Vehicle direction control method, device and equipment and storage medium

Abstract

The invention provides a vehicle direction control method, device and equipment and a storage medium, and the method comprises the steps that a difference value sequence of torque parameters is obtained, the difference value sequence refers to torque parameter difference values of a vehicle in at least three time frames, and the at least three time frames belong to the time period from the T0 moment to the T1 moment; determining a prediction coefficient according to a fluctuation trend corresponding to the difference value sequence; and calculating a torque control parameter at the T2 moment by using the difference value sequence and the prediction coefficient so as to control the direction of the vehicle according to the torque control parameter. According to the method, the torque parameter difference value of the vehicle in at least three time frames is used as a reference, the prediction coefficient and the prediction torque control parameter which are determined according to the fluctuation trend corresponding to the difference value sequence are combined, and the relatively accurate steering wheel torque control parameter can be estimated under the condition that the measured actual torque parameter contains noise.

Description

Technical Field

[0001] The present application belongs to the field of autonomous driving technology, and specifically relates to a vehicle direction control method, device, equipment and storage medium. Background Art

[0002] In the field of autonomous driving, the adjustment of the vehicle's driving direction depends on the control system's control of the vehicle's steering wheel. The control system can control the steering angle and speed of the vehicle's steering wheel according to the estimated torque control parameters to achieve control of the vehicle's driving direction.

[0003] Conventional estimation of steering wheel torque control parameters uses the angle difference and speed difference corresponding to two adjacent time frames at the current moment as the estimation basis, combined with the distance between the vehicle and the ideal driving trajectory, to estimate the torque control parameters corresponding to the steering wheel.

[0004] However, affected by the accuracy of the control system, the actual torque parameters measured by the control system contain noise, making it difficult to estimate the accurate steering wheel torque control parameters that rely on the data difference between two adjacent time frames, resulting in the inability to control the vehicle to travel in the ideal direction. Summary of the invention

[0005] The present application proposes a vehicle direction control method, device, equipment and storage medium, which can estimate relatively accurate steering wheel torque control parameters when the actual torque parameters measured contain noise, so as to improve the control accuracy of the vehicle driving in the ideal direction.

[0006] The first embodiment of the present application provides a vehicle direction control method, including:

[0007] Obtaining a torque parameter difference sequence, wherein the difference sequence refers to torque parameter differences of at least three time frames of the vehicle, wherein the at least three time frames belong to a time period from time T0 to time T1;

[0008] Determining a prediction coefficient according to the fluctuation trend corresponding to the difference sequence, wherein the prediction coefficient is a value less than 1;

[0009] The torque control parameter at time T2 is calculated using the difference sequence and the prediction coefficient, so as to control the direction of the vehicle according to the torque control parameter.

[0010] In some embodiments of the present application, the step of calculating the torque control parameter at time T2 using the difference sequence and the prediction coefficient includes:

[0011] Determining the weight of each difference in the difference sequence according to the prediction coefficient, the weight of each difference being used to characterize the influence of the corresponding difference on the torque control parameter, the weights of the differences in the difference sequence decreasing in sequence from the time T1 to the time T0, the time T1 being later than the time T0;

[0012] The weighted average result of the smoothing values ​​corresponding to each difference in the difference sequence is calculated, and the weighted average result is the torque control parameter at the time T2. The smoothing value of each difference is calculated by the difference and the weight of the difference.

[0013] In some embodiments of the present application, determining the weight of each difference in the difference sequence according to the prediction coefficient includes:

[0014] In the order from the T1 moment to the T0 moment, the weight corresponding to each difference is set as an exponential multiple of the prediction coefficient, and the exponential multiple increases sequentially with the time frame sequence in the order from the T1 moment to the T0 moment.

[0015] In some embodiments of the present application, for any difference, the smoothed value of the difference is: the difference between the first smoothing parameter and the second predicted smoothing parameter;

[0016] The first smoothing parameter is obtained by multiplying the prediction coefficient by the difference, and the second prediction smoothing parameter is obtained by multiplying the weight of the difference by the difference.

[0017] In some embodiments of the present application, the at least three time frames are adjacent and continuous time frames from the time T0 to the time T1.

