Evaluation method, device and equipment of accelerator and brake calibration table and storage medium
By obtaining and evaluating the return data of autonomous driving vehicles and adjusting the accelerator and brake calibration table, the problem of inaccurate calibration table is solved, and the autonomous driving performance and driving safety are improved.
Patent Information
- Application Number
- CN202310515443.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-09
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2043-05-09
AI Technical Summary
The existing accelerator brake calibration meter cannot be applied to different vehicles, and the calibration meter is inaccurate due to mechanical wear and aging of the vehicle during use, which affects the autonomous driving performance and driving safety.
By obtaining the effective return data of the autonomous vehicle, dividing the speed range, constructing two-dimensional data, evaluating the accuracy of the standard accelerator and brake calibration table, and adjusting the calibration table according to the deviation value to reflect the vehicle's differences and inaccuracy problems caused by aging.
Accurate evaluation of the accelerator brake calibration meter is achieved, automatic driving performance is improved, cost and efficiency is reduced, and driving safety is ensured.
Smart Images

Figure CN118940058A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of autonomous driving technology, and in particular to a method for evaluating a throttle-brake calibration table, an evaluation device for the throttle-brake calibration table, a computer device, and a readable storage medium. Background Art
[0002] At present, the accelerator and brake calibration experiment is only carried out on a certain vehicle of a certain model, and the calibration is used as the standard accelerator and brake calibration table. However, due to the differences in mechanical structure between different vehicles of the same model, the accelerator and brake calibration table may not be applicable to other models of the same model; in addition, even for the same vehicle, due to mechanical wear and vehicle aging during use, the accelerator and brake calibration table may become gradually inaccurate, seriously affecting the performance of autonomous driving and endangering driving safety. Summary of the invention
[0003] In view of this, the present application provides a method for evaluating a throttle-brake calibration table, an evaluation device for a throttle-brake calibration table, a computer device and a readable storage medium, so as to achieve accurate evaluation of the throttle-brake calibration table.
[0004] In a first aspect, an embodiment of the present application provides a method for evaluating an accelerator and brake calibration table, which is applied to a cloud server, and the method includes:
[0005] Obtaining effective return data of the autonomous driving vehicle, the effective return data including corresponding speed, acceleration, and accelerator and brake pedal opening and closing degrees;
[0006] Divide the speed into multiple speed intervals, and obtain two-dimensional data corresponding to each speed interval, the two-dimensional data including multiple accelerations and multiple accelerator and brake pedal opening and closing degrees corresponding to each acceleration;
[0007] Based on the two-dimensional data of the target speed range in the multiple speed ranges, the pre-stored standard throttle and brake calibration table of the autonomous driving vehicle is evaluated, and the standard throttle and brake calibration table includes standard two-dimensional data in the same speed range as the target speed range.
[0008] In this embodiment, a large amount of effective feedback data fed back by the autonomous driving vehicle is obtained, and the effective feedback data is the actual accelerator and brake pedal opening and closing degrees of the vehicle corresponding to different speeds and accelerations.
[0009] Since the accelerator and brake calibration table is weakly correlated with speed, the speed is segmented, that is, the speed is divided into multiple speed intervals, and then the acceleration and accelerator and brake pedal opening and closing corresponding to each speed interval are determined, that is, two-dimensional data. It should be noted that one speed interval corresponds to multiple accelerations, and each acceleration corresponds to multiple accelerator and brake pedal opening and closing degrees. By decoupling the speed, the subsequent evaluation process can be made simpler.
[0010] Furthermore, a target speed interval among multiple speed intervals is determined, and the two-dimensional data of the target speed interval is used to evaluate the standard throttle brake calibration table in the same speed interval as the target speed interval to determine whether the standard throttle brake calibration table is accurate, wherein the standard throttle brake calibration table is also a table after speed decoupling.
[0011] In the embodiment of the present application, during the use of the vehicle, each vehicle has a large amount of autonomous driving return data, and the throttle and brake calibration table can be evaluated through big data. Compared with conducting throttle and brake calibration experiments on each vehicle to evaluate the calibration table, it has higher efficiency and lower cost. By accurately evaluating the throttle and brake calibration table, it can effectively reflect the problem of inaccurate throttle and brake calibration table caused by vehicle differences, vehicle aging, etc.
