CN116279535A

CN116279535A - Vehicle control method and device, electronic equipment and computer storage medium

Info

Publication number: CN116279535A
Application number: CN202211610641.XA
Authority: CN
Inventors: 赵东方; 况宗旭; 于宁
Original assignee: Apollo Zhilian Beijing Technology Co Ltd; Apollo Zhixing Technology Guangzhou Co Ltd
Current assignee: Apollo Zhilian Beijing Technology Co Ltd; Apollo Zhixing Technology Guangzhou Co Ltd
Priority date: 2022-12-12
Filing date: 2022-12-12
Publication date: 2023-06-23

Abstract

The disclosure provides a vehicle control method and device, relates to the field of artificial intelligence, and in particular relates to the technical fields of intelligent traffic, automatic driving and the like. The specific implementation scheme is as follows: controlling the running of the vehicle to be tested by adopting different instruction issuing modes, and collecting first state information of the vehicle to be tested in the instruction issuing modes; determining an accelerator brake calibration table corresponding to the vehicle to be tested based on the first state information; verifying rationality of data in an accelerator brake calibration table; and responding to the passing of the rationality verification of the accelerator and brake calibration table, and controlling the accelerator and/or the brake of the vehicle to be tested based on the accelerator and brake calibration table. The implementation mode improves the reliability of vehicle information calibration.

Description

Vehicle control method and device, electronic equipment and computer storage medium

Technical Field

The present disclosure relates to the field of computer application technologies, and in particular, to the technical field of intelligent transportation, etc., and more particularly, to a vehicle control method and apparatus, an electronic device, a computer readable medium, and a computer program product.

Background

For a vehicle with an automatic driving function, the driving braking performance of the vehicle is an important consideration, and the design of a control method of a chassis of the vehicle and the advantages and disadvantages of the control effect are affected.

The efficiency of the calibration mode of the prior vehicle chassis driving control performance is low, on one hand, the requirement on the calibration field is high, the special test field which needs to be applied is needed, and on the other hand, the automation degree of the whole calibration process is low, and the switching and manual checking work among a plurality of platforms is involved.

Disclosure of Invention

A vehicle control method and apparatus, an electronic device, a computer-readable storage medium, and a computer program product are provided.

According to a first aspect, there is provided a vehicle control method comprising: the method comprises the steps of controlling the operation of a vehicle to be tested by adopting different instruction issuing modes, collecting first state information of the vehicle to be tested in the instruction issuing modes, and enabling the instructions to comprise: at least one of manual driving instruction, automatic driving instruction and script instruction; determining an accelerator brake calibration table corresponding to the vehicle to be tested based on the first state information; verifying rationality of data in an accelerator brake calibration table; and responding to the passing of the rationality verification of the accelerator and brake calibration table, and controlling the accelerator and/or the brake of the vehicle to be tested based on the accelerator and brake calibration table.

According to a second aspect, there is provided a vehicle control apparatus including: the acquisition unit is configured to control the operation of the vehicle to be tested by adopting different instruction issuing modes and acquire first state information of the vehicle to be tested in the instruction issuing modes; the determining unit is configured to determine an accelerator brake calibration table corresponding to the vehicle to be tested based on the first state information; the verification unit is configured to verify the rationality of the data in the throttle brake calibration table; and the loading unit is configured to control the throttle and/or the brake of the vehicle to be tested based on the throttle brake calibration table in response to passing of the verification of the rationality of the throttle brake calibration table.

According to a third aspect, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described in any one of the implementations of the first aspect.

According to a fourth aspect, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform a method as described in any implementation of the first aspect.

According to a fifth aspect, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method as described in any of the implementations of the first aspect.

The vehicle control method and device provided by the embodiment of the disclosure firstly adopt different instruction issuing modes to control the operation of the vehicle to be tested, and collect the first state information of the vehicle to be tested in the instruction issuing modes; secondly, determining an accelerator and brake calibration table corresponding to the vehicle to be tested based on the first state information; thirdly, verifying rationality of the data in the accelerator brake calibration table; and finally, responding to the passing of the rationality verification of the accelerator and brake calibration table, and controlling the accelerator and/or the brake of the vehicle to be tested based on the accelerator and brake calibration table. Therefore, the vehicle is controlled to run by adopting different instruction issuing modes, and the first state information under the different instruction issuing modes is acquired, so that the limitation of the chassis calibration time and place can be avoided; through the instruction issuing mode and the rationality verification mode of the accelerator and brake calibration table, switching of different platforms can be avoided, and reliability of vehicle information calibration is improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a flow chart of one embodiment of a vehicle control method according to the present disclosure;

FIG. 2 is a schematic structural view of a vehicle control frame according to the present disclosure;

FIG. 3 is a schematic illustration of a two-dimensional fitted curve according to the present disclosure;

FIG. 4 is a schematic illustration of a three-dimensional display of the throttle brake calibration gauge of the present disclosure;

FIG. 5 is a schematic structural view of one embodiment of a vehicle control apparatus according to the present disclosure;

fig. 6 is a block diagram of an electronic device for implementing a vehicle control method of an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In this embodiment, "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature.

The present disclosure provides a vehicle control method, fig. 1 shows a flow 100 according to one embodiment of the vehicle control method of the present disclosure, the vehicle control method including the steps of:

and step 101, controlling the operation of the vehicle to be tested by adopting different instruction issuing modes, and collecting first state information of the vehicle to be tested in the instruction issuing modes.

In this embodiment, the instruction issuing manner is a manner of issuing an instruction to the vehicle to be tested, and in this example, the instruction includes: at least one of manual driving instructions, automatic driving instructions and script instructions, wherein the manual driving instructions and the script instructions are instructions generated by personnel through different means, for example, the manual driving instructions are instructions obtained by the personnel operating an accelerator pedal and a brake pedal of a vehicle, the script instructions are instructions generated by the personnel through a programming mode, and the script instructions can be converted into step waveforms which are issued to a chassis of the vehicle and control the opening of the brake and the accelerator after being issued to the vehicle; the automatic driving instruction is an instruction automatically sent by the vehicle control system after the automatic driving function of the vehicle is started, the instruction sending modes can be various, and the instruction sending modes comprise: the vehicle can be operated in different driving states by means of manual driving, automatic driving, script issuing and the like and different instruction issuing modes.

