Calibration data updating method and device, equipment and storage medium

Abstract

The invention provides a calibration data updating method and device, equipment and a storage medium, and relates to the field of automatic driving. The method comprises the following steps: acquiring target self-vehicle data of the autonomous vehicle and standard calibration data of the autonomous vehicle, wherein the target self-vehicle data comprises acceleration and a speed control part opening degree which have a corresponding relation; a first opening degree corresponding to a first acceleration in the target vehicle data is compared with a second opening degree corresponding to a second acceleration in the standard calibration data, and the first acceleration is the same as the second acceleration; and if the first opening degree is greater than the second opening degree, updating the second opening degree to the first opening degree to obtain updated standard calibration data. According to the method, the standard calibration data is updated online through the vehicle data of the vehicle end, and the automatic driving performance of the vehicle can be improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a calibration data updating method, a calibration data updating device, a computer device, and a readable storage medium. Background Art

[0002] At present, the accelerator and brake calibration experiments are only conducted on a certain vehicle of a certain model, and the calibration data is used as the standard calibration data. However, due to mechanical wear and vehicle aging during use, the calibration data may gradually become inaccurate, seriously affecting the performance of autonomous driving and endangering driving safety.

[0003] Re-calibrating the accelerator and brakes requires recalling all vehicles, consuming a large amount of resources; the OTA (Over-the-Air Technology) method after offline calibration requires reliance on a large amount of server resources and has a slow update cycle. Summary of the invention

[0004] In view of this, the present application provides a calibration data updating method, a calibration data updating device, a computer device and a readable storage medium, which improve the updating speed and accuracy of the calibration data.

[0005] In a first aspect, an embodiment of the present application provides a method for updating calibration data, which is applied to an autonomous driving vehicle, and the method includes:

[0006] Obtaining target self-vehicle data of the autonomous driving vehicle and standard calibration data of the autonomous driving vehicle, wherein the target self-vehicle data includes acceleration and speed control component opening and closing degrees having corresponding relationships;

[0007] Comparing a first opening degree corresponding to a first acceleration in the target vehicle data with a second opening degree corresponding to a second acceleration in the standard calibration data, wherein the first acceleration is the same as the second acceleration;

[0008] If the first opening and closing degree is greater than the second opening and closing degree, the second opening and closing degree is updated to the first opening and closing degree to obtain updated standard calibration data.

[0009] In this embodiment, a large amount of target self-vehicle data of the autonomous driving vehicle itself is collected, and the target self-vehicle data corresponds to the actual opening and closing degree of the vehicle's speed control components at different speeds and accelerations, and the standard calibration data stored on the autonomous driving vehicle is obtained.

[0010] Compare the first opening and closing degree corresponding to the first acceleration in the target vehicle data with the second opening and closing degree corresponding to the second acceleration in the standard calibration data. Due to mechanical wear, vehicle aging and other reasons, at the same acceleration and speed, the actual throttle and brake opening and closing degree will definitely be larger than the standard throttle and brake opening and closing degree in the standard calibration data. Therefore, if the first opening and closing degree is larger than the second opening and closing degree, the second opening and closing degree is replaced with the first opening and closing degree to achieve the success of the standard calibration data. After the update is successful, the standard calibration data is stored back in the configuration file of the autonomous driving vehicle.

[0011] It is worth noting that the embodiment of the present application is an online update performed on the vehicle side, without the need for transmission to a cloud server. In this way, as the vehicle travels, more data on the standard calibration data can be updated, so that the standard calibration data gradually tends to the actual pedal opening and closing situation.

[0012] In the embodiment of the present application, the standard calibration data is updated online through the vehicle-side self-vehicle data, so that the standard calibration data can be more accurate, thereby improving the vehicle's autonomous driving performance. Compared with the method of re-calibrating the throttle and brakes for each vehicle, it has higher efficiency, lower cost, and does not need to rely on cloud server resources, which improves the update speed.

[0013] According to the above method of the embodiment of the present application, the following additional technical features may also be provided:

[0014] In the above technical solution, optionally, the target self-vehicle data also includes a speed having a corresponding relationship with the acceleration and the opening and closing degree of the speed control component; the first opening and closing degree corresponding to the first acceleration in the target self-vehicle data is compared with the second opening and closing degree corresponding to the second acceleration in the standard calibration data, including: dividing the speed into multiple speed intervals, and determining multiple accelerations corresponding to each speed interval and multiple opening and closing degrees of the speed control component corresponding to each acceleration; comparing the first opening and closing degree within the target speed interval among the multiple speed intervals with the second opening and closing degree in the standard calibration data, and the speed interval corresponding to the second opening and closing degree is the same as the target speed interval.

