Control method and device for automatic keeping function of vehicle and storage medium

Abstract

The invention relates to a control method, device and equipment for the automatic keeping function of a vehicle and a storage medium, and the method comprises the steps that when the vehicle is converted into a stop state from a driving state, if the treading action of a driver on a brake pedal on the vehicle is detected, treading information of the treading action is obtained; inputting the trampling information into a trained intention recognition model to obtain prediction parameters output by the intention recognition model, the prediction parameters being used for reflecting the probability that the current behavior intention of the driver is a target intention, and the target intention being to activate a vehicle auto-hold function; and determining whether to activate the auto-hold function of the vehicle according to the predicted parameter. Therefore, the secondary confirmation process of activating the vehicle automatic keeping function by the driver can be realized, so that the problems of misoperation of the driver on the vehicle keeping function, poor triggering effect and the like are avoided, and the intelligence of the vehicle automatic keeping function and the driving experience of a user are improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle control, and in particular to a control method, device and storage medium for an automatic holding function of a vehicle. Background Art

[0002] With the continuous development of automobile technology, the vehicle automatic hold function is one of the increasingly popular functions in modern cars. The vehicle automatic hold function is called the intelligent electronic handbrake. It is an intelligent feature in the automobile braking system. Its main function is to automatically keep the vehicle in place when the vehicle stops, freeing the driver's feet and preventing the vehicle from slipping, thereby improving the safety and convenience of parking.

[0003] During vehicle driving, in some specific scenarios, such as waiting for traffic lights, traffic jams, etc., the vehicle has to start and stop frequently. Sometimes the driver does not want to activate the vehicle's automatic hold function every time the vehicle brakes, because the activation of the automatic hold function will cause a short delay when the vehicle starts, which will affect the vehicle's agility and traffic efficiency. In order to avoid this problem, the prior art proposes the following method: after the vehicle stops, the driver activates the automatic hold kinetic energy by deeply or quickly braking.

[0004] However, deep braking is laborious and therefore not driver-friendly, while quick braking can easily lead to poor triggering effects and may even cause misoperation. Summary of the invention

[0005] The present application provides a control method, device and storage medium for a vehicle automatic hold function to solve the technical problem in the prior art that the activation method of the vehicle automatic hold function has a poor triggering effect and may even cause misoperation, thereby affecting the driver's driving experience.

[0006] In a first aspect, the present application provides a method for controlling an automatic holding function of a vehicle, the method comprising:

[0007] When the vehicle changes from a driving state to a stopped state, if a driver's stepping action on a brake pedal of the vehicle is detected, stepping information of the stepping action is obtained;

[0008] Inputting the pedaling information into a trained intention recognition model to obtain a prediction parameter output by the intention recognition model, wherein the prediction parameter is used to reflect the probability that the driver's current behavior intention is a target intention, wherein the target intention is to activate a vehicle automatic holding function;

[0009] A determination is made whether to activate an automatic holding function of the vehicle according to the prediction parameter.

[0010] In a possible implementation manner, determining whether to activate the automatic holding function of the vehicle according to the prediction parameter includes:

[0011] comparing the predicted parameter with a set threshold;

[0012] In the case where the predicted parameter is found to be greater than the set threshold, determining to activate the automatic holding function of the vehicle;

[0013] When it is compared that the prediction parameter is not greater than the set threshold, it is determined not to activate the automatic holding function of the vehicle.

[0014] In a possible implementation, the threshold is set in the following manner:

[0015] determining a forward driving condition of the vehicle;

[0016] When the front driving condition indicates that there is no other vehicle ahead of the vehicle, determining a preset default value as the set threshold;

[0017] When the driving condition ahead indicates that there are other vehicles ahead of the vehicle, determine the change in the distance between the other vehicles and the vehicle; determine a sensitivity coefficient based on the change; set the sensitivity coefficient and the preset default value for operation, and determine the operation result as the set threshold.

[0018] In a possible implementation manner, determining the sensitivity coefficient according to the change condition includes:

[0019] When the change reflects that the distance between the other vehicle and the vehicle remains unchanged or is getting closer, a first preset value is determined as the sensitivity coefficient, wherein the first preset value is a positive number less than 1;

[0020] When the change reflects that the distance between the other vehicle and the vehicle is getting farther and farther, a second preset value is determined as the sensitivity coefficient, wherein the second preset value is greater than 1.

[0021] In a possible implementation, the pedaling information includes at least one or more of the following: the pedaling depth of the brake pedal, the pedaling time from the start of the pedaling action to the brake pedal reaching the pedaling depth, the acceleration of the brake pedal during the pedaling process, and the reset speed of the brake pedal.