When the command is an automatic driving command and the command issuing mode of the vehicle is automatic driving, as shown in fig. 2, the vehicle to be tested is in an automatic driving state, a chassis controller of the vehicle to be tested obtains opening and speed from different sensors through a CAN (Controller Area Network ) bus, and further searches corresponding acceleration values in an accelerator and brake calibration table under different opening and different speeds, and sends the acceleration values to a chassis control algorithm to control the torque of the chassis.

When the command is a manual driving command and the command issuing mode of the vehicle is manual driving, the vehicle is in a manual driving state, and the driver controls the opening degrees of the accelerator and the brake of the vehicle.

When the command issuing mode of the vehicle is script issuing, the throttle and brake opening information is issued to the chassis controller through the script command, namely, the opening of the step waveform is generated and issued to the chassis of the vehicle through a program coding mode, so that the vehicle is automatically accelerated and decelerated.

In this embodiment, different instruction issuing modes correspond to different vehicle control modes of the vehicle, for example, a manual driving mode of manually driving the corresponding vehicle, an automatic driving mode of automatically driving the corresponding vehicle, and a script issuing mode of script issuing the corresponding vehicle. And in the script issuing mode, after the script program is started manually, a script command is issued to the vehicle, so that an opening command corresponding to the script command is automatically issued to the chassis. In the manual driving mode, the opening degrees of stepping on the brake and the accelerator pedal are determined through manual driving instructions, and the opening degree instructions are transmitted to the chassis.

In this embodiment, the first state information is used to represent an operation state and an instruction state of the vehicle to be tested, where the operation state refers to the operation state of the vehicle to be tested, and the instruction state is an instruction of the vehicle in different instruction issuing modes, and the instruction may include: at least one of manual driving instruction, automatic driving instruction and script instruction, the necessary parameters of the accelerator and brake calibration table can be obtained by converting the instruction.

Specifically, the first state information may include: speed, acceleration and opening. Wherein the opening belongs to an instruction state of the vehicle to be tested, and the opening comprises: the accelerator opening and the brake opening, and when the accelerator and brake calibration table is calculated, the opening value with a positive value represents the accelerator opening, and the opening value with a negative value represents the pedal opening. The speed and the acceleration belong to the running state of the vehicle to be tested. It should be noted that, under different instruction issuing modes, parameters corresponding to the first state information of the vehicle to be tested are the same, but specific values corresponding to the parameters may be different due to different obtaining modes of the parameters, so as to better distinguish the state information, the state information of the vehicle to be tested under the automatic driving instruction mode is second state information, and the first state information includes the second state information.

Step 102, determining an accelerator and brake calibration table corresponding to the vehicle to be tested based on the first state information.

In this embodiment, the accelerator and brake calibration table may provide a mapping relationship among the vehicle speed, the accelerator/brake pedal opening and the acceleration, and after the chassis controller in the vehicle obtains the desired acceleration, the accelerator and brake pedal opening command corresponding to the desired acceleration value may be determined through the accelerator calibration table and issued to the vehicle chassis, so as to implement accurate control of the vehicle chassis.

In this embodiment, determining, based on the first state information, the accelerator brake calibration table corresponding to the vehicle to be tested includes: and carrying out discretization storage processing on the data corresponding to the first state information, and carrying out multidimensional data fitting on the stored data to obtain an accelerator and brake calibration table corresponding to the vehicle to be tested.

In this embodiment, the first state information includes: the discretization storing of the data corresponding to the first state information includes: discretizing the opening and the speed of the motor according to the three dimensions of the opening, the speed and the acceleration; different script issuing modes and different vehicle types need to collect different data ranges and data volumes, and the problem can be solved by loading corresponding parameter files.

The data storage mode is stored for a long time in an off-line file mode, so that the problem of data loss caused by abnormal termination of the calibration process is avoided. And loading the offline file when starting the calibration process each time, and collecting and storing data on the basis of the offline file.

In this embodiment, performing multidimensional data fitting on the stored data to obtain the accelerator and brake calibration table corresponding to the vehicle to be tested includes:

starting from two dimensions of opening and speed, the two dimensions are converted into a regular grid so as to facilitate two-dimensional fitting processing. And fixing the opening degree dimension, and performing polynomial fitting by taking the speed and the acceleration as independent variables and dependent variables respectively, so that a three-dimensional fitting problem is converted into a two-dimensional fitting problem, and the complexity of processing is reduced.

In order to fix the opening degree, the data at the irregular grid is required to be processed by the processing item regular grid to be closed, and the data near the regular grid point is used for estimating the regular grid point, so that the closing process is completed. The opening degree collected by the manual driving and automatic driving working conditions is irregular, and the processing is needed. For the script issuing mode, the opening degree is regular data, and two-dimensional interpolation processing can be directly performed.

Optionally, the step 102 may further include: discretizing the opening and the acceleration in the first state information, converting the opening and the acceleration into a regular grid from two dimensions of the opening and the acceleration, fixing the opening, and performing polynomial fitting by taking the acceleration and the speed as independent variables and dependent variables respectively to obtain a two-dimensional fitting curve; and carrying out three-dimensional expansion on the two-dimensional fitting curve to obtain a three-dimensional accelerator and brake calibration table.

And 103, verifying rationality of the data in the accelerator and brake calibration table.

In order to ensure the rationality of the accelerator and brake calibration table obtained by data processing, the accelerator and brake calibration table needs to be checked.

In this embodiment, in the data processing stage, the collected data may be divided into a training set and a verification set, and the accelerator and brake calibration table is verified by using a cross verification method, and when the error of the verification result is within a reasonable range, the final verification result is output. It should be noted that, the cross-validation method is a conventional data validation method, which is not described in detail in this embodiment.

