Vehicle automatic emergency braking method and device, storage medium and vehicle

Abstract

The invention discloses a vehicle automatic emergency braking method and device, a storage medium and a vehicle. The method comprises the steps that the driving road adhesion coefficient and the real-time load of the current vehicle are obtained; a preset braking decision table is inquired according to the driving road adhesion coefficient and the real-time load, a current braking triggering threshold value is obtained, and the preset braking decision table is the corresponding relation among the road adhesion coefficient, the vehicle load and the braking triggering threshold value determined according to a preset dynamic safety distance formula at different driving speeds; and acquiring an environment sensing distance corresponding to the current vehicle, comparing the environment sensing distance with the current brake triggering threshold value, and making a brake decision on the current vehicle according to a comparison result. Therefore, the braking intervention opportunity can be adaptively adjusted according to different road conditions and different vehicle load states, then more accurate and more reasonable automatic emergency braking decisions are achieved under various complex working conditions, and the safety and adaptability of the vehicle are improved.

Description

Technical Field

[0001] This application relates to the field of vehicle braking technology, and in particular to a vehicle automatic emergency braking method, device, storage medium, and vehicle. Background Technology

[0002] With the rapid adoption of intelligent driving assistance systems in passenger vehicles, the Automatic Emergency Braking (AEB) function has become a common focus of regulations and the market. To cover more complex traffic scenarios, OEMs are generally upgrading the perception, control, and execution components on a platform basis, enabling the AEB system to work continuously under different weather, load, and road conditions, and serving as the basic safety foundation for subsequent advanced autonomous driving functions.

[0003] Current mass-production solutions mostly rely on fixed thresholds set during the calibration phase to trigger braking, with parameters typically based on good road surfaces and nominal loads. However, when the actual vehicle weight or tire-road adhesion characteristics deviate from this benchmark, the AEB system struggles to adjust the trigger timing and braking force synchronously. This can lead to premature intervention or delayed response under low-adhesion or heavy-load conditions, thereby affecting ride stability and increasing the risk of collisions. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device, storage medium and vehicle for automatic emergency braking of a vehicle, which aims to solve the technical problem that the decision logic of the existing AEB system is calibrated based on a fixed trigger threshold, and the braking timing may be inaccurate under different operating conditions.

[0005] To achieve the above objectives, this application proposes a method for automatic emergency braking of a vehicle, the method comprising: Obtain the current road surface adhesion coefficient and real-time load of the vehicle; Based on the road surface adhesion coefficient and the real-time load, the current braking trigger threshold is obtained by querying the preset braking decision table. The preset braking decision table is the correspondence between the road surface adhesion coefficient, vehicle load and braking trigger threshold determined according to the preset dynamic safety distance formula at different driving speeds. The environmental perception distance corresponding to the current vehicle is obtained, and the environmental perception distance is compared with the current braking trigger threshold. A braking decision is made for the current vehicle based on the comparison result.

[0006] In one embodiment, the step of obtaining the road surface adhesion coefficient of the current vehicle includes: Road surface image information is acquired through a visual sensor, and a first road surface adhesion coefficient estimate and a corresponding first confidence level are determined based on the road surface image information. Ground echo signals are acquired by radar sensors, and the estimated value of the second road surface adhesion coefficient and the corresponding second confidence level are determined based on the ground echo signals. Based on the first confidence level and the second confidence level, the estimated values ​​of the first road surface adhesion coefficient and the second road surface adhesion coefficient are weighted and fused to obtain the road surface adhesion coefficient.

[0007] In one embodiment, the step of obtaining the real-time load of the current vehicle includes: Obtain the support force measurement value of the vehicle suspension system and the vehicle's vertical acceleration; Based on the vehicle's vertical dynamics model, using the measured support force and vertical acceleration as observations, a state estimation algorithm is employed to estimate the vehicle's total mass in real time, thereby obtaining the real-time load.

[0008] In one embodiment, before the step of obtaining the current braking trigger threshold by querying a preset braking decision table based on the road surface adhesion coefficient and the real-time load, the method further includes: Several calibration scenarios and corresponding scenario information are determined based on preset calibration requirements. The scenario information includes: calibration driving speed, road surface adhesion coefficient, and vehicle load. Substitute each of the calibration driving speeds, each of the road surface adhesion coefficients, and each of the vehicle loads into the preset dynamic safety distance formula to obtain the safety distance threshold corresponding to each of the calibration scenarios as the braking trigger threshold. At each of the specified calibrated driving speeds, a correspondence is established between each of the specified road surface adhesion coefficients, each of the specified vehicle loads, and each of the specified braking trigger thresholds to obtain a preset braking decision table.

[0009] In one embodiment, the expression for the preset dynamic safety distance formula is:

[0010] In the formula, The dynamic safety distance value serves as the braking trigger threshold. For the calibrated driving speed, The load capacity of the vehicle. The road surface adhesion coefficient is... It is the acceleration due to gravity. For vehicle response delay time, This is a quality compensation factor.

[0011] In one embodiment, the step of obtaining the current braking trigger threshold by querying a preset braking decision table based on the road surface adhesion coefficient and the real-time load includes: Obtain the current driving speed of the current vehicle, and determine the target calibrated driving speed from each of the calibrated driving speeds based on the current driving speed; Obtain the preset braking decision table corresponding to the target calibrated driving speed; Using the road surface adhesion coefficient and the real-time load as query inputs, the braking trigger threshold corresponding to the query input is used as the current braking trigger threshold in the preset braking decision table.

