Vehicle adaptive cruise control method, device and equipment and storage medium

Abstract

The invention provides a vehicle self-adaptive cruise control method and device, equipment and a storage medium. The method comprises the steps that the distance difference value between the expected longitudinal distance between a target vehicle and a front obstacle and the actual longitudinal distance between the target vehicle and the front obstacle and the speed difference value between the target vehicle and the front obstacle are calculated; a control quantity weight parameter in the LQR algorithm is determined, and the larger the actual longitudinal distance between the control quantity weight parameter and the LQR algorithm is, the larger the control quantity weight parameter is; the smaller the longitudinal acceleration of the front obstacle is, the larger the control quantity weight parameter is, the state quantity in the LQR algorithm is a speed difference value and a distance difference value, and the control quantity is the expected longitudinal acceleration of the target vehicle to be solved; and the expected longitudinal acceleration of the target vehicle is obtained according to the control quantity weight parameter and the state quantity, and the longitudinal acceleration of the target vehicle is adjusted to be the expected value. According to the method, through a dynamic adjustment mechanism of weight parameters, the choice contradiction between fuel economy and comfort caused by fixed parameters in a traditional method can be avoided, and self-adaptive balance between fuel consumption optimization and driving smoothness is achieved under the safety priority principle according to real-time working conditions.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a vehicle adaptive cruise control method, device, equipment and storage medium. Background Technology

[0002] Cruise control is an advanced driver assistance technology that automatically adjusts the vehicle's driving status through the onboard control system. Its core function is to replace the driver's continuous operation of the power system, thereby reducing the driver's workload. Generally, this technology collects vehicle operating parameters and external environmental information, processes them using control algorithms, and outputs drive or braking commands to improve driving safety and optimize vehicle operating efficiency. With the continuous development of intelligent driving technology, cruise control has evolved from simple speed maintenance to a comprehensive control system with environmental interaction capabilities.

[0003] Currently, cruise control technology is mainly divided into two categories: constant speed cruise (CC) and adaptive cruise (ACC). Constant speed cruise achieves constant speed by locking a preset speed, suitable for simple road conditions; while adaptive cruise, through the integration of sensors such as radar and cameras, senses the movement of vehicles ahead in real time and automatically adjusts the vehicle speed to maintain a safe following distance. Existing ACC systems typically employ algorithms such as PID control and model predictive control (MPC) to achieve basic distance maintenance and speed adjustment functions while ensuring following safety.

[0004] However, traditional cruise control methods have an inherent contradiction in parameter adjustment: overemphasizing driving comfort may lead to frequent small acceleration and braking operations, thus significantly increasing fuel consumption; while simply pursuing fuel economy may cause large speed fluctuations and sudden acceleration changes, reducing the driving experience. Traditional cruise control methods cannot achieve a dynamic balance between fuel economy and driving comfort. Summary of the Invention

[0005] This application provides a vehicle adaptive cruise control method, device, equipment, and storage medium to solve the problem that traditional cruise control methods cannot achieve a dynamic balance between fuel economy and driving comfort.

[0006] In a first aspect, this application provides a vehicle adaptive cruise control method, the method comprising:

[0007] The system obtains the actual longitudinal distance between the obstacle in front of the target vehicle and the target vehicle, the longitudinal velocity and longitudinal acceleration of the obstacle in front, and the longitudinal speed of the target vehicle; calculates the speed difference between the longitudinal velocity of the obstacle in front and the longitudinal speed of the target vehicle; and calculates the distance difference between the expected longitudinal distance and the actual longitudinal distance based on the expected longitudinal distance between the target vehicle and the obstacle in front.

[0008] Based on the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead, the weight parameters of the control quantity in the linear quadratic regulator control algorithm are determined. The larger the actual longitudinal distance, the larger the weight parameter of the control quantity; the smaller the longitudinal acceleration of the obstacle ahead, the larger the weight parameter of the control quantity. The state variables in the linear quadratic regulator control algorithm are the speed difference and the distance difference, and the control quantity is the desired longitudinal acceleration of the target vehicle to be solved.

[0009] The control quantity is solved based on the weight parameters of the control quantity and the state quantity to obtain the desired longitudinal acceleration of the target vehicle;

[0010] The longitudinal acceleration of the target vehicle is adjusted to the desired longitudinal acceleration.

[0011] In one possible design, determining the weight parameters of the control quantity in the linear quadratic regulator control algorithm based on the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead includes:

[0012] Based on the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead, a predefined mapping table is consulted to determine the weight parameters of the control quantity corresponding to the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead. The predefined mapping table indicates the correspondence between different actual longitudinal distances and the longitudinal acceleration of the obstacle ahead and the weight parameters of the control quantity. In the predefined mapping table, when the actual longitudinal distance increases, the weight parameter of the control quantity increases; when the longitudinal acceleration of the obstacle ahead decreases, the weight parameter of the control quantity increases.

