A method, apparatus, device and medium for generating a vehicle steering instruction

Abstract

The present disclosure relates to the technical field of automatic driving, and particularly relates to a vehicle steering instruction generation method and device, equipment and a medium. The method comprises: periodically updating an unstable coefficient of a vehicle steering actuator after the vehicle is started; obtaining the current unstable coefficient when a steering trigger instruction of the vehicle is received; determining a control increment weight based on the current unstable coefficient; and generating the vehicle steering instruction based on the control increment weight, wherein the vehicle steering instruction comprises vehicle target steering angle data. The technical scheme provided in the present disclosure embodiment obtains the unstable coefficient reflecting the response capability of the vehicle steering actuator before generating the vehicle steering instruction each time, adjusts the MPC control increment weight based on the obtained unstable coefficient, further generates the vehicle steering instruction most suitable for the current situation, improves the stability and accuracy of vehicle steering, and further improves the robustness of the MPC trajectory tracking control algorithm.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, and in particular to a method, apparatus, device, and medium for generating vehicle steering commands. Background Technology

[0002] Model Predictive Control (MPC) is an important technology for trajectory tracking control of autonomous vehicles. Its principle is to generate control commands such as vehicle steering commands based on the current tracking error (such as the position error and direction error between the actual driving trajectory and the predetermined trajectory), thereby controlling the vehicle to drive along the predetermined trajectory.

[0003] In the process of generating vehicle steering commands based on MPC technology, the control increment weight is often a crucial parameter to consider. Changing the control increment weight alters the rate of change of the target steering angle in the steering command. A larger control increment weight results in a faster change of the target steering angle, requiring rapid vehicle steering and leading to poor vehicle stability. Conversely, a smaller control increment weight results in a slower change of the target steering angle, requiring slower steering and improving vehicle stability, but potentially slowing down the convergence of tracking errors. Therefore, setting the control increment weight appropriately is essential in MPC technology.

[0004] Currently, after the vehicle system development process is completed, the control increment weight is often set to a fixed value. Using this method to control the vehicle may lead to a deterioration in control effectiveness due to changes in the vehicle's driving environment and state. For example, during development, when the vehicle is traveling at 100 kph on a straight road, a control increment weight of 1000 can ensure good vehicle stability. However, after the vehicle has traveled 10,000 km, due to wear and tear on the steering system and increased damping of the steering mechanism, the steering system's control capability weakens compared to the development stage. In other words, the actual response of the steering system deteriorates. If the control increment weight is still set to 1000, the slower response of the steering system will cause the error between the target turning angle and the actual turning angle to increase, leading to a larger and larger error between the actual trajectory and the preset trajectory. In severe cases, control failure may even occur, causing the vehicle to lose stability and resulting in traffic accidents. Summary of the Invention

[0005] To address the aforementioned technical problems, this disclosure provides a method, apparatus, device, and medium for generating vehicle steering commands.

[0006] In a first aspect, this disclosure provides a method for generating vehicle steering commands, including:

[0007] After the vehicle starts, the instability coefficient of the vehicle steering actuator is updated periodically;

[0008] Upon receiving a steering trigger command from the vehicle, obtain the current instability coefficient;

[0009] Based on the current instability coefficient, determine the control increment weight;

[0010] Based on the control increment weights, the vehicle steering command is generated, and the vehicle steering command includes the vehicle target turning angle data.

[0011] In some embodiments, if the instability coefficient update time is not the vehicle start-up time, the periodic update of the vehicle steering actuator's instability coefficient includes:

[0012] Obtain the instability coefficient at the previous update time;

[0013] Determine the change in the instability coefficient for the current time window, where the current time window refers to the time period between the previous update time and the current update time.

[0014] The instability coefficient at the current update time is determined based on the instability coefficient at the previous update time and the change in the instability coefficient at the current time window.

[0015] In some embodiments, if the instability coefficient is updated at the time of vehicle startup, the instability coefficient is zero after the update.