[0012] In one embodiment, the step of obtaining the environmental perception distance corresponding to the current vehicle, comparing the environmental perception distance with the current braking trigger threshold, and making a braking decision for the current vehicle based on the comparison result includes: The actual perceived distance between the current vehicle and environmental obstacles is obtained as the environmental perception distance; Compare the environmental perception distance with the current braking trigger threshold; When the environmental perception distance is greater than the current braking trigger threshold, a warning prompt is generated based on the distance difference between the environmental perception distance and the current braking trigger threshold; When the environmental perception distance is less than or equal to the current braking trigger threshold, the current vehicle is controlled to make a braking decision.

[0013] Furthermore, to achieve the above objectives, this application also proposes an automatic emergency braking device for vehicles, the device comprising: The information perception module is used to obtain the current road surface adhesion coefficient and real-time load of the vehicle. The braking decision module is used to query a preset braking decision table based on the road surface adhesion coefficient and the real-time load to obtain the current braking trigger threshold. The preset braking decision table is the correspondence between the road surface adhesion coefficient, vehicle load and braking trigger threshold determined according to a preset dynamic safety distance formula at different driving speeds. The execution control module is used to obtain the environmental perception distance corresponding to the current vehicle, compare the environmental perception distance with the current braking trigger threshold, and make a braking decision for the current vehicle based on the comparison result.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium storing a vehicle automatic emergency braking program, which, when executed by a processor, implements the vehicle automatic emergency braking method as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a vehicle equipped with an electronic control unit, the electronic control unit including: a memory, a processor, and a vehicle automatic emergency braking program stored in the memory and executable on the processor, wherein when the vehicle automatic emergency braking program is executed by the processor, it implements the vehicle automatic emergency braking method as described above.

[0016] This application discloses an automatic emergency braking method for a vehicle, which includes: obtaining the road surface adhesion coefficient and real-time load of the current vehicle; querying a preset braking decision table based on the road surface adhesion coefficient and real-time load to obtain the current braking trigger threshold, wherein the preset braking decision table is the correspondence between the road surface adhesion coefficient, vehicle load and braking trigger threshold determined according to a preset dynamic safety distance formula at different driving speeds; obtaining the environmental perception distance corresponding to the current vehicle, comparing the environmental perception distance with the current braking trigger threshold, and making a braking decision for the current vehicle based on the comparison result.

[0017] Because this application can dynamically query the braking trigger threshold matching the current operating conditions based on the real-time sensed road adhesion coefficient and vehicle load, it can adaptively adjust the braking intervention timing for different road conditions and vehicle load states, compared to traditional AEB systems that use fixed thresholds. This effectively avoids the problem of delayed braking and increased collision risk caused by excessively small thresholds under low adhesion or heavy load conditions, while also preventing false triggering or unnecessary emergency braking due to excessively large thresholds under high adhesion or light load conditions. Therefore, it achieves more accurate and reasonable automatic emergency braking decisions under various complex operating conditions, improving vehicle safety and adaptability. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the first embodiment of the automatic emergency braking method for vehicles according to this application; Figure 2 This is a flowchart illustrating the second embodiment of the automatic emergency braking method for vehicles according to this application; Figure 3 This is a flowchart illustrating the third embodiment of the automatic emergency braking method for vehicles according to this application; Figure 4 This is a comparative example diagram of the automatic emergency braking method for vehicles in this application and the traditional braking method; Figure 5 This is a schematic diagram of the module structure of the automatic emergency braking device for the vehicle in this application; Figure 6 This is a schematic diagram of the electronic control unit of this application.

[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0024] This application provides a method for automatic emergency braking of a vehicle, referencing... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the automatic emergency braking method for vehicles according to this application. In this embodiment, the method includes steps S10 to S30: Step S10: Obtain the current road surface adhesion coefficient and real-time load of the vehicle.

[0025] It should be noted that the executing entity in this embodiment can be an Electronic Control Unit (ECU) with functions such as data processing, network communication, and vehicle control, or it can be a control module of other AEB systems capable of realizing vehicle braking control. Here, the control module of the AEB control system (referred to as "system") is selected as an example to illustrate the various embodiments of this application.

[0026] It should be understood that current vehicles can be equipped with cameras and sensors such as millimeter-wave radar / LiDAR. The system can use these sensors to perceive changes in road conditions in real time, thereby determining the coefficient of friction of the road surface. ,Should The value range can typically be between 0.1 (on ice) and 1.0 (on high-performance tires on dry asphalt).

[0027] Road surface adhesion coefficient (road surface adhesion coefficient) This can be a dimensionless physical quantity used to quantify the maximum friction level between the tire and the road surface, which can determine the maximum deceleration the vehicle can achieve during braking. Specifically, the system can collect and analyze data from the vehicle's forward-facing camera and front-facing millimeter-wave radar / LiDAR: using deep learning models (such as ResNet-18) to perform road surface semantic segmentation (dry, wet, snow, ice) on the camera data, and analyzing the scattering intensity characteristics of the ground echo signal based on the radar data (weak scattering indicates a smooth surface, etc.). (The value is low). Therefore, a weighted average fusion calculation method is used to calculate the result. value.

[0028] Real-time load It can measure the total mass of the vehicle, including all loads such as the body, occupants, and cargo. Specifically, the system can read the pressure or height values ​​from the four air suspension height sensors via the CAN bus, and then use the Extended Kalman Filter (EKF) algorithm, based on the vehicle's vertical dynamics model, to output a continuous estimate of the vehicle's mass in real time as the real-time load. .

