An uncertainty control method of an automatic emergency braking system

Abstract

The application discloses an uncertainty control method of an automatic emergency braking system, comprising the following steps: (1) arranging a signal collection mechanism, (2) analyzing the source of uncertainty of the automatic emergency braking system and quantifying the source, (3) establishing a safety distance model of the automatic emergency braking system with the introduction of an uncertainty parameter, and (4) constructing a judgment strategy for triggering the braking of the automatic emergency braking system under different scenes with the consideration of uncertainty. The application can solve the safety problems related to the uncertainty of the automatic emergency braking system, thereby improving the safety and reliability of the automatic emergency braking system.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and more specifically to an uncertainty control method for an automatic emergency braking system. Background Technology

[0002] With the increasing number of cars on the road each year, the incidence of traffic accidents is also rising annually, with rear-end collisions being one of the most common. Most serious rear-end collisions are caused by the driver of the following vehicle failing to brake effectively and in a timely manner. Timely braking in dangerous situations can reduce traffic accidents and mitigate their severity. The Automatic Emergency Braking (AEB) system can automatically brake to avoid an impending collision when a potential collision is detected, or mitigate the severity of a collision if it is unavoidable.

[0003] For automatic emergency braking systems, on the one hand, false activation is unacceptable. However, since the calculation of critical distances is based on inaccurate and incomplete environmental perception, uncertainty in the system output is unavoidable. This uncertainty ultimately reflects as uncertainty in braking decisions, causing the automatic emergency braking system to exhibit unexpected braking behavior under certain conditions, leading to danger. On the other hand, currently, the calculation of critical distances under different operating conditions by automatic emergency braking systems is performed in real time by the onboard central processing unit. However, when the vehicle speed is too high, the central processing unit cannot accurately and quickly calculate the critical distance, resulting in a delay in the response of the automatic emergency braking system, which can also lead to related hazards. Summary of the Invention

[0004] The present invention aims to address the problems existing in the prior art by proposing an uncertainty control method for automatic emergency braking systems. This method aims to quantify and analyze the uncertainties of automatic emergency braking systems, thereby solving safety problems caused by uncertainties and improving the safety and reliability of automatic emergency braking systems.

[0005] The specific technical solution of the present invention is as follows:

[0006] The uncertainty control method for an automatic emergency braking system of the present invention is characterized by comprising the following steps:

[0007] Step 1: Deploy the signal collection mechanism;

[0008] The signal collection mechanism includes: a main vehicle speed sensor, a front vehicle speed sensor, a front vehicle deceleration sensor, a vehicle distance sensor, and a road slope sensor;

[0009] The main vehicle speed sensor is installed on one side of the main vehicle's gearbox output shaft to collect the main vehicle's real-time speed.

[0010] The vehicle speed sensor is installed on the front bumper of the main vehicle to collect the real-time speed of the vehicle in front.

[0011] The front vehicle deceleration sensor is installed on the front bumper of the main vehicle to collect the real-time deceleration of the front vehicle;

[0012] The distance sensor is installed on the front bumper of the main vehicle to collect the real-time relative distance between the main vehicle and the vehicle in front;

[0013] The road slope sensor is installed at the front of the vehicle's center of gravity to collect the real-time slope of the road the vehicle is traveling on.

[0014] Step 2: Analyze and quantify the sources of uncertainty in the automatic emergency braking system;

[0015] Step 2.1: Quantify the parameter uncertainties of the automatic emergency braking system:

[0016] The actual speed of the main vehicle is obtained using equations (1) and (2) respectively. and the actual speed of the car in front

[0017]

[0018]

[0019] In equations (1) and (2), v1 is the measured speed of the main vehicle; v2 is the measured speed of the vehicle in front; ε v Let ε represent the measurement error of vehicle speed. v It follows the mathematical expectation of 0 and variance of . Gaussian distribution;

[0020] The true value of the deceleration a2 of the vehicle in front is obtained using equation (3).

[0021]

[0022] In equation (3), a2 is the measured value of the deceleration of the vehicle in front; ε a Let ε be the measurement error of the deceleration a2 of the vehicle in front, and let ε be the measurement error of the deceleration of the vehicle in front. a It follows the mathematical expectation of 0 and variance of . Gaussian distribution;

[0023] The true value of the relative distance between the two vehicles is obtained using equation (4).

