A method, system, and medium for online detection and compensation of a delay in a steer-by-wire mechanism

Abstract

The present application relates to a kind of online detection compensation method, system and medium of delay of steer-by-wire mechanism execution, the method comprises: Q1. Vehicle travels to bend, the heading angle data information of vehicle is acquired in real time based on vehicle IMU, the turning angle data information of vehicle is acquired in real time based on vehicle angle sensor, and simultaneously input to trained neural network model and carry out fusion, output the fusion vehicle turning angle data information;Q2. Based on the fusion vehicle turning angle data information, using reinforcement vehicle turning angle differential learning algorithm, the data information of vehicle turning angle change rate at any time is obtained, if the data information of vehicle turning angle change rate at continuous multiple times is less than preset steering mechanism nominal parameter, then it is judged that vehicle is in delay steering state, enter step Q3. The present application not only guarantees that vehicle can still travel along the intended path under abnormal conditions, but also improves the reliability and safety of automatic driving system.

Description

Technical Field

[0001] This invention relates to the field of steering mechanism technology for autonomous vehicles, and in particular to an online detection and compensation method, system and medium for the execution delay of a steer-by-wire mechanism. Background Technology

[0002] The path tracking accuracy and stability of autonomous vehicles are closely related to the performance of their EPS (Electric Power Steering) system. The rapid response and precise execution of the EPS to the desired steering angle are the foundation for the smooth operation of autonomous vehicles. With the large-scale deployment and continuous operation of autonomous vehicles, it is inevitable that some vehicles will experience aging steering actuators or significant differences in performance consistency, which poses certain difficulties for the rapid mass deployment of autonomous driving.

[0003] Steering execution delay is a typical example of reduced EPS drive-by-wire performance in vehicles. It is more likely to occur when some heavy truck chassis work for a long time, causing the power steering oil temperature to be too high or the vehicle load to be large. Specifically, it manifests as a decrease in the vehicle's maximum steering angular velocity. When the requested steering angle changes significantly, it takes a long time for the actual steering angle to reach the requested angle. This leads to a decrease in the accuracy of autonomous driving path tracking, resulting in S-shaped behavior when driving straight and out-of-line tracking when the vehicle is on a curve with large curvature, which affects the normal operation of autonomous driving. Summary of the Invention

[0004] In view of the above problems, the present invention provides an online detection and compensation method, system and medium for the execution delay of the steer-by-wire mechanism, which not only ensures that the vehicle can still travel along the expected path under abnormal conditions, but also improves the reliability and safety of the autonomous driving system.

[0005] To achieve the above and other related objectives, the present invention provides the following technical solution:

[0006] An online detection and compensation method for execution delay of a steer-by-wire mechanism, the method comprising:

[0007] Q1. When the vehicle is driving to a curve, the vehicle's heading angle data is acquired in real time based on the onboard IMU and the turning angle data is acquired in real time based on the onboard angle sensor. These data are simultaneously input into a trained neural network model for fusion, and the fused vehicle turning angle data is output.

[0008] Q2. Based on the fused vehicle steering angle data, an enhanced vehicle steering angle differential learning algorithm is used to obtain the vehicle steering angle change rate data at any time. If the vehicle steering angle change rate data is less than the preset steering mechanism nominal parameter at multiple consecutive times, it is determined that the vehicle is in a delayed steering state and proceeds to step Q3.

[0009] Q3. Based on the fact that the vehicle is in a delayed steering state, obtain the vehicle's requested turning angle data information, and use an enhanced vehicle turning angle integral learning algorithm to obtain the time interval data information from the current turning angle to the requested turning angle;

[0010] Q4. Based on the time interval data information of the vehicle from the current turning angle to the requested turning angle, the aiming distance compensation algorithm is used to obtain the vehicle compensation state data information, and the vehicle compensation state data information is input into the multimodal lateral control algorithm to compensate the vehicle's turning angle, and the compensated vehicle turning angle data information is output.

