parameters of other dimensions is used as output parameter, and fitting is actually
Relation curve；
Emulation testing unit, for the operating parameter and the whole vehicle model using at least one dimension to be tested
Module makees emulation testing；
The curve matching unit is also used to using the operating parameter of at least one dimension as input parameter, emulation
Test result is as output parameter, Curve fitting simulation relation curve；
Model calibration unit is used for the actual relationship curve and the simulation relation curve, and ties according to comparing
Fruit calibrates the whole vehicle model.
Further, above-mentioned emulation testing unit is specifically used for:
Using the operating parameter of at least one dimension as the input of the whole vehicle model, by the defeated of the whole vehicle model
Input as module to be tested out carries out emulation testing to the module to be tested, it is defeated to obtain the modular simulation to be tested
The operating parameter of other dimensions out.
Further, above-mentioned curve matching unit is specifically used for:
Using the parameter in speed, acceleration in vehicle operating parameters and control instruction value at least one dimension as input
Parameter；It will laterally compensate, turn in vehicle operating parameters, the brake of longitudinal compensation, error, throttle, torque, friction coefficient, vehicle
Parameter in wheel corner, full-vehicle steering and error at least one dimension is as output parameter.
Further, above-mentioned test module 403 is specifically used for:
Using test parameter as the input of the whole vehicle model after calibration, the operating parameter during vehicle testing is obtained；
Using the operating parameter during vehicle testing as the input of module to be tested in the vehicle, vehicle emulation is carried out
Test, and obtain the simulation track data during vehicle emulation testing；
According to the associated actual path data of test parameter and the simulation track data, the module to be tested is determined
Test result.
Embodiment five
Fig. 5 is a kind of structural schematic diagram for equipment that the embodiment of the present invention five provides.Fig. 5, which is shown, to be suitable for being used to realizing this
The block diagram of the example devices 50 of invention embodiment.The equipment 50 that Fig. 5 is shown is only an example, should not be to of the invention real
The function and use scope for applying example bring any restrictions.As shown in figure 5, the equipment 50 is showed in the form of universal computing device.
The component of the equipment 50 can include but is not limited to: one or more processor or processing unit 501, system storage
502, connect the bus 503 of different system components (including system storage 502 and processing unit 501).
Bus 503 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Equipment 50 typically comprises a variety of computer system readable media.These media can be it is any can be by equipment 50
The usable medium of access, including volatile and non-volatile media, moveable and immovable medium.
System storage 502 may include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 504 and/or cache memory 505.Equipment 50 may further include other removable/not removable
Dynamic, volatile/non-volatile computer system storage medium.Only as an example, storage system 506 can be used for read and write can not
Mobile, non-volatile magnetic media (Fig. 5 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 5, Ke Yiti
For the disc driver for being read and write to removable non-volatile magnetic disk (such as " floppy disk "), and to moving non-volatile light
The CD drive of disk (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver
It can be connected by one or more data media interfaces with bus 503.System storage 502 may include at least one journey
Sequence product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform this hair
The function of bright each embodiment.
Program/utility 508 with one group of (at least one) program module 507, can store and deposit in such as system
In reservoir 502, such program module 507 includes but is not limited to operating system, one or more application program, other programs
It may include the realization of network environment in module and program data, each of these examples or certain combination.Program mould
Block 507 usually executes function and/or method in embodiment described in the invention.
Equipment 50 can also be logical with one or more external equipments 509 (such as keyboard, sensing equipment, display 510 etc.)
Letter, can also be enabled a user to one or more equipment interact with the equipment communicate, and/or with enable the equipment 50 with
One or more of the other any equipment (such as network interface card, modem etc.) communication for calculating equipment and being communicated.It is this logical
Letter can be carried out by input/output (I/O) interface 511.Also, equipment 50 can also pass through network adapter 512 and one
Or multiple networks (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet) communication.Such as Fig. 5 institute
Show, network adapter 512 is communicated by bus 503 with other modules of equipment 50.It should be understood that although not shown in the drawings, can
Other hardware and/or software module are used with bonding apparatus 50, including but not limited to: microcode, device driver, redundancy processing
Unit, external disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 501 by the program that is stored in system storage 502 of operation, thereby executing various function application with
And data processing, such as realize test method provided by the embodiment of the present invention.
