Vehicle braking method, device and equipment based on model prediction, medium and product
By establishing a state transition model and iterative optimization algorithm in the vehicle and determining the vehicle's target acceleration, the problem of insufficient accuracy of existing automatic emergency braking methods is solved, faster and more accurate braking control is achieved, and vehicle safety is improved.
Patent Information
- Application Number
- CN202511334410.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-18
- Publication Date
- 2025-10-28
AI Technical Summary
Existing automatic emergency braking methods are insufficient in accuracy and face challenges in response speed and precision.
The model predictive control algorithm is adopted to determine the target acceleration of the vehicle in an emergency by establishing a state transition model and an iterative optimization algorithm. The braking parameters are determined based on the acceleration to achieve braking control of the vehicle.
It improves the response speed and decision-making accuracy of the automatic emergency braking system, reduces braking distance, enhances vehicle safety in emergency situations, and provides more reliable safety assurance.
Smart Images
Figure CN120840563A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of vehicle braking technology, and in particular to a model-based vehicle braking method, device, equipment, medium, and product. Background Art
[0002] Automatic emergency braking technology in vehicles can automatically apply braking measures in emergency situations to prevent collisions and thus improve driving safety.
[0003] In existing technologies, sensors are typically used to collect information about the vehicle's status and surrounding environment in real time. The processor then processes the data from different sensors to analyze potential collision hazards and, if necessary, quickly activates the vehicle's braking system to avoid or mitigate collisions through automatic braking.
[0004] However, existing automatic emergency braking methods still have shortcomings in terms of accuracy. Summary of the Invention
[0005] This application provides a model-predictive vehicle braking method, device, equipment, medium, and product, which improves the response speed and accuracy of the automatic emergency braking system by employing a model predictive control algorithm, thereby enhancing vehicle safety in emergency situations.
[0006] In a first aspect, this application provides a vehicle braking method based on model prediction, the method comprising:
[0007] Obtain the vehicle's status information during the current sampling period. The status information includes at least one of the following: the distance between the vehicle and the obstacle in front, the vehicle's own speed, or the vehicle's own acceleration.
[0008] The state information of the current sampling period is input into the preset state transition model. Under the constraints of the preset state transition model, the vehicle's acceleration in the next sampling period is determined by the iterative optimization algorithm when the preset cost function is minimized. This acceleration is taken as the target acceleration of the vehicle. The preset state transition model describes the functional relationship between the state information of the (k+1)th sampling period and the state information of the kth sampling period, the duration of the sampling period, and the speed of the obstacle ahead. The preset cost function describes the total deviation of N+1 sampling periods when the vehicle is controlled in the current sampling period. The deviation of each sampling period includes at least one of the following: the degree of state deviation and the degree of input deviation. The degree of state deviation is the degree of deviation between the state information and the reference state information. The degree of input deviation is the degree of deviation between the rate of change of the vehicle's acceleration and the rate of change of the vehicle's reference acceleration. N is an integer greater than or equal to 1, k is an integer greater than or equal to 0 and less than N, and the current sampling period is the 0th sampling period.
[0009] The braking parameters are determined based on the target acceleration of the vehicle, and the vehicle is braked based on the braking parameters.
[0010] In one possible design, in the preset state transition model, the distance between the two vehicles in the (k+1)th sampling period is positively correlated with the distance between the two vehicles in the kth sampling period, the difference between the obstacle speed and the vehicle speed in the kth sampling period, the duration of the sampling period, the vehicle acceleration in the kth sampling period, and the rate of change of the vehicle acceleration in the kth sampling period.
[0011] The vehicle speed in the (k+1)th sampling period is positively correlated with the vehicle speed in the kth sampling period, the duration of the sampling period, the vehicle acceleration in the kth sampling period, and the rate of change of the vehicle acceleration in the kth sampling period.
[0012] The vehicle acceleration in the (k+1)th sampling period is positively correlated with the vehicle acceleration in the kth sampling period, the duration of the sampling period, and the rate of change of the vehicle acceleration in the kth sampling period.
[0013] In one possible design, the preset state transition model is as follows:
[0014] ;
[0015] in, , W(k+1) is the state matrix corresponding to the state information of the (k+1)th sampling period. , It is the distance between the two vehicles in the (k+1)th sampling period. It is the speed of the vehicle in the (k+1)th sampling period. It is the vehicle acceleration in the (k+1)th sampling period;
[0016] W(k) is the state matrix corresponding to the state information of the k-th sampling period. , It is the distance between the two vehicles in the kth sampling period. It is the speed of the vehicle in the kth sampling period. It is the vehicle acceleration in the kth sampling period;
[0017] U(k) is the input matrix for the kth sampling period. , It is the rate of change of the vehicle's acceleration in the kth sampling period, and Ts is the duration of the sampling period.
[0018] In one possible design, the pre-defined cost function is as follows:
[0019] ;
[0020] in, Z is the total deviation, and Z is the optimization matrix. ,
[0021] R=0.3
[0022] , , , This is the reference state matrix corresponding to the reference state information of the k-th sampling period. , It is the reference distance between the two vehicles in the kth sampling period. It is the reference speed of the vehicle in the kth sampling period. It is the reference acceleration of the vehicle in the kth sampling period. For the input reference matrix, , Let be the rate of change of the vehicle's reference acceleration during the kth sampling period.
[0023] In one possible design, the vehicle's acceleration in the next sampling period, which minimizes a preset cost function, is determined through an iterative optimization algorithm and used as the vehicle's target acceleration, including:
[0024] The optimization matrix corresponding to the minimum preset cost function is determined by an iterative optimization algorithm and used as the target optimization matrix.
