Predictive vehicle speed control methods, devices, equipment and storage media

Abstract

This application provides a predictive vehicle speed control method, device, equipment, and storage medium, relating to the field of vehicle control technology. The method includes: dividing the road ahead into several segments; determining the speed and acceleration ranges of a target vehicle in each segment based on road information; using the distance range between the target vehicle and the vehicle ahead, the speed ranges of each segment, and the acceleration ranges as target constraints for the target vehicle in each segment; and predicting the desired speed value for each segment based on the target constraints, the current motion state information of the target vehicle, and the motion state information of the vehicle ahead, and controlling the target vehicle to travel at the corresponding desired speed value in each segment. The method of this application considers the real-time motion states of the target vehicle and the vehicle ahead, enabling the predicted speed value to match the current real-time traffic conditions.

Description

Technical Field

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

[0002] Predictive speed control is an advanced driver assistance method that uses the terrain ahead of the vehicle to predict the vehicle's speed at different times, thereby improving fuel efficiency, driving comfort, and driving safety.

[0003] However, existing predictive speed control technologies only consider the road attributes ahead, resulting in predicted speeds that cannot adapt to real-world traffic scenarios where multiple vehicles are traveling together. Summary of the Invention

[0004] This application provides a predictive vehicle speed control method, device, equipment, and storage medium to solve the problem that existing predictive vehicle speed control technologies only consider the road attributes of the road ahead, resulting in the predicted vehicle speed being unable to adapt to real-world traffic scenarios where multiple vehicles are traveling together.

[0005] In a first aspect, this application provides a predictive vehicle speed control method, comprising:

[0006] Based on the road information of the road ahead of the target vehicle, the road ahead is divided into several segments, and the road information of each segment is obtained.

[0007] Obtain the motion state information of the target vehicle at the current moment and the motion state information of the vehicle in front of the target vehicle;

[0008] Based on the road information of each road segment, determine the speed range and acceleration range of the target vehicle in each road segment;

[0009] Using the distance range between the target vehicle and the vehicle in front, the speed range of each road segment, and the acceleration range as target constraints for the target vehicle in each road segment, the expected speed of the target vehicle in each road segment is predicted based on the motion state information of the target vehicle and the motion state information of the vehicle in front.

[0010] The target vehicle is controlled to travel at the desired speed value corresponding to the current road segment on each of the road segments.

[0011] In one possible design, predicting the expected speed of the target vehicle in each road segment based on the motion state information of the target vehicle and the motion state information of the vehicle ahead includes:

[0012] The model predictive control algorithm predicts the desired speed of the target vehicle in each road segment based on the target constraint adjustment, the motion state information of the target vehicle, and the motion state information of the vehicle ahead.

[0013] In one possible design, acquiring the motion state information of the target vehicle at the current moment and the motion state information of the vehicle in front of the target vehicle includes:

[0014] Based on the filter's prediction information of the motion state of the target vehicle and the vehicle in front at the previous moment, and the detection information of the motion state of the target vehicle and the vehicle in front detected by the detection device at the current moment, the filter calculates the motion state information of the target vehicle and the vehicle in front of the target vehicle at the current moment.

[0015] In one possible design, the step of using the distance interval between the target vehicle and the vehicle ahead, the speed interval of each road segment, and the acceleration interval as target constraints for the target vehicle in each road segment, and predicting the expected speed value of the target vehicle in each road segment based on the motion state information of the target vehicle and the motion state information of the vehicle ahead, includes:

[0016] Based on the target cost function, the target constraints for each road segment, the motion state information of the target vehicle, and the motion state information of the vehicle ahead, a model predictive control algorithm is used to predict the expected speed of the target vehicle in each road segment. This is to ensure that the target cost function is minimized when the target vehicle travels at the corresponding expected speed in each road segment. The target cost function includes the target vehicle's fuel consumption penalty factor, acceleration rate of change penalty factor, and relaxation variable penalty factor. The relaxation variables are used to adjust the range of the distance interval, speed interval, and acceleration interval.

[0017] In one possible design, dividing the road ahead into several segments based on road information of the target vehicle, and obtaining road information for each of the road segments, includes:

[0018] Based on the road information of the road ahead, the road ahead is divided into several road segments;

[0019] Obtain the slope information of each sub-road segment, and determine the slope type of each sub-road segment based on the slope of each sub-road segment and the preset slope range;

[0020] In the sub-segments, consecutive sub-segments with the same slope type are merged into the road segment, and the remaining sub-segments are determined as the road segment;

[0021] Obtain the average slope information for each road segment, and use the average slope information as the road information for each road segment.

[0022] In one possible design, controlling the target vehicle to travel at the desired speed value corresponding to the current road segment on each road segment includes:

[0023] Obtain the desired location value of the target vehicle, and detect the actual speed value of the target vehicle in the current road segment and the actual location value of the target vehicle;

[0024] Calculate the speed difference between the actual vehicle speed value and the expected vehicle speed value, and the position difference between the actual position value and the expected position value;

[0025] The target acceleration is calculated using a proportional-integral algorithm based on the product of the vehicle speed difference and the proportional coefficient, and the product of the position difference and the integral coefficient.