[0015] In this embodiment, the target vehicle data is the actual opening and closing degree of the speed control component of the vehicle at different speeds and accelerations. Since the calibration data is weakly correlated with the speed, the speed is first segmented, that is, the speed is divided into multiple speed intervals, and then the acceleration and opening and closing degree of the speed control component corresponding to each speed interval are determined. It should be noted that one speed interval corresponds to multiple accelerations, and each acceleration corresponds to multiple opening and closing degrees of the speed control component.

[0016] Then, the first opening and closing degree in any target speed interval among the multiple speed intervals is compared with the second opening and closing degree in the standard calibration data, wherein the standard calibration data is also a table after speed decoupling, and the speed interval corresponding to the second opening and closing degree is the same as the target speed interval.

[0017] In the embodiment of the present application, speed decoupling is performed to make the subsequent comparison process simpler.

[0018] In any of the above technical solutions, optionally, before comparing the first opening and closing degree within a target speed range among multiple speed ranges with the second opening and closing degree in the standard calibration data, it includes: calculating the average value of the opening and closing degrees of multiple speed control components corresponding to each acceleration in the target speed range, wherein the first opening and closing degree is the average value of the opening and closing degrees of multiple speed control components corresponding to the first acceleration.

[0019] In this embodiment, each acceleration corresponds to a sequence of opening and closing degrees of the speed control components, and it is necessary to calculate the average value of the opening and closing degrees of these multiple speed control components so that each acceleration corresponds to an average value, which is convenient for subsequent comparison with standard calibration data.

[0020] For example, the first acceleration corresponds to the opening and closing degrees of multiple speed control components, and the average value of the opening and closing degrees of the multiple speed control components is calculated to obtain the first opening and closing degree, and then the first opening and closing degree is compared with the second opening and closing degree in the standard calibration data.

[0021] In any of the above technical solutions, optionally, before calculating the average value of the opening and closing degrees of multiple speed control components corresponding to each acceleration in the target speed range, it also includes: performing acceleration clustering processing on the multiple accelerations in the target speed range to obtain the acceleration after clustering processing; calculating the average value of the opening and closing degrees of multiple speed control components corresponding to each acceleration in the target speed range, including: calculating the average value of the opening and closing degrees of multiple speed control components corresponding to each acceleration after clustering processing in the target speed range.

[0022] In this embodiment, before calculating the average value of the opening and closing degrees of multiple speed control components corresponding to each acceleration in the target speed interval, acceleration clustering is performed first, for example, other accelerations adjacent to an acceleration of a certain value are clustered with the acceleration.

[0023] The reason for clustering accelerations is that when conducting throttle and brake calibration experiments, multiple standard accelerations are marked. If clustering is performed based on these accelerations, the difference between the opening and closing degrees of the standard speed control components under each acceleration and the opening and closing degrees of the actual speed control components under the corresponding actual acceleration can be easily calculated.

[0024] In any of the above technical solutions, optionally, the target self-vehicle data is the target self-vehicle data acquired multiple times, and the target self-vehicle data includes multiple first accelerations; the first opening and closing degree corresponding to the first acceleration in the target self-vehicle data is compared with the second opening and closing degree corresponding to the second acceleration in the standard calibration data, including: comparing the first opening and closing degree corresponding to each first acceleration with the second opening and closing degree respectively, and counting the number of first opening and closing degrees greater than the second opening and closing degree; updating the second opening and closing degree to the first opening and closing degree, including: if the number is greater than a first preset threshold, updating the second opening and closing degree to the average opening and closing degree of multiple first opening and closing degrees.

[0025] In this embodiment, the target self-vehicle data is target self-vehicle data acquired multiple times, and the target self-vehicle data includes multiple first accelerations, and the values ​​of the multiple first accelerations are the same, and the difference is that they are self-vehicle data collected at different times.

[0026] The first opening degree corresponding to each first acceleration is compared with the second opening degree corresponding to the second acceleration, and the number of first opening degrees greater than the second opening degree is counted. If the number of first opening degrees greater than the second opening degree is greater than a first preset threshold, indicating that the opening degrees of the speed control component collected multiple times on the first acceleration are greater than the second opening degree in the standard table, the second opening degree in the standard calibration data is updated to the average opening degree of multiple first opening degrees.

[0027] Through the above method, the opening and closing degrees of the speed control components collected multiple times on one acceleration are all greater than the opening and closing degrees in the standard table, and then the update is performed, thereby improving the reliability.

[0028] In any of the above technical solutions, optionally, obtaining target self-vehicle data of the autonomous driving vehicle includes: using a sliding window to obtain self-vehicle data from the autonomous driving vehicle within a preset time period, and using the self-vehicle data stored in the sliding window as the target self-vehicle data.