Embodiment six
The embodiment of the present invention six additionally provides a kind of computer readable storage medium, is stored thereon with computer program, should
Program can realize test method described in above-described embodiment when being executed by processor.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium can be for example but not limited to: electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or
Any above combination of person.The more specific example (non exhaustive list) of computer readable storage medium includes: with one
Or the electrical connections of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM),
Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light
Memory device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer readable storage medium can
With to be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
Person is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including but not limited to:
Wirelessly, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language, such as Java, Smalltalk, C++, also
Including conventional procedural programming language-such as " C " language or similar programming language.Program code can be complete
It executes, partly executed on the user computer on the user computer entirely, being executed as an independent software package, part
Part executes on the remote computer or executes on a remote computer or server completely on the user computer.It is relating to
And in the situation of remote computer, remote computer can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to subscriber computer, or, it may be connected to outer computer (such as led to using ISP
Cross internet connection).
Above-described embodiment serial number is for illustration only, does not represent the advantages or disadvantages of the embodiments.
Will be appreciated by those skilled in the art that each module of the above-mentioned embodiment of the present invention or each operation can be used and lead to
Computing device realizes that they can be concentrated on single computing device, or be distributed in multiple computing devices and formed
Network on, optionally, they can be realized with the program code that computer installation can be performed, so as to storing them
Be performed by computing device in the storage device, perhaps they are fabricated to each integrated circuit modules or by they
In multiple modules or operation be fabricated to single integrated circuit module to realize.In this way, the present invention is not limited to any specific
The combination of hardware and software.
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiments, the same or similar part between each embodiment may refer to each other.
The above description is only a preferred embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art
For, the invention can have various changes and changes.All any modifications made within the spirit and principles of the present invention are equal
Replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (12)
1. a kind of test method characterized by comprising
Whole vehicle model is constructed according to the property parameters of vehicle；
According to relationship of the vehicle between the vehicle actual operation parameters acquired in real road operational process, to described whole
Vehicle model is calibrated；
It is tested using the whole vehicle model after calibration.
2. the method according to claim 1, wherein being acquired in real road operational process according to the vehicle
Vehicle actual operation parameters between relationship, the whole vehicle model is calibrated, comprising:
The operation of at least one dimension in the vehicle actual operation parameters that the vehicle is acquired in real road operational process
Parameter is fitted actual relationship curve as output parameter as input parameter, the operating parameter of other dimensions；
Test module is treated using the operating parameter and the whole vehicle model of at least one dimension and makees emulation testing；
Using the operating parameter of at least one dimension as input parameter, for the simulation results as output parameter, fitting is imitative
True relation curve；
Compare the actual relationship curve and the simulation relation curve, and school is carried out to the whole vehicle model according to comparison result
It is quasi-.
3. according to the method described in claim 2, it is characterized in that, using the operating parameter of at least one dimension and described
Whole vehicle model treats test module and makees emulation testing, comprising:
Using the operating parameter of at least one dimension as the input of the whole vehicle model, the output of the whole vehicle model is made
For the input of module to be tested, emulation testing is carried out to the module to be tested, obtains the modular simulation output to be tested
The operating parameter of other dimensions.
4. according to the method described in claim 2, it is characterized in that, the vehicle acquired in real road operational process
The operating parameter of at least one dimension is as input parameter in vehicle actual operation parameters, and the operating parameter of other dimensions is as defeated
Parameter out, comprising:
Join the parameter in speed, acceleration in vehicle operating parameters and control instruction value at least one dimension as input
Number；It will laterally compensate, turn in vehicle operating parameters, the brake of longitudinal compensation, error, throttle, torque, friction coefficient, wheel
Parameter in corner, full-vehicle steering and error at least one dimension is as output parameter.
