Vehicle control method and device, equipment, storage medium and product
Through a single neuron controller, the performance index function is constructed in the vehicle using speed error and control quantity, and the weight parameters are determined for vehicle speed control, which solves the problem of insufficient robustness of the existing longitudinal control algorithm in real-time control, and realizes the complex environment Good control effect.
Patent Information
- Application Number
- CN202411240910.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-12-03
AI Technical Summary
Current longitudinal control algorithms cannot provide better control effects while easily applying real-time control of vehicles, especially when facing complex driving scenarios, which are poorly robust.
A single neuron controller is used to determine the input parameters and weight parameters through the error between the current speed and the preset target speed. Vehicle speed control is performed based on the performance index function, which reduces the calculation complexity and adjustable control parameters, and is suitable for vehicles in complex environments. control.
It achieves the ability to provide good vehicle control while being easy to implement, improves robustness, and avoids the need for high-performance computing devices.
Smart Images

Figure CN119058728A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle control method, device, equipment, storage medium and product. Background Art
[0002] With the continuous development of autonomous driving technology, the role of the longitudinal control algorithm of the vehicle in realizing autonomous driving of the vehicle is becoming more and more important. Longitudinal control refers to controlling the acceleration and deceleration of the vehicle during driving to achieve the expected speed and position. The current longitudinal control algorithms mainly include classic PID control and model predictive control. Among them, the classic PID (Proportion-Integral-Derivative controller) control has a simple implementation process and does not have too high requirements on hardware equipment, but its robustness is poor, and it is difficult to provide good control effects in complex driving scenarios; while model predictive control has better control effects, its calculation is more complicated and has higher computing power requirements on hardware equipment, and it is not easy to apply to real-time control of vehicles. Therefore, the current longitudinal control algorithm cannot provide good control effects while being easy to apply to real-time control of vehicles.
[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention
[0004] The main purpose of this application is to provide a vehicle control method, device, equipment, storage medium and product, aiming to solve the technical problem that the current longitudinal control algorithm cannot provide good control effect while being easy to apply for real-time control of the vehicle.
[0005] To achieve the above object, the present application proposes a vehicle control method, wherein the vehicle is equipped with a single neuron controller, and the vehicle control method comprises:
[0006] Determining each current input parameter of the single neuron controller by a current speed error between the current speed of the vehicle and a preset target speed, wherein the single neuron controller is provided with a weight parameter of each current input parameter;
[0007] For any one of the current input parameters, taking the function value of the performance index function of the single neuron controller as the minimum as the goal, determining the current weight value of the target weight parameter corresponding to the input parameter, wherein the performance index function is constructed by the speed error of the vehicle and the control amount of the vehicle, and the function value increases with the increase of the speed error of the vehicle and / or the control amount of the vehicle;
[0008] Based on the current input parameters and the current weight values of the corresponding target weight parameters, the current control amount of the vehicle is determined, and the speed of the vehicle is controlled by the current control amount.
[0009] Optionally, the types of current input parameters in the current input parameters include the current speed error, the first-order difference component corresponding to the current speed error, and the second-order difference component corresponding to the current speed error, and the step of determining the current input parameters of the single neuron controller by the current speed error between the current speed of the vehicle and a preset target speed includes:
[0010] Determine the first-order difference component based on the current speed error and a first historical speed error, wherein the first historical speed error is a previous speed error relative to the current speed error;
[0011] The second-order difference component is determined based on the speed error, the first historical speed error and the second historical speed error, wherein the second historical speed error is a previous speed error relative to the first historical speed error.
[0012] Optionally, the step of determining the current weight value of the target weight parameter corresponding to the input parameter with the goal of minimizing the function value of the performance indicator function of the single neuron controller comprises:
[0013] Determining the gradient of the performance indicator function with respect to the target weight parameter;
[0014] Updating the target weight parameter along the reverse direction of the gradient to obtain an updated change of the target weight parameter;
[0015] The current weight value is obtained by accumulating the updated change amount based on the historical weight value of the target weight parameter, so that the function value of the performance indicator function is minimized in the process of controlling the vehicle speed based on the current weight value, wherein the historical weight value is the weight value of the target weight parameter before executing the step of updating the target weight parameter in the opposite direction of the gradient.
[0016] Optionally, the step of determining the current control amount of the vehicle based on the current input parameters and the current weight values of the corresponding target weight parameters includes:
[0017] Based on the current input parameters and the current weight values of the corresponding target weight parameters, a weighted sum calculation is performed to obtain a weighted total amount;
[0018] The weighted total amount is gained based on the neuron gain coefficient of the single neuron controller to obtain the current control amount.