[0018] In some embodiments of the present application, determining a prediction coefficient according to a fluctuation trend corresponding to the difference sequence includes:

[0019] Determine the difference values ​​of the preset number of consecutive time frames near the time T1 in the difference value sequence as the difference value sequence to be detected;

[0020] For each group of difference values ​​to be detected in the sequence of difference values ​​to be detected, a change value from a first difference value to be detected to a second difference value to be detected in each group of difference values ​​to be detected is calculated to obtain a plurality of change values, wherein the first difference value to be detected in any group of difference values ​​to be detected is a difference value corresponding to an earlier time frame in a group of two adjacent time frames, and the second difference value to be detected is a difference value corresponding to a later time frame in the group of two adjacent time frames;

[0021] The prediction coefficient is determined according to the multiple change values.

[0022] In some embodiments of the present application, determining the prediction coefficient according to the multiple change values ​​includes:

[0023] If the absolute values ​​of the multiple change values ​​are all less than the first preset value, determining the value of the prediction coefficient in a range greater than or equal to 0.1 and less than 0.3;

[0024] If the absolute values ​​of half or more of the change values ​​among the multiple change values ​​are greater than or equal to a second preset value, the value of the prediction coefficient is determined in a range greater than or equal to 0.3 and less than 0.5, and the second preset value is greater than the first preset value;

[0025] If the absolute values ​​of the multiple change values ​​continue to increase, the value of the prediction coefficient is determined in a range greater than or equal to 0.6 and less than or equal to 0.8.

[0026] An embodiment of a second aspect of the present application provides a vehicle direction control device, comprising:

[0027] An acquisition module, used for acquiring a difference sequence of torque parameters, wherein the difference sequence refers to the difference of torque parameters of at least three time frames of the vehicle, wherein the at least three time frames belong to a period from time T0 to time T1;

[0028] A determination module, used to determine a prediction coefficient according to the fluctuation trend corresponding to the difference sequence, wherein the prediction coefficient is a value less than 1;

[0029] A calculation module is used to calculate the torque control parameter at time T2 using the difference sequence and the prediction coefficient, so as to control the direction of the vehicle according to the torque control parameter.

[0030] An embodiment of the third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in the first aspect above.

[0031] An embodiment of the fourth aspect of the present application provides a computer-readable storage medium on which a computer program is stored, and the program is executed by a processor to implement the method described in the first aspect above.

[0032] The technical solution provided in the embodiments of the present application has at least the following technical effects or advantages:

[0033] In the embodiment of the present application, the torque parameter difference of at least three time frames of the vehicle can be obtained as the torque parameter difference sequence, and the at least three time frames belong to the time period from time T0 to time T1, for example. That is, compared with the traditional prediction based on the torque parameter difference of adjacent time frames, the embodiment of the present application uses the torque parameter difference of at least three time frames as the reference parameter for prediction, and can reduce the influence of system noise on the prediction accuracy by increasing the number of reference parameters used for prediction. Further, the prediction coefficient can be determined according to the fluctuation trend corresponding to the difference sequence, and the torque control parameter at time T2 can be calculated using the difference sequence and the prediction coefficient to control the direction of the vehicle according to the torque control parameter. The fluctuation trend corresponding to the difference sequence can be used as a reference coefficient indicating the control amplitude of the torque control parameter. In this way, on the basis of reducing the influence of system noise according to the difference sequence, the variation amplitude of the torque control parameter to be predicted can also be determined by the prediction coefficient, so that the predicted steering wheel torque control parameter has higher accuracy, and then, by improving the accuracy of steering wheel control, the accuracy of vehicle direction control is improved, and the control effect is optimized.

[0034] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] By reading the detailed description of the preferred embodiment below, various other advantages and benefits will become clear to those of ordinary skill in the art. The accompanying drawings are only used for the purpose of illustrating the preferred embodiment and are not considered to be limitations of the present application. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings.

[0036] In the attached picture:

[0037] Figure 1 A schematic diagram showing the data flow of a steering wheel control mechanism provided by an embodiment of the present application is shown;

[0038] Figure 2 A flow chart of a vehicle direction control method provided by an embodiment of the present application is shown;

[0039] Figure 3 A structural diagram of a vehicle direction control device provided by an embodiment of the present application is shown;

[0040] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application is shown;

[0041] Figure 5 A schematic diagram of a storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0042] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0043] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by technicians in the field to which this application belongs.