[0022] In a possible implementation, the intent recognition model is trained in the following manner:

[0023] Acquire multiple training data, wherein the training data includes a correspondence between pedaling information of a historical pedaling action of a brake pedal and a braking requirement label, wherein when the braking requirement label is a first value, it indicates that the driver's behavioral intention when performing the historical pedaling action is the target intention, and when the braking requirement label is a second value, it indicates that the driver's behavioral intention when performing the historical pedaling action is not the target intention;

[0024] The initial model is trained using the multiple training data to obtain the intent recognition model.

[0025] In a possible implementation, the method further includes:

[0026] When it is found that the predicted parameter is less than the set threshold, a first prompt message is output, wherein the first prompt message is used to prompt the driver to confirm whether to activate the automatic hold function of the vehicle;

[0027] In a case where it is determined that the driver makes a deactivation instruction in response to the prompt message, or in a case where it is determined that the driver does not respond to the prompt message within a set time, determining not to activate the automatic hold function of the vehicle;

[0028] In a case where it is determined that the driver makes an activation instruction in response to the prompt message, it is determined to activate an automatic holding function of the vehicle.

[0029] In a second aspect, the present application provides a control device for an automatic holding function of a vehicle, the device comprising:

[0030] An information acquisition module, used for acquiring the stepping information of the brake pedal on the vehicle if the driver's stepping action on the brake pedal is detected when the vehicle changes from a driving state to a stopped state;

[0031] an intention recognition module, used for inputting the pedaling information into a trained intention recognition model to obtain a prediction parameter output by the intention recognition model, wherein the prediction parameter is used to reflect the probability that the driver's current behavior intention is a target intention, wherein the target intention is to activate a vehicle automatic holding function;

[0032] A control module is used to determine whether to activate the automatic holding function of the vehicle according to the prediction parameter.

[0033] In a possible implementation manner, determining whether to activate the automatic holding function of the vehicle according to the prediction parameter includes:

[0034] comparing the predicted parameter with a set threshold;

[0035] In the case where the predicted parameter is found to be greater than the set threshold, determining to activate the automatic holding function of the vehicle;

[0036] When it is compared that the prediction parameter is not greater than the set threshold, it is determined not to activate the automatic holding function of the vehicle.

[0037] In a possible implementation, the device further includes:

[0038] The threshold setting module is used to set the threshold in the following manner:

[0039] determining a forward driving condition of the vehicle;

[0040] When the front driving condition indicates that there is no other vehicle ahead of the vehicle, determining a preset default value as the set threshold;

[0041] When the driving condition ahead indicates that there are other vehicles ahead of the vehicle, determine the change in the distance between the other vehicles and the vehicle; determine a sensitivity coefficient based on the change; set the sensitivity coefficient and the preset default value for operation, and determine the operation result as the set threshold.

[0042] In a possible implementation, the threshold setting module includes:

[0043] The sensitivity coefficient determination unit is used to determine the sensitivity coefficient according to the change situation, specifically used to:

[0044] When the change reflects that the distance between the other vehicle and the vehicle remains unchanged or is getting closer, a first preset value is determined as the sensitivity coefficient, wherein the first preset value is a positive number less than 1;

[0045] When the change reflects that the distance between the other vehicle and the vehicle is getting farther and farther, a second preset value is determined as the sensitivity coefficient, wherein the second preset value is greater than 1.

[0046] In a possible implementation, the pedaling information includes at least one or more of the following: the pedaling depth of the brake pedal, the pedaling time from the start of the pedaling action to the brake pedal reaching the pedaling depth, the acceleration of the brake pedal during the pedaling process, and the reset speed of the brake pedal.

[0047] In a possible implementation, the device further includes:

[0048] The model training module is used to train the intent recognition model in the following way:

[0049] Acquire multiple training data, wherein the training data includes a correspondence between pedaling information of a historical pedaling action of a brake pedal and a braking requirement label, wherein when the braking requirement label is a first value, it indicates that the driver's behavioral intention when performing the historical pedaling action is the target intention, and when the braking requirement label is a second value, it indicates that the driver's behavioral intention when performing the historical pedaling action is not the target intention;

[0050] The initial model is trained using the multiple training data to obtain the intent recognition model.

[0051] In a possible implementation, the device further includes:

[0052] a prompt module, configured to output a first prompt message when the predicted parameter is less than the set threshold value, wherein the first prompt message is used to prompt the driver to confirm whether to activate the automatic hold function of the vehicle;

[0053] The control module is further configured to determine not to activate the automatic hold function of the vehicle if it is determined that the driver makes a deactivation instruction in response to the prompt message, or if it is determined that the driver does not respond to the prompt message within a set time;

[0054] In a case where it is determined that the driver makes an activation instruction in response to the prompt message, it is determined to activate an automatic holding function of the vehicle.