[0024]

[0025] In equation (4), d is the measured relative distance between the main vehicle and the vehicle in front; ε d The measurement error is the relative distance between the main vehicle and the vehicle in front, and the measurement error ε d It follows the mathematical expectation of 0 and variance of . Gaussian distribution;

[0026] The true value of the road slope is obtained using equation (5).

[0027]

[0028] In equation (5), θ is the measured value of the road slope for the main vehicle; ε θ The measurement error is ε, which represents the road slope measurement error. θ It follows the mathematical expectation of 0 and variance of . Gaussian distribution;

[0029] Step 2.2: Quantifying the model uncertainty of the automatic emergency braking system:

[0030] The true value of the peak adhesion coefficient of the target road surface is obtained using equation (6).

[0031]

[0032] In equation (6), μ max ε represents the peak adhesion coefficient of the target road surface. μ The estimation error of the road surface adhesion coefficient;

[0033] The wheel slip ratio s is obtained using equation (7):

[0034]

[0035] In equation (7), v is the velocity of the wheel center; r is the wheel radius; and ω is the angular velocity of the wheel.

[0036] The target road surface adhesion coefficient μ is obtained using equation (8):

[0037]

[0038] In equation (8), c1 represents the peak parameter of the road adhesion coefficient curve; e is the natural constant; c2 represents the shape parameter of the road adhesion coefficient curve; and c3 represents the difference parameter of the road adhesion coefficient curve.

[0039] The peak adhesion coefficient μ of the target road surface is obtained using equation (9). max :

[0040]

[0041] In equation (9), μ1 and μ2 are the road adhesion coefficients of two adjacent road surfaces, respectively; μ 1max and μ 2max These are the peak road adhesion coefficients of two adjacent road surfaces;

[0042] The estimation error ε of the road surface adhesion coefficient is obtained using equation (10). μ :

[0043] ε μ =μ-μ max (10)

[0044] Step 3: Establish a safe distance model for the automatic emergency braking system that incorporates uncertain parameters;

[0045] Step 3.1: Use equation (11) to obtain the true value of the maximum braking deceleration of the main vehicle.

[0046]

[0047] In equation (11), G is the weight of the main vehicle; m is the mass of the main vehicle; C is the mass of the main vehicle. D denoted as the air resistance coefficient; A represents the frontal area of ​​the main vehicle.

[0048] Step 3.2: Construct a safety distance model for the automatic emergency braking system when the main vehicle stops later than the preceding vehicle and when the main vehicle stops earlier than the preceding vehicle using equation (12):

[0049]

[0050] In equation (12), d0 is the actual safe distance value of the automatic emergency braking system, t0 is the preset safe distance, and t0 is the braking delay time of the main vehicle. The actual time it takes for the two vehicles to reach the same speed when the main vehicle stops earlier than the preceding vehicle, and includes:

[0051]

[0052] Step 3.4: Process the safety distance model using the Monte Carlo method to obtain the output of the automatic emergency braking system.

[0053] True value of safe distance The probability distribution;

[0054] Step 4: Construct a decision-making strategy for triggering the automatic emergency braking system under different scenarios, taking into account uncertainties;

[0055] Step 4.1: Construct the judgment condition for the relative distance between the two vehicles using equation (14):

[0056]

[0057] Step 4.2: Using the relative distance d between the two vehicles measured in real time by the signal collection mechanism, when d... br When the value is greater than d, the automatic emergency braking system triggers emergency braking, causing the main vehicle to brake at the maximum braking deceleration, where d br This represents the critical relative distance at which the automatic emergency braking system is triggered, taking into account uncertainties, and is obtained by looking up a table.

[0058] The present invention provides an electronic device, including a memory and a processor, wherein the memory is used to store a program that supports the processor in executing the uncertainty control method, and the processor is configured to execute the program stored in the memory.

[0059] The present invention discloses a computer-readable storage medium on which a computer program is stored, wherein the computer program is executed by a processor to perform the steps of the uncertainty control method.

[0060] Compared with existing technologies, the beneficial effects of this invention are reflected in:

[0061] 1. This invention quantifies the uncertainty of automatic emergency braking systems, identifies the uncertainty of the system model and five input parameters from a deterministic model, and determines the error distribution of each uncertainty parameter, thereby avoiding unexpected braking behavior caused by the uncertainty of the automatic emergency braking system.

