Vehicle control method and related equipment

Abstract

The invention provides a vehicle control method and related equipment, and the vehicle control method comprises the steps: obtaining a first gradient of a first ramp, a first accelerator opening degree of a target vehicle and a first torque value mapped by the first accelerator opening degree under the condition that a starting operation of the target vehicle on the first ramp is detected; determining a target torque value of a motor in the target vehicle according to the first gradient, the first accelerator opening degree, the first torque value and a prediction model; and controlling the motor to output torque according to the target torque value so as to enable the target vehicle to start from the first ramp. According to the method, the starting efficiency of the vehicle on the ramp is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to a vehicle control method and related equipment. BACKGROUND

[0002] In the modern transportation system, the road environment where vehicles travel is increasingly complex and diverse, and slope driving becomes a frequently encountered scenario in daily driving. Whether it is the ups and downs of streets in cities, winding roads in mountainous areas, or uphill and downhill sections in parking lots, vehicles need to frequently perform slope starting operations. Slope starting seems simple, but it involves many challenges, and its safety and stability are directly related to the life safety of the driver and passengers and the normal operation of the vehicle.

[0003] In the example technology, the starting of the vehicle on the slope is based on the altitude data of the satellite positioning system, and the altitude change rate of the vehicle is obtained through high-precision satellite positioning during the starting process. The slope gradient is calculated in combination with the driving speed. When the altitude change rate increases, it is determined that it is a slope, and the vehicle sets the motor torque compensation value according to the altitude change rate to realize the starting of the vehicle on the slope.

[0004] However, the satellite positioning system has a delay in positioning, which makes the time required for the vehicle to calculate the torque value for slope starting longer, resulting in a longer time for the vehicle to start on the slope, that is, the efficiency of the vehicle starting on the slope is low. SUMMARY

[0005] Based on the above technical status, the present application provides a vehicle control method and related equipment to solve the problem of low efficiency of vehicle starting on a slope.

[0006] In order to achieve the above technical purpose, the present application specifically proposes the following technical solutions:

[0007] In the first aspect, the present application provides a vehicle control method, comprising:

[0008] In the case where it is detected that a target vehicle starts on a first slope, a first slope gradient of the first slope, a first accelerator opening degree of the target vehicle, and a first torque value mapped by the first accelerator opening degree are obtained;

[0009] According to the first slope gradient, the first accelerator opening degree, the first torque value, and a prediction model, a target torque value of a motor in the target vehicle is determined;

[0010] According to the target torque value, the motor is controlled to output torque, so that the target vehicle starts from the first slope.

[0011] In some embodiments, the control of the motor to output torque according to the target torque value comprises:

[0012] comparing the target torque value with a torque threshold value;

[0013] in a case where the target torque value is less than the torque threshold value, gradually increasing a torque value output by the motor and decreasing a brake pressure output by a brake system in the target vehicle each time the torque value output by the motor is increased, wherein the brake system outputs a brake pressure when the target vehicle is parked on the first slope.

[0014] in some embodiments, further comprising:

[0015] in a case where the target vehicle is detected to move backward during the gradual increase of the torque value output by the motor, increasing the torque threshold value to obtain an emergency torque value and maintaining the brake pressure output by the brake system;

[0016] controlling the torque value output by the motor to increase to the emergency torque value.

[0017] in some embodiments, further comprising:

[0018] in a case where the torque value output by the motor is to be increased, obtaining a first acceleration of the target vehicle;

[0019] in a case where the first acceleration of the target vehicle is greater than a first acceleration threshold value, decreasing a preset torque increment to obtain a target torque increment and controlling the motor to increase the torque value output according to the target torque increment;

[0020] in a case where the first acceleration of the target vehicle is less than or equal to the first acceleration threshold value, increasing the torque value output by the motor according to the preset torque increment.

[0021] in some embodiments, the gradually increasing the torque value output by the motor and decreasing the brake pressure output by the brake system in the target vehicle each time the torque value output by the motor is increased, comprises:

[0022] obtaining a friction coefficient of a road on which the target vehicle is located;

[0023] determining a target interval duration according to the friction coefficient, the target interval duration being in a negative correlation with the friction coefficient;

[0024] increasing the torque value output by the motor every interval of the target interval duration and decreasing the brake pressure output by the brake system every interval of the target interval duration.

[0025] in some embodiments, the comparing the target torque value with a torque threshold value, comprises:

[0026] In a case where the target torque value is greater than or equal to a torque threshold value, a torque value of an output of the motor is controlled to be the torque threshold value, and a target delay duration is obtained;

[0027] The brake system output brake pressure is reduced by delaying the target delay duration.

[0028] In some embodiments, the target delay duration is obtained by:

[0029] A difference between the target torque value and the torque threshold value is determined.

[0030] The base delay duration is corrected according to a ratio between the difference and the target torque value to obtain the target delay duration.

[0031] In some embodiments, the base delay duration is corrected according to the ratio between the difference and the target torque value by:

[0032] A friction coefficient of a road surface on which the target vehicle is located is obtained.

[0033] The base delay duration is corrected according to the ratio and the friction coefficient.

[0034] In some embodiments, the method further comprises:

[0035] A second acceleration of the target vehicle is obtained during a process in which the brake system reduces the brake pressure.

[0036] In a case where the second acceleration is greater than a second acceleration threshold value, a torque value of an output of the motor is controlled to be reduced from the torque threshold value to a set torque value.

[0037] In some embodiments, after the brake system output brake pressure is reduced by delaying the target delay duration, the method further comprises:

[0038] In a case where the brake system output brake pressure is reduced to a pressure threshold value, a third acceleration of the target vehicle is obtained.

[0039] In a case where the third acceleration is greater than a third acceleration threshold value, the torque value of the motor output is reduced from the torque threshold value to a set value, and the brake system output brake pressure is increased to a set pressure value.

[0040] In some embodiments, the method further comprises:

[0041] A load of the target vehicle and a target safety coefficient are obtained.

[0042] The torque threshold value is determined according to the load and the target safety coefficient.

[0043] In some embodiments, the determining the target torque value of the motor in the target vehicle according to the first slope, the first accelerator opening, the first torque value, and a prediction model comprises:

[0044] inputting the first slope, the first accelerator opening, and the first torque value into the prediction model to obtain an initial torque value;

[0045] determining an accelerator opening change amount according to the last obtained second accelerator opening and the first accelerator opening;

[0046] in a case where the accelerator opening change amount is greater than a change amount threshold, correcting the initial torque value according to the accelerator opening change amount to obtain the target torque value.

[0047] In some embodiments, before the steps of obtaining the first slope of the first slope, the first accelerator opening of the target vehicle, and the first torque value mapped by the first accelerator opening, the method further comprises:

[0048] obtaining starting data of different training vehicles on different second slopes, the starting data comprising, at each time point in a starting time period, a third accelerator opening corresponding to the training vehicle, a second slope of the second slope, and a second torque value mapped by the third accelerator opening;

[0049] converting the starting data into first time series data according to each time point in the starting data, and compressing or stretching the first time series data in a time dimension to obtain second time series data;

[0050] injecting noise data into the second time series data to obtain third time series data, performing a sliding window operation on the third time series data to obtain a plurality of sliding window data, and determining training samples corresponding to the starting data according to the sliding window data;

[0051] training a preset model according to the training samples corresponding to each of the starting data to obtain the prediction model.