And 104, controlling the throttle and/or the brake of the vehicle to be tested based on the throttle brake calibration table in response to passing the rationality verification of the throttle brake calibration table.

In this embodiment, the chassis controller of the vehicle to be tested has a chassis control algorithm, the chassis control algorithm can obtain the expected acceleration value, and after the rationality verification of the accelerator and brake calibration table is passed, the accelerator and brake pedal opening commands corresponding to the expected acceleration value can be provided for the chassis controller through the accelerator and brake calibration table, so as to realize the accurate control of the vehicle to be tested.

The vehicle control frame provided in this embodiment is shown in fig. 2, and mainly depends on an external module including a positioning device, a CAN bus, and a chassis. The CAN bus CANBUS is responsible for the transfer function of command signals and status signals, and receives command signals from a script issuing and automatic driving module on one hand and status signals from a vehicle and a positioning module on the other hand. The data required for calibration may all come from the CAN bus.

The manual driving module flows to the vehicle chassis module, and the manual command flow is transferred to the CAN bus in a vehicle chassis state information mode, and the flow information from the CAN bus to the vehicle chassis module is command information of the script issuing and automatic driving module.

The three test working conditions of the script issuing mode, the automatic driving mode and the manual driving mode can be used for calibrating the performance of the chassis and generating a corresponding calibration table, the difference of the three test working conditions is mainly represented by the degree of coverage of the calibration table on the performance of the chassis, the script issuing and the manual driving can be used for obtaining all the performance of the chassis, and the automatic driving can only be used for obtaining the conventional performance of the chassis in a conventional scene.

Compared with the off-line version calibration method under the two instruction issuing modes of script issuing and manual driving, the on-line version calibration method under the automatic driving working condition can modify and start the accelerator brake calibration table in the automatic driving closed-loop operation.

The script issuing mode, the automatic driving mode and the manual driving mode in the vehicle control frame correspond to three test working conditions and test methods respectively, and different test method selections can have corresponding influence on the calibration algorithm flow.

The script issuing test method has the highest efficiency in three modes, and the stable test input signals enable the collected data to be affected by noise to a small extent, and have low requirements on the number of times of testing and the data volume, and have the disadvantage of needing a proper special test field.

For the manual driving test method, the method can be carried out on a normal road, the requirement on a special test site is reduced, the test efficiency is low, the fluctuation of a manual driving control input signal is large, the noise contained in the collected data is large, and the requirements on the test times and the data quantity are correspondingly improved.

For the automatic driving test method, human intervention is not needed, the whole calibration process can be completed in the automatic driving operation process, and the method has the disadvantages that the coverage of the obtained chassis driving braking performance is limited, and the method is similar to the manual driving method, has larger data noise, needs more data quantity support and has lower efficiency.

All the three test methods have the advantages and disadvantages, corresponding methods are selected according to different test conditions, and meanwhile, the three methods are mutually complemented, so that the three methods have the cooperative effect.

Optionally, because the data for calibrating the accelerator and brake calibration table is derived from the CAN bus, the CAN bus is used for transferring the state information of the positioning module and the chassis, and when the state in the positioning module or the chassis is abnormal, the corresponding data dead points in the accelerator and brake calibration table need to be removed.

Optionally, when the chassis driving and braking hardware of the vehicle changes, such as the remanufacturing of the chassis hardware, a larger deviation between the performance of the chassis part and the original calibration table occurs, and then the automatic driving operation may possibly have a safety accident problem. Therefore, the chassis performance calibration function of the appointed part is supported in the accelerator brake calibration table, and the data acquisition, processing and table generation processes are carried out by means of a non-automatic driving test method.

In this embodiment, when the rationality verification of the accelerator brake calibration table fails, the process returns to step 101, and the collection of the first state information and the determination of the accelerator brake calibration table are continued.

The technology of the functions realizes that the path is consistent with the full-quantity calibration process of the chassis driving braking performance, the same data acquisition, processing and evaluation modes are needed, the chassis performance calibration function of a designated part is supported in the starting accelerator braking calibration table, and the data acquisition, processing and table generation process by means of a non-automatic driving test method comprises the following steps:

Traversing the local opening range, such as [ -100,0] or [ -20, 20] and the like, and directly skipping the part which does not need calibration, so as to avoid repeated calibration; and replacing the corresponding part of the original table with the new local calibration table.

The vehicle control method provided by the embodiment of the disclosure can effectively improve the calibration efficiency of the driving and braking performance of the automatic driving vehicle. The workload of the calibration part is improved to 1.5h per person every day, and meanwhile, the problem of inconsistent vehicles is effectively solved by introducing the online calibration part, and the problem of precision control in the automatic driving process is ensured.

According to the vehicle control method provided by the embodiment of the disclosure, firstly, different instruction issuing modes are adopted to control the operation of a vehicle to be tested, and first state information of the vehicle to be tested in the instruction issuing modes is collected; secondly, determining an accelerator and brake calibration table corresponding to the vehicle to be tested based on the first state information; thirdly, verifying rationality of the data in the accelerator brake calibration table; and finally, responding to the passing of the rationality verification of the accelerator and brake calibration table, and controlling the accelerator and/or the brake of the vehicle to be tested based on the accelerator and brake calibration table. Therefore, the vehicle is controlled to run by adopting different instruction issuing modes, and the first state information under the different instruction issuing modes is acquired, so that the limitation of the chassis calibration time and place can be avoided; through the instruction issuing mode and the rationality verification mode of the accelerator and brake calibration table, switching of different platforms can be avoided, and reliability and efficiency of vehicle control are improved.

In some optional implementations of this embodiment, the controlling the operation of the vehicle to be tested by using different instruction issuing modes, and collecting the first state information of the vehicle to be tested in the instruction issuing mode includes:

in the initial stage of the vehicle to be tested, controlling the operation of the vehicle to be tested by adopting a manual driving mode or a script issuing mode, and collecting initial information of the vehicle to be tested in the manual driving mode or the script issuing mode; and in the automatic driving stage of the vehicle to be tested, controlling the operation of the vehicle to be tested by adopting an automatic driving mode, and collecting the operation information of the vehicle to be tested in the automatic driving mode.