[0029] Step S20: Based on the driving road surface adhesion coefficient and the real-time load, query the preset braking decision table to obtain the current braking trigger threshold. The preset braking decision table is the correspondence between the road surface adhesion coefficient, vehicle load and braking trigger threshold determined according to the preset dynamic safety distance formula at different driving speeds.

[0030] It should be noted that this preset braking decision table can be a map that is pre-determined and stored in the system through design, calculation, calibration, and testing before the vehicle leaves the factory or before the system is put into operation. This map can include a mapping of the correspondence between road surface adhesion coefficient, vehicle load, and braking trigger threshold at different driving speeds. The row and column indices in this mapping can correspond to different road surface adhesion coefficients. and vehicle load The value stored in each cell is a specific The optimal trigger threshold corresponding to the combination.

[0031] It is understandable that the braking trigger threshold can be the critical criterion for the system to decide whether to initiate automatic emergency braking, and it can be expressed in two equivalent forms: time threshold and distance threshold.

[0032] The time threshold can be a time-to-distance (TTC) threshold, for example, triggering when the predicted collision time is less than 2.5 seconds; the distance threshold can be a safe distance (…). Thresholds, for example, triggered when the actual distance to the vehicle in front is less than 35 meters.

[0033] Specifically, the system can use the aforementioned determined form of road surface adhesion coefficient and real-time load as query input, and obtain the corresponding braking trigger threshold (time threshold or distance threshold) through a preset braking decision table.

[0034] It should also be noted that the aforementioned preset braking decision table can be calculated based on a preset dynamic safety distance formula. This preset dynamic safety distance formula can be a functional model related to the relative speed of the vehicle (the speed difference between the vehicle and the potential collision target in front), the total system delay time, and the dynamic maximum effective deceleration, i.e., the Coupled Safety Distance Model (CSDM), which can be expressed as:

[0035] In the formula, Distance threshold For relative vehicle speed, It is the acceleration due to gravity. For vehicle response delay time, This represents the dynamic maximum effective deceleration.

[0036] Specifically, the system can pre-set several sets of data based on historical experience before the vehicle leaves the factory. This will then benefit each group The corresponding distance threshold is calculated using the above function model.

[0037] In addition, the calculated distance threshold can be converted into a time threshold, and the distance threshold or time threshold can be used as the optimal trigger threshold.

[0038] Finally, by combining the optimal trigger threshold with the aforementioned mapping relationship between vehicle relative speed, road surface adhesion coefficient, and vehicle load, a braking decision table can be constructed so that the vehicle can query it in real time during driving. This allows for quick matching of the current braking trigger threshold that meets the current operating conditions, eliminating the need for complex numerical calculations based on the aforementioned CSDM, which helps improve braking decision efficiency.

[0039] Step S30: Obtain the environmental perception distance corresponding to the current vehicle, compare the environmental perception distance with the current braking trigger threshold, and make a braking decision for the current vehicle based on the comparison result.

[0040] It should be noted that the environmental perception distance can be the actual distance between the vehicle and potential collision targets (vehicles, pedestrians, obstacles) ahead, as measured or calculated in real time by the vehicle's sensors.

[0041] It should be understood that if the current braking trigger threshold is a distance threshold, the distance threshold can be directly compared with the environmental perception distance; if the current braking trigger threshold is a time threshold, the environmental perception distance can be converted into the current predicted collision time by dividing by the relative speed, and then the current predicted collision time can be compared with the time threshold.

[0042] If the environmental perception distance does not exceed the current braking trigger threshold, or if the environmental perception distance differs significantly from the current braking trigger threshold (distance difference / time difference exceeds the preset critical difference), then the vehicle's current operating condition can be determined to be safe, and emergency braking will not be triggered or only a warning will be issued. If the environmental perception distance exceeds the current braking trigger threshold, or if the environmental perception distance differs significantly from the current braking trigger threshold (distance difference / time difference is less than the preset critical difference), it can be determined that there is an emergency risk in the current operating condition of the vehicle. At this time, the system can immediately generate an automatic emergency braking command and send it to the vehicle's brake actuator (such as ESP, iBooster) to control the current vehicle to decelerate or stop.

[0043] In its implementation, the system can obtain the actual perceived distance between the current vehicle and environmental obstacles as the environmental perception distance; compare the environmental perception distance with the current braking trigger threshold; when the environmental perception distance is greater than the current braking trigger threshold, generate a warning prompt based on the distance difference between the environmental perception distance and the current braking trigger threshold; when the environmental perception distance is less than or equal to the current braking trigger threshold, control the current vehicle to make a braking decision.

[0044] This embodiment can dynamically query the braking trigger threshold that matches the current operating conditions based on the real-time sensed road adhesion coefficient and vehicle load. Compared to traditional AEB systems that use fixed thresholds, it can adaptively adjust the braking intervention timing for different road conditions and vehicle load states. This effectively avoids the problem of delayed braking and increased collision risk caused by excessively small thresholds under low adhesion or heavy load conditions. It also prevents false triggering or unnecessary emergency braking caused by excessively large thresholds under high adhesion or light load conditions. Therefore, it achieves more accurate and reasonable automatic emergency braking decisions under various complex operating conditions, improving vehicle safety and adaptability.

[0045] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the automatic emergency braking method for vehicles according to this application.