[0052] In a second aspect, the present application provides a vehicle, comprising:

[0053] an obtaining module configured to, in a case where it is detected that a target vehicle is starting on a first slope, obtain a first slope of the first slope, a first accelerator opening of the target vehicle, and a first torque value mapped by the first accelerator opening;

[0054] a determining module configured to determine a target torque value of a motor in the target vehicle according to the first slope, the first accelerator opening, the first torque value, and a prediction model;

[0055] A control module is configured to control the motor to output torque according to the target torque value, so that the target vehicle starts from the first slope.

[0056] In a third aspect, the present application provides an electronic device, comprising a memory and a processor, wherein,

[0057] The memory is connected with the processor, and is configured to store a program;

[0058] The processor is configured to realize the vehicle control method according to the first aspect or any implementation manner of the first aspect by running the program in the memory.

[0059] In a fourth aspect, the present application provides a computer program product, wherein the computer program is executed by a processor to realize the vehicle control method according to the first aspect or any implementation manner of the first aspect.

[0060] In a fifth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to realize the vehicle control method according to the first aspect or any implementation manner of the first aspect.

[0061] The vehicle control method and related device provided by the embodiments of the present application can detect the starting operation of the vehicle on the slope, obtain the slope of the slope, the throttle opening of the vehicle and the torque value mapped by the throttle opening, determine the target torque value of the motor based on the slope, the throttle opening, the torque value and the prediction model, and control the motor to output torque through the target torque value, so that the vehicle starts from the slope. In the present application, the torque value required for the vehicle to start on the slope is determined through the prediction model, without the need for delayed positioning of the position through the satellite positioning system, the determination time of the torque value is reduced, and the starting efficiency of the vehicle on the slope is improved. BRIEF DESCRIPTION OF DRAWINGS

[0062] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of the provided drawings.

[0063] Figure 1 The flow of the vehicle control method provided by the embodiments of the present application Figure One ;

[0064] Figure 2 The flow of the vehicle control method provided by the embodiments of the present application Figure Two ;

[0065] Figure 3 A flow of a vehicle control method provided for an embodiment of the present application Figure Three ;

[0066] Figure 4 A flow of a vehicle control method provided for an embodiment of the present application Figure Four ;

[0067] Figure 5 A flow of a vehicle control method provided for an embodiment of the present application Figure Five ;

[0068] Figure 6 A flow of a vehicle control method provided for an embodiment of the present application Figure Six ;

[0069] Figure 7 A structural schematic diagram of a vehicle provided for an embodiment of the present application

[0070] Figure 8 A structural schematic diagram of an electronic device provided for an embodiment of the present application DETAILED DESCRIPTION

[0071] The technical solution provided in the embodiments of the present application is suitable for the hill start of a vehicle, and aims to solve the problem of low hill start efficiency of the vehicle. By using the technical solution described in the embodiments of the present application, the torque value required for the hill start of the vehicle is determined through a prediction model, without the need for delayed positioning of the position through a satellite positioning system, thereby reducing the determination time length of the torque value and improving the hill start efficiency of the vehicle.

[0072] The technical solution in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0073] It should be noted that the user information (including but not limited to power utilization equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of the related data need to comply with relevant laws, regulations and standards, and provide corresponding operation portals for the user to choose authorization or refusal.

[0074] In the modern transportation system, the road environment where the vehicle travels is increasingly complex and diverse, and hill driving becomes a frequently encountered scene in daily driving. Whether it is the ups and downs of the streets in the city, the winding roads in the mountainous area, or the uphill and downhill sections in the parking lot, the vehicle needs to frequently perform hill starting operation. Hill starting seems simple, but it involves many challenges, and its safety and stability are directly related to the life safety of the driver and passenger and the normal operation of the vehicle.

[0075] In the example technology, the vehicle starts on the hill based on the altitude data of the satellite positioning system, and the vehicle altitude change rate is obtained through high-precision satellite positioning during the starting process. The hill slope is calculated in combination with the driving speed. When the altitude change rate increases, it is determined that it is a hill, and the vehicle sets the motor torque compensation value according to the altitude change rate to realize the starting of the vehicle on the hill.

[0076] However, the satellite positioning system has a delay in positioning, which makes the time required for the vehicle to calculate the torque value for hill starting longer, resulting in a longer time for the vehicle to start on the hill, that is, the efficiency of the vehicle starting on the hill is lower.

[0077] Therefore, the embodiments of the present application aim to provide a vehicle control method and related equipment. When it is detected that the vehicle starts on the hill, the slope of the hill, the throttle opening of the vehicle, and the torque value mapped by the throttle opening are obtained. The target torque value of the motor is determined based on the slope, the throttle opening, the torque value, and a prediction model, and the motor is controlled to output torque through the target torque value to make the vehicle start from the hill. In the present application, the torque value required for the vehicle to start on the hill is determined through the prediction model, without the delay of positioning the position through the satellite positioning system, reducing the determination time of the torque value, and improving the starting efficiency of the vehicle on the hill. The vehicle control method and related equipment provided by the embodiments of the present application can be applied to the hill starting scene of the vehicle.

[0078] In addition, in the example technology, the vehicle starts on the hill based on the wheel speed difference detection. This scheme monitors the wheel speed difference in real time through the wheel speed sensor arranged on the four wheels. When the vehicle is parked on the hill, the system defaults that the rear wheel speed is lower than the front wheel speed (hill sliding trend). The vehicle judges the hill slope according to the wheel speed difference change rate, calculates the required driving torque in combination with the throttle pedal stroke, and maintains the brake pressure through the ESP (Electronic Stability Program, vehicle body electronic stability system) system until the motor torque reaches the threshold value. For example, the vehicle of a certain vehicle model sets the wheel speed difference > 0.3 km / h to trigger the hill assist, and the brake pressure maintaining time is up to 2 seconds.

[0079] The above scheme has the following defects:

[0080] Lag in slope recognition: Wheel speed difference signal relies on the vehicle to generate a slope displacement (about 5-10 cm) to be detected, at which point the brake pressure is restarted, causing a noticeable jerk. In a 15° steep slope test, the average response delay of this scheme is 402 ms, and the slope displacement is more than 15 cm;

[0081] High misjudgment rate in complex working conditions: In non-slope scenarios (such as concave and convex road surfaces, and single-wheel speed reduction zones), the wheel speed difference may be misjudged as a slope signal, causing the brake system to malfunction. A certain vehicle model has a mis-trigger rate of up to 23% in the parking lot deceleration zone, affecting driving smoothness;

[0082] Torque control open-loop characteristics: Without the introduction of an inclination sensor to directly measure the slope, the torque threshold value deviates by up to 25% from the actual demand when the vehicle load suddenly changes (such as loading 500 kg of goods in the trunk), causing the vehicle to roll down the slope when heavily loaded or to surge forward when lightly loaded.

[0083] The above satellite positioning system assisted vehicle also has the following defects:

[0084] Altitude data update delay: The refresh rate of civilian GPS (Global Positioning System) is usually 1 Hz. At a speed of 60 km / h, the vehicle has traveled 16.7 m within the altitude data update interval, which cannot reflect the slope change of a short slope (such as a 20 m long underground garage slope) in real time, causing the torque compensation to lag;

[0085] Multipath effect interference: In urban high-rise valley areas or tunnels, GPS signals are easily affected by reflections, causing multipath errors, and the altitude measurement error can reach ±2 m, which is converted into a slope error of more than 5° in a short distance, causing the torque threshold value to be completely deviated from the actual demand;

[0086] Dependence on external signals: In areas without GPS signals such as tunnels and underground parking lots, this scheme is completely ineffective, with an effective working rate of less than 15% in an underground garage.