[0055] In a third aspect, the present application provides a device comprising: a processor and a memory, wherein the processor is used to execute a control program of a vehicle automatic holding function stored in the memory to implement the control method of the vehicle automatic holding function described in any one of the first aspects.

[0056] In a fourth aspect, the present application provides a storage medium storing one or more programs, which can be executed by one or more processors to implement the control method of the vehicle automatic holding function described in any one of the first aspects.

[0057] The above-mentioned technical scheme provided by the embodiment of the present application has the following advantages over the prior art: the method provided by the embodiment of the present application, by detecting the pedaling information of the driver braking the vehicle when the vehicle changes from a driving state to a stopped state, inputs the pedaling information into a trained intention recognition model, obtains the prediction parameters of the model output, and judges the driver's activation requirement for the vehicle automatic hold function according to the prediction parameters, thereby determining whether to activate the vehicle automatic hold function, and provides a method for the driver to conduct a secondary confirmation of the activation of the vehicle automatic hold function. This method can intelligently identify the driver's intention and activate the vehicle automatic hold function when appropriate, which can effectively reduce the driver's misoperation of the vehicle automatic hold function, and solves the problem of poor triggering effect of the activation method in the prior art, thereby improving the intelligence of the vehicle automatic hold function and the user's driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0059] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0060] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0061] Figure 1 A flow chart of an embodiment of a control method for an automatic vehicle holding function provided in an embodiment of the present application.

[0062] Figure 2 A flow chart of another embodiment of a method for controlling an automatic vehicle holding function provided in an embodiment of the present application.

[0063] Figure 3 A flowchart of an embodiment of a threshold setting process provided in an embodiment of the present application.

[0064] Figure 4 A flowchart of an embodiment of the intent recognition model training process provided in an embodiment of the present application.

[0065] Figure 5 A block diagram of an embodiment of a control device for a vehicle automatic holding function provided in an embodiment of the present application.

[0066] Figure 6 A schematic diagram of the structure of a device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0068] The disclosure below provides many different embodiments or examples to realize the different structures of the present application. In order to simplify the disclosure of the present application, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present application. In addition, the present application can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0069] In order to solve the technical problem that the activation method of the vehicle automatic hold function in the prior art has poor triggering effect and may even cause misoperation, thereby affecting the driver's driving experience, the present application provides a control method, device, equipment and storage medium for the vehicle automatic hold function, by detecting the pedaling information of the driver braking the vehicle when the vehicle changes from a driving state to a stopped state, inputting the pedaling information into the intention recognition model, obtaining the prediction parameters output by the model, judging the user's intention based on the prediction parameters, and thus determining whether to activate the vehicle automatic hold function. A secondary confirmation process for the driver to activate the vehicle automatic hold function is realized, thereby avoiding the driver's misoperation of the vehicle hold function, poor triggering effect and other problems, and improving the intelligence of the vehicle automatic hold function and the user's driving experience.

[0070] Figure 1 This is a flow chart of a control method for the automatic vehicle holding function provided in an embodiment of the present application. In one embodiment, the execution subject of the method is a device, such as a vehicle-mounted device. Figure 1 As shown, the process includes the following steps:

[0071] Step 101: When a vehicle changes from a driving state to a stopped state, if it is detected that the driver steps on a brake pedal on the vehicle, the stepping information of the stepping action is obtained.

[0072] The above-mentioned vehicle refers to a vehicle to be subjected to automatic hold function control, and here, automatic hold function control refers to: when the automatic hold function is turned on, controlling the state of the automatic hold function, such as activation state and exit state. The activation state refers to activating the vehicle hold function, at which time the vehicle brakes will keep the vehicle brake calipers applying clamping force to the wheels to ensure that the vehicle does not slide. The exit state refers to not holding the vehicle, at which time the vehicle can slide freely. It can also be seen from this that in the technical solution of the embodiment of the present application, the automatic hold function of the above-mentioned vehicle has been turned on. The on state of the vehicle's automatic hold function: When the vehicle's automatic hold function is in the on state, it means that the function has been set to be available by the driver through the vehicle's control system, and the vehicle's system is now ready to activate the automatic hold function at any time according to specific conditions.

[0073] The vehicle's brake pedal is a power-limiting pedal, also known as the foot brake pedal or the service brake pedal. It is mainly used for deceleration and parking. It is one of the five major control parts for car driving and is used very frequently. The driver's control over it directly affects the safety of car driving.

[0074] In the technical solution of the embodiment of the present application, when the vehicle changes from a driving state to a stopped state, if the driver's stepping action on the brake pedal of the vehicle is detected, the stepping information of the stepping action is obtained. Here, the driver's stepping on the brake pedal of the vehicle is a secondary stepping, and the so-called secondary stepping means: during the driving process of the vehicle, the driver brakes the vehicle by stepping on the brake pedal until the vehicle stops, and the driver releases the brake pedal and then steps on it again. Here, an attempt is made to determine whether the driver has the intention to activate the vehicle automatic holding function by analyzing this secondary stepping behavior.

