Vehicle accelerator calibration method and device, storage medium and computer equipment

Abstract

According to the vehicle accelerator calibration method and device, the storage medium and the computer equipment provided by the invention, during the accelerator calibration test, the automatic driving vehicle after the test initial value is set is started on the experimental lane, so that the automatic driving vehicle enters the accelerator calibration test; in the vehicle driving process, the rear axle center point of the vehicle is collected in real time, the center line nearest point closest to the rear axle center point is determined from the road center line of the experimental lane, and data support is provided for follow-up accurate calculation of the vehicle direction deviation; the transverse distance deviation and the course deviation of the vehicle are determined based on the central point of the rear axle and the nearest point of the central line, and the driving direction of the vehicle is accurately controlled by using the two deviations, so that the vehicle is ensured to always run along the central line of the road. The driving direction of the vehicle is accurately controlled, and the accelerator response data generated in the testing process is more accurate and reliable, so that the accelerator calibration table generated based on the accelerator response data can truly reflect the relationship between the vehicle and the acceleration under different accelerator opening degrees.

Description

Technical Field

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

[0002] In recent years, the rapid development of autonomous vehicle technology has promoted the advancement of unmanned vehicles in the logistics industry. Throttle responsiveness is crucial in the control system of autonomous vehicles, directly determining their maneuverability. However, the relationship between acceleration and throttle opening is unknown when a vehicle leaves the factory. Therefore, throttle calibration experiments are necessary to accurately determine this relationship and provide basic data for precise control of autonomous vehicles.

[0003] Currently, when calibrating the throttle of an autonomous vehicle, the steering wheel can be fixed to allow the vehicle to travel on a sufficiently wide road. However, this requires a very high road width and therefore has significant limitations. To this end, testers use remote control to adjust the vehicle's driving direction during the test to prevent the vehicle from deviating from the experimental site. However, this method not only has time delay issues, but is also highly dependent on the operator's technical level, resulting in poor test consistency and difficulty in obtaining accurate and reliable throttle response data. Summary of the Invention

[0004] The purpose of this application is to solve at least one of the above-mentioned technical defects, especially the technical defect that the throttle calibration method in the prior art has poor test consistency and is difficult to obtain accurate and reliable throttle response data.

[0005] The present application provides a vehicle throttle calibration method, the method comprising:

[0006] Setting initial test values ​​for the autonomous driving vehicle, and starting the autonomous driving vehicle on a test track based on the initial test values ​​to enter a throttle calibration test;

[0007] During the driving process of the vehicle, the center point of the rear axle of the autonomous driving vehicle is collected in real time, and the closest point of the center line closest to the center point of the rear axle is determined on the center line of the road of the test lane;

[0008] determining a lateral distance deviation and a heading deviation of the autonomous driving vehicle based on the rear axle center point and the closest point of the centerline, and controlling a driving direction of the autonomous driving vehicle based on the lateral distance deviation and the heading deviation until the throttle calibration test is completed;

[0009] Acquire throttle response data generated by the autonomous driving vehicle during the throttle calibration test, and generate a throttle calibration table between throttle opening and acceleration based on the throttle response data.

[0010] Optionally, the test initial values ​​include a plurality of throttle opening calibration amounts, braking amounts and vehicle maximum speed;

[0011] The step of starting the autonomous driving vehicle on a test track based on the test initial value and entering a throttle calibration test includes:

[0012] For each throttle opening calibration amount, the autonomous driving vehicle is started to move forward on the test lane using the throttle opening calibration amount until the autonomous driving vehicle reaches the maximum speed of the vehicle, and the autonomous driving vehicle is decelerated and stopped according to the braking amount.

[0013] Optionally, determining the nearest point on the center line of the test lane that is closest to the center point of the rear axle includes:

[0014] Discretely sampling the center line of the experimental lane to obtain a plurality of center line discrete points;

[0015] The Euclidean distance between each centerline discrete point and the rear axle center point is determined, and the centerline discrete point with the smallest Euclidean distance is used as the centerline closest point closest to the rear axle center point.

[0016] Optionally, the calculation expression of the lateral distance deviation includes:

[0017]

[0018] Where, Indicates the lateral distance deviation; Indicates the vertical coordinate of the center point of the rear axle; Indicates the horizontal coordinate of the rear axle center point; Indicates the ordinate of the nearest point on the center line; Indicates the horizontal coordinate of the nearest point on the center line; Indicates the road heading at the nearest point on the centerline.

