Method and device for automatically adjusting sensitivity of AEB, equipment and storage medium

Abstract

A method, apparatus and device for automatically adjusting sensitivity of AEB, and a storage medium, relating to the technical field of intelligent driving, comprising: acquiring to-be-trained data, the to-be-trained data comprising environmental data, vehicle data and a labeled AEB sensitivity value; training a preset neural network according to the to-be-trained data to generate an AEB sensitivity model; based on the AEB sensitivity model, according to to-be-predicted data, obtaining an AEB sensitivity value predicted by the AEB sensitivity model; according to the AEB sensitivity value, the sensitivity of the AEB is adjusted in real time, and the technical problem that in the related technology, when the braking performance of the vehicle is affected by the state of the vehicle or external environment factors, the sensitivity of the AEB cannot be adjusted in time, so that the expected braking effect cannot be achieved, and then the vehicle collides is solved. The sensitivity of the AEB is automatically adjusted according to the state of the vehicle and the external environment, the expected braking effect is achieved, and then collision is avoided.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a method, device, equipment and readable storage medium for automatically adjusting the sensitivity of AEB. Background Art

[0002] At present, the performance of AEB has been fully verified in the development stage. In related technologies, fatigue detection cameras are used to detect the driver's attention and the driving trajectory of the target vehicle in front. When the driver's attention shifts to the target vehicle, the sensitivity of AEB is automatically adjusted to increase the sensitivity, so as to advance the triggering time of AEB and achieve the expected braking effect. However, the main reason for determining the severity of the collision in the AEB system is also the braking performance of the vehicle. The existing technology does not automatically adjust the sensitivity of AEB according to the braking performance of the vehicle. When the braking performance of the vehicle is affected by its own state or external environmental factors, the sensitivity of AEB cannot be adjusted in time, resulting in the failure to achieve the expected braking effect, which in turn causes the vehicle to collide. Summary of the invention

[0003] The present application provides a method, device, equipment and storage medium for automatically adjusting the sensitivity of AEB, which can solve the technical problem in the prior art that when the vehicle's braking performance is affected by its own state or external environmental factors, the sensitivity of AEB cannot be adjusted in time, resulting in failure to achieve the expected braking effect, which in turn causes the vehicle to collide.

[0004] In a first aspect, an embodiment of the present application provides a method for automatically adjusting the sensitivity of AEB, and the method for automatically adjusting the sensitivity of AEB includes:

[0005] Acquire data to be trained, wherein the data to be trained includes environmental data, vehicle data, and annotated AEB sensitivity values;

[0006] Training a preset neural network according to the data to be trained to generate an AEB sensitivity model;

[0007] Based on the AEB sensitivity model, and according to the data to be predicted, obtaining an AEB sensitivity value predicted by the AEB sensitivity model, wherein the data to be predicted includes current environment data and current vehicle data;

[0008] The sensitivity of AEB is adjusted in real time according to the AEB sensitivity value.

[0009] In combination with the first aspect, in one implementation, adjusting the sensitivity of the AEB in real time according to the AEB sensitivity value includes:

[0010] Querying a preset AEB sensitivity table through the AEB sensitivity value to obtain a preset deceleration and a preset advance trigger duration corresponding to the AEB sensitivity value in the preset AEB sensitivity table;

[0011] The sensitivity of AEB is adjusted according to the preset deceleration and the preset advance trigger duration.

[0012] In combination with the first aspect, in one implementation, before adjusting the sensitivity of the AEB according to the preset deceleration and the preset advance trigger duration, the method further includes:

[0013] Obtaining the current AEB sensitivity, wherein the current AEB sensitivity includes deceleration and advance triggering duration;

[0014] Comparing the preset deceleration with the deceleration, and the preset advance trigger duration with the advance trigger duration;

[0015] If the preset deceleration is different from the deceleration, or the preset advance trigger duration is different from the advance trigger duration, the sensitivity of AEB is adjusted in real time according to the AEB sensitivity value.

[0016] In combination with the first aspect, in one implementation, after adjusting the AEB sensitivity according to the preset deceleration and the preset advance trigger duration, the method further includes:

[0017] Detect whether there is an obstacle within a preset distance in front of the vehicle based on the preset radar and camera;

[0018] If an obstacle is detected in a preset distance in front of the vehicle, the AEB adjusts the sensitivity of the AEB based on the preset deceleration and the preset advance trigger duration so that the vehicle brakes in advance.