[0011] Furthermore, in step Q1, the simultaneous input to the trained neural network model for fusion includes:

[0012] Q11. Input the heading angle data and turning angle data of the vehicle into the neural network model for training and learning, determine the network parameters, and obtain the trained neural network model;

[0013] Q12. Based on the trained neural network model, input the real-time acquired vehicle heading angle data and vehicle turning angle data, perform data fusion, and obtain fused vehicle turning angle data.

[0014] Furthermore, the activation function of the neural network model is F.

[0015]

[0016] Where n is the total number of samples, A i Let B be the i-th feature matrix of the vehicle's heading angle data. i Let α be the i-th feature matrix of the vehicle's turning angle data. i β is the weight matrix corresponding to the vehicle's heading angle. i This is the weight matrix corresponding to the turning angle of the vehicle.

[0017] Furthermore, in step Q2, the data information on the rate of change of vehicle steering angle at any given time obtained by employing the enhanced vehicle steering angle differential learning algorithm includes:

[0018] Q21. Collect the fused vehicle steering angle data θ at time t. t The vehicle steering angle data θ after fusion with the data at time t+Δt t+Δt Establish the vehicle steering angle change rate function G.

[0019]

[0020] Wherein, λ1 and λ2 are weighting coefficients, and the constraints on the weighting coefficients λ1 and λ2 are as follows:

[0021] The values ​​of λ1 and λ2 are related to the fused vehicle turning angle data at different times.

[0022] Q22. Based on the vehicle steering angle change rate function G, obtain the data information of the vehicle steering angle change rate at any time.

[0023] Furthermore, in step Q4, the process of using the pre-aiming distance compensation algorithm to obtain vehicle compensation status data information includes:

[0024] Q411. Based on the time interval data from the current turning angle to the requested turning angle of the vehicle, establish a pre-aiming distance function P.

[0025] P = k3 * v * T1, where k3 is a constant parameter, v is the vehicle speed, and T1 is the time interval from the current turning angle to the requested turning angle, thus obtaining the vehicle's aiming distance data.

[0026] Q412. Based on the vehicle's pre-aiming distance data, the steering wheel angle required for the vehicle to reach the position under the current steering response delay time is obtained, thereby obtaining the vehicle compensation state data.

[0027] The step of inputting the vehicle compensation state data information into the multimodal lateral control algorithm to compensate for the vehicle's steering angle includes:

[0028] Q421. Based on the vehicle compensation state data, establish a multimodal lateral control function H.

[0029]

[0030] Where t is time, γ1, γ2, γ3 and γ4 are compensation factors, and (c1, c2) is vehicle compensation status data information;

[0031] Q422. Based on the multimodal lateral control function H, obtain the compensated vehicle steering angle data.

[0032] Furthermore, in step Q3, the time interval data information obtained by employing the enhanced vehicle turning angle integral learning algorithm from the current turning angle to the requested turning angle includes:

[0033] Q31. Obtain the fused vehicle turning angle data and the vehicle requested turning angle data at the current moment, and establish a time interval function T between the current turning angle and the requested turning angle.

[0034]

[0035] Where φ1 is the vehicle's requested turning angle function at the current moment, φ2 is the fused vehicle turning angle function at the current moment, θ2 is the vehicle's requested turning angle data at the current moment, θ1 is the fused vehicle turning angle data at the current moment, and ρ θ The rate of change of the vehicle's turning angle from the current moment's merged turning angle to the vehicle's requested turning angle;

[0036] Q32. Based on the time interval function T between the current turning angle and the requested turning angle, obtain the time interval data information of the vehicle from the current turning angle to the requested turning angle.

[0037] Furthermore, the rate of change ρ of the vehicle's turning angle from the current moment's fused turning angle to the vehicle's requested turning angle... θ ,

[0038]

[0039] Where N is the total number of samples, θ j+1 Let θ be the angle between the merged vehicle turning angle and the vehicle's requested turning angle at time j+1. j Let Δt be the angle between the merged vehicle turning angle and the vehicle's requested turning angle at time j, and let Δt be the time taken from time j to time j+1 between the merged vehicle turning angle and the vehicle's requested turning angle.

