Cruise control method, device, system and computer program product

Abstract

The present disclosure relates to a cruise control method, device, system and computer program product, and relates to the technical field of intelligent driving. The cruise control method comprises: determining a plurality of variable control parameters of a vehicle according to a preset optimization range of variable control parameters; dividing the plurality of variable control parameters into a plurality of populations to obtain variable control parameters in each population; iteratively optimizing the variable control parameters of the corresponding population according to the first performance optimal variable control parameter of each population to determine a target control parameter of the vehicle; and determining a target torque according to a first speed deviation between the target control parameter and an actual speed of the vehicle.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent driving technology, and in particular to a cruise control method, device, system and computer program product. Background Technology

[0002] With the rapid development of intelligent driving technology, vehicle cruise control has become one of the core functions of modern automotive advanced driver assistance systems. Furthermore, with the development of intelligent connected vehicles and autonomous driving technology, the performance requirements for vehicle cruise control are becoming increasingly stringent. Summary of the Invention

[0003] One of the technical problems this disclosure aims to solve is how to improve the stability and accuracy of vehicle cruise control.

[0004] According to some embodiments of the first aspect of this disclosure, a cruise control method is provided, comprising: determining multiple variable control parameters of a vehicle based on a preset optimization range of variable control parameters; dividing the multiple variable control parameters into multiple groups to obtain variable control parameters in each group; iteratively optimizing the variable control parameters of the corresponding group based on the first performance optimal variable control parameter of each group to determine the target control parameters of the vehicle; and determining the target torque based on the target control parameters, a first speed deviation between the vehicle's cruise speed and actual speed.

[0005] In some embodiments, the cruise control method further includes: determining a second performance-optimal variable control parameter for each population based on the performance parameter of each variable control parameter in each population; selecting a third performance-optimal variable control parameter for each target population from the second performance-optimal variable control parameters of the remaining populations excluding the target population, and determining a first performance-optimal variable control parameter for the target population from the second and third performance-optimal variable control parameters of the target population.

[0006] In some embodiments, selecting a third optimal variable control parameter for the target population from the second optimal variable control parameters among the remaining populations excluding the target population includes: randomly selecting a third optimal variable control parameter from the second optimal variable control parameters among the remaining populations excluding the target population; or determining the population with the smallest distance from the target population among the remaining populations excluding the target population, and determining the second optimal variable control parameter of the population with the smallest distance from the target population as the third optimal variable control parameter.

[0007] In some embodiments, dividing multiple variable control parameters into multiple populations to obtain the variable control parameters in each population includes: determining the performance parameter of each variable control parameter; determining the population size of multiple variable control parameters based on the performance parameter of each variable control parameter; and dividing the multiple variable control parameters into multiple populations based on the population size and the distance between each variable control parameter to obtain the variable control parameters in each population.

[0008] In some embodiments, determining the population size of multiple variable control parameters based on the performance parameter of each variable control parameter includes: determining the number of variable control parameters whose performance coefficient is greater than a performance threshold based on the performance coefficient of each variable control parameter; determining the population size as a first population size when the number of variable control parameters whose performance coefficient is greater than the performance threshold is greater than a population threshold; and determining the population size as a second population size when the number of variable control parameters whose performance coefficient is greater than the performance threshold is less than or equal to the population threshold, wherein the first population size is less than the second population size.

[0009] In some embodiments, iteratively optimizing the variable control parameters of the corresponding population based on the first performance-optimal variable control parameters of each population to determine the target control parameters of the vehicle includes: iteratively optimizing some or all of the variable control parameters of the corresponding population based on the first performance-optimal variable control parameters of each population until the end of a preset iteration period; determining the performance-optimal variable control parameters of the vehicle based on the performance parameters of all optimized variable control parameters, and determining the performance-optimal variable control parameters of the vehicle as the target control parameters.

[0010] In some embodiments, iteratively optimizing some or all of the variable control parameters of a corresponding population based on the first performance-optimal variable control parameter for each population includes: for each population, when the first performance-optimal variable control parameter of the population is the second performance-optimal variable control parameter of the population, iteratively optimizing some of the variable control parameters of the population, wherein the partial variable control parameters of the population include the remaining variable control parameters of the population other than the second performance-optimal variable control parameter of the population; and when the first performance-optimal variable control parameter of the population is the third performance-optimal variable control parameter of the population, iteratively optimizing all of the variable control parameters of the population.

[0011] In some embodiments, determining the performance parameter of each variable control parameter includes: determining the control speed corresponding to each variable control parameter based on each variable control parameter; and determining the performance parameter of each variable control parameter based on a second speed deviation between the cruise speed and the control speed corresponding to each variable control parameter.

[0012] In some embodiments, for each variable control parameter, there is an exponential relationship between the performance parameter of the variable control parameter and the second speed deviation of the variable control parameter.

[0013] In some embodiments, determining the control speed corresponding to each variable control parameter includes: for each variable control parameter, determining the throttle control opening of the vehicle based on the variable control parameter and a first speed deviation; determining the control torque of the vehicle based on the throttle control opening; and determining the control speed based on the control torque and the vehicle's resistance information.

[0014] In some embodiments, the target control parameters include target proportional control parameters, target integral control parameters, and target derivative gain control parameters, and the preset optimization range of the variable control parameters includes the optimization range of the proportional control parameters, the optimization range of the integral control parameters, and the optimization range of the derivative gain control parameters.

[0015] In some embodiments, the cruise control method further includes: after determining the target control parameters, storing the correspondence between the target control parameters and the cruise speed.