[0013] In one possible design, determining the weight parameters of the control quantity in the linear quadratic regulator control algorithm based on the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead includes:

[0014] The actual longitudinal distance and the longitudinal acceleration of the obstacle ahead are input into a pre-trained weight parameter mapping model, which outputs the weight parameters of the control quantity. The pre-trained weight parameter mapping model is configured such that when the actual longitudinal distance increases, the weight parameters of the output control quantity increase; when the longitudinal acceleration of the obstacle ahead decreases, the weight parameters of the output control quantity increase.

[0015] In one possible design, the method further includes:

[0016] Based on the actual longitudinal distance, the speed difference, and the longitudinal acceleration of the obstacle ahead, the weight parameters of the speed difference and the distance difference in the linear quadratic regulator control algorithm are determined. The larger the actual longitudinal distance, the smaller the weight parameter of the distance difference; the smaller the speed difference, the smaller the weight parameter of the speed difference; and the larger the longitudinal acceleration of the obstacle ahead, the larger the weight parameter of the distance difference.

[0017] In one possible design, determining the weight parameters for the velocity difference and the distance difference in the linear quadratic regulator control algorithm based on the actual longitudinal distance, the velocity difference, and the longitudinal acceleration of the obstacle ahead includes:

[0018] Determine whether the longitudinal acceleration of the obstacle in front is greater than a preset acceleration threshold;

[0019] If so, the weighting parameter of the distance difference is determined based on the longitudinal acceleration of the obstacle in front. The greater the longitudinal acceleration of the obstacle in front, the greater the weighting parameter of the distance difference.

[0020] If not, then the weighting parameter of the distance difference is determined based on the actual longitudinal distance. The larger the actual longitudinal distance, the smaller the weighting parameter of the distance difference.

[0021] In one possible design, the step of solving for the control quantity based on the weight parameters of the control quantity and the state quantity to obtain the desired longitudinal acceleration of the target vehicle includes:

[0022] The feedback coefficients of the linear quadratic regulator control algorithm are determined based on the weight parameters of the control quantity, the speed difference, and the distance difference.

[0023] The control quantity is solved by multiplying the feedback coefficient and the state quantity to obtain the desired longitudinal acceleration of the target vehicle.

[0024] In one possible design, adjusting the longitudinal acceleration of the target vehicle to the desired longitudinal acceleration includes:

[0025] Based on the desired longitudinal acceleration, the required torque of the target vehicle is calculated using the following formula:

[0026]

[0027] in, The required torque; The gear ratio of the main reducer of the target vehicle; The gear ratio of the transmission of the target vehicle; The transmission efficiency of the power system of the target vehicle; Let be the wheel rolling radius of the target vehicle; The total mass of the target vehicle; It is the acceleration due to gravity; The slope of the road in front of the target vehicle; The rolling resistance of the wheels of the target vehicle; Let be the drag coefficient of the target vehicle; The frontal area of ​​the target vehicle; The longitudinal vehicle speed; is the rotational mass conversion factor for the target vehicle; a is the desired longitudinal acceleration;

[0028] The output torque of the engine of the target vehicle is adjusted to the required torque.

[0029] Secondly, this application provides a vehicle adaptive cruise control device, the device comprising:

[0030] The status acquisition module is used to: acquire the actual longitudinal distance between the obstacle in front of the target vehicle and the target vehicle, the longitudinal velocity and longitudinal acceleration of the obstacle in front, the longitudinal speed of the target vehicle, calculate the speed difference between the longitudinal velocity of the obstacle in front and the longitudinal speed of the target vehicle, and calculate the distance difference between the expected longitudinal distance and the actual longitudinal distance based on the expected longitudinal distance between the target vehicle and the obstacle in front.

[0031] The weight parameter calculation module is used to: determine the weight parameters of the control quantity in the linear quadratic regulator control algorithm based on the actual longitudinal distance and the longitudinal acceleration of the obstacle in front. The larger the actual longitudinal distance, the larger the weight parameter of the control quantity; the smaller the longitudinal acceleration of the obstacle in front, the larger the weight parameter of the control quantity. The state quantity in the linear quadratic regulator control algorithm is the speed difference and the distance difference, and the control quantity is the desired longitudinal acceleration of the target vehicle to be solved.

[0032] An acceleration calculation module is used to: solve for the control quantity based on the weight parameters of the control quantity and the state quantity to obtain the desired longitudinal acceleration of the target vehicle;

[0033] The control module is used to adjust the longitudinal acceleration of the target vehicle to the desired longitudinal acceleration.

[0034] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0035] The memory stores computer-executed instructions;

[0036] The processor executes computer execution instructions stored in the memory to implement the vehicle adaptive cruise control method as described in the first aspect.

[0037] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the vehicle adaptive cruise control method as described in the first aspect.