[0075] The pedaling information includes at least one or more of the following: the pedaling depth of the brake pedal, the pedaling time from the start of the pedaling action to the brake pedal reaching the pedaling depth, the acceleration of the brake pedal during the pedaling process, and the reset speed of the brake pedal. The pedaling depth of the brake pedal is measured in units of angular travel, and the pedaling time can be measured in seconds. The reset speed of the brake pedal refers to the distance the brake pedal moves per unit time during the process of the brake pedal returning to its original position from the current pedaling depth when the driver releases the brake pedal. It can be seen that the pedaling information is a description of the pedal movement characteristics when the driver steps on the brake pedal for the second time after the vehicle stops.

[0076] In one embodiment, a suitable sensor, such as a displacement sensor, a pressure sensor, and / or an acceleration sensor, is installed on the brake pedal of the vehicle. These sensors can sense the changes in various physical quantities when the driver steps on the brake pedal. Then, when the driver steps on the brake pedal, the above-mentioned sensor will collect relevant physical quantity signals in real time, such as the displacement of the pedal, the pressure on the pedal, or the acceleration of the pedal. Subsequently, the original signal collected by the sensor is preprocessed, including filtering, denoising and other steps, and the preprocessed signal is converted into a digital signal. Finally, feature information that can characterize the stepping action, i.e., the above-mentioned stepping information, is extracted from the digital signal.

[0077] Step 102: input the pedaling information into the trained intention recognition model to obtain the prediction parameters output by the intention recognition model, where the prediction parameters are used to reflect the probability that the driver's current behavior intention is the target intention, and the target intention is to activate the vehicle automatic holding function.

[0078] The intention recognition model is a pre-trained machine learning or deep learning model, and its purpose is to predict the driver's intention based on the information of the driver's stepping on the brake pedal, specifically the probability that the driver's current behavioral intention is the target intention, and the target intention is to activate the vehicle's automatic holding function. In actual applications, the intention recognition model is trained based on a large amount of historical data, which records the driver's brake pedal operation and corresponding behavioral intentions in different scenarios. As for how to train the intention recognition model, an exemplary explanation is given below through specific embodiments, which will not be described in detail here.

[0079] Accordingly, in this step 102, the pedaling information obtained in step 101 is input into the trained intention recognition model to obtain the prediction parameters output by the intention recognition model. The prediction parameters can be used to reflect the probability that the driver's current behavioral intention is the target intention. The target intention here refers to activating the vehicle's automatic hold function. Based on the probability that the driver's current behavioral intention is the target intention, it is determined whether the user's intention is to activate the vehicle's automatic hold function.

[0080] Step 103: Determine whether to activate the automatic hold function of the vehicle according to the prediction parameters.

[0081] In the technical solution of the embodiment of the present application, if the prediction parameters indicate that the probability that the driver's current behavior intention is the target intention is relatively high, it means that the driver's current behavior intention is to activate the vehicle's automatic hold function, and the vehicle system will perform the corresponding operation, that is, activate the vehicle's automatic hold function. Among them, the driver's current behavior refers to the driver's stepping action on the brake pedal on the vehicle described in step 101. At this time, the vehicle brake will keep the vehicle brake caliper applying clamping force to the wheel to ensure that the vehicle does not slip. If the prediction parameters indicate that the probability that the driver's current behavior intention is the target intention is relatively low, it means that the driver's current behavior intention is not to activate the vehicle's automatic hold function, and the vehicle system will not activate the vehicle's automatic hold function. At this time, once the driver releases the brake or lightly steps on the accelerator, the vehicle can move forward at a certain speed.

[0082] The method provided in the embodiment of the present application detects the pedaling information of the driver braking the vehicle when the vehicle changes from a driving state to a stopped state, inputs the pedaling information into a trained intention recognition model, obtains the prediction parameters of the model output, and judges the probability that the driver's current behavioral intention is the target intention based on the prediction parameters, thereby determining whether to activate the vehicle automatic hold function. A method for the driver to conduct a secondary confirmation of the activation of the vehicle automatic hold function is provided. This method can intelligently identify the driver's intention and activate the vehicle automatic hold function when appropriate, effectively reduce the driver's misoperation of the vehicle automatic hold function, and solve the problem of poor triggering effect of the activation method in the prior art, thereby improving the intelligence of the vehicle automatic hold function and the user's driving experience.