[0019] Optionally, the step of controlling the vehicle speed by using the current control amount includes:
[0020] determining a total control amount based on the current control amount and a preset acceleration of the vehicle;
[0021] Based on the total control amount and the current speed, matching a target vehicle speed control action and an action amount of the target vehicle speed control action in a preset calibration table of the vehicle;
[0022] The target vehicle control action is executed with reference to the action amount to control the vehicle speed of the vehicle.
[0023] Optionally, in the performance indicator function, the speed error of the vehicle is configured with an error weight, and the control amount of the vehicle is configured with a control amount increment weight.
[0024] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle control device, wherein the vehicle is equipped with a single neuron controller, and the vehicle control device comprises:
[0025] A first determination module, configured to determine each current input parameter of the single neuron controller according to a current speed error between a current speed of the vehicle and a preset target speed;
[0026] A second determination module is used to determine, for any one of the current input parameters, a current weight value of a target weight parameter corresponding to the input parameter with the goal of minimizing the function value of the performance index function of the single neuron controller, wherein the performance index function is constructed by the speed error of the vehicle and the control amount of the vehicle, and the function value increases with the increase of the speed error of the vehicle and / or the control amount of the vehicle;
[0027] The control module is used to determine the current control amount of the vehicle based on the current input parameters and the current weight values of the corresponding target weight parameters, and control the speed of the vehicle through the current control amount.
[0028] In addition, to achieve the above-mentioned purpose, the present application also proposes an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the vehicle control method as described above.
[0029] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the vehicle control method described above are implemented.
[0030] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the vehicle control method described above are implemented.
[0031] One or more technical solutions proposed in this application have at least the following technical effects:
[0032] In this embodiment, the current input parameters of the single neuron controller are determined by the current speed error between the current speed of the vehicle and the preset target speed, wherein the single neuron controller is provided with weight parameters of the current input parameters; for any one of the current input parameters, the current weight value of the target weight parameter corresponding to the input parameter is determined with the minimum function value of the performance index function of the single neuron controller as the goal, wherein the performance index function is constructed by the speed error of the vehicle and the control amount of the vehicle, and the function value increases with the increase of the speed error of the vehicle and / or the control amount of the vehicle; based on the current input parameters and the current weight values of the corresponding target weight parameters, the current control amount of the vehicle is determined, and the speed of the vehicle is controlled by the current control amount. It can be understood that the vehicle of the present application adopts a single neuron controller, which does not require a speed control model and has fewer adjustable control parameters compared to model predictive control, and has lower calculation complexity, so high-performance computing equipment is not required. At the same time, the embodiment of the present application determines the weight value of each weight parameter in the single neuron controller under the constraint of the performance index function constructed by the speed error and the control amount. Therefore, even in a complex formation environment (there are external disturbances and system parameter changes), due to the limiting effect of the control amount in the performance index function, the robustness of vehicle control can be guaranteed, that is, the vehicle speed control based on the single neuron controller can have a good control effect. Therefore, the vehicle control method of the application can provide a good control effect while being easy to implement. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0035] Figure 1This is a flow chart of a first embodiment of a vehicle control method of the present application;
[0036] Figure 2 A schematic diagram of the structure of a single neuron controller in the vehicle control method of the present application;
[0037] Figure 3 Another structural schematic diagram of a single neuron controller in the vehicle control method of the present application;
[0038] Figure 4 A schematic diagram of the framework of the vehicle control method of the present application;
[0039] Figure 5 A schematic diagram of the structure of a vehicle control device in the vehicle control method of the present application;
[0040] Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the vehicle control method in the embodiment of the present application.
[0041] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0042] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0043] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0044] The main solution of the embodiment of the present application is: determine the current input parameters of the single neuron controller through the current speed error between the current speed of the vehicle and the preset target speed; for any one of the current input parameters, determine the current weight value of the target weight parameter corresponding to the input parameter with the goal of minimizing the function value of the performance index function of the single neuron controller, wherein the performance index function is constructed through the speed error of the vehicle and the control amount of the vehicle, and the function value increases with the increase of the speed error of the vehicle and / or the control amount of the vehicle; determine the current control amount of the vehicle based on the current input parameters and the current weight values of the corresponding target weight parameters, and control the vehicle speed through the current control amount.