[0040] Furthermore, the vehicle's requested turning angle function φ1 at the current moment is,

[0041]

[0042] Where L is a constant, Let v be the vehicle's turning angle after merging, k be the radius of curvature, and v be the radius of curvature. x (t) represents the speed of the vehicle at time t;

[0043] The vehicle steering angle function φ2 after fusion at the current moment is:

[0044] φ2 = k1θ + b, where k1 and b are constant parameters of the function, and θ is the vehicle turning angle.

[0045] To achieve the above and other related objectives, the present invention also provides an online detection and compensation system for the execution delay of a steer-by-wire mechanism, including a computer device programmed or configured to perform the steps of any of the online detection and compensation methods for the execution delay of a steer-by-wire mechanism described in any one of the present inventions.

[0046] To achieve the above and other related objectives, the present invention also provides a computer-readable storage medium storing a computer program programmed or configured to perform the online detection and compensation method for the execution delay of any of the above-described steering-by-wire mechanisms.

[0047] The present invention has the following positive effects:

[0048] 1. This invention uses a trained neural network model to fuse data and combines it with an enhanced vehicle steering angle differential learning algorithm to obtain data information on the rate of change of vehicle steering angle at any given time. This not only allows for more accurate acquisition of vehicle steering angle data, but also enables timely transmission of fault codes to the fault diagnosis module when there is an execution delay in the steering mechanism.

[0049] 2. This invention uses the time interval data from the current turning angle to the requested turning angle of the vehicle, and adopts a pre-aiming distance compensation algorithm to obtain vehicle compensation state data information. The vehicle compensation state data information is then input into a multimodal lateral control algorithm to compensate for the turning angle of the vehicle. This not only ensures that the vehicle can still travel along the expected path under abnormal conditions, but also improves the reliability and safety of the autonomous driving system. Attached Figure Description

[0050] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0051] Figure 2 This is a schematic diagram illustrating the dynamic response delay of the steering actuator of the present invention;

[0052] Figure 3 This is a schematic diagram of the lateral control process of the present invention. Detailed Implementation

[0053] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0054] Example 1: As Figure 1 or Figure 2 or Figure 3 As shown, an online detection and compensation method for the execution delay of a steer-by-wire mechanism is disclosed, the method comprising:

[0055] Q1. When the vehicle is driving to a curve, the vehicle's heading angle data is acquired in real time based on the onboard IMU and the turning angle data is acquired in real time based on the onboard angle sensor. These data are simultaneously input into a trained neural network model for fusion, and the fused vehicle turning angle data is output.

[0056] Q2. Based on the fused vehicle steering angle data, an enhanced vehicle steering angle differential learning algorithm is used to obtain the vehicle steering angle change rate data at any time. If the vehicle steering angle change rate data is less than the preset steering mechanism nominal parameter at multiple consecutive times, it is determined that the vehicle is in a delayed steering state and proceeds to step Q3.

[0057] Q3. Based on the fact that the vehicle is in a delayed steering state, obtain the vehicle's requested turning angle data information, and use an enhanced vehicle turning angle integral learning algorithm to obtain the time interval data information from the current turning angle to the requested turning angle;

[0058] Q4. Based on the time interval data information of the vehicle from the current turning angle to the requested turning angle, the aiming distance compensation algorithm is used to obtain the vehicle compensation state data information, and the vehicle compensation state data information is input into the multimodal lateral control algorithm to compensate the vehicle's turning angle, and the compensated vehicle turning angle data information is output.

[0059] In this embodiment, in step Q1, the simultaneous input to the trained neural network model for fusion includes:

[0060] Q11. Input the heading angle data and turning angle data of the vehicle into the neural network model for training and learning, determine the network parameters, and obtain the trained neural network model;

[0061] Q12. Based on the trained neural network model, input the real-time acquired vehicle heading angle data and vehicle turning angle data, perform data fusion, and obtain fused vehicle turning angle data.

[0062] In this embodiment, the activation function of the neural network model is F.

[0063]

[0064] Where n is the total number of samples, A i Let B be the i-th feature matrix of the vehicle's heading angle data. i Let α be the i-th feature matrix of the vehicle's turning angle data. i β is the weight matrix corresponding to the vehicle's heading angle. i This is the weight matrix corresponding to the turning angle of the vehicle.

