A commercial vehicle adaptive cruise vehicle distance adjustment method

Abstract

This invention relates to the field of intelligent vehicle safety technology, specifically to a method for adjusting the distance between vehicles in adaptive cruise control of commercial vehicles. The method involves acquiring various parameters of the commercial vehicle as input variables, building a dual fuzzy recognizer, employing dual fuzzy control rules to classify and fuzzify the input and output variables, and using control experience to apply fuzzy control rules between fuzzy languages ​​to obtain the output variable, vehicle distance. Finally, the adaptive cruise system maintains the distance based on the vehicle distance parameter, reducing the probability of accidents, improving road utilization, and providing the driver with a more comfortable driving experience.

Description

Technical Field

[0001] This invention relates to the field of intelligent vehicle safety technology, specifically to a method for adjusting the distance between vehicles in adaptive cruise control for commercial vehicles. Background Technology

[0002] To address the challenges of efficient cargo transportation and reduce driver fatigue in long-distance logistics, adaptive cruise control for commercial vehicles is necessary. However, ensuring adaptability to time intervals between vehicles during cruise control remains a challenge.

[0003] Existing adaptive cruise control systems have two main limitations regarding following distance. First, the fixed-distance strategy maintains a constant following distance between the vehicle and the vehicle in front, making it difficult to determine a suitable distance to meet various complex driving environments. Second, the variable-distance strategy calculates different following distances depending on changes in the driving environment, which also does not meet the needs of complex and ever-changing driving environments. Summary of the Invention

[0004] The purpose of this invention is to provide a method for adjusting the distance between vehicles in adaptive cruise control of commercial vehicles. The method aims to use dual fuzzy control technology to enable the driver to adaptively maintain the distance between vehicles while working, thereby reducing the probability of accidents.

[0005] To achieve the above objectives, the present invention provides a method for adjusting the distance between vehicles in adaptive cruise control of commercial vehicles, comprising the following steps:

[0006] Obtain vehicle information;

[0007] Using the vehicle information as input variables, a first fuzzy recognizer and a second fuzzy recognizer are built respectively.

[0008] The vehicle spacing is output after comprehensive processing by the first fuzzy recognition device and the second fuzzy recognition device.

[0009] Adaptive cruise control adjusts vehicle control based on the stated distance between vehicles.

[0010] The vehicle information includes relative distance l, relative speed v, commercial vehicle load t, and relative acceleration a, wherein the relative distance l and the relative speed v are used as input variables for a first fuzzy recognizer, and the commercial vehicle load t and the relative acceleration a are used as input variables for a second fuzzy recognizer.

[0011] The process of building the first fuzzy recognition device includes the following steps:

[0012] Using relative distance l and relative velocity v as input variables, the output variable intensity k is used.

[0013] The input and output variables are classified into levels and then fuzzed.

[0014] The fuzzification process employs a combination of trapezoidal and triangular membership functions and a Gaussian membership function.

[0015] The first fuzzy recognizer uses fuzzy control rules between fuzzy languages ​​based on control experience.

[0016] Output the strength k of the variable.

[0017] Specifically, the fuzzy control rules between fuzzy languages ​​in the first fuzzy recognizer are as follows: the larger the relative distance l and the smaller the relative speed v, the smaller the intensity k; the smaller the relative distance l and the larger the relative speed v, the larger the intensity k.

[0018] The process of building the second fuzzy recognizer includes the following steps:

[0019] Using the commercial vehicle load t, relative acceleration a, and intensity k as input variables, the output variable is the vehicle spacing Ls.

[0020] The input and output variables are classified and then fuzzed.

[0021] The second fuzzy recognizer uses fuzzy control rules between fuzzy languages ​​based on control experience.

[0022] The area centroid method was used to blur and sharpen the image.

[0023] Output the clarified variable vehicle spacing Ls.

[0024] Specifically, the fuzzy control rules between the fuzzy languages ​​of the second fuzzy recognizer are as follows: the larger the tonnage t of the commercial vehicle, the larger the relative acceleration a, and the larger the intensity k, the larger the vehicle spacing Ls will be; the smaller the tonnage t of the commercial vehicle, the smaller the relative acceleration a, and the smaller the intensity k, the smaller the vehicle spacing Ls will be.

[0025] This invention provides a method for adjusting the distance between vehicles in adaptive cruise control of commercial vehicles. By acquiring various parameters of the commercial vehicle as input variables, a dual fuzzy recognizer is built. Using dual fuzzy control rules, the input and output variables are classified and fuzzified. Fuzzy control rules between fuzzy languages ​​are obtained through control experience to obtain the output variable, vehicle distance. Finally, the adaptive cruise system maintains the distance based on the vehicle distance parameter, reducing the probability of accidents, improving road utilization, and providing the driver with a more comfortable driving experience. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a flowchart illustrating a method for adjusting the distance between vehicles in adaptive cruise control for commercial vehicles according to the present invention.