[0046] In this embodiment, to specifically illustrate how to construct the preset braking decision table, before step S20, the following steps are included: S01~S03: Step S01: Determine several calibration scenarios and corresponding scenario information according to preset calibration requirements. The scenario information includes: calibration driving speed, road surface adhesion coefficient and vehicle load.

[0047] It should be noted that pre-defined calibration requirements can be set by engineers during the vehicle development phase, based on factors such as regulatory requirements, common market operating conditions, and safety redundancy, to define performance targets and coverage. For example, the requirement is that the vehicle can effectively avoid collisions across the entire range of speeds from 20-120 km / h, from unloaded to fully loaded, and with a road surface adhesion coefficient of 0.1 (ice surface) to 0.9 (dry surface).

[0048] It should be understood that since the combination of working conditions is infinite, in engineering, a finite number of representative discrete points can be selected for testing and calculation. That is, different calibration driving speeds, road surface adhesion coefficients and vehicle loads can be selected according to the preset calibration requirements to form several calibration scenarios.

[0049] For example, the calibrated driving speed Three speed points can be selected: 30km / h, 60km / h, and 90km / h; road surface adhesion coefficient Four typical values ​​can be selected: 0.1 (ice), 0.25 (compacted snow), 0.55 (wet asphalt), and 0.85 (dry asphalt); vehicle load capacity. Three mass points can be selected: 1.6t (unloaded), 2.0t (half-loaded), and 2.4t (fully loaded). This allows for the creation of 36 specific calibration scenarios, each consisting of a unique triplet. definition.

[0050] Step S02: Substitute each of the calibrated driving speeds, each of the road surface adhesion coefficients, and each of the vehicle loads into the preset dynamic safety distance formula to obtain the safety distance threshold corresponding to each of the calibrated scenarios as the braking trigger threshold.

[0051] It should be noted that the preset dynamic safety distance formula is the aforementioned CSDM, and can also be expressed as:

[0052] In the formula, The dynamic safety distance value serves as the braking trigger threshold. For the calibrated driving speed, The load capacity of the vehicle. The road surface adhesion coefficient is... It is the acceleration due to gravity. For vehicle response delay time, This is a quality compensation factor.

[0053] in, For dynamic maximum effective deceleration, For the theoretical maximum deceleration, The mass compensation factor (usually set to 0.95~1.10) can be an empirical function based on a large amount of experimental data, used to compensate for differences in braking efficiency, load transfer and suspension response caused by changes in vehicle load.

[0054] It should also be noted that, The total system latency of a vehicle can be composed of several independently measurable components, including processing latency, communication latency, and vehicle braking system pressure build-up latency, and can be expressed as:

[0055] In the formula, This refers to the processing delay, which is the time from when the sensors detect a collision risk to when the ECU issues a braking command. The processing delay primarily depends on the algorithm complexity and the vehicle's load. It is irrelevant and can be considered a constant (usually 50-100ms). This refers to the communication delay, specifically the CAN bus communication time between the ECU and the brake actuator. (And mass) It is irrelevant and can be considered a constant (usually <10ms).

[0056] The pressure build-up delay of the braking system, i.e., the time required from the brake actuator receiving the command to the actual wheel cylinder pressure reaching the target value, can be strongly correlated with the vehicle load m and expressed as:

[0057] In the formula, = k is the target braking pressure, which varies with the vehicle load. linearly increasing, The decompression rate can be a constant determined based on historical empirical data.

[0058] Specifically, in order to determine the parameters in the formula, tests need to be conducted on a braking system test bench: the target pressure P corresponding to different masses m is simulated on the test bench. target And record the time from issuing the command to the pressure reaching P. target Precise time t measured In multiple different P target Repeated tests were conducted to obtain a series of data points (P). target , t measuredThis allows for linear fitting of the data points, thus reducing the pressure build-up delay of the aforementioned braking system. The expression is converted to:

[0059] Among them, slope That is, the pressure build-up rate The reciprocal of the , the intercept This is the inherent delay of the system.

[0060] For example, using specific test data, we can substitute a=2.5 and b=20 into the expression after linear fitting mentioned above.

[0061] Accordingly, substituting the linear expression for the braking system pressure build-up delay into the aforementioned braking system pressure build-up delay, we can obtain:

[0062] Furthermore, it can make , This will ultimately delay the pressure build-up in the braking system. Represented as:

[0063] Where K can be a coefficient obtained through bench testing and calibration, reflecting the direct impact of mass on pressure build-up time, and C can be the system's base delay, reflecting the sum of all mass-independent fixed delays in the vehicle. The total system delay calculated based on the above braking system pressure build-up delay expression can be on the order of milliseconds, for example, 100~200ms.

[0064] Step S03: At each of the specified calibrated driving speeds, establish the correspondence between each of the specified road surface adhesion coefficients, each of the specified vehicle loads, and each of the specified braking trigger thresholds to obtain a preset braking decision table.

[0065] It should be noted that, for the aforementioned calibration scenarios, the specific triples can be defined separately. Substitute the values ​​into the aforementioned CSDM for calculation to obtain the corresponding... This serves as the corresponding braking trigger threshold.

[0066] It should also be noted that, for ease of subsequent queries, different calibrated driving speeds can be used. Generate corresponding two-dimensional lookup tables (MAPs) for each lookup table. The row indexes of these MAPs can be discretized. Values ​​and column indexes can be discretized. Value. And each The value filled in the cell can be the corresponding velocity calculated based on the aforementioned step S02. Distance threshold below (Time threshold obtained from conversion) ).