5. the method according to claim 1, wherein being tested using the whole vehicle model after calibration, comprising:
Using test parameter as the input of the whole vehicle model after calibration, the operating parameter during vehicle testing is obtained；
Using the operating parameter during vehicle testing as the input of module to be tested in the vehicle, carries out vehicle emulation and survey
Examination, and obtain the simulation track data during vehicle emulation testing；
According to the associated actual path data of test parameter and the simulation track data, the test of the module to be tested is determined
As a result.
6. a kind of test device characterized by comprising
Model construction module, for constructing whole vehicle model according to the property parameters of vehicle；
Model calibration module, vehicle actual operation parameters for being acquired in real road operational process according to the vehicle it
Between relationship, the whole vehicle model is calibrated；
Test module, for being tested using the whole vehicle model after calibration.
7. device according to claim 6, which is characterized in that the model calibration module includes:
Curve matching unit, in the vehicle actual operation parameters for acquiring the vehicle in real road operational process extremely
The operating parameter of a few dimension is fitted actual relationship as output parameter as input parameter, the operating parameter of other dimensions
Curve；
Emulation testing unit, for treating test module using the operating parameter and the whole vehicle model of at least one dimension
Make emulation testing；
The curve matching unit is also used to using the operating parameter of at least one dimension as input parameter, emulation testing
As a result output parameter, Curve fitting simulation relation curve are used as；
Model calibration unit is used for the actual relationship curve and the simulation relation curve, and according to comparison result pair
The whole vehicle model is calibrated.
8. device according to claim 7, which is characterized in that the emulation testing unit is specifically used for:
Using the operating parameter of at least one dimension as the input of the whole vehicle model, the output of the whole vehicle model is made
For the input of module to be tested, emulation testing is carried out to the module to be tested, obtains the modular simulation output to be tested
The operating parameter of other dimensions.
9. device according to claim 7, which is characterized in that the curve matching unit, which has, to be used for:
Join the parameter in speed, acceleration in vehicle operating parameters and control instruction value at least one dimension as input
Number；It will laterally compensate, turn in vehicle operating parameters, the brake of longitudinal compensation, error, throttle, torque, friction coefficient, wheel
Parameter in corner, full-vehicle steering and error at least one dimension is as output parameter.
10. device according to claim 6, which is characterized in that the test module is specifically used for:
Using test parameter as the input of the whole vehicle model after calibration, the operating parameter during vehicle testing is obtained；
Using the operating parameter during vehicle testing as the input of module to be tested in the vehicle, carries out vehicle emulation and survey
Examination, and obtain the simulation track data during vehicle emulation testing；
According to the associated actual path data of test parameter and the simulation track data, the test of the module to be tested is determined
As a result.
11. a kind of equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as test method as claimed in any one of claims 1 to 5.
12. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
Such as test method as claimed in any one of claims 1 to 5 is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811459787.2A CN109522673B (en) | 2018-11-30 | 2018-11-30 | Test method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811459787.2A CN109522673B (en) | 2018-11-30 | 2018-11-30 | Test method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109522673A true CN109522673A (en) | 2019-03-26 |