[0044] The embodiments of the present application may involve an autonomous driving scenario, in which, in order to make the vehicle always travel in the direction expected by the user, the autonomous driving system controls and adjusts the vehicle's travel direction by controlling the steering wheel torque. In one embodiment, the autonomous driving system may include a steering wheel control mechanism, and during the autonomous driving process, the steering wheel control mechanism may be called to estimate (also referred to as predict) the torque control parameters of the steering wheel, and then, the steering wheel torque is controlled according to the estimated torque control parameters to control the direction of the vehicle.

[0045] It should be noted that the torque parameter may include parameters such as rotation angle, rotation speed (i.e. angular velocity) and acceleration. In one embodiment, the steering wheel control mechanism may include processing branches for two parameters, rotation speed and rotation angle. The rotation speed and acceleration may both be processed by the rotation speed processing branch in the steering wheel control mechanism.

[0046] A typical data flow of a steering wheel control mechanism is as follows Figure 1 See Figure 1, the steering wheel control mechanism may include a torque parameter measuring device, a speed estimator, an angle estimator, a speed controller, an angle controller, a control instruction fusion and a chassis. Among them, the torque parameter measuring device is used to measure the actual torque parameter of the vehicle steering wheel in units of time frames, and the actual torque parameter includes, for example, the actual speed and the time angle. Afterwards, the torque parameter measuring device inputs the measured actual speed of each time frame into the speed estimator, and inputs the measured actual angle of each time frame into the angle estimator. The speed estimator estimates the speed for the next time frame based on the received actual speed and the ideal speed, and inputs the estimation result into the speed controller. The angle controller estimates the angle for the next time frame based on the received actual angle and the ideal angle, and inputs the estimation result into the angle controller. The speed controller and the angle controller generate corresponding control parameters respectively, and perform control instruction fusion to obtain a control instruction containing the torque control parameter. The chassis is the control center of the automatic driving system, and the chassis can respond to the control instruction to control the torque of the steering wheel according to the torque control parameter to control the driving direction of the vehicle.

[0047] See again Figure 1 , the accuracy of the torque parameter measuring device is not ideal, so the actual torque parameter measured by the torque parameter measuring device contains noise. Taking the measured turning angle as an example, the actual turning angle measured by the torque parameter measuring device contains noise, so the turning angle of the next time frame estimated based on the measured actual turning angle is also poor in accuracy, resulting in poor accuracy of the estimated torque control parameter, which in turn causes a certain deviation in the direction of the vehicle controlled by controlling the steering wheel torque, resulting in poor control effect.

[0048] Based on this, the technical solution provided by the embodiment of the present application uses the torque parameter difference of at least three time frames of the vehicle as an estimation reference, and determines the prediction coefficient according to the fluctuation trend corresponding to the difference sequence, and uses the difference sequence and the prediction coefficient to calculate the torque control parameter at time T2. In this way, not only the influence of system noise on the prediction accuracy is reduced by increasing the number of reference parameters used for prediction, but also the change amplitude of the torque control parameter to be predicted is determined by the prediction coefficient, so that the predicted steering wheel torque control parameter has a higher accuracy when the accuracy of the automatic driving system remains unchanged, and then, by improving the accuracy of the control of the steering wheel, the accuracy of the vehicle direction control is improved, and the control effect is optimized.

[0049] The execution subject of this technical solution can be any device that supports vehicle direction control, including vehicles, ships, aircraft or robots. Such devices can support the vehicle direction control of the embodiment of this application through an automatic driving system. The automatic driving system can be provided with Figure 1The steering wheel speed estimation component, steering wheel torque control component and other related functional mechanisms are shown in the figure. The automatic driving system can also simulate the vehicle's driving direction through a simulation system.

[0050] A vehicle direction control method, device, equipment and storage medium proposed according to an embodiment of the present application are described below in conjunction with the accompanying drawings.

[0051] See also Figure 2 , Figure 2 A flow chart of a vehicle direction control method provided by an embodiment of the present application is shown, and the method specifically comprises the following steps:

[0052] Step S101, obtaining a difference sequence of torque parameters.

[0053] The difference sequence refers to the torque parameter difference of at least three time frames of the vehicle. For example, each difference can be the difference between the actual torque parameter s_i of the time frame of the latter time frame and the actual torque parameter s_(i-1) of the time frame of the previous time frame in two adjacent time frames. The value of i can be the total number of at least three time frames.

[0054] In one embodiment, the at least three time frames may belong to a period from time T0 to time T1. The time T0 may be earlier than the time T1. According to the description of this embodiment, the time T0 may be a historical time, and the time T1 may be the current time.