[0045] With the continuous development of autonomous driving technology, the role of the longitudinal control algorithm of the vehicle in realizing autonomous driving of the vehicle is becoming more and more important. Longitudinal control refers to controlling the acceleration and deceleration of the vehicle during driving to achieve the expected speed and position. The current longitudinal control algorithms mainly include classic PID control and model predictive control. Among them, classic PID control achieves precise control of the system by adjusting the three parameters of proportion, integration and differentiation. However, PID control often has difficulty in achieving good control effects when facing complex nonlinear systems, especially in the presence of external disturbances and changes in system parameters. Therefore, although the PID control implementation process is simple and does not have high requirements for hardware equipment, its poor robustness makes it difficult to achieve good control effects. Model predictive control MPC (Model Predictive Control) is an advanced control method that optimizes the current control input by predicting the future behavior of the system. Although MPC performs well in processing multiple variables and constraints, its high computational complexity has high computing power requirements for hardware equipment and is not easy to be applied to the longitudinal control of the vehicle in real time. Therefore, the current longitudinal control algorithm cannot provide good control effects while being easy to apply to the real-time control of the vehicle.
[0046] The present application provides a solution to control the vehicle speed through a single neuron controller. Compared with model predictive control, there is no need for a speed control model and there are fewer adjustable control parameters. At the same time, the calculation complexity is lower, so no high-performance computing equipment is required. At the same time, the embodiment of the present application determines the weight value of each weight parameter in the single neuron controller under the constraint of the performance index function constructed by the speed error and the control amount. Therefore, even in a complex formation environment (there are external disturbances and system parameter changes), due to the limiting effect of the control amount in the performance index function, the robustness of the vehicle control can be guaranteed, that is, the vehicle speed control based on the single neuron controller can have a good control effect. Therefore, the vehicle control method of the application can provide a good control effect while being easy to implement.
[0047] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a vehicle, a car computer, a cloud server, a computer, a mobile phone, etc., or an electronic device that can realize the above functions.
[0048] Based on this, the present application embodiment provides a vehicle control method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the vehicle control method of the present application.
[0049] In this embodiment, the vehicle is equipped with a single neuron controller, and the vehicle control method includes steps S10 to S30:
[0050] Step S10, determining each current input parameter of the single neuron controller by a current speed error between the current speed of the vehicle and a preset target speed, wherein the single neuron controller is provided with a weight parameter of each current input parameter;
[0051] It should be noted that, in this embodiment, the control method of the vehicle can be applied to the vehicle, and accordingly, a single neuron control is configured on the vehicle, and the single neuron control can be a PID controller built based on a single neuron. It is worth noting that although the controller is a single neuron, a single neuron can have multiple input parameters.
[0052] Exemplarily, the current speed of the above-mentioned vehicle may be the real-time speed of the vehicle, while the preset target speed is the preset speed that the vehicle wants to reach. For example, if the vehicle is in cruise control mode, the preset target speed may be the cruising speed set by the user; if the vehicle is in automatic driving mode, the preset target speed may be the speed determined by the vehicle based on the current driving environment (e.g., the speed limit of the road on which the vehicle is located). The difference between the current speed of the vehicle and the preset target speed is calculated to obtain the current speed error. The current input parameters of the single neuron controller are determined based on the current speed error. For example, the current speed error can be directly used as one of the current input parameters. In addition, the rate of change corresponding to the current speed error (differential term) and the integral accumulation corresponding to the current speed error (integral term) can also be used as current input parameters to form the current input parameters. And a weight parameter is set for each current input parameter in the single neuron controller.
[0053] Step S20, for any one of the current input parameters, with the goal of minimizing the function value of the performance index function of the single neuron controller, determining the current weight value of the target weight parameter corresponding to the input parameter, wherein the performance index function is constructed by the speed error of the vehicle and the control amount of the vehicle, and the function value increases with the increase of the speed error of the vehicle and / or the control amount of the vehicle;
[0054] It should be noted that each current input parameter is configured with a weight parameter, and the process of determining the weight value of each weight parameter, or the process of updating each weight parameter is the same. Therefore, in this embodiment, the process of determining the weight value of a weight parameter corresponding to a current input parameter will be taken as an example for explanation.