[0012] According to the above method of the embodiment of the present application, the following additional technical features may also be provided:
[0013] In the above technical solution, optionally, a pre-stored standard throttle and brake calibration table for an autonomous driving vehicle is evaluated based on two-dimensional data of a target speed interval among multiple speed intervals, including: for a target speed interval among multiple speed intervals, calculating the average opening and closing degrees of multiple throttle and brake pedals corresponding to each acceleration in the target speed interval; constructing target calibration data for the target speed interval based on multiple accelerations in the target speed interval and the average opening and closing degrees corresponding to each acceleration; and evaluating the standard throttle and brake calibration table based on the target calibration data for the target speed interval.
[0014] In this embodiment, each acceleration corresponds to a sequence of throttle and brake pedal opening and closing degrees, and it is necessary to calculate the average values of the multiple throttle and brake pedal opening and closing degrees so that each acceleration corresponds to an opening and closing degree average value, and construct target calibration data including multiple accelerations and an opening and closing degree average value corresponding to each acceleration, so as to facilitate subsequent evaluation of the standard throttle and brake calibration table.
[0015] In any of the above technical solutions, optionally, the average opening and closing degrees of multiple accelerator and brake pedals corresponding to each acceleration in the target speed range are calculated, including: performing acceleration clustering processing on multiple accelerations in the target speed range to obtain accelerations after clustering processing; calculating the average opening and closing degrees of multiple accelerator and brake pedals corresponding to each acceleration after clustering processing.
[0016] In this embodiment, before calculating the average opening and closing degrees of multiple accelerator and brake pedal opening and closing degrees corresponding to each acceleration, acceleration clustering is performed first, for example, other accelerations adjacent to an acceleration of a certain value are clustered with the acceleration.
[0017] The reason for clustering acceleration is that when conducting the throttle and brake calibration experiment, multiple standard accelerations will be marked. If clustering is performed based on these accelerations, the difference between the standard throttle and brake pedal opening and closing degree under each acceleration and the actual throttle and brake pedal opening and closing degree under the corresponding actual acceleration can be easily calculated.
[0018] In any of the above technical solutions, optionally, the standard throttle brake calibration table is evaluated based on the target calibration data of the target speed range, including: calculating the deviation value between the target calibration data and the standard two-dimensional data in the standard throttle brake calibration table; if the deviation value is greater than or equal to a first preset threshold, it is determined that there is a deviation in the standard throttle brake calibration table.
[0019] In this embodiment, it is determined whether there is a deviation in the standard throttle brake calibration table based on the deviation value between the target calibration data and the standard two-dimensional data in the standard throttle brake calibration table.
[0020] This application aims to conduct offline evaluation of the vehicle's throttle and brake calibration table through a large amount of reflux data, quantify the error between the vehicle's actual data and the standard throttle and brake calibration table, and effectively reflect the problem of inaccurate throttle and brake calibration table caused by vehicle differences, vehicle aging, etc.
[0021] In any of the above technical solutions, optionally, after determining that there is a deviation in the standard throttle brake calibration table, it also includes: adjusting the standard two-dimensional data in the standard throttle brake calibration table according to the deviation value; or, adjusting the standard throttle brake calibration table using target calibration data; and sending the adjusted standard throttle brake calibration table to the autonomous driving vehicle.
[0022] In this embodiment, after determining that the standard throttle brake calibration table has a deviation, the standard throttle brake calibration table can be adjusted according to the deviation value, or the data in the standard throttle brake calibration table can be directly replaced with the target calibration data to update the standard throttle brake calibration table. The updated standard throttle brake calibration table is then sent to the autonomous driving vehicle, so that the autonomous driving vehicle performs autonomous driving according to the updated calibration table, thereby improving the autonomous driving performance of the vehicle.
[0023] In any of the above technical solutions, optionally, obtaining valid reflow data of the autonomous driving vehicle includes: obtaining reflow data from the autonomous driving vehicle, and storing the reflow data in a sliding window in the order of acquisition time; and using the reflow data within a preset time period stored in the sliding window as valid reflow data.
[0024] 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.
[0025] The sliding window is used to store more frames of return data of the autonomous driving vehicle offline, which facilitates the screening of effective return data.
[0026] In any of the above technical solutions, optionally, before storing the reflow data in the sliding window in the order of acquisition time, it also includes: retaining the autonomous driving data in the reflow data.
[0027] In this embodiment, after receiving the return data from the autonomous driving vehicle, an initial screening is performed first. This is because the vehicle-side return data includes two states: manual driving data and autonomous driving data. The standard throttle and brake calibration table will be evaluated using the autonomous driving data later. Therefore, in order to avoid the impact of manual driving data on the evaluation, the manual driving data in the return data is filtered out and the autonomous driving data in the return data is retained.
[0028] In any of the above technical solutions, optionally, the reflux data within a preset time period stored in the sliding window is used as valid reflux data, including: determining whether the reflux data within the preset time period stored in the sliding window is steady-state data; if the reflux data is steady-state data, then using the reflux data as valid reflux data.