[0065] In this embodiment, in step Q2, the data information on the rate of change of vehicle steering angle at any given time obtained by employing an enhanced vehicle steering angle differential learning algorithm includes:

[0066] Q21. Collect the fused vehicle steering angle data θ at time t. t The vehicle steering angle data θ after fusion with the data at time t+Δtt+Δt Establish the vehicle steering angle change rate function G.

[0067]

[0068] Wherein, λ1 and λ2 are weighting coefficients, and the constraints on the weighting coefficients λ1 and λ2 are as follows:

[0069] The values ​​of λ1 and λ2 are related to the fused vehicle turning angle data at different times.

[0070] Q22. Based on the vehicle steering angle change rate function G, obtain the data information of the vehicle steering angle change rate at any time.

[0071] In this embodiment, in step Q4, the process of using the pre-aiming distance compensation algorithm to obtain vehicle compensation status data information includes:

[0072] Q411. Based on the time interval data from the current turning angle to the requested turning angle of the vehicle, establish a pre-aiming distance function P.

[0073] P = k3 * v * T1, where k3 is a constant parameter, v is the vehicle speed, and T1 is the time interval from the current turning angle to the requested turning angle, thus obtaining the vehicle's aiming distance data.

[0074] Q412. Based on the vehicle's pre-aiming distance data, the steering wheel angle required for the vehicle to reach the position under the current steering response delay time is obtained, thereby obtaining the vehicle compensation state data.

[0075] The step of inputting the vehicle compensation state data information into the multimodal lateral control algorithm to compensate for the vehicle's steering angle includes:

[0076] Q421. Based on the vehicle compensation state data, establish a multimodal lateral control function H.

[0077]

[0078] Where t is time, γ1, γ2, γ3 and γ4 are compensation factors, and (c1, c2) is vehicle compensation status data information;

[0079] Q422. Based on the multimodal lateral control function H, obtain the compensated vehicle steering angle data.

[0080] Example 2: Based on the online detection and compensation method for the execution delay of the steer-by-wire mechanism in Example 1, the present invention will be further explained and described below.

[0081] like Figure 1 or Figure 2 or Figure 3 As shown, an online detection and compensation method for the execution delay of a steer-by-wire mechanism is disclosed, the method comprising:

[0082] Q1. When the vehicle is driving to a curve, the vehicle's heading angle data is acquired in real time based on the onboard IMU and the turning angle data is acquired in real time based on the onboard angle sensor. These data are simultaneously input into a trained neural network model for fusion, and the fused vehicle turning angle data is output.

[0083] Q2. Based on the fused vehicle steering angle data, an enhanced vehicle steering angle differential learning algorithm is used to obtain the vehicle steering angle change rate data at any time. If the vehicle steering angle change rate data is less than the preset steering mechanism nominal parameter at multiple consecutive times, it is determined that the vehicle is in a delayed steering state and proceeds to step Q3.

[0084] Q3. Based on the fact that the vehicle is in a delayed steering state, obtain the vehicle's requested turning angle data information, and use an enhanced vehicle turning angle integral learning algorithm to obtain the time interval data information from the current turning angle to the requested turning angle;

[0085] Q4. Based on the time interval data information of the vehicle from the current turning angle to the requested turning angle, the aiming distance compensation algorithm is used to obtain the vehicle compensation state data information, and the vehicle compensation state data information is input into the multimodal lateral control algorithm to compensate the vehicle's turning angle, and the compensated vehicle turning angle data information is output.

[0086] In this embodiment, in step Q3, obtaining the time interval data information from the current turning angle to the requested turning angle using an enhanced vehicle turning angle integral learning algorithm includes:

[0087] Q31. Obtain the fused vehicle turning angle data and the vehicle requested turning angle data at the current moment, and establish a time interval function T between the current turning angle and the requested turning angle.

[0088]

[0089] Where φ1 is the vehicle's requested turning angle function at the current moment, φ2 is the fused vehicle turning angle function at the current moment, θ2 is the vehicle's requested turning angle data at the current moment, θ1 is the fused vehicle turning angle data at the current moment, and ρ θ The rate of change of the vehicle's turning angle from the current moment's merged turning angle to the vehicle's requested turning angle;

[0090] Q32. Based on the time interval function T between the current turning angle and the requested turning angle, obtain the time interval data information of the vehicle from the current turning angle to the requested turning angle.

