Vehicle control methods, devices, vehicle-side control equipment, readable storage media, and program products

Abstract

This application relates to a vehicle control method, apparatus, vehicle-side control device, computer-readable storage medium, and computer program product. By determining the initial self-learning acceleration corresponding to the target cycle each time the vehicle meets the target cycle, based on the acceleration during vehicle deceleration, and further determining the current self-learning acceleration, the vehicle deceleration is controlled based on the corresponding current feedback coefficient during deceleration. Compared to traditional deceleration control based on fixed-level kinetic energy recovery, this application learns the initial self-learning acceleration each time the vehicle meets the target cycle, combines several initial self-learning accelerations to determine the current self-learning acceleration, and controls the vehicle deceleration according to the current feedback coefficient corresponding to the current self-learning acceleration during deceleration. This allows the determined feedback coefficient to better match the user's driving habits through acceleration learning, thereby reducing vehicle energy consumption.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a vehicle control method, device, vehicle-side control equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] With the development of vehicle technology, intelligent energy recovery systems such as kinetic energy regeneration have become mainstream features in vehicles. Currently, kinetic energy regeneration systems in vehicles typically have a few fixed levels, switching between different intensities of energy recovery. However, based on fixed levels of kinetic energy recovery, the vehicle's deceleration intensity does not match the user's desired intensity, requiring the user to frequently and actively control the vehicle's speed, thus increasing energy consumption.

[0003] Therefore, current vehicle control methods suffer from high energy consumption. Summary of the Invention

[0004] Based on this, this application addresses the aforementioned technical problems by providing a vehicle control method, apparatus, vehicle-side control equipment, computer-readable storage medium, and computer program product that can reduce energy consumption.

[0005] In a first aspect, this application provides a vehicle control method, including:

[0006] In response to the feedback coefficient learning instruction, the vehicle deceleration within the target acceleration range is obtained during deceleration; the target acceleration range represents the acceleration range during vehicle deceleration.

[0007] Whenever the vehicle meets the target period, the original self-learning acceleration corresponding to the target period is determined based on the vehicle's acceleration within the target period; the target period includes one or more of the following: target distance period and target duration period;

[0008] The current self-learning acceleration is determined based on the original self-learning acceleration corresponding to the most recent target cycles, and the current feedback coefficient corresponding to the current self-learning acceleration is obtained according to the mapping relationship.

[0009] When the vehicle's intended movement is to decelerate, the vehicle is controlled to decelerate based on the current feedback coefficient.

[0010] Secondly, this application also provides a vehicle control device, comprising:

[0011] The acquisition module is used to acquire the acceleration of the vehicle during deceleration within a target acceleration range in response to the feedback coefficient learning instruction; the target acceleration range represents the acceleration range of the vehicle during deceleration.

[0012] The first determining module is configured to determine the original self-learning acceleration corresponding to the target period based on the acceleration of the vehicle within the target period whenever the vehicle meets the target period; the target period includes one or more of the following: target distance period and target duration period;

[0013] The second determining module is used to determine the current self-learning acceleration based on the original self-learning acceleration corresponding to the most recent target cycles, and to obtain the current feedback coefficient corresponding to the current self-learning acceleration based on the mapping relationship.

[0014] The control module is used to control the vehicle to decelerate based on the current feedback coefficient when the vehicle's driving intention is to decelerate.

[0015] Thirdly, this application also provides a vehicle-side control device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the methods described above.

[0016] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0017] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the above aspects.

[0018] The vehicle control method, apparatus, vehicle-side control equipment, computer-readable storage medium, and computer program product provided in this application determine the vehicle's acceleration within a target acceleration range during deceleration by responding to feedback coefficient learning commands. Whenever the vehicle meets a target cycle, the application determines the original self-learning acceleration corresponding to the target cycle based on the vehicle's acceleration within that cycle. It then determines the current self-learning acceleration based on the original self-learning accelerations corresponding to the most recent target cycles. When the vehicle's intended movement is deceleration, the application controls the vehicle's deceleration based on the current feedback coefficient corresponding to the current self-learning acceleration. Compared to traditional deceleration control based on fixed-level kinetic energy recovery, this application collects the vehicle's acceleration within the target acceleration range. Each time the vehicle travels a distance that meets the target cycle, it learns the original self-learning acceleration and determines the current self-learning acceleration by combining it with the most recent original self-learning accelerations. When the vehicle decelerates, it controls the deceleration according to the current feedback coefficient corresponding to the current self-learning acceleration. This acceleration learning allows the determined feedback coefficient to better match the user's driving habits, reducing the need for the user to actively control the vehicle's speed and thus lowering the vehicle's energy consumption.

[0019] Regarding the beneficial effects of any of the technical solutions in the second to fifth aspects mentioned above, refer to the beneficial effects of the corresponding technical solutions in the first aspect; repeated examples will not be listed here. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of an optional flow of a vehicle control method in one embodiment;

[0022] Figure 2 This is a schematic diagram of an optional flow of the vehicle control method in another embodiment;

[0023] Figure 3 This is a schematic diagram of an optional structure of the vehicle control device in one embodiment;

[0024] Figure 4 This is a schematic diagram of an optional internal structure of the vehicle-side control device in one embodiment. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of this application.

[0026] The terms "first," "second," etc., used in this application may be used to describe various elements, but these elements are not limited by these terms. These terms are used only to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0027] In related technologies, intelligent feedback systems such as kinetic energy recovery have become mainstream vehicle configurations. Currently, most vehicles offer only three levels of energy recovery, limiting user choices. Furthermore, the feedback levels in vehicles on the market do not match actual user behavior, leading to the following problems: if the feedback level is lower than the user's actual driving behavior, the user will frequently brake, resulting in energy waste and increased fatigue; if the feedback level is higher than the user's actual driving behavior, it can cause motion sickness for passengers.