[0025] Extract the vehicle's acceleration for the first sampling period from the target optimization matrix and use it as the vehicle's target acceleration.
[0026] In one possible design, braking parameters are determined based on the vehicle's target acceleration, including:
[0027] The braking effect of target acceleration on the vehicle is simulated on the vehicle's display device;
[0028] When no user input is received regarding the braking effect, the braking parameters are determined based on the target acceleration of the vehicle.
[0029] Upon receiving a user's adjustment command for the braking effect, the target acceleration is adjusted according to the adjusted braking effect, and the process returns to the step of simulating the braking effect of the target acceleration on the vehicle's display device.
[0030] In one possible design, braking parameters are determined based on the vehicle's target acceleration, including:
[0031] Based on the structure of the braking system, a braking system model is constructed. The braking system model is used to describe the positive correlation function relationship between the acceleration input to the braking system and the braking parameters, including braking pressure and braking duration.
[0032] Input the target acceleration of the vehicle into the braking system model to obtain the braking parameters corresponding to the target acceleration.
[0033] In one possible design, braking control of the vehicle is performed based on braking parameters, including:
[0034] The braking parameters are sent to the control unit of the braking system so that the control unit can parse the braking parameters and execute the braking operation.
[0035] Secondly, this application provides a model-predictive vehicle braking device, the device comprising:
[0036] The acquisition module is used to acquire the vehicle's status information in the current sampling period. The status information includes at least one of the following: the distance between the vehicle and the obstacle in front, the vehicle's own speed, or the vehicle's own acceleration.
[0037] The determination module is used to input the state information of the current sampling period into the preset state transition model, and under the constraints of the preset state transition model, to determine the vehicle's own acceleration in the next sampling period when the preset cost function is minimized through an iterative optimization algorithm, which is used as the target acceleration of the vehicle. The preset state transition model describes the functional relationship between the state information of the (k+1)th sampling period and the state information of the kth sampling period, the duration of the sampling period, and the speed of the obstacle in front. The preset cost function describes the total deviation of N+1 sampling periods when the vehicle is controlled in the current sampling period. The deviation of each sampling period includes at least one of the following: the degree of state deviation and the degree of input deviation. The degree of state deviation is the degree of deviation between the state information and the reference state information. The degree of input deviation is the degree of deviation between the rate of change of the vehicle's acceleration and the rate of change of the vehicle's reference acceleration. N is an integer greater than or equal to 1, k is an integer greater than or equal to 0 and less than N, and the current sampling period is the 0th sampling period.
[0038] The control module is used to determine braking parameters based on the target acceleration of the vehicle, and to control the vehicle's braking based on the braking parameters.
[0039] In one possible design, in the preset state transition model, the distance between the two vehicles in the (k+1)th sampling period is positively correlated with the distance between the two vehicles in the kth sampling period, the difference between the obstacle speed and the vehicle speed in the kth sampling period, the duration of the sampling period, the vehicle acceleration in the kth sampling period, and the rate of change of the vehicle acceleration in the kth sampling period.
[0040] The vehicle speed in the (k+1)th sampling period is positively correlated with the vehicle speed in the kth sampling period, the duration of the sampling period, the vehicle acceleration in the kth sampling period, and the rate of change of the vehicle acceleration in the kth sampling period.
[0041] The vehicle acceleration in the (k+1)th sampling period is positively correlated with the vehicle acceleration in the kth sampling period, the duration of the sampling period, and the rate of change of the vehicle acceleration in the kth sampling period.
[0042] In one possible design, the preset state transition model is as follows:
[0043] ;
[0044] in, , W(k+1) is the state matrix corresponding to the state information of the (k+1)th sampling period. , It is the distance between the two vehicles in the (k+1)th sampling period. It is the speed of the vehicle in the (k+1)th sampling period. It is the vehicle acceleration in the (k+1)th sampling period;
[0045] W(k) is the state matrix corresponding to the state information of the k-th sampling period. , It is the distance between the two vehicles in the kth sampling period. It is the speed of the vehicle in the kth sampling period. It is the vehicle acceleration in the kth sampling period;
[0046] U(k) is the input matrix for the kth sampling period. , It is the rate of change of the vehicle's acceleration in the kth sampling period, and Ts is the duration of the sampling period.
[0047] In one possible design, the pre-defined cost function is as follows:
[0048] ;
[0049] in, Z is the total deviation, and Z is the optimization matrix. ,
[0050] R=0.3
[0051] , , , This is the reference state matrix corresponding to the reference state information of the k-th sampling period. , It is the reference distance between the two vehicles in the kth sampling period. It is the reference speed of the vehicle in the kth sampling period. It is the reference acceleration of the vehicle in the kth sampling period. For the input reference matrix, , Let be the rate of change of the vehicle's reference acceleration during the kth sampling period.
[0052] In one possible design, the determination module includes: an optimization matrix determination module and an extraction module.
[0053] The optimization matrix determination module is used to determine the optimization matrix corresponding to the minimum preset cost function through an iterative optimization algorithm, which is used as the target optimization matrix.
[0054] The extraction module is used to extract the vehicle's acceleration for the first sampling period from the target optimization matrix, and use it as the vehicle's target acceleration.
[0055] In one possible design, the control module includes: a display module, a parameter determination module, and an adjustment module;
[0056] The display module is used to simulate the braking effect of the target acceleration on the vehicle's display device.
[0057] The parameter determination module is used to determine braking parameters based on the target acceleration of the vehicle when no user operation on braking effect is received.