[0055] In one embodiment, the at least three time frames may be discontinuous time frames from the time T0 to the time T1. In another embodiment, the at least three time frames are adjacent and continuous time frames from the time T0 to the time T1, which is conducive to improving the accuracy of the estimated torque control parameter.

[0056] Step S102, determining a prediction coefficient according to a fluctuation trend corresponding to the difference sequence.

[0057] The prediction coefficient is a value less than 1.

[0058] It should be noted that the fluctuation trend corresponding to the difference sequence can be used as a reference coefficient indicating the control amplitude of the torque control parameter. It can be seen that the prediction coefficient can be used to characterize the variation amplitude of the torque control parameter to be predicted.

[0059] In some embodiments, the preset number of consecutive difference values ​​in the difference value sequence near the time T1 can be determined as the difference value sequence to be detected. Exemplarily, the preset number can be flexibly set, and in one example, the preset number can be 5.

[0060] For example, the difference value sequence includes 10 difference values ​​in total, and the time T1 can be used as the starting time, and the 5 consecutive difference values ​​before the time T1 can be used as the difference values ​​to be detected.

[0061] In this way, data that is closer to the changing trend corresponding to the real-time status of the vehicle can be obtained.

[0062] The fluctuation trend corresponding to the difference sequence can be determined by the change value (i.e., difference) between multiple consecutive differences. Based on this, further, the difference values ​​to be detected of two adjacent time frames are taken as a group of difference values ​​to be detected. For each group of difference values ​​to be detected in the difference sequence to be detected, the change value from the first difference value to be detected to the second difference value to be detected in the group of difference values ​​to be detected is calculated to obtain multiple change values. The first difference value to be detected in any group of difference values ​​to be detected is the difference value corresponding to the earlier time frame in the group, and the second difference value to be detected is the difference value corresponding to the later time frame in the group.

[0063] For example, in a sequence of five difference values ​​to be detected, the corresponding time frames from early to late are x1, x2, x3, x4 and x5. For example, x1 and x2 are taken as a group, and the difference value of time frame x1 minus the change value of time frame x2 is calculated, and the change value represents the change trend from time frame x1 to time frame x2. x2 and x3 are taken as a group, and the difference value of time frame x2 minus the change value of time frame x3 is calculated, and the change value represents the change trend from time frame x2 to time frame x3. And so on, 4 change values ​​are obtained.

[0064] Among them, the magnitude of the absolute values ​​of the multiple change values ​​can characterize the change trend of the difference to be detected. The change trend of the difference to be detected can include, for example, stable, fluctuating, continuously rising or continuously falling. Different types of change trends can characterize the current road conditions of the vehicle, as well as the speed, angle and acceleration required in the future. Based on this, in the embodiment of the present application, the prediction coefficient can be determined in the following manner.

[0065] Example 1: If the absolute values ​​of the multiple change values ​​are all smaller than the first preset value, the value of the prediction coefficient is determined in a range greater than or equal to 0.1 and less than 0.3.

[0066] When the absolute values ​​of the multiple change values ​​are all smaller than the first preset value, it can be considered that the change trend of the difference is relatively stable and the road condition of the vehicle is relatively stable. For example, the adjustment range of the acceleration of the turning angle and the rotation speed can be relatively small, and the value of the prediction coefficient can also be small.

[0067] Example 2: If the absolute values ​​of half or more of the multiple change values ​​are greater than or equal to a second preset value, the value of the prediction coefficient is determined in a range greater than or equal to 0.3 and less than 0.5, and the second preset value is greater than the first preset value.

[0068] When the absolute values ​​of half or more of the multiple change values ​​are greater than or equal to the second preset value, it can be considered that the change trend of the difference value fluctuates greatly, and the road condition where the vehicle is located may have many potholes. In this case, the control of the vehicle should be strengthened, and accordingly, the adjustment range of the acceleration of the turning angle and the speed can be relatively large, and the value of the prediction coefficient can also be large.

[0069] Example 3: If the absolute values ​​of the multiple change values ​​continue to increase, the value of the prediction coefficient is determined in a range greater than or equal to 0.6 and less than or equal to 0.8.

[0070] If the absolute values ​​of multiple change values ​​continue to increase, it means that the difference is continuously increasing or decreasing, and the trajectory of the vehicle may be a curve with a large angle. In this case, the adjustment range of the acceleration of the turning angle and the speed should be mainly to adapt to the trajectory as quickly as possible, so the value of the prediction coefficient can also be larger.