[0016] In some embodiments, determining the change in the instability coefficient within the current time window includes:

[0017] Obtain the actual increment and target increment of the vehicle steering angle within the current time window;

[0018] Based on the actual increment and the target increment, the change in the instability coefficient for this time window is determined.

[0019] In some embodiments, the time of the Pth update of the instability coefficient is the same as the time of the Qth generation of the vehicle steering command; the time of the (P+1)th update of the instability coefficient is the same as the time of the (Q+m)th generation of the vehicle steering command; where P, Q, and m are all positive integers;

[0020] When the instability coefficient is updated for the (P+1)th time, obtaining the actual increment and target increment of the vehicle steering angle within the current time window includes:

[0021] Obtain the first steering wheel angle data of the vehicle at the time of the Pth update of the instability coefficient and the second steering wheel angle data of the vehicle at the time of the (P+1)th update of the instability coefficient;

[0022] Based on the first steering wheel angle data and the second steering wheel angle data, the actual increment of the vehicle steering angle within the current time window is determined;

[0023] Obtain the vehicle target angle data from all vehicle steering commands generated from the Qth to the Q+m-1th generation;

[0024] Based on the vehicle target turning angle data in all the vehicle turning commands generated from the Qth to the Q+m-1th time, the target increment of the vehicle turning angle within the current time window is determined.

[0025] In some embodiments, determining the change in the instability coefficient within the current time window based on the actual increment and the target increment includes:

[0026] If the product of the actual increment and the target increment is greater than or equal to 0, and the absolute value of the difference between the actual increment and the target increment is less than or equal to the first set threshold, the change in the instability coefficient of the current time window is determined to be the first preset value.

[0027] If the product of the actual increment and the target increment is greater than or equal to 0, and the absolute value of the difference between the actual increment and the target increment is greater than the first preset threshold, the change in the instability coefficient of the current time window is determined to be the second preset value.

[0028] If the product of the actual increment and the target increment is less than 0, the change in the instability coefficient of this time window is determined to be the third preset value;

[0029] The first preset value is less than 0, the second preset value and the third preset value are both greater than 0, and the second preset value is less than or equal to the third preset value.

[0030] In some embodiments, the absolute value of the first preset value is less than or equal to the absolute value of the second preset value.

[0031] In some embodiments, determining the control increment weight based on the current instability coefficient includes:

[0032] Based on the current instability coefficient and the basic weight of the control increment, the control increment weight is determined.

[0033] In some embodiments, the control increment weights are determined based on the current instability coefficient, the basic weights of the control increment, and the following formula;

[0034] ρ=ρ base *e α

[0035] Where, ρ base To control the incremental base weights; α is the current instability coefficient.

[0036] Secondly, this disclosure also provides a vehicle steering command generation apparatus, comprising:

[0037] The update module is used to periodically update the instability coefficient of the vehicle steering actuator after the vehicle is started.

[0038] The acquisition module is used to acquire the current instability coefficient when a steering trigger command is received from the vehicle.

[0039] The determination module is used to determine the control increment weights based on the current instability coefficient;

[0040] The generation module is used to generate the vehicle steering command based on the control increment weight, the vehicle steering command including the vehicle target turning angle data.

[0041] Thirdly, this disclosure also provides an electronic device, including: a processor and a memory;

[0042] The processor executes the steps of any of the above methods by calling programs or instructions stored in memory.

[0043] Fourthly, this disclosure also provides a computer-readable storage medium that stores a program or instructions that cause a computer to perform the steps of any of the above methods.

[0044] Compared with the prior art, the technical solution provided in this disclosure has the following advantages: by monitoring the response stability of the vehicle steering system in real time, the current instability coefficient is obtained before each vehicle steering command is generated, and the MPC control increment weight is automatically adjusted according to the current instability coefficient to further generate the most suitable vehicle steering command for the current situation. This avoids vehicle control instability caused by the weakening of the vehicle steering system's response capability due to changes in vehicle parameters or environment, and further improves the robustness of the MPC trajectory tracking control algorithm under different vehicle parameters and different environments. Attached Figure Description

[0045] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0046] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1A flowchart illustrating a method for generating vehicle steering commands according to an embodiment of this disclosure;

[0048] Figure 2 A flowchart illustrating a method for periodically updating the instability coefficient when the instability coefficient update time is not the vehicle start-up time, provided as an embodiment of this disclosure;

[0049] Figure 3 To control a vehicle using the technical solution provided in this embodiment, a graph showing the change of vehicle steering angle over time is provided.