[0016] According to some embodiments of the second aspect of this disclosure, a cruise control device is provided, comprising: a first determining unit configured to determine a plurality of variable control parameters of a vehicle based on a preset optimization range of variable control parameters; a dividing unit configured to divide the plurality of variable control parameters into a plurality of populations to obtain variable control parameters in each population; an optimizing unit configured to iteratively optimize the variable control parameters of a corresponding population based on a first optimal variable control parameter of each population to determine a target control parameter of the vehicle; and a second determining unit configured to determine a target torque based on the target control parameter, a first speed deviation between the vehicle's cruise speed and actual speed.

[0017] According to some embodiments of the third aspect of this disclosure, a cruise control device is provided, including: a memory and a processor coupled to the memory, the processor being configured to execute the cruise control method of any of the above embodiments based on instructions stored in the memory.

[0018] According to some embodiments of the fourth aspect of this disclosure, a cruise control system is provided, comprising: a cruise control device as described in any of the foregoing embodiments; and a sensor configured to acquire and transmit the actual speed of the vehicle to the cruise control device.

[0019] According to some embodiments of the fifth aspect of this disclosure, a computer-readable storage medium is provided that stores computer instructions thereon, which, when executed by a processor, implement the cruise control method of any of the above embodiments.

[0020] According to some embodiments of the sixth aspect of this disclosure, a computer program product is provided, including computer instructions that, when executed by a processor, implement the cruise control method in any of the above embodiments.

[0021] In the above embodiments, multiple variable control parameters of the vehicle are determined based on the preset optimization range of the variable control parameters, providing feasibility for subsequent determination of target control parameters. By dividing the multiple variable control parameters into multiple populations, it is helpful to iteratively optimize the variable control parameters in each population. The local optimal particle (i.e., the first performance optimal variable control parameter) in each population guides the optimization of other particles (variable control parameters in each population), which can improve the global exploration capability of the variable control parameter optimization process, better maintain the diversity of variable control parameters, and reduce the risk of getting trapped in local optima. This helps to determine target control parameters with stability and accuracy, so as to determine target torque with stability and accuracy, thereby improving the stability and accuracy of the vehicle cruise control process. Attached Figure Description

[0022] The accompanying drawings, which form part of this specification, illustrate embodiments of this disclosure and, together with the specification, serve to explain the principles of this disclosure.

[0023] This disclosure can be more clearly understood with reference to the accompanying drawings and the following detailed description.

[0024] Figure 1 Schematic diagrams illustrating some embodiments of the cruise control method of this disclosure are shown.

[0025] Figure 2 Schematic diagrams illustrating some embodiments of the optimization of the two-dimensional variable control parameters of this disclosure are shown.

[0026] Figure 3 Schematic diagrams illustrating some embodiments of the optimization of variable control parameters of this disclosure are shown.

[0027] Figure 4 Schematic diagrams illustrating some embodiments of the cruise control system of this disclosure are shown.

[0028] Figure 5 Schematic diagrams illustrating other embodiments of the cruise control method of this disclosure are shown.

[0029] Figure 6 Schematic diagrams showing some embodiments of the cruise control device of this disclosure are provided.

[0030] Figure 7 Schematic diagrams of other embodiments of the cruise control device of this disclosure are shown.

[0031] Figure 8 Schematic diagrams of other embodiments of the cruise control system of this disclosure are shown. Detailed Implementation

[0032] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0033] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0034] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0035] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, they should be considered part of the specification.

[0036] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0037] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0038] With increasingly stringent performance requirements for vehicle cruise control, improving the stability and accuracy of vehicle cruise control is a problem that needs to be solved.

[0039] To address the aforementioned issues, this disclosure proposes a cruise control method, as detailed below.

[0040] Figure 1 Flowcharts illustrating some embodiments of the cruise control method of this disclosure are shown.

[0041] like Figure 1 As shown, the cruise control method includes steps 110 to 140, and the cruise control method is executed by the cruise control device.

[0042] In step 110, multiple variable control parameters of the vehicle are determined based on the preset optimization range of the variable control parameters.

[0043] For example, variable control parameters can be one-dimensional, two-dimensional, or multi-dimensional parameters.

[0044] For example, the variable control parameters are PID (Proportional-Integral-Derivative) parameters. PID parameters include kp (proportional parameter), ki (integral parameter), and kd (derivative parameter). The proportional parameter is used to generate the control quantity based on the current error (e.g., the first speed deviation between the vehicle's cruising speed and the actual speed). The integral parameter is used to accumulate historical errors and eliminate steady-state errors. The derivative parameter is used to predict the trend of microstrip error changes and suppress oscillations.

[0045] In step 120, the multiple variable control parameters are divided into multiple populations to obtain the variable control parameters in each population.

[0046] For example, multiple variable control parameters can be regarded as multiple particles. The position information of the particles is used to represent the variable control parameters corresponding to the particles, and the velocity direction information of the particles is used to indicate the optimization direction of the particles. If the variable control parameter is a one-dimensional parameter, the space in which the particles are located is a one-dimensional space; if the variable control parameter is a two-dimensional parameter, the space in which the particles are located is a two-dimensional space; and if the variable control parameter is a three-dimensional parameter, the space in which the particles are located is a three-dimensional space.

[0047] For example, in the process of dividing multiple variable control parameters into multiple populations, the division can be based on the position information of multiple particles and the population size, or it can be based on the distance between particles and the population size.

[0048] For example, particles can be divided based on their position information and population size, with each population containing the same number of particles. Alternatively, particles can be divided based on their distance from each other, determining whether the distance is less than or equal to a preset distance threshold. If the distance between some particles is less than or equal to the preset distance threshold, these particles are considered to belong to the same population, and the number of particles in each population can be different.