[0028] Based on this, this application introduces intelligent feedback coefficient learning and implements a feedback factor (feedback coefficient) with infinitely adjustable feedback levels. By collecting the vehicle's acceleration within the target acceleration range, the application learns the original self-learning acceleration each time the vehicle travels a distance that meets the target cycle. Combining this with the most recent original self-learning accelerations, the application determines the current self-learning acceleration. When the vehicle decelerates, it controls the deceleration according to the current feedback coefficient corresponding to the current self-learning acceleration. Thus, through acceleration learning, the determined feedback coefficient is made more in line with the user's driving habits, reducing the need for the user to actively control the vehicle speed and thereby reducing the vehicle's energy consumption.

[0029] In one embodiment, such as Figure 1 As shown, a vehicle control method is provided. This embodiment illustrates the application of this method to a vehicle control unit. It is understood that this method can also be applied to a server, and further to a system including a vehicle control unit and a server, and is implemented through the interaction between the vehicle control unit and the server, including the following steps S201 to S204. Wherein:

[0030] Step S201: In response to the feedback coefficient learning instruction, obtain the acceleration of the vehicle during deceleration within the target acceleration range; the target acceleration range represents the acceleration range during vehicle deceleration.

[0031] The aforementioned vehicles can be four-wheeled vehicles, such as new energy vehicles equipped with kinetic energy recovery systems. The principle of kinetic energy recovery is that when an electric vehicle decelerates or brakes, the motor reverses direction to convert kinetic energy into electrical energy, which is then stored back in the battery. Different kinetic energy recovery intensities can be set, each corresponding to a different feedback coefficient. For example, a larger feedback coefficient results in a greater acceleration when the user releases the brake or the vehicle decelerates, meaning the vehicle decelerates faster; conversely, a smaller feedback coefficient results in a smaller acceleration when the user releases the brake or the vehicle decelerates, meaning the vehicle decelerates more slowly.

[0032] Different users have different preferences for the intensity of regenerative braking when driving a vehicle; some users prefer a higher intensity, while others prefer a lower intensity. When the intensity of braking does not match the user's preference, the user will actively intervene in the vehicle's deceleration control to match the deceleration force with their preference. Therefore, the vehicle control unit can self-learn the feedback coefficient to ensure that the intensity of regenerative braking matches the user's preference when using the self-learned feedback coefficient.

[0033] The vehicle control unit can set learning options on the vehicle's display device, such as displaying a feedback coefficient learning button. Users can trigger the learning option to initiate a learning command for the feedback coefficients. Responding to the feedback coefficient learning command, the vehicle control unit can initiate the learning process for the feedback coefficients. The vehicle control unit can self-learn the vehicle's feedback coefficients while the vehicle is in motion. For example, the vehicle control unit can acquire the vehicle's acceleration during deceleration. This acceleration can be within a target acceleration range. The target acceleration range can be a pre-set acceleration range corresponding to the vehicle's deceleration, where the direction of acceleration within this range is opposite to the vehicle's direction of travel.

[0034] The target acceleration range mentioned above can be set according to actual conditions. The target acceleration range can be an acceleration range that allows the electric motor braking system to independently complete the deceleration task. When the deceleration demand is less than the maximum value of the target acceleration range, the system can recover energy simply by generating braking force through motor reversal. However, when the deceleration demand exceeds the maximum value of the target acceleration range, it means the driver has a stronger intention to decelerate, and the electric motor alone cannot meet the demand. A mechanical friction braking system must be introduced to provide sufficient braking force to ensure driving safety. Therefore, setting the target acceleration range for feedback coefficient self-learning is the core operating condition area for energy recovery in pure electric motor braking mode, independent of the mechanical braking system, and suitable for self-learning algorithms.

[0035] Step S202: Whenever the vehicle meets the target period, determine the original self-learning acceleration corresponding to the target period based on the vehicle's acceleration within the target period; the target period includes one or more of the following: target distance period and target duration period.

[0036] To ensure the timeliness of the feedback coefficients from self-learning, the vehicle control unit can learn the vehicle's acceleration during deceleration on a cyclical basis. The target cycle can include one or more of a target distance cycle and a target duration cycle. The target distance cycle can be based on the distance traveled by the vehicle, and the target duration cycle can be based on the duration of travel. The cycle can be repeated based on parameters such as the distance and duration of travel.

[0037] Taking the target distance period as an example, whenever the vehicle travels the distance corresponding to the target distance period (e.g., every 1 km), the vehicle control unit can acquire the acceleration generated by the vehicle within the target acceleration range during the target distance period. Therefore, the vehicle control unit can determine the original self-learning acceleration corresponding to the target distance period based on the various accelerations within that period. In other words, the original self-learning acceleration corresponds to the target distance period. When the vehicle travels multiple target distance periods, the vehicle control unit can generate multiple original self-learning accelerations.

[0038] Taking the target duration period as an example, whenever the vehicle travels for the duration corresponding to the target duration period (e.g., every hour the vehicle travels), the vehicle control unit can acquire the acceleration generated by the vehicle within the target acceleration range during the target duration period. Therefore, the vehicle control unit can determine the original self-learning acceleration corresponding to the target duration period based on each acceleration within that period. In other words, the original self-learning acceleration corresponds to the target duration period. When the vehicle travels a distance equivalent to multiple target duration periods, the vehicle control unit can generate multiple original self-learning accelerations.