[0083] Figure 2 This is a flow chart of another embodiment of a method for controlling an automatic vehicle holding function provided in an embodiment of the present application. Figure 2 The process shown in Figure 1 Based on the process shown in FIG, this paper focuses on how to determine whether to activate the vehicle's automatic holding function based on the prediction parameters. Figure 2 As shown, the process includes the following steps:

[0084] Step 201: When the vehicle changes from a driving state to a stopped state, if it is detected that the driver steps on the brake pedal of the vehicle, the stepping information of the stepping action is obtained.

[0085] Step 202: input the pedaling information into the trained intention recognition model to obtain the prediction parameters output by the intention recognition model.

[0086] The prediction parameter is used to reflect the probability that the driver's current behavior intention is the target intention, and the target intention is to activate the vehicle automatic holding function.

[0087] Step 203, compare the prediction parameter with the set threshold; if the prediction parameter is greater than the set threshold, execute step 204; if the prediction parameter is not greater than the set threshold, execute step 205.

[0088] Step 204: Determine whether to activate the automatic hold function of the vehicle.

[0089] Step 205: Determine whether to activate the automatic hold function of the vehicle.

[0090] In step 203 to step 205, the prediction parameter output by the model is compared with the set threshold. When the prediction parameter is compared to be greater than the set threshold, it means that the driver has a high probability of expecting to activate the automatic hold function of the vehicle. At this time, it is determined to activate the automatic hold function of the vehicle, thereby activating the automatic hold function of the vehicle so that the vehicle remains in a stationary parking state to meet the driver's expectations. On the contrary, when the prediction parameter is compared to be not greater than the set threshold, it means that the driver is more inclined not to activate the automatic hold function of the vehicle. At this time, it is determined not to activate the automatic hold function of the vehicle, so that once the driver releases the brake or lightly steps on the accelerator, the vehicle can move forward at a certain speed.

[0091] pass Figure 2 It can be seen from the embodiment shown that by comparing the prediction parameters obtained by the intention recognition model and the size of the set threshold, the driver's behavioral intention can be quickly determined, and then whether to activate the vehicle automatic hold function can be determined based on the driver's behavioral intention. This improves the intelligence and accuracy of the vehicle automatic hold function, can effectively reduce the driver's misoperation of the vehicle automatic hold function, and improves the user's driving experience.

[0092] In addition, in one embodiment, when it is compared that the prediction parameter is not greater than a set threshold, a first prompt message is output, and the first prompt message is used to prompt the driver to confirm whether to activate the automatic hold function of the vehicle. Afterwards, when it is determined that the driver makes an inactivation instruction in response to the prompt message, or when it is determined that the driver does not respond to the prompt message within a set time, it is determined not to activate the automatic hold function of the vehicle. When it is determined that the driver makes an activation instruction in response to the prompt message, it is determined to activate the automatic hold function of the vehicle.

[0093] The first prompt message may be in the form of any signal of a sound signal or a light signal, such as outputting a voice prompt or a signal light prompt, which is not limited in the embodiment of the present application.

[0094] In actual application, if the driver makes an activation instruction in response to the prompt message (such as confirmation through voice command, touch screen operation or button on the steering wheel), the vehicle's automatic hold function is activated. This can adjust the state of the vehicle's automatic hold function according to the driver's actual intention, thereby meeting the driver's needs.

[0095] If the driver explicitly indicates that the vehicle's automatic hold function is not to be activated (such as through voice commands, touch screen operation, or confirmation by buttons on the steering wheel), the vehicle's automatic hold function is determined not to be activated. This can also adjust the state of the vehicle's automatic hold function according to the driver's true intention, thereby meeting the driver's needs.

[0096] If the driver does not respond to the prompt message within a set time, the vehicle's automatic hold function can be deactivated by default. This can avoid unexpected situations caused by the driver being distracted or not noticing the prompt message.

[0097] It can be seen from the above description that the above embodiment, by further using a human-computer interaction method to ask the driver whether to confirm not to activate the vehicle's automatic hold function when it is determined according to the intention recognition model that the driver does not have the need to activate the vehicle's automatic hold function, can adjust the state of the vehicle's automatic hold function according to the driver's actual intention, thereby meeting the driver's needs and providing a more humane control strategy.

[0098] In one embodiment, the above-mentioned threshold value is not a fixed value, but can be dynamically and adaptively set according to the actual driving scenario to improve the accuracy of the driver's intention recognition result. Figure 3 , is a flow chart of an embodiment of a process for setting a threshold value provided by an embodiment of the present application. Figure 3 As shown, the process includes the following steps:

[0099] Step 301, determine the driving condition ahead of the vehicle, and judge whether there are other vehicles ahead of the vehicle. If there are other vehicles ahead, execute step 303; if there are no other vehicles ahead, execute step 302.

[0100] Step 302: Determine the preset default value as the set threshold.