[0026] Control the target vehicle to travel at the target acceleration.

[0027] In one possible design, controlling the target vehicle to travel at the desired speed value corresponding to the current road segment on each road segment further includes:

[0028] According to the formula for calculating expected torque, the expected wheel torque corresponding to the current road segment is calculated. The formula for calculating expected torque is as follows:

[0029]

[0030] Where, r eff R is the effective radius of the target vehicle's wheels, and R is the gear ratio of the target vehicle's transmission. x J is the rolling resistance of the target vehicle wheels. e w is the effective rotational inertia of the engine of the target vehicle. e c is the engine speed of the target vehicle. a The drag coefficient of the target vehicle;

[0031] The target vehicle wheel torque is adjusted to the desired torque.

[0032] In one possible design, after determining the speed range and acceleration range of the target vehicle in each road segment, and before using the distance range between the target vehicle and the vehicle ahead, the speed range, and the acceleration range of each road segment as target constraints for the target vehicle in each road segment, the method further includes:

[0033] The minimum parking distance, minimum following distance, and minimum following time information between the target vehicle and the vehicle in front are obtained from the driver of the target vehicle. Based on the minimum parking distance, minimum following distance, and minimum following time information, the distance range is determined.

[0034] In one possible design, determining the distance range based on the minimum parking distance information, the minimum following distance information, and the minimum following time information includes:

[0035] The distance interval is calculated according to the distance interval calculation formula, which is:

[0036]

[0037] in, Let p(k) be the minimum parking distance at time k, and p(k) be the distance between the target vehicle and the vehicle in front at time k. Max (k) represents the maximum permissible distance between the target vehicle and the vehicle in front at time k, d Min h is the minimum following distance. Min Let v(k) be the minimum following time, and v(k) be the speed of the target vehicle at time k.

[0038] In one possible design, based on the road information of each road segment, the speed range and acceleration range of the target vehicle in each road segment are determined, including:

[0039] Based on the average slope information of each road segment, the speed range and acceleration range of the target vehicle in each road segment are determined.

[0040] Secondly, this application provides a predictive vehicle speed control device, the device comprising:

[0041] The segmentation module is used to: divide the road ahead of the target vehicle into several segments based on the road information of the road ahead, and obtain the road information of each segment;

[0042] The acquisition module is used to: acquire the motion state information of the target vehicle at the current moment and the motion state information of the vehicle in front of the target vehicle;

[0043] The determination module is used to: determine the speed range and acceleration range of the target vehicle in each of the road segments based on the road information of each road segment;

[0044] The prediction module is used to: use the distance interval between the target vehicle and the vehicle in front, the speed interval of each road segment, and the acceleration interval as target constraints for the target vehicle in each road segment, and the model prediction control algorithm predicts the expected vehicle speed value for each road segment based on the target constraints for each road segment, the motion state information of the target vehicle, and the motion state information of the vehicle in front.

[0045] The control module is used to control the target vehicle to travel at the desired speed value corresponding to the current road segment on each of the road segments.

[0046] Thirdly, this application provides a predictive vehicle speed control device, the device comprising: a processor, and a memory communicatively connected to the processor;

[0047] The memory stores computer-executed instructions;

[0048] The processor executes computer execution instructions stored in the memory to implement the predictive vehicle speed control method as described in the first aspect.

[0049] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the predictive vehicle speed control method as described in the first aspect.

[0050] This application provides a predictive vehicle speed control method, device, equipment, and storage medium, which achieves the following technical effects:

[0051] This application determines the speed and acceleration ranges of the target vehicle on each road segment based on the road information, ensuring that the expected speed value for each road segment matches the road attributes. In this application, based on the real-time motion state information of the target vehicle and vehicles ahead, the expected speed value for each road segment that simultaneously satisfies the speed range, acceleration range, and distance range between the target vehicle and vehicles ahead is calculated. The predicted speed value not only matches the road attributes but also, by considering the real-time motion state of the target vehicle and vehicles ahead, matches the current real-time traffic conditions, ensuring that the target vehicle meets the distance range and thus guaranteeing driving safety. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 A flowchart of a predictive vehicle speed control method provided in this application embodiment;

[0054] Figure 2 This is a schematic diagram of the model predictive control algorithm for predicting the desired vehicle speed provided in the embodiments of this application;

[0055] Figure 3 A flowchart illustrating a method for determining the speed and acceleration range of a target vehicle in each road segment, as provided in this application embodiment;

[0056] Figure 4 This is a schematic diagram of the process for obtaining road information provided in an embodiment of this application;

[0057] Figure 5 This is a schematic diagram of a predictive adaptive cruise control system provided in an embodiment of this application;

[0058] Figure 6 This is a schematic diagram of multi-source sensor fusion sensing provided in an embodiment of this application;

[0059] Figure 7 This is a schematic diagram of proportional-integral control provided in an embodiment of this application;

