Automatic driving longitudinal control accelerator and brake calibration processing method and device

Abstract

The embodiment of the invention provides an automatic driving longitudinal control accelerator and brake calibration processing method and device, and relates to the technical field of automatic driving. The method comprises the following steps: acquiring a first data set of a to-be-tested vehicle under a passive control working condition, and acquiring a second data set of the to-be-tested vehicle under an active control working condition; correcting the acceleration in the second data set according to the first data set; and determining an acceleration calibration result corresponding to pure accelerator brake based on the second data set after acceleration correction. According to the embodiment of the invention, the two-dimensional function solving problem in the existing data calibration process is converted into fitting of a plurality of one-dimensional functions, the experimental scene design of calibration data acquisition and debugging can be simplified, and an accurate calibration result is obtained, so that the accuracy and convenience of accelerator and brake calibration processing are improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and more specifically, to a throttle and brake calibration processing method, device, equipment and storage medium for autonomous driving longitudinal control. Background Art

[0002] With the progress of society, the application demand of autonomous driving is becoming more and more extensive. The realization of autonomous driving requires obtaining the corresponding relationship between the throttle and brake opening and the speed and acceleration. At present, the calibration process of the throttle and brake usually converts the problem to be solved into a two-dimensional nonlinear function, collects test data and fits it according to the reference function to obtain the calibration result. Since there is a certain amount of noise in the collection of test data, especially when the throttle and brake are switched, the fitting surface of the two-dimensional function will be distorted, so accurate calibration data cannot be obtained. In addition, when debugging the longitudinal control of autonomous driving, since the two-dimensional nonlinear function does not have a clear correspondence with the actual driving scene, the debugging and modification process of the calibration data is cumbersome and complicated.

[0003] In summary, there is an urgent need for a solution that can improve the accuracy and convenience of throttle and brake calibration processing. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a throttle and brake calibration processing method, device, equipment and storage medium for autonomous driving longitudinal control, so as to improve the accuracy and convenience of throttle and brake calibration processing.

[0005] In a first aspect, an embodiment of the present application provides a throttle and brake calibration processing method for longitudinal control of an autonomous driving, comprising:

[0006] Acquire a first data set of the vehicle under test under passive control conditions, and acquire a second data set of the vehicle under test under active control conditions; wherein the first data set records different vehicle speeds and their corresponding accelerations, and the second data set records different throttle or brake openings and their corresponding vehicle speeds and accelerations;

[0007] Correcting the acceleration in the second data set according to the first data set;

[0008] The acceleration calibration result corresponding to pure throttle braking is determined based on the second data set after the acceleration correction.

[0009] In an embodiment of the present application, by converting the two-dimensional function solving problem in the existing data calibration process into the fitting of multiple one-dimensional functions, the experimental scenario design for calibration data collection and debugging can be simplified, and accurate calibration results can be obtained, thereby improving the accuracy and convenience of throttle and brake calibration processing.

[0010] In some possible embodiments, the correcting the acceleration in the second data set according to the first data set includes:

[0011] Performing polynomial fitting based on the first data set to obtain a first acceleration fitting function;

[0012] Correcting the acceleration in the second data set based on the first acceleration fitting function;

[0013] The step of determining the acceleration calibration result corresponding to pure throttle braking based on the second data set after the acceleration correction includes:

[0014] A second acceleration fitting function is obtained by performing polynomial fitting based on the second data set after acceleration correction, and an acceleration calibration result corresponding to pure throttle braking is determined based on the second acceleration fitting function.

[0015] In an embodiment of the present application, by performing data fitting on the first data set under passive control conditions, the amount of data used to correct the acceleration in the second data set can be increased. At the same time, by performing polynomial fitting on the second data set, the calibration results of the throttle, brake and acceleration are obtained, thereby further improving the accuracy of the throttle, brake calibration processing.

[0016] In some possible embodiments, the correcting the acceleration in the second data set based on the first acceleration fitting function includes:

[0017] Acquire a set of acceleration correction values ​​corresponding to each vehicle speed in the second data set based on the first acceleration fitting function;

[0018] The acceleration in the second data set is corrected according to the acceleration correction value set.