[0029] In any of the above technical solutions, optionally, a method for determining steady-state data is defined. Specifically, the preset time period includes multiple sub-time periods; determining whether the reflux 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 accelerator and brake pedals within each sub-time period is less than or equal to a second preset threshold, then determining that the reflux data within the preset time period is steady-state data.
[0030] In this embodiment, the state of the reflux 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 accelerator and brake pedals reaches an approximately linear state.
[0031] When the reflux data is steady-state data, it indicates that it is the data generated when the vehicle is already running stably. In this state, it is easier to find the corresponding rules between acceleration and the opening and closing degree of the accelerator and brake pedals, and the corresponding rules are more reliable.
[0032] When it is determined that the reflux data in the sliding window have reached a steady state, these data are valid reflux data. By using the valid reflux data to evaluate the standard throttle brake calibration table, the accuracy of the standard throttle brake calibration table evaluation is improved.
[0033] In a second aspect, an embodiment of the present application provides an evaluation device for an accelerator brake calibration table, comprising:
[0034] A data acquisition module is used to acquire effective return flow data of the autonomous driving vehicle, where the effective return flow data includes corresponding speed, acceleration, and accelerator and brake pedal opening and closing degrees;
[0035] A speed division module is used to divide the speed into multiple speed intervals and obtain two-dimensional data corresponding to each speed interval, wherein the two-dimensional data includes multiple accelerations and multiple accelerator and brake pedal opening and closing degrees corresponding to each acceleration;
[0036] The evaluation module is used to evaluate the pre-stored standard throttle and brake calibration table of the autonomous driving vehicle according to the two-dimensional data of the target speed range in multiple speed ranges, wherein the standard throttle and brake calibration table includes standard two-dimensional data in the same speed range as the target speed range.
[0037] In the embodiment of the present application, during the use of the vehicle, each vehicle has a large amount of autonomous driving return data, and the throttle and brake calibration table can be evaluated through big data. Compared with conducting throttle and brake calibration experiments on each vehicle to evaluate the calibration table, it has higher efficiency and lower cost. By accurately evaluating the throttle and brake calibration table, it can effectively reflect the problem of inaccurate throttle and brake calibration table caused by vehicle differences, vehicle aging, etc.
[0038] 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.
[0039] 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.
[0040] 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.
[0041] 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.
[0042] 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
[0043] 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:
[0044] Figure 1 One of the flow charts of the evaluation method of the brake calibration table according to the embodiment of the present application is shown;
[0045] Figure 2 A schematic diagram showing the reflux data of an embodiment of the present application is shown;
[0046] Figure 3 A schematic diagram showing a backflow data state of an embodiment of the present application;
[0047] Figure 4 A schematic diagram showing two-dimensional data corresponding to a speed range of 0 to 10 mps according to an embodiment of the present application is shown;
[0048] 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;
[0049] Figure 6 A schematic diagram showing the evaluation of the speed range of 10 mps to 20 mps in the embodiment of the present application is shown;
[0050] Figure 7 A schematic diagram showing the evaluation of the speed range above 20 mps in the embodiment of the present application is shown;
[0051] Figure 8 A second flow chart of a method for evaluating a brake calibration table according to an embodiment of the present application is shown;
[0052] Fig. 9 A structural block diagram of a brake calibration table evaluation device according to an embodiment of the present application is shown;
[0053] Fig.10 A structural block diagram of a computer device according to an embodiment of the present application is shown. DETAILED DESCRIPTION
[0054] 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.
[0055] 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.
[0056] In conjunction with the accompanying drawings, the evaluation method for the throttle-brake calibration table, the evaluation device for the throttle-brake calibration table, the computer equipment and the readable storage medium provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.
[0057] The present application embodiment provides a method for evaluating an accelerator brake calibration table, which is applied to a cloud server, such as Figure 1 As shown, the method includes:
[0058] Step 101, obtaining effective reflux data of the autonomous driving vehicle, where the effective reflux data includes corresponding speed, acceleration, and accelerator and brake pedal opening and closing degrees.
[0059] In this step, a large amount of feedback data from the autonomous driving vehicle is received, such as Figure 2As shown, the reflux data is the actual accelerator and brake pedal opening and closing degrees of the vehicle corresponding to different speeds and accelerations, wherein the X coordinate is the speed, the Y coordinate is the acceleration, and the Z coordinate is the accelerator and brake pedal opening and closing degrees.