[0050] Figure 4 Based on Figure 3 The graph showing the change of the instability coefficient over time is obtained.

[0051] Figure 5 A graph showing the relationship between the control increment weight and the instability coefficient is provided in this embodiment of the disclosure;

[0052] Figure 6 A schematic diagram of a vehicle steering command generation device provided in an embodiment of this disclosure;

[0053] Figure 7 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0054] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0055] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0056] Figure 1 A flowchart illustrating a method for generating vehicle steering commands according to an embodiment of this disclosure is provided. This method is applicable to autonomous vehicles and can be executed by a vehicle control system. The method includes the following steps:

[0057] S101. After the vehicle starts, the instability coefficient of the vehicle steering actuator is updated periodically.

[0058] The instability coefficient characterizes the stability of the current vehicle steering actuator's response.

[0059] From the moment the vehicle starts, the vehicle control system updates the instability coefficient at regular intervals. The instability coefficient characterizes the stability of the vehicle's steering actuator response, i.e., the vehicle's ability to execute MPC commands. Because the steering system experiences wear and tear during driving, the steering mechanism damping changes from its initial or factory settings, causing variations in the vehicle's instability coefficient. Therefore, the vehicle's instability coefficient is updated online in real time. Understandably, the time interval for updating the instability coefficient can be set by the developers based on actual conditions.

[0060] There are various ways to implement this step, and this application does not limit this approach. Optionally, if the instability coefficient update time is not the vehicle startup time, the instability coefficient at the previous update time is obtained; the change in the instability coefficient within the current time window is determined, where the current time window refers to the period between the previous update time and the current update time; based on the instability coefficient at the previous update time and the change in the instability coefficient within the current time window, the instability coefficient at the current update time is determined. Essentially, this setting means that after the vehicle starts, the vehicle instability coefficient is corrected in real time based on the excellent response stability of the vehicle steering actuator, ensuring that at any given time, the vehicle instability coefficient matches the excellent response stability of the vehicle steering actuator.

[0061] Optionally, if the instability coefficient is updated at the time the vehicle starts, the updated instability coefficient is the instability coefficient at the time the vehicle was last turned off.

[0062] Alternatively, if the instability coefficient is updated at the moment the vehicle starts, the updated instability coefficient will be zero. That is, the default instability coefficient is zero when the vehicle starts. This is because, in reality, the vehicle's state may change during the engine shutdown phase, such as due to parts replacement, which could significantly improve the response stability of the steering actuator. In this case, compared to the scheme where the updated instability coefficient is based on the instability coefficient at the moment the vehicle starts (the time of the previous engine shutdown), setting the updated instability coefficient to 0 more accurately reflects the response stability of the steering actuator.

[0063] S102. When a steering trigger command is received from the vehicle, the current instability coefficient is obtained.

[0064] For example, the vehicle control system generates a steering trigger command for the vehicle every control cycle. Upon receiving a steering trigger command, the system first obtains the vehicle's instability coefficient at the current moment.

[0065] S103. Based on the current instability coefficient, determine the control increment weight.

[0066] Based on the vehicle instability coefficient at the moment the vehicle steering command is generated, the vehicle control system determines the control increment weights.

[0067] S104. Generate vehicle steering commands based on control increment weights.

[0068] The vehicle steering command includes the vehicle's target turning angle data.

[0069] Generating vehicle steering commands based on control increment weights is a conventional technique in this field and will not be described in detail here.