[0019] In combination with the first aspect, in one implementation, training a preset neural network according to the to-be-trained data to generate an AEB sensitivity model includes:

[0020] The training data is input into a preset neural network to train the preset neural network, wherein the vehicle data includes tire pressure, braking force limit value, braking force system reaction time, braking force system state, brake cylinder pressure, wheel cylinder pressure, and vehicle weight; the environmental data includes road characteristics and weather conditions; and the preset neural network includes Y=(X 1 +X 2 +X 3 +......+X n ) / n, Y is the AEB sensitivity value, X 1 is the tire pressure value, X 2is the value of the braking force limit value, X 3 is the value of the braking force system reaction time, X 4 is the value of the braking force system state, X 5 is the value of the pressure of the brake cylinder, X 6 is the value of the wheel cylinder pressure, X 7 is the value of the vehicle body weight, X 8 is the value of the road feature, X 9 is the value of the weather state, and n is the number of types of environmental data and vehicle data;

[0021] Determining whether the preset neural network after training is in a convergence state;

[0022] If it is determined that the preset neural network after training is in a convergence state, an AEB sensitivity model is generated.

[0023] In combination with the first aspect, in one implementation, determining whether the preset neural network after training is in a convergence state includes:

[0024] Obtaining a loss value of the preset neural network after training;

[0025] If the loss value is less than or equal to a preset standard loss value, it is determined that the preset neural network is in a convergence state;

[0026] If the loss value is greater than a preset standard loss value, it is determined that the preset neural network is not in a convergence state, and the preset neural network is trained again until the preset neural network is in a convergence state.

[0027] In combination with the first aspect, in one implementation, determining whether the preset neural network after training is in a convergence state includes:

[0028] Obtaining the number of training times of the preset neural network;

[0029] If the number of training times is less than a preset standard number of training times, it is determined that the preset neural network is not in a convergence state, and the preset neural network is trained again until the preset neural network is in a convergence state;

[0030] If the number of training times is greater than or equal to a preset standard number of times, it is determined that the preset neural network is in a convergence state.

[0031] In a second aspect, an embodiment of the present application provides a device for automatically adjusting the sensitivity of AEB, and the device for automatically adjusting the sensitivity of AEB includes:

[0032] An acquisition module, used for acquiring data to be trained, wherein the data to be trained includes environmental data, vehicle data and annotated AEB sensitivity values;

[0033] A training module, used for training a preset neural network according to the data to be trained to generate an AEB sensitivity model;

[0034] A prediction module, configured to obtain an AEB sensitivity value predicted by the AEB sensitivity model based on the AEB sensitivity model and data to be predicted, wherein the data to be predicted includes current environment data and current vehicle data;

[0035] The adjustment module is used to adjust the sensitivity of the automatic emergency braking system in real time according to the AEB sensitivity value.

[0036] In a third aspect, an embodiment of the present application provides a device for automatically adjusting the sensitivity of AEB, wherein the device for automatically adjusting the sensitivity of AEB comprises a processor, a memory, and an automatic adjustment AEB sensitivity program stored in the memory and executable by the processor, wherein when the automatic adjustment AEB sensitivity program is executed by the processor, the steps of the method for automatically adjusting the sensitivity of AEB as described above are implemented.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which is stored a program for automatically adjusting the sensitivity of AEB, wherein when the program for automatically adjusting the sensitivity of AEB is executed by a processor, the steps of the method for automatically adjusting the sensitivity of AEB as described above are implemented.

[0038] The beneficial effects brought by the technical solution provided in the embodiments of the present application include:

[0039] By acquiring data to be trained, wherein the data to be trained includes environmental data, vehicle data and annotated AEB sensitivity values; training a preset neural network according to the data to be trained to generate an AEB sensitivity model; based on the AEB sensitivity model, acquiring AEB sensitivity values ​​predicted by the AEB sensitivity model according to the data to be predicted, wherein the data to be predicted includes current environmental data and current vehicle data; and adjusting the sensitivity of AEB in real time according to the AEB sensitivity values, a technical problem in related technologies that when the vehicle's braking performance is affected by its own state or external environmental factors, the sensitivity of AEB cannot be adjusted in time, thereby failing to achieve the expected braking effect and further causing a vehicle collision is solved. By automatically adjusting the sensitivity of AEB according to the vehicle's own state and the external environment, the expected braking effect is achieved, thereby avoiding a collision. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1This is a flow chart of an embodiment of a method for automatically adjusting the sensitivity of AEB according to the present application;

[0041] Figure 2 For this application Figure 1 A detailed flow chart of step S40;

[0042] Figure 3 This is a functional module diagram of an embodiment of a device for automatically adjusting the sensitivity of AEB in the present application;

[0043] Figure 4 This is a schematic diagram of the hardware structure of the device for automatically adjusting the sensitivity of AEB involved in the embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the solution of the present application, 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 only 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 creative work are within the scope of protection of this application.