[0062] 2. This invention provides a determination strategy for triggering automatic emergency braking system braking under different scenarios that takes into account uncertainties. When the vehicle is running, the corresponding critical distance can be obtained from the calibration table according to the corresponding working conditions, which greatly reduces the response time of the automatic emergency braking system and improves the real-time performance and accuracy of the automatic emergency braking system.

[0063] 3. This invention uses the vehicle's native built-in signal collection mechanism, thus without increasing hardware costs. Based on the original braking critical distance model, it realizes the quantitative analysis of the uncertainty of the automatic emergency braking system, and has better usage effect and value. Attached Figure Description

[0064] Figure 1 This is a logic diagram of an uncertainty control method for an automatic emergency braking system according to the present invention.

[0065] Figure 2 This is a diagram illustrating the operation of an automatic emergency braking system.

[0066] Figure 3 The diagram shows the identification results of the maximum adhesion coefficient of asphalt pavement.

[0067] Figure 4 Error diagram of the identification results of the maximum adhesion coefficient of asphalt pavement;

[0068] Figure 5 The speed curves of the two vehicles when the main vehicle brakes to a stop later than the vehicle in front;

[0069] Figure 6 The speed curves of the two vehicles when the main vehicle stops earlier than the vehicle in front;

[0070] Figure 7 A probability distribution diagram of the true critical braking distance when the main vehicle stops later than the vehicle in front;

[0071] Figure 8 A probability distribution diagram of the true critical braking distance when the main vehicle stops earlier than the vehicle in front;

[0072] Figure 9 This diagram illustrates the strategies for determining when to trigger the automatic emergency braking system in different scenarios. Detailed Implementation

[0073] In this embodiment, an uncertainty control method for an automatic emergency braking system is described, such as... Figure 1 The following steps are shown:

[0074] Step 1: Deploy the signal collection mechanism;

[0075] The signal collection mechanism includes: main vehicle speed sensor, front vehicle speed sensor, front vehicle deceleration sensor, distance sensor, and road slope sensor;

[0076] The main vehicle speed sensor is installed on one side of the main vehicle's transmission output shaft to collect the main vehicle's real-time speed.

[0077] The vehicle speed sensor is installed on the front bumper of the main vehicle to collect the real-time speed of the vehicle in front;

[0078] The front vehicle deceleration sensor is installed on the front bumper of the main vehicle to collect the real-time deceleration of the vehicle in front;

[0079] The distance sensor is installed on the front bumper of the main vehicle to collect the real-time relative distance between the main vehicle and the vehicle in front;

[0080] The road slope sensor is installed at the front of the vehicle's center of gravity to collect the real-time slope of the road the vehicle is traveling on;

[0081] Step 2: Analyze and quantify the sources of uncertainty in the automatic emergency braking system;

[0082] Step 2.1: As Figure 2 As shown, the parameter uncertainties of the quantified automatic emergency braking system are:

[0083] Under this operating condition, the actual vehicle speed is obtained using equations (1) and (2) respectively. and the actual speed of the car in front

[0084]

[0085]

[0086] In equations (1) and (2), v1 is the measured speed of the main vehicle; v2 is the measured speed of the vehicle in front; ε v Let ε represent the measurement error of vehicle speed. v It follows the mathematical expectation of 0 and variance of . Gaussian distribution;

[0087] The true value of the deceleration a2 of the vehicle in front is obtained using equation (3).

[0088]

[0089] In equation (3), a2 is the measured value of the deceleration of the vehicle in front; ε a Let ε be the measurement error of the deceleration a2 of the vehicle in front, and let ε be the measurement error of the deceleration of the vehicle in front. a It follows the mathematical expectation of 0 and variance of . Gaussian distribution;

[0090] The true value of the relative distance between the two vehicles is obtained using equation (4).

[0091]

[0092] In equation (4), d is the measured relative distance between the main vehicle and the vehicle in front; ε d The measurement error is the relative distance between the main vehicle and the vehicle in front, and the measurement error ε d It follows the mathematical expectation of 0 and variance of . Gaussian distribution;

[0093] The true value of the road slope is obtained using equation (5).