[0058] The adjustment module is used to adjust the target acceleration according to the adjusted braking effect when it receives the user's adjustment operation for the braking effect, and return the steps of simulating the braking effect of the target acceleration on the vehicle's display device.
[0059] In one possible design, the adjustment modules include: a building module and an input module;
[0060] The construction module is used to build a braking system model based on the structure of the braking system. The braking system model is used to describe the positive correlation function relationship between the acceleration input to the braking system and the braking parameters, including braking pressure and braking duration.
[0061] The input module is used to input the target acceleration of the vehicle into the braking system model to obtain the braking parameters corresponding to the target acceleration.
[0062] In one possible design, the control module also includes: a sending module;
[0063] The transmitting module is used to send braking parameters to the control unit of the braking system, so that the control unit can parse the braking parameters and perform braking operations.
[0064] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;
[0065] The memory stores the instructions that the computer executes;
[0066] The processor executes computer execution instructions stored in memory to implement a model prediction-based vehicle braking method according to the first aspect of the invention.
[0067] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement a model-predictive vehicle braking method according to the first aspect of the invention.
[0068] Fifthly, this application provides a computer program product, including a computer program, which, when executed by a processor, is used to implement a model-based vehicle braking method according to the first aspect of the invention.
[0069] This application provides a model-based vehicle braking method, device, equipment, medium, and product. The method includes: acquiring the vehicle's state information in the current sampling period; inputting the state information of the current sampling period into a preset state transition model, and under the constraints of the preset state transition model, determining the vehicle's acceleration in the next sampling period when the preset cost function is minimized through an iterative optimization algorithm, which is taken as the vehicle's target acceleration; determining braking parameters based on the vehicle's target acceleration, and performing braking control on the vehicle based on the braking parameters. The following technical effects are achieved: By inputting the vehicle's state information in the current sampling period into a pre-established state transition model, the vehicle's acceleration in the next sampling period is obtained under the constraints of the state transition model when the preset cost function is minimized. This vehicle acceleration in the next sampling period is used as the target acceleration to determine the vehicle's braking parameters. Based on these braking parameters, the vehicle is controlled for braking, improving the accuracy and response speed of the automatic emergency braking system. This allows the vehicle to respond more quickly and accurately in emergency situations, thus improving driving safety in emergency situations. Furthermore, by accurately predicting the vehicle's state information in future moments, the target acceleration is obtained, and braking parameters are derived to control the vehicle. This improves braking efficiency and reduces braking distance, thereby avoiding or mitigating collisions and providing further safety for passengers. Attached Figure Description
[0070] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0071] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0072] Figure 1 A flowchart illustrating a model-predictive vehicle braking method provided in this application embodiment. Figure 1 ;
[0073] Figure 2 A flowchart illustrating a model-predictive vehicle braking method provided in this application embodiment. Figure 2 ;
[0074] Figure 3 A schematic diagram of a model-predictive vehicle braking device provided in an embodiment of this application;
[0075] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.
[0076] Figure label:
[0077] 310 - Acquisition Module; 320 - Determination Module; 330 - Control Module;
[0078] 410 - Processor; 420 - Memory; 430 - Communication components; 440 - Bus. Detailed Implementation
[0079] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0080] In the embodiments of this application, the terms "first" and "second" are used to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that "first" and "second" do not necessarily imply difference. It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate that something is being used as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in this application should not be construed as being better or more advantageous than other embodiments or design schemes. Specifically, the use of "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner. In the embodiments of this application, "at least one" refers to one or more, and "more than one" refers to two or more.
[0081] It should be noted that the phrase "at...time" in the embodiments of this application can refer to the instant at which a certain situation occurs, or to a period of time after the occurrence of a certain situation; the embodiments of this application do not specifically limit this. Furthermore, the electronic rearview mirror malfunction handling method for automobiles provided in the embodiments of this application is merely an example; an electronic rearview mirror malfunction handling method for automobiles may also include more or fewer elements.
[0082] To facilitate a clear description of the technical solutions in the embodiments of this application, some terms and technologies involved in the embodiments of this application will be briefly introduced below:
[0083] Automatic Emergency Braking (AEB) is an advanced driver assistance technology designed to avoid or mitigate a collision by automatically applying braking force (automatic braking) if the driver fails to take timely action. Current AEB systems typically rely on sensors, cameras, and radar to detect obstacles ahead and automatically apply braking when necessary.
[0084] Model Predictive Control (MPC): Determines the current control input by solving a finite-time optimization problem at each control time step and can handle system constraints. MPC uses a system model to predict behavior over a future period and optimizes control actions based on this prediction.
[0085] Automatic emergency braking (AEM) technology can automatically apply the brakes when a potential collision hazard is detected, effectively avoiding or reducing the occurrence of collisions and significantly improving driving safety. Current AEM systems generally use multiple sensors to collect real-time vehicle status and surrounding environment information. This information is then integrated and analyzed by a processor. A high-performance processor fuses and analyzes this multi-source data to predict potential collision hazards. Once a hazard is detected, the system quickly activates the braking system to automatically brake and avoid or mitigate the impact of a collision.
[0086] Nevertheless, existing vehicle automatic emergency braking technology still suffers from poor accuracy and faces challenges in terms of response speed and precision.
[0087] Based on this, embodiments of this application propose a model-predictive vehicle braking method, device, equipment, medium, and product, which can be used in the field of vehicle braking technology and aims to solve the above-mentioned technical problems of the prior art. By establishing a state transition model and based on the model predictive control algorithm, accurate prediction of vehicle dynamic characteristics is achieved, improving the response speed and decision accuracy of the automatic emergency braking system, providing more reliable safety protection for the vehicle in emergency situations, ensuring that the vehicle can respond more quickly and accurately when facing emergency situations, thereby improving the vehicle's braking efficiency and reducing braking distance, improving the vehicle's safety in emergency situations, avoiding or mitigating vehicle collisions, and providing further safety protection for drivers and passengers.