[0019] In an embodiment of the present application, the acceleration correction value corresponding to each vehicle speed in the second data set is obtained through the first acceleration fitting function to correct the acceleration in the second data set, thereby further improving the accuracy of the throttle and brake calibration processing.

[0020] In some possible embodiments, the first data set further records a first slope data set;

[0021] The performing polynomial fitting based on the first data set to obtain a first acceleration fitting function includes:

[0022] Acquire a first correction value set corresponding to each acceleration in the first data set based on the first slope data set;

[0023] Correcting the acceleration in the first data set according to the first correction value set;

[0024] A first acceleration fitting function is obtained by performing polynomial fitting based on the first acceleration-corrected data set.

[0025] In an embodiment of the present application, the acceleration of the first data set is corrected by collecting slope data, and the corrected first data set is used as the data basis to correct the acceleration of the second data set, thereby further improving the accuracy of the throttle and brake calibration processing.

[0026] In some possible embodiments, the second data set further records a second slope data set;

[0027] Before performing polynomial fitting based on the second data set after the acceleration correction to obtain the second acceleration fitting function, the method further includes:

[0028] A second correction value set corresponding to each acceleration in the second data set is acquired based on the second slope data set, and the acceleration in the second data set is corrected according to the second correction value set.

[0029] In the embodiment of the present application, by collecting slope data to correct the acceleration data of the second data set, the influence of the slope on the data calibration can be eliminated, and the accuracy of the throttle and brake calibration processing can be further improved.

[0030] In some possible embodiments, the passive control operating condition includes at least one of an idle condition and a coasting condition; the idle condition is a condition when the speed of the vehicle to be tested is less than a preset idle speed threshold and the accelerator and brake are not working; the coasting condition is a condition when the speed of the vehicle to be tested is greater than the preset idle speed threshold and the accelerator and brake are not working.

[0031] In an embodiment of the present application, by dividing the passive control conditions into idling and coasting, wherein a preset vehicle speed threshold is used as the basis for dividing the two conditions, the nonlinear factors affecting the throttle and brake calibration data can be further decoupled into a combination of different operating conditions, thereby further improving the accuracy of the throttle and brake calibration processing.

[0032] In some possible embodiments, the active control operating condition includes a slow acceleration and deceleration control operating condition, a comfortable acceleration and deceleration control operating condition, and a sudden acceleration and deceleration control operating condition;

[0033] The slow acceleration and deceleration control condition is a condition in which the acceleration magnitude of the vehicle to be tested is within a preset first acceleration threshold range;

[0034] The comfortable acceleration and deceleration control condition is a condition in which the acceleration magnitude of the vehicle to be tested is within a preset second acceleration threshold range;

[0035] The sudden acceleration and deceleration control condition is a condition in which the acceleration magnitude of the vehicle to be tested is within a preset third acceleration threshold range;

[0036] The maximum value of the first acceleration threshold range is smaller than the minimum value of the second acceleration threshold range, and the maximum value of the second acceleration threshold range is smaller than the minimum value of the third acceleration threshold range.

[0037] In an embodiment of the present application, the active control conditions include different acceleration and deceleration condition data, so that the data collected by the test can cover a wider range of actual driving scenarios, thereby further improving the accuracy of the throttle and brake calibration processing.

[0038] In a second aspect, an embodiment of the present application provides a throttle and brake calibration processing device for longitudinal control of autonomous driving, comprising:

[0039] An acquisition module, used to acquire a first data set of the vehicle under test under passive control conditions, and to acquire a second data set of the vehicle under test under active control conditions; wherein the first data set records different vehicle speeds and their corresponding accelerations, and the second data set records different throttle or brake openings and their corresponding vehicle speeds and accelerations;

[0040] a correction module, configured to correct the acceleration in the second data set according to the first data set;

[0041] The calibration module is used to determine the acceleration calibration result corresponding to the pure throttle braking based on the second data set after the acceleration correction.

[0042] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method described in any embodiment of the first aspect can be implemented.