[0070] This embodiment of the invention periodically updates the instability coefficient of the vehicle steering actuator after vehicle startup. The instability coefficient characterizes the current stability of the vehicle steering actuator's response. Upon receiving a steering trigger command from the vehicle, the current instability coefficient is acquired. Based on the current instability coefficient, control increment weights are determined. Based on the control increment weights, a vehicle steering command is generated, which includes the vehicle's target turning angle data. Essentially, the instability coefficient changes with the response stability of the vehicle steering system. Before each generation of a vehicle steering command, the instability coefficient is acquired, and the MPC control increment weights are automatically adjusted based on the instability coefficient to further generate the most suitable vehicle steering command for the current situation. This avoids vehicle control instability caused by a weakening of the vehicle steering system's response capability due to changes in vehicle parameters or the environment, thus improving the stability and accuracy of vehicle steering and further enhancing the robustness of the MPC trajectory tracking control algorithm under different vehicle parameters and environments.

[0071] Figure 2 This is a flowchart illustrating a method for periodically updating the instability coefficient when the instability coefficient update time is not the vehicle startup time, as provided in this disclosure embodiment. See also... Figure 2 The method includes:

[0072] S201, obtain the instability coefficient at the previous update time.

[0073] For example, if the current update is the (P+1)th unstable coefficient, obtain the unstable coefficient obtained after the Pth update.

[0074] S202, obtain the actual increment and target increment of the vehicle steering angle within the current time window.

[0075] The current time window refers to the period between the previous update and the current update. The vehicle control system obtains the actual increment and target increment of the vehicle steering angle within the current time window, that is, it obtains the actual increment of the vehicle steering angle of the vehicle steering control system and the pre-set target increment of the vehicle steering angle.

[0076] Optionally, if the time of the Pth update of the instability coefficient is the same as the time of the Qth generation of the vehicle steering command; and the time of the (P+1)th update of the instability coefficient is the same as the time of the (Q+m)th generation of the vehicle steering command, where P, Q, and m are all positive integers. When the (P+1)th update of the instability coefficient occurs, the actual increment and target increment of the vehicle steering angle within the current time window are obtained, including: obtaining the first steering wheel angle data of the vehicle at the time of the Pth update of the instability coefficient and the second steering wheel angle data of the vehicle at the time of the (P+1)th update of the instability coefficient; determining the actual increment of the vehicle steering angle within the current time window based on the first steering wheel angle data and the second steering wheel angle data; obtaining the vehicle target angle data from all vehicle steering commands generated from the Qth to the (Q+m-1)th generation; and determining the target increment of the vehicle steering angle within the current time window based on the vehicle target angle data from all vehicle steering commands generated from the Qth to the (Q+m-1)th generation.

[0077] Those skilled in the art will understand that if the time of the Pth update of the instability coefficient is the same as the time of the Qth generation of the vehicle steering command; and the time of the P+1th update of the instability coefficient is the same as the time of the Q+mth generation of the vehicle steering command, it means that the vehicle's instability coefficient was only updated once during the time period from the Pth update of the instability coefficient to the P+1th update of the instability coefficient; and during this time period, the vehicle control system generated m vehicle steering commands, that is, the time interval between two adjacent updates of the instability coefficient is an integer multiple of the time interval between two adjacent generation of vehicle steering commands.

[0078] Figure 3 To control a vehicle using the technical solution provided in this disclosure, a graph showing the change of steering wheel angle over time is presented. For example, when the vehicle control system updates the instability coefficient for the fifth time, the current time window refers to the period between the fourth and fifth updates of the instability coefficient by the vehicle control system. Figure 3 Within the t4 time window, the actual increment of the vehicle's steering angle is obtained. Specifically, the steering wheel angle at the beginning of the t4 time window is taken as the first steering wheel angle, and the steering wheel angle at the end of the t4 time window is taken as the second steering wheel angle. The difference between the second steering wheel angle and the first steering wheel angle is taken as the actual increment of the vehicle's steering angle within this time window.

[0079] Assuming the 4th update of the instability coefficient coincides with the 16th generation of the vehicle steering command, and the 5th update of the instability coefficient coincides with the 21st generation of the vehicle steering command, then the target vehicle angle data from all vehicle steering commands generated from the 16th to the 20th generation are obtained. Based on this target vehicle angle data, the time window for the 5th update of the instability coefficient (i.e., ...) is determined. Figure 3 The target increment of the vehicle steering angle within the time window of time t4. Optionally, the target vehicle steering angle data from all vehicle steering commands generated from the 16th to the 20th can be accumulated to obtain the target increment of the vehicle steering angle within the time window of the 5th update of the instability coefficient.