[0038] The vehicle adaptive cruise control method, device, equipment, and storage medium provided in this application have the following technical advantages:

[0039] This scheme dynamically determines the LQR control weight parameter using both actual longitudinal distance and the longitudinal acceleration of the obstacle ahead. When the actual longitudinal distance increases, the control weight parameter is increased to suppress acceleration fluctuations, thereby reducing fuel consumption caused by frequent acceleration or braking of the target vehicle. Simultaneously, when the longitudinal acceleration of the obstacle ahead decreases, the control weight parameter is increased, allowing the target vehicle to prioritize limiting power output to improve economy under stable following conditions. Conversely, when the actual longitudinal distance decreases or the longitudinal acceleration of the obstacle ahead suddenly increases, the control weight parameter automatically decreases, allowing for greater acceleration adjustment margin to quickly respond to safety requirements. Therefore, in dynamic traffic scenarios, this coordinated adjustment mechanism of the weight parameter avoids the trade-off between fuel economy and comfort caused by fixed parameters in traditional methods, and achieves an adaptive balance between fuel consumption optimization and driving smoothness based on real-time operating conditions and the principle of safety priority. Attached Figure Description

[0040] 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.

[0041] Figure 1 Flowchart of the vehicle adaptive cruise control method provided in the embodiments of this application Figure 1 ;

[0042] Figure 2 This is a schematic diagram of vehicle longitudinal acceleration control provided in an embodiment of this application;

[0043] Figure 3 Flowchart of the vehicle adaptive cruise control method provided in the embodiments of this application Figure 2 ;

[0044] Figure 4 Flowchart of the vehicle adaptive cruise control method provided in the embodiments of this application Figure 3 ;

[0045] Figure 5 A schematic diagram of the vehicle adaptive cruise control device provided in this application;

[0046] Figure 6 A schematic diagram of the structure of the electronic device provided in this application.

[0047] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0048] 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.

[0049] First, let me explain the terms used in this application:

[0050] Linear Quadratic Regulator Control Algorithm: Also known as the LQR algorithm, it is an optimal control method based on a state-space model. It designs a feedback controller by minimizing a quadratic cost function that includes the state deviation and the control input.

[0051] State variables: In this scheme, they refer to a two-dimensional vector composed of velocity difference and distance difference, reflecting the dynamic characteristics of the system.

[0052] Control variable: refers to the longitudinal acceleration command to be optimized, which is the output of the LQR algorithm.

[0053] Weighting parameters: represent the priority of different control objectives. This scheme achieves a balance between economy and comfort through dynamic adjustment.

[0054] To address the problem that traditional cruise control methods cannot achieve a dynamic balance between fuel economy and driving comfort, the technical concept of this application is:

[0055] The actual longitudinal distance between the target vehicle and the obstacle in front, the longitudinal velocity and acceleration of the obstacle, and the longitudinal speed of the target vehicle are obtained. The distance difference between the expected longitudinal distance and the actual longitudinal distance, and the speed difference between the longitudinal velocity of the obstacle and the longitudinal speed of the target vehicle are calculated. Next, based on the actual longitudinal distance and the longitudinal acceleration of the obstacle, the weight parameters of the control quantity in the Linear Quadratic Regulator (LQR) control algorithm are determined: the larger the actual longitudinal distance, the larger the weight parameter of the control quantity; the smaller the longitudinal acceleration of the obstacle, the larger the weight parameter of the control quantity. The state variables of the LQR algorithm are the distance difference and the speed difference, and the control variable is the expected longitudinal acceleration of the target vehicle. The expected longitudinal acceleration of the target vehicle is calculated based on the weight parameters and state variables of the control quantity, and the longitudinal acceleration of the target vehicle is adjusted to this expected longitudinal acceleration.

[0056] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0057] Example 1

[0058] This application provides a vehicle adaptive cruise control method, which can be applied to the vehicle's adaptive cruise control system. Figure 1 Flowchart of the vehicle adaptive cruise control method provided in the embodiments of this application Figure 1 ,like Figure 1 As shown, the method includes:

[0059] S101. Obtain the actual longitudinal distance between the obstacle in front of the target vehicle and the target vehicle, the longitudinal velocity and longitudinal acceleration of the obstacle in front, and the longitudinal speed of the target vehicle; calculate the speed difference between the longitudinal velocity of the obstacle in front and the longitudinal speed of the target vehicle; and, based on the expected longitudinal distance between the target vehicle and the obstacle in front, calculate the distance difference between the expected longitudinal distance and the actual longitudinal distance.

[0060] In this application, obstacles ahead can be, for example, motor vehicles, non-motor vehicles, pedestrians, etc. Specifically, the actual longitudinal distance can be calculated by fusing direct ranging data from the vehicle-mounted millimeter-wave radar with target recognition results from the camera; the longitudinal velocity of the obstacle ahead can be measured by the vehicle-mounted millimeter-wave radar and calculated differentially using historical data of the obstacle's longitudinal velocity; the longitudinal speed of the target vehicle can be measured by wheel speed sensors or an inertial navigation system. Furthermore, motion parameters directly uploaded by the vehicle ahead can be obtained via V2X communication, or the motion state of the obstacle ahead can be estimated using cluster analysis of point cloud data from the lidar mounted on the target vehicle.