The determining, based on the first state information, the accelerator and brake calibration table corresponding to the vehicle to be tested includes: obtaining an initial table based on the initial information; obtaining an operation form based on the operation information; and in response to the unmatched initial form and the running form, covering corresponding data in the initial form by the running form to obtain an accelerator brake calibration table corresponding to the vehicle to be tested.

In this optional implementation manner, the initial stage of the vehicle refers to a stage in which the vehicle does not have an accelerator brake calibration table, and for this initial stage, the accelerator brake performance of the chassis of the vehicle cannot be completely represented due to the limited coverage of the chassis driving brake performance obtained in the automatic driving mode, and the initial table is obtained through the manual driving model or the script issuing mode.

In this alternative implementation, the autopilot mode refers to a vehicle being in an autopilot state, where the vehicle does not require manual intervention.

In this optional implementation manner, the automatic driving stage control opportunity may be performed after the initial table is obtained, specifically, in response to detecting the initial table obtained by the initial information, it is determined that the vehicle to be tested may be in the automatic driving stage, and the operation of the vehicle to be tested is controlled by adopting the automatic driving mode.

In this optional implementation manner, the initial table and the running table each have a plurality of fields (for example, an opening, a speed, and an acceleration), each field corresponds to data (for example, an opening value corresponding to the opening, a speed value corresponding to the speed, and an acceleration value corresponding to the acceleration), and when the fields in the initial table are the same as the fields in the running table, but the data corresponding to the same fields are different, it is determined that the initial table is not matched with the running table, and the data corresponding to the field in the running table is used to replace the data corresponding to the field in the initial table.

The method for determining the accelerator and brake calibration table of the vehicle to be tested, which is provided by the alternative implementation mode, comprises the steps of firstly controlling the vehicle to be tested to run by adopting a manual driving mode or a script issuing model in the initial stage of the vehicle to be tested, and determining an initial table; in an automatic driving stage of the vehicle to be tested, controlling the vehicle to be tested to run by adopting an automatic driving mode, and determining a running form; the corresponding data in the initial table is further covered by the running table, so that the obtained accelerator and brake calibration table is comprehensive in data and accurate in data, and the reliability of the accelerator and brake calibration table is improved.

Optionally, the controlling the operation of the vehicle to be tested by adopting different instruction issuing modes, and collecting the first state information of the vehicle to be tested in the instruction issuing mode includes:

selecting a test time period, wherein the test time period comprises: the method comprises the steps of controlling the operation of a vehicle to be tested by adopting a manual driving mode or a script issuing mode in a first time period and a second time period positioned after the first time period, and collecting first information of the vehicle to be tested in the manual driving mode or the script issuing mode; and in a second time period, controlling the operation of the vehicle to be tested by adopting an automatic driving mode, and collecting second information of the vehicle to be tested in the automatic driving mode.

The determining, based on the first state information, the accelerator and brake calibration table corresponding to the vehicle to be tested includes: obtaining a first table based on the first information; obtaining a second table based on the second information; and in response to the fact that the first table is not matched with the second table, covering corresponding data in the first table by adopting the second table to obtain an accelerator brake calibration table corresponding to the vehicle to be tested.

In some optional implementations of this embodiment, the obtaining the initial table based on the initial information includes: discretizing the data in the initial information to obtain initial discrete data; fixing the opening value in the initial discrete data, and performing polynomial function calculation on the speed and the acceleration to obtain an initial two-dimensional fitting curve; traversing all opening values in the initial discrete data, and performing three-dimensional expansion on the initial two-dimensional fitting curve to obtain an initial table.

In this embodiment, the initial two-dimensional fitted curve is a two-dimensional fitted curve, and as shown in fig. 3, a schematic diagram of the two-dimensional fitted curve is shown, in fig. 3, the horizontal axis is velocity, the vertical axis is acceleration, the two-dimensional fitted curve b is a curve obtained by performing a smooth fitting process on the discrete curve a at a fixed opening value (for example, an opening value is 85), wherein the offline curve a is a curve obtained by performing a binomial function calculation on the velocity and the acceleration.

In this embodiment, the initial table is a three-dimensional table, and when the accelerator brake calibration table is used for representing the relationship among the speed, the acceleration and the opening, the accelerator brake calibration table is a three-dimensional table representing the corresponding relationship among the speed, the acceleration and the opening, as shown in fig. 4, which is a schematic diagram of three-dimensional display of the accelerator brake calibration table, wherein in fig. 4, s represents the speed, t represents the opening, n represents the acceleration, and data in the initial table may be relatively inaccurate relative to the accelerator brake calibration table, so that the initial table needs to be corrected in order to obtain the accelerator brake calibration table.

According to the method for obtaining the initial table, polynomial function calculation is firstly carried out on initial information to obtain an initial two-dimensional fitting curve, and then three-dimensional expansion is carried out on the initial two-dimensional fitting curve in traversing of all opening values in initial discrete data to obtain the initial table, so that a reliable implementation mode is provided for obtaining the initial table.

In some optional implementations of this embodiment, the obtaining the operation table based on the operation information includes: discretizing the data in the operation information to obtain operation discrete data; fixing the opening value in the running discrete data, and performing polynomial function calculation on the speed and the acceleration to obtain a running two-dimensional fitting curve; traversing all opening values in the running discrete data, and performing three-dimensional expansion on the running two-dimensional fitting curve to obtain a running table.

In this embodiment, the running two-dimensional fitting curve is a two-dimensional fitting curve, the running table is a three-dimensional table, and when the accelerator brake calibration table is used for representing the relationship among the speed, the acceleration and the opening, the accelerator brake calibration table is a three-dimensional table for representing the corresponding relationship among the speed, the acceleration and the opening, and data in the running table may be relatively inaccurate relative to the accelerator brake calibration table, so that the running table needs to be corrected in order to obtain the accelerator brake calibration table.