[0087] To solve the above problems, the vehicle control method of the present application is proposed. Specifically, the present application systematically solves the core problems of existing slope starting technology in terms of precision, response, adaptability, etc. through the technical combination of "high-precision sensing + threshold division + closed-loop control", achieving zero slope rolling, no forward surge, and smooth starting of the vehicle in the full slope range (0-20%), and filling the technical gap in the field of high-precision slope starting control. For specific details, see the following embodiments.

[0088] Exemplary Method

[0089] Figure 1 The flow of a vehicle control method provided by the embodiments of the present application Figure OneAs shown in Figure 1 The vehicle control method provided by the embodiment includes the following steps.

[0090] In step S101, in a case where it is detected that the target vehicle is starting on the first slope, a first slope of the first slope, a first accelerator opening of the target vehicle, and a first torque value of the first accelerator opening mapping are obtained.

[0091] In the embodiment, in a case where the vehicle is parked on a slope and starting, the vehicle needs to determine the torque value of the motor required for starting. The starting operation includes the ignition of the vehicle and the depression of the accelerator by the driver.

[0092] Specifically, a six-axis tilt sensor is arranged in the vehicle, and the slope of the road where the vehicle is located is obtained through the six-axis tilt sensor. The slope is defined as the first slope, and if the first slope is greater than the slope threshold, it can be determined that the vehicle is parked on the slope. The slope is defined as the first slope.

[0093] In the embodiment, the six-axis tilt sensor can be a six-axis tilt sensor with a resolution of 0.2°. In addition, the sampling rate of the six-axis tilt sensor is 100Hz or even higher.

[0094] The 0.2° resolution reduces the slope detection error from the traditional scheme of >2° to within ±1°, accurately identifies micro-slopes below 0.5° (such as underground garage ramps), and avoids torque threshold deviation caused by slope misjudgment. For example, on a 10° slope, the error of the traditional scheme can be 2°, and the error of the present application is only 1°.

[0095] In addition, the 100Hz sampling rate can capture real-time slope changes of short slopes below 20m (such as garage ramps), and compared with the delay of 16.7m driving distance of the GPS scheme with a refresh rate of 1Hz, zero-delay detection is achieved.

[0096] It should be noted that the 0.2° and 100Hz described above are only used for example and do not limit the parameters of the six-axis tilt sensor, that is, the resolution of the six-axis tilt sensor is less than the resolution threshold, and the sampling rate is greater than the sampling rate threshold.

[0097] When the vehicle is on the first slope and starting, the vehicle obtains the first slope of the first slope, the current accelerator opening of the vehicle, and the torque value of the motor mapped by the accelerator opening. In order to distinguish from other vehicles described below, the vehicle that needs to start on the slope is defined as the target vehicle, the current accelerator opening is defined as the first accelerator opening, and the torque value is defined as the first torque value. The first torque value can be found through the mapping relationship table of the accelerator opening and the torque value.

[0098] In step S102, a target torque value of the motor in the target vehicle is determined according to the first slope, the first throttle opening, the first torque value, and the prediction model.

[0099] The prediction model can be a LSTM (Long Short-Term Memory) model. The neural network model is the core of the prediction model, and its unique gating mechanism can effectively handle long-term dependencies in time series data, which is very suitable for the data of slope θ + throttle opening α + torque output T with time sequence characteristics when starting on a slope.

[0100] The prediction model adopts a three-layer network structure, including an input layer, a hidden layer, and an output layer. The input layer includes 3 neurons corresponding to the input slope θ + throttle opening α + torque output T time series data. The hidden layer is set to two layers, each including 64 LSTM neurons, and a ReLU activation function is introduced to introduce a nonlinear factor and enhance the fitting ability of the model to complex data patterns. The output layer includes one neuron for outputting the optimal torque prediction value T_pred of the motor at the next time.

[0101] The prediction model also introduces a Dropout layer, which randomly deactivates part of the neurons during the training process (with a deactivation rate of 0.2) to prevent model overfitting and improve the generalization ability of the model. At the same time, a batch normalization layer is added between the hidden layer and the output layer to standardize the input data, accelerate the convergence speed of the model, and improve the stability of the model.

[0102] When the first slope, the first torque value, and the first throttle opening are obtained, the target torque value of the motor can be determined based on the first slope, the first torque value, the first throttle opening, and the prediction model.

[0103] In an example, the first torque value, the first throttle opening, and the first slope are input into the prediction model, and the prediction model can output the target torque value of the motor.

[0104] In another example, the first torque value, the first accelerator opening degree, and the first slope are input to the prediction model to obtain an initial torque value output by the prediction model, the target vehicle determines an accelerator opening degree change amount based on the last obtained second accelerator opening degree and the first accelerator opening degree, and if the accelerator opening degree change amount is greater than a change amount threshold, the initial torque value is corrected based on the accelerator opening degree change amount to obtain a target torque value. For example, when the driver deeply presses the accelerator, a from 20% to 50% increase in a is greater than a change amount threshold, and the model output of 450Nm is increased to 500Nm within 10ms. In this way, the motor torque value is dynamically adjusted to make the motor output torque value conform to the current state of the target vehicle.

[0105] In step S103, the motor is controlled to output torque according to the target torque value, so that the target vehicle starts from the first slope.

[0106] After obtaining the target torque value, the target vehicle controls the motor to output torque based on the target torque value, so that the vehicle starts from the first slope. For example, the torque value of the motor can be adjusted to the target torque value.

[0107] In this embodiment, when the vehicle is detected to start on the slope, the slope of the slope, the accelerator opening degree of the vehicle, and the torque value corresponding to the accelerator opening degree are obtained, the target torque value of the motor is determined based on the slope, the accelerator opening degree, the torque value, and the prediction model, and the vehicle starts from the slope by controlling the motor to output torque through the target torque value. In this application, the torque value required for the vehicle to start on the slope is determined by the prediction model, without the need for delayed positioning of the position by the satellite positioning system, reducing the determination time of the torque value and improving the starting efficiency of the vehicle on the slope.

[0108] Figure 2 A vehicle control method provided in the embodiment of the application Figure Two , based on Figure 1 As shown in the embodiment, step S103 includes:

[0109] In step S201, the target torque value is compared with the torque threshold.

[0110] In this embodiment, the target vehicle is provided with a torque threshold, and the target vehicle compares the target torque value with the torque threshold.

[0111] In an example, a preset torque value in the target vehicle is used as the torque threshold.

[0112] In another example, the torque threshold can be dynamically adjusted. The target vehicle obtains its own load and target safety factor, and determines the torque threshold by the load, the first slope and the target safety factor. The torque threshold T_thresh = k x m x g x sin θ, where k is the target safety factor (the base value is 1.1), m is the vehicle load (including the body weight and the load), g is the acceleration of gravity (take 9.8 m / s 2 ), θ is the slope.

[0113] The load of the target vehicle can be determined by the current of the motor. There is a certain linear relationship between the output torque and the current of the motor during the operation of the motor, and the torque is related to the load of the vehicle. According to the principle of motor, the motor output torque T = Kt x I, where Kt is the motor torque constant, and I is the motor current. When starting on a slope, the relationship between the torque T required by the vehicle and the load m and the slope θ is T = k x m x g x sin θ (k is the safety factor). By combining these two formulas, the relationship between the load m and the motor current I can be derived, so as to inversely deduce the load by the motor current. Through a large amount of experimental data, the mapping relationship formula between the motor current and the load is fitted: m = k_m x (I-I_0), where k_m is the current-load conversion coefficient, k_m is obtained by experiment calibration, for example, k_m is 2.1 kg / A; I is the real-time current of the motor; I_0 is the motor current when the vehicle is empty (measured by experiment, different vehicle models have different I_0 values, the I_0 of the vehicle is 50 A). Further, since factors such as battery aging and tire pressure change will affect the mapping relationship between the current and the load, k_m needs to be dynamically calibrated. The vehicle collects the motor current and the actual load (measured by the on-board weighing sensor) data every 50 ms, and updates the k_m value online by using the least square method, to ensure the accuracy of the load inverse deduction. When the target vehicle starts on the first slope, the load of the target vehicle can be obtained by obtaining the flow of the motor.