| CN109522673B CN109522673B (en) | 2024-06-04 |
Family
ID=65794748
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811459787.2A Active CN109522673B (en) | 2018-11-30 | 2018-11-30 | Test method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109522673B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110285985A (en) * | 2019-05-31 | 2019-09-27 | 驭势科技（浙江）有限公司 | Appraisal procedure, device, system and the storage medium of intelligent vehicle steering system |
| CN110598234A (en) * | 2019-05-07 | 2019-12-20 | 重庆长安汽车股份有限公司 | Vehicle dynamics model parameter calibration method |
| CN110807238A (en) * | 2019-08-26 | 2020-02-18 | 腾讯科技（深圳）有限公司 | Simulation model calibration method and related equipment |
| CN111897305A (en) * | 2020-06-02 | 2020-11-06 | 浙江吉利汽车研究院有限公司 | Data processing method, device, equipment and medium based on automatic driving |
| EP3761274A1 (en) * | 2019-07-01 | 2021-01-06 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, apparatus, storage medium and electronic device for testing dynamic parameter of vehicle |
| CN112328970A (en) * | 2020-11-05 | 2021-02-05 | 深圳壹账通智能科技有限公司 | Accident prediction method and system based on vehicle performance parameters |
| CN114486245A (en) * | 2022-03-31 | 2022-05-13 | 东风汽车集团股份有限公司 | Test method, device, equipment and storage medium |
| CN114662269A (en) * | 2021-11-12 | 2022-06-24 | 国家电投集团科学技术研究院有限公司 | Model parameter debugging method and device and storage medium |
| WO2022143919A1 (en) * | 2020-12-31 | 2022-07-07 | 广州极飞科技股份有限公司 | Steering parameter detection method and apparatus, computer device, and readable storage medium |
| CN114859796A (en) * | 2022-06-09 | 2022-08-05 | 中国第一汽车股份有限公司 | Vehicle control method, electronic device and storage medium |
| CN115258323A (en) * | 2021-04-29 | 2022-11-01 | 北京小米移动软件有限公司 | Film tearing control method and device, electronic equipment and storage medium |
| CN116124270A (en) * | 2023-04-18 | 2023-05-16 | 深圳亿维锐创科技股份有限公司 | Automatic intelligent calibration method for dynamic truck scale |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108152050A (en) * | 2017-12-22 | 2018-06-12 | 南京越博动力***股份有限公司 | A kind of whole-car parameters calibration method |
| CN108734949A (en) * | 2017-04-18 | 2018-11-02 | 百度在线网络技术（北京）有限公司 | Automatic driving vehicle emulation platform construction method, device, equipment and storage medium |
| CN108737955A (en) * | 2018-04-28 | 2018-11-02 | 交通运输部公路科学研究所 | LDW/LKA test evaluation system and methods based on virtual lane line |
-
2018
- 2018-11-30 CN CN201811459787.2A patent/CN109522673B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108734949A (en) * | 2017-04-18 | 2018-11-02 | 百度在线网络技术（北京）有限公司 | Automatic driving vehicle emulation platform construction method, device, equipment and storage medium |
| CN108152050A (en) * | 2017-12-22 | 2018-06-12 | 南京越博动力***股份有限公司 | A kind of whole-car parameters calibration method |
| CN108737955A (en) * | 2018-04-28 | 2018-11-02 | 交通运输部公路科学研究所 | LDW/LKA test evaluation system and methods based on virtual lane line |
Non-Patent Citations (2)
| Title |
|---|
| 王秋等: "基于随机模型预测控制的自主车辆转向控制", 《信息与控制》 * |
| 王萍等: "高速公路车辆智能驾驶仿真平台", 《***仿真学报》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598234A (en) * | 2019-05-07 | 2019-12-20 | 重庆长安汽车股份有限公司 | Vehicle dynamics model parameter calibration method |
| CN110285985A (en) * | 2019-05-31 | 2019-09-27 | 驭势科技（浙江）有限公司 | Appraisal procedure, device, system and the storage medium of intelligent vehicle steering system |
| EP3761274A1 (en) * | 2019-07-01 | 2021-01-06 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, apparatus, storage medium and electronic device for testing dynamic parameter of vehicle |
| US11634148B2 (en) | 2019-07-01 | 2023-04-25 | Apollo Intelligent Driving Technology (Beijing) Co., Ltd. | Method, apparatus, storage medium and electronic device for testing dynamic parameter of vehicle |
| CN110807238B (en) * | 2019-08-26 | 2022-11-18 | 腾讯科技（深圳）有限公司 | Simulation model calibration method and related equipment |
| CN110807238A (en) * | 2019-08-26 | 2020-02-18 | 腾讯科技（深圳）有限公司 | Simulation model calibration method and related equipment |