[0049] In step 130, the variable control parameters of the corresponding population are iteratively optimized based on the first performance-optimal variable control parameters of each population to determine the target control parameters of the vehicle.

[0050] For each population, the first performance-optimal variable control parameter of the population can be the best variable control parameter in that population, or it can be the best variable control parameter in other populations.

[0051] Treating the variable control parameter as a particle, iteratively optimizing the variable control parameter of the corresponding population can be understood as iteratively optimizing the particle of the corresponding population. The optimization process is then described directly using the particle, as shown in formulas (1) and (2).

[0052] (1).

[0053] (2).

[0054] in, This represents the velocity information of the i-th particle at time t+1. This represents the velocity information of the i-th particle at time t. The inertial weight represents the proportion of velocity information of the i-th particle retained at time t. and These represent two acceleration coefficients that influence the historical optimal position of the i-th particle at time t. Used to influence the position of the best-performing particle in the population containing the i-th particle at time t. and These are two independent random numbers uniformly generated within the range [0,1]. This represents the position information of the i-th particle at time t+1. This represents the position information of the i-th particle at time t. Let represent the historical best position of the i-th particle at time t, where the historical best position refers to the position where the i-th particle performed optimally before time t. It represents the first performance-optimal variable control parameter of the population containing the i-th particle at time t (i.e., the performance-optimal particle of the population containing the i-th particle at time t, which may or may not belong to the population).

[0055] Compared to determining the position of the i-th particle at time t+1 based on its historical best position at time t and the best-performing particle among all particles at time t, this method divides multiple particles into multiple populations and determines the position of the i-th particle at time t+1 based on its historical best position at time t and the best-performing particle in its population at time t. This approach improves the global exploration capability of the particle optimization process, ensures particle diversity, and reduces the risk of getting trapped in local optima.

[0056] Taking two-dimensional variable control parameters as an example, Figure 2 Schematic diagrams illustrating some embodiments of the optimization of the two-dimensional variable control parameters of this disclosure are shown.

[0057] like Figure 2 As shown, 21 represents the position information of a particle before optimization, 24 represents the position information of the particle after optimization, 22 represents the historical best position of the particle, and 23 represents the first best-performing particle in the population to which the particle belongs. This indicates that the particle's velocity information has been optimized.

[0058] In step 140, the target torque is determined based on the target control parameters, the first speed deviation between the vehicle's cruise speed and actual speed.

[0059] For example, the target control parameters include the target proportional control parameter (i.e., the target proportional parameter), the target integral control parameter (i.e., the target integral parameter), and the target derivative gain control parameter (i.e., the target derivative parameter). The preset optimization range of the variable control parameters in step 110 includes the optimization range of the proportional control parameter, the optimization range of the integral control parameter, and the optimization range of the derivative gain control parameter.

[0060] In the above embodiments, multiple variable control parameters of the vehicle are determined based on the preset optimization range of the variable control parameters, providing feasibility for subsequent determination of target control parameters. By dividing the multiple variable control parameters into multiple populations, it is helpful to iteratively optimize the variable control parameters in each population. The local optimal particle (i.e., the first performance optimal variable control parameter) in each population guides the optimization of other particles (variable control parameters in each population), which can improve the global exploration capability of the variable control parameter optimization process, better maintain the diversity of variable control parameters, and reduce the risk of getting trapped in local optima. This helps to determine target control parameters with stability and accuracy, so as to determine target torque with stability and accuracy, thereby improving the stability and accuracy of the vehicle cruise control process.

[0061] The following examples illustrate how to determine the first performance-optimal variable control parameter for each population.

[0062] In some embodiments, a second performance-optimal variable control parameter is determined for each population based on the performance parameter of each variable control parameter in each population; each population is sequentially used as a target population, and a third performance-optimal variable control parameter for the target population is selected from the second performance-optimal variable control parameters of the remaining populations excluding the target population; a first performance-optimal variable control parameter for the target population is determined from the second and third performance-optimal variable control parameters of the target population.

[0063] For example, determine the performance corresponding to the second optimal variable control parameter of the target population (e.g., the fitness value corresponding to the second optimal variable control parameter of the target population) and the performance corresponding to the third optimal variable control parameter of the target population (e.g., the fitness value corresponding to the third optimal variable control parameter of the target population). If the performance corresponding to the second optimal variable control parameter is better than the performance corresponding to the third optimal variable control parameter, then the second optimal variable control parameter is determined as the first optimal variable control parameter of the target population. If the performance corresponding to the third optimal variable control parameter is better than the performance corresponding to the second optimal variable control parameter, then the third optimal variable control parameter is determined as the first optimal variable control parameter of the target population. The first optimal variable control parameter of the target population is used to guide the optimization of other variable control parameters in the target population.

[0064] For example, the second-best performance variable control parameter for each population (i.e., the position information of the best-performing particle in each population) can be stored in a shared pool, such as... , where l represents the population size, and the third performance-optimal variable control parameter of the target population can be selected in the shared pool.

[0065] The first performance-optimal variable control parameter for the target population is determined as shown in formula (3).

[0066] (3).

[0067] in, This represents the second performance-optimal variable control parameter for the target population. The performance (performance parameter) represents the second best performance variable control parameter of the target population. Let represent the second optimal variable control parameter in the r-th population, where r takes the index of each population (numbered from 1 to l) excluding the target population. This represents the performance of the second-best variable control parameter in the r-th population.