[0061] S102. Based on the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead, determine the weight parameters of the control quantity in the linear quadratic regulator control algorithm. The larger the actual longitudinal distance, the larger the weight parameters of the control quantity; the smaller the longitudinal acceleration of the obstacle ahead, the larger the weight parameters of the control quantity. In the linear quadratic regulator control algorithm, the state variables are the speed difference and the distance difference, and the control variable is the desired longitudinal acceleration of the target vehicle to be solved.

[0062] This step aims to achieve a dynamic balance of control objectives. Since different following scenarios have varying weights for fuel economy, safety, and comfort, the control weights need to be adaptively adjusted using operating condition characteristic parameters. Specifically, the weight parameter of the control quantity refers to the penalty coefficient of the acceleration term in the cost function of the LQR algorithm. A larger parameter indicates a stricter restriction on acceleration changes, corresponding to a control strategy that prioritizes driving comfort and fuel economy. In this step, the weight parameter of the control quantity can be determined, for example, by: looking up a table based on the real-time measured actual longitudinal distance and the acceleration of the vehicle ahead; using a fuzzy logic controller, taking distance deviation and acceleration change rate as input variables, and outputting the weight parameter of the control quantity through preset fuzzy rules; and designing an adaptive function based on a safe distance model, reducing the weight parameter of the control quantity to improve fuel economy when the actual longitudinal distance exceeds a safe threshold.

[0063] Optionally, based on the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead, the weight parameters of the control quantity in the linear quadratic regulator control algorithm are determined, including:

[0064] The actual longitudinal distance and the longitudinal acceleration of the obstacle ahead are input into a pre-trained weight parameter mapping model. The pre-trained weight parameter mapping model outputs the weight parameters of the control quantity. The pre-trained weight parameter mapping model is configured such that when the actual longitudinal distance increases, the weight parameters of the output control quantity increase; when the longitudinal acceleration of the obstacle ahead decreases, the weight parameters of the output control quantity increase.

[0065] Specifically, the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead are input into a pre-trained weight parameter mapping model, which outputs the weight parameters of the LQR control quantity. The mapping rule is as follows:

[0066] When the actual longitudinal distance increases: the weighting parameter of the control quantity increases, suppressing the acceleration fluctuation of the target vehicle and improving fuel economy;

[0067] When the longitudinal acceleration of the obstacle in front decreases (i.e., the obstacle in front decelerates): increase the weight parameter of the control quantity to avoid sudden deceleration of the target vehicle and ensure the riding comfort of the target vehicle passengers.

[0068] S103. Solve for the control quantity based on the weight parameters and state quantity of the control quantity to obtain the desired longitudinal acceleration of the target vehicle.

[0069] Since the LQR algorithm can achieve optimal control through state feedback, a state equation solution model containing dynamic weight parameters needs to be constructed. Specifically, the state variable is a two-dimensional vector consisting of velocity and distance differences, and the control variable is the desired longitudinal acceleration to be solved. The specific calculation process of the LQR algorithm is as follows:

[0070] In this application, the state variables are:

[0071]

[0072] The state transition equation is:

[0073]

[0074] in, For the desired longitudinal distance, This is the actual longitudinal distance. The speed of the obstacle ahead. Let the longitudinal speed of the target vehicle be denoted as . Here is the state transition matrix. To control the input matrix, To control the quantity.

[0075] Constructing the cost function of the LQR algorithm

[0076]

[0077] and The cost weight matrix for the state variables and control variables is defined as follows:

[0078]

[0079]

[0080] in,

[0081] The weighting coefficient for the distance difference;

[0082] Weighting coefficients for speed differences;

[0083] The weighting coefficients for the control quantity.

[0084] By minimizing the cost function, the control quantity u can be obtained as follows:

[0085]

[0086] Feedback coefficient matrix This can be obtained by solving the following Riccati equation:

[0087]

[0088]

[0089] in, Let be the symmetric positive definite solution matrix of the Riccati equation.

[0090] Solving for the feedback coefficient matrix can be done by calling a pre-stored Riccati equation solving module to calculate the feedback coefficient matrix in real time; alternatively, a combination of offline calculation and online interpolation can be used to pre-build a database of feedback coefficient matrices corresponding to different combinations of weight parameters.

[0091] S104. Adjust the longitudinal acceleration of the target vehicle to the desired longitudinal acceleration.

[0092] This step completes the physical conversion of control commands into actuators. Specifically, the required torque of the target vehicle's engine can be determined based on the desired longitudinal acceleration, and the output torque of the target vehicle's engine can be adjusted to that required torque. Figure 2 This is a schematic diagram of vehicle longitudinal acceleration control provided in an embodiment of this application, such as... Figure 2 As shown, the target vehicle's front-mounted IVIR system (such as millimeter-wave radar, camera, lidar) acquires real-time motion information of obstacles ahead. Combined with the target vehicle's own motion state information, the method described in this embodiment outputs the target vehicle's desired longitudinal acceleration to the virtual driver model. The virtual driver model adjusts the target vehicle's longitudinal acceleration to the desired longitudinal acceleration by performing the following operations: converting the desired longitudinal acceleration into the target vehicle's required torque using the vehicle's inverse longitudinal dynamics model, and adjusting the target vehicle's engine torque to the required torque; determining the desired transmission gear based on the desired longitudinal acceleration, and adjusting the target vehicle's transmission gear to the desired gear; the brake force distribution module allocates the drive and braking force ratios according to the desired longitudinal acceleration, and sends them to the braking system, XBR (electronic brake booster), and in-cylinder control unit, respectively. The electronic brake booster adjusts the brake fluid pressure according to the instructions and controls the caliper clamping force. For hybrid or gasoline vehicles, it assists in deceleration through in-cylinder braking (such as fuel cut-off, throttle closure) to reduce the mechanical braking load.