[0045] First, some technical terms in the present application are explained to facilitate those skilled in the art to understand the present application.

[0046] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0047] In a first aspect, an embodiment of the present application provides a method for automatically adjusting the sensitivity of AEB.

[0048] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for automatically adjusting the sensitivity of AEB in this application. Figure 1 As shown, the method for automatically adjusting the sensitivity of AEB includes:

[0049] Step S10: Acquire data to be trained, wherein the data to be trained includes environmental data, vehicle data, and annotated AEB sensitivity values;

[0050] Exemplarily, training data is obtained through pre-installed sensors on the vehicle, wherein environmental data includes road characteristics and weather conditions, and vehicle data includes tire pressure, braking force limit value, braking force system reaction time, braking force system status, brake cylinder pressure, wheel cylinder pressure, and vehicle weight. Then, the degree of influence of these data on the braking force is quantified, and the greater the influence, the greater the value. For example, when the weather condition is no rain, the weather condition value is 1, and when the weather condition is light rain, the weather condition value is 2. Similar quantification is performed on other data; the AEB sensitivity values ​​are manually labeled.

[0051] Step S20: training a preset neural network according to the data to be trained to generate an AEB sensitivity model;

[0052] Exemplarily, the acquired multiple groups of data to be trained are input into a preset neural network for training until the preset neural network is in a convergence state. When the number of training times or the loss value of the preset neural network reaches a preset standard value, it indicates that the preset neural network is in a convergence state. After that, an AEB sensitivity model is generated.

[0053] Specifically, the training of the preset neural network according to the training data to generate the AEB sensitivity model includes: inputting the training data into the preset neural network to train the preset neural network, wherein the vehicle data includes tire pressure, braking force limit value, braking force system reaction time, braking force system state, brake cylinder pressure, wheel cylinder pressure, and vehicle weight; the environmental data includes road characteristics and weather conditions; and the preset neural network includes

[0054] Y=(X 1 +X 2 +X 3 +......+X n ) / n, Y is the AEB sensitivity value, X 1 is the tire pressure value, X 2 is the value of the braking force limit value, X 3 is the value of the braking force system reaction time, X 4 is the value of the braking force system state, X 5 is the value of the pressure of the brake cylinder, X 6 is the value of the wheel cylinder pressure, X 7 is the value of the vehicle body weight, X 8 is the value of the road feature, X 9is the value of the weather state, and n is the number of types of the environmental data and the vehicle's own data; determining whether the preset neural network after training is in a convergence state; if it is determined that the preset neural network after training is in a convergence state, generating an AEB sensitivity model.

[0055] For example, when the vehicle's own state or external environmental factors affect the vehicle's braking performance, resulting in insufficient braking force and failure to achieve the target deceleration and target reaction time, it is necessary to adjust the values ​​corresponding to the above data to adjust the sensitivity so that the vehicle can achieve the target deceleration and target reaction time, for example: X 1 is the tire pressure value. When the tire pressure is insufficient, the friction coefficient between the tire and the ground will decrease, affecting the braking performance. For example, commercial vehicles have a large number of tires. When the tire pressure is within the normal range, X 1 The value of X is 1. When the tire pressure of one tire is lower than the normal range, 1 The value of is 1.2. When the number of tire pressures below the normal range increases by 1, X 1 The value of X increases by 0.2. For example, when the tire pressure of 5 tires is lower than the normal range, 1 The value of is 2.

[0056] X 2 The braking force limit value is set. The braking system will limit the braking force in certain conditions. The normal braking deceleration can reach 6m / s. 2 , but under the condition of braking force limitation, the deceleration may be only 4m / s 2 , resulting in a longer braking distance, which may lead to a collision. Determine X according to the braking force limit value 2 When the braking force is unlimited, the vehicle deceleration can reach 6m / s 2 Above, X 2 The value is 1. When the braking force is limited, the vehicle deceleration cannot reach 6m / s 2 For example, when the deceleration is 5m / s 2 ~6m / s 2 At this time, X 2 The value is 2, when the deceleration is 4m / s 2 ~5m / s 2 At this time, X 2 The value is 3, when the deceleration is 3m / s 2 ~4m / s 2 At this time, X 2 The value is 4, when the deceleration is 2m / s 2 ~3m / s 2 At this time, X 2 The value of is 5.