[0068] By determining the first optimal variable control parameter for the target population from the optimal variable control parameter in the target population and the optimal variable control parameter in one of the remaining populations (excluding the target population), the information exchange capacity among the populations can be improved, enabling the sharing of optimal variable control parameters among different populations, increasing population diversity, and balancing the convergence and diversity of the variable control parameter optimization process. Furthermore, by preserving the possibility that the optimal variable control parameter in one of the remaining populations (excluding the target population) might guide the optimization process of the variable control parameters in the target population, the risk of the optimization process getting trapped in local optima is reduced. This also allows the variable control parameters in the target population to optimize in a positive direction (i.e., the particles corresponding to the variable control parameters in the target population move in a positive direction), improving the convergence and accuracy of the iterative optimization process of the variable control parameters.

[0069] Figure 3 Schematic diagrams illustrating some embodiments of the optimization of variable control parameters of this disclosure are shown.

[0070] like Figure 3 As shown, multiple variable control parameters correspond to multiple particles. 31 includes multiple particles corresponding to multiple variable control parameters determined according to the preset optimization range of the variable control parameters. The multiple particles in 31 are then divided into particle swarms (i.e., populations), resulting in multiple populations in 32 (such as...). Figure 3 As shown, taking the division of multiple particles into 5 populations as an example, namely population A, population B, population C, population D and population E, where, as Figure 3 As shown, during the population partitioning process, the population is partitioned based on the population size and the position information of each particle.

[0071] like Figure 3As shown, each population includes at least one best-performing particle. After determining the best-performing particle in each population, a shared pool (also called a sample pool) 33 is constructed, which includes the best-performing particle in each population. Subsequently, each population is used as the target population in turn. It is determined whether to update the best-performing particle in each population. Specifically, a best-performing particle is randomly selected from the best-performing particles in other populations besides the target population. The performance of the best-performing particle in the target population is compared with the performance of the randomly selected best-performing particle. If the performance of the randomly selected best-performing particle is better than that of the best-performing particle in the target population, then the randomly selected best-performing particle replaces the best-performing particle in the target population and becomes the best-performing particle in the target population. The best-performing particle in the target population can serve as the optimization direction for other particles in the target population, guiding their movement. Subsequently, other particles in the target population can be optimized based on the best-performing particle. The optimization of other particles in the target population mainly involves updating the velocity information (i.e., the optimization direction of the particle) and position information (i.e., the values ​​of the variable control parameters corresponding to the particle).

[0072] Taking population A as an example, a top-performing particle is randomly selected from the top-performing particles in populations B, C, D, and E. Assuming this randomly selected particle is the top-performing particle in population B, the performance of the top-performing particle in population A is compared with that in population B. The particle with the best performance between these two groups is then designated as the top-performing particle in population A. Subsequently, based on this top-performing particle, some or all particles in population A are optimized, resulting in 34 updated particles. If the iteration cycle ends, the top-performing particle in these 34 particles is selected as the target particle. The target control parameters can be determined based on the position of the target particle.

[0073] The following examples illustrate how to select the third performance-optimal variable control parameter for the target population.

[0074] In some embodiments, a third optimal variable control parameter is randomly selected from the second optimal variable control parameters in the remaining population excluding the target population; or the population with the smallest distance from the target population is determined in the remaining population excluding the target population, and the second optimal variable control parameter in the population with the smallest distance from the target population is determined as the third optimal variable control parameter.

[0075] By randomly selecting the third optimal variable control parameter of the target population from the second optimal variable control parameters in the remaining populations excluding the target population, the second optimal variable control parameter in each of the remaining populations has the opportunity to be used as the third optimal variable control parameter of the target population. In other words, the second optimal variable control parameter in each of the remaining populations has the opportunity to guide the optimization of the variable control parameters in the target population, which can better realize the sharing of optimal variable control parameters among different populations.

[0076] By identifying the population with the smallest distance from the target population among the remaining populations excluding the target population, and determining the second-optimal variable control parameter in the population with the smallest distance from the target population as the third-optimal variable control parameter of the target population, the second-optimal variable control parameter in the population with the smallest distance from the target population has strong local reference value, which can improve the stability of the variable control parameter optimization process of the target population.

[0077] The following examples illustrate how to divide multiple variable control parameters into multiple populations.

[0078] In some embodiments, a performance parameter for each variable control parameter is determined; based on the performance parameter of each variable control parameter, the population size of multiple variable control parameters is determined; based on the population size and the distance between each variable control parameter, the multiple variable control parameters are divided into multiple populations to obtain the variable control parameters in each population.

[0079] The distance between each variable control parameter can represent the difference between each variable control parameter. Based on the distance between each variable control parameter, multiple variable control parameters are divided into multiple populations. That is, variable control parameters with small differences are divided into one population, which helps to iteratively optimize the variable control parameters in each population. Considering that variable control parameters with small differences will have similar optimization directions, they can be treated as variable control parameters in the same population for unified optimization, which improves the accuracy of the optimization process.

[0080] For determining the population size of multiple variable control parameters, in some embodiments, based on the performance coefficient of each variable control parameter, the number of variable control parameters with performance coefficients greater than a performance threshold is determined; if the number of variable control parameters with performance coefficients greater than the performance threshold is greater than a population threshold, the population size is determined as a first population size; if the number of variable control parameters with performance coefficients greater than the performance threshold is less than or equal to the population threshold, the population size is determined as a second population size, wherein the first population size is less than the second population size.

[0081] If the performance coefficient of a variable control parameter is greater than the performance threshold, it means that the performance of the variable control parameter meets the minimum requirements. If the number of variable control parameters with performance coefficients greater than the performance threshold is greater than the quantity threshold, it means that there are a large number of variable control parameters that meet the minimum requirements, i.e., the performance of more variable control parameters is better. If the number of variable control parameters with performance coefficients greater than the performance threshold is less than or equal to the quantity threshold, it means that there are a small number of variable control parameters that meet the minimum requirements, i.e., the performance of fewer variable control parameters is better.