[0114] In addition, the target safety factor can also be adjusted. The target vehicle is provided with a road surface μ (friction coefficient) estimation module, when a low μ road surface (such as ice and snow road surface μ = 0.2) is detected, the safety factor k is automatically increased (from 1.1 to 1.3), to increase the safety margin of the torque threshold, and to avoid the vehicle from slipping.

[0115] It should be noted that when the load inversely deduced by the motor current suddenly changes (Δm > 50 kg), the system immediately dynamically adjusts the torque threshold formula according to the new load m_new: T_thresh = k x (m_new + 75 kg) x g x sin θ, where 75 kg is the default weight of the driver. For example, when the load suddenly changes from 300 kg to 500 kg, the system completes the adjustment of the torque threshold within 200 ms, to ensure that the torque output can adapt to the change of the load.

[0116] Step S202, in the case that the target torque value is less than the torque threshold value, the torque value output by the motor is gradually increased, and the brake pressure of the brake system in the target vehicle is reduced each time the torque value output by the motor is increased, wherein the brake system outputs the brake pressure when the target vehicle is parked on the first slope.

[0117] When the target torque value is less than the torque threshold value, the cooperative control mode is performed, and the cooperative control mode is a "torque step increase + brake delayed release" mechanism, and the control of the motor and the brake system is performed.

[0118] Specifically, when the target vehicle is parked on the first slope, the brake system in the vehicle outputs a target brake pressure, which can be used to prevent the vehicle from rolling down the slope, and the brake pressure can reduce the vehicle speed during the starting stage to avoid the vehicle moving forward too fast when starting. For example, the brake pressure is greater than the pressure threshold value, for example, the brake pressure is 8 bar.

[0119] The target vehicle controls the torque value output by the motor to gradually increase, and the brake pressure of the brake system is reduced each time the torque value output by the motor is increased, that is, the torque value output by the motor is increased, and the brake pressure is released (reduced). For example, the actual output torque T_out = min(T_pred + ΔT_step x n, T_thresh); brake release progress = T_out / T_thresh x 100%, wherein ΔT_step is a torque increment step, for example, 50 Nm; n is the increment number, for example, 1 increment every 10 ms; the stepwise increase of the torque avoids impact, and the brake pressure is released in proportion to the torque to ensure smooth transition of the power and the brake force.

[0120] Specifically, the torque value output by the motor includes an initial starting stage and a torque chasing stage, and the duration of the initial starting stage is about 0-50 ms. The target vehicle detects that T_pred = 300 Nm < T_thresh = 450 Nm, T_thresh can be an adjusted value, for example, an adjusted value after the load suddenly increases from 300 kg to 500 kg, and immediately triggers the cooperative control mode, that is, enters the initial starting stage, at this time, the brake system maintains the maximum brake pressure (such as 8 bar) to prevent the vehicle from rolling down the slope. The motor starts to increase the torque in steps, for example, outputs 350 Nm at the 10th ms and outputs 400 Nm at the 20th ms.

[0121] The duration of the torque chasing stage is about 50-100 ms, and when T_out reaches 450 Nm (equal to T_thresh), the torque increment is stopped, and at this time, the brake release progress synchronously reaches 100%.

[0122] In addition, a smooth transition phase and a stable start phase can also be included. After the brake release progress synchronization reaches 100%, the wheel speed v change is monitored in real time, and if the wheel speed difference Δv is less than the wheel speed difference threshold, such as Δv < 0.5 km / h, it is determined that the smooth transition state is reached.

[0123] When the actual torque T_out output by the motor is greater than or equal to T_thresh, and this state lasts for a set duration, such as 50 ms, and in addition the brake pressure is completely released, the normal torque control mode is entered, which refers to a mode in which the torque value output by the motor is not gradually increased.

[0124] In addition, the prediction model updates the model according to the real-time collected θ, α, and load m data of the target vehicle, and the target vehicle stabilizes T_out output by the motor within the range of T_thresh ± 20 Nm through PID (Proportion Integration Differentiation) feedback adjustment (proportion coefficient Kp = 0.8).

[0125] In addition, in the case where the torque value output by the motor needs to be increased, the forward surge of the target vehicle needs to be suppressed. Specifically, the target vehicle obtains its own acceleration, which is defined as the first acceleration, which can be the wheel speed acceleration of the target vehicle. When the first acceleration is greater than the first acceleration threshold, such as first acceleration > 0.3g, the target vehicle reduces the preset torque increment to obtain the target torque increment, and the preset torque increment is ΔT_step mentioned above. The target torque increment is, for example, half of the preset torque increment. The target vehicle then controls the motor to increase the torque value output by the motor according to the target torque increment, and after a set duration, it is restored, for example, after 10 ms, the torque value output by the motor is gradually restored. That is, after 10 ms, if the motor needs to increase the output torque, the torque value output by the motor is increased according to the preset torque increment, and before 10 ms, if the motor needs to increase the output torque, the torque value output by the motor is increased according to the target torque increment. When the first acceleration is less than or equal to the first acceleration threshold, the torque value output by the motor is increased according to the preset torque increment.

[0126] Further, when the torque value output by the motor needs to be increased, the friction coefficient of the road on which the target vehicle is located is obtained. When the friction coefficient is less than the friction threshold, the preset torque increment is reduced to obtain the target torque increment, and the preset torque increment is ΔT_step mentioned above. The target torque increment is, for example, half of the preset torque increment. The motor is controlled to increase the torque value output by the motor according to the target torque increment, and the total time of brake release is extended to avoid tire slip. If the friction coefficient is greater than or equal to the friction threshold, the torque value output by the motor is increased according to the preset torque increment.

[0127] The target vehicle is also provided with a coasting prevention mechanism. For example, during the process of gradually increasing the torque value output by the motor, if it is detected that the target vehicle moves backward, the torque threshold value is increased to obtain an emergency torque value, and the brake pressure output by the brake system is maintained; the torque value output by the motor is controlled to increase to the emergency torque value. For example, if it is detected that the vehicle moves backward (the displacement sensor is greater than or equal to 3 cm) during the torque increase process, the brake release is immediately paused, and the torque is increased to 1.1 times of T_thresh (the emergency torque value) at one time, thereby inhibiting the tendency of coasting down the slope.

[0128] In this embodiment, by using the above deep learning-based prediction model, the torque output can be accurately predicted according to historical driving data, the torque threshold value is dynamically adjusted according to the load change, the safety, comfort and adaptability of the vehicle starting on a slope are effectively improved, and the deficiencies of the traditional scheme in terms of individualized matching, load response and extreme working condition processing are solved.

[0129] In this embodiment, when the target torque value is greater than the torque threshold value, the torque value output by the motor is gradually increased, and the brake pressure output by the brake system is reduced each time the torque value of the motor is increased, thereby ensuring smooth transition of the power and braking force of the vehicle.

[0130] Figure 3 A vehicle control method provided in this embodiment Figure Three . Based on the embodiment shown in Figure 2 , step S202 includes:

[0131] In step S301, the friction coefficient of the road where the target vehicle is located is obtained.