[0088] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0089] Figure 1 A flowchart illustrating a model-predictive vehicle braking method provided in this application embodiment. Figure 1 .like Figure 1 As shown, the method includes:
[0090] S101. Obtain the vehicle's status information in the current sampling period.
[0091] In this embodiment of the application, the execution entity of a model prediction-based vehicle braking method can be an electronic control unit (ECU) in the vehicle. This ECU can be a controller specifically designed for the model prediction-based vehicle braking method, or it can be an existing brake control unit (BCU) in the vehicle. No specific limitation is made here.
[0092] Specifically, the vehicle can periodically collect its state information through various sensors. This state information includes at least one of the following: the distance between the vehicle and an obstacle ahead, the vehicle's own speed, or the vehicle's own acceleration. To ensure driving safety, the ECU can calculate a target acceleration for the vehicle in each sampling period and control the vehicle based on this target acceleration, thereby improving vehicle safety in emergency situations. The ECU uses the same control method for the vehicle in each sampling period; this embodiment only details the model-predictive vehicle braking method for one sampling period.
[0093] First, the ECU acquires the vehicle's status information during the current sampling period in order to determine the vehicle's target acceleration based on this status information.
[0094] S102. Input the state information of the current sampling period into the preset state transition model, and under the constraints of the preset state transition model, determine the vehicle acceleration corresponding to the minimum preset cost function in the next sampling period through an iterative optimization algorithm, which is used as the target acceleration of the vehicle.
[0095] Specifically, the ECU stores a preset state transition model pre-set by technicians. Therefore, the ECU can input the state information of the current sampling period into this preset state transition model to predict the vehicle's state information over the next N sampling periods (N time points) based on the vehicle's current state information. Then, through an iterative optimization algorithm, it determines the target acceleration of the vehicle corresponding to the minimum preset cost function. The target acceleration of the vehicle refers to the vehicle's acceleration in the next sampling period when the preset cost function is minimized.
[0096] The preset state transition model describes the functional relationship between the state information of the (k+1)th sampling period and the state information of the kth sampling period, the duration of the sampling period, and the speed of the obstacle in front.
[0097] In one possible design, in the preset state transition model, the distance between the two vehicles in the (k+1)th sampling period is positively correlated with the distance between the two vehicles in the kth sampling period, the difference between the obstacle speed and the vehicle speed in the kth sampling period, the duration of the sampling period, the vehicle acceleration in the kth sampling period, and the rate of change of the vehicle acceleration in the kth sampling period.
[0098] The vehicle speed in the (k+1)th sampling period is positively correlated with the vehicle speed in the kth sampling period, the duration of the sampling period, the vehicle acceleration in the kth sampling period, and the rate of change of the vehicle acceleration in the kth sampling period.
[0099] The vehicle acceleration in the (k+1)th sampling period is positively correlated with the vehicle acceleration in the kth sampling period, the duration of the sampling period, and the rate of change of the vehicle acceleration in the kth sampling period.
[0100] The specific formulas for the above-mentioned preset state transition model are as follows:
[0101]
[0102] Where N is an integer greater than or equal to 1, k is an integer greater than or equal to 0 and less than N, the current sampling period is the 0th sampling period, and k = 0, 1, ..., N-1. D D represents the distance between the two vehicles in the (k+1)th sampling period. Let the distance between the two vehicles be the distance during the k-th sampling period. This is the difference between the obstacle speed and the vehicle speed in the k-th sampling period. Here, the obstacle usually refers to the vehicle in front. This usually refers to the relative speeds of the two vehicles during the k-th sampling period. Let Ts be the vehicle acceleration during the k-th sampling period, and Ts be the duration of the sampling period. The rate of change of the vehicle's acceleration in the kth sampling period can be obtained by using... The vehicle acceleration during the (k-1)th sampling period The difference between them is obtained by dividing by Ts, that is . The speed of the vehicle in the (k+1)th sampling period is... Let the speed of the vehicle be the speed in the kth sampling period. This is the vehicle acceleration during the (k+1)th sampling period.
[0103] Furthermore, by introducing an input matrix , The specific formula for the above-mentioned preset state transition model can also be expressed in matrix form, as follows:
[0104] ;
[0105] in, , W(k+1) is the state matrix corresponding to the state information of the (k+1)th sampling period.
[0106] , It is the distance between the two vehicles in the (k+1)th sampling period. It is the speed of the vehicle in the (k+1)th sampling period. It is the vehicle acceleration in the (k+1)th sampling period.
[0107] W(k) is the state matrix corresponding to the state information of the k-th sampling period. , It is the distance between the two vehicles in the kth sampling period. It is the speed of the vehicle in the kth sampling period. It is the vehicle acceleration in the kth sampling period.
[0108] U(k) is the input matrix for the kth sampling period. , It is the rate of change of the vehicle's acceleration in the kth sampling period, and Ts is the duration of the sampling period.
[0109] Next, we will introduce the preset cost function. The preset cost function describes the total deviation over N+1 sampling periods from 0 to N when controlling the vehicle in the current sampling period. The deviation in each sampling period includes at least one of the following: the degree of state deviation and the degree of input deviation. The degree of state deviation is the degree of deviation between the state information and the reference state information, and the degree of input deviation is the degree of deviation between the rate of change of the vehicle's acceleration and the rate of change of the vehicle's reference acceleration.