[0055] Exemplarily, for any one of the current input parameters, the current weight value of the target weight parameter corresponding to the current input parameter is determined with the goal of minimizing the function value of the performance index function of the single neuron controller. The performance index function is also the loss function of the single neuron controller. The performance index function is constructed by the speed error of the vehicle and the control amount of the vehicle, and the function value of the performance index function increases with the increase of the speed error of the vehicle and / or the control amount of the vehicle. It can be understood that the performance index function is used to evaluate the control performance of the single neuron controller. For example, for the speed error in the performance index function, the speed error is the difference between the real-time speed of the vehicle and the preset target speed of the vehicle. In the actual vehicle speed control process, the control target is that the real-time speed of the vehicle is close to the preset target speed. Correspondingly, the smaller the speed error, the closer it is to the control target of the vehicle. Therefore, the speed error can reflect the control performance of the single neuron controller. As for the control amount of the vehicle in the performance index function, it represents the size of adjusting the vehicle state quantity. In the actual vehicle speed control, there is a certain relationship between the control amount of the vehicle and the user's vehicle riding experience. That is, the larger the control amount of the vehicle, the greater the magnitude of the vehicle state change. For example, if the control amount is too large, it will cause a sudden and substantial increase or decrease in the vehicle speed in the actual vehicle control scenario. Correspondingly, the intuitive experience given to the user is that the vehicle has poor stability during driving. Therefore, the control amount can also reflect the control performance of the single neuron controller.
[0056] The specific structural form of the specific performance index function can be set by the technicians, and when the function value of the performance index function increases with the increase of the speed error of the vehicle and / or the control amount of the vehicle, the minimum function value of the performance index function is used as the goal in the weight value determination process to determine the current weight value of the input parameter corresponding to the target weight parameter. For example, the performance index function is used as the loss function of the single neuron controller, and the gradient descent back propagation update algorithm (i.e., updating in the opposite direction of the gradient to ensure that the function value of the performance index function is minimized) is used to obtain the current weight value of the parameter corresponding to the target weight parameter.
[0057] Step S30, determining a current control amount of the vehicle based on the current input parameters and the current weight values of the corresponding target weight parameters, and controlling the speed of the vehicle by the current control amount.
[0058] Exemplarily, after traversing the current input parameters in the current input parameters, the current weight value of the target weight parameter corresponding to each current input parameter can be obtained. Then, a weighted sum calculation is performed based on each current input parameter and each current weight value, and the result of the weighted sum is gain (i.e., multiplied by a preset gain coefficient) to obtain the current control amount of the vehicle, and then the current control amount is used to control the speed of the vehicle.
[0059] In this embodiment, the current input parameters of the single neuron controller are determined by the current speed error between the current speed of the vehicle and the preset target speed, wherein the single neuron controller is provided with weight parameters of the current input parameters; for any one of the current input parameters, the current weight value of the target weight parameter corresponding to the input parameter is determined with the minimum function value of the performance index function of the single neuron controller as the goal, wherein the performance index function is constructed by the speed error of the vehicle and the control amount of the vehicle, and the function value increases with the increase of the speed error of the vehicle and / or the control amount of the vehicle; based on the current input parameters and the current weight values of the corresponding target weight parameters, the current control amount of the vehicle is determined, and the speed of the vehicle is controlled by the current control amount. It can be understood that the vehicle of the present application adopts a single neuron controller, which does not require a speed control model and has fewer adjustable control parameters compared to model predictive control, and has lower calculation complexity, so high-performance computing equipment is not required. At the same time, the embodiment of the present application determines the weight value of each weight parameter in the single neuron controller under the constraint of the performance index function constructed by the speed error and the control amount. Therefore, even in a complex formation environment (there are external disturbances and system parameter changes), due to the limiting effect of the control amount in the performance index function, the robustness of vehicle control can be guaranteed, that is, the vehicle speed control based on the single neuron controller can have a good control effect. Therefore, the vehicle control method of the application can provide a good control effect while being easy to implement.
[0060] In a feasible implementation manner, in the performance indicator function, the speed error of the vehicle is configured with an error weight, and the control amount of the vehicle is configured with a control amount increment weight.
[0061] Exemplarily, in the performance indicator function, the speed error of the vehicle is also configured with an error weight, and the control amount of the vehicle is also configured with a control amount increment weight. The performance indicator function is as follows:
[0062]
[0063] Where e(k) is the speed error when the weight value is determined for the kth time (or the weight parameter is updated), Δu(k) is the control amount when the weight value is determined for the kth time, Q is the error weight, and R is the control amount increment weight.
[0064] It should be noted that in actual applications, the error weight and the control quantity increment weight can be set by technical personnel according to actual needs. For example, increasing Q can improve the vehicle's dynamic performance, and increasing R can improve the vehicle's anti-disturbance performance.
[0065] In a feasible implementation manner, the types of current input parameters in the current input parameters include the current speed error, the first-order difference component corresponding to the current speed error, and the second-order difference component corresponding to the current speed error. The step of determining the current input parameters of the single neuron controller by the current speed error between the current speed of the vehicle and the preset target speed includes steps S11 to S12:
[0066] Step S11, determining the first-order difference component based on the current speed error and a first historical speed error, wherein the first historical speed error is a previous speed error relative to the current speed error;
[0067] Step S12, determining the second-order difference component based on the speed error, the first historical speed error and the second historical speed error, wherein the second historical speed error is a previous speed error relative to the first historical speed error.