[0029] In this embodiment, the sliding window is a stack that stores historical data. For example, the sliding window records the first 100 frames of data starting from the current time. Each cycle runs for 0.02 seconds, so the sliding window is equivalent to storing all data in the past 2 seconds.

[0030] The sliding window is used to store more frames of ego vehicle data of the autonomous driving vehicle offline, which facilitates the screening of target ego vehicle data.

[0031] In any of the above technical solutions, optionally, before storing the vehicle data into the sliding window in the order of acquisition time, it also includes: filtering out manual driving data in the vehicle data.

[0032] In this embodiment, the own vehicle data is first screened, because the own vehicle data includes two states: manual driving data and automatic driving data, and the standard calibration data needs to be updated through the automatic driving data later. Therefore, in order to avoid the influence of manual driving data on the update, the manual driving data in the own vehicle data is filtered out and the automatic driving data in the own vehicle data is retained.

[0033] In any of the above technical solutions, optionally, the self-vehicle data stored in the sliding window is used as the target self-vehicle data, including: determining whether the self-vehicle data within a preset time period stored in the sliding window is steady-state data; if the self-vehicle data is steady-state data, using the self-vehicle data as the target self-vehicle data.

[0034] In any of the above technical solutions, optionally, a method for determining steady-state data is defined. Specifically, determining whether the vehicle data within a preset time period stored in the sliding window is steady-state data includes: constructing a linear fitting function of the acceleration and the opening and closing degree of the speed control component based on the stored vehicle data acquired before the preset time period; calculating the minimum square error between the vehicle data within the preset time period and the linear fitting function; if the minimum square error is less than or equal to a second preset threshold, determining that the vehicle data within the preset time period is steady-state data.

[0035] In this embodiment, the state of the vehicle data stored in the sliding window is judged, and the steady state refers to a state in which the corresponding relationship between the acceleration and the opening and closing degree of the speed control component reaches an approximately linear state.

[0036] When the vehicle data is steady-state data, it indicates that it is data generated when the vehicle is already running stably. In this state, it is easier to find the corresponding rules between the opening and closing degrees of the acceleration and speed control components, and the corresponding rules are more reliable.

[0037] When it is determined that the ego vehicle data in the sliding window have reached a steady state, these data are the target ego vehicle data. By using the target ego vehicle data to update the standard calibration data, the accuracy of the standard calibration data update is improved.

[0038] In a second aspect, an embodiment of the present application provides a calibration data updating device, including:

[0039] A data acquisition module, used to acquire target vehicle data of the autonomous driving vehicle and standard calibration data of the autonomous driving vehicle, wherein the target vehicle data includes acceleration and speed control component opening and closing degrees having corresponding relationships;

[0040] A comparison module, used for comparing a first opening degree corresponding to a first acceleration in the target vehicle data with a second opening degree corresponding to a second acceleration in the standard calibration data, wherein the first acceleration is the same as the second acceleration;

[0041] The updating module is used for updating the second opening degree to the first opening degree if the first opening degree is greater than the second opening degree, so as to obtain updated standard calibration data.

[0042] In the embodiment of the present application, the standard calibration data is updated online through the vehicle-side self-vehicle data, so that the standard calibration data can be more accurate, thereby improving the vehicle's autonomous driving performance. Compared with the method of re-calibrating the throttle and brakes for each vehicle, it has higher efficiency, lower cost, and does not need to rely on cloud server resources, which improves the update speed.

[0043] In a third aspect, an embodiment of the present application provides a computer device, which includes a processor and a memory, wherein the memory stores programs or instructions that can be executed on the processor, and when the programs or instructions are executed by the processor, the steps of the method of the first aspect are implemented.

[0044] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method of the first aspect are implemented.

[0045] In a fifth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface, wherein the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the method of the first aspect.

[0046] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the method of the first aspect.

[0047] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0049] Figure 1 A schematic diagram showing a flow chart of a method for updating calibration data according to an embodiment of the present application;

[0050] Figure 2 A schematic diagram showing vehicle data according to an embodiment of the present application is shown;

[0051] Figure 3 A schematic diagram showing the state of vehicle data according to an embodiment of the present application is shown;

[0052] Figure 4 A schematic diagram showing two-dimensional calibration data corresponding to a speed range of 0 to 10 mps according to an embodiment of the present application is shown;

[0053] Figure 5 A schematic diagram showing the evaluation of the speed range of 0 to 10 mps in an embodiment of the present application is shown;

[0054] Figure 6 A structural block diagram of a calibration data updating device according to an embodiment of the present application is shown;

[0055] Figure 7 A structural block diagram of a computer device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0057] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0058] The following, in conjunction with the accompanying drawings, describes in detail the calibration data updating method, calibration data updating device, computer equipment and readable storage medium provided in the embodiments of the present application through specific embodiments and their application scenarios.