[0071] Step S103: Calculate the torque control parameter at time T2 using the difference sequence and the prediction coefficient.

[0072] Here, time T2 is, for example, a time corresponding to the next time frame after time T1.

[0073] It should be noted that the longer the data is from moment T2, the less influence it has on moment T2. Then, in one embodiment of the present application, the influence of data of different time frames on the torque control parameters at moment T2 can be arranged by setting the weight of each difference in the difference sequence. Among them, the weight of each difference in the difference sequence decreases in sequence from moment T1 to moment T0. The weight of each difference can be calculated based on the prediction coefficient.

[0074] Exemplarily, the weight corresponding to each difference may be set as an exponential multiple of the prediction coefficient in the order from the time T1 to the time T0. Taking the prediction coefficient as α as an example, the weight corresponding to the difference of the time frame at the time T1 is, for example, α, and the weight corresponding to the difference of a time frame before the time T1 is, for example, α^2. And so on, which will not be elaborated here.

[0075] Furthermore, a weighted average result of the smoothing values ​​corresponding to each difference in the difference sequence can be calculated, and the weighted average result is the torque control parameter at the time T2. The smoothing value of each difference is calculated by the difference and the weight of the difference. Exemplarily, for any difference, the smoothing value of the difference is: the difference between the first smoothing parameter and the second predicted smoothing parameter. The first smoothing parameter is obtained by multiplying the predicted coefficient by the difference, and the second predicted smoothing parameter is obtained by multiplying the weight of the difference by the difference.

[0076] For example, the torque control parameter at time T2 can be calculated by the following algorithm:

[0077] 〖{aligned}^{·{s}}_i&

[0078] =α(s_i-s_{i-1}) / T+α(1-α)(s_{i-1}-s_{i-2}) / T+α(1-α)^2(s_{i-2}-s_{i-3}) / T+…\\&

[0079] =\frac{1}{T}[αs_i-α^2s_{i-1}-α^2(1-α)s_{i-2}-α^2(1-α)^2s_{i-3}-α^2(1-α)^3s_{i-4}-…]

[0080] \end{aligned}

[0081] Among them, s_i refers to the torque control parameter of the time frame corresponding to the moment T2; (s_{iy}-s_{iy-1}) refers to the difference between the torque parameter of the time frame (iy) and the torque parameter of the time frame (iy-1) in the difference sequence; T refers to the total duration corresponding to the difference sequence, for example, it can be the duration from the moment T0 to the moment T1.

[0082] It should be understood that the torque parameter can be any one of the steering wheel torque angle, speed, and speed acceleration. In some embodiments, the above algorithms can be used to estimate the corresponding parameters for the three parameters. In other embodiments, the above algorithms can be used to estimate the corresponding parameters for parameters with large noise. For example, the above algorithm can be used only for the angle to estimate the angle. This is not limited here.

[0083] In the embodiment of the present application, the torque parameter difference of at least three time frames of the vehicle can be obtained as the torque parameter difference sequence, and the at least three time frames belong to the time period from time T0 to time T1, for example. That is, compared with the traditional prediction based on the torque parameter difference of adjacent time frames, the embodiment of the present application uses the torque parameter difference of at least three time frames as the reference parameter for prediction, and can reduce the influence of system noise on the prediction accuracy by increasing the number of reference parameters used for prediction. Further, the prediction coefficient can be determined according to the fluctuation trend corresponding to the difference sequence, and the torque control parameter at time T2 can be calculated using the difference sequence and the prediction coefficient to control the direction of the vehicle according to the torque control parameter. The fluctuation trend corresponding to the difference sequence can be used as a reference coefficient indicating the control amplitude of the torque control parameter. In this way, on the basis of reducing the influence of system noise according to the difference sequence, the variation amplitude of the torque control parameter to be predicted can also be determined by the prediction coefficient, so that the predicted steering wheel torque control parameter has higher accuracy, and then, by improving the accuracy of steering wheel control, the accuracy of vehicle direction control is improved, and the control effect is optimized.