[0043] In a fourth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a computer program, wherein when the computer program is executed by a processor, the method described in any embodiment of the first aspect can be implemented.

[0044] In a fifth aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the method described in any embodiment of the first aspect when executing the program. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 One of the flowcharts of the throttle and brake calibration processing method for the longitudinal control of the autonomous driving provided in the embodiment of the present application;

[0047] Figure 2 A schematic diagram of a corresponding relationship between acceleration and speed of a vehicle under passive control conditions provided in an embodiment of the present application;

[0048] Figure 3 A schematic diagram of a corresponding relationship between the throttle opening and acceleration of a vehicle provided in an embodiment of the present application;

[0049] Figure 4 A schematic diagram of a corresponding relationship between the vehicle brake opening and acceleration provided in an embodiment of the present application;

[0050] Figure 5 A schematic diagram of data fitting of acceleration and speed of a vehicle under passive control conditions provided in an embodiment of the present application;

[0051] Figure 6 A data fitting diagram of the vehicle throttle opening and acceleration provided in an embodiment of the present application;

[0052] Figure 7 A schematic diagram of data fitting of vehicle brake opening and acceleration provided in an embodiment of the present application;

[0053] Figure 8 A second flowchart of the throttle and brake calibration processing method for the longitudinal control of the autonomous driving provided in the embodiment of the present application;

[0054] Fig. 9 A schematic diagram of the structure of a throttle and brake calibration processing device for longitudinal control of an autonomous driving system provided in an embodiment of the present application;

[0055] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0057] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0058] In the prior art, the accelerator brake calibration process is converted into a two-dimensional nonlinear comparison function for solution:

[0059] cmd=f(v,a)

[0060] Where cmd represents the brake or throttle opening (positive numbers correspond to throttle, negative numbers correspond to brake). Due to the influence of idling and other resistances in actual driving scenarios, this function exhibits strong nonlinearity.

[0061] It is understandable that the data calibration process based on the above-mentioned two-dimensional nonlinear function has the following problems: 1. Due to the large noise in the collection of test data, especially when the accelerator and brake are switched, the fitting surface based on the function will be distorted, so it is impossible to obtain accurate calibration data. 2. Due to the large randomness of manually collected data, the single action (acceleration or braking) is maintained for a short time, and there is a certain delay when the vehicle responds to the accelerator or brake, which makes it impossible to collect accurate steady-state correspondence, further affecting the accuracy of the calibration results. 3. Due to factors such as limited site when collecting data, it is impossible to collect scene data such as emergency braking and rapid acceleration on highways, resulting in inaccurate fitting surface estimation due to incomplete data coverage. 4. During the debugging process of autonomous driving longitudinal control, due to the lack of a clear one-to-one correspondence between calibration data and scene factors, it is impossible to quickly fix the problem of inaccurate calibration.

[0062] In view of the problems existing in the above-mentioned prior art, the embodiment of the present application transforms the problem of solving the two-dimensional function in the existing data calibration process into the fitting of three one-dimensional functions, including:

[0063] a idle =g1(v)

[0064] a throttle =g2(cmd throttle )

[0065] a brake =g3(cmd brake )

[0066] Then the ideal acceleration of the vehicle can be expressed as:

[0067]

[0068] Therefore, the longitudinal command that the automatic driving control should issue is:

[0069]

[0070] Among them, a idle Indicates the acceleration when the accelerator and brake are not working (passive control condition), a throttle Indicates the acceleration corresponding to the throttle operation, a brake Indicates the acceleration corresponding to the braking operation.

[0071] See also Figure 2 Function g1 represents the corresponding relationship between vehicle acceleration at different speeds when the vehicle is in passive control condition (the throttle and brake opening are both 0 or in the dead zone). This function reflects the main nonlinear factors in the longitudinal direction of the vehicle, including the driving force at idle speed and the resistance at different speeds.

[0072] Figure 3 and Figure 4 They are curve graphs corresponding to functions g2 and g3, respectively, which represent the acceleration values ​​corresponding to the throttle and brake torques (expressed as throttle or brake opening percentages) provided by the vehicle at a certain speed.