[0094]

[0095] In equation (5), θ is the measured value of the road slope for the main vehicle; ε θ The measurement error is ε, which represents the road slope measurement error. θ It follows the mathematical expectation of 0 and variance of . Gaussian distribution;

[0096] ε v ε aε d and ε θ The magnitude of the value is influenced by the performance of the corresponding sensor; the smaller the value, the better the sensor performance, and the smaller the uncertainty of the measured parameter. Therefore, given a fixed model, improving the sensor performance can reduce the uncertainty of the model input parameters, and further reduce the uncertainty of the model output.

[0097] Step 2.2: Quantifying the model uncertainty of the automatic emergency braking system:

[0098] The true value of the peak adhesion coefficient of the target road surface is obtained using equation (6).

[0099]

[0100] In equation (6), μ max ε represents the peak adhesion coefficient of the target road surface. μ The estimation error of the road surface adhesion coefficient;

[0101] The wheel slip ratio s is obtained using equation (7):

[0102]

[0103] In equation (7), v is the velocity of the wheel center; r is the wheel radius; and ω is the angular velocity of the wheel.

[0104] The target road surface adhesion coefficient μ is obtained using equation (8):

[0105]

[0106] In equation (8), c1 represents the peak parameter of the road adhesion coefficient curve; e is the natural constant; c2 represents the shape parameter of the road adhesion coefficient curve; and c3 represents the difference parameter of the road adhesion coefficient curve.

[0107] Based on the similar nonlinear variation trend of the adhesion coefficient-slip ratio curve with the slip ratio, especially among two road surfaces with similar adhesion coefficients, the peak adhesion coefficient μ of the target road surface can be obtained using equation (9) based on the analogy. max :

[0108]

[0109] In equation (9), μ1 and μ2 are the road adhesion coefficients of two adjacent road surfaces, respectively; μ 1max and μ 2max These are the peak road adhesion coefficients of two adjacent road surfaces;

[0110] The maximum adhesion coefficient of wet asphalt pavement can be identified based on the parameters of dry cement pavement and wet cobblestone pavement. The identification results are as follows: Figure 3 As shown.

[0111] The estimation error ε of the road surface adhesion coefficient is obtained using equation (10). μ :

[0112] ε μ =μ-μ max (10)

[0113] like Figure 4 As shown, ε is obtained as shown in equation (10). μ -s curve diagram; When a vehicle brakes suddenly, the anti-lock braking system (ABS) typically controls the slip ratio between 10% and 20% to maximize the road surface adhesion coefficient, thus ε μ The range of values ​​is Figure 4 The identification error is 10%-20% with a slip ratio.

[0114] Step 3: Establish a safe distance model for the automatic emergency braking system that incorporates uncertain parameters;

[0115] Step 3.1: Use equation (11) to obtain the true value of the maximum braking deceleration of the main vehicle.

[0116]

[0117] In equation (11), G is the weight of the main vehicle; m is the mass of the main vehicle; C is the mass of the main vehicle. D denoted as the air resistance coefficient; A represents the frontal area of ​​the main vehicle.

[0118] Step 3.2: As Figure 5 , Figure 6 As shown, the safety distance model of the automatic emergency braking system when the main vehicle stops later than the preceding vehicle and when the main vehicle stops earlier than the preceding vehicle is constructed using equation (12):

[0119]

[0120] In equation (12), d0 is the actual safe distance value of the automatic emergency braking system; t0 is the preset safe distance; t0 is the braking delay time of the main vehicle. The actual time it takes for the two vehicles to reach the same speed when the main vehicle stops earlier than the preceding vehicle, and includes:

[0121]

[0122] Step 3.4: Process the safety distance model using the Monte Carlo method to obtain the true safety distance value output by the automatic emergency braking system. probability distribution:

[0123] When the lead vehicle comes to a stop later than the preceding vehicle, the lead vehicle's speed is set to 60 km / h, the preceding vehicle's speed is also set to 60 km / h, and the braking deceleration is set to 8 m / s². 2 Each time the model is run, a randomly generated uncertainty error is input, and the output is statistically analyzed. The obtained probability density distribution is as follows Figure 7 As shown in part (a) of the diagram, the cumulative distribution is as follows: Figure 7 As shown in part (b);