[0059] The present application embodiment provides a method for updating calibration data, such as Figure 1 As shown, the method includes:

[0060] Step 101, obtaining target vehicle data of the autonomous driving vehicle and standard calibration data of the autonomous driving vehicle, wherein the target vehicle data includes acceleration and speed control component opening and closing degrees having corresponding relationships.

[0061] In this step, a large amount of self-driving vehicle data is collected, that is, vehicle return data, such as Figure 2As shown, the actual speed control component opening and closing degree of the vehicle corresponding to the self-driving vehicle data at different speeds and accelerations, wherein the X coordinate is the speed, the Y coordinate is the acceleration, and the Z coordinate is the speed control component opening and closing degree, and the speed control component refers to the accelerator brake pedal, or the accelerator brake pedal. And, obtain the standard calibration data stored on the autonomous driving vehicle, the standard calibration data refers to the acceleration brake calibration data, or the accelerator brake calibration data.

[0062] After collecting a large amount of self-driving data, the self-driving data is first screened because the self-driving data includes two states: manual driving data and automatic driving data. The standard calibration data will be updated through automatic driving data later. Therefore, in order to avoid the influence of manual driving data on the update, the manual driving data in the self-driving data is filtered out and the automatic driving data in the self-driving data is retained.

[0063] After the initial screening, the vehicle data is stored in the sliding window in the order of acquisition time, so that the sliding window stores the vehicle data within the preset time period. The sliding window is a stack that stores historical data. For example, the sliding window records the first 100 frames of data starting from the current time, and each cycle runs for 0.02 seconds, so the sliding window is equivalent to saving all the data in the past 2 seconds.

[0064] The sliding window is used to store more frames of ego vehicle data of the autonomous driving vehicle, which facilitates the subsequent steady-state screening of the target ego vehicle data.

[0065] Furthermore, it is determined whether the vehicle data stored in the sliding window within the preset time period is steady-state data. Steady state means that the corresponding relationship between acceleration and the opening and closing degree of the speed control component reaches an approximately linear state. When the vehicle data is steady-state data, it indicates that it is data generated when the vehicle is already running stably, and the corresponding relationship between acceleration and the opening and closing degree of the speed control component reaches an approximately linear state. In this state, it is easier to find the corresponding law between acceleration and the opening and closing degree of the speed control component, and the corresponding law is more reliable. It is difficult to find the corresponding law between acceleration and the opening and closing degree of the speed control component for non-steady-state data, so the non-steady-state data is deleted.

[0066] When it is determined that the ego vehicle data in the sliding window have reached a steady state, these data are the target ego vehicle data. By using the target ego vehicle data to update the standard calibration data, the accuracy of the standard calibration data is improved.

[0067] It should be noted that the method of the embodiment of the present application is more suitable for scenarios where the vehicle can operate stably, such as high-speed scenarios.

[0068] In one embodiment of the present application, a method for determining steady-state data is defined. Specifically, the preset time period includes multiple sub-time periods; determining whether the vehicle data within the preset time period stored in the sliding window is steady-state data includes: if the absolute value of the change in the opening and closing degree of the speed control component within each sub-time period is less than or equal to a third preset threshold, then determining that the vehicle data within the preset time period is steady-state data.

[0069] In this embodiment, the absolute value of the change in the opening and closing degree of the speed control component in each sub-time period of the preset time period is less than or equal to the third preset threshold, indicating that the change fluctuation of the opening and closing degree of the speed control component in the preset time period is small, and the vehicle data in the preset time period is determined to be steady-state data.

[0070] like Figure 3 As shown, the interval from 0 to a1 is screened to be a state with large up and down fluctuations, and the interval from a1 to a2 is a state with small fluctuations and approximately linear, so only the data corresponding to the interval from a1 to a2 is retained.

[0071] In another embodiment of the present application, another method for determining steady-state data is defined. Specifically, determining whether the vehicle data within a preset time period stored in the sliding window is steady-state data includes: constructing a linear fitting function of the acceleration and the opening and closing degree of the speed control component based on the stored vehicle data acquired before the preset time period; calculating the minimum square error between the vehicle data within the preset time period and the linear fitting function; if the minimum square error is less than or equal to a second preset threshold, determining that the vehicle data within the preset time period is steady-state data.

[0072] In this embodiment, a linear fitting function of the acceleration and the opening and closing degree of the speed control component is constructed based on the stored vehicle data, and the error between the vehicle data within a preset time period and the linear fitting function is calculated. If the error is small, the vehicle data within the preset time period is determined to be steady-state data.