[0101] Step 303: Determine the change in the distance between other vehicles and the vehicle.

[0102] Step 304: determine a sensitivity coefficient according to the change in the distance, perform a setting operation on the sensitivity coefficient and a preset default value, and determine the operation result as a set threshold.

[0103] For ease of understanding, steps 301 to 304 are described in a unified manner as follows:

[0104] In actual applications, in different parking scenarios, the driver's needs for the vehicle's automatic hold function are likely to be different. For example, when a vehicle is at an intersection and stops to wait for a red light, if there are other vehicles in front of it and the distance between the vehicle in front and the vehicle in front is very close, the driver usually wants to activate the vehicle's automatic hold function to keep the vehicle parked. If there are other vehicles in front and the distance between the vehicle in front and the vehicle in front is getting farther and farther, it means that the red light has turned green and the vehicle is moving forward through the green light in turn. At this time, the driver usually does not need to activate the vehicle's automatic hold function.

[0105] Accordingly, in one embodiment, the threshold value can be determined according to the driving condition in front of the vehicle. Specifically, if there are no other vehicles in front, a preset default value, such as 0.5, is determined as the threshold value. If there are other vehicles in front, and the distance between the other vehicles and the vehicle remains unchanged or gets closer, the driver is likely to activate the vehicle automatic hold function at this time, so in order to increase the probability of activating the vehicle automatic hold function, the threshold value can be reduced. Further, in order to reduce the threshold value, a first preset value (such as 0.8) less than 1 is determined as the sensitivity coefficient, then, step 304 is executed, and the sensitivity coefficient is set and operated with the preset default value, such as multiplication operation, and a threshold value less than the default value can be obtained. If there are other vehicles in front, and the distance between the other vehicles and the vehicle is getting farther and farther, the driver is likely not to activate the vehicle automatic hold function at this time, so in order to reduce the probability of activating the vehicle automatic hold function, the threshold value can be increased. Furthermore, in order to increase the set threshold, a second preset value greater than 1 (such as 1.2) is determined as the sensitivity coefficient. Then, step 304 is executed to perform a setting operation, such as a multiplication operation, on the sensitivity coefficient and the preset default value, so that a set threshold greater than the default value can be obtained.

[0106] Figure 3 The embodiment shown can improve the accuracy of the driver's intention recognition results by dynamically and adaptively setting the set threshold for determining the driver's intention according to the actual driving scenario, thereby further enhancing the intelligence of the vehicle's automatic hold function, and can accurately activate the vehicle's automatic hold function when the driver needs it, freeing the driver's feet and helping to improve the driver's driving experience.

[0107] Figure 4 The following is a flow chart of an embodiment of the training process of an intent recognition model provided in the present application. Figure 4 As shown, the process includes the following steps:

[0108] Step 401: Obtain multiple pieces of training data.

[0109] The training data includes the corresponding relationship between the pedaling information of the historical pedaling action of the brake pedal and the braking requirement label. When the braking requirement label is a first value, it indicates that the driver's behavioral intention when performing the historical pedaling action is the target intention, and when the braking requirement label is a second value, it indicates that the driver's behavioral intention when performing the historical pedaling action is not the target intention.

[0110] Optionally, the above historical stepping actions may be from the same user or different users. In the case where the historical stepping actions are from the same user, a user-specific intention recognition model can be trained for a certain user, thereby realizing personalized intention recognition for each user and improving the accuracy of the intention recognition result.

[0111] Step 402: Use multiple training data to train the initial model to obtain an intent recognition model.

[0112] In one embodiment, the initial model adopts a logistic regression model. For example, the following formula (1) is a representation of a logistic regression model:

[0113]

[0114] In the above formula (1), x1 represents the depression depth of the brake pedal, a represents the coefficient corresponding to the depression depth of the brake pedal, for example, a can be 0.05, x2 represents the depression time from the start of the depression action to the time when the brake pedal reaches the depression depth, b represents the coefficient corresponding to the depression time from the start of the depression action to the time when the brake pedal reaches the depression depth, for example, b can be -1, x3 represents the acceleration during the process of the brake pedal being depressed, c represents the coefficient corresponding to the acceleration during the process of the brake pedal being depressed, for example, c can be 0.01, x4 represents the reset speed of the brake pedal, d represents the coefficient corresponding to the reset speed of the brake pedal, for example, d can be 1, and y represents the prediction parameter.

[0115] In this embodiment, the purpose of training the initial logistic regression model using multiple training data is to obtain the values ​​of each coefficient in formula (1). Once the values ​​of each coefficient are determined, a trained intent recognition model is obtained.

[0116] In addition, in practical applications, after the intention recognition model is trained, it can also be fine-tuned or optimized according to actual driver feedback and vehicle status to improve its accuracy and robustness.