[0060] Figure 8 A schematic diagram of a predictive vehicle speed control device provided in an embodiment of this application;

[0061] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0062] 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 numerals in different drawings represent 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, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0063] First, the relevant concepts or terms involved in this application will be explained:

[0064] Model Predictive Control (MPC) is an advanced control strategy widely used in industrial process control, autonomous driving, energy management, and other fields. The core idea of ​​MPC is to use a mathematical model of the system to predict its future behavior and then use an optimization algorithm to calculate the optimal control input in each control cycle to achieve the predetermined control objective. The following are the basic steps of the MPC algorithm:

[0065] 1. System Modeling:

[0066] First, a mathematical model of the controlled system needs to be established. This model is usually a state-space model or a transfer function model of the system, which describes the dynamic behavior of the system.

[0067] 2. Prediction:

[0068] Using the system model and the current system state, predict the system output over a future period (prediction time domain). These predicted outputs are calculated based on assumed future control input sequences.

[0069] 3. Optimization:

[0070] Define an optimization objective function, typically a weighted sum that includes an error term and a control cost. The error term represents the deviation between the system output and the reference trajectory, and the control cost represents the magnitude or rate of change of the control input.

[0071] In the prediction time domain, solve this optimization problem to find the control input sequence that minimizes the objective function.

[0072] 4. Implement control:

[0073] Only the first control input from the optimized control input sequence is applied to the actual system.

[0074] In the next control cycle, repeat the above steps to make new predictions and optimizations using the new system state.

[0075] 5. Feedback:

[0076] Since MPC is a model-based predictive control, there may be errors between the actual system and the model. Therefore, the system state is updated and predictions and optimizations are performed again in each control cycle to achieve closed-loop control.

[0077] To address the problem that existing predictive speed control technologies only consider the road attributes ahead, resulting in predicted speeds that cannot adapt to real-world traffic scenarios with multiple vehicles traveling together, this application's technical concept is as follows: Based on the road information ahead of the target vehicle, the road ahead is divided into several segments, and the road information for each segment is acquired separately. Simultaneously, the motion state information of the vehicles ahead of the target vehicle and the motion state information of the target vehicle at the current moment are also acquired. Based on the road information of each segment, the speed and acceleration ranges of the target vehicle within each segment can be determined. The model predictive control algorithm, based on these ranges and the distance range between the target vehicle and the vehicles ahead, and using the motion state information of the vehicles ahead and the target vehicle at the current moment, calculates the expected speed value of the target vehicle on each segment. When the target vehicle travels at the corresponding expected speed value on each segment, it can satisfy all the ranges. When the target vehicle reaches a certain segment, it is controlled to travel at the expected speed value corresponding to that segment.

[0078] 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.

[0079] Example 1

[0080] This application provides a predictive speed control method that can be applied to the vehicle's control unit. Figure 1 This is a flowchart illustrating a predictive vehicle speed control method provided in an embodiment of this application. Figure 1 As shown, the method includes:

[0081] S101. Based on the road information of the road ahead of the target vehicle, divide the road ahead into several segments and obtain the road information of each segment.

[0082] Typically, the target vehicle can be itself. Based on road information such as terrain and curvature data of a certain length of road ahead (e.g., two kilometers), this road can be divided into several segments. These segments can consist of multiple road segments with similar terrain or curvature. The target vehicle can obtain road information by accessing an electronic map of the road ahead.

[0083] S102. Obtain the motion status information of the target vehicle at the current moment and the motion status information of the vehicle in front of the target vehicle;

[0084] Specifically, the motion status information of the target vehicle and the vehicles ahead can be sensed at the current moment through the fusion of multiple detection devices. For example, millimeter-wave radar, cameras, lidar, inertial navigation units, and other vehicle-side, roadside, and cloud-based sensors can be used to acquire this motion status information. Motion status information can include the vehicle's current position, speed, acceleration, etc. By acquiring the current motion status information and the motion status information of the vehicles ahead through multiple detection devices, changes in traffic flow can be perceived in real time.

[0085] S103. Based on the road information of each road segment, determine the speed range and acceleration range of the target vehicle in each road segment;

[0086] Specifically, based on the terrain, curvature, speed limit information, etc. of each road segment, the speed range and acceleration range of each road segment can be determined as constraints for the target vehicle. That is, when the target vehicle is driving on a certain road segment, the speed of the target vehicle must be within the speed range and the acceleration must be within the acceleration range, so that the predicted vehicle speed matches the road attributes of the road ahead.

[0087] S104. Using the distance interval between the target vehicle and the vehicle in front, the speed interval of each segment of the continuous road, and the acceleration interval as target constraints for the target vehicle in each segment of the continuous road, and based on the motion state information of the target vehicle and the motion state information of the vehicle in front, predict the expected speed value of the target vehicle in each segment of the continuous road.