[0019] Optionally, the calculation expression of the heading deviation includes:

[0020]

[0021] Where, Indicates heading deviation; Indicates the vehicle heading at the center point of the rear axle; Indicates the road heading at the nearest point on the centerline.

[0022] Optionally, the controlling the driving direction of the autonomous driving vehicle based on the lateral distance deviation and the heading deviation includes:

[0023] A linear quadratic regulator built into the autonomous driving vehicle is used to solve the steering angle based on the lateral distance deviation and the heading deviation, and the steering wheel angle of the autonomous driving vehicle is adjusted according to the solution result.

[0024] Optionally, generating a throttle calibration table between throttle opening and acceleration based on the throttle response data includes:

[0025] Performing data fitting on the vehicle speed at different throttle openings in the throttle response data to generate an acceleration fitting curve;

[0026] A throttle calibration table between throttle opening and acceleration is generated according to the acceleration fitting curve.

[0027] The present application also provides a vehicle throttle calibration device, comprising:

[0028] A vehicle testing module, configured to set initial test values ​​for the autonomous driving vehicle and, based on the initial test values, start the autonomous driving vehicle on a test track to enter a throttle calibration test;

[0029] a data acquisition module, configured to acquire the center point of the rear axle of the autonomous driving vehicle in real time during driving, and to determine the nearest point on the center line of the experimental lane that is closest to the center point of the rear axle;

[0030] a direction control module, configured to determine a lateral distance deviation and a heading deviation of the autonomous driving vehicle based on the rear axle center point and the closest point of the centerline, and to control a driving direction of the autonomous driving vehicle based on the lateral distance deviation and the heading deviation until the throttle calibration test is completed;

[0031] A throttle calibration module is used to obtain throttle response data generated by the autonomous driving vehicle during the throttle calibration test, and generate a throttle calibration table between throttle opening and acceleration based on the throttle response data.

[0032] The present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the vehicle throttle calibration method as described in any one of the above embodiments.

[0033] The present application also provides a computer device, comprising: one or more processors, and a memory;

[0034] The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the vehicle throttle calibration method as described in any one of the above embodiments are performed.

[0035] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0036] The vehicle throttle calibration method, device, storage medium and computer equipment provided by the present application can, before the throttle calibration test, first set the test initial value of the autonomous driving vehicle, and then start the autonomous driving vehicle on the test lane based on the test initial value so that the vehicle drives forward and enters the throttle calibration test; during the vehicle driving process, the rear axle center point of the autonomous driving vehicle can be collected in real time, and the nearest centerline point closest to the rear axle center point can be determined from the centerline of the road of the test lane, providing data support for the subsequent accurate calculation of the vehicle direction deviation; here, the lateral distance deviation and heading deviation of the autonomous driving vehicle can be determined based on the rear axle center point and the nearest centerline point, and then the driving direction of the autonomous driving vehicle can be accurately controlled based on the lateral distance deviation and heading deviation, ensuring that the vehicle always drives along the centerline of the test lane during the throttle calibration test. Through precise control and stable testing of the vehicle's driving direction, the throttle response data generated by the autonomous driving vehicle during the throttle calibration test has high accuracy and reliability. Therefore, the throttle calibration table generated based on the throttle response data can truly reflect the relationship between the autonomous driving vehicle and acceleration at different throttle openings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0038] Figure 1 A flow chart of a vehicle throttle calibration method provided in an embodiment of the present application;

[0039] Figure 2 A schematic diagram of a vehicle throttle calibration method provided in an embodiment of the present application;

[0040] Figure 3 A schematic structural diagram of a vehicle throttle calibration device provided in an embodiment of the present application;

[0041] Figure 4 A schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0043] Currently, when calibrating the throttle of an autonomous vehicle, the steering wheel can be fixed to allow the vehicle to travel on a sufficiently wide road. However, this requires a very high road width and therefore has significant limitations. To this end, testers use remote control to adjust the vehicle's driving direction during the test to prevent the vehicle from deviating from the experimental site. However, this method not only has time delay issues, but is also highly dependent on the operator's technical level, resulting in poor test consistency and difficulty in obtaining accurate and reliable throttle response data.