[0110] The specific formula for the cost function is as follows:
[0111] in, This is the reference state matrix corresponding to the reference state information of the k-th sampling period. , It is the reference distance between the two vehicles in the kth sampling period. It is the reference speed of the vehicle in the kth sampling period. It is the reference acceleration of the vehicle in the kth sampling period. For the input reference matrix, , Let be the rate of change of the vehicle's reference acceleration during the kth sampling period. This is the state matrix corresponding to the state information of the Nth sampling period. , It is the distance between the two vehicles in the Nth sampling period. It is the speed of the vehicle in the Nth sampling period. It is the vehicle acceleration in the Nth sampling period. This is the reference state matrix corresponding to the reference state information of the Nth sampling period. , It is the reference distance between the two vehicles in the Nth sampling period. It is the reference speed of the vehicle in the Nth sampling period. This is the vehicle's reference acceleration during the Nth sampling period. The reference state information is pre-calculated based on the sampling period and can be a preset fixed value. Q, R, and These are the corresponding weight matrices. Specifically,
[0112] R=0.3 .
[0113] In one possible design, the pre-defined cost function can be transformed into the following formula:
[0114] ;
[0115] in, Z is the total deviation, and Z is the optimization matrix. , Let U be the state matrix for the 0th sampling period (current time), and U(0) be the input matrix for the 0th sampling period (current time). Let U(1) be the state matrix for the first sampling period (the next sampling period after the current time), and let U(1) be the input matrix for the first sampling period. For the first The state matrix of each sampling period, U( ) is the first The input matrix for each sampling period.
[0116] Specifically, ;
[0117] .
[0118] S103. Determine the braking parameters based on the target acceleration of the vehicle, and perform braking control on the vehicle based on the braking parameters.
[0119] Specifically, after determining the target acceleration of the vehicle, the ECU can further determine the specific braking parameters for braking based on the target acceleration, and then perform the next step of braking control based on the braking parameters to improve the driving safety of the vehicle during braking.
[0120] This embodiment provides a model-based vehicle braking method, which includes: acquiring the vehicle's state information in the current sampling period; inputting the state information of the current sampling period into a preset state transition model, and under the constraints of the preset state transition model, determining the vehicle's acceleration in the next sampling period when the preset cost function is minimized through an iterative optimization algorithm, which is taken as the vehicle's target acceleration; determining braking parameters based on the vehicle's target acceleration, and performing braking control on the vehicle based on the braking parameters.
[0121] The following technical effects are achieved: By inputting the vehicle's state information in the current sampling period into a pre-established state transition model, the vehicle's acceleration in the next sampling period is obtained under the constraints of the state transition model when the preset cost function is minimized. This vehicle acceleration in the next sampling period is used as the target acceleration to determine the vehicle's braking parameters. Based on these braking parameters, the vehicle is controlled for braking, improving the accuracy and response speed of the automatic emergency braking system. This allows the vehicle to respond more quickly and accurately in emergency situations, thus improving driving safety in emergency situations. Furthermore, by accurately predicting the vehicle's state information in future moments, the target acceleration is obtained, and braking parameters are derived to control the vehicle. This improves braking efficiency and reduces braking distance, thereby avoiding or mitigating collisions and providing further safety for passengers.
[0122] Figure 2 A flowchart illustrating a model-predictive vehicle braking method provided in this application embodiment. Figure 2 In one possible example, such as Figure 2 As shown, in this embodiment... Figure 1 Based on the examples, a detailed explanation is provided on how to extract the target acceleration of the vehicle and how to determine the braking parameters. For example... Figure 2 As shown, the method includes:
[0123] S201. Obtain the vehicle's status information during the current sampling period.
[0124] S202. Input the state information of the current sampling period into the preset state transition model.
[0125] S201-S202 are similar to S101-S102, and the parts with the same content will not be described again in this embodiment.
[0126] S203. Under the constraints of the preset state transition model, the optimization matrix corresponding to the minimum preset cost function is determined by the iterative optimization algorithm, and is used as the target optimization matrix.
[0127] Specifically, the ECU can determine the target optimization matrix that minimizes the output of a preset cost function through an iterative optimization algorithm. This target optimization matrix contains N+1 target state matrices, i.e., it includes... And W(N), k=0,1,…,N-1.
[0128] S204. Extract the vehicle acceleration of the first sampling period from the target optimization matrix and use it as the target acceleration of the vehicle.
[0129] Specifically, the target optimization matrix contains the target state matrix corresponding to the state information of the first sampling period when k=1. The ECU can obtain the target state matrix corresponding to the state information in the first sampling period. In the process, the vehicle acceleration of the first sampling period is extracted. , in order to The target acceleration is used to control the vehicle.
[0130] S205. Simulate the braking effect of the target acceleration on the vehicle on the vehicle's display device.
[0131] Specifically, the ECU determines the target acceleration of the vehicle in the first sampling period in the future. Then, braking parameters can be further determined based on the target acceleration of the vehicle. Specifically, the braking effect after controlling the vehicle according to the target acceleration can first be simulated on the in-vehicle display equipment. For example, the impact of the target acceleration on the braking effect can be simulated and displayed through the vehicle's central control display screen, such as displaying information like braking distance, vehicle speed after braking, and braking time under the target acceleration condition through charts or 3D animations; the vehicle's speed changes during braking according to the target acceleration can also be displayed to the user in real time through the digital instrument panel display screen; the simulation results of the target acceleration braking effect can also be displayed to the user through the vehicle's head-up display screen; and the braking effect of the target acceleration can also be displayed through the multi-function steering wheel display screen, without any limitations.