[0073] like Figure 1 As shown, the embodiment of the present application provides a throttle and brake calibration processing method for longitudinal control of autonomous driving, which may include the steps of:

[0074] S1. Obtain a first data set of the vehicle under test under passive control conditions, and obtain a second data set of the vehicle under test under active control conditions; wherein the first data set records different vehicle speeds and their corresponding accelerations, and the second data set records different throttle or brake openings and their corresponding vehicle speeds and accelerations.

[0075] It should be noted that the vehicle to be tested is first controlled to run under different working conditions, and the data of this process is collected through the data acquisition device. Data collection can be performed based on a certain collection frequency, for example, a set of data is collected every second; for data collected under passive control conditions, each set of data includes at least vehicle speed (in m / s) and acceleration (in m / s 2 , positive numbers represent acceleration, negative numbers represent deceleration).

[0076] For the data collected under active control conditions, each set of data includes at least vehicle speed, acceleration, and throttle and brake opening (positive numbers represent throttle, negative numbers represent brakes); after a certain period of data collection, data sets under different working conditions are obtained, including a first data set of the vehicle to be tested under passive control conditions and a second data set of the vehicle to be tested under active control conditions.

[0077] It can be understood that the operating conditions of the vehicle to be tested include two categories: passive control conditions and active control conditions. Passive control conditions refer to operating conditions when the accelerator and brake are not working, such as idling and coasting conditions. Active control conditions are operating conditions controlled by the accelerator or brake.

[0078] S2. Correct the acceleration in the second data set according to the first data set.

[0079] It should be noted that each vehicle speed value recorded in the first data set has one and only one corresponding acceleration, which is the acceleration generated by the engine idling or other resistance when the accelerator brake is not executed. Therefore, the acceleration in the second data set can be corrected according to the acceleration value to eliminate the influence of nonlinear factors on the acceleration corresponding to the accelerator brake, thereby obtaining the acceleration generated by pure accelerator brake.

[0080] It is understandable that, since the second data set records different throttle or brake openings and their corresponding vehicle speeds and accelerations, the first data set and the second data set have a common reference data of vehicle speed, so that the first data set and the second data set can be matched and corrected based on the vehicle speed. For example, the first data set records the array (1m / s, +0.2m / s 2 ), which represents the +0.2m / s when the vehicle is not accelerator-braking and the speed is 1m / s 2 Acceleration, then for all arrays with a speed of 1 m / s in the second data set, this 0.2 m / s needs to be eliminated 2 The acceleration after correction can be considered as the acceleration generated by pure accelerator braking.

[0081] S3. Determine an acceleration calibration result corresponding to pure throttle braking based on the second data set after acceleration correction.

[0082] It should be noted that after the acceleration of the second data set is corrected (the vehicle speed data in each array can be omitted at this time), multiple sets of data with different throttle or brake openings and corresponding accelerations can be obtained. This data set represents the acceleration generated purely by throttle and brake. According to the second data set after the acceleration correction, the acceleration calibration result corresponding to pure throttle and brake can be obtained by polynomial fitting or interpolation.

[0083] It is understandable that in the subsequent autonomous driving longitudinal control processing, based on the acceleration calibration results corresponding to the pure throttle brake, the acceleration generated by other factors can be superimposed and considered in combination with the actual driving scenario to obtain accurate longitudinal control instructions.

[0084] Based on this, by converting the two-dimensional function solving problem in the existing data calibration process into the fitting of multiple one-dimensional functions, the experimental scenario design for calibration data collection and debugging can be simplified. By designing simple driving scenarios for data collection, the calibration data covering all scenarios can be inferred, thereby improving the accuracy and convenience of throttle and brake calibration processing.

[0085] In some possible embodiments, step S2 may include:

[0086] Performing polynomial fitting based on the first data set to obtain a first acceleration fitting function;

[0087] Correcting the acceleration in the second data set based on the first acceleration fitting function;

[0088] Step S3 may include:

[0089] A second acceleration fitting function is obtained by performing polynomial fitting based on the second data set after acceleration correction, and an acceleration calibration result corresponding to pure throttle braking is determined based on the second acceleration fitting function.