[0039] The original self-learning acceleration represents the self-learning acceleration statistically obtained within a single target period (target distance period / target duration period) when the vehicle decelerates during kinetic energy recovery (including deceleration due to kinetic energy recovery and deceleration actively intervened by the user during kinetic energy recovery). The vehicle control unit can statistically analyze each acceleration within the target acceleration range within the target period to obtain the original self-learning acceleration corresponding to the target period.

[0040] When the target period is the target distance period, the vehicle control unit can determine whether the target distance period is met based on the vehicle's speed signal. Specifically, after the vehicle control unit detects that intelligent feedback coefficient learning has been activated and triggers the feedback coefficient learning command, the vehicle control unit can integrate the vehicle's speed signal and determine the distance traveled based on the integrated speed signal. Whenever the vehicle travels the distance corresponding to the target distance period, the vehicle control unit can reset the integration, send a reset signal MailRst, and determine the original self-learning acceleration for the current target distance period.

[0041] Step S203: Determine the current self-learning acceleration based on the original self-learning acceleration corresponding to the most recent target cycles, and obtain the current feedback coefficient corresponding to the current self-learning acceleration based on the mapping relationship.

[0042] The vehicle control unit can analyze the raw self-learning acceleration corresponding to multiple target periods to determine a more accurate self-learning acceleration. To ensure that the self-learning acceleration aligns with the user's latest preferences, the vehicle control unit can acquire the raw self-learning acceleration corresponding to the most recent target periods. "Most recent" refers to a historical time period starting from the current time. The vehicle control unit can set the number of raw self-learning accelerations participating in the statistical analysis, for example, setting it to acquire a certain number of recent target periods. The specific number of recent target periods can be set according to actual needs. The vehicle control unit acquires the raw self-learning acceleration corresponding to the most recent number of target periods, and then performs self-learning on these raw self-learning accelerations to obtain a more accurate current self-learning acceleration.

[0043] The vehicle control unit also maintains a mapping relationship between self-learning acceleration and feedback coefficients. The feedback coefficient represents the intensity of kinetic energy recovery. The vehicle control unit can pre-set the mapping relationship between self-learning acceleration and feedback coefficients so that when the vehicle control unit learns the corresponding current self-learning acceleration, it can determine the current feedback coefficient corresponding to the current self-learning acceleration through the mapping relationship. This ensures that the kinetic energy recovery intensity corresponding to the current feedback coefficient matches the user's deceleration preferences when driving the vehicle, reducing the need for the user to actively control the vehicle speed during deceleration.

[0044] Step S204: When the vehicle's driving intention is to decelerate, control the vehicle to decelerate according to the aforementioned current feedback coefficient.

[0045] Once the vehicle control unit learns the corresponding current feedback coefficient, it can set the intensity of kinetic energy recovery according to this coefficient. Therefore, when the vehicle's intended movement is deceleration (e.g., entering kinetic energy recovery mode), the vehicle control unit controls the vehicle to decelerate and recover kinetic energy according to the current feedback coefficient. This current feedback coefficient can be updated over time, based on the updated self-learned acceleration, thus matching the user's latest driving preferences.

[0046] In the aforementioned vehicle control method, by responding to feedback coefficient learning commands, the vehicle's acceleration within the target acceleration range during deceleration is determined. Whenever the vehicle meets the target cycle, the original self-learning acceleration corresponding to the target cycle is determined based on the vehicle's acceleration within the target cycle. The current self-learning acceleration is determined based on the original self-learning accelerations corresponding to the most recent target cycles. When the vehicle's driving intention is deceleration, the vehicle deceleration is controlled based on the current feedback coefficient corresponding to the current self-learning acceleration. Compared to traditional deceleration control based on fixed-level kinetic energy recovery, this application collects the vehicle's acceleration within the target acceleration range. Each time the vehicle meets the target cycle, it learns the original self-learning acceleration and, combined with the most recent original self-learning accelerations, determines the current self-learning acceleration. When the vehicle decelerates, it controls the deceleration according to the current feedback coefficient corresponding to the current self-learning acceleration. This allows the determined feedback coefficient to better match the user's driving habits through acceleration learning, reducing the need for the user to actively control the vehicle speed and thus lowering the vehicle's energy consumption.

[0047] In one embodiment, determining the original self-learning acceleration corresponding to the target period based on the vehicle's acceleration within the target period includes: dividing the target acceleration interval according to a preset interval to obtain each target acceleration sub-interval corresponding to the target acceleration interval; and determining the original self-learning acceleration corresponding to the target period based on each acceleration located in each of the target acceleration sub-intervals within the target period.

[0048] In this embodiment, the vehicle control unit collects acceleration data within the target acceleration range during vehicle deceleration. This allows the vehicle control unit to determine the initial self-learning acceleration based on the collected acceleration data. The learning of this initial self-learning acceleration can be performed in units of a target period. Whenever the vehicle meets a target period (e.g., a target distance period or a target duration period), the vehicle control unit learns the initial self-learning acceleration corresponding to that target period. The target acceleration range covers a relatively large range of accelerations. The vehicle control unit can segment the target acceleration range to determine the initial self-learning acceleration from a more granular perspective.

[0049] The vehicle control unit can divide the target acceleration interval into multiple target acceleration sub-intervals according to a preset interval. Each acceleration within the target acceleration interval can fall within a different target acceleration sub-interval. The vehicle control unit can then determine the original self-learning acceleration corresponding to the target period based on the accelerations located within each of these target acceleration sub-intervals within the target period. For example, different target acceleration sub-intervals may have different levels of importance. The vehicle control unit determines the original self-learning acceleration based on the importance of the target acceleration sub-interval in which the acceleration is located. The importance level indicates the contribution of the acceleration to the original self-learning acceleration.