[0091] In this embodiment, the rate of change ρ of the vehicle's turning angle after fusion at the current moment to the vehicle's requested turning angle is... θ ,

[0092]

[0093] Where N is the total number of samples, θ j+1 Let θ be the angle between the merged vehicle turning angle and the vehicle's requested turning angle at time j+1. j Let Δt be the angle between the merged vehicle turning angle and the vehicle's requested turning angle at time j, and let Δt be the time taken from time j to time j+1 between the merged vehicle turning angle and the vehicle's requested turning angle.

[0094] In this embodiment, the vehicle's requested turning angle function φ1 at the current moment is,

[0095]

[0096] Where L is a constant, Let v be the vehicle's turning angle after merging, k be the radius of curvature, and v be the radius of curvature. x (t) represents the speed of the vehicle at time t;

[0097] The vehicle steering angle function φ2 after fusion at the current moment is:

[0098] φ2 = k1θ + b, where k1 and b are constant parameters of the function, and θ is the vehicle turning angle.

[0099] The present invention provides an online detection and compensation system for the execution delay of a steer-by-wire mechanism, comprising a computer device programmed or configured to perform the steps of any of the online detection and compensation methods for the execution delay of a steer-by-wire mechanism described in the present invention.

[0100] The present invention provides a computer-readable storage medium storing a computer program programmed or configured to perform an online detection and compensation method for the execution delay of any of the above-described steering-by-wire mechanisms.

[0101] Any references to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0102] In summary, this invention not only ensures that the vehicle can still travel along the expected path under abnormal conditions, but also improves the reliability and safety of the autonomous driving system.

[0103] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An online detection and compensation method for the execution delay of a steer-by-wire mechanism, characterized in that, The method includes: Q1. When the vehicle is driving to a curve, the vehicle's heading angle data is acquired in real time based on the onboard IMU and the turning angle data is acquired in real time based on the onboard angle sensor. These data are simultaneously input into a trained neural network model for fusion, and the fused vehicle turning angle data is output. Q2. Based on the fused vehicle steering angle data, an enhanced vehicle steering angle differential learning algorithm is used to obtain the vehicle steering angle change rate data at any time. If the vehicle steering angle change rate data is less than the preset steering mechanism nominal parameter at multiple consecutive times, it is determined that the vehicle is in a delayed steering state and proceeds to step Q3. Q3. Based on the fact that the vehicle is in a delayed steering state, obtain the vehicle's requested turning angle data information, and use an enhanced vehicle turning angle integral learning algorithm to obtain the time interval data information from the current turning angle to the requested turning angle; Q4. Based on the time interval data information of the vehicle from the current turning angle to the requested turning angle, the aiming distance compensation algorithm is used to obtain the vehicle compensation state data information, and the vehicle compensation state data information is input into the multimodal lateral control algorithm to compensate the vehicle's turning angle, and the compensated vehicle turning angle data information is output. In step Q4, the process of using the pre-aiming distance compensation algorithm to obtain vehicle compensation status data information includes: Q411. Based on the time interval data from the current turning angle to the requested turning angle of the vehicle, establish a pre-aiming distance function P. P=k3*v*T1, Where k3 is a constant parameter, v is the vehicle speed, and T1 is the time interval from the current turning angle to the requested turning angle, the vehicle's aiming distance data is obtained. Q412. Based on the vehicle's pre-aiming distance data, the steering wheel angle required for the vehicle to reach the position under the current steering response delay time is obtained, thereby obtaining the vehicle compensation state data. The step of inputting the vehicle compensation state data information into the multimodal lateral control algorithm to compensate for the vehicle's steering angle includes: Q421. Based on the vehicle compensation state data, establish a multimodal lateral control function H. ， Where t is time, γ1, γ2, γ3 and γ4 are compensation factors, and (c1, c2) are vehicle compensation status data. Q422. Based on the multimodal lateral control function H, obtain the compensated vehicle steering angle data.