[0090] It should be noted that, when correcting the acceleration in the second data set, a polynomial fitting is first performed on the first data set, so that the discrete first data set can be converted into a continuous curve. Based on the obtained first acceleration fitting function, the acceleration correction value corresponding to any vehicle speed can be obtained within the value range to correct the acceleration in the second data set.

[0091] See also Figure 5 As an example, the dots in the figure represent the first data set collected under the passive control condition, and the curve in the figure represents the curve corresponding to the first acceleration fitting function obtained by fitting the first data set.

[0092] In addition, since the collected data is collected based on a certain frequency, the arrays in the second data set are discrete. Based on these discrete arrays, the corresponding fitting curves can be obtained by polynomial fitting and other methods. Based on this, the acceleration corresponding to any pure throttle brake can be obtained according to the fitting curve.

[0093] See also Figure 6 and Figure 7 , as an example, Figure 6 This is a schematic diagram of data fitting corresponding to the execution of the throttle, where the part with acceleration less than 0 represents the corresponding scene when reversing; Figure 7 This is a schematic diagram of data fitting corresponding to braking, where the part with acceleration greater than 0 represents the corresponding scene when reversing. Figure 6 and Figure 7In FIG. 1 , the dots represent the second data set after acceleration correction, and the curve represents the curve corresponding to the second acceleration fitting function.

[0094] In some possible embodiments, correcting the acceleration in the second data set based on the first acceleration fitting function includes:

[0095] Acquire a set of acceleration correction values ​​corresponding to each vehicle speed in the second data set based on the first acceleration fitting function;

[0096] The acceleration in the second data set is corrected according to the acceleration correction value set.

[0097] It should be noted that, since the second data set itself is recorded at a certain acquisition frequency, an acceleration correction value can be obtained corresponding to each array in the second data set. As for the first data set, the same vehicle speed has a unique corresponding acceleration, so the acceleration correction value corresponding to each vehicle speed in the second data set can be obtained to achieve correction of all accelerations in the second data set.

[0098] In some possible embodiments, the first data set further records a first slope data set;

[0099] Performing polynomial fitting based on the first data set to obtain a first acceleration fitting function may include:

[0100] Acquire a first correction value set corresponding to each acceleration in the first data set based on the first slope data set;

[0101] Correcting the acceleration in the first data set according to the first correction value set;

[0102] A first acceleration fitting function is obtained by performing polynomial fitting based on the first acceleration-corrected data set.

[0103] Optionally, when collecting data of different operating conditions, a relatively straight road with a relatively flat slope can be selected to minimize the influence of other factors such as slope and curvature. In actual operation, the slope data can also be recorded in real time during the data collection process.

[0104] It is understandable that the known slope and vehicle mass can be converted into the acceleration corresponding to the slope according to the force analysis. For each set of vehicle speed-acceleration data in the first data set, the corresponding acceleration correction value can be obtained according to the slope data, and the corresponding acceleration can be corrected to eliminate the influence of the slope on the acceleration data.

[0105] In some possible embodiments, the second data set further records a second slope data set;

[0106] Before performing polynomial fitting based on the second data set after acceleration correction to obtain a second acceleration fitting function, the method further includes:

[0107] A second correction value set corresponding to each acceleration in the second data set is acquired based on the second slope data set, and the acceleration in the second data set is corrected according to the second correction value set.

[0108] Optionally, the corresponding slope data can also be recorded synchronously during the process of collecting the second data set. Similar to the above-mentioned elimination of the acceleration generated by the slope in the first data set, based on the synchronously collected second slope data set, the correction value corresponding to each acceleration in the second data set can also be obtained for correcting the corresponding acceleration.

[0109] Based on this, by eliminating the acceleration caused by the slope during the collection of the first data set and the second data set, more accurate acceleration data generated by pure throttle braking can be obtained.