[0124] When the lead vehicle comes to a stop before the preceding vehicle, the lead vehicle's speed is set to 60 km / h, the preceding vehicle's speed is also set to 60 km / h, and the braking deceleration is set to 6 m / s². 2 , The probability density distribution is as follows Figure 8 As shown in part (a) of the diagram, the cumulative distribution is as follows: Figure 8 As shown in part (b);

[0125] Step 4: Construct a decision-making strategy for triggering the automatic emergency braking system under different scenarios, taking into account uncertainties;

[0126] Step 4.1: To ensure driving safety, when the automatic emergency braking system is not triggered, use equation (14) to construct the condition that the relative distance d between the two vehicles should satisfy:

[0127]

[0128] In equation (14), d br This represents the critical relative distance at which the automatic emergency braking system is triggered, taking into account uncertainties.

[0129] Substituting equation (12) into equation (14), we obtain equation (15) which establishes the condition for determining the relative distance between the two vehicles:

[0130]

[0131] From equation (15), the probability density distribution and cumulative distribution of d can be obtained through Monte Carlo simulation. Let p be the unacceptable rate of the automatic emergency braking system, when P(d≥d) br When ) ≥ 1 - p, the probability of an unexpected event occurring in the system is considered acceptable, and d is obtained at this time. br The value is the relative distance at which the automatic emergency braking system is triggered, taking into account uncertainties in the current scenario.

[0132] Step 4.2: As Figure 9 As shown, firstly, under different operating scenarios, the condition P(d≥d) is satisfied. br d ≥ 1-p br Perform calibration and create d brThe calibration table is used, and then the braking deceleration and speed information of the vehicle in front are collected in real time. Based on the collected information, the corresponding d is looked up from the calibration table. br And compare it with the relative distance d between the two vehicles measured in real time by the signal collection mechanism. When d br When the value is greater than d, the automatic emergency braking system triggers emergency braking, causing the main vehicle to brake at the maximum braking deceleration. Although this method sacrifices some storage space, it reduces the complexity of the automatic emergency braking system's decision-making calculations, shortens the decision-making time, and achieves better real-time performance.

[0133] In this embodiment, an electronic device includes a memory and a processor. The memory stores a program that supports the processor in executing the above-described method, and the processor is configured to execute the program stored in the memory.

[0134] In this embodiment, a computer-readable storage medium stores a computer program, which is executed by a processor to perform the steps of the above method.

Claims

1. An uncertainty control method for an automatic emergency braking system, characterized in that, Includes the following steps: Step 1: Deploy the signal collection mechanism; Step 2: Analyze and quantify the sources of uncertainty in the automatic emergency braking system; Step 2.1: Quantify the parameter uncertainties of the automatic emergency braking system; Step 2.2: Quantify the model uncertainty of the automatic emergency braking system; Step 3: Establish a safe distance model for the automatic emergency braking system that incorporates uncertain parameters; Step 3.1: Use equation (11) to obtain the true value of the maximum braking deceleration of the main vehicle. : (11) In equation (11), The weight of the main vehicle; The quality of the main vehicle; This refers to the air drag coefficient; The frontal area of ​​the main vehicle; The true value of the peak adhesion coefficient of the target road surface; This represents the actual value of the road slope. The actual speed of the main vehicle; Step 3.2: Construct a safety distance model for the automatic emergency braking system when the main vehicle stops later than the preceding vehicle and when the main vehicle stops earlier than the preceding vehicle using equation (12): (12) In equation (12), The actual speed of the vehicle in front. slow down the vehicle in front The true value; This represents the actual safe distance value for the automatic emergency braking system. The preset safe distance; The braking delay time of the main vehicle; The actual time it takes for the two vehicles to reach the same speed when the main vehicle stops earlier than the preceding vehicle, and includes: (13) Step 3.4: Process the safety distance model using the Monte Carlo method to obtain the true safety distance value output by the automatic emergency braking system. The probability distribution; Step 4: Construct a decision-making strategy for triggering the automatic emergency braking system under different scenarios, taking into account uncertainties; Step 4.1: Construct the judgment condition for the relative distance between the two vehicles using equation (14): (14) From equation (14), through Monte Carlo simulation, we obtain... The probability density distribution and cumulative distribution of , denoted as For the unacceptable rate of non-compliance of the automatic emergency braking system, the following conditions must be met. time Perform calibration and manufacture Calibration table; Step 4.2: Utilize the real-time relative distance between the two vehicles measured by the signal collection mechanism. ,when At that time, the automatic emergency braking system triggers emergency braking, causing the vehicle to brake at maximum deceleration. This represents the critical relative distance at which the automatic emergency braking system is triggered, taking into account uncertainties, and is obtained by looking up a table.