[0060] After receiving the return data from the autonomous driving vehicle, an initial screening is performed first. This is because the return data from the vehicle end includes two states: manual driving data and autonomous driving data. The standard throttle and brake calibration table will be evaluated using the autonomous driving data later. Therefore, in order to avoid the impact of manual driving data on the evaluation, the manual driving data in the return data is filtered out and the autonomous driving data in the return data is retained.
[0061] After the initial screening, the reflux data is stored in the sliding window in the order of acquisition time, so that the reflux data within the preset time period is stored in the sliding window. 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, then the sliding window is equivalent to saving all the data in the past 2 seconds.
[0062] The sliding window is used to store more frames of reflux data of the autonomous driving vehicle offline, which facilitates the subsequent steady-state screening of effective reflux data.
[0063] Furthermore, it is determined whether the reflux 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 accelerator and brake pedal reaches an approximately linear state. When the reflux 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 accelerator and brake pedal 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 accelerator and brake pedal, 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 accelerator and brake pedal for non-steady-state data, so the non-steady-state data is deleted.
[0064] When it is determined that the reflux data in the sliding window have reached a steady state, these data are valid reflux data. By using the valid reflux data to evaluate the standard throttle brake calibration table, the accuracy of the standard throttle brake calibration table evaluation is improved.
[0065] 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.
[0066] 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 reflux 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 accelerator and brake pedals within each sub-time period is less than or equal to a second preset threshold, then determining that the reflux data within the preset time period is steady-state data.
[0067] In this embodiment, the absolute value of the change in the opening and closing degree of the accelerator and brake pedal in each sub-time period of the preset time period is less than or equal to the second preset threshold, indicating that the change fluctuation of the opening and closing degree of the accelerator and brake pedal in the preset time period is small, and the reflux data in the preset time period is determined to be steady-state data.
[0068] 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.
[0069] In another embodiment of the present application, another method for determining steady-state data is defined. Specifically, determining whether the reflux data within a preset time period stored in the sliding window is steady-state data includes: constructing a linear fitting function of acceleration and accelerator and brake pedal opening and closing according to the stored reflux data acquired before the preset time period; calculating the minimum square error between the reflux data within the preset time period and the linear fitting function; if the minimum square error is less than or equal to a third preset threshold, determining that the reflux data within the preset time period is steady-state data.
[0070] In this embodiment, a linear fitting function of acceleration and accelerator and brake pedal opening and closing is constructed based on the stored reflux data, and the error between the reflux data within a preset time period and the linear fitting function is calculated. If the error is small, the reflux data within the preset time period is determined to be steady-state data.
[0071] Exemplarily, a linear function of y=kx+b is obtained by the least square method, where k and b are known coefficients, x represents acceleration, and y represents the degree of opening and closing of the accelerator and brake pedals. 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 third 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.
[0072] Through initial data screening, sliding windows, and steady-state data screening, effective reflux data is obtained to avoid the appearance of some noise data, thereby improving the accuracy of subsequent evaluations.
[0073] Step 102, divide the speed into a plurality of speed intervals, and obtain two-dimensional data corresponding to each speed interval, wherein the two-dimensional data includes a plurality of accelerations and a plurality of accelerator and brake pedal opening and closing degrees corresponding to each acceleration.
[0074] In this step, based on prior knowledge, it can be known that the accelerator brake calibration table is weakly correlated with speed, that is, under the same acceleration condition, the higher the speed, the smaller the change in the accelerator brake pedal opening and closing degree.
[0075] Therefore, after obtaining the effective return flow data, speed decoupling processing is performed to convert the return flow 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 accelerator and brake pedal opening and closing corresponding to each speed interval are determined, that is, two-dimensional data, such as Figure 4 As shown, the two-dimensional data of acceleration and accelerator and brake pedal opening and closing 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 accelerator and brake pedal opening and closing degrees.
[0076] By decoupling the speed, the three-dimensional data is decoupled into two-dimensional data, which enables subsequent evaluation according to different speeds and the two-dimensional standard throttle and brake calibration table, making the evaluation process simpler.
[0077] Step 103, based on the two-dimensional data of the target speed interval in the multiple speed intervals, the pre-stored standard throttle and brake calibration table of the autonomous driving vehicle is evaluated, and the standard throttle and brake calibration table includes standard two-dimensional data in the same speed interval as the target speed interval.
[0078] In this step, any one target speed interval among multiple speed intervals is determined, and the two-dimensional data of the target speed interval is used to evaluate the standard throttle brake calibration table in the same speed interval as the target speed interval to determine whether the standard throttle brake calibration table is accurate, wherein the standard throttle brake calibration table is also a table after speed decoupling.