[0080] S203. Based on the actual increment and the target increment, determine the change in the instability coefficient for this time window.

[0081] There are multiple ways to implement this step, and this application does not impose any limitations on the comparison. For example, if the product of the actual increment and the target increment is greater than or equal to 0, and the absolute value of the difference between the actual increment and the target increment is less than or equal to a first preset threshold, the change in the instability coefficient of this time window is determined to be a first preset value. If the product of the actual increment and the target increment is greater than or equal to 0, and the absolute value of the difference between the actual increment and the target increment is greater than the first preset threshold, the change in the instability coefficient of this time window is determined to be a second preset value. If the product of the actual increment and the target increment is less than 0, the change in the instability coefficient of this time window is determined to be a third preset value. Wherein, the first preset value is less than 0, the second preset value and the third preset value are both greater than 0, and the second preset value is less than or equal to the third preset value.

[0082] Those skilled in the art will understand that if the product of the actual increment and the target increment is greater than or equal to 0, and the absolute value of the difference between the actual increment and the target increment is less than or equal to a first preset threshold, the vehicle steering actuator response can be considered relatively stable. By setting the first preset value to be less than 0, the instability coefficient can be reduced, thereby improving the tracking error convergence rate. If the product of the actual increment and the target increment is greater than or equal to 0, and the absolute value of the difference between the actual increment and the target increment is greater than the first preset threshold, or if the product of the actual increment and the target increment is less than 0, both of these situations can be considered as the vehicle steering actuator response being unstable. By setting both the second preset value and the third preset value to be greater than 0, the instability coefficient can be increased, achieving the purpose of rapid suppression of instability and ensuring vehicle driving safety.

[0083] Furthermore, the absolute value of the first preset value can be set to be less than or equal to the absolute value of the second preset value. In practice, it is possible that although the vehicle steering actuator response is unstable, accidental factors may cause the actual vehicle increment and the target increment to tend to be consistent. To address this situation, by setting the absolute value of the first preset value to be less than or equal to the absolute value of the second preset value, the goal is to determine over a longer period of time whether the convergence of the actual vehicle increment and the target increment is due to the suppression of vehicle steering actuator instability, thus avoiding the instability coefficient from repeatedly adjusting in the direction of increasing or decreasing.

[0084] S204. Based on the instability coefficient at the previous update time and the change in the instability coefficient at the current time window, determine the instability coefficient at the current update time.

[0085] There are multiple ways to implement this step, and this application does not impose any limitations on the comparison. For example, it is possible to calculate the sum of the instability coefficient at the previous update time and the change in the instability coefficient at the current time window, and use the sum as the instability coefficient at the current update time.

[0086] Figure 4 Based on Figure 3 The graph showing the change of the instability coefficient over time. See [link / reference]. Figure 3 and Figure 4 Assume the first preset value is -0.6ε, the second preset value is ε, and the third preset value is 2ε. In time windows t1, t2, or t3, if the product of the actual increment and the target increment is greater than or equal to 0, and the absolute value of the difference between the actual increment and the target increment is greater than the first set threshold, it indicates that the response of the vehicle steering system is not stable enough, and the change in the instability coefficient is ε. The instability coefficient at this update time is the sum of the instability coefficient at the previous update time and ε.

[0087] In time windows t4, t5, t6, t7, or t8, the product of the actual increment and the target increment is less than 0. At this time, the response of the vehicle steering system is very unstable, and the change in the instability coefficient is 2ε. The instability coefficient at the current update time is the sum of the instability coefficient at the previous update time and 2ε.