[0057] X3 is the value of the braking system reaction time. As the vehicle is used, the braking system reaction time will be extended. For a vehicle with a speed of 80 km / h, if the braking system reaction time is delayed by 0.5 s, the braking distance will be extended by 11 m. For example, the braking system reaction time is 0.75 s when it leaves the factory. At this time, X 3 The value of X is 1. When the braking system reaction time is greater than 1s, 3 The value of 3, when the braking system reaction time is greater than 1.5s, X 3 The value of is 5.

[0058] X 4 is the value of the braking force system state. When there is a fault in the braking system, some faults may affect the braking force. When there is no fault or the fault has no effect on the braking force system, X 4 The value of X is 1. When there is a fault that affects the braking force, 4 The values ​​include 2, 3, 4, and 5. The specific value needs to be determined according to the impact of the fault on the braking force.

[0059] X 5 is the value of the brake cylinder pressure. Commercial vehicle trailers generally use air pressure brakes. Insufficient air pressure leads to insufficient braking force and slow response. For example, when the brake cylinder pressure is higher than or equal to 600Kpa, X 5 The value of X is 1. When the pressure of the brake cylinder is lower than 600Kpa and higher than or equal to 500Kpa, 5 The value of is 2. When the pressure of the brake cylinder is lower than 500Kpa, X 5 The value of is 3.

[0060] X 6 is the value of wheel cylinder pressure. When the wheel cylinder pressure is insufficient, the braking system responds with delay and the braking force is insufficient. For example, when the wheel cylinder pressure is higher than or equal to 700Kpa, X 6 The value of X is 1. When the wheel cylinder pressure is lower than 700Kpa and higher than or equal to 600Kpa, 6 The value of is 2. When the wheel cylinder pressure is lower than 600Kpa and higher than or equal to 500Kpa, X 6 The value of is 3.

[0061] X 7 The value of the vehicle weight is the initial design of the AEB system based on the vehicle being fully loaded, but some sections of the road allow an overload of 10%. When the vehicle is not overloaded, X 7 The value of is 1. When the vehicle is overloaded, X 7 The value of is 3.

[0062] X 8is the value of the road feature, the road features are asphalt road, cement road, and sand road, and the corresponding X 8 The value of is 1, 2, 3.

[0063] X 9 is the value of the weather state, which mainly includes: no rain, light rain, moderate rain, heavy rain, light snow, moderate snow, heavy snow, X 9 The corresponding values ​​are 1, 2, 3, 4, 3, 4, and 5 respectively.

[0064] Specifically, the determining whether the preset neural network after training is in a convergence state includes: obtaining the loss value of the preset neural network after training; if the loss value is less than or equal to a preset standard loss value, determining that the preset neural network is in a convergence state; if the loss value is greater than the preset standard loss value, determining that the preset neural network is not in a convergence state, and training the preset neural network again until the preset neural network is in a convergence state.

[0065] Exemplarily, when the loss value is 0.1, the loss value is less than the preset standard loss value of 0.5, and it is determined that the preset neural network is in a convergence state; when the loss value is 0.6, the loss value is greater than the preset standard loss value of 0.5, and it is determined that the preset neural network is not in a convergence state, and the preset neural network is trained again until the preset neural network is in a convergence state; when the loss value is 0.5, the loss value is equal to the standard loss value of 0.5, and it is determined that the preset neural network is in a convergence state.

[0066] Specifically, the determining whether the preset neural network after training is in a convergence state includes: obtaining the number of training times of the preset neural network; if the number of training times is less than a preset standard number of training times, determining that the preset neural network is not in a convergence state, and training the preset neural network again until the preset neural network is in a convergence state; if the number of training times is greater than or equal to the preset standard number of times, determining that the preset neural network is in a convergence state.

[0067] Exemplarily, when the number of training times is greater than or equal to the preset standard number of training times of 10,000, it is determined that the preset neural network is in a convergence state, and when the number of training times is less than the preset standard number of training times of 10,000, it is determined that the preset neural network is not in a convergence state.

[0068] Exemplarily, when the preset neural network is in a convergence state, it means that the number of training times or the loss value of the preset neural network has reached the standard value, which means that the AEB sensitivity value output at this time meets the standard, and the AEB sensitivity can be adjusted in real time according to the AEB sensitivity value.