[0132] S206. Upon receiving a user's adjustment operation for the braking effect, adjust the target acceleration according to the adjusted braking effect, and return to the step of simulating the braking effect of the target acceleration on the vehicle's display device.
[0133] Specifically, after observing the braking effect of the target acceleration on the vehicle's display, the user can adjust the braking effect, such as adjusting the braking distance, the vehicle speed after braking, and the braking time. Upon receiving the user's adjustment, the ECU can further adjust the target acceleration and continue displaying it to the user on the vehicle's display, controlling the vehicle according to the adjusted target acceleration to simulate the braking effect. This process returns to the step of simulating the braking effect of the target acceleration on the vehicle's display until the user no longer adjusts the target acceleration.
[0134] S207. When no user operation on braking effect is received, construct a braking system model based on the structure of the braking system.
[0135] Specifically, when the ECU does not receive user adjustments to the braking effect, it can construct a braking system model based on the braking system's structure. For example, if the user is satisfied with the braking effect and agrees to brake the vehicle according to the target acceleration, or if the sampling period is relatively short, the ECU can default to performing braking operations based on the target acceleration without user intervention.
[0136] The braking system model is used to describe the positive correlation function between the acceleration input to the braking system and the braking parameters, including braking pressure and braking duration.
[0137] The ECU constructs a braking system model based on the system's structure, including: First, using the target acceleration as input and the braking pressure and braking duration as outputs; then, establishing dynamic equations, for example, based on Newton's second law, the target acceleration equals the braking force divided by the vehicle's mass. The braking force is typically proportional to the braking pressure, and this ratio is a constant of the braking system, which can be determined based on its specific structure. The braking duration can be determined by considering the vehicle's current initial speed, specifically equal to the initial speed divided by the target acceleration; finally, establishing a positive correlation function between the target acceleration, braking pressure, and braking duration; this positive correlation function constitutes the braking system model.
[0138] S208. Input the target acceleration of the vehicle into the braking system model to obtain the braking parameters corresponding to the target acceleration.
[0139] Specifically, the ECU inputs the target acceleration of the vehicle into the braking system model, thereby outputting the braking pressure and braking duration corresponding to the target acceleration.
[0140] S209. Send the braking parameters to the control unit of the braking system so that the control unit can parse the braking parameters and execute the braking operation.
[0141] Specifically, after obtaining the braking parameters, the ECU can further send the braking parameters to the control unit of the braking system through the vehicle network, such as the Controller Area Network (CAN) bus. The control unit of the braking system can then analyze the braking parameters and execute the braking operation to achieve braking control of the vehicle.
[0142] In one possible implementation, the ECU can also be the control unit of the braking system, namely the BCU. That is, after obtaining the braking parameters, the ECU can further directly control the vehicle's braking based on the braking pressure and braking duration.
[0143] This application provides a model-based vehicle braking method that simulates the braking effect of a target acceleration on the vehicle's display device, enabling real-time adjustment of the braking effect based on the target acceleration output to the user. The method constructs a braking system model based on the system's structure to obtain the braking parameters corresponding to the target acceleration. The braking parameters are then analyzed by the braking system's control unit, and braking operations are executed, achieving precise braking control of the vehicle.
[0144] In this embodiment of the invention, electronic devices or main control devices can be divided into functional modules according to the above method examples. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional module. It should be noted that the module division in this embodiment of the invention is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.
[0145] Figure 3 This is a schematic diagram of a model-predictive vehicle braking device provided as an embodiment of this application. Figure 3 As shown, the model-predictive vehicle braking device includes: an acquisition module 310, a determination module 320, and a control module 330;
[0146] The acquisition module 310 is used to acquire the vehicle's status information in the current sampling period. The status information includes at least one of the following: the distance between the vehicle and the obstacle in front, the vehicle's own speed, or the vehicle's own acceleration.
[0147] The determination module 320 is used to input the state information of the current sampling period into the preset state transition model, and under the constraints of the preset state transition model, determine the vehicle acceleration corresponding to the minimum preset cost function in the next sampling period through an iterative optimization algorithm, which is used as the target acceleration of the vehicle. The preset state transition model describes the functional relationship between the state information of the (k+1)th sampling period and the state information of the kth sampling period, the duration of the sampling period, and the speed of the obstacle in front. The preset cost function describes the total deviation of N+1 sampling periods when the vehicle is controlled in the current sampling period. The deviation of each sampling period includes at least one of the following: the degree of state deviation and the degree of input deviation. The degree of state deviation is the degree of deviation between the state information and the reference state information. The degree of input deviation is the degree of deviation between the rate of change of the vehicle acceleration and the rate of change of the vehicle reference acceleration. N is an integer greater than or equal to 1, k is an integer greater than or equal to 0 and less than N, and the current sampling period is the 0th sampling period.
[0148] The control module 330 is used to determine braking parameters based on the target acceleration of the vehicle and to perform braking control on the vehicle based on the braking parameters.
[0149] In one possible design, in the preset state transition model, the distance between the two vehicles in the (k+1)th sampling period is positively correlated with the distance between the two vehicles in the kth sampling period, the difference between the obstacle speed and the vehicle speed in the kth sampling period, the duration of the sampling period, the vehicle acceleration in the kth sampling period, and the rate of change of the vehicle acceleration in the kth sampling period.
[0150] The vehicle speed in the (k+1)th sampling period is positively correlated with the vehicle speed in the kth sampling period, the duration of the sampling period, the vehicle acceleration in the kth sampling period, and the rate of change of the vehicle acceleration in the kth sampling period.
[0151] The vehicle acceleration in the (k+1)th sampling period is positively correlated with the vehicle acceleration in the kth sampling period, the duration of the sampling period, and the rate of change of the vehicle acceleration in the kth sampling period.