[0093] Specifically, the longitudinal acceleration of the target vehicle is adjusted to the desired longitudinal acceleration using a vehicle inverse longitudinal dynamics model, including:

[0094] Based on the desired longitudinal acceleration, the required torque of the target vehicle is calculated using the following formula:

[0095]

[0096] in, For the required torque; The gear ratio of the target vehicle's main reducer; The gear ratio of the target vehicle's transmission; The transmission efficiency of the target vehicle's powertrain; The target vehicle's wheel rolling radius; The total mass of the target vehicle; It is the acceleration due to gravity; The slope of the road in front of the target vehicle; The rolling resistance of the target vehicle's wheels; The drag coefficient of the target vehicle; The frontal area of ​​the target vehicle; This refers to the longitudinal speed of the vehicle. denoted by , where is the rotational mass conversion factor for the target vehicle; 'a' represents the desired longitudinal acceleration.

[0097] The technical effects of this embodiment are as follows:

[0098] This scheme dynamically determines the LQR control weight parameter using both actual longitudinal distance and the longitudinal acceleration of the obstacle ahead. When the actual longitudinal distance increases, the control weight parameter is increased to suppress acceleration fluctuations, thereby reducing fuel consumption caused by frequent acceleration or braking of the target vehicle. Simultaneously, when the longitudinal acceleration of the obstacle ahead decreases, the control weight parameter is increased, allowing the target vehicle to prioritize limiting power output to improve economy under stable following conditions. Conversely, when the actual longitudinal distance decreases or the longitudinal acceleration of the obstacle ahead suddenly increases, the control weight parameter automatically decreases, allowing for greater acceleration adjustment margin to quickly respond to safety requirements. Therefore, in dynamic traffic scenarios, this coordinated adjustment mechanism of the weight parameter avoids the trade-off between fuel economy and comfort caused by fixed parameters in traditional methods, and achieves an adaptive balance between fuel consumption optimization and driving smoothness based on real-time operating conditions and the principle of safety priority.

[0099] Example 2

[0100] Figure 3 Flowchart of the vehicle adaptive cruise control method provided in the embodiments of this application Figure 2 .like Figure 3 As shown, the method includes:

[0101] S301. Obtain the actual longitudinal distance between the obstacle in front of the target vehicle and the target vehicle, the longitudinal velocity and longitudinal acceleration of the obstacle in front, and the longitudinal speed of the target vehicle; calculate the speed difference between the longitudinal velocity of the obstacle in front and the longitudinal speed of the target vehicle; and, based on the expected longitudinal distance between the target vehicle and the obstacle in front, calculate the distance difference between the expected longitudinal distance and the actual longitudinal distance.

[0102] S302. Based on the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead, query a predefined mapping table to determine the weight parameters of the control quantity corresponding to the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead. The predefined mapping table indicates the correspondence between different actual longitudinal distances and the longitudinal acceleration of the obstacle ahead and the weight parameters of the control quantity. In the predefined mapping table, when the actual longitudinal distance increases, the weight parameter of the control quantity increases; when the longitudinal acceleration of the obstacle ahead decreases, the weight parameter of the control quantity increases.

[0103] Similar to Example 1, the state variables in the linear quadratic regulator control algorithm are the speed difference and distance difference, and the control variable is the desired longitudinal acceleration of the target vehicle to be solved. Since the weights of fuel economy, safety, and comfort requirements dynamically change in different following scenarios, this step uses a predefined mapping relationship to adaptively adjust the control variable weight parameters, thereby achieving a balance between aggressive tracking and smooth energy saving in the LQR algorithm.

[0104] In this step, a two-dimensional mapping table can be constructed, where the horizontal axis can be the actual longitudinal distance, the vertical axis can be the longitudinal acceleration of the obstacle in front, and the output value is the control variable weight parameter. The mapping rule is: the control variable weight parameter increases monotonically with the increase of the actual longitudinal distance and increases with the decrease (negative increase) of the longitudinal acceleration of the obstacle in front.

[0105] In practical implementation, for example:

[0106] 1. Design a discretized lookup table to divide the actual longitudinal distance and the longitudinal acceleration of the obstacle in front into intervals. Calculate the weight parameter value of the continuous domain control quantity through bilinear interpolation. For example, when the actual longitudinal distance ∈ [50m, 80m) and the longitudinal acceleration of the obstacle in front ∈ [-3m / s2, -1m / s2), the weight parameter increases linearly from 1.2 to 1.8.