[0068] It should be noted that, in this embodiment, the current speed error can be used as a current input parameter, the first-order difference component corresponding to the current speed can be used as a current input parameter, and the second-order difference component corresponding to the current speed can also be used as a current input parameter.
[0069] Exemplarily, based on the current speed error and the first historical speed error, the first-order difference component corresponding to the current speed error is determined, for example, the first-order difference component may be the difference between the current speed error and the first historical speed error. The first historical speed error is the previous speed error relative to the current speed error. If e(k) is the current speed error, the first historical speed error is e(k-1), and accordingly, the first-order difference component is e(k)-e(k-1).
[0070] Based on the current speed error, the first historical speed error and the second historical speed error, the second-order difference component corresponding to the current speed error is determined, such as determining the sum of the current speed error and the second historical speed error to obtain the total error, and then taking the difference between the total error and twice the first historical speed error as the second-order difference component. Among them, the second historical speed error is the previous speed error relative to the first historical speed error. Based on the above example, if e(k) is set as the current speed error, the first historical speed error is e(k-1), the second historical speed error is e(k-2), and accordingly, the second-order difference component is e(k)-2e(k-1)+e(k-2).
[0071] Reference Figure 2 Schematic diagram of a single neuron controller in this application. Figure 2As shown in the figure, x1 to x3 are the current input parameters, and ω1 to ω3 are the weight parameters of the current input parameters. A is the result of weighted calculation, K is the neuron gain coefficient, and Δu is the current control amount. The learning algorithm includes the above performance indicator function, which can be used to update the weight parameters (i.e., determine the weight value of the weight parameters).
[0072] In a feasible implementation manner, the step of determining the current weight value of the target weight parameter corresponding to the input parameter with the goal of minimizing the function value of the performance indicator function of the single neuron controller includes steps S21 to S23:
[0073] Step S21, determining the gradient of the performance indicator function with respect to the target weight parameter;
[0074] Step S22, updating the target weight parameter along the reverse direction of the gradient to obtain an updated change of the target weight parameter;
[0075] Step S23, accumulating the updated change amount on the basis of the historical weight value of the target weight parameter to obtain the current weight value, so that the function value of the performance indicator function is minimized in the process of controlling the vehicle speed based on the current weight value, wherein the historical weight value is the weight value of the target weight parameter before executing the step of updating the target weight parameter in the opposite direction of the gradient.
[0076] It should be noted that the performance indicator function can be as follows:
[0077]
[0078] Where e(k) is the speed error when the weight value is determined for the kth time (or the weight parameter is updated), Δu(k) is the control amount increment when the weight value is determined for the kth time, Q is the error weight, and R is the control amount increment weight.
[0079] The gradient of the performance index function J with respect to the weight parameter ω(k) (or the target weight parameter) is:
[0080]
[0081] In the formula, because the partial derivative of the output (i.e., y(k)) with respect to the input is unknown, so it is approximated by a symbolic function. Further:
[0082]
[0083] Δu(k)=Kx T ω=Kx T ω(k-1)+Kx T Δω(k)
[0084] Update the weight parameter ω(k) along the negative gradient of J. Combining the above three equations, we have:
[0085]
[0086] So the updated change is:
[0087]
[0088] In the above formula, e(k) is the speed error when the weight value is determined for the kth time (or the weight parameter is updated), Δu(k) is the control amount when the weight value is determined for the kth time, Δω(k) is the update change, Q is the error weight, R is the control amount increment weight, K is the neuron gain coefficient, x is the input parameter, ω is the weight parameter, η is the learning rate, and I is a 3×3 unit matrix.
[0089] After obtaining the updated change of the target weight parameter, the updated change is added to the historical weight value of the target weight parameter to obtain the current weight value. In the process of controlling the vehicle speed based on the single neuron controller configured with the current weight value, the function value of the performance index function can be guaranteed to be minimum.
[0090] In a feasible implementation manner, the step of determining the current control amount of the vehicle based on the current input parameters and the current weight values of the corresponding target weight parameters includes steps S311 to S312:
[0091] Step 311, performing weighted sum calculation based on the current input parameters and the current weight values of the corresponding target weight parameters to obtain a weighted total amount;
[0092] Step S312, gaining the weighted total amount based on the neuron gain coefficient of the single neuron controller to obtain the current control amount.