[0073] Exemplarily, a linear function of y=kx+b is obtained by the least square method, k and b are both known coefficients, x represents acceleration, and y represents the opening and closing degree of the speed control component. Based on the linear function, each actual x value can obtain a corresponding y value, and then the minimum square error of the corresponding y value and the actual y value is compared. If the minimum square error is less than or equal to the second preset threshold, it indicates that the actual x value and the actual y value are a set of approximately linear data, that is, they are steady-state data.

[0074] Through initial data screening, sliding windows, and steady-state data screening, the target vehicle data is obtained to avoid some noise data and improve the accuracy of subsequent updates.

[0075] Step 102 : Compare a first opening degree corresponding to a first acceleration in the target vehicle data with a second opening degree corresponding to a second acceleration in the standard calibration data, wherein the first acceleration is the same as the second acceleration.

[0076] Step 103: if the first opening degree is greater than the second opening degree, the second opening degree is updated to the first opening degree to obtain updated standard calibration data.

[0077] In step 102 and step 103, the first opening and closing degree corresponding to the first acceleration in the target vehicle data is compared with the second opening and closing degree corresponding to the second acceleration in the standard calibration data. Due to mechanical wear, vehicle aging and other reasons, at the same acceleration and speed, the actual throttle brake opening and closing degree must be larger than the standard throttle brake opening and closing degree in the standard calibration data. Therefore, if the first opening and closing degree is larger than the second opening and closing degree, the second opening and closing degree is replaced by the first opening and closing degree to achieve the success of the standard calibration data. After the update is successful, the standard calibration data is stored again in the configuration file of the autonomous driving vehicle.

[0078] In one embodiment of the present application, before comparison, based on prior knowledge, it is known that the calibration data is weakly correlated with the speed, that is, under the same acceleration, the higher the speed, the smaller the change in the opening and closing degree of the speed control component.

[0079] Therefore, after acquiring the target vehicle data, speed decoupling processing is performed to convert the target vehicle data into two-dimensional data. Specifically, the speed is segmented, that is, the speed is divided into multiple speed intervals, for example, the speed is divided into a speed interval of 0 to 10 mps (meters per second, m / s), a speed interval of 10 mps to 20 mps, and a speed interval above 20 mps. Then the acceleration and speed control component opening and closing corresponding to each speed interval are determined, such as Figure 4 As shown, the acceleration and speed control component opening and closing degrees corresponding to the speed range of 0 to 10 mps. It should be noted that one speed range corresponds to multiple accelerations, and each acceleration corresponds to multiple speed control component opening and closing degrees.

[0080] Then, the first opening and closing degree in any target speed interval among the multiple speed intervals is compared with the second opening and closing degree in the standard calibration data, wherein the standard calibration data is also a table after speed decoupling, and the speed interval corresponding to the second opening and closing degree is the same as the target speed interval.

[0081] By performing speed decoupling and decoupling the three-dimensional data into two-dimensional data, the subsequent comparison and update process can be made simpler.

[0082] In one embodiment of the present application, the first opening degree compared with the second opening degree in the standard calibration data is the average value corresponding to the first acceleration. Since each acceleration corresponds to a sequence of opening degrees of the speed control component, it is necessary to calculate the average value of the opening degrees of these multiple speed control components so that each acceleration corresponds to an average value, which is convenient for subsequent comparison with the standard calibration data.

[0083] It is worth noting that before calculating the average value of the opening and closing degrees of multiple speed control components corresponding to each acceleration in the target speed interval, it is necessary to perform acceleration clustering processing on the multiple accelerations in the target speed interval. Figure 4 Mark multiple acceleration points in , and then cluster other accelerations adjacent to the marked acceleration points with the marked acceleration points, such as Figure 5 As shown, the acceleration after clustering processing and the opening and closing degrees of multiple speed control components corresponding to each acceleration after clustering processing are obtained.

[0084] The reason for clustering accelerations is that when conducting throttle and brake calibration experiments, multiple standard accelerations are marked. If clustering is performed based on these accelerations, the difference between the opening and closing degrees of the standard speed control components under each acceleration and the opening and closing degrees of the actual speed control components under the corresponding actual acceleration can be easily calculated.