[0069] Step S30: Based on the AEB sensitivity model, according to the data to be predicted, obtaining the AEB sensitivity value predicted by the AEB sensitivity model, wherein the data to be predicted includes current environment data and current vehicle data;

[0070] Exemplarily, the current environment data and the current vehicle data are obtained through the vehicle preset sensor, and the environment data and the current vehicle data are input into the preset neural network training, and the AEB sensitivity value is predicted by the AEB sensitivity model. For example, when the preset sensor in the vehicle detects that the weather condition is no rain, the corresponding value is 1; the road feature is cement road, and the corresponding value of water is 2; the deceleration corresponding to the braking force limit value is 4m / s 2 , the corresponding value is 3; the number of tire pressures below the normal range is 2, and the corresponding value is 1.4; the braking system reaction time is 1.2s, and the corresponding value is 3; the wheel cylinder pressure is 650Kpa, and the corresponding value is 2; the brake cylinder pressure is 700Kpa, and the corresponding value is 1; the vehicle body weight is overloaded, and the corresponding value is 3; there is a slight fault in the braking system, and the corresponding value is 2; substitute the above quantitative values ​​into the AEB sensitivity prediction model, that is, Y=(1+2+3+1.4+3+2+1+3+2) / 9=2.04, and the AEB sensitivity value is 2.04.

[0071] Step S40: adjusting the sensitivity of AEB in real time according to the AEB sensitivity value.

[0072] Exemplarily, the current required AEB sensitivity value is predicted according to the AEB sensitivity model, and a preset AEB sensitivity table is queried according to the AEB sensitivity value to obtain the preset deceleration and preset advance trigger duration corresponding to the AEB sensitivity value, and then the AEB sensitivity of the current vehicle is measured in real time. If the current AEB sensitivity is consistent with the preset deceleration and preset advance trigger duration corresponding to the AEB sensitivity predicted by the large model, there is no need to adjust the current AEB sensitivity. If they are inconsistent, the current AEB sensitivity needs to be adjusted.

[0073] In the present embodiment, by acquiring data to be trained, wherein the data to be trained includes environmental data, vehicle data and annotated AEB sensitivity values; training a preset neural network according to the data to be trained to generate an AEB sensitivity model; based on the AEB sensitivity model, acquiring AEB sensitivity values ​​predicted by the AEB sensitivity model according to the data to be predicted, wherein the data to be predicted includes current environmental data and current vehicle data; adjusting the sensitivity of AEB in real time according to the AEB sensitivity values, a technical problem in the related art that when the vehicle's braking performance is affected by its own state or external environmental factors, the sensitivity of AEB cannot be adjusted in time, thereby resulting in the inability to achieve the expected braking effect, thereby causing the vehicle to collide, is solved. By automatically adjusting the sensitivity of AEB according to the vehicle's own state and the external environment, the expected braking effect is achieved, thereby avoiding collision.

[0074] Further, in one embodiment, referring to Figure 2 , Figure 2 For this application Figure 1 Detailed flow chart of step S40 in FIG. Figure 2 As shown, the real-time adjustment of the AEB sensitivity according to the AEB sensitivity value includes:

[0075] Step S41: querying a preset AEB sensitivity table through the AEB sensitivity value to obtain a preset acceleration and a preset advance trigger duration corresponding to the AEB sensitivity value in the preset AEB sensitivity table;

[0076] For example, according to the sensitivity model, the AEB sensitivity values ​​are all greater than or equal to 1. The AEB sensitivity table is shown in the following table:

[0077] Sensitivity value (Y) Preset deceleration() Preset advance trigger time 1≤Y<1.5 6 T 1.5≤Y<2 7 1.2T Y≥2 8 1.5T

[0078] For example, when the AEB sensitivity value is 1.3, in the AEB sensitivity table, the corresponding preset deceleration is 6m / s 2 , the preset advance trigger time is T, when the AEB sensitivity is 1.8, the corresponding preset deceleration is 7m / s 2 The preset advance trigger time is 1.2T, where T is the original advance trigger time when the AEB sensitivity is 1, and the value range of T is 1.3s to 2s.