[0093] Exemplarily, after determining the current input parameters and the current weight values of the target weight parameters corresponding to the current input parameters, the current input parameters and the current weight values are weighted and summed to obtain the weighted total amount. The weighted total amount is amplified by the neuron gain coefficient in the single neuron controller to obtain the current control amount. Figure 3 , is another structural diagram of a single neuron controller, Figure 3 Zhongyu Figure 2 The same parts can be referred to in Figure 2 In addition, Figure 3The state converter can convert vehicle data (such as speed error) into data that can be processed by a single neuron. The object is the vehicle or a component in the vehicle (such as brake or accelerator), and y can be a specific control action. Accordingly, the calculation formula for the weighted total based on the above example is as follows:
[0094]
[0095] In the formula, A is the weighted total amount, x i is the i-th current input parameter, ω i is the weight parameter corresponding to the i-th current input parameter, e(k) is the speed error (or current speed error) when the weight value is determined (or the weight parameter is updated) for the kth time, Δe(k) is the first-order difference component corresponding to the speed error, Δ 2 e(k) is the second-order difference corresponding to the speed error. Furthermore, the calculation formula of the control quantity is as follows:
[0096]
[0097] Wherein, Δu(k) determines the control amount corresponding to the weight value for the kth time (i.e., the current control amount), and K is the neuron gain coefficient.
[0098] It should be noted that in actual applications, the neuron gain coefficient is usually updated, and the specific updating process can be updated by technical personnel according to actual needs.
[0099] In a feasible implementation manner, the step of controlling the vehicle speed by the current control amount includes steps S321 to S322:
[0100] Step S321, determining a total control amount based on the current control amount and a preset acceleration of the vehicle;
[0101] Step S322, matching a target vehicle speed control action and an action amount of the target vehicle speed control action in a preset calibration table of the vehicle based on the total control amount and the current speed;
[0102] Step S323, executing the target vehicle control action with reference to the action amount to control the vehicle speed.
[0103] Exemplarily, the preset acceleration can also be set in advance by the user (such as the owner or driver) according to the needs. The total control amount can be obtained by adding the current control amount to the preset acceleration. Match the target speed control action and the action amount of the target speed control action corresponding to the total control amount and the current speed of the vehicle from the vehicle calibration table. Among them, the target speed control action can be "stepping on the accelerator", "releasing the accelerator", "stepping on the brake" and "releasing the brake", etc. The action amount of the target speed control action can be the opening of the accelerator or brake, such as 10%.
[0104] It should be noted that calibration tables are usually used in traditional PID control algorithms. However, in traditional PID control algorithms, it is necessary to collect vehicle speed and acceleration information under different throttle and brake control amounts on a flat road to establish a calibration table. However, the accuracy of this method is easily affected by the external environment, such as weather changes and vehicle load changes. In addition, the process of establishing a calibration table is cumbersome and requires high accuracy of the data. Once external conditions change, the effectiveness of the calibration table will be greatly reduced. However, in the embodiment of the present application, since the single neuron controller can achieve a good control effect, the error of the calibration table can be compensated by the single neuron controller. And since the single neuron controller can play a compensatory role, a simplified calibration table can be used, which reduces the accuracy requirements of the calibration table. For example, under different throttle and brake control amounts, the throttle and brake step amount of this process is 10% (accounting for 10% of the maximum control amount), and the vehicle speed and acceleration information is collected to make an offline calibration table (that is, the preset calibration table in the embodiment of the present application). Figure 4 As shown in FIG. 1 , it is a schematic diagram of the framework of the vehicle control method in this application. Figure 4 As shown, the reference speed is the preset target speed of the vehicle, the feedback speed is the current speed of the vehicle, the improved single neuron PID controller is the single neuron controller in this application, the corresponding improved single neuron PID controller output result is the current control quantity, the simple calibration table in the open-loop control is the above preset calibration table, the reference acceleration is the above target acceleration, and in the open-loop control, the basis for matching in the simple calibration table includes the reference acceleration, the result of the improved single neuron PID controller output and the current speed of the vehicle. The matching result in the simple calibration table is the change of the throttle / brake, and the change of the throttle / brake will act on the controlled vehicle, thereby realizing the control of the vehicle speed.
[0105] The present application provides a vehicle control device, wherein the vehicle is equipped with a single neuron controller, referring to Figure 5 , the control device of the vehicle comprises:
[0106] A first determination module 10 is used to determine each current input parameter of the single neuron controller according to a current speed error between the current speed of the vehicle and a preset target speed, wherein the single neuron controller is provided with a weight parameter of each current input parameter;
[0107] A second determination module 20 is used to determine, for any one of the current input parameters, a current weight value of a target weight parameter corresponding to the input parameter with the goal of minimizing the function value of the performance index function of the single neuron controller, wherein the performance index function is constructed by the speed error of the vehicle and the control amount of the vehicle, and the function value increases with the increase of the speed error of the vehicle and / or the control amount of the vehicle;
[0108] The control module 30 is used to determine the current control amount of the vehicle based on the current input parameters and the current weight values of the corresponding target weight parameters, and control the speed of the vehicle through the current control amount.