[0088] The distance range between the target vehicle and the vehicle ahead is used as a distance constraint to ensure a reasonable distance between them, thus guaranteeing driving safety. The aforementioned distance range, speed range, and acceleration range for each road segment are used as the target constraints for the target vehicle on each road segment. Model predictive control algorithms can be used to predict the expected speed for each road segment based on the target constraints, the current motion state information of the target vehicle, and the motion state information of the vehicle ahead. Specifically, first, a mathematical model for predicting vehicle speed needs to be established. Using this model, along with the current motion state information of the target vehicle and the vehicle ahead, the expected speed over a future period (prediction time domain) is predicted. Figure 2 This is a schematic diagram illustrating the model predictive control algorithm for predicting the desired vehicle speed, as provided in the embodiments of this application. Figure 2As shown, in practical applications, the aforementioned target constraints, the motion state information of the target vehicle at the current moment, the motion state information of the vehicle in front, and the target cost function are input into the model prediction solver. The model prediction solver then integrates the motion states of the target vehicle and the vehicle in front to output the expected vehicle speed value corresponding to each road segment in the future. Compared with the prior art, which only considers the road attribute information to predict vehicle speed, this embodiment considers the motion states of the target vehicle and the vehicle in front, so that the predicted vehicle speed value can match the current real-time traffic conditions.

[0089] It should be noted that the model predictive control algorithm outputs the expected vehicle speed values ​​at different future times. These different future times correspond to different road segments. The target vehicle arrives at the road segment corresponding to that future time at a certain future time, and at each future time, the target vehicle is controlled to adjust its speed to the expected vehicle speed value corresponding to that future time.

[0090] S105. Control the target vehicle to travel at the desired speed value corresponding to the current road segment on each road segment.

[0091] The method provided in this embodiment achieves the following technical effects:

[0092] This embodiment determines the speed and acceleration ranges of the target vehicle on each road segment based on the road information, ensuring that the expected vehicle speed for each segment matches the road attributes. In this embodiment, the model predictive control algorithm calculates the expected vehicle speed for each road segment that simultaneously satisfies the speed range, acceleration range, and distance range between the target vehicle and the vehicle ahead, based on the real-time motion state information of the target vehicle and the vehicle ahead. The predicted speed not only matches the road attributes but also, by considering the real-time motion state of the target vehicle and the vehicle ahead, matches the current real-time traffic conditions, ensuring the target vehicle meets the distance range and thus guaranteeing driving safety. Furthermore, since the model predictive control algorithm predicts speed based on a pre-set target cost function, the predicted speed meets the expected optimization objective.

[0093] The following specific embodiment will be used to describe in detail the predictive speed control method of this application.

[0094] Example 2

[0095] Figure 3 This document provides a flowchart of a method for determining the speed and acceleration ranges of a target vehicle in each road segment, as illustrated in an embodiment of this application. Figure 3 As shown, the method includes:

[0096] S301. Based on the road information ahead, the road ahead is divided into several road segments;

[0097] Specifically, road information such as curvature, slope, and length can be obtained from the in-vehicle electronic map. The road ahead can then be discretized into N sub-segments, and the dataset of these sub-segments can be... Where S i Let α be the length of the i-th sub-segment. i Let be the slope of the i-th sub-segment.

[0098] Figure 4 This is a schematic diagram of the process for obtaining road information provided in an embodiment of this application, such as... Figure 4 As shown, by analyzing the ADAS (Advanced Driver Assistance Systems Map), road information such as slope, curvature, and speed limits of the road ahead can be obtained. The ADAS map contains a wealth of detailed road information, such as lane lines, curbs, traffic signs, traffic lights, speed limits, slope, and curvature. This information helps the vehicle better understand and adapt to the road environment.

[0099] S302. Obtain the slope information of each sub-segment, and determine the slope type of each sub-segment based on the slope of each sub-segment and the preset slope range.

[0100] Specifically, the slope type of each sub-segment can be determined using formulas (1)-(3):

[0101]

[0102]

[0103]

[0104] Where, α up The road attribute is the uphill slope threshold; α down The road attribute is a downhill slope threshold; N is the number of road segments ahead, A+B+C=N. Formulas (1)-(3) can be used to determine whether each sub-segment is uphill, downhill, or flat. In the above formulas, 0, 1, and 2 are used to mark the road slope type for easy identification by the equipment; for example, a mark of 0 indicates a downhill road.

[0105] S303. In a sub-segment, continuous sub-segments with the same slope type are merged into a road segment, and the remaining sub-segments are identified as road segments.

[0106] For example, if two road segments are geographically continuous (i.e., connected) and have the same slope type (either flat or downhill), then these two road segments are merged into a single road segment. After merging using the above method, the remaining road segments are identified as road segments, thus completing the division of road segments.