The method for obtaining the running form provided by the alternative implementation mode firstly carries out polynomial function calculation on the running information to obtain the running two-dimensional fitting curve, and secondly carries out three-dimensional expansion on the running two-dimensional fitting curve in traversing all opening values in the running discrete data to obtain the running form, thereby providing a reliable implementation mode for obtaining the running form.

In some optional implementations of the disclosure, the verifying the rationality of the data in the accelerator brake calibration table includes: dividing the accelerator brake calibration table into a training set and a verification set; fixing opening values in the training set, and calculating two-dimensional fitting curves under different opening values, wherein the two-dimensional fitting curves are used for representing the corresponding relation between the speed and the acceleration under the fixed opening values; calculating the calculated value of each acceleration value in the corresponding verification set based on the two-dimensional fitting curve; determining the mean square error of an accelerator and brake calibration table based on the acceleration values and the calculated values of all opening values in the verification set; and determining that the throttle brake calibration table passes the rationality verification in response to the mean square error being smaller than the set threshold.

In this optional implementation manner, the training set and the verification set are three-dimensional data sets, the three-dimensional data represent data of three dimensions of speed, acceleration and opening respectively, after a two-dimensional fitting curve is obtained, a speed value (a value corresponding to the speed) in the verification set is brought into the two-dimensional fitting curve, and a calculated value corresponding to an acceleration value (a value corresponding to the acceleration) under the current opening can be obtained. The calculated acceleration value may be the same as the acceleration value or may be different from the acceleration value.

In this alternative implementation, the set threshold may be a value set based on development requirements.

In this alternative implementation, a portion of the data (e.g., 80%) in the throttle brake calibration table may be used as a training set and another portion of the data (e.g., 20%) may be used as a verification set.

The data provided by the alternative implementation mode is validated reasonably, the average dividing error is counted through the accelerator and brake calibration table, and when the average dividing error is within a preset range, the calibration result is correct, so that a reliable implementation mode is provided for validating the accelerator and brake calibration table.

In another embodiment of the present disclosure, the vehicle control method further includes: when the vehicle to be tested is in an automatic driving state, acquiring second state information of the vehicle to be tested in real time; based on the second state information, at least one state fitting curve is obtained, wherein the state fitting curve is used for representing the corresponding relation between the speed and the acceleration under different opening values; based on the throttle brake calibration table and the state fitting curve, verifying the rationality of the throttle brake calibration table; and updating the accelerator brake calibration table based on the second state information to obtain an updated calibration table, and loading the updated calibration table into a memory of the vehicle to be tested in response to the accelerator brake calibration table failing to pass the rationality verification.

In this embodiment, the second state information may also include: the speed, acceleration and opening of the vehicle in the automatic driving state, wherein the opening comprises an accelerator opening and a pedal opening, and the obtaining at least one state fitting curve based on the second state information comprises: selecting three-dimensional arrays with opening value intervals meeting preset interval quantity and larger than preset quantity in the second state information, concentrating all the three-dimensional arrays on a certain fixed opening in a mode of approaching to regular grid points, and obtaining at least one state fitting curve in a linear curve fitting mode, wherein each state fitting curve corresponds to one opening, and the state fitting curve is a speed and acceleration corresponding relation curve.

Based on the throttle brake calibration table and the state fitting curve, the rationality verification of the throttle brake calibration table comprises the following steps: and fixing the opening value in the accelerator brake calibration table, performing curve fitting by adopting a two-term function of the speed and the acceleration in the accelerator brake calibration table to obtain a curve to be measured, comparing the state curve with the curve to be measured, determining the error of the curve to be measured and the curve to be measured, responding to the error exceeding an error threshold value, determining that the curve to be measured is not matched with the state curve, and replacing an abnormal calibration point in the accelerator brake calibration table by adopting second state information to obtain an updated calibration table if the accelerator brake calibration table fails to pass the rationality verification.

In this embodiment, since the vehicle is running in an automatic driving closed loop, the replacement and update of the accelerator and brake calibration table needs to implement safe and noninductive replacement, on one hand, the offline calibration file of the accelerator and brake calibration table needs to be updated, and on the other hand, the updated calibration file of the updated calibration table needs to be loaded into the memory for the control algorithm. The method is easy to realize for storing the updated calibration file, and corresponding algorithm adaptation work is needed for the problem of loading the offline calibration file in the running process. One possible adaptation method is as follows: the user of the off-line calibration file detects whether the updated calibration file is generated or not in real time, and when the updated calibration file is generated, loading and switching of the updated calibration file are completed.

According to the vehicle control method, the throttle brake calibration table is validated reasonably through the state fitting curve obtained by collecting the second state information of the vehicle to be tested in the automatic driving state, and when the throttle brake calibration table does not pass the validation, the throttle brake calibration table is updated based on the second state information to obtain the updated calibration table, so that an online calibration method is provided for the throttle brake calibration table, the accuracy of the throttle brake calibration table is guaranteed, and the reliability of vehicle control is improved.

In some optional implementations of the disclosure, the vehicle under test includes: a plurality of vehicles under the same vehicle type; the method comprises the steps of controlling the operation of the vehicle to be tested by adopting different instruction issuing modes, and collecting first state information of the vehicle to be tested in the instruction issuing modes, wherein the first state information comprises: randomly selecting a first vehicle of the plurality of vehicles; controlling the first vehicle to run by adopting a manual driving mode or a script issuing mode, and collecting first state information of the first vehicle in the manual driving mode or the script issuing mode;

responding to the passing of the rationality verification of the accelerator brake calibration table, controlling the vehicle to be tested based on the accelerator brake calibration table comprises the following steps: and in response to passing the verification of the rationality of the throttle brake calibration table of the first vehicle, loading the throttle brake calibration table of the first vehicle into the memories of the respective vehicles of the plurality of vehicles.

In this optional implementation manner, the accelerator and brake calibration table is loaded into the memory of the vehicle, so that the accelerator and brake calibration table of the first vehicle can participate in actual control of chassis of a plurality of vehicles.