[0109] Optionally, the types of current input parameters in the current input parameters include the current speed error, a first-order difference component corresponding to the current speed error, and a second-order difference component corresponding to the current speed error, and the first determining module 10 is further used to:
[0110] Determine the first-order difference component based on the current speed error and a first historical speed error, wherein the first historical speed error is a previous speed error relative to the current speed error;
[0111] The second-order difference component is determined based on the speed error, the first historical speed error and the second historical speed error, wherein the second historical speed error is a previous speed error relative to the first historical speed error.
[0112] Optionally, the second determining module 20 is further configured to:
[0113] Determining the gradient of the performance indicator function with respect to the target weight parameter;
[0114] Updating the target weight parameter along the reverse direction of the gradient to obtain an updated change of the target weight parameter;
[0115] The current weight value is obtained by accumulating the updated change amount based on the historical weight value of the target weight parameter, so that the function value of the performance indicator function is minimized in the process of controlling the vehicle speed based on the current weight value, wherein the historical weight value is the weight value of the target weight parameter before executing the step of updating the target weight parameter in the opposite direction of the gradient.
[0116] Optionally, the control module 30 is further used for:
[0117] Based on the current input parameters and the current weight values of the corresponding target weight parameters, a weighted sum calculation is performed to obtain a weighted total amount;
[0118] The weighted total amount is gained based on the neuron gain coefficient of the single neuron controller to obtain the current control amount.
[0119] Optionally, the control module 30 is further used for:
[0120] determining a total control amount based on the current control amount and a preset acceleration of the vehicle;
[0121] Based on the total control amount and the current speed, matching a target vehicle speed control action and an action amount of the target vehicle speed control action in a preset calibration table of the vehicle;
[0122] The target vehicle control action is executed with reference to the action amount to control the vehicle speed of the vehicle.
[0123] Optionally, in the performance indicator function, the speed error of the vehicle is configured with an error weight, and the control amount of the vehicle is configured with a control amount increment weight.
[0124] The vehicle control device provided by the present application adopts the vehicle control method in the above embodiment, aiming to solve the technical problem that the current longitudinal control algorithm cannot provide a good control effect while being easy to apply for real-time control of the vehicle. Compared with the prior art, the beneficial effects of the vehicle control device provided by the embodiment of the present application are the same as the beneficial effects of the vehicle control method provided by the above embodiment 1, and the other technical features in the vehicle control device are the same as the features disclosed in the above embodiment method, which will not be repeated here.
[0125] The present application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle control method in the above-mentioned embodiment one.
[0126] Reference below Figure 6, which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. The electronic devices in the embodiments of the present application may include but are not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Displays), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0127] like Figure 6 As shown, the electronic device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read On ly Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the electronic device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an electronic device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.
[0128] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0129] The electronic device provided by the present application adopts the vehicle control method in the above embodiment, which can solve the technical problem that the longitudinal control algorithm cannot provide a good control effect while being easy to apply for real-time control of the vehicle. Compared with the prior art, the beneficial effects of the electronic device provided by the present application are the same as the beneficial effects of the vehicle control method provided by the above embodiment, and the other technical features in the electronic device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0130] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0131] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0132] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, wherein the computer-readable program instructions are used to execute the vehicle control method in the above-mentioned embodiment.
[0133] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read On ly Memory), an erasable programmable read-only memory (EPROM: Erasable Programmab le Read On ly Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read On ly Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.
[0134] The computer-readable storage medium may be included in the electronic device, or may exist independently without being installed in the electronic device.
[0135] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by an electronic device, the electronic device: determines each current input parameter of the single neuron controller through the current speed error between the current speed of the vehicle and the preset target speed, wherein the single neuron controller is provided with a weight parameter of each current input parameter; for any one of the current input parameters, determines the current weight value of the target weight parameter corresponding to the input parameter with the goal of minimizing the function value of the performance index function of the single neuron controller, wherein the performance index function is constructed through the speed error of the vehicle and the control amount of the vehicle, and the function value increases with the increase of the speed error of the vehicle and / or the control amount of the vehicle; determines the current control amount of the vehicle based on the current input parameters and the current weight values of the corresponding target weight parameters, and controls the vehicle speed through the current control amount.