[0079] Specifically, for any target speed interval among multiple speed intervals, the average opening and closing degrees of multiple throttle and brake pedals corresponding to each acceleration in the target speed interval are calculated; based on the multiple accelerations in the target speed interval and the average opening and closing degrees corresponding to each acceleration, the target calibration data for the target speed interval is constructed; based on the target calibration data of the target speed interval, the standard throttle and brake calibration table is evaluated.
[0080] In this embodiment, each acceleration corresponds to a sequence of throttle and brake pedal opening and closing degrees, and it is necessary to calculate the average values of the multiple throttle and brake pedal opening and closing degrees so that each acceleration corresponds to an opening and closing degree average value, and construct two-dimensional target calibration data including multiple accelerations and an opening and closing degree average value corresponding to each acceleration, so as to facilitate the subsequent evaluation of the standard throttle and brake calibration table.
[0081] It is worth noting that before calculating the average opening and closing degrees of multiple accelerator and brake pedals corresponding to each acceleration in the target speed range, it is necessary to perform acceleration clustering processing on multiple accelerations in the target speed range. 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 clustered acceleration and multiple accelerator and brake pedal opening and closing degrees corresponding to each clustered acceleration are obtained.
[0082] The reason for clustering acceleration is that when conducting the throttle and brake calibration experiment, multiple standard accelerations will be marked. If clustering is performed based on these accelerations, the difference between the standard throttle and brake pedal opening and closing degree under each acceleration and the actual throttle and brake pedal opening and closing degree under the corresponding actual acceleration can be easily calculated.
[0083] After clustering, the average opening and closing degrees of multiple accelerator and brake pedals corresponding to each clustered acceleration are calculated. The first curve of the two-dimensional target calibration data composed of multiple clustered accelerations and an average opening and closing degree corresponding to each clustered acceleration is as shown in FIG. Figure 5 shown.
[0084] It should be noted that when evaluating the standard throttle brake calibration table according to the target calibration data of the target speed range, the deviation value between the target calibration data and the standard two-dimensional data in the standard throttle brake calibration table is calculated, wherein the standard two-dimensional data in the standard throttle brake calibration table is also two-dimensional data after speed decoupling. For example, the deviation value is compared by using the target calibration data corresponding to the speed range of 0 to 10 mps and the standard two-dimensional data in the standard throttle brake calibration table corresponding to the speed range of 0 to 10 mps, wherein the second curve formed by the standard two-dimensional data in the standard throttle brake calibration table is as follows: Figure 5 If the deviation value is greater than or equal to the first preset threshold, it is determined that there is a deviation in the standard throttle brake calibration table.
[0085] The above provides a method for evaluating the throttle-brake calibration table in the speed range of 0 to 10 mps. Through this method, the throttle-brake calibration table corresponding to different speed ranges is evaluated.
[0086] For example, Figure 5 This is a schematic diagram of the evaluation of the speed range from 0 to 10 mps. Figure 6 This is a schematic diagram of the evaluation of the speed range from 10mps to 20mps. Figure 7 This is a schematic diagram of the evaluation of the speed range above 20mps. Figure 5 and Figure 6 As shown, for the first autonomous driving vehicle, in the speed range of 0 to 20 mps, the deviation value between the first curve corresponding to the reflux data of the first autonomous driving vehicle and the second curve of the standard throttle brake calibration table is relatively large, indicating that the first autonomous driving vehicle has an obvious problem of insufficient braking. Figure 5 and Figure 6 In the figure, the deviation between the third curve corresponding to the return flow data of the second autonomous driving vehicle and the second curve of the standard throttle brake calibration table is small, indicating that the standard throttle brake calibration table of the second autonomous driving vehicle is more accurate. Figure 7 As shown, in the speed range above 20mps, the first and third curves corresponding to the reflux data of the two autonomous driving vehicles have a certain deviation value from the second curve of the standard throttle brake calibration table, that is, the standard throttle brake calibration table corresponding to the speed range above 20mps is not accurate enough.
[0087] In the embodiment of the present application, during the use of the vehicle, each vehicle has a large amount of autonomous driving return data, and the throttle and brake calibration table can be evaluated through big data. Compared with conducting throttle and brake calibration experiments on each vehicle to evaluate the calibration table, it has higher efficiency and lower cost. By accurately evaluating the throttle and brake calibration table, it can effectively reflect the problem of inaccurate throttle and brake calibration table caused by vehicle differences, vehicle aging, etc.