[0084] The present application also provides a vehicle direction control device, which is used to execute the vehicle direction control method provided in any of the above embodiments. Figure 3 As shown, the device comprises:

[0085] An acquisition module 31 is used to acquire a difference sequence of torque parameters, wherein the difference sequence refers to the difference of torque parameters of at least three time frames of the vehicle, and the at least three time frames belong to the time period from time T0 to time T1; a determination module 32 is used to determine a prediction coefficient according to a fluctuation trend corresponding to the difference sequence, and the prediction coefficient is a value less than 1; a calculation module 33 is used to calculate the torque control parameter at time T2 using the difference sequence and the prediction coefficient, so as to control the direction of the vehicle according to the torque control parameter.

[0086] Optionally, the calculation module 33 is also used to determine the weight of each difference in the difference sequence according to the prediction coefficient, the weight of each difference is used to characterize the influence of the corresponding difference on the torque control parameter, the weights of each difference in the difference sequence decreases sequentially in the order from the T1 moment to the T0 moment, and the T1 moment is later than the T0 moment; and calculate the weighted average result of the smoothing values ​​corresponding to each difference in the difference sequence, the weighted average result is the torque control parameter at the T2 moment, and the smoothing value of each difference is calculated by the difference and the weight of the difference.

[0087] Optionally, the determination module 32 is further used to set the weight corresponding to each difference as an exponential multiple of the prediction coefficient in the order from the T1 moment to the T0 moment, and the exponential multiple increases sequentially with the time frame sequence in the order from the T1 moment to the T0 moment.

[0088] Optionally, for any difference, the smoothing value of the difference is: the difference between a first smoothing parameter and a second prediction smoothing parameter; wherein the first smoothing parameter is obtained by multiplying the prediction coefficient by the difference, and the second prediction smoothing parameter is obtained by multiplying the weight of the difference by the difference.

[0089] Optionally, the at least three time frames are adjacent and continuous time frames from the T0 moment to the T1 moment.

[0090] Optionally, the determination module 32 is further used to determine the preset number of continuous difference values ​​in the difference sequence adjacent to the T1 moment as the difference value sequence to be detected; and for each group of difference values ​​to be detected in the difference value sequence to be detected, calculate the change value from the first difference value to be detected to the second difference value to be detected in each group of difference values ​​to be detected, to obtain multiple change values, wherein the first difference value to be detected in any group of difference values ​​to be detected is the difference value corresponding to the earlier time frame in a group of two adjacent time frames, and the second difference value to be detected is the difference value corresponding to the later time frame in the group of two adjacent time frames; and determine the prediction coefficient according to the multiple change values.

[0091] Optionally, the determination module 32 is further configured to determine a value of the prediction coefficient in a range greater than or equal to 0.1 and less than 0.3 if the absolute values ​​of the multiple change values ​​are all less than a first preset value;

[0092] Optionally, the determination module 32 is further configured to determine a value of the prediction coefficient in a range greater than or equal to 0.3 and less than 0.5 if the absolute values ​​of half or more of the change values ​​among the multiple change values ​​are greater than or equal to a second preset value, and the second preset value is greater than the first preset value;

[0093] Optionally, the determination module 32 is further configured to determine a value of the prediction coefficient within a range greater than or equal to 0.6 and less than or equal to 0.8 if the absolute values ​​of the multiple change values ​​continue to increase.

[0094] The vehicle direction control device provided in the embodiment of the present application and the vehicle direction control method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0095] The present application also provides an electronic device to execute the above vehicle direction control method. Figure 4It shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 4 As shown, the electronic device 4 includes: a processor 400, a memory 401, a bus 402 and a communication interface 403, wherein the processor 400, the communication interface 403 and the memory 401 are connected via the bus 402; the memory 401 stores a computer program that can be run on the processor 400, and when the processor 400 runs the computer program, the vehicle direction control method provided in any of the aforementioned embodiments of the present application is executed.

[0096] The memory 401 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the device network element and at least one other network element is realized through at least one communication interface 403 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0097] The bus 402 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 401 is used to store a program, and the processor 400 executes the program after receiving an execution instruction. The vehicle direction control method disclosed in any implementation of the embodiment of the present application may be applied to the processor 400, or implemented by the processor 400.

[0098] The processor 400 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 400. The above processor 400 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 401, and the processor 400 reads the information in the memory 401 and completes the steps of the above method in combination with its hardware.

[0099] The electronic device provided in the embodiment of the present application and the vehicle direction control method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0100] The present application also provides a computer-readable storage medium corresponding to the vehicle direction control method provided in the above embodiment. Figure 5 The computer-readable storage medium shown is a CD 30 on which a computer program (ie, a program product) is stored. When the computer program is run by a processor, the vehicle direction control method provided by any of the aforementioned embodiments will be executed.