[0132] In this embodiment, the torque value is increased every interval of a set time length, and the set time length is the same as the friction coefficient of the road where the target vehicle is located. The smaller the friction coefficient, the more likely the target vehicle is to slip when starting, the longer the release time of the brake pressure of the brake system, and the smaller the torque increased by the motor each time, thereby avoiding vehicle slip.

[0133] To this end, the target vehicle obtains the friction coefficient of the road where it is located. The target vehicle can collect road surface images through its own camera and identify the type of road surface to obtain the friction coefficient associated with the type.

[0134] In step S302, the target interval time length is determined according to the friction coefficient, and the target interval time length and the friction coefficient are in a negative correlation relationship.

[0135] After obtaining the friction coefficient, the target vehicle determines a target interval duration based on the friction coefficient, and the target interval duration. For example, when the road surface is an icy road surface, the friction coefficient is 0.2, and the duration for which the brake system releases the brake pressure is 200 ms. The target vehicle increases the torque value of the motor to the target torque value by 5 times, and therefore, the target interval duration is 50 ms.

[0136] In step S303, the torque value output by the motor is increased every target interval duration, and the brake pressure output by the brake system is reduced every target interval duration.

[0137] After obtaining the target interval duration, the torque value output by the motor is increased every target interval duration, and the brake pressure output by the brake system is reduced every target interval duration.

[0138] In this embodiment, the target interval duration is determined based on the friction coefficient of the road surface on which the vehicle is located, and the target interval duration is negatively correlated with the friction coefficient, so that the vehicle releases the brake pressure for a longer time on a road surface with a smaller friction coefficient, thereby avoiding wheel slip of the vehicle.

[0139] Figure 4 A vehicle control method provided in this embodiment Figure Four Based on any one of the embodiments shown in Figure 2 or Figure 3 , after step S201, the method further includes:

[0140] In step S401, when the target torque value is greater than or equal to the torque threshold value, the torque value output by the motor is controlled to be the torque threshold value, and a target delay duration is obtained.

[0141] In this embodiment, when the target torque value is greater than or equal to the torque threshold value, to avoid vehicle forward movement caused by excessive torque output, a “torque limiting + brake rapid coordination” mechanism is adopted, and the core formula is: actual output torque T_out = T_thresh, brake release delay time = (T_pred-T_thresh) / T_pred x 50 ms. By limiting the actual output torque within the threshold range, and setting the brake release delay time according to the proportion of the predicted torque exceeding the threshold, the stability of starting is ensured.

[0142] Specifically, the target vehicle limits the torque value output by the motor to the torque threshold value, for example, T_pred = 550 Nm > T_thresh = 450 Nm, and immediately limits the actual output torque to 450 Nm. After the target delay duration ends, the brake release phase is entered, and the brake system releases the brake pressure at a speed of 100% / 30 ms, and is completely released within 30 ms.

[0143] In the process of reducing the brake pressure of the brake system, the wheel acceleration of the target vehicle is obtained in real time as the second acceleration, and if the second acceleration is greater than the second acceleration threshold, the torque value output by the motor is set to the torque threshold minus the torque threshold. For example, if the second acceleration is greater than 0.2g, T_out is temporarily reduced to 400Nm, and when the second acceleration returns to normal (the second acceleration is less than or equal to 0.2g), T_out is increased to 450Nm again. G is the acceleration of gravity. When the wheel speed of the target vehicle is stable and there is no obvious forward trend, T_out is maintained at T_thresh. The prediction model continuously updates T_pred based on real-time data such as θ, α, and m. If T_pred falls below T_thresh, the corresponding control mode is automatically switched.

[0144] The target vehicle obtains a target delay duration, which is used to delay the release of brake pressure by the brake system.

[0145] In an example, a preset duration can be used as the target delay duration.

[0146] In another example, the difference between the target torque value and the torque threshold is determined, and the base delay duration is modified based on the ratio between the difference and the target torque value to obtain the target delay duration. For example, T_pred = 550Nm > T_thresh = 450Nm, and the target delay duration = ((550-450) / 550) x 50ms ≈ 9ms, that is, the brake system maintains the brake pressure for 9ms, and the brake pressure is, for example, 6bar. Further, the target vehicle can shorten or lengthen the delay duration of the brake system to release the brake pressure based on the road surface. Specifically, the target vehicle obtains the friction coefficient of the road surface on which the target vehicle is located, and modifies the base delay duration based on the ratio between the difference and the target torque value, and the friction coefficient to obtain the target delay duration. For example, on a dry road surface (μ = 0.8), the brake release delay time can be appropriately shortened, and the minimum is not less than 10ms; on a wet road surface (μ = 0.5), the brake release delay time is maintained or lengthened.

[0147] In step S402, the brake pressure output by the brake system is reduced by delaying for a target delay duration.

[0148] After obtaining the target delay duration, the brake pressure output by the brake system is reduced by delaying for the target delay duration.

[0149] In this embodiment, when the target torque value is greater than or equal to the torque threshold, the torque value output by the motor is set to the torque threshold, and the brake pressure is released after a delay, which avoids the vehicle from forward movement caused by the large torque output by the motor and the small brake pressure, and improves the starting safety of the vehicle.

[0150] Figure 5A flow of a vehicle control method provided for an embodiment of the present application Figure Five . Based on Figure 4 As shown in the embodiment, after step S402, further comprising:

[0151] Step S501, in the case that the brake pressure output by the brake system is reduced to a pressure threshold value, obtaining a third acceleration of the target vehicle.

[0152] In the embodiment, the target vehicle is further provided with a forward surge prevention mechanism. Specifically, in the case that the brake pressure output by the brake system is reduced to a pressure threshold value, it is determined that the brake release of the brake system is complete, and the pressure threshold value is a small value, for example, 0. In this case, the vehicle obtains a forward surge acceleration, which refers to the acceleration of the vehicle and is defined as the third acceleration.

[0153] Step S502, in the case that the third acceleration threshold value is greater than the third acceleration threshold value, reducing the torque value output by the motor from the torque threshold value to a set value, and increasing the brake pressure output by the brake system to a set pressure value.

[0154] In the case that the third acceleration is greater than the third acceleration threshold value, the torque value output by the motor is reduced from the torque threshold value to a set value. For example, if the vehicle forward surge acceleration is detected to be greater than 0.3g, T_out is immediately reduced to 80% of T_thresh. Further, if the brake pressure is less than the pressure set value, the brake pressure is increased to the pressure set value, for example, the brake pressure is increased to 3bar, and after 20ms, the brake pressure is gradually reduced.

[0155] In addition, the prediction model will predict the torque based on the current vehicle state every interval set time (for example, 10ms), and if T_pred is still greater than T_thresh for a plurality of times (for example, three times), the weight of the accelerator opening degree a in the LSTM model is reduced to reduce the prediction deviation.

[0156] In the embodiment, after the brake pressure output by the brake system is reduced to the pressure threshold value, if the acceleration of the vehicle is too large, the torque value output by the motor is reduced to prevent the vehicle from forward surge and improve the driving safety of the vehicle.

[0157] Figure 6 A flow of a vehicle control method provided for an embodiment of the present application Figure Six . Based on Figures 1 to 5 According to any one of the embodiments, before step S101, further comprising:

[0158] In step S601, starting data of different training vehicles on different second slopes is acquired, the starting data including third throttle opening degrees, second slopes and second torque values corresponding to the third throttle opening degrees and the second slopes at each time point of a starting time period of the training vehicle.