[0152] In one possible design, the preset state transition model is as follows:
[0153] ;
[0154] in, , W(k+1) is the state matrix corresponding to the state information of the (k+1)th sampling period. , It is the distance between the two vehicles in the (k+1)th sampling period. It is the speed of the vehicle in the (k+1)th sampling period. It is the vehicle acceleration in the (k+1)th sampling period;
[0155] W(k) is the state matrix corresponding to the state information of the k-th sampling period. , It is the distance between the two vehicles in the kth sampling period. It is the speed of the vehicle in the kth sampling period. It is the vehicle acceleration in the kth sampling period;
[0156] U(k) is the input matrix for the kth sampling period. , It is the rate of change of the vehicle's acceleration in the kth sampling period, and Ts is the duration of the sampling period.
[0157] In one possible design, the pre-defined cost function is as follows:
[0158] ;
[0159] in, Z is the total deviation, and Z is the optimization matrix. ,
[0160] R=0.3
[0161] , , , This is the reference state matrix corresponding to the reference state information of the k-th sampling period. , It is the reference distance between the two vehicles in the kth sampling period. It is the reference speed of the vehicle in the kth sampling period. It is the reference acceleration of the vehicle in the kth sampling period. For the input reference matrix, , Let be the rate of change of the vehicle's reference acceleration during the kth sampling period.
[0162] In one possible design, the determination module 320 includes: an optimization matrix determination module and an extraction module.
[0163] The optimization matrix determination module is used to determine the optimization matrix corresponding to the minimum preset cost function through an iterative optimization algorithm, which is used as the target optimization matrix.
[0164] The extraction module is used to extract the vehicle's acceleration for the first sampling period from the target optimization matrix, and use it as the vehicle's target acceleration.
[0165] In one possible design, the control module 330 includes: a display module, a parameter determination module, and an adjustment module;
[0166] The display module is used to simulate the braking effect of the target acceleration on the vehicle's display device.
[0167] The parameter determination module is used to determine braking parameters based on the target acceleration of the vehicle when no user operation on braking effect is received.
[0168] The adjustment module is used to adjust the target acceleration according to the adjusted braking effect when it receives the user's adjustment operation for the braking effect, and return the steps of simulating the braking effect of the target acceleration on the vehicle's display device.
[0169] In one possible design, the adjustment modules include: a building module and an input module;
[0170] The construction module is used to build a braking system model based on the structure of the braking system. The braking system model is used to describe the positive correlation function relationship between the acceleration input to the braking system and the braking parameters, including braking pressure and braking duration.
[0171] The input module is used to input the target acceleration of the vehicle into the braking system model to obtain the braking parameters corresponding to the target acceleration.
[0172] In one possible design, the control module 330 further includes a transmitting module;
[0173] The transmitting module is used to send braking parameters to the control unit of the braking system, so that the control unit can parse the braking parameters and perform braking operations.
[0174] This embodiment provides a model prediction-based vehicle braking device that can execute a model prediction-based vehicle braking method described in the above embodiment. Its implementation principle and technical effects are similar, and will not be repeated here.
[0175] In the aforementioned specific implementation of a model-predictive vehicle braking device, each module can be implemented as a processor. The processor can execute computer execution instructions stored in the memory, thereby enabling the processor to execute the aforementioned model-predictive vehicle braking method.
[0176] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device includes at least one processor 410 and a memory 420. The electronic device also includes a communication component 430. The processor 410, memory 420, and communication component 430 are connected via a bus 440.
[0177] In the specific implementation process, at least one processor 410 executes computer execution instructions stored in memory 420, causing at least one processor 410 to execute a model prediction-based vehicle braking method as executed on the electronic device side as described above.
[0178] The specific implementation process of processor 410 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.
[0179] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.
[0180] The memory may include high-speed RAM, and may also include non-volatile storage (NVM), such as at least one disk storage.
[0181] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.
[0182] The above description of the functions implemented by electronic devices and main control devices has introduced the solutions provided by the embodiments of the present invention. It is understood that, in order to implement the above functions, the electronic device or main control device includes hardware structures and / or software modules corresponding to the execution of each function. By combining the units and algorithm steps of the various examples described in the embodiments of the present invention, the embodiments of the present invention can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the technical solutions of the embodiments of the present invention.
[0183] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the above-described model-prediction-based vehicle braking method.
[0184] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.
[0185] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in an electronic device or a host device.
[0186] This application also provides a computer program product, which includes a computer program stored in a readable storage medium. At least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to cause the electronic device to perform the solution provided in any of the above embodiments.
[0187] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disk, or optical disk.
[0188] The technical solutions of this application have been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. The above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.
Claims
1. A vehicle braking method based on model prediction, characterized in that, include: Obtain the vehicle's status information in the current sampling period. The status information includes at least one of the following: the distance between the vehicle and the obstacle in front, the vehicle's own speed, or the vehicle's own acceleration. The state information of the current sampling period is input into a preset state transition model. Under the constraints of the preset state transition model, the vehicle's acceleration in the next sampling period is determined by an iterative optimization algorithm when the preset cost function is minimized. This acceleration is taken as the target acceleration of the vehicle. The preset state transition model describes the functional relationship between the state information of the (k+1)th sampling period and the state information of the kth sampling period, the duration of the sampling period, and the speed of the obstacle ahead. The preset cost function describes the total deviation of N+1 sampling periods when vehicle control is performed in the current sampling period. The deviation of each sampling period includes at least one of the following: state deviation degree and input deviation degree. The state deviation degree is the deviation between the state information and the reference state information. The input deviation degree is the deviation between the rate of change of the vehicle's acceleration and the rate of change of the vehicle's reference acceleration. N is an integer greater than or equal to 1, k is an integer greater than or equal to 0 and less than N, and the current sampling period is the 0th sampling period. Braking parameters are determined based on the target acceleration of the vehicle, and braking control of the vehicle is performed based on the braking parameters.