[0044] Based on this, this application proposes the following technical solutions, please refer to the following for details:

[0045] In one embodiment, Figure 1 As shown, Figure 1 A flow chart of a vehicle throttle calibration method provided in an embodiment of the present application; the present application provides a vehicle throttle calibration method, which specifically includes the following:

[0046] S110: Setting the initial test values ​​of the autonomous driving vehicle, and starting the autonomous driving vehicle on the experimental lane based on the initial test values ​​to enter the throttle calibration test.

[0047] In this step, before the throttle calibration test, the tester can first set the test initial value of the autonomous driving vehicle on the vehicle control system, so that the vehicle control system can start the autonomous driving vehicle on the experimental lane based on the test initial value, allowing the vehicle to move forward and enter the throttle calibration test.

[0048] It is understandable that the test initial values ​​here may include initial parameters such as the throttle opening used during vehicle driving, the amount of braking used during deceleration and braking, and the maximum speed that the vehicle can reach. By setting the test initial values, this application can clarify the initial state of the autonomous driving vehicle and ensure that the various control variables are in a known and controllable state during the vehicle testing phase, thereby improving the repeatability and consistency of the test. Next, the vehicle control system can activate the autonomous driving function of the autonomous driving vehicle on a closed or semi-closed test lane, so that the vehicle starts and moves forward in an orderly manner according to the set test initial values, thereby smoothly entering the throttle calibration test phase.

[0049] S120: During the driving process of the vehicle, the center point of the rear axle of the autonomous driving vehicle is collected in real time, and the nearest point of the center line closest to the center point of the rear axle is determined from the center line of the road of the test lane.

[0050] In this step, after the vehicle is started to enter the throttle calibration test through step S110, during the vehicle driving process, the vehicle control system can collect the rear axle center point of the autonomous driving vehicle in real time, and determine the nearest point of the center line closest to the rear axle center point from the road center line of the test lane, providing data support for the subsequent accurate calculation of the vehicle direction deviation.

[0051] It is understood that the rear axle center point refers to the point on the vehicle's rear wheel axis that is located exactly halfway between the left and right rear wheels. Since the steering behavior of an autonomous vehicle is modeled around the rear axle, this application can use the rear axle center point as the reference mass point for the autonomous vehicle, thereby reducing the impact of head yaw caused by steering during vehicle position tracking.

[0052] Specifically, if Figure 2 As shown, Figure 2 A schematic diagram of a scenario of a vehicle throttle calibration method provided in an embodiment of the present application; the vehicle control system can construct a coordinate system based on the real-time position of the autonomous vehicle, and then determine the relative position of the rear axle center point of the autonomous vehicle in the coordinate system. The rear axle center point can be expressed as ,in, and Respectively represent the horizontal and vertical coordinates of the rear axle center point, Represents the vehicle heading at the rear axle center point. After collecting the rear axle center point of the autonomous vehicle, the vehicle control system can also filter out the point closest to the current rear axle center point of the vehicle from the road centerline on the experimental road in real time as the centerline closest point. The centerline closest point can be expressed as ,in, and They represent the horizontal and vertical coordinates of the nearest point on the center line, The road heading at the closest point to the centerline. Based on these two points, the vehicle control system can further establish the geometric relationship between the vehicle and the lane centerline, thereby accurately understanding the autonomous vehicle's deviation from the road centerline.

[0053] S130: Determine the lateral distance deviation and heading deviation of the autonomous driving vehicle based on the rear axle center point and the closest point of the center line, and control the driving direction of the autonomous driving vehicle based on the lateral distance deviation and heading deviation until the throttle calibration test is completed.

[0054] In this step, after obtaining the nearest point between the center point of the rear axle and the center line through step S120, the vehicle control system can determine the lateral distance deviation and heading deviation of the autonomous driving vehicle based on the nearest point between the center point of the rear axle and the center line, and then accurately control the driving direction of the autonomous driving vehicle based on the lateral distance deviation and heading deviation to ensure that the vehicle always travels along the center line of the test lane during the throttle calibration test.

[0055] It's understandable that lateral distance deviation and heading deviation are two core error metrics for autonomous vehicle direction control. Together, they reflect the spatial deviation between the vehicle's current position and the target route, and are the basis for precise driving control and route direction correction. Lateral distance deviation refers to the vertical deviation between the autonomous vehicle and the road centerline, reflecting the degree of lateral deviation from the ideal path. Heading deviation, on the other hand, refers to the angle between the vehicle's current direction of travel and the road centerline, indicating whether the vehicle's forward direction is directly tangent to the path.