[0110] In some possible embodiments, the passive control operating condition includes at least one of an idle condition and a coasting condition; the idle condition is a condition when the speed of the vehicle to be tested is less than a preset idle speed threshold and the accelerator and brake are not working; the coasting condition is a condition when the speed of the vehicle to be tested is greater than a preset idle speed threshold and the accelerator and brake are not working.

[0111] It should be noted that for gasoline vehicles, even if the throttle is not operated, the vehicle will be driven by the engine idling. Starting from rest, the vehicle will generate acceleration under the engine idling drive until it reaches the idle speed and then travels at a constant speed (without other resistance factors), at which time the vehicle acceleration is zero. It is understandable that since electric vehicles do not have the idle drive driving condition, it is not necessary to collect data under the idle condition for the data calibration of electric vehicles.

[0112] In the embodiment of the present application, the idle condition refers to the operating condition of the vehicle from stationary to idling without accelerator braking. The coasting condition refers to the operating condition of the vehicle from a certain speed (such as stepping on the accelerator in advance to increase the speed to 60km / h) to idling speed under the influence of air resistance, ground or mechanical friction and other factors (the slope effect is not considered here) without accelerator braking.

[0113] It is understandable that, for a reversing driving situation, the adaptation of the reversing control can be achieved by collecting the data during reversing and using the same data calibration method as the above embodiment.

[0114] Based on this, the accuracy of the throttle brake calibration process is further improved by further decoupling the nonlinear factors that affect the throttle brake calibration data into different operating conditions.

[0115] In some possible embodiments, the active control operating conditions include a slow acceleration and deceleration control operating condition, a comfortable acceleration and deceleration control operating condition, and a sudden acceleration and deceleration control operating condition;

[0116] The slow acceleration and deceleration control condition is a condition in which the acceleration magnitude of the vehicle to be tested is within a preset first acceleration threshold range;

[0117] The comfortable acceleration and deceleration control condition is a condition in which the acceleration magnitude of the vehicle to be tested is within a preset second acceleration threshold range;

[0118] The sudden acceleration and deceleration control condition is a condition in which the acceleration magnitude of the vehicle to be tested is within a preset third acceleration threshold range;

[0119] The maximum value of the first acceleration threshold range is smaller than the minimum value of the second acceleration threshold range, and the maximum value of the second acceleration threshold range is smaller than the minimum value of the third acceleration threshold range.

[0120] It should be noted that in order to further improve the accuracy of data calibration, active control conditions when collecting data may include slow acceleration and deceleration control, comfortable acceleration and deceleration control, and violent acceleration and deceleration control. Among them, for slow acceleration and deceleration control conditions, the tester can lightly step on the accelerator pedal or brake pedal to slowly accelerate or decelerate when driving the vehicle to be tested, for example, to control the vehicle to generate ±0.5~1m / s 2 The acceleration is maintained for a certain period of time, such as 5s; when collecting data, if the acceleration of the vehicle to be tested is within the preset first acceleration threshold range (0.5-1m / s 2 ), these data are classified as data of slow acceleration and deceleration control conditions.

[0121] Similarly, for comfortable acceleration and deceleration control conditions, when collecting data, if the acceleration of the vehicle to be tested is within the preset second acceleration threshold range (for example, 1 to 1.5 m / s 2 ), the data are classified as data of comfortable acceleration and deceleration control conditions; similarly, for the violent acceleration and deceleration control condition, when collecting data, if it is judged that the acceleration of the vehicle to be tested is within the preset third acceleration threshold range (for example, greater than 3m / s 2 ), these data are classified as data of sudden acceleration and deceleration control conditions.

[0122] See also Figure 8 , as an example, Figure 8 This is a flow chart of a throttle and brake calibration processing method for autonomous driving longitudinal control provided by an embodiment of the present application, which can be implemented by the following steps:

[0123] 1. Use the calibration tool to set the calibration mode: idle, coasting, acceleration, braking; and set the calibration properties: throttle dead zone = 0, brake dead zone = 0, calibration method = "coasting condition", etc.