[0085] After clustering, the average value of the opening and closing degrees of multiple speed control components corresponding to each clustered acceleration is calculated. Figure 5 As shown, for the first autonomous driving vehicle, in the speed range of 0 to 20 mps, the curve formed by the average values ​​of the accelerations after clustering processing is the first curve, and the curve formed by the opening and closing degree of the standard speed control component in the standard calibration data is the second curve. The deviation between the first curve and the second curve is large, indicating that the autonomous driving vehicle has an obvious problem of insufficient braking, so the first curve is used to update the second curve. For the second autonomous driving vehicle, in the speed range of 0 to 20 mps, the curve formed by the average values ​​of the accelerations after clustering processing is the third curve, and in the acceleration range of -4 to -0.5 m / s 2 In the range, the second curve is greater than the third curve, and the second curve does not need to be updated; when the acceleration is -0.5 to -0.25 m / s 2 The third curve is greater than the second curve, and the second curve is updated using the third curve.

[0086] In one embodiment of the present application, in order to ensure credibility, the speed control component opening and closing degrees collected multiple times on one acceleration are all greater than the opening and closing degrees in the standard table before updating. Specifically, the target self-vehicle data is the target self-vehicle data acquired multiple times, and the target self-vehicle data includes multiple first accelerations; the first opening and closing degree corresponding to the first acceleration in the target self-vehicle data is compared with the second opening and closing degree corresponding to the second acceleration in the standard calibration data, including: comparing the first opening and closing degree corresponding to each first acceleration with the second opening and closing degree respectively, and counting the number of first opening and closing degrees greater than the second opening and closing degree; updating the second opening and closing degree to the first opening and closing degree, including: if the number is greater than the first preset threshold, then updating the second opening and closing degree to the average opening and closing degree of multiple first opening and closing degrees.

[0087] For example, if the opening and closing degrees of the speed control component are collected 10 times at the first acceleration, and each time the opening and closing degree of the speed control component is greater than the opening and closing degree in the standard table, it can be very sure that the opening and closing degree in the standard table is no longer applicable, and it is then updated.

[0088] It is worth noting that the embodiment of the present application is an online update performed on the vehicle side, without the need for transmission to a cloud server. In this way, as the vehicle travels, more data on the standard calibration data can be updated, so that the standard calibration data gradually tends to the actual pedal opening and closing situation.

[0089] In the embodiment of the present application, the standard calibration data is updated online through the vehicle-side self-vehicle data, so that the standard calibration data can be more accurate, thereby improving the vehicle's autonomous driving performance. Compared with the method of re-calibrating the throttle and brakes for each vehicle, it has higher efficiency, lower cost, and does not need to rely on cloud server resources, which improves the update speed.

[0090] As a specific implementation of the above calibration data updating method, the present application embodiment provides a calibration data updating device. Figure 6 As shown, the calibration data updating device 600 includes: a data acquisition module 601 , a comparison module 602 and an updating module 603 .

[0091] The data acquisition module 601 is used to acquire target vehicle data of the autonomous driving vehicle and standard calibration data of the autonomous driving vehicle, wherein the target vehicle data includes acceleration and speed control component opening and closing degrees having corresponding relationships;

[0092] A comparison module 602 is used to compare a first opening degree corresponding to a first acceleration in the target vehicle data with a second opening degree corresponding to a second acceleration in the standard calibration data, wherein the first acceleration is the same as the second acceleration;

[0093] The updating module 603 is used to update the second opening degree to the first opening degree if the first opening degree is greater than the second opening degree, so as to obtain updated standard calibration data.

[0094] In this embodiment, a large amount of target self-vehicle data of the autonomous driving vehicle itself is collected, and the target self-vehicle data corresponds to the actual opening and closing degree of the vehicle's speed control components at different speeds and accelerations, and the standard calibration data stored on the autonomous driving vehicle is obtained.

[0095] Compare the first opening and closing degree corresponding to the first acceleration in the target vehicle data with the second opening and closing degree corresponding to the second acceleration in the standard calibration data. Due to mechanical wear, vehicle aging and other reasons, at the same acceleration and speed, the actual throttle and brake opening and closing degree will definitely be larger than the standard throttle and brake opening and closing degree in the standard calibration data. Therefore, if the first opening and closing degree is larger than the second opening and closing degree, the second opening and closing degree is replaced with the first opening and closing degree to achieve the success of the standard calibration data. After the update is successful, the standard calibration data is stored back in the configuration file of the autonomous driving vehicle.

[0096] In the embodiment of the present application, the standard calibration data is updated online through the vehicle-side self-vehicle data, so that the standard calibration data can be more accurate, thereby improving the vehicle's autonomous driving performance. Compared with the method of re-calibrating the throttle and brakes for each vehicle, it has higher efficiency, lower cost, and does not need to rely on cloud server resources, which improves the update speed.