2. The uncertainty control method for an automatic emergency braking system according to claim 1, characterized in that, Step 1 includes the following steps: The signal collection mechanism includes: a main vehicle speed sensor, a front vehicle speed sensor, a front vehicle deceleration sensor, a vehicle distance sensor, and a road slope sensor; The main vehicle speed sensor is installed on one side of the main vehicle's gearbox output shaft to collect the main vehicle's real-time speed. The vehicle speed sensor is installed on the front bumper of the main vehicle to collect the real-time speed of the vehicle in front. The front vehicle deceleration sensor is installed on the front bumper of the main vehicle to collect the real-time deceleration of the front vehicle; The distance sensor is installed on the front bumper of the main vehicle to collect the real-time relative distance between the main vehicle and the vehicle in front; The road slope sensor is installed at the front of the vehicle's center of gravity to collect real-time slope data of the road the vehicle is traveling on.

3. The uncertainty control method for an automatic emergency braking system according to claim 2, characterized in that, Step 2.1 includes the following steps: The actual speed of the main vehicle is obtained using equations (1) and (2) respectively. and the actual speed of the car in front : (1) (2) In equations (1) and (2), The measured value of the main vehicle speed; This is the measured speed of the vehicle in front; This refers to the measurement error of vehicle speed, and the measurement error of vehicle speed... It follows the mathematical expectation of 0 and variance of . Gaussian distribution; The deceleration of the vehicle in front is obtained using equation (3). The true value : (3) In equation (3), The measured value of the deceleration of the vehicle in front; slow down the vehicle in front The measurement error, and the measurement error of the deceleration of the vehicle in front. It follows the mathematical expectation of 0 and variance of . Gaussian distribution; The true value of the relative distance between the two vehicles is obtained using equation (4). : (4) In equation (4), The measured value of the relative distance between the main vehicle and the vehicle in front; The measurement error is the relative distance between the main vehicle and the vehicle in front, and the measurement error... It follows the mathematical expectation of 0 and variance of . Gaussian distribution; The true value of the road slope is obtained using equation (5). : (5) In equation (5), The measured value of the slope of the road on which the main vehicle travels; This refers to the measurement error of the road slope, and the measurement error... It follows the mathematical expectation of 0 and variance of . The Gaussian distribution.

4. The uncertainty control method for an automatic emergency braking system according to claim 3, characterized in that, Step 2.2 includes the following steps: The true value of the peak adhesion coefficient of the target road surface is obtained using equation (6). : (6) In equation (6), The target road surface peak adhesion coefficient; The estimation error of the road surface adhesion coefficient; The wheel slip ratio is obtained using equation (7). : (7) In equation (7), The speed at the center of the wheel; The radius of the wheel; The angular velocity of the wheel; The target road surface adhesion coefficient is obtained using equation (8). : (8) In equation (8), The peak parameter representing the road surface adhesion coefficient curve; It is a natural constant; The shape parameters of the road surface adhesion coefficient curve; The parameter representing the difference in the road surface adhesion coefficient curve; The peak adhesion coefficient of the target road surface is obtained using equation (9). : (9) In equation (9), and These are the road adhesion coefficients of two adjacent road surfaces; and These are the peak road adhesion coefficients of two adjacent road surfaces; The estimation error of the road surface adhesion coefficient is obtained using equation (10). : (10)。 5. An electronic device, comprising a memory and a processor, characterized in that, The memory is used to store a program that supports the processor in executing any of the uncertainty control methods of claims 1-4, and the processor is configured to execute the program stored in the memory.

6. A computer-readable storage medium storing a computer program thereon, characterized in that, The computer program, when executed by the processor, performs the steps of any one of the uncertainty control methods described in claims 1-3.

Images