[0101] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0102] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the vehicle direction control method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0103] It should be noted that:

[0104] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known structures and technologies are not shown in detail so as not to obscure the understanding of this description.

[0105] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following schematic diagram: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the claims below, the inventive aspects are less than all the features of the single embodiment disclosed above. Therefore, the claims following the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.

[0106] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0107] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A vehicle direction control method, characterized in that: include: Obtaining a torque parameter difference sequence, wherein the difference sequence refers to torque parameter differences of at least three time frames of the vehicle, wherein the at least three time frames belong to a time period from time T0 to time T1; Determining a prediction coefficient according to the fluctuation trend corresponding to the difference sequence, wherein the prediction coefficient is a value less than 1; The torque control parameter at time T2 is calculated using the difference sequence and the prediction coefficient, so as to control the direction of the vehicle according to the torque control parameter.

2. The method according to claim 1, characterized in that The step of calculating the torque control parameter at time T2 using the difference sequence and the prediction coefficient includes: Determining the weight of each difference in the difference sequence according to the prediction coefficient, the weight of each difference being used to characterize the influence of the corresponding difference on the torque control parameter, the weights of the differences in the difference sequence decreasing in sequence from the time T1 to the time T0, the time T1 being later than the time T0; The weighted average result of the smoothing values ​​corresponding to each difference in the difference sequence is calculated, and the weighted average result is the torque control parameter at the time T2. The smoothing value of each difference is calculated by the difference and the weight of the difference.

3. The method according to claim 2, characterized in that The step of determining the weight of each difference in the difference sequence according to the prediction coefficient comprises: In the order from the T1 moment to the T0 moment, the weight corresponding to each difference is set as an exponential multiple of the prediction coefficient, and the exponential multiple increases sequentially with the time frame sequence in the order from the T1 moment to the T0 moment.

4. The method according to claim 2, characterized in that: For any difference, the smoothing value of the difference is: the difference between the first smoothing parameter and the second prediction smoothing parameter; The first smoothing parameter is obtained by multiplying the prediction coefficient by the difference, and the second prediction smoothing parameter is obtained by multiplying the weight of the difference by the difference.

5. The method according to any one of claims 1 to 4, characterized in that The at least three time frames are adjacent and continuous time frames from the time T0 to the time T1.

6. The method according to claim 1, characterized in that Determining the prediction coefficient according to the fluctuation trend corresponding to the difference sequence includes: Determine the preset number of consecutive difference values ​​in the difference value sequence near the time T1 as the difference value sequence to be detected; For each group of difference values ​​to be detected in the sequence of difference values ​​to be detected, a change value from a first difference value to be detected to a second difference value to be detected in each group of difference values ​​to be detected is calculated to obtain a plurality of change values, wherein the first difference value to be detected in any group of difference values ​​to be detected is a difference value corresponding to an earlier time frame in a group of two adjacent time frames, and the second difference value to be detected is a difference value corresponding to a later time frame in the group of two adjacent time frames; The prediction coefficient is determined according to the multiple change values.

7. The method according to claim 6, characterized in that The step of determining the prediction coefficient according to the multiple change values ​​comprises: If the absolute values ​​of the multiple change values ​​are all less than the first preset value, determining the value of the prediction coefficient in a range greater than or equal to 0.1 and less than 0.3; If the absolute values ​​of half or more of the change values ​​among the multiple change values ​​are greater than or equal to a second preset value, the value of the prediction coefficient is determined in a range greater than or equal to 0.3 and less than 0.5, and the second preset value is greater than the first preset value; If the absolute values ​​of the multiple change values ​​continue to increase, the value of the prediction coefficient is determined in a range greater than or equal to 0.6 and less than or equal to 0.

8.

8. A vehicle direction control device, characterized in that: include: An acquisition module, used for acquiring a difference sequence of torque parameters, wherein the difference sequence refers to the difference of torque parameters of at least three time frames of the vehicle, wherein the at least three time frames belong to a period from time T0 to time T1; A determination module, used to determine a prediction coefficient according to the fluctuation trend corresponding to the difference sequence, wherein the prediction coefficient is a value less than 1; A calculation module is used to calculate the torque control parameter at time T2 using the difference sequence and the prediction coefficient, so as to control the direction of the vehicle according to the torque control parameter.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor runs the computer program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method according to any one of claims 1 to 7.

Images