[0088] Within time windows t9, t10, t11, t12, t13, t14, or t15, if the product of the actual increment and the target increment is greater than or equal to 0, and the absolute value of the difference between the actual increment and the target increment is less than or equal to the first set threshold, it indicates that the response of the vehicle steering system is relatively stable and the instability has been improved. The change in the instability coefficient is -0.6ε. The instability coefficient at this update time is the sum of the instability coefficient at the previous update time and -0.6ε.

[0089] The above technical solution obtains the actual and target increments of the vehicle's steering angle within the current time window; determines the change in the instability coefficient within the current time window based on the actual and target increments; and determines the instability coefficient at the current update time based on the instability coefficient at the previous update time and the change in the instability coefficient within the current time window. This allows for real-time monitoring of the vehicle's steering actuator response, rapid identification of whether the vehicle has experienced steering control instability, and timely updating of the instability coefficient to an appropriate value. This facilitates rapid suppression of instability and improves the stability and robustness of the MPC trajectory tracking control algorithm in response to changes in the vehicle and environment.

[0090] Optionally, based on the above technical solution, S103 can be replaced by: determining the control increment weight based on the current instability coefficient and the basic control increment weight. There are multiple ways to implement this step, and no restrictions are imposed on this method.

[0091] Furthermore, the control increment weights can be determined based on the current instability coefficient, the common control increment base weights, and the following formula;

[0092] ρ=ρ base *e α

[0093] Where, ρ base The incremental base weight is used to control the weight; α is the current instability coefficient. In practice, the incremental base weight can be a fixed value or set according to the vehicle's wear condition or the terrain features of the current driving area. This application does not impose any restrictions on this.

[0094] Figure 5 This is a graph illustrating the relationship between the control increment weight and the instability coefficient, provided in an embodiment of this disclosure. Figure 5 As shown, the larger the instability coefficient α, the larger the control increment weight ρ, that is, when the vehicle becomes unstable, the instability is quickly suppressed by increasing the control increment weight ρ.

[0095] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0096] Figure 6 This is a schematic diagram of the structure of the vehicle steering command generation device provided in the embodiments of this disclosure, as shown below. Figure 6As shown, the device includes: an update module 610, an acquisition module 620, a determination module 630, and a generation module 640; wherein, the update module 610 is used to periodically update the instability coefficient of the vehicle steering actuator after the vehicle starts; the acquisition module 620 is used to acquire the current instability coefficient when a steering trigger command is received from the vehicle; the determination module 630 is used to determine the control increment weight based on the current instability coefficient; and the generation module 640 is used to generate the vehicle steering command based on the control increment weight, the vehicle steering command including the vehicle target turning angle data.

[0097] In some embodiments, the update module 610 is further configured to: if the time of updating the instability coefficient is not the time of vehicle startup, the update module 610 is further configured to obtain the instability coefficient at the previous update time; determine the change in the instability coefficient in the current time window, wherein the current time window refers to the time period between the previous update time and the current update time; and determine the instability coefficient at the current update time based on the instability coefficient at the previous update time and the change in the instability coefficient in the current time window.

[0098] In some embodiments, the update module 610 is further configured to: if the instability coefficient update time is the vehicle start time, the instability coefficient is zero after the update.

[0099] In some embodiments, the acquisition module 620 is further configured to acquire the actual increment and the target increment of the vehicle steering angle within the current time window; and determine the change in the instability coefficient within the current time window based on the actual increment and the target increment. Wherein, the time of the Pth update of the instability coefficient is the same as the time of the Qth generation of the vehicle steering command; the time of the P+1th update of the instability coefficient is the same as the time of the Q+mth generation of the vehicle steering command; where P, Q, and m are all positive integers; when the instability coefficient is updated for the P+1th time, obtaining the actual increment and target increment of the vehicle steering angle within the current time window includes: obtaining the first steering wheel angle data of the vehicle at the time of the Pth update of the instability coefficient and the second steering wheel angle data of the vehicle at the time of the P+1th update of the instability coefficient; determining the actual increment of the vehicle steering angle within the current time window based on the first steering wheel angle data and the second steering wheel angle data; obtaining the vehicle target angle data from all the vehicle steering commands generated from the Qth to the Q+m-1th times; and determining the target increment of the vehicle steering angle within the current time window based on the vehicle target angle data from all the vehicle steering commands generated from the Qth to the Q+m-1th times.