[0067] Please refer to Table 1 here. Table 1 is a two-dimensional lookup example where the braking trigger threshold is a time threshold.

[0068] Table 1 Example of a 2D lookup table (MAP)

[0069] For example, if the calibrated driving speed By selecting three speed points—30km / h, 60km / h, and 90km / h—a preset braking decision table containing two-dimensional lookup tables MAP_v30, MAP_v60, and MAP_v90 can be obtained. Each two-dimensional lookup table stores the optimal braking trigger threshold for different road conditions and loads at the corresponding speed (as shown in Table 1 above). This preset braking decision table is then burned into the vehicle's electronic control unit (ECU), thereby transforming complex real-time calculations into a pre-calculated result database (preset braking decision table) to meet the real-time requirements of vehicle braking.

[0070] Accordingly, step S20 specifically includes: steps S201~S203: Step S201: Obtain the current driving speed of the current vehicle, and determine the target calibration driving speed from each of the calibration driving speeds based on the current driving speed.

[0071] It should be noted that the current driving speed can be the vehicle's absolute speed relative to the ground (when the potential collision target ahead is stationary) or its relative speed to the potential collision target ahead. This can be obtained from the vehicle's wheel speed sensors or by combining GPS / IMU data.

[0072] It should be understood that since the current driving speed can change in real time during vehicle operation (e.g., the current driving speed is 57 km / h), while the aforementioned calibration speed is a discrete speed point (30 km / h, 60 km / h, 90 km / h), the corresponding target calibration speed can be determined first based on the current driving speed.

[0073] Specifically, the nearest neighbor matching method can be used to find the calibration speed closest to the current speed. For example, if the current speed is 57 km / h and the closest calibration speed is 60 km / h, then the target calibration speed can be determined to be 60 km / h. Alternatively, speed ranges can be set, such as using MAP_v30 when the current speed is 0-45 km / h, MAP_v60 when the current speed is 46-75 km / h, and MAP_v90 when the current speed is above 76 km / h.

[0074] Step S202: Obtain the preset braking decision table corresponding to the target calibrated driving speed.

[0075] Step S203: Using the road surface adhesion coefficient and the real-time load as query inputs, the braking trigger threshold corresponding to the query input is used as the current braking trigger threshold in the preset braking decision table.

[0076] It should be noted that after determining the target calibration speed (e.g., the target calibration speed is 60km / h), the corresponding two-dimensional lookup table (MAP_v60) can be determined from the various two-dimensional lookup tables included in the preset braking decision table.

[0077] It should also be noted that the road surface adhesion coefficient obtained in real time is... and real-time load Even though the values ​​are continuous, while the indexes in the table are discrete, the difference operation can still be used when looking up the table: For example, first, in the MAP_v60 table, find The two nearest discrete μ indices, for example =0.55 and =0.85; Next, find The two nearest discrete Index, for example =2.0t and =2.4t, thus determining the cells at the four corners: ( , (), , (), , (), , Each cell can correspond to a braking trigger threshold.

[0078] Finally, you can directly take the average or weighted average of the braking trigger thresholds in the above four cells (the weights can be based on the road surface adhesion coefficient). The current braking trigger threshold is obtained by considering the proximity of the real-time load m to its respective associated index value.

[0079] Alternatively, a bilinear interpolation method can be used: for example, when the current driving speed is 57 km / h, it can be considered to be between the rated driving speed of 60 km / h and the rated driving speed of 30 km / h. The final current braking trigger threshold can be obtained by interpolating the results obtained from MAP_v60 and MAP_v30 according to the speed ratio, and this embodiment does not impose any restrictions on this.

[0080] This embodiment pre-calculates and calibrates under various calibration scenarios with different combinations of driving speed, road surface adhesion coefficient, and vehicle load based on a dynamic safety distance formula, constructing a pre-set braking decision table that stores corresponding relationships. During actual operation, the system quickly obtains the current braking trigger threshold by querying the corresponding decision table based on the real-time acquired driving speed, road surface adhesion coefficient, and vehicle load. This allows the braking trigger threshold to accurately match the current vehicle speed, road surface conditions, and load status, achieving adaptive and precise decision-making for different operating conditions. It effectively avoids the problems of braking too late under low adhesion or heavy load conditions, or braking too early under high adhesion or light load conditions caused by fixed thresholds, significantly improving the safety and applicability of the automatic emergency braking system under all operating conditions.

[0081] Based on the first and second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to that in embodiments one and two above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the automatic emergency braking method for vehicles according to this application.

[0082] In this embodiment, to specifically illustrate how to obtain the road surface adhesion coefficient of the current vehicle, Step S10 specifically includes: Steps S101~S103: Step S101: Obtain road surface image information through a visual sensor, and determine the first road surface adhesion coefficient estimate and the corresponding first confidence level based on the road surface image information.

[0083] It should be noted that the vision sensor can be the vehicle's forward-facing camera, which can acquire images of the road surface in front of the vehicle, including rich visual features such as texture, color, water stains, ice and snow.

[0084] It should be understood that the system can pre-train or deploy a lightweight convolutional neural network model (such as MobileNetV2) to classify the input road surface image and output the probability distribution of its categories such as "dry asphalt", "wet asphalt", "snow", and "ice": P_dry, P_wet, P_snow, P_ice.