[0028] Figure 2 This is a schematic diagram of the fuzzy control process of the present invention.

[0029] Figure 3 This is a schematic diagram of the control flow of the first fuzzy recognizer of the present invention.

[0030] Figure 4 This is a schematic diagram of the control flow of the second fuzzy recognizer of the present invention. Detailed Implementation

[0031] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0032] Please see Figure 1 This invention provides a method for adjusting the distance between vehicles in adaptive cruise control of commercial vehicles, comprising the following steps:

[0033] S1: Obtain vehicle information;

[0034] S2: Using the vehicle information as input variables, build a first fuzzy recognizer and a second fuzzy recognizer respectively;

[0035] S3: The vehicle spacing is output after comprehensive processing by the first fuzzy recognizer and the second fuzzy recognizer;

[0036] S4: Adaptive cruise control adjusts vehicle control based on the stated distance to other vehicles.

[0037] The commercial vehicle adaptive cruise distance adjustment method of this invention processes input and output variables based on a fuzzy control flow. First, the input signal is fuzzified (i.e., the process of obtaining the membership degree of the fuzzy set from the specific input according to the membership function). Then, fuzzy inference is performed to obtain fuzzy conclusions from the fuzzy rules and the membership degrees of the input to the relevant fuzzy sets. Finally, defuzzification is the process of converting the fuzzy conclusions into specific and precise outputs. This patent uses the area centroid method; please refer to [link to relevant documentation] for details. Figure 2 .

[0038] The present invention will be further described below with reference to specific implementation steps:

[0039] First, obtain the required input parameters based on external sensors (camera, millimeter-wave radar) and vehicle sensors: relative distance l, relative speed v, commercial vehicle load t, and relative acceleration a;

[0040] The sensor input information is categorized, and the first fuzzy recognition unit is built. The overall process is as follows: Figure 3 ;

[0041] Step S101: First, take the relative distance l and relative speed v of the commercial vehicle as input quantities, and take the intensity k as output quantity;

[0042] Step S102: Divide the input quantities relative distance l and relative velocity v into five levels.

[0043] The output intensity k is divided into five levels;

[0044] Step S103: Faded out all variables;

[0045] The relative distance l ranges from [0, 150], and the corresponding fuzzy subsets are: negative large (NB), negative small (NS), zero (ZO), positive small (ZS), and positive large (NB), which can be simply represented as {NB, NS, ZO, ZS, NB}.

[0046] The relative velocity v ranges from [-10, 80], and the corresponding fuzzy subsets are: negative large (NB), negative small (NS), zero (ZO), positive small (ZS), and positive large (NB), which can be simply represented as {NB, NS, ZO, ZS, NB}.

[0047] The range of the output intensity k is [0, 1], and the corresponding fuzzy subset is {small, Low, Medium, big, High}, which can be simply represented as {S, L, M, B, H}.

[0048] Trapezoidal and triangular combined membership functions (abbreviated as TT-type membership functions) and Gaussian membership functions are adopted;

[0049] The membership function (trapmf) curve of the trapezoidal function is shown in the following formula.

[0050]

[0051] In the formula, x represents the domain of the parameter, and a, b, c, and d determine the shape of the membership function.

[0052] The membership function (trinmf) curve of a trigonometric function is shown in the following equation:

[0053]

[0054] In the formula, x is the domain of the parameter, and a, b, c determine the shape of the membership function, and satisfy a <b。

[0055] The curve of the Gaussian membership function (gaussmf) is as follows:

[0056]

[0057] In the formula, c is the center point of the Gaussian membership function, and σ determines the width of the function curve;

[0058] Step S104: Establish fuzzy control rules between fuzzy languages ​​based on control experience;

[0059] The fuzzy rule states that the greater the relative distance l, the smaller the relative velocity v, and therefore the weaker the strength; conversely, the smaller the relative distance l, the greater the relative velocity v, and therefore the stronger the strength.

[0060] Table 1. Rule Table for Fuzzy Control

[0061]

[0062] Output intensity k to the second fuzzy recognizer

[0063] Then, the second fuzzy recognition device is built;

[0064] The overall process for building the second fuzzy recognition device is as follows: Figure 4 ;

[0065] Step S201: Using the vehicle's commercial vehicle load tonnage t, relative acceleration a, and intensity k as input quantities, and the vehicle spacing L... s As an output quantity;

[0066] Step S202: Divide the commercial vehicle load tonnage t and relative acceleration a of the vehicle into three levels;

[0067] Output vehicle spacing L s Divided into five levels;

[0068] Step S203: Fadeify all variables;

[0069] The range of the commercial vehicle load tonnage t is [0, 35], and the corresponding fuzzy subsets are: small (S), medium (M), and large (B), which can be simply represented as {S, M, B}.