[0050] Specifically, when determining the initial self-learning acceleration, the vehicle control unit can segment and statistically analyze the target acceleration range of the vehicle, and determine the initial self-learning acceleration of the vehicle through contribution calculation. The vehicle control unit performs differential calculations using the vehicle speed signal, such as a = v / t represents the acceleration during vehicle deceleration. Here, a represents acceleration, v represents the vehicle speed signal, and t represents the sampling period, as described above (target period). The vehicle control unit can also acquire the acceleration output by the inertial measurement unit (IMU) during vehicle deceleration and determine the acceleration within the target acceleration range. Taking the target acceleration range as 0-0.2g during vehicle deceleration as an example, the vehicle control unit segments the 0-0.2g acceleration range, for example, using a preset interval of 0.02g, thus dividing the 0-0.2g acceleration range into ten target acceleration sub-ranges. The vehicle control unit analyzes each acceleration and determines the acceleration occurring in each target acceleration sub-range, denoted as C. x , where C x This represents the acceleration that occurs within the target acceleration sub-interval x. For example, the reporter's velocity occurring within the target acceleration sub-interval of 0-0.02g can be denoted as C. 0.02 Therefore, the vehicle control unit can combine the accelerations of each target acceleration sub-interval to determine the original self-learning acceleration corresponding to the target period.

[0051] In this embodiment, the vehicle control unit can segment the target acceleration range, and based on each target acceleration sub-range and each acceleration obtained after segmentation, learn the original self-learning acceleration, thereby improving the matching degree between the learned acceleration and the user's acceleration preference during deceleration.

[0052] In one embodiment, determining the original self-learning acceleration corresponding to the target period based on the accelerations located in each of the target acceleration sub-intervals within the target period includes: for each of the target acceleration sub-intervals, determining the weight corresponding to the target acceleration sub-interval based on the acceleration corresponding to the target acceleration sub-interval and the target vehicle speed; the target vehicle speed representing the vehicle speed when the acceleration is generated; and determining the original self-learning acceleration corresponding to the target period based on the weights corresponding to each of the target acceleration sub-intervals and the accelerations.

[0053] In this embodiment, the vehicle control unit can determine the original self-learning acceleration based on the segmented target acceleration sub-intervals and the accelerations located within each target acceleration sub-interval. Specifically, for each segmented target acceleration sub-interval, the vehicle control unit can determine the weight of that sub-interval, i.e., the contribution of the accelerations within that sub-interval to the original self-learning acceleration. When determining the weight, the vehicle control unit can obtain the vehicle speed at which the acceleration corresponding to the target acceleration sub-interval is generated, as the target vehicle speed, for example, the instantaneous speed of the vehicle at the time the acceleration is generated. Therefore, the vehicle control unit can determine the weight corresponding to the target acceleration sub-interval based on the accelerations corresponding to the target acceleration sub-intervals and the aforementioned target vehicle speed.

[0054] The target acceleration interval includes multiple target acceleration sub-intervals. For each target acceleration sub-interval containing acceleration, the vehicle control unit can determine the weight of each target acceleration sub-interval. Thus, the vehicle control unit can determine the original self-learning acceleration corresponding to the target period based on the weights corresponding to each of the above-mentioned target acceleration sub-intervals and each of the above-mentioned accelerations.

[0055] Specifically, the acceleration in each of the above target acceleration sub-intervals can be denoted as C. x The vehicle control unit determines the self-learning contribution (weight) i for each target acceleration sub-interval. x , where i x=f(x,y)=αxy+β. x represents vehicle speed, y represents vehicle acceleration during deceleration, α represents the adjustment coefficient for vehicle speed and acceleration, and β represents the weight adjustment coefficient. β can be a preset small value to ensure a small contribution even at low vehicle speeds and low accelerations. The vehicle control unit can calibrate this weight on a real vehicle to obtain the above relationship. The weight for each target acceleration sub-interval can be different; for example, the weight for the 0-0.02g interval is i. 0.02 =0.01g. The vehicle control unit can combine various weights and accelerations to determine the original self-learning acceleration. Specifically, it can be expressed as: DeccRaw = ∑(C x *i x ) / ∑C x Where DeccRaw represents the original self-learning acceleration, and C... x Let i represent the acceleration of the target acceleration subinterval x. x This represents the weight of the target acceleration sub-interval x. The vehicle control unit can generate the original self-learning acceleration in units of the target period. When the vehicle meets the target period, the vehicle control unit sends a reset signal MailRst==1, indicating that the target period has been met. The vehicle control unit then determines the original self-learning acceleration within this target period and, after determination, sets C... x Reset to zero to perform acceleration acquisition for the next target cycle.

[0056] Through this embodiment, the vehicle control unit can combine the acceleration of each target acceleration sub-interval and the weight of each target acceleration sub-interval to determine the original self-learning acceleration within the target period, thereby improving the matching degree between the original self-learning acceleration and the acceleration when the user decelerates.

[0057] In one embodiment, determining the current self-learning acceleration based on the raw self-learning acceleration corresponding to the most recent target cycles includes: whenever the vehicle meets the target storage conditions, storing the raw self-learning acceleration corresponding to the target cycle into a target array; the target array includes the raw self-learning acceleration corresponding to the most recent target cycles; determining the current self-learning acceleration based on each of the raw self-learning accelerations in the target array; the target storage conditions include one or more of the following: whenever the vehicle travels the distance corresponding to the target distance cycle, whenever the vehicle travels the duration corresponding to the target duration cycle.