[0085] In addition, a baseline adhesion coefficient can be preset for each road surface type. Value (e.g., dried asphalt) =0.85, wet asphalt =0.60, snow-covered road surface =0.25, ice surface =0.12).

[0086] Accordingly, the estimated value of the first road surface adhesion coefficient can be expressed as: The corresponding first confidence level can be expressed as: .

[0087] The first confidence level reflects the model's confidence in the current classification result. For example, when the image is clear and the features are obvious, the probability of the model classifying it as "dry land" can be as high as 0.95, resulting in a high confidence level; when the lighting is poor or the road surface features are blurred, the probabilities of each category are similar (e.g., all around 0.3), resulting in a low confidence level.

[0088] Step S102: Obtain ground echo signals through radar sensors, and determine the second road surface adhesion coefficient estimate and the corresponding second confidence level based on the ground echo signals.

[0089] It should be understood that radar sensors can refer to millimeter-wave radar or lidar, which can emit electromagnetic waves or lasers towards the ground and receive the echoes. And the smoother the road surface (…), the better. The lower the value, the weaker the radar wave scattering and the lower the echo signal strength.

[0090] Specifically, a linear mapping model can be pre-calibrated based on measured data:

[0091] In the formula, The second road surface adhesion coefficient, and For calibration coefficients, The echo intensity is determined for the ground echo signal. This allows for situations where, for example, a strong radar signal... Approximately 0.8; when the signal is weak, Close to 0.

[0092] Furthermore, the second confidence level, i.e., the radar confidence level, can also be measured based on the stability of the radar estimate. For example, it can be calculated based on the most recent several frames (e.g., 5 frames). The standard deviation of the estimated values. A smaller standard deviation indicates more stable radar readings and higher confidence levels. The higher the confidence level, the more the radar confidence level can be calculated using the following formula: =1 - (last 5 frames) (Standard deviation of the estimated value / 0.5).

[0093] Step S103: Based on the first confidence level and the second confidence level, the estimated value of the first road surface adhesion coefficient and the estimated value of the second road surface adhesion coefficient are weighted and fused to obtain the road surface adhesion coefficient.

[0094] It should be understood that the adaptive weighted average method can be directly used to determine the road surface adhesion coefficient, and the fusion formula for this road surface adhesion coefficient can be expressed as:

[0095] In the formula, That is, the coefficient of adhesion of the road surface. Weight It can be dynamically determined by the confidence levels (first confidence level and second confidence level) of each sensor.

[0096] The visual weights can then be: Radar weights can be: .

[0097] In a practical implementation, the system can determine the visual weight and radar weight based on the first confidence level and the second confidence level, respectively, and then perform multiplication operations with the first road surface adhesion coefficient estimate and the second road surface adhesion coefficient to obtain the driving road surface adhesion coefficient.

[0098] Based on the complementary approach of visual and radar sensors, the road surface adhesion coefficient is determined. In well-lit and clear conditions (such as dry ground during a sunny day), visual confidence is high, and the results are primarily visual, which is advantageous for utilizing its precise classification capabilities. However, in situations with limited vision (such as at night, under strong glare, or in dense fog), or when facing low-light conditions that are difficult to distinguish visually... When dealing with road surfaces (such as light ice and water film), considering that radar operates based on physical scattering characteristics, its confidence level may be higher. In this case, radar judgment can be the primary method, ensuring the system's all-weather working capability.

[0099] Furthermore, to specifically illustrate how to obtain the real-time load m of the current vehicle, step S10 also includes: steps S104~S105: Step S104: Obtain the measured values ​​of the support force of the vehicle suspension system and the vertical acceleration of the vehicle.

[0100] It should be understood that for vehicles equipped with air suspension, the system can directly read the pressure sensor data inside the four air springs via the CAN bus.

[0101] Specifically, the pressure value can be converted into force based on the effective bearing area of ​​each air spring (obtained through calibration): F_i = P_i * A_i. The sum of the supporting forces of the four springs is then the total vertical supporting force F_total on the vehicle. F_total equals the vehicle's weight when stationary or moving at a constant speed, and reflects the resultant force of gravity and inertia when moving dynamically.

[0102] It should be noted that the vehicle's vertical acceleration can be obtained through the onboard inertial measurement unit (IMU), reflecting the vehicle's acceleration a_z in the vertical direction. Positive values ​​indicate upward acceleration, and negative values ​​indicate downward acceleration.

[0103] Step S105: Based on the vehicle vertical dynamics model, using the measured support force and the vertical acceleration as observations, a state estimation algorithm is used to estimate the total mass of the vehicle in real time to obtain the real-time load.

[0104] It should be noted that, based on Newton's second law, the net force on a vehicle in the vertical direction is equal to its mass multiplied by its vertical acceleration. That is: .in, This is the estimated total mass of the vehicle. It is gravitational acceleration.

[0105] Therefore, the measured total support force can be... As an observation Construct the observation equation: ,in, It is observation noise. And... This constitutes the observation matrix.

[0106] Accordingly, since the total mass of the vehicle changes slowly over time, the state equation can be modeled as follows: ,in, This refers to process noise (representing slow changes in quality). In practical implementation, the Extended Kalman Filter (EKF) algorithm can be used to solve the above observation equation and state equation: based on the mass estimate of the previous time step, the mass at the current time step is predicted; and the actual measured mass at the current time step is used to... and Substitute the values ​​and compare them with the predicted values ​​to calculate the Kalman gain. Then, correct the predicted quality value to obtain the optimal estimated quality at the current time. The EKF algorithm outputs at each step. That is, the required real-time load. .