[0082] When the performance of a large number of variable control parameters is good, multiple variable control parameters are divided into a smaller population; when the performance of a small number of variable control parameters is good, multiple variable control parameters are divided into a larger population. This balances the stability and efficiency in the optimization process of variable control parameters.

[0083] The following examples illustrate how to determine the target control parameters for a vehicle.

[0084] In some embodiments, based on the first performance-optimal variable control parameter of each population, some or all of the variable control parameters of the corresponding population are iteratively optimized until the preset iteration period ends; based on the performance parameters of all optimized variable control parameters, the performance-optimal variable control parameter of the vehicle is determined, and the performance-optimal variable control parameter of the vehicle is determined as the target control parameter.

[0085] By using the best-performing variable control parameter among the optimized variable control parameters as the target control parameter, it is helpful to improve the stability and accuracy of the target torque determined subsequently based on the target control parameter.

[0086] The specifics regarding when to iteratively optimize some of the variable control parameters of the corresponding population, and when to iteratively optimize all the variable control parameters of the corresponding population, are as follows.

[0087] In some embodiments, for each population, when the first performance-optimal variable control parameter of the population is the second performance-optimal variable control parameter of the population, some variable control parameters of the population are iteratively optimized, wherein some variable control parameters of the population include the remaining variable control parameters of the population other than the second performance-optimal variable control parameter of the population; when the first performance-optimal variable control parameter of the population is the third performance-optimal variable control parameter of the population, all variable control parameters of the population are iteratively optimized.

[0088] Considering that the first optimal variable control parameter of a population may be the second optimal variable control parameter in the population, or it may be the second optimal variable control parameter in the remaining populations (i.e., the third optimal variable control parameter of the population), the optimization of all or some of the variable control parameters of the population can be determined based on whether the first optimal variable control parameter of the population is a variable control parameter in the population. This ensures that all variable control parameters that need to be optimized can be optimized, balancing the stability and efficiency of the iterative optimization process of variable control parameters.

[0089] The following examples illustrate how to determine the performance parameters for each variable control parameter.

[0090] In some embodiments, the control speed corresponding to each variable control parameter is determined based on each variable control parameter; and the performance parameter of each variable control parameter is determined based on the second speed deviation between the cruise speed and the control speed corresponding to each variable control parameter.

[0091] In some embodiments, for each variable control parameter, there is an exponential relationship between the performance parameter of the variable control parameter and the second speed deviation of the variable control parameter.

[0092] For example, the relationship between the performance parameters of the variable control parameters and the second speed deviation of the variable control parameters is shown in Equation (4).

[0093] (4).

[0094] in, Performance parameters representing variable control parameters, This indicates the second speed deviation, which refers to the absolute value of the difference between the cruise speed and the control speed. and These are fixed parameters.

[0095] The performance parameters of the variable control parameters have an exponential relationship with the second velocity deviation of the variable control parameters. This relationship can amplify the differences between the performance parameters of different variable control parameters, which helps to find the optimal variable control parameters in the process of optimizing the variable control parameters and improves the convergence and accuracy of the optimization process.

[0096] For each variable control parameter corresponding to the control speed, in some embodiments, for each variable control parameter, the throttle control opening of the vehicle is determined based on the variable control parameter and the first speed deviation; the control torque of the vehicle is determined based on the throttle control opening; and the control speed is determined based on the control torque and the vehicle's resistance information.

[0097] Different variable control parameters correspond to different control speeds. Vehicle resistance information includes rolling resistance, air resistance, and gradient resistance.

[0098] First, the first speed deviation is adjusted by the variable control parameters to obtain the throttle opening of the vehicle. The control torque (i.e. the motor demand torque) corresponding to the throttle opening of the vehicle can be obtained by looking up the table. Then, the wheel torque of the vehicle is determined according to the motor demand torque and the gear ratio of the vehicle. Finally, the control speed of the vehicle is determined according to the wheel torque and resistance information of the vehicle, as shown in formulas (5) to (7).

[0099] (5).

[0100] (6).

[0101] (7).

[0102] in, Indicates wheel torque. This indicates the vehicle's resistance information. Indicates the moment of inertia. The value is 1. This indicates the vehicle's weight, and this indicates the vehicle's wheel radius. Indicates the vehicle's control angular velocity. This indicates the vehicle's controlled speed.

[0103] In some embodiments, after the target control parameters are determined, the correspondence between the target control parameters and the cruise speed is stored.

[0104] For example, the correspondence between cruise speed range and target control parameters can also be stored. For instance, when the cruise speed is less than or equal to 40 km / h, there is one target control parameter, and when the cruise speed is greater than 40 km / h but less than or equal to 60 km / h, there is another target control parameter.

[0105] By storing the correspondence between target control parameters and cruise speed, it is possible to directly call target control parameters based on cruise speed, which can improve the efficiency of cruise control. Without increasing any additional hardware costs, it reduces the computational load of the cruise control process and ensures the real-time performance of the cruise control process.

[0106] Figure 4 Schematic diagrams illustrating some embodiments of the cruise control system of this disclosure are shown.

[0107] like Figure 4As shown, firstly, based on the cruise speed (i.e., cruise speed) 41 and the actual speed obtained by the sensor 45, the first speed deviation 42 is determined. The PID cruise controller 43 can generate the throttle opening according to the determined target control parameters (i.e. target PID control parameters) and the first speed deviation 42. The vehicle control system 44 can determine the target torque of the vehicle according to the throttle opening, thereby controlling the torque of the vehicle and adjusting the speed of the vehicle, thus forming a closed-loop control.