[0107] S304. Obtain the average slope information for each road segment;

[0108] Specifically, it can be calculated using the following formula:

[0109]

[0110] Among them, a ave This represents the average slope of a certain road segment. It should be noted that since step S301 divides the road ahead into N sub-segments, the sub-segment indices range from 1 to N. For example, if a sub-segment is the 5th sub-segment out of all sub-segments, then its index is 5. The sub-segment index in this embodiment can be understood as the order of a sub-segment among all sub-segments. Since this road segment may be composed of multiple merged sub-segments, m is the starting index of this road segment on the map, and n is the ending index of this road segment on the map; that is, m is the index of the starting sub-segment of this road segment, and n is the index of the ending sub-segment of this road segment. i To form the length of the i-th sub-segment among all sub-segments, α i Let i be the slope of the sub-segment with index i.

[0111] By determining the average gradient of each road segment, the speed and acceleration limits of each segment can be determined, so that the speed and acceleration of the target vehicle are matched with the road terrain.

[0112] S305. Based on the average slope information of each road segment, determine the speed range and acceleration range of the target vehicle in each road segment;

[0113] Specifically, the speed limit and acceleration limit for each road segment can be determined based on the average gradient of each segment. For example:

[0114] 0 - s(k) ≤ v(k) ≤ v Max (k)+s(k)

[0115] a Min -s(k)≤a(k)≤a Max (k)+s(k)

[0116] v(k) is the velocity of the target vehicle at time k. Max (k) represents the speed limit of the target vehicle at time k, and a(k) represents the acceleration of the target vehicle at time k.Min Let a be the minimum acceleration of the target vehicle. Max s(k) represents the acceleration limit of the target vehicle at time k, and s(k) is a slack variable greater than or equal to 0, used to adjust the range of the speed range and acceleration range. Because road conditions are complex and changeable in actual applications, flexibly adjusting the speed range and acceleration range through slack variables can better adapt to the actual situation.

[0117] Alternatively, the rate of change of acceleration can be considered as a constraint condition for the rate of change of acceleration:

[0118]

[0119] j Min ≤j(k)≤j Max

[0120] Where j(k) is the rate of change of acceleration of the target vehicle at time k, and T s (k) represents the time step of the target vehicle between time k and time k-1, j Max j is the maximum rate of change of acceleration. Min This represents the minimum rate of change of acceleration. The purpose of considering the rate of change of acceleration is that if the rate of change of acceleration is too large, it will affect the comfort of the passengers in the target vehicle; if the rate of change of acceleration is too low, the speed of the target vehicle cannot be adjusted to the desired speed in a timely manner.

[0121] S306. Obtain the motion status information of the target vehicle at the current moment and the motion status information of the vehicle in front of the target vehicle;

[0122] Specifically, based on the filter's prediction of the target vehicle's and the vehicle ahead's motion states from the previous moment, and the detection information of the target vehicle's and the vehicle ahead's motion states detected by the detection equipment at the current moment, the filter calculates the current motion state information of the target vehicle and the vehicle ahead. That is, through the filter's motion state initialization, motion state prediction, and motion state update phases, the optimal estimation of the target vehicle's and the vehicle ahead's motion states is achieved at the current moment. At the current moment, the detection information of the target vehicle's and the vehicle ahead's motion states in the target vehicle's coordinate system can be obtained through various sensors. The filter can be a Kalman filter, particle filter, extended Kalman filter, etc. The state space of the target vehicle's and the vehicle ahead's motion states can be, for example, x = (p xk ,p yk ,v xk ,v yk ,a xk ,a yk ), p xk ,p ykThese are the x-coordinates and y-coordinates of the vehicle at time k relative to the target vehicle. xk ,v yk Let a be the vehicle's velocity along the x-axis and y-axis of the target vehicle at time k. xk ,a yk , respectively, represent the vehicle's acceleration along the x-axis and y-axis of the target vehicle at time k.

[0123] S307. Obtain the minimum parking distance, minimum following distance, and minimum following time information between the target vehicle and the vehicle in front, input by the driver of the target vehicle; and determine the distance range based on the minimum parking distance, minimum following distance, and minimum following time information.

[0124] Optionally, a distance range can be determined based on minimum parking distance information, minimum following distance information, and minimum following time information, including:

[0125] Calculate the distance interval using the distance interval calculation formula, which is:

[0126]

[0127] in, Let p(k) be the minimum parking distance at time k, and p(k) be the distance between the target vehicle and the vehicle in front at time k. Max (k) represents the maximum permissible distance between the target vehicle and the vehicle in front at time k, d Min For the minimum following distance, h Min Let v(k) be the target vehicle's speed at time k, and v(k) be the minimum following time. Minimum stopping distance refers to the shortest distance a vehicle needs to travel from the moment it detects the need to stop until it comes to a complete stop. Minimum following distance refers to the shortest safe distance between two vehicles during driving, ensuring the following vehicle has sufficient time and distance to react and brake if the preceding vehicle suddenly decelerates or stops, thus avoiding a rear-end collision. Minimum following time refers to the shortest time interval between the following and preceding vehicles, ensuring safe driving. By using these distance ranges, it can be ensured that the distance between the target vehicle and the preceding vehicle meets the safety requirements for driving.