[0107] This embodiment acquires road surface image information and ground echo signals using visual and radar sensors respectively, and independently calculates the estimated road surface adhesion coefficient and its corresponding confidence level. Then, based on the confidence level, the two are adaptively weighted and fused to obtain the driving road surface adhesion coefficient. Simultaneously, by acquiring the vehicle suspension support force and vertical acceleration, and using a state estimation algorithm based on a vertical dynamic model, the total vehicle mass is estimated in real time to obtain the real-time load. This achieves real-time, continuous, and high-precision perception of two key parameters: road surface condition and vehicle load. This provides accurate and reliable input for subsequent adaptive decision-making, ensuring that the automatic emergency braking system can make optimized decisions based on precise real-time operating conditions, effectively improving the system's adaptability to complex and changing environments and the overall reliability of decision-making.

[0108] In addition, you can refer to this place. Figure 4 The automatic emergency braking method of the vehicle applied in this application is compared and explained with the traditional method based on fixed threshold triggering braking. Figure 4 This is a comparative example diagram of the automatic emergency braking method for vehicles in this application and the traditional braking method.

[0109] Depend on Figure 4 It can be seen that, in Figure 4 In the middle, the road surface adhesion coefficient is If the current vehicle is represented as M (the vehicle load is m), then the braking timing determined based on the automatic emergency braking method of this application (the braking timing of this application) can be earlier than the braking timing determined based on the conventional method (the conventional braking timing).

[0110] The distance traveled from the moment the vehicle begins braking in this application to the point where it comes to a complete stop can be the dynamic safety distance determined based on the CSDM of this application. The distance traveled from the start of conventional braking to the point where the vehicle comes to a complete stop can be considered the AEB braking distance determined based on the conventional braking model. .

[0111] In this application, CSDM can be represented as:

[0112] In the formula, Distance threshold For relative vehicle speed, For vehicle response delay time, This represents the dynamic maximum effective deceleration.

[0113] The traditional braking model can be represented as:

[0114] In the formula, For traditional fixed threshold AEB braking distance, For a fixed TTC threshold, The maximum deceleration of a fixed vehicle.

[0115] Due to low adhesion ( Small) and / or heavy load ( Under harsh working conditions (such as large-scale operations), the method described in this application can detect in real time. and m, dynamically calculated It will get longer. It will become smaller, thus reducing the safe distance. Significant growth. The system can therefore be implemented at an earlier time (e.g. Figure 4 As shown, braking is triggered at a position further away from the obstacle, allowing sufficient braking distance for the vehicle to avoid a collision. This enables more precise and rational automatic emergency braking decisions under various complex conditions, improving vehicle safety and adaptability.

[0116] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the automatic emergency braking method for vehicles in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0117] This application also proposes an automatic emergency braking device for vehicles; please refer to [reference needed]. Figure 5 , Figure 5 This is a schematic diagram of the module structure of the automatic emergency braking device for vehicles according to this application. The device includes: The information perception module 501 is used to obtain the current road surface adhesion coefficient and real-time load of the vehicle. The braking decision module 502 is used to query a preset braking decision table based on the driving road surface adhesion coefficient and the real-time load to obtain the current braking trigger threshold. The preset braking decision table is the correspondence between the road surface adhesion coefficient, vehicle load and braking trigger threshold determined according to a preset dynamic safety distance formula at different driving speeds. The execution control module 503 is used to obtain the environmental perception distance corresponding to the current vehicle, compare the environmental perception distance with the current braking trigger threshold, and make a braking decision for the current vehicle based on the comparison result.

[0118] This embodiment of the device can dynamically query the braking trigger threshold that matches the current operating conditions based on the real-time sensed road surface adhesion coefficient and vehicle load. Therefore, compared to traditional AEB systems that use fixed thresholds, it can adaptively adjust the braking intervention timing for different road conditions and vehicle load states. This effectively avoids the problem of delayed braking and increased collision risk caused by excessively small thresholds under low adhesion or heavy load conditions. It also prevents false triggering or unnecessary emergency braking caused by excessively large thresholds under high adhesion or light load conditions. Thus, it achieves more accurate and reasonable automatic emergency braking decisions under various complex operating conditions, improving vehicle safety and adaptability.

[0119] This application also proposes a vehicle equipped with an electronic control unit, the electronic control unit comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the automatic emergency braking method for the vehicle described in Embodiment 1 above.

[0120] The following is for reference. Figure 6 , Figure 6 This is a schematic diagram of the electronic control unit of this application. Figure 6 The electronic control unit shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.

[0121] like Figure 6As shown, the electronic control unit may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the electronic control unit. The processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. The communication device 1009 allows the electronic control unit to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows an electronic control unit with various systems, it should be understood that it is not required to implement or possess all of the systems shown. More or fewer systems may be implemented alternatively.

[0122] The electronic control unit in the vehicle provided in this application, employing the automatic emergency braking method described in the above embodiments, can solve the technical problem of automatic emergency braking of vehicles. Compared with the prior art, the beneficial effects of the vehicle provided in this application are the same as those of the automatic emergency braking method provided in the above embodiments, and other technical features in the electronic control unit of this vehicle are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0123] This application also provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to perform the vehicle automatic emergency braking method in the above embodiments.