[0056] Specifically, during the throttle calibration test, to ensure the autonomous vehicle always drives stably along the centerline of the test lane and obtain highly consistent throttle response data, the vehicle control system can accurately calculate the autonomous vehicle's lateral distance deviation and heading deviation in real time based on the geometric relationship between the rear axle center point and the closest point on the centerline. The vehicle control system can then use these two deviations as important feedback signals for closed-loop control, driving the lateral control algorithm to dynamically adjust the vehicle's front wheel angle or control command, thereby achieving high-precision control of the vehicle's driving direction and ensuring that the vehicle can stably drive along the road centerline throughout the throttle calibration process.

[0057] S140: Acquire throttle response data generated by the autonomous driving vehicle during the throttle calibration test, and generate a throttle calibration table between throttle opening and acceleration based on the throttle response data.

[0058] In this step, after the vehicle's driving direction is precisely controlled and stably tested through S130, the throttle response data generated by the autonomous driving vehicle during the throttle calibration test has high accuracy and reliability. Therefore, the throttle calibration table generated based on the throttle response data can truly reflect the relationship between the autonomous driving vehicle and acceleration at different throttle openings.

[0059] Among them, throttle response data refers to the relevant data on the actual response of the autonomous driving vehicle when the vehicle is started at different throttle openings during the throttle calibration test. It can reflect the data set of the relationship between throttle opening and vehicle dynamic response; this data is mainly used to describe the mapping relationship between throttle opening and parameters such as acceleration and vehicle speed, and is the basic basis for generating a throttle calibration table.

[0060] It's understandable that the throttle response data generated by the vehicle truly reflects the vehicle's actual acceleration response at different throttle openings, fully revealing the functional relationship between throttle input and vehicle longitudinal power output. Therefore, the throttle calibration table constructed based on this throttle response data not only has strong physical authenticity and data representativeness, but also serves as a highly reliable basic reference data in autonomous driving control systems, supporting the dynamic matching of throttle openings and acceleration commands, achieving refined control of the vehicle's acceleration process.

[0061] In the above embodiment, before the throttle calibration test, the test initial values ​​of the autonomous driving vehicle can be set first, and then the autonomous driving vehicle can be started on the test lane based on the test initial values ​​so that the vehicle moves forward and enters the throttle calibration test. During the vehicle's driving process, the center point of the autonomous driving vehicle's rear axle can be collected in real time, and the closest centerline point closest to the center point of the rear axle can be determined from the centerline of the test lane to provide data support for the subsequent accurate calculation of the vehicle's direction deviation. Here, the lateral distance deviation and heading deviation of the autonomous driving vehicle can be determined based on the rear axle center point and the closest centerline point. Then, the driving direction of the autonomous driving vehicle can be accurately controlled based on the lateral distance deviation and heading deviation to ensure that the vehicle always moves along the centerline of the test lane during the throttle calibration test. Through precise control and stable testing of the vehicle's driving direction, the throttle response data generated by the autonomous driving vehicle during the throttle calibration test has high accuracy and reliability. Therefore, the throttle calibration table generated based on the throttle response data can truly reflect the relationship between the autonomous driving vehicle and acceleration at different throttle openings.

[0062] In one embodiment, the test initial values ​​in step S110 may include multiple throttle opening calibration values, braking values, and vehicle maximum speed. The process of starting the autonomous driving vehicle on the test lane based on the test initial values ​​and entering the throttle calibration test may include:

[0063] S111: For each throttle opening calibration amount, the autonomous driving vehicle is started to move forward on the test lane using the throttle opening calibration amount until the autonomous driving vehicle reaches the maximum vehicle speed, and the autonomous driving vehicle is decelerated and stopped according to the braking amount.

[0064] In this embodiment, during the throttle calibration test, the vehicle control system can use each throttle opening calibration amount to start the autonomous driving vehicle to move forward on the test lane until the autonomous driving vehicle reaches the maximum speed of the vehicle, and then decelerate and stop the autonomous driving vehicle according to the braking amount.