[0088] As a refinement and extension of the above embodiment, the embodiment of the present invention provides another evaluation method of the accelerator brake calibration table, such as Figure 8 As shown, the method includes:
[0089] Step 801, obtaining effective return flow data of the autonomous driving vehicle, where the effective return flow data includes corresponding speed, acceleration, and accelerator and brake pedal opening and closing degrees;
[0090] Step 802, dividing the speed into a plurality of speed intervals, and acquiring two-dimensional data corresponding to each speed interval, wherein the two-dimensional data includes a plurality of accelerations and a plurality of accelerator and brake pedal opening and closing degrees corresponding to each acceleration;
[0091] Step 803, evaluating a pre-stored standard throttle and brake calibration table of an autonomous driving vehicle according to the two-dimensional data of a target speed interval among the multiple speed intervals, wherein the standard throttle and brake calibration table includes standard two-dimensional data in a speed interval that is the same as the target speed interval;
[0092] Step 804, adjusting the standard two-dimensional data in the standard throttle brake calibration table according to the deviation value, or adjusting the standard throttle brake calibration table using the target calibration data;
[0093] Step 805, sending the adjusted standard throttle and brake calibration table to the autonomous driving vehicle.
[0094] In this embodiment, after determining that there is a deviation in the standard throttle brake calibration table, the standard throttle brake calibration table can be adjusted according to the deviation value, or the target calibration data can be directly used to replace the data in the standard throttle brake calibration table to achieve an update of the standard throttle brake calibration table.
[0095] For example, in the standard throttle brake calibration table, when the throttle brake opening and closing degree is 0.25%, the acceleration can reach -2m / s 2 However, the return data from the vehicle side shows that the acceleration can only reach -2m / s when the throttle brake opening and closing degree is 0.27%. 2 The reason may be that the brake pads of the vehicle are worn, which requires more braking to achieve the same expected acceleration. In this way, the deviation between the standard throttle brake calibration table and the return data of the vehicle end is obtained, and the standard throttle brake calibration table is updated according to the deviation, or the acceleration in the standard throttle brake calibration table is directly -2m / s 2 The corresponding throttle brake opening and closing degree is updated to 0.27%.
[0096] The updated standard accelerator and brake calibration table is then sent to the autonomous driving vehicle, so that the autonomous driving vehicle can drive autonomously according to the updated calibration table, thereby improving the vehicle's autonomous driving performance.
[0097] As a specific implementation of the evaluation method of the throttle brake calibration table, the embodiment of the present application provides an evaluation device for the throttle brake calibration table. Fig. 9 As shown, the evaluation device 900 of the throttle brake calibration table includes: a data acquisition module 901, a speed division module 902 and an evaluation module 903.
[0098] The data acquisition module 901 is used to acquire effective reflux data of the autonomous driving vehicle, wherein the effective reflux data includes speed, acceleration, and throttle and brake pedal opening and closing degrees with corresponding relationships;
[0099] A speed division module 902, used to divide the speed into a plurality of speed intervals, and obtain two-dimensional data corresponding to each of the speed intervals, wherein the two-dimensional data includes a plurality of accelerations and a plurality of accelerator and brake pedal opening and closing degrees corresponding to each of the accelerations;
[0100] The evaluation module 903 is used to evaluate the pre-stored standard throttle and brake calibration table of the autonomous driving vehicle based on the two-dimensional data of the target speed range in the multiple speed ranges, wherein the standard throttle and brake calibration table includes standard two-dimensional data in the same speed range as the target speed range.
[0101] In this embodiment, a large amount of effective feedback data fed back by the autonomous driving vehicle is obtained, and the effective feedback data is the actual accelerator and brake pedal opening and closing degrees of the vehicle corresponding to different speeds and accelerations.
[0102] Since the accelerator and brake calibration table is weakly correlated with speed, the speed is segmented, that is, the speed is divided into multiple speed intervals, and then the acceleration and accelerator and brake pedal opening and closing corresponding to each speed interval are determined, that is, two-dimensional data. It should be noted that one speed interval corresponds to multiple accelerations, and each acceleration corresponds to multiple accelerator and brake pedal opening and closing degrees. By decoupling the speed, the subsequent evaluation process can be made simpler.
[0103] Furthermore, a target speed interval among multiple speed intervals is determined, and the two-dimensional data of the target speed interval is used to evaluate the standard throttle brake calibration table in the same speed interval as the target speed interval to determine whether the standard throttle brake calibration table is accurate, wherein the standard throttle brake calibration table is also a table after speed decoupling.