In this optional implementation manner, the first vehicle is a vehicle selected randomly from vehicles to be tested, and when the experimental environment meets the conditions, the first vehicle can be controlled by adopting a manual driving mode or a script issuing mode.

In the alternative implementation manner, for the situation that the full-capacity-drive braking performance of the chassis needs to be obtained, the current situation of the site can be combined to select between two test working conditions of a manual driving mode and a script issuing mode, and the first vehicle is controlled to run, so that an accelerator and brake calibration table of the first vehicle is obtained.

In the alternative implementation manner, the accelerator and brake calibration table obtained through the first vehicle can be used as a calibration table of all vehicles in the vehicles to be tested, and each vehicle controls a chassis control algorithm based on the calibration table, so that a reliable basis is provided for the chassis control algorithm of all vehicles in the vehicles to be tested.

In another embodiment of the present disclosure, the vehicle control method may further include: controlling the second vehicle to run in an automatic driving mode in response to the third state information of the second vehicle being inconsistent with the third state information of the first vehicle among the plurality of vehicles; determining an accelerator brake calibration table corresponding to the second vehicle based on third state information of the second vehicle; after the throttle brake calibration table of the second vehicle passes the rationality verification, the throttle brake calibration table of the second vehicle is used for replacing the throttle brake calibration table of the first vehicle and is loaded into a memory of the second vehicle, so that the throttle brake calibration table of the second vehicle participates in the actual control of the chassis of the second vehicle.

In this embodiment, for the same vehicle model, there is a consistency difference between different workshops, but the difference is often not large. Therefore, only one full-quantity calibration is needed for one vehicle type, and partial performance is calibrated and improved in an automatic driving on-line calibration mode for the problem that different workshops of the same vehicle type are inconsistent.

According to the vehicle control method, after the accelerator and brake calibration table of the first vehicle is obtained through the first state information of the first vehicle, the reliability of chassis information of a plurality of vehicles in the vehicle to be tested can be improved through the fact that the second vehicle in the vehicle to be tested is inconsistent with the first state information of the first vehicle and the accelerator and brake calibration table is obtained and verified through the fact that the accelerator and brake calibration table is independently carried out on the second vehicle.

With further reference to fig. 5, as an implementation of the method shown in the above figures, the present disclosure provides an embodiment of a vehicle control apparatus, which corresponds to the method embodiment shown in fig. 1, and which is particularly applicable to various electronic devices.

As shown in fig. 5, the vehicle control apparatus 500 provided in the present embodiment includes: the device comprises an acquisition unit 501, a determination unit 502, a verification unit 503 and a loading unit 504. The collecting unit 501 may be configured to control the operation of the vehicle to be tested by adopting different instruction issuing modes, and collect the first state information of the vehicle to be tested in the instruction issuing mode. The determining unit 502 may be configured to determine an accelerator brake calibration table corresponding to the vehicle to be tested based on the first state information. The verification unit 503 may be configured to perform verification on the rationality of the data in the accelerator brake calibration table. The loading unit 504 may be configured to control the throttle and/or brake of the vehicle under test based on the throttle brake calibration table in response to the verification of the rationality of the throttle brake calibration table passing.

In the present embodiment, in the vehicle control apparatus 500: the specific processing and the technical effects of the acquisition unit 501, the determination unit 502, the verification unit 503, and the loading unit 504 may refer to the descriptions related to step 101, step 102, step 103, and step 104 in the corresponding embodiment of fig. 1, and are not described herein.

In some optional implementations of this embodiment, the acquisition unit 501 is further configured to: in the initial stage of the vehicle to be tested, controlling the operation of the vehicle to be tested by adopting a manual driving mode or a script issuing mode, and collecting initial information of the vehicle to be tested in the manual driving mode or the script issuing mode; in an automatic driving stage of the vehicle to be tested, controlling the operation of the vehicle to be tested by adopting an automatic driving mode, and collecting the operation information of the vehicle to be tested in the automatic driving mode; the determining unit 502 is further configured to: obtaining an initial table based on the initial information; obtaining an operation form based on the operation information; and in response to the unmatched initial form and the running form, covering corresponding data in the initial form by the running form to obtain an accelerator brake calibration table corresponding to the vehicle to be tested.

In some optional implementations of this embodiment, the determining unit 502 is further configured to: discretizing the data in the initial information to obtain initial discrete data; fixing the opening value in the initial discrete data, and performing polynomial function calculation on the speed and the acceleration to obtain an initial two-dimensional fitting curve; traversing all opening values in the initial discrete data, and performing three-dimensional expansion on the initial two-dimensional fitting curve to obtain an initial table.

In some optional implementations of the present disclosure, the determining unit 502 is further configured to: discretizing the data in the operation information to obtain operation discrete data; fixing the opening value in the running discrete data, and performing polynomial function calculation on the speed and the acceleration to obtain a running two-dimensional fitting curve; traversing all opening values in the running discrete data, and performing three-dimensional expansion on the running two-dimensional fitting curve to obtain a running table.

In some optional implementations of the present disclosure, the verification unit 503 is further configured to: the opening value in the throttle brake calibration table is fixed, and a two-dimensional fitting curve under different openings is calculated, wherein the two-dimensional fitting curve is used for representing the corresponding relation between the speed and the acceleration under the fixed opening value; calculating calculated values corresponding to all acceleration values in an accelerator and brake calibration table based on the two-dimensional fitting curve; determining the mean square error of the accelerator and brake calibration table based on the acceleration values and the calculated values of all opening values in the accelerator and brake calibration table; and determining that the throttle brake calibration table passes the rationality verification in response to the mean square error being smaller than the set threshold.