[0058] In this embodiment, the vehicle control unit can collect multiple raw self-learning accelerations through multiple target periods. The raw self-learning accelerations for each target period can be stored in a target array. The vehicle control unit stores the raw self-learning accelerations when it detects that the target storage conditions are met. For example, when the target period is a target distance period, the vehicle control unit stores the raw self-learning acceleration whenever it detects the distance corresponding to the target distance period; when the target period is a target duration period, the vehicle control unit stores the raw self-learning acceleration whenever it detects the duration corresponding to the target duration period. The target array can be a pre-set array of a predetermined size, used to store the raw self-learning accelerations. The vehicle control unit can store the raw self-learning accelerations in the target array according to the order in which they were acquired. For example, the earlier the original self-learning acceleration is acquired, the later it is stored in the target array. When a new original self-learning acceleration is stored in the target array, the vehicle control unit can store the new acceleration at the beginning of the array and shift all existing accelerations one position to the right to make room for the newest acceleration. When there is no space in the target array to store the newest acceleration, the vehicle control unit can remove the oldest acceleration stored in the array to ensure the timeliness of the original self-learning acceleration in the target array.

[0059] The vehicle control unit can determine the current self-learning acceleration based on the various original self-learning accelerations in the target array. The current self-learning acceleration can be obtained by statistically analyzing several recent original self-learning accelerations, in order to more accurately match the user's acceleration preferences when decelerating the vehicle.

[0060] Specifically, the vehicle control unit can obtain the current self-learning acceleration by performing a rolling average of the original self-learning acceleration. To ensure that the calculated self-learning deceleration reflects recent user preferences, the vehicle control unit can determine the current self-learning acceleration using a rolling average algorithm. The vehicle control unit can design two arrays to store the original self-learning acceleration, with the array dimension j, for example, a dimension of 10 (this value can be adjusted based on the actual vehicle performance), indicating that 10 original self-learning accelerations can be stored. When the vehicle control unit receives the reset signal MailRst==1, indicating that the vehicle meets the target cycle, the vehicle control unit stores the value of the original self-learning acceleration ArryNew[0] once in the target array Arrynew, and discards the last data in the target array, i.e., Arrynew[8]=Arryold[9]. After the above storage is completed, the vehicle control unit uses the updated target array as Arryold=Arrynew; thus, the current self-learning deceleration can be expressed as: DeccStudy=∑Arryold / j. Here, j represents the dimension of the target array, and DeccStudy represents the current self-learning acceleration. After determining the current self-learning acceleration, the vehicle control unit can determine the corresponding feedback coefficient based on a mapping relationship. Since the vehicle's deceleration acceleration during kinetic energy recovery is between 0-0.2g, the mapping relationship can be expressed as follows: a self-learning acceleration of 0 corresponds to a feedback coefficient of 0; a self-learning acceleration of 0.05g corresponds to a feedback coefficient of 0.25; a self-learning acceleration of 0.1g corresponds to a feedback coefficient of 0.5; a self-learning acceleration of 0.15g corresponds to a feedback coefficient of 0.7; and a self-learning acceleration of 0.2g corresponds to a feedback coefficient of 1. That is, the larger the self-learning acceleration, the larger the corresponding feedback coefficient, indicating a positive correlation between the self-learning acceleration and the feedback coefficient. A larger feedback coefficient results in a greater deceleration force during kinetic energy recovery. This mapping relationship can be adjusted based on actual vehicle performance.

[0061] In this embodiment, the vehicle control unit can combine multiple recent original self-learning accelerations and determine the current self-learning acceleration through a rolling average method, so that the determined current self-learning acceleration matches the acceleration preference of the user when driving the vehicle to decelerate, thereby reducing the increase in energy consumption caused by the user's active intervention in vehicle speed control.

[0062] In one embodiment, when the vehicle's driving intention is to decelerate, controlling the vehicle to decelerate based on the aforementioned current feedback coefficient includes: determining the current required torque corresponding to the vehicle based on the vehicle's pedal opening; if the aforementioned current required torque is less than zero, determining that the vehicle's driving intention is to decelerate; and determining the current torque output by the vehicle based on the aforementioned current feedback coefficient and the aforementioned current required torque to control the vehicle to decelerate.

[0063] In this embodiment, after determining the corresponding current feedback coefficient, the vehicle control unit can control the vehicle to decelerate based on the current feedback coefficient. This deceleration can be in scenarios such as kinetic energy recovery. The vehicle control unit can detect the accelerator pedal opening and determine the vehicle's current torque requirement based on the pedal opening. The current torque requirement represents the torque the vehicle needs to output based on the pedal opening. If the current torque requirement is less than zero, it indicates that the vehicle needs to decelerate. The vehicle control unit can then determine the vehicle's driving intention as deceleration, and thus, based on the current feedback coefficient and the current torque requirement, determine the current torque output by the vehicle, thereby controlling the vehicle to decelerate according to the user's preferred deceleration intensity.

[0064] Specifically, the vehicle control unit adjusts the current required torque PedalMapTq corresponding to the pedal opening based on the current feedback coefficient, achieving closed-loop control of the vehicle feedback coefficient. When the vehicle control unit detects that the current required torque PedalMapTq is less than zero based on the pedal opening, it can determine the requested torque (current torque) of the vehicle motor by combining the vehicle's current feedback coefficient. This can be expressed as: TqReq = PedalMapTq * RgnFactor, where TqReq represents the current torque and RgnFactor represents the current feedback coefficient.

[0065] Through this embodiment, the vehicle control unit can combine the current feedback coefficient to correct the current required torque when the vehicle intends to decelerate, thereby outputting torque that matches the user's deceleration preference during deceleration, reducing the user's active intervention control during vehicle deceleration and lowering the vehicle's energy consumption.