[0128] Optionally, the following constraints can also be set:

[0129]

[0130] p Min (k) represents the minimum permissible distance between the target vehicle and the vehicle in front at time k, s p (k) is a slack variable that is greater than or equal to 0.

[0131] Because drivers can determine the minimum stopping distance, minimum following distance, and minimum following time based on the current real-time traffic conditions, the distance range between the target vehicle and the vehicle in front is more in line with the actual traffic conditions.

[0132] S308. The model predictive control algorithm predicts the expected speed value of each road segment based on the target constraints of each road segment, the motion state information of the target vehicle, and the motion state information of the vehicle in front.

[0133] The model predictive control algorithm predicts the desired speed value for each road segment based on the target cost function, the target constraints for each road segment, the motion state information of the target vehicle, and the motion state information of the vehicle ahead. This is to ensure that the target vehicle travels at the corresponding desired speed value in each road segment, so that the function value of the target cost function is minimized. The target cost function includes the target vehicle's fuel consumption penalty factor, acceleration change rate penalty factor, and slack variable penalty factor. The slack variables are used to adjust the range of distance interval, speed interval, and acceleration interval.

[0134] Specifically, the objective cost function can be:

[0135]

[0136] k = 1, ..., H T

[0137] in, As a fuel consumption penalty factor, c j2 j 2 (k) is the penalty factor for the rate of change of acceleration, c h s h (k) c Hard s(k) is the slack variable penalty factor, T s (k) represents the time step of the target vehicle between time k and time k-1. It should be noted that the slack variable penalty factor includes several slack variables from the target constraint, where s(k) represents the slack variables for adjusting the speed and acceleration intervals. h(k) represents the slack variables for adjusting the distance interval. When these slack variables are large, the speed interval, acceleration interval, and distance interval are obviously relatively loose. The target vehicle does not need to frequently adjust its speed and acceleration, resulting in lower fuel consumption and higher ride comfort. The fuel consumption penalty factor and acceleration change rate penalty factor are also smaller. However, because the speed interval, acceleration interval, and distance interval are relatively loose, the predicted speed may not match the actual driving conditions. For example, if the predicted speed is too low, it will take too long to reach the destination. Conversely, when these slack variables are small, the speed interval, acceleration interval, and distance interval are relatively tight. The target vehicle needs to frequently adjust its speed and acceleration, resulting in higher fuel consumption and lower ride comfort. The fuel consumption penalty factor and acceleration change rate penalty factor are also larger. However, because the speed interval, acceleration interval, and distance interval are relatively tight, the target vehicle can better match the actual driving conditions. Clearly, the fuel consumption penalty factor, the acceleration change rate penalty factor, and the slack variable penalty factor are mutually exclusive. By finding the optimal predicted vehicle speed value, the function value of the objective cost function is minimized, thereby achieving a balance between fuel economy, ride comfort, and the timeliness of the predicted vehicle speed for the target vehicle.

[0138] S309. Control the target vehicle to travel at the desired speed value corresponding to the current road segment on each road segment.

[0139] Optionally, this step may include:

[0140] Obtain the desired location value of the target vehicle, and detect the actual speed value and actual location value of the target vehicle in the current road segment;

[0141] Calculate the speed difference between the actual vehicle speed and the expected vehicle speed, and the position difference between the actual position and the expected position.

[0142] The target acceleration is calculated using the proportional-integral algorithm based on the product of the speed difference and the proportional coefficient, and the product of the position difference and the integral coefficient.

[0143] Control the target vehicle to travel at the target acceleration.

[0144] The calculation formula for the proportional-integral algorithm can be:

[0145]

[0146] in, For the desired acceleration, k p This is the proportionality coefficient. This is the actual vehicle speed value. Let x be the desired vehicle speed value, and x be the actual position value. des This represents the desired position value.

[0147] By using the proportional-integral algorithm, the actual speed of the target vehicle can be kept close to the desired speed.

[0148] Optionally, this step may also include:

[0149] Based on the formula for calculating expected torque, calculate the expected wheel torque corresponding to the current road segment. The formula for calculating expected torque is:

[0150]

[0151] Where, r eff R is the effective radius of the target vehicle's wheels, R is the gear ratio of the target vehicle's transmission, and R is the effective radius of the target vehicle's wheels. x J represents the rolling resistance of the target vehicle's wheels. e w is the effective rotational inertia of the target vehicle's engine. e c represents the engine speed of the target vehicle. a The target vehicle's drag coefficient;

[0152] Adjust the target vehicle's wheel torque to the desired torque.

[0153] Calculating the actual torque required by the target vehicle's wheels using the desired torque calculation formula can make the estimation of the target vehicle's wheel torque more accurate.