[0100] In some embodiments, the acquisition module 620 is further configured to: determine the change in the instability coefficient of the current time window as a first preset value if the product of the actual increment and the target increment is greater than or equal to 0, and the absolute value of the difference between the actual increment and the target increment is less than or equal to a first preset threshold; determine the change in the instability coefficient of the current time window as a second preset value if the product of the actual increment and the target increment is greater than or equal to 0, and the absolute value of the difference between the actual increment and the target increment is greater than the first preset threshold; determine the change in the instability coefficient of the current time window as a third preset value if the product of the actual increment and the target increment is less than 0; wherein the first preset value is less than 0, the second preset value and the third preset value are both greater than 0, and the second preset value is less than or equal to the third preset value. Wherein, the absolute value of the first preset value is less than or equal to the absolute value of the second preset value.

[0101] In some embodiments, the determining module 630 is further configured to determine the control increment weight based on the current instability coefficient and the basic control increment weight. Specifically, the control increment weight is determined based on the current instability coefficient, the basic control increment weight, and the following formula;

[0102] ρ=ρ base *e α

[0103] Where, ρ base To control the incremental base weights; α is the instability coefficient.

[0104] The apparatus disclosed in the above embodiments can implement the process flow of the methods disclosed in the above method embodiments and has the same or corresponding beneficial effects. To avoid repetition, it will not be described again here.

[0105] Figure 7 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this disclosure, such as... Figure 7 As shown, the electronic device includes:

[0106] One or more processors 701, Figure 7 Take the 701 processor as an example;

[0107] Memory 702;

[0108] The electronic device may further include an input device 703 and an output device 704.

[0109] The processor 701, memory 702, input device 703, and output device 704 in the electronic device can be connected via a bus or other means. Figure 7 Taking the example of a connection between China and Israel via a bus.

[0110] Memory 702, as a non-transitory computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the vehicle steering command generation method in the embodiments of this disclosure (e.g., appendix). Figure 6 The update module 610, acquisition module 620, determination module 630, and generation module 640 are shown. The processor 701 executes various functional applications and data processing of the server by running software programs, instructions, and modules stored in the memory 702, thereby implementing the vehicle control command generation method of the above method embodiment.

[0111] The memory 702 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device. Furthermore, the memory 702 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 702 may optionally include memory remotely located relative to the processor 701, and these remote memories can be connected to the terminal device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0112] Input device 703 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the electronic device. Output device 704 may include display devices such as a display screen.

[0113] This disclosure also provides a computer-readable storage medium storing a program or instructions that, when executed by a computer, are used to perform a method for generating a vehicle steering command, the method comprising:

[0114] After the vehicle starts, the instability coefficient of the vehicle steering actuator is updated periodically;

[0115] Upon receiving a steering trigger command from the vehicle, obtain the current instability coefficient;

[0116] Based on the current instability coefficient, determine the control increment weight;

[0117] Based on the control increment weights, the vehicle steering command is generated, and the vehicle steering command includes the vehicle target turning angle data.

[0118] Optionally, when executed by a computer processor, the computer-executable instructions can also be used to execute the technical solution of the vehicle steering instruction generation method provided in any embodiment of this disclosure.

[0119] Based on the above description of the implementation methods, those skilled in the art will clearly understand that this disclosure can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of this disclosure.

[0120] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0121] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of generating a vehicle steering command, characterized by, The method comprises: periodically updating an instability coefficient of a vehicle steering actuator after the vehicle is started; the instability coefficient characterizes the ability of a steering system of the vehicle to execute model predictive control instructions; the instability coefficient changes with the degree of wear of the steering system of the vehicle; when a steering trigger instruction of the vehicle is received, a current instability coefficient is obtained; based on the current instability coefficient, a control increment weight is determined; the control increment weight affects the rate of change of a target steering angle of the vehicle in a vehicle steering instruction; based on the control increment weight, the vehicle steering instruction is generated, and the vehicle steering instruction comprises vehicle target steering angle data.