[0066] In one embodiment, in response to a feedback coefficient learning instruction, obtaining the acceleration of the vehicle during deceleration within a target acceleration range includes: in response to a feedback coefficient learning instruction, obtaining the current gear and current speed of the vehicle; if the current gear is a target gear and the current speed is greater than a speed threshold, then obtaining the acceleration of the vehicle during deceleration within the target acceleration range; the target gear represents the gear that enables the vehicle to move.

[0067] In this embodiment, the vehicle control unit can learn the feedback coefficient only under specific conditions. After detecting that the feedback coefficient learning command has been triggered, the vehicle control unit can obtain the vehicle's current gear and current speed. The vehicle control unit detects the current gear and current speed, checking if the current gear is the target gear and if the current speed is greater than a speed threshold. The target gear refers to the gear the vehicle is in while driving, such as forward or reverse. If the vehicle control unit detects that the current gear is not the target gear, or the current speed is less than or equal to the speed threshold, the vehicle control unit can determine that the vehicle does not meet the feedback coefficient learning conditions. In this case, the vehicle control unit can output a prompt message indicating that the feedback coefficient learning conditions are not met, prompting the user to make corrections. If the vehicle control unit detects that the current gear is the target gear and the current speed is greater than the speed threshold, the vehicle control unit can determine that the current state meets the conditions for feedback coefficient self-learning. In this case, the vehicle control unit can determine to initiate self-learning of the feedback coefficient and obtain the vehicle's acceleration within the target acceleration range during deceleration.

[0068] Specifically, the vehicle control unit can display a feedback coefficient learning switch on the vehicle's display device. After the user turns on the feedback coefficient learning switch on the display device, the vehicle control unit determines that the feedback coefficient learning command has been triggered. The vehicle control unit can obtain information such as the vehicle's current speed and current gear. When the following conditions are met, the vehicle control unit determines to start the self-learning of the feedback coefficient: the feedback coefficient learning switch is turned on, the current vehicle gear is in D (forward) / R (reverse) gear, and the vehicle speed is greater than 5 kph (kilometers per hour, vehicle speed threshold).

[0069] In this embodiment, the vehicle control unit can determine whether the vehicle meets the conditions for self-learning of the feedback coefficient based on the vehicle's current speed and gear. Only when the conditions are met will the self-learning of the feedback coefficient be performed, thereby improving the accuracy of the learned feedback coefficient.

[0070] In one exemplary embodiment, such as Figure 2 As shown, Figure 2 This is a schematic diagram of an optional flow of a vehicle control method in another embodiment. This embodiment includes the following steps:

[0071] The vehicle control unit can display the feedback coefficient learning switch on the vehicle's display device. After the user turns on the feedback coefficient learning switch on the display device, the vehicle control unit determines that the feedback coefficient learning command has been triggered. The vehicle control unit can obtain information such as the vehicle's current speed and current gear. When the following conditions are met, the vehicle control unit determines to start the self-learning of the feedback coefficient: the feedback coefficient learning switch is turned on, the current vehicle gear is D (forward) / R (reverse), and the vehicle speed is greater than 5 kph (kilometers per hour, vehicle speed threshold).

[0072] When the vehicle control unit detects that intelligent feedback coefficient learning has been activated and triggers the feedback coefficient learning command, taking the target period as the target distance period as an example, the vehicle control unit can integrate the vehicle speed signal and determine the distance traveled based on the integrated speed signal. Whenever the vehicle travels the distance corresponding to the target distance period, the vehicle control unit can reset the integration, send a reset signal MailRst, and determine the original self-learning acceleration for the current target distance period. Taking the target period as the target duration period as an example, the vehicle control unit can accumulate the vehicle's travel time from the last time the duration period was met to the current time. Whenever the vehicle travels the duration corresponding to the target duration period, the vehicle control unit can reset the integration, send a reset signal MailRst, and determine the original self-learning acceleration for the current target duration period.

[0073] When determining the initial self-learning acceleration, the vehicle control unit can segment and statistically analyze the target acceleration range of the vehicle, and determine the initial self-learning acceleration of the vehicle through contribution calculation. Specifically, the vehicle control unit performs differential calculations using the vehicle speed signal, such as a = v / The vehicle control unit obtains the acceleration during vehicle deceleration, where a represents acceleration, v represents vehicle speed signal, and t represents sampling period, as described above (target period). The vehicle control unit can also acquire the acceleration output by the inertial measurement unit (IMU) during vehicle deceleration and determine the acceleration within the target acceleration range. Taking the target acceleration range as 0-0.2g during vehicle deceleration as an example, the vehicle control unit segments the 0-0.2g acceleration range, for example, using a preset interval of 0.02g, thus dividing the 0-0.2g acceleration range into ten target acceleration sub-ranges. The vehicle control unit analyzes each acceleration and determines the acceleration appearing in each target acceleration sub-range, denoted as Cx, where Cx represents the acceleration appearing in the target acceleration sub-range x. For example, the speed of a reporter appearing in the 0-0.02g target acceleration sub-range can be denoted as Cx. 0.02Therefore, the vehicle control unit can combine the accelerations of each target acceleration sub-interval to determine the original self-learning acceleration corresponding to the target period.

[0074] The vehicle control unit determines the self-learning contribution (weight) i for each target acceleration sub-interval. x , where i x =f(x,y)=αxy+β. x represents vehicle speed, y represents vehicle acceleration during deceleration, α represents the adjustment coefficient for vehicle speed and acceleration, and β represents the weight adjustment coefficient. β can be a preset small value to ensure a small contribution even at low vehicle speeds and low accelerations. The vehicle control unit can calibrate this weight on a real vehicle to obtain the above relationship. The weight for each target acceleration sub-interval can be different; for example, the weight for the 0-0.02g interval is i. 0.02 =0.01g. The vehicle control unit can determine the original self-learning acceleration by combining various weights and accelerations. Specifically, it can be expressed as: DeccRaw = ∑(C x *i x ) / ∑C x Where DeccRaw represents the original self-learning acceleration, and C... x Let i represent the acceleration of the target acceleration subinterval x. x This represents the weight of the target acceleration sub-interval x. The vehicle control unit can generate the original self-learning acceleration in units of the target period. When the vehicle meets the target period (e.g., whenever the vehicle travels the target distance period, or whenever the vehicle travels the target duration period), the vehicle control unit sends a reset signal MailRst==1, indicating that the target period is met. Based on the determination of the original self-learning acceleration within the current target period, the vehicle control unit then sets C... x Reset to zero to perform acceleration acquisition for the next target period.