[0117] Figure 4In the embodiment shown, by training the initial model with multiple training data, an intention recognition model for identifying the driver's intention for the vehicle's automatic hold function can be obtained. The model can accurately identify the driver's intention, thereby activating the vehicle's automatic hold function under appropriate circumstances, effectively reducing the driver's misoperation of the vehicle's automatic hold function, and solving problems such as poor activation triggering effect in the prior art, thereby improving the intelligence of the vehicle's automatic hold function and the user's driving experience.

[0118] Figure 5 This is a block diagram of an embodiment of a control device for a vehicle automatic holding function provided in an embodiment of the present application. Figure 5 As shown, the device comprises:

[0119] The information acquisition module 51 is used for acquiring the stepping information of the brake pedal of the vehicle if the stepping action of the driver on the brake pedal of the vehicle is detected when the vehicle changes from the driving state to the stopping state;

[0120] an intention recognition module 52, for inputting the pedaling information into a trained intention recognition model to obtain a prediction parameter output by the intention recognition model, wherein the prediction parameter is used to reflect the probability that the driver's current behavior intention is a target intention, wherein the target intention is to activate the vehicle automatic holding function;

[0121] The control module 53 is used to determine whether to activate the automatic holding function of the vehicle according to the prediction parameters.

[0122] In a possible implementation manner, the control module 53 is specifically configured to:

[0123] comparing the predicted parameter with a set threshold;

[0124] In the case where the predicted parameter is found to be greater than the set threshold, determining to activate the automatic holding function of the vehicle;

[0125] When it is compared that the prediction parameter is not greater than the set threshold, it is determined not to activate the automatic holding function of the vehicle.

[0126] In a possible implementation, the device further includes:

[0127] The threshold setting module is used to set the threshold in the following manner:

[0128] determining a forward driving condition of the vehicle;

[0129] When the front driving condition indicates that there is no other vehicle ahead of the vehicle, determining a preset default value as the set threshold;

[0130] When the driving condition ahead indicates that there are other vehicles ahead of the vehicle, determine the change in the distance between the other vehicles and the vehicle; determine a sensitivity coefficient based on the change; set the sensitivity coefficient and the preset default value for operation, and determine the operation result as the set threshold.

[0131] In a possible implementation, the threshold setting module includes:

[0132] The sensitivity coefficient determination unit is used to determine the sensitivity coefficient according to the change situation, specifically used to:

[0133] When the change reflects that the distance between the other vehicle and the vehicle remains unchanged or is getting closer, a first preset value is determined as the sensitivity coefficient, wherein the first preset value is a positive number less than 1;

[0134] When the change reflects that the distance between the other vehicle and the vehicle is getting farther and farther, a second preset value is determined as the sensitivity coefficient, wherein the second preset value is greater than 1.

[0135] In a possible implementation, the pedaling information includes at least one or more of the following: the pedaling depth of the brake pedal, the pedaling time from the start of the pedaling action to the brake pedal reaching the pedaling depth, the acceleration of the brake pedal during the pedaling process, and the reset speed of the brake pedal.

[0136] In a possible implementation, the device further includes:

[0137] The model training module is used to train the intent recognition model in the following way:

[0138] Acquire multiple training data, wherein the training data includes a correspondence between pedaling information of a historical pedaling action of a brake pedal and a braking requirement label, wherein when the braking requirement label is a first value, it indicates that the driver's behavioral intention when performing the historical pedaling action is the target intention, and when the braking requirement label is a second value, it indicates that the driver's behavioral intention when performing the historical pedaling action is not the target intention;

[0139] The initial model is trained using the multiple training data to obtain the intent recognition model.

[0140] In a possible implementation, the device further includes:

[0141] a prompt module, configured to output a first prompt message when the predicted parameter is less than the set threshold value, wherein the first prompt message is used to prompt the driver to confirm whether to activate the automatic hold function of the vehicle;

[0142] The control module 53 is further configured to determine not to activate the automatic hold function of the vehicle when it is determined that the driver makes a deactivation instruction in response to the prompt message, or when it is determined that the driver does not respond to the prompt message within a set time;

[0143] In a case where it is determined that the driver makes an activation instruction in response to the prompt message, it is determined to activate an automatic holding function of the vehicle.

[0144] like Figure 6 As shown, an embodiment of the present application provides a device, including a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.