2. The method according to claim 1, characterized in that, In the preset state transition model, the distance between the two vehicles in the (k+1)th sampling period is positively correlated with the distance between the two vehicles in the kth sampling period, the difference between the obstacle speed and the vehicle speed in the kth sampling period, the duration of the sampling period, the vehicle acceleration in the kth sampling period, and the rate of change of the vehicle acceleration in the kth sampling period. The vehicle speed in the (k+1)th sampling period is positively correlated with the vehicle speed in the kth sampling period, the duration of the sampling period, the vehicle acceleration in the kth sampling period, and the rate of change of the vehicle acceleration in the kth sampling period. The vehicle acceleration in the (k+1)th sampling period is positively correlated with the vehicle acceleration in the kth sampling period, the duration of the sampling period, and the rate of change of the vehicle acceleration in the kth sampling period.
3. The method according to claim 2, characterized in that, The preset state transition model is as follows: ； in, , W(k+1) is the state matrix corresponding to the state information of the (k+1)th sampling period. , It is the distance between the two vehicles in the (k+1)th sampling period. It is the speed of the vehicle in the (k+1)th sampling period. It is the vehicle acceleration in the (k+1)th sampling period; W(k) is the state matrix corresponding to the state information of the k-th sampling period. , It is the distance between the two vehicles in the kth sampling period. It is the speed of the vehicle in the kth sampling period. It is the vehicle acceleration in the kth sampling period; U(k) is the input matrix for the kth sampling period. , It is the rate of change of the vehicle's acceleration in the kth sampling period, and Ts is the duration of the sampling period.
4. The method according to claim 3, characterized in that, The preset cost function is as follows: ； in, Z is the total deviation, and Z is the optimization matrix. , R=0.3 , , , This is the reference state matrix corresponding to the reference state information of the k-th sampling period. , It is the reference distance between the two vehicles in the kth sampling period. It is the reference speed of the vehicle in the kth sampling period. It is the reference acceleration of the vehicle in the kth sampling period. For the input reference matrix, , Let be the rate of change of the vehicle's reference acceleration during the kth sampling period.
5. The method according to claim 4, characterized in that, The step of determining the vehicle's acceleration in the next sampling period when the preset cost function is minimized through an iterative optimization algorithm, and using this acceleration as the target acceleration of the vehicle, includes: The optimization matrix corresponding to the minimum preset cost function is determined by an iterative optimization algorithm and used as the target optimization matrix. The vehicle acceleration for the first sampling period is extracted from the target optimization matrix and used as the target vehicle acceleration.
6. The method according to any one of claims 1 to 5, characterized in that, The step of determining braking parameters based on the target acceleration of the vehicle includes: The braking effect of the target acceleration on the vehicle is simulated on the vehicle's display device; When no user operation is received regarding the braking effect, the braking parameters are determined based on the target acceleration of the vehicle. Upon receiving a user's adjustment operation for the braking effect, the target acceleration is adjusted according to the adjusted braking effect, and the process returns to the step of simulating the braking effect of the target acceleration on the vehicle's display device.
7. The method according to claim 6, characterized in that, The step of determining braking parameters based on the target acceleration of the vehicle includes: A braking system model is constructed based on the structure of the braking system. The braking system model is used to describe the positive correlation function relationship between the acceleration input to the braking system and the braking parameters, including braking pressure and braking duration. The target acceleration of the vehicle is input into the braking system model to obtain the braking parameters corresponding to the target acceleration.
8. The method according to claim 7, characterized in that, The step of controlling the vehicle's braking according to the braking parameters includes: The braking parameters are sent to the control unit of the braking system so that the control unit can parse the braking parameters and perform braking operations.
9. A vehicle braking device based on model prediction, characterized in that, include: The acquisition module is used to acquire the vehicle's status information in the current sampling period. The status information includes at least one of the following: the distance between the vehicle and the obstacle in front, the vehicle's own speed, or the vehicle's own acceleration. A determination module is used to input the state information of the current sampling period into a preset state transition model, and under the constraints of the preset state transition model, determine the vehicle acceleration corresponding to the next sampling period when the preset cost function is minimized through an iterative optimization algorithm, which is taken as the target acceleration of the vehicle. The preset state transition model describes the functional relationship between the state information of the (k+1)th sampling period and the state information of the kth sampling period, the duration of the sampling period, and the speed of the obstacle ahead. The preset cost function describes the total deviation over N+1 sampling periods when vehicle control is performed in the current sampling period. The deviation of each sampling period includes at least one of the following: state deviation degree and input deviation degree. The state deviation degree is the deviation between the state information and the reference state information. The input deviation degree is the deviation between the rate of change of the vehicle acceleration and the rate of change of the vehicle reference acceleration. N is an integer greater than or equal to 1, k is an integer greater than or equal to 0 and less than N, and the current sampling period is the 0th sampling period. The control module is used to determine braking parameters based on the target acceleration of the vehicle, and to perform braking control on the vehicle based on the braking parameters.
10. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the model prediction-based vehicle braking method as described in any one of claims 1 to 8.
11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the model-prediction-based vehicle braking method as described in any one of claims 1 to 8.
12. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the model prediction-based vehicle braking method as described in any one of claims 1 to 8.