[0075] The vehicle control unit can obtain the current self-learning acceleration by performing a rolling average of the original self-learning acceleration. To ensure that the calculated self-learning deceleration reflects recent user preferences, the vehicle control unit can determine the current self-learning acceleration using a rolling average algorithm. The vehicle control unit can design two arrays to store the original self-learning acceleration, with the array dimension j. For example, the dimension can be 10 (this value can be adjusted based on the actual vehicle performance), indicating that 10 original self-learning accelerations can be stored. When the vehicle control unit receives the reset signal MailRst==1, indicating that the vehicle meets the target cycle, the vehicle control unit stores the value of the original self-learning acceleration ArryNew[0] in the target array Arrynew and discards the last data in the target array, i.e., Arrynew[8]=Arryold[9]. After the above storage is completed, the vehicle control unit uses the updated target array as Arryold=Arrynew; thus, the current self-learning deceleration can be expressed as: DeccStudy=∑Arryold / j. Here, j represents the dimension of the target array, and DeccStudy represents the current self-learning acceleration. After determining the current self-learning acceleration, the vehicle control unit can determine the corresponding feedback coefficient based on a mapping relationship. Since the vehicle's deceleration acceleration during kinetic energy recovery is between 0-0.2g, the mapping relationship can be expressed as follows: a self-learning acceleration of 0 corresponds to a feedback coefficient of 0; a self-learning acceleration of 0.05g corresponds to a feedback coefficient of 0.25; a self-learning acceleration of 0.1g corresponds to a feedback coefficient of 0.5; a self-learning acceleration of 0.15g corresponds to a feedback coefficient of 0.7; and a self-learning acceleration of 0.2g corresponds to a feedback coefficient of 1. That is, the larger the self-learning acceleration, the larger the corresponding feedback coefficient, indicating a positive correlation between the self-learning acceleration and the feedback coefficient. A larger feedback coefficient results in a greater deceleration force during kinetic energy recovery. This mapping relationship can be adjusted based on actual vehicle performance.

[0076] Through the above embodiments, by collecting the vehicle's acceleration within the target acceleration range, and learning the initial self-learning acceleration each time the vehicle travels a distance that meets the target cycle, and combining this with several recent initial self-learning accelerations, the current self-learning acceleration is determined. When the vehicle decelerates, the current feedback coefficient corresponding to the current self-learning acceleration is used to control the vehicle's deceleration. This acceleration learning allows the determined feedback coefficient to better match the user's driving habits, reducing the need for the user to actively control the vehicle's speed and thus reducing energy consumption. Furthermore, by matching the feedback coefficient during kinetic energy recovery deceleration to the user's actual driving behavior, the user will reduce the frequency of braking, leading to lower energy consumption and reduced fatigue. Matching the feedback coefficient to the user's actual driving behavior can also reduce motion sickness.

[0077] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0078] Based on the same inventive concept, this application also provides a vehicle control device for implementing the vehicle control method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more vehicle control device embodiments provided below can be found in the limitations of the vehicle control method described above, and will not be repeated here.

[0079] In one exemplary embodiment, such as Figure 3 As shown, a vehicle control device is provided, including: an acquisition module 500, a first determination module 501, a second determination module 502, and a control module 503, wherein:

[0080] The acquisition module 500 is used to acquire the acceleration of the vehicle during deceleration within the target acceleration range in response to the feedback coefficient learning instruction; the target acceleration range represents the acceleration range of the vehicle during deceleration.

[0081] The first determining module 501 is used to determine the original self-learning acceleration corresponding to the target period based on the acceleration of the vehicle within the target period whenever the vehicle meets the target period; the target period includes one or more of the following: target distance period and target duration period.

[0082] The second determining module 502 is used to determine the current self-learning acceleration based on the original self-learning acceleration corresponding to the most recent target cycles, and to obtain the current feedback coefficient corresponding to the current self-learning acceleration based on the mapping relationship.

[0083] The control module 503 is used to control the vehicle to decelerate according to the current feedback coefficient when the vehicle's driving intention is to decelerate.

[0084] In one embodiment, the first determining module 501 is configured to divide the target acceleration interval according to a preset interval to obtain each target acceleration sub-interval corresponding to the target acceleration interval; and to determine the original self-learning acceleration corresponding to the target period according to each of the accelerations located in each of the target acceleration sub-intervals within the target period.

[0085] In one embodiment, the first determining module 501 is configured to determine the weight corresponding to each of the target acceleration sub-intervals based on the acceleration corresponding to the target acceleration sub-interval and the target vehicle speed; the target vehicle speed represents the vehicle speed when the acceleration is generated; and determine the original self-learning acceleration corresponding to the target period based on the weight corresponding to each of the target acceleration sub-intervals and each of the accelerations.

[0086] In one embodiment, the second determining module 502 is configured to store the original self-learning acceleration corresponding to the target period into a target array whenever the vehicle meets the target storage conditions; the target array includes the original self-learning acceleration corresponding to the most recent target periods; and determine the current self-learning acceleration based on each of the original self-learning accelerations in the target array; the target storage conditions include one or more of the following: whenever the vehicle travels the distance corresponding to the target distance period, whenever the vehicle travels the duration corresponding to the target duration period.