2. The online detection and compensation method for the execution delay of the steer-by-wire mechanism according to claim 1, characterized in that, In step Q1, the simultaneous input to the trained neural network model for fusion includes: Q11. Input the heading angle data and turning angle data of the vehicle into the neural network model for training and learning, determine the network parameters, and obtain the trained neural network model; Q12. Based on the trained neural network model, input the real-time acquired vehicle heading angle data and vehicle turning angle data, perform data fusion, and obtain fused vehicle turning angle data.

3. The online detection and compensation method for the execution delay of the steer-by-wire mechanism according to claim 2, characterized in that: The activation function of the neural network model is F. ， Where n is the total number of samples, A i Let B be the i-th feature matrix of the vehicle's heading angle data. i Let α be the i-th feature matrix of the vehicle's turning angle data. i β is the weight matrix corresponding to the vehicle's heading angle. i This is the weight matrix corresponding to the turning angle of the vehicle.

4. The online detection and compensation method for the execution delay of the steer-by-wire mechanism according to claim 1, characterized in that, In step Q2, the data information on the rate of change of vehicle steering angle at any given time obtained by employing an enhanced vehicle steering angle differential learning algorithm includes: Q21. Collect the fused vehicle steering angle data θ at time t. t The vehicle steering angle data θ after fusion with the data at time t+∆t t+∆t Establish the vehicle steering angle change rate function G. , Wherein, λ1 and λ2 are weighting coefficients, and the constraints on the weighting coefficients λ1 and λ2 are as follows: ， The values ​​of λ1 and λ2 are related to the fused vehicle turning angle data at different times. Q22. Based on the vehicle steering angle change rate function G, obtain the data information of the vehicle steering angle change rate at any time.

5. The online detection and compensation method for the execution delay of the steer-by-wire mechanism according to claim 1, characterized in that, In step Q3, the time interval data information obtained by using the enhanced vehicle turning angle integral learning algorithm from the current turning angle to the requested turning angle includes: Q31. Obtain the fused vehicle turning angle data and the vehicle requested turning angle data at the current moment, and establish a time interval function T between the current turning angle and the requested turning angle. ， Where φ1 is the vehicle's requested turning angle function at the current moment, φ2 is the fused vehicle turning angle function at the current moment, θ2 is the vehicle's requested turning angle data at the current moment, θ1 is the fused vehicle turning angle data at the current moment, and ρ θ The rate of change of the vehicle's turning angle from the current moment's merged turning angle to the vehicle's requested turning angle; Q32. Based on the time interval function T between the current turning angle and the requested turning angle, obtain the time interval data information of the vehicle from the current turning angle to the requested turning angle.

6. The online detection and compensation method for the execution delay of the steer-by-wire mechanism according to claim 5, characterized in that: The rate of change ρ of the angle from the vehicle's current turning angle to the vehicle's requested turning angle. θ , ， Where N is the total number of samples, θ j+1 Let θ be the angle between the merged vehicle turning angle and the vehicle's requested turning angle at time j+1. j Let ∆t be the angle between the merged vehicle turning angle and the vehicle's requested turning angle at time j, and let ∆t be the time taken from time j to time j+1 between the merged vehicle turning angle and the vehicle's requested turning angle.

7. The online detection and compensation method for the execution delay of the steer-by-wire mechanism according to claim 5, characterized in that: The vehicle's requested turning angle function φ1 at the current moment is... ， Where L is a constant, Let v be the vehicle's turning angle after merging, k be the radius of curvature, and v be the radius of curvature. x (t) represents the speed of the vehicle at time t; The vehicle steering angle function φ2 after fusion at the current moment is: ， Where k1 and b are constant parameters of the function, and θ is the vehicle turning angle.

8. An online detection and compensation system for the execution delay of a steer-by-wire mechanism, comprising a computer device, characterized in that, The computer device is programmed or configured to perform the steps of the online detection and compensation method for the execution delay of the steering-by-wire mechanism as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is programmed or configured to perform the online detection and compensation method for the execution delay of the steering-by-wire mechanism as described in any one of claims 1 to 7.

Images