[0079] In another embodiment, the AEB sensitivity level is determined according to the AEB sensitivity value. According to the sensitivity model, the AEB sensitivity value is greater than or equal to 1. When the AEB sensitivity value is greater than or equal to 1 and less than 1.5, the corresponding AEB sensitivity level is 1. When the AEB sensitivity value is greater than or equal to 1.5 and less than 2, the corresponding AEB sensitivity level is 2. When the AEB sensitivity value is greater than or equal to 2, the corresponding AEB sensitivity level is 3. After the AEB sensitivity level is determined, the AEB sensitivity table is queried as shown below:

[0080] Sensitivity level Preset deceleration() Preset advance trigger time 1 6 T 2 7 1.2T 3 8 1.5T

[0081] The preset deceleration and preset advance trigger duration corresponding to the AEB sensitivity value in the preset AEB sensitivity table are obtained through the AEB sensitivity table. For example, when the AEB sensitivity value is 1.4, the corresponding AEB sensitivity level is 1. In the AEB sensitivity level table, the corresponding preset deceleration is 6m / s. 2 , the preset advance trigger time is T, when the AEB sensitivity value is 1.9, the corresponding AEB sensitivity level is 2, and the corresponding preset deceleration is 7m / s 2 The preset advance trigger time is 1.2T, where T is the original advance trigger time when the AEB sensitivity value is 1, and the value range of T is 1.3s to 2s.

[0082] Step S42: adjusting the sensitivity of AEB according to the preset acceleration and the preset advance triggering time.

[0083] Exemplarily, according to the preset deceleration and preset advance trigger duration obtained by querying, AEB adjusts the braking system target deceleration and target advance trigger duration in real time. For example, when the AEB sensitivity is 2.6, it can be seen from the AEB sensitivity table that the corresponding preset deceleration is 8m / s. 2 , the preset advance trigger time is 1.5T. If T is 1.4s, the preset advance trigger time is 2.1s, after which AEB adjusts the target deceleration of the braking system to 8m / s 2 , the target advance trigger time is 2.1s.

[0084] Specifically, before adjusting the sensitivity of AEB according to the preset deceleration and the preset advance trigger duration, it also includes: obtaining the current AEB sensitivity, wherein the current AEB sensitivity includes deceleration and advance trigger duration; comparing the preset deceleration with the deceleration, and the preset advance trigger duration with the advance trigger duration; if the preset deceleration is different from the deceleration, or the preset advance trigger duration is different from the advance trigger duration, adjusting the sensitivity of AEB in real time according to the AEB sensitivity value.

[0085] For example, when the deceleration at a certain moment is detected to be 7 m / s 2 , the advance trigger time is 1.2T, and the corresponding AEB sensitivity value is 1.5≤Y<2. At this time, the AEB sensitivity predicted by the AEB sensitivity model is 1.8, and the corresponding preset deceleration is 7m / s 2 , the preset advance trigger duration is 1.2T, and the corresponding values ​​of the two are consistent, so no adjustment is required. For another example, when the deceleration at a certain moment is detected to be 6m / s 2 , the advance trigger time is T, at this time the AEB sensitivity model predicts the AEB sensitivity is 2, and the corresponding preset deceleration is 8m / s 2 , the preset advance trigger time is 1.5T. If the corresponding values ​​are inconsistent, the deceleration needs to be adjusted to 8m / s 2 , the trigger duration is adjusted to 1.5T.

[0086] Specifically, after adjusting the AEB sensitivity according to the preset deceleration and the preset advance trigger time, it also includes: detecting whether there is an obstacle in a preset distance in front of the vehicle according to the preset radar and the camera; if an obstacle is detected in the preset distance in front of the vehicle, the AEB adjusts the AEB sensitivity based on the preset deceleration and the preset advance trigger time to make the vehicle brake in advance.

[0087] For example, when the preset radar and camera detect an obstacle within 5m in front of the vehicle, if the preset deceleration is set to 8m / s 2 , the preset advance trigger time is 2.3s, then 8m / s 2 deceleration, start braking 2.3s in advance.

[0088] In this embodiment, the sensitivity of AEB is adjusted in real time according to the AEB sensitivity value, which solves the technical problem in the related art that when the braking performance of the vehicle is affected by its own state or external environmental factors, the sensitivity of AEB cannot be adjusted in time, resulting in failure to achieve the expected braking effect, thereby causing a vehicle collision. By automatically adjusting the sensitivity of AEB according to the vehicle's own state and the external environment, the expected braking effect is achieved, thereby avoiding a collision.

[0089] In a second aspect, an embodiment of the present application also provides a device for automatically adjusting the sensitivity of AEB.

[0090] In one embodiment, referring to Figure 3 , Figure 3 This is a functional module diagram of an embodiment of a device for automatically adjusting the sensitivity of AEB in this application. Figure 3 As shown, the device for automatically adjusting the sensitivity of AEB includes:

[0091] An acquisition module 01 is used to acquire data to be trained, wherein the data to be trained includes environmental data, vehicle data, and annotated AEB sensitivity values;

[0092] A training module 02 is used to train a preset neural network according to the training data to generate an AEB sensitivity model;

[0093] A prediction module 03 is used to obtain an AEB sensitivity value predicted by the AEB sensitivity model based on the AEB sensitivity model and data to be predicted, wherein the data to be predicted includes current environment data and current vehicle data;

[0094] The adjustment module 04 is used to adjust the sensitivity of the automatic emergency braking system in real time according to the AEB sensitivity value.