[0108] Figure 5 Schematic diagrams illustrating other embodiments of the cruise control method of this disclosure are shown.

[0109] like Figure 5 As shown, the cruise control method includes steps 510 to 570.

[0110] In step 510, cruise control is initiated.

[0111] In step 520, multiple variable control parameters are initialized based on the preset optimization range of the variable control parameters.

[0112] If we consider each variable control parameter as a particle, and determine the specific data of the variable control parameter through the position information of the particle, then initializing multiple variable control parameters can be understood as initializing the position and velocity information of multiple particles. Among them, the velocity information is initialized to zero, and the position information can be randomly generated based on the optimization range of the variable control parameter.

[0113] In step 530, cruise control simulation is performed.

[0114] For example, set the controller parameters (vehicle weight, wheel radius, drag information, etc.) in the simulation environment and run the vehicle cruise simulation.

[0115] In step 540, the variable control parameters in each population are optimized.

[0116] Determine the first performance-optimal variable control parameter for each population, and optimize the variable control parameters in each population based on the first performance-optimal variable control parameter for each population.

[0117] In step 550, it is determined whether the iteration cycle has ended.

[0118] If the iteration cycle ends, proceed directly to step 570; if the iteration cycle does not end, proceed directly to step 560.

[0119] In step 560, the simulation environment and the first performance-optimal variable control parameters for each population are updated, and step 530 is then re-executed.

[0120] In step 570, cruise control is terminated.

[0121] In the above embodiments, by using the locally optimal particle (i.e. the first performance optimal variable control parameter) within each population to guide the optimization of other particles (variable control parameters in each population), the global exploration capability of the variable control parameter optimization process can be improved, the diversity of variable control parameters can be better maintained, and the risk of getting trapped in local optima can be reduced. This helps to determine the target control parameter with stability and accuracy, so as to determine the target torque with stability and accuracy, thereby improving the stability and accuracy of the vehicle cruise control process.

[0122] Figure 6 Schematic diagrams showing some embodiments of the cruise control device of this disclosure are provided.

[0123] The cruise control device 60 includes a first determining unit 61, a dividing unit 62, an optimization unit 63, and a second determining unit 64.

[0124] The first determining unit 61 is configured to determine multiple variable control parameters of the vehicle based on a preset optimization range of variable control parameters.

[0125] The partitioning unit 62 is configured to divide multiple variable control parameters into multiple populations to obtain the variable control parameters in each population.

[0126] The optimization unit 63 is configured to iteratively optimize the variable control parameters of the corresponding population based on the first performance-optimal variable control parameters of each population, so as to determine the target control parameters of the vehicle.

[0127] The second determining unit 64 is configured to determine the target torque based on the target control parameters, a first speed deviation between the vehicle's cruise speed and actual speed.

[0128] In the above embodiments, multiple variable control parameters of the vehicle are determined based on the preset optimization range of the variable control parameters, providing feasibility for subsequent determination of target control parameters. By dividing the multiple variable control parameters into multiple populations, it is helpful to iteratively optimize the variable control parameters in each population. The local optimal particle (i.e., the first performance optimal variable control parameter) in each population guides the optimization of other particles (variable control parameters in each population), which can improve the global exploration capability of the variable control parameter optimization process, better maintain the diversity of variable control parameters, and reduce the risk of getting trapped in local optima. This helps to determine target control parameters with stability and accuracy, so as to determine target torque with stability and accuracy, thereby improving the stability and accuracy of the vehicle cruise control process.

[0129] In some embodiments, the optimization unit 63 is further configured to: determine a second performance-optimal variable control parameter for each population based on the performance parameter of each variable control parameter in each population; sequentially use each population as a target population; select a third performance-optimal variable control parameter for the target population from the second performance-optimal variable control parameters of the remaining populations excluding the target population; and determine a first performance-optimal variable control parameter for the target population from the second and third performance-optimal variable control parameters of the target population.

[0130] In some embodiments, the optimization unit 63 is further configured to randomly select a third optimal variable control parameter from the second optimal variable control parameters in the remaining population excluding the target population; or to determine the population with the smallest distance from the target population in the remaining population excluding the target population, and to determine the second optimal variable control parameter in the population with the smallest distance from the target population as the third optimal variable control parameter.

[0131] In some embodiments, the partitioning unit 62 is further configured to determine the performance parameter of each variable control parameter; determine the population size of multiple variable control parameters based on the performance parameter of each variable control parameter; and partition the multiple variable control parameters into multiple populations based on the population size and the distance between each variable control parameter to obtain the variable control parameters in each population.

[0132] In some embodiments, the partitioning unit 62 is further configured to determine the number of variable control parameters whose performance coefficients are greater than a performance threshold based on the performance coefficient of each variable control parameter; if the number of variable control parameters whose performance coefficients are greater than the performance threshold is greater than a quantity threshold, determine the population size as a first population size; if the number of variable control parameters whose performance coefficients are greater than the performance threshold is less than or equal to the quantity threshold, determine the population size as a second population size, wherein the first population size is less than the second population size.

[0133] In some embodiments, the optimization unit 63 is further configured to iteratively optimize some or all of the variable control parameters of the corresponding population based on the first performance-optimal variable control parameter of each population until the preset iteration period ends; determine the vehicle's performance-optimal variable control parameter based on the performance parameters of all optimized variable control parameters, and determine the vehicle's performance-optimal variable control parameter as the target control parameter.