[0065] Specifically, the vehicle control system can use each throttle opening calibration amount as an input parameter in turn to drive the autonomous driving vehicle to automatically start and move forward on the test lane, and keep the throttle opening unchanged during the process until the vehicle gradually accelerates under stable control to reach its maximum speed that can be achieved at the throttle opening; then, the vehicle control system can perform orderly deceleration according to the preset braking control amount, and bring the vehicle to a smooth stop without affecting the stability of the system.

[0066] It should be noted that during the test, the vehicle control system can collect key parameters such as throttle opening, vehicle speed, acceleration, engine speed, etc. in real time, and use them as throttle response data to construct a mapping relationship between throttle opening and acceleration response. This ensures that each throttle opening calibration quantity is measured independently under standardized and controllable working conditions, thereby avoiding interference factors introduced by human operation and improving the accuracy and consistency of throttle response data.

[0067] In one embodiment, the process of determining the nearest point on the center line of the test lane that is closest to the center point of the rear axle in step S120 may include:

[0068] S121: Discretely sample the center line of the experimental lane to obtain multiple center line discrete points.

[0069] S122: Determine the Euclidean distance between each centerline discrete point and the rear axle center point, and use the centerline discrete point with the smallest Euclidean distance as the centerline closest point closest to the rear axle center point.

[0070] In this embodiment, the vehicle control system can discretely sample the road center line of the experimental lane to obtain multiple center line discrete points, and then determine the Euclidean distance between each center line discrete point and the rear axle center point, and use the center line discrete point with the smallest Euclidean distance as the center line closest point closest to the rear axle center point.

[0071] Specifically, the vehicle control system can obtain the road centerline of the experimental lane through high-precision maps or image recognition-based technical means, and then sample the road centerline at a certain resolution and discretize it into a series of centerline discrete points, which can be expressed as The vehicle control system can then As the reference point, the Euclidean distance between it and each discrete point on the center line is calculated. By traversing all discrete points, the point with the smallest Euclidean distance is selected as the closest point on the center line corresponding to the current rear axle center point, thereby establishing a spatial association between the vehicle's current position and the ideal path. Here, the Euclidean distance The calculation formula can be expressed as follows:

[0072]

[0073] It can be understood that selecting the closest point on the centerline not only simplifies the process of determining the geometric relationship between the road centerline and the vehicle's position, but also improves the efficiency and accuracy of the system's path matching and deviation calculations during actual operation, providing a stable input basis for the real-time acquisition of lateral distance deviation and heading deviation. Furthermore, this method exhibits excellent scalability and adaptability, and can be applied to lane centerline trajectory extraction tasks of various shapes and complexities, providing critical data support for ensuring the stability of throttle calibration tests.

[0074] In one embodiment, the calculation expression of the lateral distance deviation in step S130 may include:

[0075]

[0076] Where, Indicates the lateral distance deviation; Indicates the vertical coordinate of the center point of the rear axle; Indicates the horizontal coordinate of the rear axle center point; Indicates the ordinate of the nearest point on the center line; Indicates the horizontal coordinate of the nearest point on the center line; Indicates the road heading at the nearest point on the centerline.

[0077] In this embodiment, the vehicle control system uses a dot product operation to project the difference vector between the center point of the rear axle and the nearest point on the centerline perpendicular to the road centerline, thereby calculating the lateral distance deviation of the autonomous vehicle. Using this calculation expression, the present application can quantify the lateral deviation between the autonomous vehicle and the road centerline in real time, thereby correcting the vehicle's driving direction during throttle calibration tests, providing a stable and controllable testing environment for throttle response data, and ensuring that the calibration results truly reflect the vehicle's dynamic response characteristics at different throttle openings.

[0078] In one embodiment, the calculation expression of the heading deviation in step S130 may include:

[0079]

[0080] Where, Indicates heading deviation; Indicates the vehicle heading at the center point of the rear axle; Indicates the road heading at the nearest point on the centerline.

[0081] In this embodiment, the vehicle control system calculates the difference between the current heading angle measured by the automatic driving and the tangent direction angle of the road centerline to obtain the vehicle's heading deviation. Through the real-time calculation and control of the heading deviation, the present application can not only effectively reduce the lateral deviation trend caused by the direction deviation during vehicle driving, but also intervene in advance to correct the deviation before it evolves into an obvious trajectory deviation, thereby improving the path tracking stability and control system response sensitivity of the entire test process. Compared with the method of relying solely on lateral deviation control, adding heading deviation feedback can enhance the robustness of path tracking and avoid data disturbances caused by directional control lag.