[0124] 2. Read key parameters of the vehicle, including response delay, dead zone, speed range, whether to reverse, etc.;

[0125] 3. Collect and process vehicle data, including vehicle speed, acceleration, ramp data, throttle percentage, brake percentage, etc.;

[0126] 4. Circularly acquire data and calibrate VA data for idle and coasting conditions;

[0127] 5. After completing the VA data calibration of the idle and coasting conditions, cyclically obtain the data of the acceleration and deceleration control conditions (the data must meet the set requirements, such as the acceleration is within the set threshold range), calibrate the data for the acceleration and deceleration conditions respectively, and finally obtain the acceleration calibration results corresponding to the throttle and brake and export the results.

[0128] Please refer to Fig. 9 , Fig. 9 The block diagram of the throttle and brake calibration processing device for the longitudinal control of the automatic driving provided by some embodiments of the present application is shown. It should be understood that the throttle and brake calibration processing device for the longitudinal control of the automatic driving is similar to the above Figure 1 Corresponding to the method embodiment, it is able to execute each step involved in the above method embodiment. The specific functions of the throttle and brake calibration processing device for autonomous driving longitudinal control can be found in the description above. To avoid repetition, the detailed description is appropriately omitted here.

[0129] Fig. 9 The throttle brake calibration processing device for the longitudinal control of the automatic driving includes at least one software function module that can be stored in the memory in the form of software or firmware or solidified in the throttle brake calibration processing device for the longitudinal control of the automatic driving, and the throttle brake calibration processing device for the longitudinal control of the automatic driving includes:

[0130] The acquisition module 910 is used to acquire a first data set of the vehicle under test under passive control conditions, and to acquire a second data set of the vehicle under test under active control conditions; wherein the first data set records different vehicle speeds and their corresponding accelerations, and the second data set records different throttle or brake openings and their corresponding vehicle speeds and accelerations;

[0131] A correction module 920, configured to correct the acceleration in the second data set according to the first data set;

[0132] The calibration module 930 is used to determine the acceleration calibration result corresponding to the pure throttle braking based on the second data set after the acceleration correction.

[0133] It can be understood that the above-mentioned device item embodiment corresponds to the method item embodiment of the present invention. The throttle and brake calibration processing device for autonomous driving longitudinal control provided by the embodiment of the present invention can implement the throttle and brake calibration processing method for autonomous driving longitudinal control provided by any method item embodiment of the present invention.

[0134] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method, and will not be described in detail here.

[0135] like Fig.10 As shown, some embodiments of the present application provide an electronic device 1000, which includes: a memory 1010, a processor 1020, and a computer program stored in the memory 1010 and executable on the processor 1020, wherein the processor 1020 reads the program from the memory 1010 through a bus 1030 and executes the program to implement a method of any embodiment included in the throttle and brake calibration processing method for autonomous driving longitudinal control as described above.

[0136] Processor 1020 can process digital signals and can include various computing structures, such as complex instruction set computer structure, reduced instruction set computer structure, or a structure that implements a combination of multiple instruction sets. In some examples, processor 1020 can be a microprocessor.

[0137] The memory 1010 may be used to store instructions executed by the processor 1020 or data related to the execution of instructions. These instructions and / or data may include codes for implementing some or all functions of one or more modules described in the embodiments of the present application. The processor 1020 of the disclosed embodiment may be used to execute instructions in the memory 1010 to implement the method shown above. The memory 1010 includes a dynamic random access memory, a static random access memory, a flash memory, an optical memory, or other memory known to those skilled in the art.

[0138] Some embodiments of the present application further provide a computer-readable storage medium having a computer program stored thereon. The computer program is executed by a processor to execute the method described in the method embodiment.

[0139] Some embodiments of the present application further provide a computer program product, which, when executed on a computer, enables the computer to execute the method described in the method embodiment.

[0140] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0141] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0142] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0143] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0144] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0145] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0146] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A throttle and brake calibration processing method for autonomous driving longitudinal control, characterized in that: include: Acquire a first data set of the vehicle under test under passive control conditions, and acquire a second data set of the vehicle under test under active control conditions; wherein the first data set records different vehicle speeds and their corresponding accelerations, and the second data set records different throttle or brake openings and their corresponding vehicle speeds and accelerations; Correcting the acceleration in the second data set according to the first data set; The acceleration calibration result corresponding to pure throttle braking is determined based on the second data set after the acceleration correction.