[0134] In some embodiments, the optimization unit 63 is further configured to, for each population, iteratively optimize some of the population's variable control parameters when the first optimal variable control parameter of the population is the second optimal variable control parameter of the population, wherein the partial variable control parameters of the population include the remaining variable control parameters in the population other than the second optimal variable control parameter of the population; and iteratively optimize all of the population's variable control parameters when the first optimal variable control parameter of the population is the third optimal variable control parameter of the population.

[0135] In some embodiments, the partitioning unit 62 is further configured to determine the control speed corresponding to each variable control parameter based on each variable control parameter; and to determine the performance parameter of each variable control parameter based on the second speed deviation between the cruise speed and the control speed corresponding to each variable control parameter.

[0136] In some embodiments, for each variable control parameter, there is an exponential relationship between the performance parameter of the variable control parameter and the second speed deviation of the variable control parameter.

[0137] In some embodiments, the partitioning unit 62 is further configured to, for each variable control parameter, determine the throttle control opening of the vehicle based on the variable control parameter and the first speed deviation; determine the control torque of the vehicle based on the throttle control opening; and determine the control speed based on the control torque and the vehicle's resistance information.

[0138] In some embodiments, the target control parameters include target proportional control parameters, target integral control parameters, and target derivative gain control parameters, and the preset optimization range of the variable control parameters includes the optimization range of the proportional control parameters, the optimization range of the integral control parameters, and the optimization range of the derivative gain control parameters.

[0139] Figure 7 Schematic diagrams of other embodiments of the cruise control device of this disclosure are shown.

[0140] like Figure 7 As shown, the cruise control device 60 of this embodiment includes a memory 71 and a processor 72 coupled to the memory 71. The processor 72 is configured to execute the cruise control method of any of the foregoing embodiments based on instructions stored in the memory 71.

[0141] The memory 71 may include, for example, system memory, fixed non-volatile storage media, etc. The system memory stores, for example, the operating system, application programs, boot loader, and other programs.

[0142] The cruise control device 60 may also include an input / output interface 73, a network interface 74, and a storage interface 75. These interfaces 73, 74, and 75, as well as the memory 71 and processor 72, can be connected via, for example, a bus 76. The input / output interface 73 provides a connection interface for input / output devices such as a monitor, mouse, keyboard, touchscreen, microphone, and speakers. The network interface 74 provides a connection interface for various networked devices. The storage interface 75 provides a connection interface for external storage devices such as SD cards and USB flash drives.

[0143] In the above embodiments, multiple variable control parameters of the vehicle are determined based on the preset optimization range of the variable control parameters, providing feasibility for subsequent determination of target control parameters. By dividing the multiple variable control parameters into multiple populations, it is helpful to iteratively optimize the variable control parameters in each population. The local optimal particle (i.e., the first performance optimal variable control parameter) in each population guides the optimization of other particles (variable control parameters in each population), which can improve the global exploration capability of the variable control parameter optimization process, better maintain the diversity of variable control parameters, and reduce the risk of getting trapped in local optima. This helps to determine target control parameters with stability and accuracy, so as to determine target torque with stability and accuracy, thereby improving the stability and accuracy of the vehicle cruise control process.

[0144] Figure 8 Schematic diagrams of other embodiments of the cruise control system of this disclosure are shown.

[0145] like Figure 8 As shown, the cruise control system 80 includes the cruise control device 60 and sensor 81 in any of the above embodiments.

[0146] Sensor 81 is configured to acquire and transmit the vehicle’s actual speed to the cruise control unit.

[0147] In the above embodiments, multiple variable control parameters of the vehicle are determined based on the preset optimization range of the variable control parameters, providing feasibility for subsequent determination of target control parameters. By dividing the multiple variable control parameters into multiple populations, it is helpful to iteratively optimize the variable control parameters in each population. The local optimal particle (i.e., the first performance optimal variable control parameter) in each population guides the optimization of other particles (variable control parameters in each population), which can improve the global exploration capability of the variable control parameter optimization process, better maintain the diversity of variable control parameters, and reduce the risk of getting trapped in local optima. This helps to determine target control parameters with stability and accuracy, so as to determine target torque with stability and accuracy, thereby improving the stability and accuracy of the vehicle cruise control process.

[0148] In some embodiments, a computer program product is protected, comprising a computer program or instructions that, when executed by a processor, implement the cruise control method described above. The computer program product includes computer instructions carried on a computer-readable medium, the computer instructions containing program code for performing the methods shown in the flowchart. In such embodiments, the computer instructions can be downloaded and installed from a network, installed from a storage device, or installed from a ROM via a cruise control device. When the computer program is executed by the CPU, it performs the functions defined in the methods of the embodiments of this disclosure.

[0149] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0150] The cruise control method, apparatus, system, and computer program product of this disclosure have been described in detail above. To avoid obscuring the concept of this disclosure, some details known in the art have not been described. Those skilled in the art can fully understand how to implement the technical solutions disclosed herein based on the above description.

[0151] The methods and systems of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.

[0152] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A cruise control method, comprising: Based on the preset optimization range of the variable control parameters, determine multiple variable control parameters of the vehicle; The multiple variable control parameters are divided into multiple populations to obtain the variable control parameters in each population. Based on the performance parameters of each variable control parameter in each population, determine the second performance-optimal variable control parameter for each population; Each population is taken as the target population in turn, and the third performance optimal variable control parameter of the target population is selected from the second performance optimal variable control parameters of the remaining populations excluding the target population. The first performance-optimal variable control parameter of the target population is determined from the second performance-optimal variable control parameter and the third performance-optimal variable control parameter of the target population; Based on the first performance-optimal variable control parameters of each population, the variable control parameters of the corresponding population are iteratively optimized to determine the target control parameters of the vehicle. The target torque is determined based on the target control parameters, the first speed deviation between the vehicle's cruising speed and actual speed.