[0082] In one embodiment, the process of controlling the driving direction of the autonomous driving vehicle based on the lateral distance deviation and the heading deviation in step S130 may include:

[0083] S131: Using the built-in linear quadratic regulator of the autonomous driving vehicle, the steering angle is solved based on the lateral distance deviation and the heading deviation, and the steering wheel angle of the autonomous driving vehicle is adjusted according to the solution result.

[0084] In this embodiment, when controlling the vehicle's driving direction, the vehicle control system can use the linear quadratic regulator built into the autonomous driving vehicle to solve the angle based on the lateral distance deviation and heading deviation, and adjust the steering wheel angle of the autonomous driving vehicle according to the solution result to ensure that the vehicle always moves forward along the center line of the road.

[0085] Specifically, the linear quadratic regulator (LQR), the core of the lateral control algorithm, can be used to correct the vehicle's directional deviation in real time. During throttle calibration testing, the vehicle control system can input the two core errors—lateral distance deviation and heading deviation—into the LQR at a preset frequency as state variables. The LQR then constructs a state feedback control law based on the vehicle's kinematic model and cost function design. Within the linear system framework, it solves for the optimal solution that minimizes path deviation and control input cost, thereby determining the current steering wheel angle control variable that the vehicle should apply. The vehicle control system then converts this angle control variable into an executable steering wheel control command, which acts in real time on the vehicle's steering mechanism, guiding the vehicle to maintain the optimal driving posture throughout the test and avoiding interference caused by trajectory deviation or directional drift.

[0086] In one embodiment, the process of generating a throttle calibration table between throttle opening and acceleration based on the throttle response data in step S140 may include:

[0087] S141: Performing data fitting on the vehicle speed at different throttle openings in the throttle response data to generate an acceleration fitting curve.

[0088] S142: Generate a throttle calibration table between throttle opening and acceleration according to the acceleration fitting curve.

[0089] In this embodiment, when calibrating the throttle of an autonomous driving vehicle, the vehicle control system can perform data fitting on the vehicle speed at different throttle openings in the throttle response data to generate an acceleration fitting curve, and then generate a throttle calibration table between the throttle opening and the acceleration based on the acceleration fitting curve to support dynamic matching between the throttle opening and the acceleration command.

[0090] Specifically, through the throttle response data, the vehicle control system can analyze the vehicle speed that changes over time under each set of throttle openings. By performing numerical differentiation or differential calculations on the vehicle speed at each throttle opening, the corresponding acceleration curve can be obtained. Here, smoothing filtering, error elimination and other methods can also be used to optimize each acceleration curve to ensure the continuity and accuracy of the acceleration curve. Next, the vehicle control system can perform interpolation fitting based on the acceleration data points in the acceleration curve corresponding to each throttle opening to generate an acceleration fitting curve that represents the relationship between throttle opening and acceleration. By sorting the acceleration fitting curves corresponding to all throttle openings, a throttle calibration table covering multiple throttle opening ranges can be constructed to achieve a high-precision mapping relationship between throttle opening and acceleration.

[0091] The vehicle throttle calibration device provided in an embodiment of the present application is described below. The vehicle throttle calibration device described below and the vehicle throttle calibration method described above can be referenced to each other.

[0092] In one embodiment, Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of a vehicle throttle calibration device provided in an embodiment of the present application. The present application also provides a vehicle throttle calibration device, including a vehicle test module 210, a data acquisition module 220, a direction control module 230, and a throttle calibration module 240, specifically including the following:

[0093] The vehicle testing module 210 is configured to set initial test values ​​for the autonomous driving vehicle and start the autonomous driving vehicle on a test track based on the initial test values ​​to enter a throttle calibration test.

[0094] The data acquisition module 220 is configured to acquire the center point of the rear axle of the autonomous driving vehicle in real time during the driving process, and to determine the closest point on the center line of the test lane that is closest to the center point of the rear axle;

[0095] a direction control module 230 for determining a lateral distance deviation and a heading deviation of the autonomous driving vehicle based on the rear axle center point and the closest point of the centerline, and controlling the driving direction of the autonomous driving vehicle based on the lateral distance deviation and the heading deviation until the throttle calibration test is completed;

[0096] The throttle calibration module 240 is used to obtain throttle response data generated by the autonomous driving vehicle during the throttle calibration test, and generate a throttle calibration table between throttle opening and acceleration based on the throttle response data.