[0107] Second, a fuzzy logic controller is used to convert the actual longitudinal distance and the longitudinal acceleration of the obstacle in front into linguistic variables such as "near distance / medium distance / long distance" and "emergency braking / mild braking / constant speed", and output weight parameters through a rule base.

[0108] In terms of technical effectiveness, this mapping mechanism increases the control weight parameters when following a vehicle at a long distance to suppress unnecessary acceleration fluctuations, thereby saving fuel, while dynamically reducing the control weight parameters when the vehicle in front brakes suddenly to enhance response speed.

[0109] S303. Solve for the control quantity based on the weight parameters and state quantity of the control quantity to obtain the desired longitudinal acceleration of the target vehicle.

[0110] S304. Adjust the longitudinal acceleration of the target vehicle to the desired longitudinal acceleration.

[0111] In this embodiment, S301, S303, and S304 can be referred to in Embodiment 1, and will not be described again here.

[0112] Figure 4 Flowchart of the vehicle adaptive cruise control method provided in the embodiments of this application Figure 3 ,like Figure 4 As shown, the method includes:

[0113] S401. Obtain the actual longitudinal distance between the obstacle in front of the target vehicle and the target vehicle, the longitudinal velocity and longitudinal acceleration of the obstacle in front, and the longitudinal speed of the target vehicle; calculate the speed difference between the longitudinal velocity of the obstacle in front and the longitudinal speed of the target vehicle; and, based on the expected longitudinal distance between the target vehicle and the obstacle in front, calculate the distance difference between the expected longitudinal distance and the actual longitudinal distance.

[0114] S402. Based on the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead, query a predefined mapping table to determine the weight parameters of the control quantity corresponding to the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead. The predefined mapping table indicates the correspondence between different actual longitudinal distances and the longitudinal acceleration of the obstacle ahead and the weight parameters of the control quantity. In the predefined mapping table, when the actual longitudinal distance increases, the weight parameter of the control quantity increases; when the longitudinal acceleration of the obstacle ahead decreases, the weight parameter of the control quantity increases.

[0115] S403. Based on the actual longitudinal distance, speed difference, and longitudinal acceleration of the obstacle ahead, determine the weight parameters for speed difference and distance difference in the linear quadratic regulator control algorithm. The larger the actual longitudinal distance, the smaller the weight parameter for distance difference; the smaller the speed difference, the smaller the weight parameter for speed difference; the larger the longitudinal acceleration of the obstacle ahead, the larger the weight parameter for distance difference.

[0116] Because different driving scenarios have dynamically different requirements for distance tracking accuracy and speed convergence speed, this step introduces a condition judgment mechanism based on actual longitudinal distance, speed difference, and acceleration of obstacles ahead, to dynamically adjust the state variable weight parameters (i.e., the Q matrix in Example 1). , This allows the LQR controller to achieve an adaptive balance between safety and comfort. The specific impact of each weighting parameter on vehicle control is as follows:

[0117] When the speed difference weight parameter increases, the controller's sensitivity to speed deviations between the target vehicle and obstacles ahead is enhanced, allowing the vehicle to more proactively eliminate speed differences through acceleration or braking. This is suitable for scenarios requiring rapid speed convergence (such as cutting in from another vehicle). Conversely, when the speed difference weight parameter decreases, the controller's response to speed deviations becomes smoother, making it suitable for low-speed congestion scenarios. This avoids the jerking sensation caused by frequent acceleration and deceleration, improving ride comfort.

[0118] Increasing the distance difference weight parameter enhances the controller's attention to the deviation between the actual and expected distances, prompting the vehicle to adjust its speed more aggressively to reduce distance errors. This is suitable for short-distance following or emergency deceleration scenarios where safety is prioritized. Conversely, when the actual longitudinal distance is large, decreasing the distance difference weight parameter reduces the sensitivity to distance deviations, suppresses unnecessary aggressive control (such as excessive braking at long distances), and thus optimizes fuel economy.

[0119] When a significant increase in longitudinal acceleration of an obstacle ahead is detected (such as a sudden deceleration), the distance difference weight parameter is increased, causing the controller to prioritize responding to distance changes rather than speed tracking, thereby quickly establishing a safe redundancy distance and avoiding collision risks. Conversely, if the longitudinal acceleration of the obstacle ahead is gradual (such as constant speed or slow acceleration), reducing the weight parameter can reduce excessive correction to instantaneous distance fluctuations and maintain a smooth following experience.

[0120] Optionally, based on the actual longitudinal distance, velocity difference, and longitudinal acceleration of the obstacle ahead, the weight parameters for the velocity difference and distance difference in the linear quadratic regulator control algorithm are determined, including:

[0121] Determine whether the longitudinal acceleration of the obstacle ahead is greater than a preset acceleration threshold;

[0122] If so, the weighting parameter of the distance difference is determined based on the longitudinal acceleration of the obstacle in front. The greater the longitudinal acceleration of the obstacle in front, the greater the weighting parameter of the distance difference.