[0159] In this embodiment, starting data of different training vehicles on different second slopes is acquired, the starting data including third throttle opening degrees, second slopes and second torque values corresponding to the third throttle opening degrees and the second slopes at each time point of a starting time period of the training vehicle. Specifically, the starting data is derived from the hill starting data of drivers with different driving styles (such as aggressive, smooth and cautious) on different slope scenes (slope 0°-30°, different road conditions such as dry asphalt, wet road, icy road, etc.). For example, 50,000 sets of time series data of slope θ + throttle opening degree α + torque output T can be collected, of which 80% is used for model training and 20% is used for model verification.

[0160] The starting data needs to be constructed into time series data, which needs to be strictly preprocessed before being input into the model. First, the original data is subjected to outlier detection and elimination, and the data exceeding ±3 times the standard deviation of the mean value is regarded as an outlier and eliminated. Then, the data is normalized, and the slope θ (range 0°-30°), throttle opening degree α (range 0%-100%) and torque output T (range 0-1000 Nm) are respectively mapped to the interval [0, 1], and the normalization formula adopted is: x_norm=(x-x_min) / (x_max-x_min), where x is the original data, x_min and x_max are the minimum and maximum values of the data, respectively.

[0161] In addition, the second torque value in the starting data is the optimal torque prediction value T_pred, which refers to the torque value that can enable the vehicle to achieve smooth starting (neither sliding nor forward surging) under the current slope θ, throttle opening degree α and historical torque output T. The determination of this value is based on a large amount of experimental data, and in different slope scenes, the motion state (such as acceleration, displacement, etc.) of the vehicle is monitored in real time by sensors, and when the vehicle is in a smooth starting state, the torque output value at that time is recorded as the optimal torque value for training and verification of the model.

[0162] In step S602, the starting data is converted into first time series data according to each time point in the starting data, and the first time series data is compressed or stretched in the time dimension to obtain second time series data.

[0163] Each time point in the start-up data corresponds to a set of parameters, that is, the slope θ + the accelerator opening degree α + the torque output T. The data from early to late at each time point is sorted to construct time series data, which is defined as first time series data.

[0164] To enhance the generalization ability of the model, each first time series data is enhanced. Specifically, the first time series data is compressed or stretched in time temperature, that is, the second time series data is obtained, and the stretching / compression ratio is between 0.8-1.2.

[0165] Step S603, injecting noise data into the second time series data to obtain third time series data, and performing a sliding window operation on the third time series data to obtain a plurality of sliding window data, and determining the training sample corresponding to the start-up data according to the sliding window data.

[0166] After obtaining the second time series data, noise data is injected into the second time series data to obtain third time series data, and the noise data can be random Gaussian noise. In order to construct time series data samples, a sliding window method is used, the window size is set to 50 (i.e. containing 50 continuous time series data points), the step size is set to 1, each window corresponds to an output torque prediction value T_pred (i.e. the torque value at the next time after the window ends), that is, the sliding window operation is performed on the sliding window third time series data. In this way, the original one-dimensional time series data is converted into two-dimensional sample data suitable for model training (sample number x window size x feature number).

[0167] The third time series data is subjected to a sliding window operation, and a plurality of sliding window data is obtained, each of which can be constructed as a training sample.

[0168] Step S604, training the preset model according to the training sample corresponding to each start-up data to obtain a prediction model.

[0169] After obtaining each training sample, the preset model can be trained based on each training sample to obtain a prediction model. Specifically, the preset model uses mean square error as a loss function, and simultaneously introduces a regularization term and a torque change rate constraint term, and the loss function expression is:

[0170] Loss = MSE(T_pred, T_optimal) + λ1 x L2_regularization + λ2 x |dT_pred / dt|, wherein, MSE(T_pred, T_optimal) is the mean square error between the predicted torque value and the optimal torque value; L2_regularization is an L2 regularization term of the model parameter, used to prevent model overfitting; |dT_pred / dt| is the absolute value of the change rate of the torque prediction value, used to suppress torque mutation and improve driving comfort; λ1 and λ2 are weight coefficients, respectively set to 0.001 and 0.1.

[0171] The optimizer used by the model combines the advantages of momentum gradient descent and adaptive learning rate, and can quickly converge and find the global optimal solution. The initial learning rate is set to 0.001, and the learning rate is exponentially decayed (decay rate is 0.95, decayed once every 10 epochs) as the training round increases.

[0172] The training round is set to 100 and the batch size is set to 32. In the training process, the early stopping method is used, and when the validation set loss does not decrease continuously for 10 epochs, the training is stopped to avoid model overfitting. At the same time, the model parameters are saved once every 5 epochs to facilitate subsequent evaluation and optimization of the model. Epoch refers to the process of traversing the entire training data set once. Each epoch contains multiple iterations, each iteration contains a forward propagation and a backward propagation to update the model weights

[0173] The mean absolute error (MAE), root mean square error (RMSE) and determination coefficient (R 2 ) are used as evaluation indicators of the model. On the test set, the MAE of the model is 15 Nm, the RMSE is 20 Nm, and the R2 is 0.95, indicating that the model has high prediction accuracy and goodness of fit.

[0174] In this embodiment, a plurality of training samples are obtained by enhancing the time series data, and a prediction model is trained based on each training sample to prevent overfitting of the prediction model.

[0175] Exemplary Apparatus

[0176] Corresponding to the vehicle control method described above, the embodiments of the present application also provide a vehicle. Figure 7 is a module schematic diagram of a vehicle provided by the embodiments of the present application. The vehicle 700 provided by the embodiments of the present application comprises:

[0177] The acquisition module 710 is configured to acquire a first slope of the first slope, a first accelerator opening degree of the target vehicle, and a first torque value of the first accelerator opening degree mapping in a case where it is detected that the target vehicle starts on the first slope.

[0178] The determination module 720 is configured to determine a target torque value of the motor in the target vehicle according to the first slope, the first accelerator opening degree, the first torque value, and a prediction model.

[0179] The control module 730 is configured to control the motor to output torque according to the target torque value, so that the target vehicle starts from the first slope.

[0180] In some implementations, the vehicle 700 is further configured to:

[0181] Compare the target torque value with a torque threshold value.

[0182] In a case where the target torque value is less than the torque threshold value, gradually increase the torque value output by the motor, and decrease the brake pressure output by the brake system in the target vehicle each time the torque value output by the motor is increased, wherein the brake system outputs the brake pressure when the target vehicle is parked on the first slope.

[0183] In some implementations, the vehicle 700 is further configured to:

[0184] In a process of gradually increasing the torque value output by the motor, in a case where it is detected that the target vehicle moves backward, increase the torque threshold value to obtain an emergency torque value, and maintain the brake pressure output by the brake system.

[0185] Control the torque value output by the motor to increase to the emergency torque value.

[0186] In some implementations, the vehicle 700 is further configured to:

[0187] In a case where the torque value output by the motor is to be increased, acquire a first acceleration of the target vehicle.

[0188] In a case where the first acceleration of the target vehicle is greater than a first acceleration threshold value, decrease a preset torque increment to obtain a target torque increment, and control the motor to increase the torque value output according to the target torque increment.

[0189] In a case where the first acceleration of the target vehicle is less than or equal to the first acceleration threshold value, increase the torque value output by the motor according to the preset torque increment.

[0190] In some implementations, the vehicle 700 is further configured to:

[0191] Acquire a friction coefficient of a road on which the target vehicle is located.

[0192] The target interval duration is determined according to the friction coefficient, and the target interval duration is in a negative correlation with the friction coefficient.

[0193] The torque value output by the motor is increased every target interval duration, and the brake pressure output by the brake system is decreased every target interval duration.

[0194] In some implementations, the vehicle 700 is further configured to:

[0195] In a case where the target torque value is greater than or equal to the torque threshold value, the torque value output by the motor is controlled to be the torque threshold value, and a target delay duration is obtained.