2. The method of claim 1, wherein, if the instability coefficient is updated at a time other than when the vehicle is started, the periodically updating the instability coefficient of the vehicle steering actuator comprises: obtaining an instability coefficient at a previous update time; determining a change in the instability coefficient in a current time window, the current time window being a time period from the previous update time to the current update time; based on the instability coefficient at the previous update time and the change in the instability coefficient in the current time window, determining the instability coefficient at the current update time.

3. The method of claim 1, wherein, if the instability coefficient is updated at a time when the vehicle is started, the instability coefficient after the update is zero. The method comprises: obtaining an actual increment and a target increment of a steering angle of the vehicle in the current time window; 4. The method of claim 2, wherein, based on the actual increment and the target increment, determining the change in the instability coefficient in the current time window. The time of the Pth update of the instability coefficient is the same as the time of the Qth generation of the vehicle steering instruction, and the time of the (P+1) th update of the instability coefficient is the same as the time of the (Q+m) th generation of the vehicle steering instruction; wherein P, Q and m are positive integers. When the (P+1) th update of the instability coefficient is performed, the method comprises:

5. The method of claim 4, wherein, obtaining first steering wheel angle data of the vehicle at the time of the Pth update of the instability coefficient and second steering wheel angle data of the vehicle at the time of the (P+1) th update of the instability coefficient; based on the first steering wheel angle data and the second steering wheel angle data, determining the actual increment of the steering angle of the vehicle in the current time window; obtaining vehicle target steering angle data in all the vehicle steering instructions generated from the Qth to the (Q+m-1) th; based on the vehicle target steering angle data in all the vehicle steering instructions generated from the Qth to the (Q+m-1) th, determining the target increment of the steering angle of the vehicle in the current time window. The method comprises: if the product of the actual increment and the target increment is greater than or equal to 0, and the absolute value of the difference between the actual increment and the target increment is less than or equal to a first preset threshold, determining the change in the instability coefficient in the current time window to be a first preset value.

6. The method of claim 4, wherein, ​ ​ If the product of the actual increment and the target increment is greater than or equal to 0, and the absolute value of the difference between the actual increment and the target increment is greater than a first set threshold, determining that the current time window unstable coefficient change amount is a second preset value; If the product of the actual increment and the target increment is less than 0, determining that the current time window unstable coefficient change amount is a third preset value; The first preset value is less than 0, the second preset value and the third preset value are both greater than 0, and the second preset value is less than or equal to the third preset value.

7. The method of claim 6, wherein, The absolute value of the first preset value is less than or equal to the absolute value of the second preset value.

8. The method of claim 4, wherein, The method comprises: Determining the control increment weight based on the current unstable coefficient, comprising: Determining the control increment weight based on the current unstable coefficient and the control increment base weight.

9. The method of claim 8, wherein, wherein, is a control increment base weight; is a current instability coefficient.

10. A device for generating a vehicle steering command, characterized by Determining the control increment weight based on the current unstable coefficient, the control increment base weight, and the following formula: Comprising: An updating module configured to periodically update the unstable coefficient of the vehicle steering actuator after the vehicle is started; the unstable coefficient represents the ability of the steering system of the vehicle to execute the model prediction control instruction; the unstable coefficient changes with the degree of wear of the vehicle steering system; An obtaining module configured to obtain the current unstable coefficient when the steering trigger instruction of the vehicle is received; A determining module configured to determine the control increment weight based on the current unstable coefficient; The control increment weight affects the change rate of the target steering angle of the vehicle in the vehicle steering instruction; 11. An electronic device, comprising: A generating module configured to generate the vehicle steering instruction based on the control increment weight; the vehicle steering instruction comprises target steering angle data of the vehicle. Comprising: A processor and a memory; 12. A computer-readable storage medium, characterized in that, The processor is configured to execute the steps of the method according to any one of claims 1 to 9 by calling the program or instruction stored in the memory. The computer readable storage medium stores the program or instruction, which causes the computer to execute the steps of the method according to any one of claims 1 to 9.

Images