[0123] If not, the weighting parameter of the distance difference is determined based on the actual longitudinal distance. The larger the actual longitudinal distance, the smaller the weighting parameter of the distance difference.

[0124] Specifically, the step of determining whether the longitudinal acceleration of the obstacle ahead exceeds a preset acceleration threshold aims to differentiate between emergency and normal operating conditions, thereby switching between different weight parameter calculation logics. Since emergency braking scenarios prioritize safety, while smooth following emphasizes economy, threshold determination is used to switch the primary and secondary control objectives. In practice, for example:

[0125] I. Threshold Dynamic Calibration: The preset acceleration threshold is adaptively adjusted based on the road surface adhesion coefficient (obtained by the ESP sensor), for example, -2.5 for dry asphalt pavement. For wet and slippery surfaces, set the value to -1.5. To avoid accidental triggering;

[0126] II. Hysteresis Comparator Design: Setting the hysteresis interval [-2.2] -1.8 To prevent weight parameter oscillations caused by acceleration fluctuations, i.e., when the longitudinal acceleration of the obstacle in front is below -2.2... If the system enters emergency mode, it needs to be restored to -1.8. Only after completing the above steps will you be able to exit.

[0127] S404. Solve for the control quantity based on the weight parameters of the control quantity, the weight parameters of the state quantity, and the state quantity to obtain the desired longitudinal acceleration of the target vehicle.

[0128] S405. Adjust the longitudinal acceleration of the target vehicle to the desired longitudinal acceleration.

[0129] Figure 5 This is a schematic diagram of the vehicle adaptive cruise control device provided in this application, as shown below. Figure 5 As shown, the device includes:

[0130] The status acquisition module 501 is used to: acquire the actual longitudinal distance between the obstacle in front of the target vehicle and the target vehicle, the longitudinal velocity and longitudinal acceleration of the obstacle in front, the longitudinal speed of the target vehicle, calculate the speed difference between the longitudinal velocity of the obstacle in front and the longitudinal speed of the target vehicle, and calculate the distance difference between the expected longitudinal distance and the actual longitudinal distance based on the expected longitudinal distance between the target vehicle and the obstacle in front.

[0131] The weight parameter calculation module 502 is used to: determine the weight parameters of the control quantity in the linear quadratic regulator control algorithm based on the actual longitudinal distance and the longitudinal acceleration of the obstacle in front. The larger the actual longitudinal distance, the larger the weight parameter of the control quantity; the smaller the longitudinal acceleration of the obstacle in front, the larger the weight parameter of the control quantity. The state quantities in the linear quadratic regulator control algorithm are the speed difference and the distance difference, and the control quantity is the expected longitudinal acceleration of the target vehicle to be solved.

[0132] The acceleration calculation module 503 is used to: solve the control quantity based on the weight parameters of the control quantity and the state quantity to obtain the desired longitudinal acceleration of the target vehicle;

[0133] The control module 504 is used to adjust the longitudinal acceleration of the target vehicle to the desired longitudinal acceleration. The vehicle adaptive cruise control device provided in this embodiment can execute the method provided in the above-described method embodiment, and its implementation principle and technical effect are similar, so it will not be described in detail here.

[0134] Figure 6 A schematic diagram of the structure of the electronic device provided in this application. Figure 6 As shown, the electronic device 60 provided in this embodiment includes at least one processor 601 and a memory 602. Optionally, the device 60 further includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.

[0135] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0136] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0137] 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.

[0138] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0139] 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.

[0140] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0141] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0142] 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.

[0143] 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 the device.

[0144] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0145] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0146] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0147] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0148] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0149] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A vehicle adaptive cruise control method, characterized in that, The method includes: The system obtains the actual longitudinal distance between the obstacle in front of the target vehicle and the target vehicle, the longitudinal velocity and longitudinal acceleration of the obstacle in front, and the longitudinal speed of the target vehicle; calculates the speed difference between the longitudinal velocity of the obstacle in front and the longitudinal speed of the target vehicle; and calculates the distance difference between the expected longitudinal distance and the actual longitudinal distance based on the expected longitudinal distance between the target vehicle and the obstacle in front. Based on the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead, the weight parameters of the control quantity in the linear quadratic regulator control algorithm are determined. The larger the actual longitudinal distance, the larger the weight parameter of the control quantity; the smaller the longitudinal acceleration of the obstacle ahead, the larger the weight parameter of the control quantity. The state variables in the linear quadratic regulator control algorithm are the speed difference and the distance difference, and the control quantity is the desired longitudinal acceleration of the target vehicle to be solved. The control quantity is solved based on the weight parameters of the control quantity and the state quantity to obtain the desired longitudinal acceleration of the target vehicle; The longitudinal acceleration of the target vehicle is adjusted to the desired longitudinal acceleration.