[0097] In the above embodiment, before the throttle calibration test, the test initial values ​​of the autonomous driving vehicle can be set first, and then the autonomous driving vehicle can be started on the test lane based on the test initial values ​​so that the vehicle moves forward and enters the throttle calibration test. During the vehicle's driving process, the center point of the autonomous driving vehicle's rear axle can be collected in real time, and the closest centerline point closest to the center point of the rear axle can be determined from the centerline of the test lane to provide data support for the subsequent accurate calculation of the vehicle's direction deviation. Here, the lateral distance deviation and heading deviation of the autonomous driving vehicle can be determined based on the rear axle center point and the closest centerline point. Then, the driving direction of the autonomous driving vehicle can be accurately controlled based on the lateral distance deviation and heading deviation to ensure that the vehicle always moves along the centerline of the test lane during the throttle calibration test. Through precise control and stable testing of the vehicle's driving direction, the throttle response data generated by the autonomous driving vehicle during the throttle calibration test has high accuracy and reliability. Therefore, the throttle calibration table generated based on the throttle response data can truly reflect the relationship between the autonomous driving vehicle and acceleration at different throttle openings.

[0098] In one embodiment, the initial test values ​​in the vehicle test module 210 may include multiple throttle opening calibration values, brake values, and vehicle maximum speed; the vehicle test module 210 may further include:

[0099] The vehicle start-stop submodule is used to start the autonomous vehicle forward on the test lane using each throttle opening calibration quantity until the autonomous vehicle reaches the maximum vehicle speed, and then decelerate and stop the autonomous vehicle according to the braking amount.

[0100] In one embodiment, the data collection module 220 may include:

[0101] The discrete sampling submodule is used to discretely sample the road centerline of the experimental lane to obtain multiple centerline discrete points.

[0102] The distance calculation submodule is used to determine the Euclidean distance between each centerline discrete point and the rear axle center point, and to take the centerline discrete point with the smallest Euclidean distance as the centerline closest point closest to the rear axle center point.

[0103] In one embodiment, the direction control module 230 may include:

[0104]

[0105] Where, Indicates the lateral distance deviation; Indicates the vertical coordinate of the center point of the rear axle; Indicates the horizontal coordinate of the rear axle center point; Indicates the ordinate of the nearest point on the center line; Indicates the horizontal coordinate of the nearest point on the center line; Indicates the road heading at the nearest point on the centerline.

[0106] In one embodiment, the direction control module 230 may further include:

[0107]

[0108] Where, Indicates heading deviation; Indicates the vehicle heading at the center point of the rear axle; Indicates the road heading at the nearest point on the centerline.

[0109] In one embodiment, the direction control module 230 may further include:

[0110] The steering angle calculation submodule uses the built-in linear quadratic regulator of the autonomous vehicle to calculate the steering angle based on the lateral distance deviation and heading deviation, and adjusts the steering wheel angle of the autonomous vehicle based on the solution results.

[0111] In one embodiment, the throttle calibration module 240 may include:

[0112] The curve fitting submodule is used to perform data fitting on the vehicle speed at different throttle openings in the throttle response data and generate an acceleration fitting curve.

[0113] The throttle calibration submodule is used to generate a throttle calibration table between throttle opening and acceleration according to the acceleration fitting curve.

[0114] In one embodiment, the present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the vehicle throttle calibration method as described in any of the above embodiments.

[0115] In one embodiment, the present application also provides a computer device having computer-readable instructions stored therein. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the vehicle throttle calibration method as described in any one of the above embodiments.

[0116] Schematically, as Figure 4 As shown, Figure 4 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. The computer device 300 can be provided as a server. Figure 4 Computer device 300 includes a processing component 302, which further includes one or more processors, and a memory resource represented by memory 301 for storing instructions executable by processing component 302, such as an application. The application stored in memory 301 may include one or more modules, each corresponding to a set of instructions. In addition, processing component 302 is configured to execute the instructions to perform the vehicle throttle calibration method according to any of the above embodiments.

[0117] The computer device 300 may further include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 may operate based on an operating system stored in the memory 301, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or the like.

[0118] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0119] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0120] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referenced to each other.