[0154] In this embodiment, a predictive adaptive cruise control system can be constructed according to the above method. In practical applications, the above steps S301 to S309 can be executed by the system. Figure 5 This is a schematic diagram of a predictive adaptive cruise control system provided in an embodiment of this application, as shown below. Figure 5As shown, the system includes a road network reconstruction module 501 based on an in-vehicle electronic map, a multi-source sensor fusion perception module 502, a human-machine interaction module 503, a vehicle speed planning module 504 based on a model predictive control algorithm, and a vehicle motion control module 505. The road network reconstruction module 501 based on the vehicle electronic map executes steps S301 to S304; the multi-source sensor fusion perception module 502 perceives the current motion state information of the vehicle and the motion state information of the vehicle in front through multi-source sensor fusion, such as through millimeter-wave radar, camera, lidar, inertial navigation unit, and other vehicle-side, road-side, and cloud-side sensors; the human-machine interaction module 503 interacts with the driver of the target vehicle to obtain the minimum stopping distance, minimum following distance, and minimum following time input by the driver; the vehicle speed planning module 504 based on the model predictive control algorithm obtains the information input by the road network reconstruction module 501, the multi-source sensor fusion perception module 502, and the human-machine interaction module 503, and then executes steps S305 to S308 to predict the expected vehicle speed values ​​at different future times, forming a sequence of expected vehicle speed values; the vehicle motion control module 505 executes step S309 to control the vehicle speed according to the expected vehicle speed value sequence.

[0155] Figure 6 This is a schematic diagram of multi-source sensor fusion sensing provided in an embodiment of this application, as shown below. Figure 6 As shown, the multi-source sensor fusion perception module 502 obtains various data from the vehicle and the vehicle in front through millimeter-wave radar, camera, lidar, inertial navigation unit, and other vehicle-side, road-side, and cloud-side sensors, and obtains motion status information of the vehicle and the vehicle in front through data fusion.

[0156] Figure 7 This is a schematic diagram of proportional-integral control provided in an embodiment of this application, such as... Figure 7 As shown, the vehicle motion control module 505 outputs the desired acceleration based on the current actual vehicle speed and position using the proportional-integral controller. The desired acceleration is then input into the vehicle kinematic model to calculate the desired torque of the current vehicle wheels. The torque of the vehicle wheels is then adjusted to the current desired torque, thereby adjusting the vehicle speed to be close to the current desired speed value.

[0157] 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.

[0158] Figure 8 This is a schematic diagram of a predictive vehicle speed control device provided in an embodiment of this application. Figure 8 As shown, the device 80 includes:

[0159] The segmentation module 801 is used to: divide the road ahead into several segments based on the road information of the road ahead of the target vehicle, and obtain the road information of each segment separately;

[0160] The acquisition module 802 is used to: acquire the motion status information of the target vehicle at the current moment and the motion status information of the vehicle in front of the target vehicle;

[0161] The determination module 803 is used to: determine the speed range and acceleration range of the target vehicle in each road segment based on the road information of each road segment;

[0162] The prediction module 804 is used to: use the distance range between the target vehicle and the vehicle in front, the speed range of each road segment, and the acceleration range as the target constraints for the target vehicle in each road segment, and the model prediction control algorithm to predict the expected vehicle speed value of each road segment based on the target constraints of each road segment, the motion state information of the target vehicle, and the motion state information of the vehicle in front.

[0163] The control module 805 is used to control the target vehicle to travel at the desired speed value corresponding to the current road segment on each road segment.

[0164] This embodiment provides a predictive vehicle speed control device that can execute the predictive vehicle speed control method described in the above embodiment. Its implementation principle and technical effects are similar, and will not be repeated here.

[0165] In the specific implementation of the aforementioned predictive speed control device, each module can be implemented as a processor. The processor can execute computer execution instructions stored in the memory, so that the processor executes the above-mentioned gear control method based on heavy-duty vehicles.

[0166] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 9 As shown, the electronic device 90 includes at least one processor 901 and a memory 902. The electronic device 90 also includes a communication component 903. The processor 901, memory 902, and communication component 903 are connected via a bus 904.

[0167] In a specific implementation, at least one processor 901 executes computer execution instructions stored in the memory 902, causing at least one processor 901 to execute the aforementioned predictive vehicle speed control method.

[0168] The specific implementation process of processor 901 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0169] 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.

[0170] The memory may include high-speed RAM, and may also include non-volatile storage (NVM), such as at least one disk storage.

[0171] 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.

[0172] 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 achieve 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 scope 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 to exceed the scope of the technical solutions of the embodiments of the present invention.

[0173] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the aforementioned predictive vehicle speed control method.

[0174] The aforementioned computer-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.

[0175] 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.

[0176] This application also provides a computer program product, comprising: a computer program stored in a readable storage medium, wherein 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 scheme provided in any of the above embodiments.

[0177] 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.

[0178] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention 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; and 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 the present invention.