[0104] In the embodiment of the present application, during the use of the vehicle, each vehicle has a large amount of autonomous driving return data, and the throttle and brake calibration table can be evaluated through big data. Compared with conducting throttle and brake calibration experiments on each vehicle to evaluate the calibration table, it has higher efficiency and lower cost. By accurately evaluating the throttle and brake calibration table, it can effectively reflect the problem of inaccurate throttle and brake calibration table caused by vehicle differences, vehicle aging, etc.
[0105] Furthermore, the evaluation module 903 is specifically used to: for a target speed interval among multiple speed intervals, calculate the average opening and closing degrees of multiple throttle and brake pedals corresponding to each acceleration in the target speed interval; construct target calibration data for the target speed interval based on multiple accelerations in the target speed interval and the average opening and closing degrees corresponding to each acceleration; and evaluate the standard throttle and brake calibration table based on the target calibration data of the target speed interval.
[0106] Furthermore, the evaluation module 903 is specifically used to: perform acceleration clustering processing on multiple accelerations in the target speed range to obtain the acceleration after clustering processing; calculate the average opening and closing degree of multiple accelerator and brake pedal opening and closing degrees corresponding to each acceleration after clustering processing.
[0107] Furthermore, the evaluation module 903 is specifically used to: calculate the deviation value between the target calibration data and the standard two-dimensional data in the standard throttle brake calibration table; if the deviation value is greater than or equal to the first preset threshold, it is determined that there is a deviation in the standard throttle brake calibration table.
[0108] Furthermore, the device also includes: an adjustment module, used to adjust the standard two-dimensional data in the standard throttle brake calibration table according to the deviation value; or, to adjust the standard throttle brake calibration table using target calibration data; and a sending module, used to send the adjusted standard throttle brake calibration table to the autonomous driving vehicle.
[0109] Furthermore, the data acquisition module 901 is specifically used to: acquire the reflow data from the autonomous driving vehicle, and store the reflow data in the sliding window in the order of acquisition time; and use the reflow data within a preset time period stored in the sliding window as valid reflow data.
[0110] Furthermore, the device also includes: a screening module, used to retain the autonomous driving data in the reflow data.
[0111] Furthermore, the data acquisition module 901 is specifically used to: determine whether the reflow data within a preset time period stored in the sliding window is steady-state data; if the reflow data is steady-state data, take the reflow data as valid reflow data.
[0112] Furthermore, the preset time period includes multiple sub-time periods; the data acquisition module 901 is specifically used to: 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 second preset threshold, then the reflux data in the preset time period is determined to be steady-state data.
[0113] Furthermore, the data acquisition module 901 is specifically used to: construct a linear fitting function of acceleration and accelerator and brake pedal opening and closing based on the stored reflux data acquired before the preset time period; calculate the minimum square error between the reflux data within the preset time period and the linear fitting function; if the minimum square error is less than or equal to the third preset threshold, determine that the reflux data within the preset time period is steady-state data.
[0114] The evaluation device 900 of the throttle brake calibration table 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 a terminal. Exemplarily, the computer device can be a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted computer device, a mobile Internet device (Mobile Internet Device, MID), a robot, a wearable device, an ultra-mobile personal computer (Ultra-Mobile Personal Computer, UMPC), a netbook or a personal digital assistant (Personal Digital Assistant, PDA), etc. It can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (Personal Computer, PC), etc., and the embodiment of the present application is not specifically limited.
[0115] The evaluation device 900 of the throttle brake calibration table provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented in the embodiment of the throttle brake calibration table evaluation method are not described here.
[0116] The present application also provides a computer device, such as Fig.10 As shown, the computer device 1000 includes a processor 1001 and a memory 1002. The memory 1002 stores programs or instructions that can be executed on the processor 1001. When the program or instructions are executed by the processor 1001, the various steps of the evaluation method embodiment of the above-mentioned throttle brake calibration table are implemented, and the same technical effect can be achieved. To avoid repetition, they are not repeated here.
[0117] 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.
[0118] The memory 1002 can be used to store software programs and various data. The memory 1002 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 1002 may include a volatile memory or a non-volatile memory, or the memory 1002 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 1002 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.
[0119] The processor 1001 may include one or more processing units; optionally, the processor 1001 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 1001.
[0120] 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 embodiment of the evaluation method of the above-mentioned throttle brake calibration table is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0121] 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 embodiment of the evaluation method of the above-mentioned throttle brake calibration table, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0122] 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.
[0123] 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 evaluation method embodiment of the throttle brake calibration table as described above, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0124] 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.