[0136] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0137] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0138] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0139] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned vehicle control method, and can solve the technical problem that the existing data display method is difficult to intuitively and clearly complete data visualization. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the vehicle control method provided in the above-mentioned embodiment, and will not be repeated here.
[0140] The present application also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the vehicle control method as described above are implemented.
[0141] The computer program product provided by the present application can solve the technical problem of vehicle control. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the vehicle control method provided by the above embodiment, which will not be repeated here.
[0142] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A vehicle control method, characterized in that: The vehicle is equipped with a single neuron controller, and the control method of the vehicle includes: Determining each current input parameter of the single neuron controller by a current speed error between the current speed of the vehicle and a preset target speed, wherein the single neuron controller is provided with a weight parameter of each current input parameter; For any one of the current input parameters, taking the function value of the performance index function of the single neuron controller as the minimum as the goal, determining the current weight value of the target weight parameter corresponding to the input parameter, wherein the performance index function is constructed by the speed error of the vehicle and the control amount of the vehicle, and the function value increases with the increase of the speed error of the vehicle and / or the control amount of the vehicle; Based on the current input parameters and the current weight values of the corresponding target weight parameters, the current control amount of the vehicle is determined, and the speed of the vehicle is controlled by the current control amount.
2. The vehicle control method according to claim 1, characterized in that: The types of current input parameters in the current input parameters include the current speed error, the first-order difference component corresponding to the current speed error, and the second-order difference component corresponding to the current speed error. The step of determining the current input parameters of the single neuron controller by the current speed error between the current speed of the vehicle and the preset target speed includes: Determine the first-order difference component based on the current speed error and a first historical speed error, wherein the first historical speed error is a previous speed error relative to the current speed error; The second-order difference component is determined based on the speed error, the first historical speed error and the second historical speed error, wherein the second historical speed error is a previous speed error relative to the first historical speed error.
3. The vehicle control method according to claim 1, characterized in that: The step of determining the current weight value of the target weight parameter corresponding to the input parameter with the goal of minimizing the function value of the performance indicator function of the single neuron controller comprises: Determining the gradient of the performance indicator function with respect to the target weight parameter; Updating the target weight parameter along the reverse direction of the gradient to obtain an updated change of the target weight parameter; The current weight value is obtained by accumulating the updated change amount based on the historical weight value of the target weight parameter, so that the function value of the performance indicator function is minimized in the process of controlling the vehicle speed based on the current weight value, wherein the historical weight value is the weight value of the target weight parameter before executing the step of updating the target weight parameter in the opposite direction of the gradient.
4. The vehicle control method according to claim 1, characterized in that: The step of determining the current control amount of the vehicle based on the current input parameters and the current weight values of the corresponding target weight parameters includes: Based on the current input parameters and the current weight values of the corresponding target weight parameters, a weighted sum calculation is performed to obtain a weighted total amount; The weighted total amount is gained based on the neuron gain coefficient of the single neuron controller to obtain the current control amount.
5. The vehicle control method according to claim 1, characterized in that: The step of controlling the vehicle speed by the current control amount comprises: determining a total control amount based on the current control amount and a preset acceleration of the vehicle; Based on the total control amount and the current speed, matching a target vehicle speed control action and an action amount of the target vehicle speed control action in a preset calibration table of the vehicle; The target vehicle control action is executed with reference to the action amount to control the vehicle speed of the vehicle.
6. The vehicle control method according to claim 1, characterized in that: In the performance indicator function, the speed error of the vehicle is configured with an error weight, and the control amount of the vehicle is configured with a control amount increment weight.
7. A vehicle control device, characterized in that: The vehicle is equipped with a single neuron controller, and the control device of the vehicle includes: A first determination module, configured to determine each current input parameter of the single neuron controller according to a current speed error between a current speed of the vehicle and a preset target speed; A second determination module is used to determine, for any one of the current input parameters, a current weight value of a target weight parameter corresponding to the input parameter with the goal of minimizing the function value of the performance index function of the single neuron controller, wherein the performance index function is constructed by the speed error of the vehicle and the control amount of the vehicle, and the function value increases with the increase of the speed error of the vehicle and / or the control amount of the vehicle; The control module is used to determine the current control amount of the vehicle based on the current input parameters and the current weight values of the corresponding target weight parameters, and control the speed of the vehicle through the current control amount.
8. An electronic device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the vehicle control method according to any one of claims 1 to 6.
9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the vehicle control method according to any one of claims 1 to 6 are implemented.
10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the vehicle control method according to any one of claims 1 to 6 are implemented.