[0124] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0125] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described automatic emergency braking method for vehicles, thereby solving the technical problem of the automatic emergency braking method for vehicles. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the automatic emergency braking method for vehicles provided in the above embodiments, and will not be repeated here.

[0126] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other elements in the process, method, article, or system that includes that element.

[0127] The above embodiment numbers are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. They are only some embodiments of this application and do not limit the scope of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included within the protection scope of this application.

Claims

1. A method for automatic emergency braking of a vehicle, characterized in that, The method includes: Obtain the current road surface adhesion coefficient and real-time load of the vehicle; Based on the road surface adhesion coefficient and the real-time load, the current braking trigger threshold is obtained by querying the preset braking decision table. The preset braking decision table is the correspondence between the road surface adhesion coefficient, vehicle load and braking trigger threshold determined according to the preset dynamic safety distance formula at different driving speeds. The environmental perception distance corresponding to the current vehicle is obtained, and the environmental perception distance is compared with the current braking trigger threshold. A braking decision is made for the current vehicle based on the comparison result.

2. The method as described in claim 1, characterized in that, The step of obtaining the road surface adhesion coefficient of the current vehicle includes: Road surface image information is acquired through a visual sensor, and a first road surface adhesion coefficient estimate and a corresponding first confidence level are determined based on the road surface image information. Ground echo signals are acquired by radar sensors, and the estimated value of the second road surface adhesion coefficient and the corresponding second confidence level are determined based on the ground echo signals. Based on the first confidence level and the second confidence level, the estimated values ​​of the first road surface adhesion coefficient and the second road surface adhesion coefficient are weighted and fused to obtain the road surface adhesion coefficient.

3. The method as described in claim 1, characterized in that, The step of obtaining the real-time load of the current vehicle includes: Obtain the support force measurement value of the vehicle suspension system and the vehicle's vertical acceleration; Based on the vehicle's vertical dynamics model, using the measured support force and vertical acceleration as observations, a state estimation algorithm is employed to estimate the vehicle's total mass in real time, thereby obtaining the real-time load.

4. The method as described in claim 1, characterized in that, Before the step of obtaining the current braking trigger threshold by querying the preset braking decision table based on the road surface adhesion coefficient and the real-time load, the method further includes: Several calibration scenarios and corresponding scenario information are determined based on preset calibration requirements. The scenario information includes: calibration driving speed, road surface adhesion coefficient, and vehicle load. Substitute each of the calibration driving speeds, each of the road surface adhesion coefficients, and each of the vehicle loads into the preset dynamic safety distance formula to obtain the safety distance threshold corresponding to each of the calibration scenarios as the braking trigger threshold. At each of the specified calibrated driving speeds, a correspondence is established between each of the specified road surface adhesion coefficients, each of the specified vehicle loads, and each of the specified braking trigger thresholds to obtain a preset braking decision table.

5. The method as described in claim 4, characterized in that, The expression for the preset dynamic safety distance formula is: In the formula, The dynamic safety distance value serves as the braking trigger threshold. For the calibrated driving speed, The load capacity of the vehicle. The road surface adhesion coefficient is... It is the acceleration due to gravity. For vehicle response delay time, This is a quality compensation factor.

6. The method as described in claim 4, characterized in that, The step of obtaining the current braking trigger threshold by querying the preset braking decision table based on the road surface adhesion coefficient and the real-time load includes: Obtain the current driving speed of the current vehicle, and determine the target calibrated driving speed from each of the calibrated driving speeds based on the current driving speed; Obtain the preset braking decision table corresponding to the target calibrated driving speed; Using the road surface adhesion coefficient and the real-time load as query inputs, the braking trigger threshold corresponding to the query input is used as the current braking trigger threshold in the preset braking decision table.

7. The method as described in claim 1, characterized in that, The step of obtaining the environmental perception distance corresponding to the current vehicle, comparing the environmental perception distance with the current braking trigger threshold, and making a braking decision for the current vehicle based on the comparison result includes: The actual perceived distance between the current vehicle and environmental obstacles is obtained as the environmental perception distance; Compare the environmental perception distance with the current braking trigger threshold; When the environmental perception distance is greater than the current braking trigger threshold, a warning prompt is generated based on the distance difference between the environmental perception distance and the current braking trigger threshold; When the environmental perception distance is less than or equal to the current braking trigger threshold, the current vehicle is controlled to make a braking decision.

8. An automatic emergency braking device for a vehicle, characterized in that, The device includes: The information perception module is used to obtain the current road surface adhesion coefficient and real-time load of the vehicle. The braking decision module is used to query a preset braking decision table based on the road surface adhesion coefficient and the real-time load to obtain the current braking trigger threshold. The preset braking decision table is the correspondence between the road surface adhesion coefficient, vehicle load and braking trigger threshold determined according to a preset dynamic safety distance formula at different driving speeds. The execution control module is used to obtain the environmental perception distance corresponding to the current vehicle, compare the environmental perception distance with the current braking trigger threshold, and make a braking decision for the current vehicle based on the comparison result.

9. A storage medium, characterized in that, The storage medium stores a vehicle automatic emergency braking program, which, when executed by a processor, implements the vehicle automatic emergency braking method as described in any one of claims 1 to 7.

10. A vehicle, characterized in that, The vehicle is equipped with an electronic control unit, which includes a memory, a processor, and a vehicle automatic emergency braking program stored in the memory and executable on the processor. When the vehicle automatic emergency braking program is executed by the processor, it implements the vehicle automatic emergency braking method as described in any one of claims 1 to 7.

Images