[0196] The brake pressure output by the brake system is decreased by the target delay duration.

[0197] In some implementations, the vehicle 700 is further configured to:

[0198] A difference between the target torque value and the torque threshold value is determined.

[0199] The base delay duration is corrected according to a ratio between the difference and the target torque value to obtain the target delay duration.

[0200] In some implementations, the vehicle 700 is further configured to:

[0201] A friction coefficient of a road surface on which the target vehicle is located is obtained.

[0202] The base delay duration is corrected according to the ratio and the friction coefficient.

[0203] In some implementations, the vehicle 700 is further configured to:

[0204] A second acceleration of the target vehicle is obtained during a process in which the brake system decreases the brake pressure.

[0205] In a case where the second acceleration is greater than a second acceleration threshold value, the torque value output by the motor is decreased from the torque threshold value to a set torque value.

[0206] In some implementations, the vehicle 700 is further configured to:

[0207] A third acceleration of the target vehicle is obtained in a case where the brake pressure output by the brake system is decreased to a pressure threshold value.

[0208] In a case where the third acceleration is greater than a third acceleration threshold value, the torque value output by the motor is decreased from the torque threshold value to a set value, and the brake pressure output by the brake system is increased to a set pressure value.

[0209] In some implementations, the vehicle 700 is further configured to:

[0210] obtain a load of the target vehicle and a target safety factor;

[0211] determine a torque threshold according to the load and the target safety factor.

[0212] In some implementations, the vehicle 700 is further configured to:

[0213] input the first slope, the first throttle opening and the first torque value into the prediction model to obtain an initial torque value;

[0214] determine a throttle opening change amount according to the last obtained second throttle opening and the first throttle opening;

[0215] in a case where the throttle opening change amount is greater than a change amount threshold, correct the initial torque value according to the throttle opening change amount to obtain a target torque value.

[0216] In some implementations, the vehicle 700 is further configured to:

[0217] obtain start-up data of different training vehicles on different second slopes, the start-up data including, at each time point in a start-up time period of the training vehicle, a third throttle opening corresponding to the training vehicle, a second slope of the second slope and a second torque value mapped by the third throttle opening;

[0218] convert the start-up data into first time series data according to each time point in the start-up data, and compress or stretch the first time series data in a time dimension to obtain second time series data;

[0219] inject noise data into the second time series data to obtain third time series data, perform a sliding window operation on the third time series data to obtain a plurality of sliding window data, and determine a training sample corresponding to the start-up data according to the sliding window data;

[0220] train a preset model according to the training sample corresponding to each start-up data to obtain a prediction model.

[0221] The vehicle provided in this embodiment and the vehicle control method provided in the above embodiments of the present application belong to the same application concept, can execute the vehicle control method provided in any of the above embodiments of the present application, and have the corresponding function modules and beneficial effects of executing the vehicle control method. Technical details not described in detail in this embodiment can be referred to the specific processing content of the vehicle control method provided in the above embodiments of the present application, which will not be described here.

[0222] The functions implemented by each module in the vehicle can be implemented by the same or different processors, which is not limited in the embodiments of the present application.

[0223] It should be understood that the modules in the above vehicle can be implemented in the form of processor calling firmware. For example, the system includes a processor connected with a memory, the memory stores instructions, and the processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of the modules of the device, wherein the processor can be a general processor such as CPU or microprocessor, and the memory can be a memory in the device or a memory outside the system. Alternatively, the modules in the system can be implemented in the form of hardware circuit, and the functions of part or all of the modules can be realized by the design of the hardware circuit, which can be understood as one or more processors; for example, in one implementation, the hardware circuit is ASIC, and the functions of part or all of the modules are realized by the design of the logical relationship of the elements in the circuit; for example, in another implementation, the hardware circuit can be realized by PLD, and taking FPGA as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by a configuration file, so as to realize the functions of part or all of the modules. All the modules of the above vehicle can be realized in the form of processor calling firmware, or realized in the form of hardware circuit, or part of them are realized in the form of processor calling firmware, and the remaining part is realized in the form of hardware circuit.

[0224] In the embodiments of the present application, the processor is a circuit with signal processing capability. In one implementation, the processor can be a circuit with instruction reading and running capability, such as CPU, microprocessor, GPU, or DSP, etc. In another implementation, the processor can realize certain functions through the logical relationship of the hardware circuit, which is fixed or can be reconfigured, such as ASIC or PLD implemented hardware circuit, such as FPGA, etc. In the reconfigurable hardware circuit, the process of the processor loading the configuration document to realize the configuration of the hardware circuit can be understood as the process of the processor loading instructions to realize the functions of part or all of the above modules. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as a kind of ASIC, such as NPU, TPU, DPU, etc.

[0225] It can be seen that each module in the above vehicle can be one or more processors (or processing circuits) configured to implement the above method, such as CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0226] In addition, each module in the above vehicle can be integrated together or can be implemented independently. In one implementation, the modules are integrated together to implement a SOC. The SOC can include at least one processor for implementing any of the above methods or functions of the modules of the apparatus, and the at least one processor can be of different types, such as a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0227] Exemplary Electronic Device

[0228] Another structural diagram of an electronic device is provided in an embodiment of the present application, as shown in Figure 8 The electronic device includes a memory 800 and a processor 810; the memory 800 is connected to the processor 810 and is configured to store a program; the processor 810 is configured to implement the vehicle control method disclosed in any of the above embodiments by running the program stored in the memory 800.

[0229] Specifically, the electronic device can further include a bus, a communication interface 820, an input device 830, and an output device 840. The electronic device can further include a data transceiving module, an image monitoring module, and a signal monitoring module.

[0230] The processor 810, the memory 800, the communication interface 820, the input device 830, and the output device 840 are connected to each other through the bus. Among them:

[0231] The bus can include a path for transmitting information between various components in the electronic device.

[0232] The processor 810 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or can be an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs of the present application. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a ready-to-use programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0233] The processor 810 can include a main processor and can further include a baseband chip, a modem, etc.

[0234] The memory 800 stores programs for implementing the technical solutions of the present application, and can also store operating systems and other key services. Specifically, the programs can include program codes, and the program codes include computer operation instructions. More specifically, the memory 800 can include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk memory, a flash, and the like.

[0235] The input device 830 can include devices that receive data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor, and the like.

[0236] The output device 840 can include devices that allow information to be output to a user, such as a display screen, a printer, a speaker, and the like.

[0237] The communication interface 820 can include devices of the transceiver type or the like for communicating with other devices or communication networks, such as an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), and the like.

[0238] The processor 810 executes the programs stored in the memory 800 and calls other devices, which can be used to implement each step of any vehicle control method provided by the above-described embodiments.

[0239] The embodiments of the present application also propose a chip including a processor and a data interface, the processor reading and running programs stored on a memory through the data interface to execute the vehicle control method introduced in any of the above-described embodiments. The specific processing process and its beneficial effects can be referred to the above-described embodiments of the vehicle control method.

[0240] Exemplary Computer Program Product and Storage Medium

[0241] In addition to the above methods and devices, the embodiments of the present application can also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps of the vehicle control method according to various embodiments of the present application described in any of the above-described embodiments.

[0242] The computer program product can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the remote computing device, as a stand-alone software package, partly on the user's computing device and partly on the remote computing device, or entirely on the remote computing device or server.

[0243] In addition, an embodiment of the present application can also be a storage medium, which stores a computer program, and the computer program is executed by a processor to perform the steps of the vehicle control method according to various embodiments of the present application described in any embodiment of the present specification. Specifically, the steps of the vehicle control method can be implemented.