In some optional implementations of the disclosure, the apparatus further includes: a first calibration unit (not shown in the figures) configured to: when the vehicle to be tested is in an automatic driving state, acquiring second state information of the vehicle to be tested in real time; based on the second state information, at least one state fitting curve is obtained, wherein the state fitting curve is used for representing the corresponding relation between the speed and the acceleration under different opening values; based on the throttle brake calibration table and the state fitting curve, verifying the rationality of the throttle brake calibration table; and updating the accelerator brake calibration table based on the second state information to obtain an updated calibration table, and loading the updated calibration table into a memory of the vehicle to be tested in response to the accelerator brake calibration table failing to pass the rationality verification.

In some optional implementations of the disclosure, the vehicle under test includes: a plurality of vehicles under the same vehicle type; the acquisition unit is further configured to: randomly selecting a first vehicle of the plurality of vehicles; controlling the first vehicle to run by adopting a manual driving mode or a script issuing mode, and collecting first state information of the first vehicle in the manual driving mode or the script issuing mode; the loading unit is further configured to: in response to the verification of the rationality of the throttle brake calibration table of the first vehicle passing, the throttle brake calibration table of the first vehicle is loaded into the memory of each of the plurality of vehicles, respectively, to control the throttle and/or brake of each of the plurality of vehicles based on the throttle brake calibration table of the first vehicle.

In some optional implementations of the disclosure, the apparatus 500 further includes: a second calibration unit (not shown in the figures), wherein the second calibration unit is configured to: controlling the second vehicle to run in an automatic driving mode in response to the third state information of the second vehicle being inconsistent with the third state information of the first vehicle among the plurality of vehicles; determining an accelerator brake calibration table corresponding to the second vehicle based on third state information of the second vehicle; and after the throttle brake calibration table of the second vehicle passes the rationality verification, replacing the throttle brake calibration table of the first vehicle with the throttle brake calibration table of the second vehicle, and loading the throttle brake calibration table of the second vehicle into a memory of the second vehicle.

In the vehicle control device provided by the embodiment of the present disclosure, first, the acquisition unit 501 controls the operation of the vehicle to be tested by adopting different instruction issuing modes, and acquires the first state information of the vehicle to be tested in the instruction issuing mode; secondly, the determining unit 502 determines an accelerator brake calibration table corresponding to the vehicle to be tested based on the first state information; again, the verification unit 503 performs rationality verification on the data in the accelerator brake calibration table; finally, the loading unit 504 controls the throttle and/or brake of the vehicle under test based on the throttle brake calibration table in response to the verification of the rationality of the throttle brake calibration table passing. Therefore, the vehicle is controlled to run by adopting different instruction issuing modes, and the first state information under the different instruction issuing modes is acquired, so that the limitation of the chassis calibration time and place can be avoided; through the instruction issuing mode and the rationality verification mode of the accelerator and brake calibration table, switching of different platforms can be avoided, and the reliability of vehicle control is improved.

In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public order colloquial is not violated.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

Fig. 6 illustrates a schematic block diagram of an example electronic device 600 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the apparatus 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data required for the operation of the device 600 may also be stored. The computing unit 601, ROM 602, and RAM603 are connected to each other by a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

Various components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, mouse, etc.; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the respective methods and processes described above, such as a vehicle control method. For example, in some embodiments, the vehicle control method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM602 and/or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the vehicle control method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the vehicle control method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable vehicle control apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A vehicle control method, the method comprising:

the method comprises the steps of controlling the operation of a vehicle to be tested by adopting different instruction issuing modes, and collecting first state information of the vehicle to be tested in the instruction issuing modes, wherein the instruction comprises the following steps: at least one of manual driving instruction, automatic driving instruction and script instruction;

determining an accelerator brake calibration table corresponding to the vehicle to be tested based on the first state information;

verifying rationality of the data in the accelerator brake calibration table;

and responding to the passing of the rationality verification of the accelerator and brake calibration table, and controlling the accelerator and/or the brake of the vehicle to be tested based on the accelerator and brake calibration table.

2. The method of claim 1, wherein the controlling the operation of the vehicle under test by using different instruction issuing modes, and collecting the first state information of the vehicle under test in the instruction issuing modes, includes:

In the initial stage of a vehicle to be tested, controlling the vehicle to be tested to run by adopting a manual driving mode or a script issuing mode, and collecting initial information of the vehicle to be tested in the manual driving mode or the script issuing mode;

in an automatic driving stage of the vehicle to be tested, controlling the operation of the vehicle to be tested by adopting an automatic driving mode, and collecting the operation information of the vehicle to be tested in the automatic driving mode;

the determining, based on the first state information, an accelerator brake calibration table corresponding to the vehicle to be tested includes:

based on the initial information, an initial table is obtained;

obtaining an operation table based on the operation information;

and responding to the mismatching of the initial table and the running table, and covering corresponding data in the initial table by adopting the running table to obtain an accelerator and brake calibration table corresponding to the vehicle to be tested.

3. The method of claim 2, wherein the obtaining an initial table based on the initial information comprises:

discretizing the data in the initial information to obtain initial discrete data;

fixing the opening value in the initial discrete data, and performing polynomial function calculation on the speed and the acceleration to obtain an initial two-dimensional fitting curve;

And traversing all opening values in the initial discrete data, and performing three-dimensional expansion on the initial two-dimensional fitting curve to obtain an initial table.

4. The method of claim 2, wherein the deriving an operation table based on the operation information comprises:

discretizing the data in the operation information to obtain operation discrete data;

fixing the opening value in the running discrete data, and performing polynomial function calculation on the speed and the acceleration to obtain a running two-dimensional fitting curve;

traversing all opening values in the running discrete data, and performing three-dimensional expansion on the running two-dimensional fitting curve to obtain a running table.

5. The method of one of claims 1-4, wherein said validating the data in the throttle brake calibration table comprises:

dividing the accelerator brake calibration table into a training set and a verification set;

fixing the opening value in the training set, and calculating a two-dimensional fitting curve under different openings, wherein the two-dimensional fitting curve is used for representing the corresponding relation between the speed and the acceleration under the fixed opening value;

calculating calculated values corresponding to all acceleration values in the verification set based on the two-dimensional fitting curve, and determining the mean square error of the accelerator and brake calibration table based on the acceleration values and the calculated values under all opening values in the verification set;

And determining that the throttle brake calibration table passes the rationality verification in response to the mean square error being smaller than a set threshold.