[0095] Furthermore, in one embodiment, the training module 02 is also used for:

[0096] The training data is input into a preset neural network to train the preset neural network, wherein the vehicle data includes tire pressure, braking force limit value, braking force system reaction time, braking force system state, brake cylinder pressure, wheel cylinder pressure, and vehicle weight; the environmental data includes road characteristics and weather conditions; and the preset neural network includes Y=(X 1 +X 2 +X 3 +......+X n ) / n, Y is the AEB sensitivity value, X 1 is the tire pressure value, X 2 is the value of the braking force limit value, X 3 is the value of the braking force system reaction time, X 4 is the value of the braking force system state, X 5 is the value of the pressure of the brake cylinder, X 6 is the value of the wheel cylinder pressure, X 7 is the value of the vehicle body weight, X 8 is the value of the road feature, X 9 is the value of the weather state, and n is the number of types of environmental data and vehicle data;

[0097] Determining whether the preset neural network after training is in a convergence state;

[0098] If it is determined that the preset neural network after training is in a convergence state, an AEB sensitivity model is generated.

[0099] Furthermore, in one embodiment, the adjustment module 04 is also used for:

[0100] Querying a preset AEB sensitivity table through the AEB sensitivity value to obtain a preset acceleration and a preset advance trigger duration corresponding to the AEB sensitivity value in the preset AEB sensitivity table;

[0101] The sensitivity of AEB is adjusted according to the preset acceleration and the preset advance triggering time.

[0102] Among them, the functional implementation of each module in the above-mentioned automatic adjustment of AEB sensitivity device corresponds to the various steps in the above-mentioned automatic adjustment of AEB sensitivity method embodiment, and its functions and implementation processes are no longer repeated here one by one.

[0103] In a third aspect, an embodiment of the present application provides a device for automatically adjusting the sensitivity of AEB. The device for automatically adjusting the sensitivity of AEB may be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0104] Reference Figure 4 , Figure 4 Schematic diagram of the hardware structure of the automatic AEB sensitivity adjustment device involved in the embodiment of the present application. In the embodiment of the present application, the automatic AEB sensitivity adjustment device may include a processor, a memory, a communication interface and a communication bus.

[0105] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0106] The communication interface includes an input / output (I / O) interface, a physical interface, and a logical interface, etc., which are used to interconnect the components inside the automatic AEB sensitivity adjustment device, and an interface used to interconnect the automatic AEB sensitivity adjustment device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0107] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0108] The processor may be a general-purpose processor, which may call the automatic AEB sensitivity adjustment program stored in the memory and execute the automatic AEB sensitivity adjustment method provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the automatic AEB sensitivity adjustment program is called may refer to the various embodiments of the automatic AEB sensitivity adjustment method of the present application, which will not be described in detail here.

[0109] Those skilled in the art will understand that Figure 3 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0110] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0111] The computer-readable storage medium of the present application stores a program for automatically adjusting the sensitivity of AEB, wherein when the program for automatically adjusting the sensitivity of AEB is executed by a processor, the steps of the method for automatically adjusting the sensitivity of AEB as described above are implemented.

[0112] Among them, the method implemented when the automatic adjustment of the AEB sensitivity program is executed can refer to the various embodiments of the method for automatically adjusting the AEB sensitivity of the present application, and will not be repeated here.

[0113] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0114] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0115] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0116] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0117] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0118] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0119] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for automatically adjusting the sensitivity of AEB, characterized in that: The method for automatically adjusting the sensitivity of AEB includes: Acquire data to be trained, wherein the data to be trained includes environmental data, vehicle data, and annotated AEB sensitivity values; Training a preset neural network according to the data to be trained to generate an AEB sensitivity model; Based on the AEB sensitivity model, and according to the data to be predicted, obtaining an AEB sensitivity value predicted by the AEB sensitivity model, wherein the data to be predicted includes current environment data and current vehicle data; The sensitivity of AEB is adjusted in real time according to the AEB sensitivity value.

2. The method for automatically adjusting the sensitivity of AEB according to claim 1, characterized in that: The real-time adjustment of the AEB sensitivity according to the AEB sensitivity value includes: Querying a preset AEB sensitivity table through the AEB sensitivity value to obtain a preset deceleration and a preset advance trigger duration corresponding to the AEB sensitivity value in the preset AEB sensitivity table; The sensitivity of AEB is adjusted according to the preset deceleration and the preset advance trigger duration.