[0097] Furthermore, the target vehicle data also includes a speed having a corresponding relationship with the acceleration and the opening and closing degree of the speed control component; the comparison module 602 is specifically used to: divide the speed into multiple speed intervals, and determine multiple accelerations corresponding to each speed interval and multiple opening and closing degrees of the speed control components corresponding to each acceleration; compare the first opening and closing degree in the target speed interval among the multiple speed intervals with the second opening and closing degree in the standard calibration data, and the speed interval corresponding to the second opening and closing degree is the same as the target speed interval.

[0098] Furthermore, the device also includes: a calculation module, which is used to calculate the average value of the opening and closing degrees of multiple speed control components corresponding to each acceleration in the target speed range, wherein the first opening and closing degree is the average value of the opening and closing degrees of multiple speed control components corresponding to the first acceleration.

[0099] Furthermore, the calculation module is specifically used to: perform acceleration clustering processing on multiple accelerations in the target speed range to obtain the acceleration after clustering processing; and calculate the average value of the opening and closing degrees of multiple speed control components corresponding to each acceleration after clustering processing.

[0100] Furthermore, the target self-vehicle data is the target self-vehicle data acquired multiple times, and the target self-vehicle data includes multiple first accelerations; the comparison module 602 is specifically used to: compare the first opening and closing degrees corresponding to each first acceleration with the second opening and closing degrees, and count the number of first opening and closing degrees that are greater than the second opening and closing degrees; update the second opening and closing degree to the first opening and closing degree, including: if the number is greater than a first preset threshold, updating the second opening and closing degree to the average opening and closing degree of multiple first opening and closing degrees.

[0101] Furthermore, the data acquisition module 601 is specifically used to: use a sliding window to obtain the self-vehicle data within a preset time period from the autonomous driving vehicle, and use the self-vehicle data stored in the sliding window as the target self-vehicle data.

[0102] Furthermore, the device also includes: a screening module, which is used to filter out manual driving data in the vehicle data.

[0103] Furthermore, the data acquisition module 601 is specifically used to: determine whether the vehicle data within a preset time period stored in the sliding window is steady-state data; if the vehicle data is steady-state data, use the vehicle data as target vehicle data.

[0104] Furthermore, the data acquisition module 601 is specifically used to: construct a linear fitting function of the acceleration and speed control component opening and closing degree based on the stored self-vehicle data acquired before the preset time period; calculate the minimum square error between the self-vehicle data within the preset time period and the linear fitting function; if the minimum square error is less than or equal to the second preset threshold value, determine that the self-vehicle data within the preset time period is steady-state data.

[0105] Furthermore, the preset time period includes multiple sub-time periods; the data acquisition module 601 is specifically used for: if the absolute value of the change in the opening and closing degree of the accelerator and brake pedals in each sub-time period is less than or equal to a third preset threshold, then the reflux data in the preset time period is determined to be steady-state data.

[0106] The updating device 600 of calibration data in the embodiment of the present application can be a computer device, or a component in the computer device, such as an integrated circuit or a chip. The computer device can be a terminal, or other devices other than the terminal. Exemplarily, the computer device can be a mobile phone, a tablet computer, a laptop computer, a handheld computer, a vehicle-mounted computer device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (Augmented Reality, AR) / virtual reality (Virtual Reality, VR) device, a robot, a wearable device, a super mobile personal computer (Ultra-Mobile Personal Computer, UMPC), a netbook or a personal digital assistant (Personal Digital Assistant, PDA), etc., and can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (Personal Computer, PC), a television (Television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0107] The calibration data updating device 600 provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented in the embodiment of the calibration data updating method are not described here.

[0108] The present application also provides a computer device, such as Figure 7 As shown, the computer device 700 includes a processor 701 and a memory 702. The memory 702 stores programs or instructions that can be executed on the processor 701. When the program or instructions are executed by the processor 701, the various steps of the above-mentioned calibration data updating method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they are not repeated here.

[0109] It should be noted that the computer device in the embodiment of the present application includes the above-mentioned mobile computer device and non-mobile computer device.

[0110] The memory 702 can be used to store software programs and various data. The memory 702 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 702 may include a volatile memory or a non-volatile memory, or the memory 702 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 702 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0111] The processor 701 may include one or more processing units; optionally, the processor 701 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 701.

[0112] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned calibration data updating method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0113] An embodiment of the present application also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned calibration data updating method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0114] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0115] An embodiment of the present application also provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the calibration data updating method embodiment as described above, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0116] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes 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 one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0117] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for updating calibration data, characterized in that: include: Acquire target self-vehicle data of the autonomous driving vehicle and standard calibration data of the autonomous driving vehicle, wherein the target self-vehicle data includes an opening and closing degree of an acceleration and a speed control component having a corresponding relationship; Comparing a first opening degree corresponding to a first acceleration in the target vehicle data with a second opening degree corresponding to a second acceleration in the standard calibration data, wherein the first acceleration is the same as the second acceleration; If the first opening and closing degree is greater than the second opening and closing degree, the second opening and closing degree is updated to the first opening and closing degree to obtain updated standard calibration data.