Claims

1. A predictive vehicle speed control method, characterized in that, The method includes: Based on the road information of the road ahead of the target vehicle, the road ahead is divided into several segments, and the road information of each segment is obtained. Obtain the motion state information of the target vehicle at the current moment and the motion state information of the vehicle in front of the target vehicle; Based on the road information of each road segment, determine the speed range and acceleration range of the target vehicle in each road segment; The system obtains the minimum parking distance, minimum following distance, and minimum following time information between the target vehicle and the vehicle in front, input by the driver of the target vehicle. Based on the minimum parking distance, minimum following distance, and minimum following time information, the system determines the distance range between the target vehicle and the vehicle in front. Using the distance interval, the speed interval, and the acceleration interval of each road segment as target constraints for the target vehicle in each road segment, the expected speed of the target vehicle in each road segment is predicted based on the motion state information of the target vehicle and the motion state information of the vehicle in front. The target vehicle is controlled to travel at the desired speed value corresponding to the current road segment on each of the road segments.

2. The method according to claim 1, characterized in that, The step of obtaining the motion state information of the target vehicle at the current moment and the motion state information of the vehicle in front of the target vehicle includes: Based on the predicted motion state information of the target vehicle and the vehicle in front of the target vehicle at the previous moment, and the detected motion state information of the target vehicle and the vehicle in front of the target vehicle at the current moment, the motion state information of the target vehicle and the vehicle in front of the target vehicle at the current moment are calculated.

3. The method according to claim 1, characterized in that, The step of using the distance interval between the target vehicle and the vehicle ahead, the speed interval of each road segment, and the acceleration interval as target constraints for the target vehicle in each road segment, and predicting the expected speed of the target vehicle in each road segment based on the motion state information of the target vehicle and the motion state information of the vehicle ahead, includes: Based on the target cost function, the target constraints for each road segment, the motion state information of the target vehicle, and the motion state information of the vehicle ahead, a model predictive control algorithm is used to predict the expected speed of the target vehicle in each road segment. This is to ensure that the target cost function is minimized when the target vehicle travels at the corresponding expected speed in each road segment. The target cost function includes the target vehicle's fuel consumption penalty factor, acceleration rate of change penalty factor, and relaxation variable penalty factor. The relaxation variables are used to adjust the range of the distance interval, speed interval, and acceleration interval.

4. The method according to claim 1, characterized in that, The step of dividing the road ahead into several segments based on road information of the target vehicle, and obtaining road information for each of the segments, includes: Based on the road information of the road ahead, the road ahead is divided into several road segments; Obtain the slope information of each sub-road segment, and determine the slope type of each sub-road segment based on the slope of each sub-road segment and the preset slope range; In the sub-segments, consecutive sub-segments with the same slope type are merged into the road segment, and the remaining sub-segments are determined as the road segment; Obtain the average slope information for each road segment, and use the average slope information as the road information for each road segment.

5. The method according to claim 1, characterized in that, Controlling the target vehicle to travel at the desired speed value corresponding to the current road segment on each of the road segments includes: Obtain the desired location value of the target vehicle, and detect the actual speed value of the target vehicle in the current road segment and the actual location value of the target vehicle; Calculate the speed difference between the actual vehicle speed value and the expected vehicle speed value, and the position difference between the actual position value and the expected position value; The target acceleration is calculated using a proportional-integral algorithm based on the product of the vehicle speed difference and the proportional coefficient, and the product of the position difference and the integral coefficient. Control the target vehicle to travel at the target acceleration.

6. The method according to claim 5, characterized in that, The method of controlling the target vehicle to travel at the desired speed value corresponding to the current road segment on each road segment further includes: According to the formula for calculating expected torque, the expected wheel torque corresponding to the current road segment is calculated. The formula for calculating expected torque is as follows: Among them, is the effective radius of the wheel of the target vehicle, is the gear ratio of the gearbox of the target vehicle, is the rolling resistance of the wheel of the target vehicle, is the effective moment of inertia of the engine of the target vehicle, is the engine speed of the target vehicle, is the wind resistance coefficient of the target vehicle; The target vehicle wheel torque is adjusted to the desired torque.

7. A predictive vehicle speed control device, characterized in that, The device includes: The segmentation module is used to: divide the road ahead of the target vehicle into several segments based on the road information of the road ahead, and obtain the road information of each segment; The acquisition module is used to: acquire the motion state information of the target vehicle at the current moment, the motion state information of the vehicle in front of the target vehicle; and acquire the minimum parking distance information, minimum following distance information, and minimum following time information of the target vehicle and the vehicle in front, input by the driver of the target vehicle. The determination module is used to: determine the speed range and acceleration range of the target vehicle in each road segment based on the road information of each road segment; and determine the distance range between the target vehicle and the vehicle in front based on the minimum stopping distance information, the minimum following distance information, and the minimum following time information. The prediction module is used to: use the distance interval, the speed interval of each road segment, and the acceleration interval as target constraints for the target vehicle in each road segment, and use the model prediction control algorithm to predict the expected vehicle speed value for each road segment based on the target constraints of each road segment, the motion state information of the target vehicle, and the motion state information of the vehicle ahead. The control module is used to control the target vehicle to travel at the desired speed value corresponding to the current road segment on each of the road segments.

8. A predictive vehicle speed control device, characterized in that, The device includes: 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 predictive vehicle speed control method as described in any one of claims 1 to 6.

9. 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 predictive vehicle speed control method as described in any one of claims 1 to 6.

Images