2. The method according to claim 1, characterized in that, The step of determining the weight parameters of the control quantity in the linear quadratic regulator control algorithm based on the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead includes: Based on the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead, a predefined mapping table is consulted to determine the weight parameters of the control quantity corresponding to the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead. The predefined mapping table indicates the correspondence between different actual longitudinal distances and the longitudinal acceleration of the obstacle ahead and the weight parameters of the control quantity. In the predefined mapping table, when the actual longitudinal distance increases, the weight parameter of the control quantity increases; when the longitudinal acceleration of the obstacle ahead decreases, the weight parameter of the control quantity increases.

3. The method according to claim 1, characterized in that, The step of determining the weight parameters of the control quantity in the linear quadratic regulator control algorithm based on the actual longitudinal distance and the longitudinal acceleration of the obstacle ahead includes: The actual longitudinal distance and the longitudinal acceleration of the obstacle ahead are input into a pre-trained weight parameter mapping model, which outputs the weight parameters of the control quantity. The pre-trained weight parameter mapping model is configured such that when the actual longitudinal distance increases, the weight parameters of the output control quantity increase; when the longitudinal acceleration of the obstacle ahead decreases, the weight parameters of the output control quantity increase.

4. The method according to claim 1, characterized in that, The method further includes: Based on the actual longitudinal distance, the speed difference, and the longitudinal acceleration of the obstacle ahead, the weight parameters of the speed difference and the distance difference in the linear quadratic regulator control algorithm are determined. The larger the actual longitudinal distance, the smaller the weight parameter of the distance difference; the smaller the speed difference, the smaller the weight parameter of the speed difference; and the larger the longitudinal acceleration of the obstacle ahead, the larger the weight parameter of the distance difference.

5. The method according to claim 4, characterized in that, The step of determining the weight parameters of the velocity difference and the distance difference in the linear quadratic regulator control algorithm based on the actual longitudinal distance, the velocity difference, and the longitudinal acceleration of the obstacle ahead includes: Determine whether the longitudinal acceleration of the obstacle in front is greater than a preset acceleration threshold; If so, the weighting parameter of the distance difference is determined based on the longitudinal acceleration of the obstacle in front. The greater the longitudinal acceleration of the obstacle in front, the greater the weighting parameter of the distance difference. If not, then the weighting parameter of the distance difference is determined based on the actual longitudinal distance. The larger the actual longitudinal distance, the smaller the weighting parameter of the distance difference.

6. The method according to claim 4, characterized in that, The step of solving the control quantity based on the weight parameters of the control quantity and the state quantity to obtain the desired longitudinal acceleration of the target vehicle includes: The feedback coefficients of the linear quadratic regulator control algorithm are determined based on the weight parameters of the control quantity, the speed difference, and the distance difference. The control quantity is solved by multiplying the feedback coefficient and the state quantity to obtain the desired longitudinal acceleration of the target vehicle.

7. The method according to any one of claims 1-6, characterized in that, The step of adjusting the longitudinal acceleration of the target vehicle to the desired longitudinal acceleration includes: Based on the desired longitudinal acceleration, the required torque of the target vehicle is calculated using the following formula: in, The required torque; The gear ratio of the main reducer of the target vehicle; The gear ratio of the transmission of the target vehicle; The transmission efficiency of the power system of the target vehicle; Let be the wheel rolling radius of the target vehicle; The total mass of the target vehicle; It is the acceleration due to gravity; The slope of the road in front of the target vehicle; The rolling resistance of the wheels of the target vehicle; Let be the drag coefficient of the target vehicle; The frontal area of ​​the target vehicle; The longitudinal vehicle speed; is the rotational mass conversion factor for the target vehicle; a is the desired longitudinal acceleration; The output torque of the engine of the target vehicle is adjusted to the required torque.

8. A vehicle adaptive cruise control device, characterized in that, The device includes: The status acquisition module is used to: acquire the actual longitudinal distance between the obstacle in front of the target vehicle and the target vehicle, the longitudinal velocity and longitudinal acceleration of the obstacle in front, the longitudinal speed of the target vehicle, calculate the speed difference between the longitudinal velocity of the obstacle in front and the longitudinal speed of the target vehicle, and calculate the distance difference between the expected longitudinal distance and the actual longitudinal distance based on the expected longitudinal distance between the target vehicle and the obstacle in front. The weight parameter calculation module is used to: determine the weight parameters of the control quantity in the linear quadratic regulator control algorithm based on the actual longitudinal distance and the longitudinal acceleration of the obstacle in front. The larger the actual longitudinal distance, the larger the weight parameter of the control quantity; the smaller the longitudinal acceleration of the obstacle in front, the larger the weight parameter of the control quantity. The state quantity in the linear quadratic regulator control algorithm is the speed difference and the distance difference, and the control quantity is the desired longitudinal acceleration of the target vehicle to be solved. An acceleration calculation module is used to: solve for the control quantity based on the weight parameters of the control quantity and the state quantity to obtain the desired longitudinal acceleration of the target vehicle; The control module is used to adjust the longitudinal acceleration of the target vehicle to the desired longitudinal acceleration.

9. 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 vehicle adaptive cruise control method as described in any one of claims 1 to 7.

10. 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 vehicle adaptive cruise control method as described in any one of claims 1 to 7.

Images