| CN111897305A (en) * | 2020-06-02 | 2020-11-06 | 浙江吉利汽车研究院有限公司 | Data processing method, device, equipment and medium based on automatic driving |
| CN112328970A (en) * | 2020-11-05 | 2021-02-05 | 深圳壹账通智能科技有限公司 | Accident prediction method and system based on vehicle performance parameters |
| WO2022143919A1 (en) * | 2020-12-31 | 2022-07-07 | 广州极飞科技股份有限公司 | Steering parameter detection method and apparatus, computer device, and readable storage medium |
| CN115258323A (en) * | 2021-04-29 | 2022-11-01 | 北京小米移动软件有限公司 | Film tearing control method and device, electronic equipment and storage medium |
| CN114662269A (en) * | 2021-11-12 | 2022-06-24 | 国家电投集团科学技术研究院有限公司 | Model parameter debugging method and device and storage medium |
| CN114486245A (en) * | 2022-03-31 | 2022-05-13 | 东风汽车集团股份有限公司 | Test method, device, equipment and storage medium |
| CN114486245B (en) * | 2022-03-31 | 2024-04-23 | 东风汽车集团股份有限公司 | Test method, device, equipment and storage medium |
| CN114859796A (en) * | 2022-06-09 | 2022-08-05 | 中国第一汽车股份有限公司 | Vehicle control method, electronic device and storage medium |
| CN116124270A (en) * | 2023-04-18 | 2023-05-16 | 深圳亿维锐创科技股份有限公司 | Automatic intelligent calibration method for dynamic truck scale |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109522673B (en) | 2024-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109522673A (en) | A kind of test method, device, equipment and storage medium | |
| O'Kelly et al. | F1/10: An open-source autonomous cyber-physical platform | |
| Chen et al. | A novel integrated simulation and testing platform for self-driving cars with hardware in the loop | |
| CN109491369B (en) | Method, device, equipment and medium for evaluating performance of vehicle actual control unit | |
| Flad et al. | Cooperative shared control driver assistance systems based on motion primitives and differential games | |
| CN109446662A (en) | Generation method and device, the computer equipment and storage medium of vehicle simulation track | |
| CN113032285A (en) | High-precision map testing method and device, electronic equipment and storage medium | |
| Lattarulo et al. | Urban Motion Planning Framework Based on N‐Bézier Curves Considering Comfort and Safety | |
| CN108508881A (en) | Automatic Pilot control strategy method of adjustment, device, equipment and storage medium | |
| Naumann et al. | Coincar-sim: An open-source simulation framework for cooperatively interacting automobiles | |
| Santa Cruz et al. | Nnlander-verif: A neural network formal verification framework for vision-based autonomous aircraft landing | |
| Yang et al. | Multi-vehicle experiment platform: A digital twin realization method | |
| Verma et al. | Implementation and validation of behavior cloning using scaled vehicles | |
| Xiong et al. | Design and Implementation of Digital Twin‐Assisted Simulation Method for Autonomous Vehicle in Car‐Following Scenario | |
| Daza et al. | Sim-to-real transfer and reality gap modeling in model predictive control for autonomous driving | |
| Li et al. | Design and performance evaluation of a simple semi-physical human-vehicle collaborative driving simulation system | |
| Li et al. | A real-time co-simulation framework for virtual test and validation on a high dynamic vehicle test bed | |
| Zhang et al. | A survey of vehicle dynamics modeling methods for autonomous racing: Theoretical models, physical/virtual platforms, and perspectives | |
| Zhao et al. | Driving experience and behavior change in remote driving-an explorative experimental study | |
| CN112835362A (en) | Automatic lane change planning method and device, electronic equipment and storage medium | |
| CN112597005A (en) | Closed-loop simulation test system and method for automatic driving full-stack algorithm | |
| Brisan et al. | A modular road auto-generating algorithm for developing the road models for driving simulators | |
| Phuong et al. | Building a mathematics model for lane‐change technology of autonomous vehicles | |
| Liu et al. | Research on lane change motion planning steering input based on optimal control theory | |
| Weiss et al. | Combining virtual reality and steer-by-wire systems to validate driver assistance concepts |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |