Method and device for calibrating parameters of automatic driving algorithm, terminal and vehicle

Abstract

The invention provides a parameter calibration method and device of an automatic driving algorithm, a terminal and a vehicle. The method comprises the following steps: acquiring vehicle parameters of a to-be-calibrated vehicle model; respectively calculating the similarity between the vehicle parameters of the to-be-calibrated vehicle model and the vehicle parameters of the vehicle models with the known calibration parameters; taking the calibration parameter corresponding to the vehicle model with the maximum value in each similarity as the calibration parameter of the vehicle model to be calibrated; and substituting the calibration parameters of the to-be-calibrated vehicle model into the initial automatic driving algorithm to obtain a target automatic driving algorithm corresponding to the to-be-calibrated vehicle model. According to the method, the vehicle model which is closest to the vehicle parameters of the to-be-calibrated vehicle model in the vehicle models with the known calibration parameters is searched, the calibration parameters of the vehicle model serve as the calibration parameters of the to-be-calibrated vehicle model, the parameters of the automatic driving algorithm do not need to be continuously adjusted through real vehicle experiments, and manpower, material resources and time are saved.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to a method, device, terminal and vehicle for calibrating parameters of an automatic driving algorithm. Background Art

[0002] With the development of artificial intelligence, autonomous driving technology is becoming more and more mature and is being used in more and more vehicles. Due to differences in the performance of the vehicle's own power chassis system and the response characteristics of the vehicle's electronic control system, the same set of autonomous driving algorithms will perform differently on different models. Therefore, during the vehicle mass production development process, when the same set of autonomous driving algorithms is adapted to different mass production models, autonomous driving calibration is required to adjust the parameters in the autonomous driving algorithm so that the autonomous driving algorithm produces consistent control effects on different models.

[0003] In the existing technology, autonomous driving calibration usually requires a large number of real-car experiments, repeated adjustment of parameters, and the consumption of a large amount of manpower, equipment, and time. It also requires a dedicated automobile testing field, and the calibration cost is very high. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, terminal and vehicle for calibrating the parameters of an autonomous driving algorithm to solve the problem in the prior art that autonomous driving calibration requires actual vehicle testing, wastes manpower and material resources, and has high calibration costs.

[0005] In a first aspect, an embodiment of the present invention provides a method for calibrating parameters of an autonomous driving algorithm, comprising:

[0006] Obtain vehicle parameters of the model to be calibrated;

[0007] Calculate the similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters;

[0008] The calibration parameters corresponding to the vehicle model with the largest value in each similarity are used as the calibration parameters of the vehicle model to be calibrated;

[0009] Substitute the calibration parameters of the vehicle model to be calibrated into the initial autonomous driving algorithm to obtain the target autonomous driving algorithm corresponding to the vehicle model to be calibrated.

[0010] Optionally, the similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters is calculated respectively, including:

[0011] Calculating the Mahalanobis distances between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters;

[0012] The similarity is determined based on the Mahalanobis distance, wherein the Mahalanobis distance is inversely proportional to the similarity.

[0013] Optionally, respectively calculating the Mahalanobis distances between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters, including:

[0014] The K-means algorithm is used to calculate the Mahalanobis distance between the vehicle parameters of the model to be calibrated and the vehicle parameters of each model with known calibration parameters.

[0015] Optionally, before substituting the calibration parameters of the vehicle type to be calibrated into the initial autonomous driving algorithm to obtain a target autonomous driving algorithm corresponding to the vehicle type to be calibrated, the calibration method further includes:

[0016] According to the vehicle parameters of the vehicle model to be calibrated, a simulation model of the vehicle model to be calibrated is established;

[0017] Substituting the calibration parameters of the vehicle model to be calibrated into the initial automatic driving algorithm to obtain the intermediate automatic driving algorithm corresponding to the vehicle model to be calibrated;

[0018] Applying the intermediate automatic driving algorithm corresponding to the vehicle model to be calibrated to the simulation model of the vehicle model to be calibrated to perform automatic driving test, and correcting the calibration parameters of the vehicle model to be calibrated according to the test results to obtain corrected calibration parameters;

[0019] Substitute the calibration parameters of the vehicle to be calibrated into the initial autonomous driving algorithm to obtain the target autonomous driving algorithm corresponding to the vehicle to be calibrated, which is:

[0020] Substitute the corrected calibration parameters into the initial autonomous driving algorithm to obtain the target autonomous driving algorithm corresponding to the vehicle model to be calibrated.

[0021] Optionally, before obtaining the vehicle parameters of the vehicle model to be calibrated, the calibration method further includes:

[0022] Obtaining vehicle information of each vehicle model with known calibration parameters and storing it in a database; wherein the vehicle information includes: vehicle parameters and calibration parameters;

[0023] Calculate the similarity between the vehicle parameters of the model to be calibrated and the vehicle parameters of each model with known calibration parameters, including:

[0024] Obtain vehicle parameters of each vehicle model with known calibration parameters from a database;

[0025] The similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters is calculated respectively.

[0026] Optionally, vehicle parameters include: steering wheel angle, steering wheel torque, braking deceleration, response time of longitudinal acceleration, delay time, overshoot, steady-state error, steady-state maximum value, vehicle mass, vehicle size, vehicle center of mass height, and tire-road adhesion coefficient.

[0027] In a second aspect, an embodiment of the present invention provides a device for calibrating parameters of an autonomous driving algorithm, including:

[0028] A vehicle parameter acquisition module is used to obtain vehicle parameters of the vehicle model to be calibrated;

[0029] A similarity calculation module is used to calculate the similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters;

[0030] A calibration parameter determination module is used to use the calibration parameters corresponding to the vehicle model with the largest value among the similarities as the calibration parameters of the vehicle model to be calibrated;

[0031] The algorithm output module is used to substitute the calibration parameters of the vehicle model to be calibrated into the initial autonomous driving algorithm to obtain the target autonomous driving algorithm corresponding to the vehicle model to be calibrated.

[0032] In a third aspect, an embodiment of the present invention provides a calibration terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of a method for calibrating the parameters of an autonomous driving algorithm provided in the first aspect or any possible implementation of the first aspect.

[0033] In a fourth aspect, an embodiment of the present invention provides a vehicle, comprising the calibration terminal provided in the third aspect above.

[0034] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of a method for calibrating parameters of an autonomous driving algorithm provided in the first aspect or any possible implementation method of the first aspect.

[0035] The embodiment of the present invention provides a method, device, terminal and vehicle for calibrating the parameters of an autonomous driving algorithm. The above method includes: obtaining the vehicle parameters of the vehicle model to be calibrated; respectively calculating the similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters; using the calibration parameters corresponding to the vehicle model with the largest value in each similarity as the calibration parameters of the vehicle model to be calibrated; substituting the calibration parameters of the vehicle model to be calibrated into the initial autonomous driving algorithm to obtain the target autonomous driving algorithm corresponding to the vehicle model to be calibrated. In the embodiment of the present invention, the similarity between the vehicle parameters of the vehicle model to be calibrated and the calibration parameters of each vehicle model with known calibration parameters is calculated, and a vehicle model closest to the vehicle model to be calibrated is found, and the calibration parameters of the vehicle model are used as the calibration parameters of the vehicle model to be calibrated. There is no need to continuously adjust the parameters of the autonomous driving algorithm through actual vehicle experiments, saving manpower, material resources and time. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0037] Figure 1 is a flow chart of an implementation method of a parameter calibration method of an autonomous driving algorithm provided by an embodiment of the present invention;

[0038] Figure 2 is a flowchart of another method for calibrating parameters of an autonomous driving algorithm provided by an embodiment of the present invention;

[0039] Figure 3 is a schematic diagram of the structure of a device for calibrating parameters of an autonomous driving algorithm provided in an embodiment of the present invention;

[0040] Figure 4 is a schematic diagram of a calibration terminal provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0042] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0043] See also Figure 1 , which shows a flow chart of a method for calibrating parameters of an autonomous driving algorithm provided by an embodiment of the present invention, and the execution subject of the above method can be any terminal device. For example, it can be a computer in a debugging workshop or other terminal devices outside the vehicle, and there is no specific limitation.

[0044] The above method is described in detail as follows:

[0045] S101: Obtain vehicle parameters of the vehicle model to be calibrated;

[0046] The parameters of the autonomous driving algorithm are strongly correlated with the response characteristics of the vehicle's execution system: EPS (Electric Power Steering), ESP (Electronic Stability Program), ibooster (electronic brake assist system), engine / motor, and the parameters of the entire vehicle.

[0047] Among them, the response characteristics of the execution system mainly include the steering wheel angle, steering wheel torque, braking deceleration, longitudinal acceleration response time, delay time, overshoot, steady-state error and steady-state maximum value. The vehicle parameters are mainly vehicle mass, size, center of mass height, tire-road adhesion coefficient, etc. The above parameters form the vehicle parameters of the vehicle, affect the parameters of the autonomous driving algorithm, and are used to determine the calibration parameters.

[0048] S102: Calculating the similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters;

[0049] Since the parameters of the autonomous driving algorithm are strongly correlated with the parameters of each vehicle, if the vehicle parameters of two models are the same or close, the calibration parameters of the autonomous driving algorithm of one model can be directly applied to the autonomous driving algorithm of the other model.

[0050] The vehicle parameters of various vehicle models and the calibration parameters obtained from the final debugging can be obtained from the records of the previous actual vehicle debugging process. The calibration parameters of each vehicle model are known. Calculate the similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle models with known calibration parameters. The greater the similarity, the more consistent the two vehicle models are, and the calibration parameters can be universal. The calibration parameters corresponding to the vehicle model with the greatest similarity can be used as the calibration parameters of the vehicle model to be calibrated, and the autonomous driving algorithm of the vehicle model to be calibrated can be obtained.

[0051] S103: taking the calibration parameters corresponding to the vehicle model with the largest value among the similarities as the calibration parameters of the vehicle model to be calibrated;

[0052] S104: Substitute the calibration parameters of the vehicle type to be calibrated into the initial automatic driving algorithm to obtain a target automatic driving algorithm corresponding to the vehicle type to be calibrated.

[0053] In the embodiment of the present invention, based on previous debugging records, the calibration parameters of the vehicle model with the greatest similarity to the vehicle parameters of the vehicle model to be calibrated are found as the calibration parameters of the vehicle model to be calibrated. There is no need to perform actual vehicle debugging, and the calibration parameters can be directly obtained, which saves a lot of manpower and material resources and shortens the debugging time.

[0054] In a possible implementation, S102 may include:

[0055] S1021: Calculating the Mahalanobis distances between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters;

[0056] S1022: Determine the similarity according to the Mahalanobis distance; wherein the Mahalanobis distance is inversely proportional to the similarity.

[0057] Mahalanobis distance represents the distance between a point and a distribution. It is an effective method to calculate the similarity between two unknown sample sets. The Mahalanobis distance takes into account the relationship between various parameters, and the calculation result is closer to reality.

[0058] Based on the above, in the embodiment of the present invention, the similarity is determined according to the Mahalanobis distance, which can accurately reflect the similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of the vehicle model with known calibration parameters. The larger the Mahalanobis distance, the smaller the similarity; conversely, the smaller the Mahalanobis distance, the greater the similarity.

[0059] Specifically, the Mahalanobis distance may be used as the denominator of the similarity, and the numerator may be 1, so as to calculate the similarity.

[0060] In a possible implementation, S1021 may include:

[0061] 1. Use the K-means algorithm (k-means clustering algorithm) to calculate the Mahalanobis distance between the vehicle parameters of the model to be calibrated and the vehicle parameters of each model with known calibration parameters.

[0062] K-means clustering is the most widely used clustering method. Its goal is to divide a set of real columns into K clusters, so that: for each real column in the cluster, the centroid of the cluster is closest to the real column; the cluster set composed of these K clusters has the smallest dissimilarity, which is suitable for the calculation of Mahalanobis distance. Therefore, in the embodiment of the present invention, the K-means algorithm is used to determine the Mahalanobis distance, which has a simple calculation process and high accuracy.

[0063] In one possible implementation, reference Figure 2 Before S104, the calibration method may further include:

[0064] S105: Establishing a simulation model of the vehicle model to be calibrated according to the vehicle parameters of the vehicle model to be calibrated;

[0065] S106: Substituting the calibration parameters of the vehicle type to be calibrated into the initial automatic driving algorithm to obtain an intermediate automatic driving algorithm corresponding to the vehicle type to be calibrated;

[0066] S107: applying the intermediate automatic driving algorithm corresponding to the vehicle model to be calibrated to the simulation model of the vehicle model to be calibrated to perform an automatic driving test, and correcting the calibration parameters of the vehicle model to be calibrated according to the test results to obtain corrected calibration parameters;

[0067] S104 may specifically be: substituting the corrected calibration parameters into the initial automatic driving algorithm to obtain a target automatic driving algorithm corresponding to the vehicle type to be calibrated.

[0068] In the embodiment of the present invention, the calibration parameters of the vehicle model with known calibration parameters are directly applied to the vehicle to be calibrated. Since the similarity may not be 100%, the determined calibration parameters may have errors. Therefore, in the embodiment of the present invention, a simulation model of the vehicle model to be calibrated is established, and the determined calibration parameters are applied to the model for simulation, and the calibration parameters are continuously adjusted to finally obtain accurate corrected calibration parameters. The calibration parameters are more accurate, which effectively improves the accuracy of the autonomous driving algorithm.

[0069] In one possible implementation, reference Figure 2 Before S101, the calibration method may further include:

[0070] S108: Acquire vehicle information of each vehicle model with known calibration parameters and store it in a database; wherein the vehicle information includes: vehicle parameters and calibration parameters;

[0071] S102 may include:

[0072] S1023: Acquire vehicle parameters of each vehicle model with known calibration parameters from a database;

[0073] S1024: Calculate the similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters.

[0074] In the embodiment of the present invention, the calibration parameters and vehicle parameters determined during the actual measurement process can be stored in a database to form a sample library (database) for determining the calibration parameters. The more data stored in the database, the more accurate the determined calibration parameters will be.

[0075] In one possible implementation, the vehicle parameters may include: steering wheel angle, steering wheel torque, braking deceleration, response time of longitudinal acceleration, delay time, overshoot, steady-state error, steady-state maximum value, vehicle mass, vehicle size, vehicle center of mass height, and tire-road adhesion coefficient.

[0076] Specifically, vehicle parameters include but are not limited to the above, and can be set according to actual application requirements.

[0077] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0078] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0079] Figure 3 The structure diagram of the calibration device for the parameters of the automatic driving algorithm provided by the embodiment of the present invention is shown. For the convenience of explanation, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0080] like Figure 3 As shown, the calibration device for the parameters of the autonomous driving algorithm includes:

[0081] The vehicle parameter acquisition module 21 is used to acquire the vehicle parameters of the vehicle model to be calibrated;

[0082] A similarity calculation module 22 is used to respectively calculate the similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters;

[0083] The calibration parameter determination module 23 is used to use the calibration parameters corresponding to the vehicle model with the largest value among the similarities as the calibration parameters of the vehicle model to be calibrated;

[0084] The algorithm output module 24 is used to substitute the calibration parameters of the vehicle type to be calibrated into the initial automatic driving algorithm to obtain the target automatic driving algorithm corresponding to the vehicle type to be calibrated.

[0085] In a possible implementation, the similarity calculation module 22 may include:

[0086] A distance calculation unit, used to respectively calculate the Mahalanobis distance between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters;

[0087] The first similarity determination unit is used to determine the similarity according to the Mahalanobis distance; wherein the Mahalanobis distance is inversely proportional to the similarity.

[0088] In a possible implementation, the distance calculation unit may be specifically used for:

[0089] 1. Use the K-means algorithm to calculate the Mahalanobis distance between the vehicle parameters of the model to be calibrated and the vehicle parameters of each model with known calibration parameters.

[0090] In a possible implementation manner, the calibration device may further include:

[0091] A model building module, used to build a simulation model of the vehicle model to be calibrated according to the vehicle parameters of the vehicle model to be calibrated;

[0092] An intermediate algorithm determination module is used to substitute the calibration parameters of the vehicle model to be calibrated into the initial automatic driving algorithm to obtain an intermediate automatic driving algorithm corresponding to the vehicle model to be calibrated;

[0093] A correction module is used to apply the intermediate automatic driving algorithm corresponding to the vehicle model to be calibrated to the simulation model of the vehicle model to be calibrated to perform an automatic driving test, and to correct the calibration parameters of the vehicle model to be calibrated according to the test results to obtain the corrected calibration parameters;

[0094] The algorithm output module 24 can be specifically used to: substitute the corrected calibration parameters into the initial automatic driving algorithm to obtain the target automatic driving algorithm corresponding to the vehicle type to be calibrated.

[0095] In a possible implementation manner, the calibration device may further include:

[0096] A database building module is used to obtain vehicle information of each vehicle model with known calibration parameters and store it in a database; wherein the vehicle information includes: vehicle parameters and calibration parameters;

[0097] The similarity calculation module 22 may include:

[0098] A data acquisition unit, used to acquire vehicle parameters of each vehicle model with known calibration parameters from a database;

[0099] The second similarity determination unit is used to respectively calculate the similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters.

[0100] In one possible implementation, the vehicle parameters may include: steering wheel angle, steering wheel torque, braking deceleration, response time of longitudinal acceleration, delay time, overshoot, steady-state error, steady-state maximum value, vehicle mass, vehicle size, vehicle center of mass height, and tire-road adhesion coefficient.

[0101] Figure 4 is a schematic diagram of a calibration terminal provided by an embodiment of the present invention. Figure 4 As shown, the calibration terminal 3 of this embodiment includes: a processor 30 and a memory 31. The memory 31 is used to store a computer program 32, and the processor 30 is used to call and run the computer program 32 stored in the memory 31 to perform the steps in the calibration method embodiments of the parameters of the above-mentioned various automatic driving algorithms, such as Figure 1 Alternatively, the processor 30 is used to call and run the computer program 32 stored in the memory 31 to implement the functions of each module / unit in the above-mentioned device embodiments, such as Figure 3The functions of modules 21 to 24 are shown.

[0102] Exemplarily, the computer program 32 may be divided into one or more modules / units, one or more modules / units are stored in the memory 31 and executed by the processor 30 to implement the present invention. One or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 32 in the calibration terminal 3. For example, the computer program 32 may be divided into Figure 3 Modules / units 21 to 24 are shown.

[0103] The calibration terminal 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The calibration terminal 3 may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will appreciate that Figure 4 It is only an example of the calibration terminal 3 and does not constitute a limitation on the calibration terminal 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0104] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0105] The memory 31 may be an internal storage unit of the calibration terminal 3, such as a hard disk or memory of the calibration terminal 3. The memory 31 may also be an external storage device of the calibration terminal 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the calibration terminal 3. Further, the memory 31 may also include both an internal storage unit and an external storage device of the calibration terminal 3. The memory 31 is used to store computer programs and other programs and data required by the terminal. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0106] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0107] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0108] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0109] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0110] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0111] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0112] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0113] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for calibrating parameters of an autonomous driving algorithm. It is characterized in that include: Obtain vehicle parameters of the model to be calibrated; Respectively calculating the similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters; The calibration parameters corresponding to the vehicle model with the largest value among the similarities are used as the calibration parameters of the vehicle model to be calibrated; The calibration parameters of the vehicle type to be calibrated are substituted into the initial automatic driving algorithm to obtain the target automatic driving algorithm corresponding to the vehicle type to be calibrated.

2. The method for calibrating parameters of the autonomous driving algorithm according to claim 1, It is characterized in that The respectively calculating the similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters includes: Calculating the Mahalanobis distances between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters; The similarity is determined according to the Mahalanobis distance, wherein the Mahalanobis distance is inversely proportional to the similarity.

3. The method for calibrating parameters of the autonomous driving algorithm according to claim 1, It is characterized in that The respectively calculating the Mahalanobis distances between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters comprises: The K-means algorithm is used to calculate the Mahalanobis distances between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters.

4. A method for calibrating parameters of an autonomous driving algorithm according to any one of claims 1 to 3, It is characterized in that Before substituting the calibration parameters of the vehicle type to be calibrated into the initial automatic driving algorithm to obtain the target automatic driving algorithm corresponding to the vehicle type to be calibrated, the calibration method further includes: Establishing a simulation model of the vehicle model to be calibrated according to the vehicle parameters of the vehicle model to be calibrated; Substituting the calibration parameters of the vehicle type to be calibrated into the initial automatic driving algorithm to obtain an intermediate automatic driving algorithm corresponding to the vehicle type to be calibrated; Applying the intermediate automatic driving algorithm corresponding to the vehicle type to be calibrated to the simulation model of the vehicle type to be calibrated to perform an automatic driving test, and correcting the calibration parameters of the vehicle type to be calibrated according to the test results to obtain corrected calibration parameters; Substituting the calibration parameters of the vehicle to be calibrated into the initial automatic driving algorithm to obtain the target automatic driving algorithm corresponding to the vehicle to be calibrated is specifically: Substitute the corrected calibration parameters into the initial autonomous driving algorithm to obtain a target autonomous driving algorithm corresponding to the vehicle type to be calibrated.

5. A method for calibrating parameters of an autonomous driving algorithm according to any one of claims 1 to 3, It is characterized in that Before obtaining the vehicle parameters of the vehicle model to be calibrated, the calibration method further includes: Obtaining vehicle information of each vehicle model with known calibration parameters and storing it in a database; wherein the vehicle information includes: vehicle parameters and calibration parameters; The respectively calculating the similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters includes: Acquire vehicle parameters of each vehicle model with known calibration parameters from the database; The similarities between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters are calculated respectively.

6. A method for calibrating parameters of an autonomous driving algorithm according to any one of claims 1 to 3, It is characterized in that The vehicle parameters include: steering wheel angle, steering wheel torque, braking deceleration, response time of longitudinal acceleration, delay time, overshoot, steady-state error, steady-state maximum value, vehicle mass, vehicle size, vehicle center of mass height, and tire-road adhesion coefficient.

7. A device for calibrating parameters of an autonomous driving algorithm, It is characterized in that include: A vehicle parameter acquisition module is used to obtain vehicle parameters of the vehicle model to be calibrated; A similarity calculation module, used to respectively calculate the similarity between the vehicle parameters of the vehicle model to be calibrated and the vehicle parameters of each vehicle model with known calibration parameters; A calibration parameter determination module, used to use the calibration parameters corresponding to the vehicle model with the largest value among the similarities as the calibration parameters of the vehicle model to be calibrated; The algorithm output module is used to substitute the calibration parameters of the vehicle type to be calibrated into the initial automatic driving algorithm to obtain the target automatic driving algorithm corresponding to the vehicle type to be calibrated.

8. A calibration terminal, It is characterized in that It comprises a processor and a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the steps of the method for calibrating the parameters of the autonomous driving algorithm as described in any one of claims 1 to 6.

9. A vehicle, It is characterized in that Comprising the calibration terminal as claimed in claim 8.

10. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the steps of the method for calibrating the parameters of the autonomous driving algorithm as described in any one of claims 1 to 6 above are implemented.

Images