[0121] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A vehicle throttle calibration method, characterized in that: The method comprises: Setting initial test values ​​for the autonomous driving vehicle, and starting the autonomous driving vehicle on a test track based on the initial test values ​​to enter a throttle calibration test; During the driving process of the vehicle, the center point of the rear axle of the autonomous driving vehicle is collected in real time, and the closest point of the center line closest to the center point of the rear axle is determined on the center line of the road of the test lane; determining a lateral distance deviation and a heading deviation of the autonomous driving vehicle based on the rear axle center point and the closest point of the centerline, and controlling a driving direction of the autonomous driving vehicle based on the lateral distance deviation and the heading deviation until the throttle calibration test is completed; Acquire throttle response data generated by the autonomous driving vehicle during the throttle calibration test, and generate a throttle calibration table between throttle opening and acceleration based on the throttle response data.

2. The vehicle throttle calibration method according to claim 1, characterized in that: The test initial values ​​include a plurality of throttle opening calibration values, brake values ​​and vehicle maximum speed; The step of starting the autonomous driving vehicle on a test track based on the test initial value and entering a throttle calibration test includes: For each throttle opening calibration amount, the autonomous driving vehicle is started to move forward on the test lane using the throttle opening calibration amount until the autonomous driving vehicle reaches the maximum speed of the vehicle, and the autonomous driving vehicle is decelerated and stopped according to the braking amount.

3. The vehicle throttle calibration method according to claim 1, characterized in that: Determining the nearest point on the center line of the test lane that is closest to the center point of the rear axle includes: Discretely sampling the center line of the experimental lane to obtain a plurality of center line discrete points; The Euclidean distance between each centerline discrete point and the rear axle center point is determined, and the centerline discrete point with the smallest Euclidean distance is used as the centerline closest point closest to the rear axle center point.

4. The vehicle throttle calibration method according to claim 1, characterized in that: The calculation expression of the lateral distance deviation includes: Where, Indicates the lateral distance deviation; Indicates the vertical coordinate of the center point of the rear axle; Indicates the horizontal coordinate of the rear axle center point; Indicates the ordinate of the nearest point on the center line; Indicates the horizontal coordinate of the nearest point on the center line; Indicates the road heading at the nearest point on the centerline.

5. The vehicle throttle calibration method according to claim 1, characterized in that: The calculation expression of the heading deviation includes: Where, Indicates heading deviation; Indicates the vehicle heading at the center point of the rear axle; Indicates the road heading at the nearest point on the centerline.

6. The vehicle throttle calibration method according to claim 1, characterized in that: The controlling the driving direction of the autonomous driving vehicle based on the lateral distance deviation and the heading deviation includes: A linear quadratic regulator built into the autonomous driving vehicle is used to solve the steering angle based on the lateral distance deviation and the heading deviation, and the steering wheel angle of the autonomous driving vehicle is adjusted according to the solution result.

7. The vehicle throttle calibration method according to claim 1, characterized in that: The generating of a throttle calibration table between throttle opening and acceleration based on the throttle response data comprises: Performing data fitting on the vehicle speed at different throttle openings in the throttle response data to generate an acceleration fitting curve; A throttle calibration table between throttle opening and acceleration is generated according to the acceleration fitting curve.

8. A vehicle throttle calibration device, characterized in that: include: A vehicle testing module, configured to set initial test values ​​for the autonomous driving vehicle and, based on the initial test values, start the autonomous driving vehicle on a test track to enter a throttle calibration test; a data acquisition module, configured to acquire the center point of the rear axle of the autonomous driving vehicle in real time during driving, and to determine the nearest point on the center line of the experimental lane that is closest to the center point of the rear axle; a direction control module, configured to determine a lateral distance deviation and a heading deviation of the autonomous driving vehicle based on the rear axle center point and the closest point of the centerline, and to control a driving direction of the autonomous driving vehicle based on the lateral distance deviation and the heading deviation until the throttle calibration test is completed; A throttle calibration module is used to obtain throttle response data generated by the autonomous driving vehicle during the throttle calibration test, and generate a throttle calibration table between throttle opening and acceleration based on the throttle response data.

9. A storage medium, characterized in that: The storage medium stores computer-readable instructions, which, when executed by one or more processors, enable the one or more processors to perform the steps of the vehicle throttle calibration method according to any one of claims 1 to 7.

10. A computer device, characterized in that: include: one or more processors, and memory; The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the vehicle throttle calibration method according to any one of claims 1 to 7 are performed.

Images