[0145] Memory 113, used for storing computer programs;

[0146] In one embodiment of the present application, the processor 111 is used to execute the program stored in the memory 113 to implement a method for controlling the automatic holding function of a vehicle provided by any of the aforementioned method embodiments, including:

[0147] When the vehicle changes from a driving state to a stopped state, if a driver's stepping action on a brake pedal of the vehicle is detected, stepping information of the stepping action is obtained;

[0148] Inputting the pedaling information into a trained intention recognition model to obtain a prediction parameter output by the intention recognition model, wherein the prediction parameter is used to reflect the probability that the driver's current behavior intention is a target intention, wherein the target intention is to activate a vehicle automatic holding function;

[0149] A determination is made whether to activate an automatic holding function of the vehicle according to the prediction parameter.

[0150] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of a method for controlling an automatic vehicle holding function as provided in any of the aforementioned method embodiments are implemented.

[0151] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0152] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0153] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0154] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A method for controlling a vehicle automatic holding function, characterized in that: The method comprises: When the vehicle changes from a driving state to a stopped state, if a driver's stepping action on a brake pedal of the vehicle is detected, stepping information of the stepping action is obtained; Inputting the pedaling information into a trained intention recognition model to obtain a prediction parameter output by the intention recognition model, wherein the prediction parameter is used to reflect the probability that the driver's current behavior intention is a target intention, wherein the target intention is to activate a vehicle automatic holding function; A determination is made whether to activate an automatic holding function of the vehicle according to the prediction parameter.

2. The method according to claim 1, characterized in that; The determining whether to activate the automatic holding function of the vehicle according to the prediction parameter comprises: comparing the predicted parameter with a set threshold; In the case where the predicted parameter is found to be greater than the set threshold, determining to activate the automatic holding function of the vehicle; When it is compared that the prediction parameter is not greater than the set threshold, it is determined not to activate the automatic holding function of the vehicle.

3. The method according to claim 2, characterized in that The threshold is set in the following way: determining a forward driving condition of the vehicle; When the front driving condition indicates that there is no other vehicle ahead of the vehicle, determining a preset default value as the set threshold; When the driving condition ahead indicates that there are other vehicles ahead of the vehicle, determine the change in the distance between the other vehicles and the vehicle; determine a sensitivity coefficient based on the change; set the sensitivity coefficient and the preset default value for operation, and determine the operation result as the set threshold.

4. The method according to claim 3, characterized in that Determining the sensitivity coefficient according to the change condition includes: When the change reflects that the distance between the other vehicle and the vehicle remains unchanged or is getting closer, a first preset value is determined as the sensitivity coefficient, wherein the first preset value is a positive number less than 1; When the change reflects that the distance between the other vehicle and the vehicle is getting farther and farther, a second preset value is determined as the sensitivity coefficient, wherein the second preset value is greater than 1.

5. The method according to claim 1, characterized in that The pedaling information includes at least one or more of the following: the pedaling depth of the brake pedal, the pedaling time from the start of the pedaling action to the brake pedal reaching the pedaling depth, the acceleration of the brake pedal during the pedaling process, and the reset speed of the brake pedal.

6. The method according to claim 1, characterized in that The intent recognition model is trained in the following way: Acquire multiple training data, wherein the training data includes a correspondence between pedaling information of a historical pedaling action of a brake pedal and a braking requirement label, wherein when the braking requirement label is a first value, it indicates that the driver's behavioral intention when performing the historical pedaling action is the target intention, and when the braking requirement label is a second value, it indicates that the driver's behavioral intention when performing the historical pedaling action is not the target intention; The initial model is trained using the multiple training data to obtain the intent recognition model.

7. The method according to claim 2, characterized in that The method further comprises: When it is found that the predicted parameter is less than the set threshold, a first prompt message is output, wherein the first prompt message is used to prompt the driver to confirm whether to activate the automatic hold function of the vehicle; In a case where it is determined that the driver makes a deactivation instruction in response to the prompt message, or in a case where it is determined that the driver does not respond to the prompt message within a set time, determining not to activate the automatic hold function of the vehicle; In a case where it is determined that the driver makes an activation instruction in response to the prompt message, it is determined to activate an automatic holding function of the vehicle.

8. A control device for a vehicle automatic holding function, characterized in that: The device comprises: An information acquisition module, used for acquiring the stepping information of the brake pedal on the vehicle if the driver's stepping action on the brake pedal is detected when the vehicle changes from a driving state to a stopped state; an intention recognition module, used for inputting the pedaling information into a trained intention recognition model to obtain a prediction parameter output by the intention recognition model, wherein the prediction parameter is used to reflect the probability that the driver's current behavior intention is a target intention, wherein the target intention is to activate an automatic hold function of the vehicle; A control module is used to determine whether to activate the automatic holding function of the vehicle according to the prediction parameter.

9. A device, characterized in that: include: A processor and a memory, wherein the processor is used to execute a control program of a vehicle automatic holding function stored in the memory to implement a control method of a vehicle automatic holding function according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the control method of the vehicle automatic holding function according to any one of claims 1-7.

Images