6. The method of claim 5, the method further comprising:

when the vehicle to be tested is in an automatic driving state, acquiring second state information of the vehicle to be tested in real time;

based on the second state information, at least one state fitting curve is obtained, wherein the state fitting curve is used for representing the corresponding relation between the speed and the acceleration under different opening values;

based on the accelerator brake calibration table and the state fitting curve, verifying the rationality of the accelerator brake calibration table;

and in response to the fact that the throttle brake calibration table fails to pass the rationality verification, updating the throttle brake calibration table based on the second state information to obtain an updated calibration table, and loading the updated calibration table into a memory of the vehicle to be tested.

7. The method of claim 1, wherein the vehicle under test comprises: a plurality of vehicles under the same vehicle type; the method for controlling the operation of the vehicle to be tested by adopting different instruction issuing modes comprises the following steps of:

Randomly selecting a first vehicle of the plurality of vehicles;

controlling the first vehicle to run by adopting the manual driving mode or the script issuing mode, and collecting first state information of the first vehicle in the manual driving mode or the script issuing mode;

the verifying of the rationality in response to the accelerator brake calibration table comprises the following steps of controlling the accelerator and/or the brake of the vehicle to be tested based on the accelerator brake calibration table:

and in response to passing the rationality verification of the throttle brake calibration table of the first vehicle, loading the throttle brake calibration table of the first vehicle into memories of each of the plurality of vehicles respectively so as to control the throttle and/or brake of each of the plurality of vehicles based on the throttle brake calibration table of the first vehicle.

8. The method of claim 7, the method further comprising:

controlling operation of a second vehicle of the plurality of vehicles in an autonomous driving mode in response to the first status information of the second vehicle not being consistent with the first status information of the first vehicle;

determining an accelerator and brake calibration table corresponding to the second vehicle based on the first state information of the second vehicle;

And after the throttle brake calibration table of the second vehicle passes the rationality verification, replacing the throttle brake calibration table of the first vehicle with the throttle brake calibration table of the second vehicle, and loading the throttle brake calibration table of the second vehicle into a memory of the second vehicle.

9. A vehicle control apparatus, the apparatus comprising:

the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is configured to control the operation of a vehicle to be tested by adopting different instruction issuing modes and acquire first state information of the vehicle to be tested in the instruction issuing modes;

a determining unit configured to determine an accelerator brake calibration table corresponding to the vehicle to be tested based on the first state information;

the verification unit is configured to verify the rationality of the data in the accelerator brake calibration table;

and the loading unit is configured to control the throttle and/or the brake of the vehicle to be tested based on the throttle brake calibration table in response to passing of the verification of the rationality of the throttle brake calibration table.

10. The apparatus of claim 9, wherein the acquisition unit is further configured to: in the initial stage of a vehicle to be tested, controlling the vehicle to be tested to run by adopting a manual driving mode or a script issuing mode, and collecting initial information of the vehicle to be tested in the manual driving mode or the script issuing mode; in an automatic driving stage of the vehicle to be tested, controlling the operation of the vehicle to be tested by adopting an automatic driving mode, and collecting the operation information of the vehicle to be tested in the automatic driving mode;

The determination unit is further configured to: based on the initial information, an initial table is obtained; obtaining an operation table based on the operation information; and responding to the mismatching of the initial table and the running table, and covering corresponding data in the initial table by adopting the running table to obtain an accelerator and brake calibration table corresponding to the vehicle to be tested.

11. The apparatus of claim 10, wherein the determining unit is further configured to: discretizing the data in the initial information to obtain initial discrete data;

12. The apparatus of claim 10, wherein the determining unit is further configured to: discretizing the data in the operation information to obtain operation discrete data;

13. The apparatus according to one of claims 9-12, wherein the verification unit is further configured to: fixing the opening value in the accelerator brake calibration table, and calculating a two-dimensional fitting curve under different openings, wherein the two-dimensional fitting curve is used for representing the corresponding relation between the speed and the acceleration under the fixed opening value;

calculating calculated values corresponding to all acceleration values in the accelerator and brake calibration table based on the two-dimensional fitting curve;

determining the mean square error of the accelerator and brake calibration table based on the acceleration values and the calculated values of all opening values in the accelerator and brake calibration table;

14. The apparatus of claim 13, the apparatus further comprising: a first calibration unit;

the first calibration unit is configured to: when the vehicle to be tested is in an automatic driving state, acquiring second state information of the vehicle to be tested in real time;

15. The apparatus of claim 9, wherein the vehicle under test comprises: a plurality of vehicles under the same vehicle type; the acquisition unit is further configured to: randomly selecting a first vehicle of the plurality of vehicles; controlling the first vehicle to run by adopting the manual driving mode or the script issuing mode, and collecting first state information of the first vehicle in the manual driving mode or the script issuing mode;

the loading unit is further configured to: and in response to passing the rationality verification of the throttle brake calibration table of the first vehicle, loading the throttle brake calibration table of the first vehicle into memories of each of the plurality of vehicles respectively so as to control the throttle and/or brake of each of the plurality of vehicles based on the throttle brake calibration table of the first vehicle.

16. The apparatus of claim 15, the apparatus further comprising: a second calibration unit;

the second calibration unit is configured to: controlling operation of a second vehicle in the plurality of vehicles in an autonomous driving mode in response to the third status information of the second vehicle not being consistent with the third status information of the first vehicle; determining an accelerator and brake calibration table corresponding to the second vehicle based on third state information of the second vehicle; and after the throttle brake calibration table of the second vehicle passes the rationality verification, replacing the throttle brake calibration table of the first vehicle with the throttle brake calibration table of the second vehicle, and loading the throttle brake calibration table of the second vehicle into a memory of the second vehicle.

17. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

18. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-8.

19. A computer program product comprising a computer program which, when executed by a processor, implements the method of any of claims 1-8.