[0244] For each method embodiment described above, in order to simply describe, it is expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the order of the described actions, because according to the present application, some steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0245] It should be noted that each of the embodiments in the specification is described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same and similar parts between each embodiment can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, it is described more simply, and the relevant parts can be referred to the part of the method embodiment.

[0246] The steps in the method of each embodiment of the present application can be adjusted, combined and reduced in sequence according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0247] The units of the device in each embodiment of the present application can be combined, divided and reduced according to actual needs.

[0248] It should be understood that the disclosed terminal, device and method can be implemented in other ways. For example, the terminal embodiments described above are merely illustrative. For example, the division of modules or sub-modules is merely a logical function division. In actual implementation, another division manner can be used. For example, a plurality of sub-modules or modules can be combined or integrated into another module, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed modules can be indirect coupling or communication connection through some interfaces, devices or modules, and can be electrical, mechanical or other forms.

[0249] The modules or sub-modules described as separate components can or can not be physically separate, and the components of the modules or sub-modules can or can not be physical modules or sub-modules, i.e., can be located in one place or distributed on a plurality of network modules or sub-modules. Some or all of the modules or sub-modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0250] In addition, the functional modules or sub-modules in each embodiment of the present application can be integrated into a processing module, or each module or sub-module can exist physically, or two or more modules or sub-modules can be integrated into one module. The integrated module or sub-module can be realized in the form of hardware or firmware functional module or sub-module.

[0251] The skilled person can further realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized in electronic hardware, computer firmware or a combination of the two. In order to clearly illustrate the interchangeability of hardware and firmware, the composition and steps of the examples have been described in the above description. Whether the functions are realized in hardware or firmware depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0252] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein can be directly implemented by hardware, a firmware unit executed by a processor, or a combination of the two. The firmware unit can be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0253] Finally, it should be noted that, in this document, the term "only" is used simply to set off from one element to another, not to necessarily require or imply any such actual relationship or order between or among the elements. Moreover, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0254] The above description of disclosed embodiments provides enabling concepts for making or using the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A vehicle control method, characterized in that, include: If the starting operation of the target vehicle is detected on the first slope, the first slope of the first slope, the first throttle opening of the target vehicle, and the first torque value mapped by the first throttle opening are obtained. Based on the first slope, the first throttle opening, the first torque value, and the prediction model, the target torque value of the motor in the target vehicle is determined. The motor is controlled to output torque according to the target torque value so that the target vehicle can start from the first ramp.

2. The vehicle control method according to claim 1, characterized in that, The step of controlling the motor to output torque according to the target torque value includes: Compare the target torque value with the torque threshold; When the target torque value is less than the torque threshold, the torque value output by the motor is gradually increased, and the braking pressure of the braking system in the target vehicle is reduced each time the torque value output by the motor is increased. The braking pressure is controlled to be output by the braking system when the target vehicle stops on the first slope.

3. The vehicle control method according to claim 2, characterized in that, Also includes: As the torque output of the motor gradually increases, if the target vehicle is detected to be moving backward, the torque threshold is increased to obtain an emergency torque value, and the braking pressure output by the braking system is maintained. The torque value output by the motor is increased to the emergency torque value.

4. The vehicle control method according to claim 2, characterized in that, Also includes: When the torque value output by the motor needs to be increased, the first acceleration of the target vehicle is obtained; When the first acceleration of the target vehicle is greater than the first acceleration threshold, the preset torque increment is reduced to obtain the target torque increment, and the motor is controlled to increase the output torque value according to the target torque increment; If the first acceleration of the target vehicle is less than or equal to the first acceleration threshold, the torque value output by the motor is increased according to the preset torque increment.

5. The vehicle control method according to claim 2, characterized in that, The step of gradually increasing the torque output of the motor and decreasing the braking pressure of the braking system in the target vehicle each time the torque output of the motor is increased includes: Obtain the coefficient of friction of the road where the target vehicle is located; The target interval duration is determined based on the friction coefficient, and the target interval duration is negatively correlated with the friction coefficient. The torque value output by the motor is increased every time the target interval is elapsed, and the braking pressure output by the braking system is decreased every time the target interval is elapsed.

6. The vehicle control method according to claim 2, characterized in that, The comparison of the target torque value with the torque threshold includes: If the target torque value is greater than or equal to the torque threshold, the torque value of the motor output is controlled to be the torque threshold, and the target delay duration is obtained; Delaying the target delay duration reduces the braking pressure output by the braking system.

7. The vehicle control method according to claim 6, characterized in that, The acquisition of the target delay duration includes: Determine the difference between the target torque value and the torque threshold; The base delay duration is corrected based on the ratio between the difference and the target torque value to obtain the target delay duration.

8. The vehicle control method according to claim 7, characterized in that, The step of correcting the base delay duration based on the ratio between the difference and the target torque value includes: Obtain the coefficient of friction of the road surface where the target vehicle is located; The base delay time is corrected based on the ratio and the friction coefficient.

9. The vehicle control method according to claim 6, characterized in that, Also includes: During the process of the braking system reducing the braking pressure, the second acceleration of the target vehicle is obtained; When the second acceleration is greater than the second acceleration threshold, the torque value output by the motor is controlled to decrease from the torque threshold to the set torque value.

10. The vehicle control method according to claim 6, characterized in that, After the target delay time reduces the braking pressure output by the braking system, the method further includes: When the braking pressure output by the braking system decreases to a pressure threshold, the third acceleration of the target vehicle is obtained; If the third acceleration threshold is greater than the third acceleration threshold, the torque value output by the motor is reduced from the torque threshold to the set value, and the braking pressure output by the braking system is increased to the set pressure value.

11. The vehicle control method according to claim 2, characterized in that, Also includes: Obtain the load capacity and target safety factor of the target vehicle; The torque threshold is determined based on the load and the target safety factor.

12. The vehicle control method according to claim 1, characterized in that, The step of determining the target torque value of the motor in the target vehicle based on the first slope, the first throttle opening, the first torque value, and the prediction model includes: The first slope, the first throttle opening, and the first torque value are input into the prediction model to obtain the initial torque value. Based on the previously obtained second throttle opening and first throttle opening, determine the change in throttle opening; If the change in throttle opening is greater than a threshold value, the initial torque value is corrected based on the change in throttle opening to obtain the target torque value.

13. The vehicle control method according to any one of claims 1-12, characterized in that, Before the steps of obtaining the first slope of the first ramp, the first throttle opening of the target vehicle, and the first torque value mapped by the first throttle opening, the method further includes: Acquire starting data for different training vehicles on different second slopes. The starting data includes the third throttle opening, the second slope of the second slope, and the second torque value mapped by the third throttle opening at each time point of the starting time period. Based on each time point in the starting data, the starting data is converted into first time series data, and the first time series data is compressed or stretched in the time dimension to obtain second time series data. Noise data is injected into the second time series data to obtain the third time series data, and a sliding window operation is performed on the third time series data to obtain multiple sliding window data. The training sample corresponding to the starting data is determined based on the sliding window data. The preset model is trained based on the training samples corresponding to each of the initial data points to obtain the prediction model.

14. A vehicle, characterized in that, include: The acquisition module is used to acquire, when the starting operation of the target vehicle on the first slope is detected, the first slope of the first slope, the first throttle opening of the target vehicle, and the first torque value mapped by the first throttle opening. The determination module is used to determine the target torque value of the motor in the target vehicle based on the first slope, the first throttle opening, the first torque value, and the prediction model. The control module is used to control the motor to output torque according to the target torque value, so that the target vehicle can start from the first ramp.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the vehicle control method as described in any one of claims 1-13.

Images