2. The method according to claim 1, characterized in that The target vehicle data also includes a speed having a corresponding relationship with the acceleration and the opening and closing degree of the speed control component; The comparing the first opening degree corresponding to the first acceleration in the target vehicle data with the second opening degree corresponding to the second acceleration in the standard calibration data includes: Dividing the speed into a plurality of speed intervals, and determining a plurality of accelerations corresponding to each of the speed intervals and a plurality of speed control component opening and closing degrees corresponding to each of the accelerations; A first opening / closing degree in a target speed interval among the plurality of speed intervals is compared with a second opening / closing degree in the standard calibration data, and the speed interval corresponding to the second opening / closing degree is the same as the target speed interval.

3. The method according to claim 1, characterized in that Before comparing the first opening and closing degree in the target speed interval among the plurality of speed intervals with the second opening and closing degree in the standard calibration data, the method includes: An average value of the opening and closing degrees of a plurality of speed control components corresponding to each of the accelerations in the target speed interval is calculated, wherein the first opening and closing degree is an average value of the opening and closing degrees of a plurality of speed control components corresponding to the first acceleration.

4. The method according to claim 3, characterized in that Before calculating the average value of the opening and closing degrees of the plurality of speed control components corresponding to each of the accelerations in the target speed interval, the method further includes: Performing acceleration clustering processing on multiple accelerations in the target speed interval to obtain acceleration after clustering processing; The calculating the average value of the opening and closing degrees of the plurality of speed control components corresponding to each of the accelerations in the target speed interval comprises: The average value of the opening and closing degrees of the plurality of speed control components corresponding to each clustered acceleration in the target speed interval is calculated.

5. The method according to claim 1, characterized in that If the target vehicle data is target vehicle data acquired multiple times, the target vehicle data includes multiple first accelerations; The comparing the first opening degree corresponding to the first acceleration in the target vehicle data with the second opening degree corresponding to the second acceleration in the standard calibration data includes: Compare the first opening and closing degrees corresponding to each of the first accelerations with the second opening and closing degrees, and count the number of first opening and closing degrees that are greater than the second opening and closing degrees; The updating the second opening / closing degree to the first opening / closing degree includes: If the number is greater than a first preset threshold, the second opening degree is updated to an average opening degree of a plurality of the first opening degrees.

6. The method according to any one of claims 1 to 5, characterized in that The step of obtaining target vehicle data of the autonomous driving vehicle includes: The self-driving vehicle data within a preset time period is acquired using a sliding window, and the self-driving vehicle data stored in the sliding window is used as the target self-driving vehicle data.

7. The method according to claim 6, characterized in that Before storing the vehicle data in the sliding window, the method further includes: Manual driving data in the vehicle data is filtered out.

8. The method according to claim 6, characterized in that The using the vehicle data stored in the sliding window as target vehicle data includes: Determining whether the vehicle data within a preset time period stored in the sliding window is steady-state data; If the own vehicle data is steady-state data, the own vehicle data is used as target own vehicle data.

9. The method according to claim 8, characterized in that The determining whether the vehicle data within a preset time period stored in the sliding window is steady-state data includes: Constructing a linear fitting function of acceleration and opening and closing degree of a speed control component according to the stored vehicle data acquired before the preset time period; Calculating the minimum square error between the vehicle data within the preset time period and the linear fitting function; If the minimum square error is less than or equal to a second preset threshold, it is determined that the vehicle data within the preset time period is steady-state data.

10. A calibration data updating device, characterized in that: include: A data acquisition module, used to acquire target vehicle data of the autonomous driving vehicle and standard calibration data of the autonomous driving vehicle, wherein the target vehicle data includes acceleration and speed control component opening and closing degrees having corresponding relationships; A comparison module, used for comparing a first opening degree corresponding to a first acceleration in the target vehicle data with a second opening degree corresponding to a second acceleration in the standard calibration data, wherein the first acceleration is the same as the second acceleration; An updating module is used to update the second opening degree to the first opening degree if the first opening degree is greater than the second opening degree, so as to obtain updated standard calibration data.

11. A computer device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a program or instruction running on the processor, and when the program or instruction is executed by the processor, the steps of the calibration data updating method according to any one of claims 1 to 9 are implemented.

12. A readable storage medium having a program or instruction stored thereon, characterized in that: When the program or instruction is executed by a processor, the steps of the calibration data updating method according to any one of claims 1 to 9 are implemented.

Images