[0087] In one embodiment, the control module 503 is used to determine the current required torque of the vehicle based on the pedal opening of the vehicle; if the current required torque is less than zero, it is determined that the vehicle's driving intention is to decelerate; and based on the current feedback coefficient and the current required torque, it determines the current torque output by the vehicle to control the vehicle to decelerate.

[0088] In one embodiment, the acquisition module 500 is used to acquire the current gear and current speed of the vehicle in response to the feedback coefficient learning instruction; if the current gear is the target gear and the current speed is greater than the speed threshold, then the acceleration of the vehicle during deceleration within the target acceleration range is acquired; the target gear represents the gear that enables the vehicle to move.

[0089] Each module in the aforementioned vehicle control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the vehicle-side control device in hardware form or independent of it, or stored in the memory of the vehicle-side control device in software form, so that the processor can call and execute the corresponding operations of each module.

[0090] In one exemplary embodiment, a vehicle-side control device is provided, the internal structure of which can be shown in the following diagram. Figure 4 As shown, the vehicle-mounted control device includes a processor and a memory. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium storing a computer program. When executed by the processor, the computer program implements a vehicle control method.

[0091] Those skilled in the art will understand that Figure 4 The structure shown is a block diagram of a portion of the structure related to the solution of this application, and does not constitute a limitation on the vehicle-side control device to which the solution of this application is applied. The specific vehicle-side control device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0092] In one exemplary embodiment, a vehicle-mounted control device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0093] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0094] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0095] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0096] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program mentioned can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0097] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0098] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A vehicle control method, characterized in that, The method includes: In response to the feedback coefficient learning instruction, the vehicle deceleration within the target acceleration range is obtained during deceleration; the target acceleration range represents the acceleration range during vehicle deceleration. Whenever the vehicle meets the target period, the original self-learning acceleration corresponding to the target period is determined based on the vehicle's acceleration within the target period; the target period includes one or more of the following: target distance period and target duration period; The current self-learning acceleration is determined based on the original self-learning acceleration corresponding to the most recent target cycles, and the current feedback coefficient corresponding to the current self-learning acceleration is obtained according to the mapping relationship. When the vehicle's intended movement is to decelerate, the vehicle is controlled to decelerate based on the current feedback coefficient.

2. The method according to claim 1, characterized in that, Determining the original self-learning acceleration corresponding to the target period based on the vehicle's acceleration within the target period includes: The target acceleration interval is divided according to a preset interval to obtain each target acceleration sub-interval corresponding to the target acceleration interval; The original self-learning acceleration corresponding to the target period is determined based on the accelerations located in each of the target acceleration sub-intervals within the target period.

3. The method according to claim 2, characterized in that, The step of determining the original self-learning acceleration corresponding to the target period based on each of the accelerations located in each of the target acceleration sub-intervals within the target period includes: For each target acceleration sub-interval, a weight corresponding to the target acceleration sub-interval is determined based on the acceleration corresponding to the target acceleration sub-interval and the target vehicle speed; the target vehicle speed represents the vehicle speed when the acceleration is generated. Based on the weights corresponding to each of the target acceleration sub-intervals and each of the accelerations, the original self-learning acceleration corresponding to the target period is determined.

4. The method according to claim 1, characterized in that, The step of determining the current self-learning acceleration based on the original self-learning acceleration corresponding to the most recent target cycles includes: Whenever the vehicle meets the target storage conditions, the original self-learning acceleration corresponding to the target period is stored in the target array; the target array includes the original self-learning acceleration corresponding to the most recent target periods; the target storage conditions include one or more of the following: whenever the vehicle travels the distance corresponding to the target distance period, whenever the vehicle travels the duration corresponding to the target duration period; The current self-learning acceleration is determined based on each of the original self-learning accelerations in the target array.

5. The method according to claim 1, characterized in that, When the vehicle's intended movement is to decelerate, controlling the vehicle to decelerate based on the current feedback coefficient includes: Based on the pedal opening of the vehicle, determine the current required torque for the vehicle. If the current required torque is less than zero, then the vehicle's driving intention is determined to be deceleration; Based on the current feedback coefficient and the current required torque, the current torque output by the vehicle is determined to control the vehicle to decelerate.

6. The method according to any one of claims 1 to 5, characterized in that, The step of responding to the feedback coefficient learning instruction to obtain the vehicle's acceleration within the target acceleration range during deceleration includes: In response to the feedback coefficient learning instruction, the current gear and current speed of the vehicle are obtained; If the current gear is the target gear and the current vehicle speed is greater than the vehicle speed threshold, then the acceleration of the vehicle during deceleration within the target acceleration range is obtained; the target gear represents the gear that enables the vehicle to move.

7. A vehicle control device, characterized in that, The device includes: The acquisition module is used to acquire the acceleration of the vehicle during deceleration within a target acceleration range in response to the feedback coefficient learning instruction; the target acceleration range represents the acceleration range of the vehicle during deceleration. The first determining module is configured to determine the original self-learning acceleration corresponding to the target period based on the acceleration of the vehicle within the target period whenever the vehicle meets the target period; the target period includes one or more of the following: target distance period and target duration period; The second determining module is used to determine the current self-learning acceleration based on the original self-learning acceleration corresponding to the most recent target cycles, and to obtain the current feedback coefficient corresponding to the current self-learning acceleration based on the mapping relationship. The control module is used to control the vehicle to decelerate based on the current feedback coefficient when the vehicle's driving intention is to decelerate.

8. A vehicle-end control device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images