[0070] The relative acceleration a ranges from [0, 4], and the corresponding fuzzy subsets are: small (S), medium (M), and large (B), which can be simply represented as {S, M, B}.

[0071] Intensity k is controlled using a fuzzy control rule table with 25 rules.

[0072] Output vehicle spacing L s The range is [0, 1], and the corresponding fuzzy subset is {small, Low, Medium, big, High}, which can be simply represented as {S, L, M, B, H};

[0073] Trapezoidal and triangular combined membership functions (abbreviated as TT-type membership functions) and Gaussian membership functions are adopted;

[0074] The membership function (trapmf) curve of the trapezoidal function is shown in the following formula.

[0075]

[0076] In the formula, x represents the domain of the parameter, and a, b, c, and d determine the shape of the membership function.

[0077] The membership function (trinmf) curve of a trigonometric function is shown in the following equation:

[0078]

[0079] In the formula, x is the domain of the parameter, and a, b, c determine the shape of the membership function, and satisfy a <b。

[0080] The curve of the Gaussian membership function (gaussmf) is as follows:

[0081]

[0082] In the formula, c is the center point of the Gaussian membership function, and σ determines the width of the function curve;

[0083] Step S204: Establish fuzzy control rules between fuzzy languages ​​based on control experience;

[0084] The fuzzy rule states that the larger the commercial vehicle's load tonnage t, the greater the relative acceleration a, and the greater the intensity k, the greater the vehicle spacing L. sThe larger the commercial vehicle load tonnage t, the smaller the relative acceleration a, and the smaller the intensity k, the larger the vehicle spacing L will be; s It will be smaller;

[0085] Table 2. Rule Table for Fuzzy Control

[0086]

[0087] Step S205: Blur reduction, using the area centroid method

[0088]

[0089] In the formula, u j For discrete elements of the fuzzy universe, A(u) j ) for u j Membership degree of the location;

[0090] Clear vehicle spacing L s Output is sent to the adaptive cruise control;

[0091] The above description discloses only one preferred embodiment of the present invention, and should not be construed as limiting the scope of the present invention. Those skilled in the art will understand that all or part of the processes of the above embodiments can be implemented, and equivalent changes made in accordance with the claims of the present invention are still within the scope of the invention.

Claims

1. A method for adaptive cruise vehicle distance adjustment for a commercial vehicle, characterized in that, Includes the following steps: Obtain vehicle information; The vehicle information includes relative distance. Relative velocity Commercial vehicle load and relative acceleration The relative distance and the relative velocity The input variables for the first fuzzy recognizer, the commercial vehicle load and the relative acceleration Input variables for the second fuzzy recognizer; Using the vehicle information as input variables, a first fuzzy recognizer and a second fuzzy recognizer are built respectively. The vehicle spacing is output after comprehensive processing by the first fuzzy recognition device and the second fuzzy recognition device. The process of building the first fuzzy recognition device includes the following steps: relative distance and relative velocity As input variables, the strength of output variables ; The input and output variables are classified into levels and then fuzzed. The fuzzification process employs a combination of trapezoidal and triangular membership functions and a Gaussian membership function. The first fuzzy recognizer uses fuzzy control rules between fuzzy languages ​​based on control experience. Output variable intensity ; The process of building a second fuzzy detector includes the following steps: Commercial vehicle load , relative acceleration and strength as input variables, output variable vehicle distance ; The input and output variables are classified and then fuzzed. The second fuzzy recognizer uses fuzzy control rules between fuzzy languages ​​based on control experience. The area centroid method was used to blur and sharpen the image. clearing the variable vehicle distance outputting; Adaptive cruise control adjusts vehicle control based on the stated distance between vehicles.

2. The commercial vehicle adaptive cruise vehicle spacing adjustment method as described in claim 1, characterized in that, The fuzzy control rules between fuzzy languages ​​in the first fuzzy recognizer are specifically relative distances. The larger the relative speed The smaller the value, the stronger the intensity. The smaller; relative distance The smaller the relative speed The larger the value, the stronger the strength. The larger.

3. The commercial vehicle adaptive cruise vehicle spacing adjustment method as described in claim 1, characterized in that, The fuzzy control rules between the fuzzy languages ​​of the second fuzzy recognizer are specifically based on the tonnage of the commercial vehicle load. The larger the relative acceleration Larger, stronger The larger the spacing, the greater the distance between vehicles. The larger it will be; the tonnage of commercial vehicles The smaller the relative acceleration Smaller, stronger The smaller the distance, the better. It will become smaller.

Images