2. The cruise control method according to claim 1, wherein, The selection of the third performance-optimal variable control parameter for the target population from the second performance-optimal variable control parameters among the remaining populations excluding the target population includes: From the second optimal performance variable control parameters in the remaining population excluding the target population, the third optimal performance variable control parameter is randomly selected; or Among the remaining populations excluding the target population, determine the population with the smallest distance from the target population, and determine the second performance-optimal variable control parameter of the population with the smallest distance from the target population as the third performance-optimal variable control parameter.

3. The cruise control method according to claim 1, wherein, The step of dividing the multiple variable control parameters into multiple populations to obtain the variable control parameters in each population includes: Determine the performance parameters for each variable control parameter; Based on the performance parameters of each variable control parameter, determine the population size of the plurality of variable control parameters; Based on the population size and the distance between each variable control parameter, the multiple variable control parameters are divided into multiple populations to obtain the variable control parameters in each population.

4. The cruise control method according to claim 3, wherein, Determining the population size of the plurality of variable control parameters based on the performance parameters of each variable control parameter includes: Based on the performance coefficient of each variable control parameter, determine the number of variable control parameters whose performance coefficient is greater than the performance threshold; If the number of variable control parameters whose performance coefficient is greater than the performance threshold is greater than the number threshold, the population size is determined to be the first population size. If the number of variable control parameters whose performance coefficient is greater than the performance threshold is less than or equal to the quantity threshold, the population size is determined as the second population size, wherein the first population size is less than the second population size.

5. The cruise control method according to claim 1 or 2, wherein, The step of iteratively optimizing the variable control parameters of the corresponding population based on the first performance-optimal variable control parameters of each population to determine the target control parameters of the vehicle includes: Based on the first performance-optimal variable control parameter of each population, some or all of the variable control parameters of the corresponding population are iteratively optimized until the preset iteration period ends. Based on the performance parameters of all optimized variable control parameters, the optimal variable control parameters for the vehicle's performance are determined, and these optimal variable control parameters are set as the target control parameters.

6. The cruise control method according to claim 5, wherein, The step of iteratively optimizing some or all of the variable control parameters of the corresponding population based on the first performance-optimal variable control parameter of each population includes: For each population, when the first performance-optimal variable control parameter of the population is the second performance-optimal variable control parameter of the population, some variable control parameters of the population are iteratively optimized, wherein the some variable control parameters of the population include the remaining variable control parameters of the population other than the second performance-optimal variable control parameter of the population. If the first optimal variable control parameter of the population is the third optimal variable control parameter of the population, then all variable control parameters of the population are iteratively optimized.

7. The cruise control method according to claim 3, wherein, The performance parameters for determining each variable control parameter include: Based on each variable control parameter, determine the control speed corresponding to each variable control parameter; The performance parameter of each variable control parameter is determined based on the second speed deviation between the cruise speed and the control speed corresponding to each variable control parameter.

8. The cruise control method according to claim 7, wherein, For each of the variable control parameters, there is an exponential relationship between the performance parameter of the variable control parameter and the second speed deviation of the variable control parameter.

9. The cruise control method according to claim 7, wherein, The step of determining the control speed corresponding to each variable control parameter based on each variable control parameter includes: For each of the variable control parameters, the throttle control opening of the vehicle is determined based on the variable control parameter and the first speed deviation; The control torque of the vehicle is determined based on the throttle control opening. The control speed is determined based on the control torque and the vehicle's resistance information.

10. The cruise control method according to any one of claims 1 to 4, wherein, The target control parameters include target proportional control parameters, target integral control parameters, and target derivative gain control parameters. The preset optimization range of the variable control parameters includes the optimization range of the proportional control parameters, the optimization range of the integral control parameters, and the optimization range of the derivative gain control parameters.

11. The cruise control method according to claim 7, further comprising: After determining the target control parameters, the correspondence between the target control parameters and the cruise speed is stored.

12. A cruise control device, comprising: The first determining unit is configured to determine multiple variable control parameters of the vehicle based on a preset optimization range of variable control parameters. The partitioning unit is configured to divide the plurality of variable control parameters into multiple populations to obtain the variable control parameters in each population. The optimization unit is configured to determine a second performance-optimal variable control parameter for each population based on the performance parameters of each variable control parameter in each population. Each population is sequentially designated as the target population. From the second optimal variable control parameters of the remaining populations excluding the target population, the third optimal variable control parameter of the target population is selected. From the second optimal variable control parameter and the third optimal variable control parameter of the target population, the first optimal variable control parameter of the target population is determined. Based on the first performance-optimal variable control parameters of each population, the variable control parameters of the corresponding population are iteratively optimized to determine the target control parameters of the vehicle. The second determining unit is configured to determine the target torque based on the target control parameters, a first speed deviation between the vehicle's cruise speed and actual speed.

13. A cruise control device, comprising: Memory; and A processor coupled to the memory, the processor being configured to execute the cruise control method of any one of claims 1 to 11 based on instructions stored in the memory.

14. A cruise control system, comprising: The cruise control device as described in claim 12 or 13; The sensor is configured to acquire and transmit the vehicle’s actual speed to the cruise control device.

15. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the cruise control method according to any one of claims 1 to 11.

16. A computer program product comprising a computer program that, when executed by a processor, implements the cruise control method of any one of claims 1 to 11.

Images