[0125] 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 evaluating an accelerator brake calibration table, characterized in that: include: Acquire effective reflux data of the autonomous driving vehicle, wherein the effective reflux data includes speed, acceleration, and accelerator and brake pedal opening and closing degrees having corresponding relationships; Dividing the speed into a plurality of speed intervals, and acquiring two-dimensional data corresponding to each of the speed intervals, the two-dimensional data including a plurality of accelerations and a plurality of accelerator and brake pedal opening and closing degrees corresponding to each of the accelerations; Based on the two-dimensional data of the target speed range in the multiple speed ranges, the pre-stored standard throttle and brake calibration table of the autonomous driving vehicle is evaluated, and the standard throttle and brake calibration table includes standard two-dimensional data in the same speed range as the target speed range.
2. The method according to claim 1, characterized in that The step of evaluating the pre-stored standard throttle and brake calibration table of the autonomous driving vehicle according to the two-dimensional data of the target speed interval in the plurality of speed intervals includes: For a target speed interval in the plurality of speed intervals, calculating an average value of the opening and closing degrees of the plurality of accelerator and brake pedals corresponding to each of the accelerations in the target speed interval; Constructing target calibration data for the target speed interval according to the plurality of accelerations in the target speed interval and an average value of the opening and closing degrees corresponding to each acceleration; The standard throttle and brake calibration table is evaluated according to the target calibration data of the target speed range.
3. The method according to claim 2, characterized in that The calculating the average opening and closing degree of a plurality of accelerator and brake pedal opening and closing degrees corresponding to each of the accelerations in the target speed interval comprises: Performing acceleration clustering processing on multiple accelerations in the target speed interval to obtain acceleration after clustering processing; The average opening and closing degrees of multiple accelerator and brake pedals corresponding to each clustered acceleration are calculated.
4. The method according to claim 2, characterized in that: The step of evaluating the standard throttle and brake calibration table according to the target calibration data of the target speed range includes: Calculating the deviation between the target calibration data and the standard two-dimensional data in the standard throttle and brake calibration table; If the deviation value is greater than or equal to a first preset threshold value, it is determined that there is a deviation in the standard throttle and brake calibration table.
5. The method according to claim 4, characterized in that After determining that the standard throttle and brake calibration table has a deviation, the method further includes: Adjusting the standard two-dimensional data in the standard throttle brake calibration table according to the deviation value; or adjusting the standard throttle brake calibration table using the target calibration data; The adjusted standard throttle and brake calibration table is sent to the autonomous driving vehicle.
6. The method according to any one of claims 1 to 5, characterized in that The obtaining of effective return flow data of the autonomous driving vehicle includes: Acquire return flow data from the autonomous driving vehicle, and store the return flow data into a sliding window in the order of acquisition time; The reflux data within a preset time period stored in the sliding window is used as valid reflux data.
7. The method according to claim 6, characterized in that Before storing the reflux data in the sliding window in the order of acquisition time, the method further includes: The autonomous driving data in the reflow data is retained.
8. The method according to claim 6, characterized in that The step of taking the reflux data within a preset time period stored in the sliding window as valid reflux data includes: Determining whether the reflux data within a preset time period stored in the sliding window is steady-state data; If the reflux data is steady-state data, the reflux data is taken as valid reflux data.
9. The method according to claim 8, characterized in that The preset time period includes a plurality of sub-time periods; and the determining whether the reflux 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 accelerator and brake pedals in each of the sub-time periods is less than or equal to the second preset threshold, it is determined that the reflux data in the preset time period is steady-state data.
10. An evaluation device for an accelerator brake calibration table, characterized in that: include: A data acquisition module, used to acquire effective reflux data of the autonomous driving vehicle, wherein the effective reflux data includes speed, acceleration, and accelerator and brake pedal opening and closing degrees with corresponding relationships; A speed division module, used to divide the speed into a plurality of speed intervals, and obtain two-dimensional data corresponding to each of the speed intervals, wherein the two-dimensional data includes a plurality of accelerations and a plurality of accelerator and brake pedal opening and closing degrees corresponding to each of the accelerations; An evaluation module is used to evaluate a pre-stored standard throttle and brake calibration table of the autonomous driving vehicle based on two-dimensional data of a target speed interval in a plurality of speed intervals, wherein the standard throttle and brake calibration table includes standard two-dimensional data in a speed interval that is the same as the target speed interval.
11. A computer device, characterized in that: It 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 evaluation method of the throttle-brake calibration table as described in 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 the processor, the steps of the evaluation method of the throttle and brake calibration table as described in any one of claims 1 to 9 are implemented.
Citation Information
Patent Citations
Takeoff assistance
CN104812671A
Road load spectrum preparation method based on density peak machine learning algorithm
CN112395940A
Electronic element and electrically controlled display element
DE102018010197A1