3. The method for automatically adjusting the sensitivity of AEB according to claim 2, characterized in that: Before adjusting the sensitivity of the AEB according to the preset deceleration and the preset advance trigger duration, the method further includes: Obtaining the current AEB sensitivity, wherein the current AEB sensitivity includes deceleration and advance triggering duration; Comparing the preset deceleration with the deceleration, and the preset advance trigger duration with the advance trigger duration; If the preset deceleration is different from the deceleration, or the preset advance trigger duration is different from the advance trigger duration, the sensitivity of AEB is adjusted in real time according to the AEB sensitivity value.

4. The method for automatically adjusting the sensitivity of AEB according to claim 2, characterized in that: After adjusting the AEB sensitivity according to the preset deceleration and the preset advance trigger duration, the method further includes: Detect whether there is an obstacle within a preset distance in front of the vehicle based on the preset radar and camera; If an obstacle is detected in a preset distance in front of the vehicle, the AEB adjusts the sensitivity of the AEB based on the preset deceleration and the preset advance trigger duration so that the vehicle brakes in advance.

5. The method for automatically adjusting the sensitivity of AEB according to claim 1, characterized in that: The training of the preset neural network according to the to-be-trained data to generate the AEB sensitivity model comprises: The data to be trained is input into a preset neural network to train the preset neural network, wherein the vehicle data includes tire pressure, braking force limit value, braking force system reaction time, braking force system state, brake cylinder pressure, wheel cylinder pressure, and vehicle weight; the environmental data includes road characteristics and weather conditions; the preset neural network includes Y=(X1+X2+X3+......+X n ) / n, Y is the AEB sensitivity value, X1 is the tire pressure value, X2 is the braking force limit value, X3 is the braking force system reaction time value, X4 is the braking force system state value, X5 is the brake cylinder pressure value, X6 is the wheel cylinder pressure value, X7 is the vehicle weight value, X8 is the road feature value, X9 is the weather condition value, and n is the number of types of environmental data and vehicle data; Determining whether the preset neural network after training is in a convergence state; If it is determined that the preset neural network after training is in a convergence state, an AEB sensitivity model is generated.

6. The method for automatically adjusting the sensitivity of AEB according to claim 5, characterized in that: Determining whether the preset neural network after training is in a convergence state includes: Obtaining a loss value of the preset neural network after training; If the loss value is less than or equal to a preset standard loss value, it is determined that the preset neural network is in a convergence state; If the loss value is greater than a preset standard loss value, it is determined that the preset neural network is not in a convergence state, and the preset neural network is trained again until the preset neural network is in a convergence state.

7. The method for automatically adjusting the sensitivity of AEB according to claim 5, characterized in that: Determining whether the preset neural network after training is in a convergence state includes: Obtaining the number of training times of the preset neural network; If the number of training times is less than a preset standard number of training times, it is determined that the preset neural network is not in a convergence state, and the preset neural network is trained again until the preset neural network is in a convergence state; If the number of training times is greater than or equal to a preset standard number of times, it is determined that the preset neural network is in a convergence state.

8. A device for automatically adjusting the sensitivity of AEB, characterized in that: The automatic AEB sensitivity adjustment device comprises: An acquisition module, used to acquire data to be trained, wherein the data to be trained includes environmental data, vehicle data, and annotated AEB sensitivity values; A training module, used for training a preset neural network according to the data to be trained to generate an AEB sensitivity model; A prediction module, configured to obtain an AEB sensitivity value predicted by the AEB sensitivity model based on the AEB sensitivity model and data to be predicted, wherein the data to be predicted includes current environment data and current vehicle data; The adjustment module is used to adjust the sensitivity of the automatic emergency braking system in real time according to the AEB sensitivity value.

9. A device for automatically adjusting the sensitivity of AEB, characterized in that: The automatic AEB sensitivity adjustment device includes a processor, a memory, and an automatic AEB sensitivity adjustment program stored in the memory and executable by the processor, wherein when the automatic AEB sensitivity adjustment program is executed by the processor, the steps of the automatic AEB sensitivity adjustment method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program for automatically adjusting the sensitivity of AEB, wherein when the program for automatically adjusting the sensitivity of AEB is executed by a processor, the steps of the method for automatically adjusting the sensitivity of AEB as claimed in any one of claims 1 to 7 are implemented.

Images