2. The throttle and brake calibration processing method for autonomous driving longitudinal control according to claim 1 is characterized in that: The correcting the acceleration in the second data set according to the first data set includes: Performing polynomial fitting based on the first data set to obtain a first acceleration fitting function; Correcting the acceleration in the second data set based on the first acceleration fitting function; The step of determining the acceleration calibration result corresponding to pure throttle braking based on the second data set after the acceleration correction includes: A second acceleration fitting function is obtained by performing polynomial fitting based on the second data set after acceleration correction, and an acceleration calibration result corresponding to pure throttle braking is determined based on the second acceleration fitting function.

3. The throttle and brake calibration processing method for automatic driving longitudinal control according to claim 2 is characterized in that: The correcting the acceleration in the second data set based on the first acceleration fitting function includes: Acquire a set of acceleration correction values ​​corresponding to each vehicle speed in the second data set based on the first acceleration fitting function; The acceleration in the second data set is corrected according to the acceleration correction value set.

4. The throttle and brake calibration processing method for automatic driving longitudinal control according to claim 2 is characterized in that: The first data set also records a first slope data set; The performing polynomial fitting based on the first data set to obtain a first acceleration fitting function includes: Acquire a first correction value set corresponding to each acceleration in the first data set based on the first slope data set; Correcting the acceleration in the first data set according to the first correction value set; A first acceleration fitting function is obtained by performing polynomial fitting based on the first acceleration-corrected data set.

5. The throttle and brake calibration processing method for automatic driving longitudinal control according to claim 2 is characterized in that: The second data set also records a second slope data set; Before performing polynomial fitting based on the second data set after the acceleration correction to obtain the second acceleration fitting function, the method further includes: A second correction value set corresponding to each acceleration in the second data set is acquired based on the second slope data set, and the acceleration in the second data set is corrected according to the second correction value set.

6. The throttle and brake calibration processing method for autonomous driving longitudinal control according to claim 1, characterized in that: The passive control operating condition includes at least one of an idle condition and a coasting condition; the idle condition is a condition when the speed of the vehicle to be tested is less than a preset idle speed threshold and the accelerator and brake are not working; the coasting condition is a condition when the speed of the vehicle to be tested is greater than the preset idle speed threshold and the accelerator and brake are not working.

7. The throttle and brake calibration processing method for autonomous driving longitudinal control according to claim 1, characterized in that: The active control conditions include slow acceleration and deceleration control conditions, comfortable acceleration and deceleration control conditions, and sudden acceleration and deceleration control conditions; The slow acceleration and deceleration control condition is a condition in which the acceleration magnitude of the vehicle to be tested is within a preset first acceleration threshold range; The comfortable acceleration and deceleration control condition is a condition in which the acceleration magnitude of the vehicle to be tested is within a preset second acceleration threshold range; The sudden acceleration and deceleration control condition is a condition in which the acceleration magnitude of the vehicle to be tested is within a preset third acceleration threshold range; The maximum value of the first acceleration threshold range is smaller than the minimum value of the second acceleration threshold range, and the maximum value of the second acceleration threshold range is smaller than the minimum value of the third acceleration threshold range.

8. A throttle and brake calibration processing device for autonomous driving longitudinal control, characterized in that: include: An acquisition module, used to acquire a first data set of the vehicle under test under passive control conditions, and to acquire a second data set of the vehicle under test under active control conditions; wherein the first data set records different vehicle speeds and their corresponding accelerations, and the second data set records different throttle or brake openings and their corresponding vehicle speeds and accelerations; a correction module, configured to correct the acceleration in the second data set according to the first data set; The calibration module is used to determine the acceleration calibration result corresponding to the pure throttle braking based on the second data set after the acceleration correction.

9. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the throttle and brake calibration processing method for autonomous driving longitudinal control as described in any one of claims 1-7 can be implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the throttle and brake calibration processing method for autonomous driving longitudinal control as described in any one of claims 1-7 is executed.

Images