CN115257736B

CN115257736B - Vehicle distance maintenance speed planning method based on fuzzy reasoning true value evolution

Info

Publication number: CN115257736B
Application number: CN202211001373.1A
Authority: CN
Inventors: 孟天闯; 黄晋; 李惠乾; 李星宇; 杨殿阁
Original assignee: Tsinghua University
Current assignee: Tsinghua University
Priority date: 2022-08-19
Filing date: 2022-08-19
Publication date: 2024-06-25
Anticipated expiration: 2042-08-19
Also published as: CN115257736A

Abstract

The application relates to a vehicle distance maintenance speed planning method, a vehicle distance maintenance speed planning device, computer equipment, a storage medium and a computer program product based on fuzzy reasoning true value evolution. The method comprises the following steps: the method comprises the steps of obtaining a current vehicle distance error between a current vehicle distance and an expected vehicle distance and a current vehicle speed error between a current vehicle speed and an expected vehicle speed. And determining the membership of the vehicle distance error corresponding to the current vehicle distance error according to the membership function corresponding to the vehicle distance error, and determining the membership of the vehicle speed error corresponding to the current vehicle speed error according to the membership function corresponding to the vehicle speed error. And determining the acceleration which enables the value of the reasoning loss function to be at the minimum value as the expected acceleration according to the vehicle distance error membership degree, the vehicle speed error membership degree, the membership degree experience function, the membership degree function corresponding to the acceleration and the reasoning loss function. By the method, the accuracy of the expected acceleration can be improved.

Description

Vehicle distance maintenance speed planning method based on fuzzy reasoning true value evolution

Technical Field

The application relates to the technical field of automatic driving, in particular to a vehicle distance maintenance speed planning method based on fuzzy reasoning true value evolution.

Background

With the development of the automatic driving technology, an automatic following technology has emerged, specifically, by adjusting the speed of the own vehicle, to maintain a fixed relative distance from the preceding vehicle.

In the related art, an empirical running speed table is generally established from historical running data of a vehicle, that is, when the speed of a preceding vehicle, the distance between the preceding vehicle and the speed of the own vehicle are within a certain range, the acceleration of the vehicle should be adjusted to a certain desired acceleration. Wherein, the difference of the experience running speed table established by different people is large, so the accuracy of manually establishing the experience running speed table is low.

Because the accuracy of the establishment of the empirical running speedometer directly determines the accuracy of the expected acceleration, the accuracy of the expected acceleration determined in the related art is also low, and the accuracy of vehicle speed planning based on the accuracy is also low.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a vehicle distance maintenance speed planning method, apparatus, computer device, computer readable storage medium and computer program product based on fuzzy inference truth-value evolution, which can improve the accuracy of vehicle speed planning.

In a first aspect, the present application provides a vehicle speed planning method. The method comprises the following steps:

acquiring a current vehicle distance error between a current vehicle distance and an expected vehicle distance and a current vehicle speed error between a current vehicle speed and an expected vehicle speed;

determining a vehicle distance error membership corresponding to the current vehicle distance error according to a membership function corresponding to the vehicle distance error; determining the membership of the vehicle speed error corresponding to the current vehicle speed error according to the membership function corresponding to the vehicle speed error;

Determining acceleration which enables the value of the reasoning loss function to be at the minimum value as the expected acceleration of the vehicle according to the vehicle distance error membership, the vehicle speed error membership, the membership empirical function, the membership function corresponding to the acceleration and the reasoning loss function; the membership empirical function is used for reflecting the relation among the membership of the expected acceleration, the membership of the vehicle speed error and the membership of the vehicle distance error; the reasoning loss function is used for reflecting the degree of loss of the reasoning credibility of the expected acceleration reasoning to the vehicle speed error and the vehicle distance error.

In one embodiment, before determining, as the expected acceleration, the acceleration that makes the value of the inference loss function be at the minimum value according to the vehicle distance error membership, the vehicle speed error membership, the membership empirical function, the membership function corresponding to the acceleration, and the inference loss function, the method further includes:

Acquiring historical driving experience data of the vehicle; the historical experience data comprises acceleration, vehicle distance error and vehicle speed error;

According to the membership function corresponding to the vehicle distance error, the membership function corresponding to the vehicle speed error and the membership function corresponding to the acceleration, determining historical acceleration membership, historical vehicle distance error membership and historical vehicle speed error membership of acceleration, vehicle distance error and vehicle speed error in the historical driving experience data respectively;

fitting according to the historical acceleration membership, the historical vehicle distance error membership and the historical vehicle speed error membership to obtain a membership empirical function for reflecting the relationship among the membership of the expected acceleration, the membership of the vehicle speed error and the membership of the vehicle distance error.

In one embodiment, determining a membership degree of a vehicle distance error corresponding to the current vehicle distance error according to a membership degree function corresponding to the vehicle distance error; before determining the membership of the vehicle speed error corresponding to the current vehicle speed error according to the membership function corresponding to the vehicle speed error, the method further comprises:

respectively acquiring boundary parameters of expected acceleration, vehicle speed error and vehicle distance error;

Constructing a function with boundary parameters conforming to boundary parameters corresponding to the vehicle speed error as a membership function of the vehicle speed error;

constructing a function with boundary parameters conforming to boundary parameters corresponding to the vehicle distance error as a membership function of the vehicle distance error;

and constructing a function with boundary parameters corresponding to the expected acceleration as a membership function corresponding to the expected acceleration.

In one embodiment, the acquiring the boundary parameter of the desired acceleration includes:

Acquiring vehicle data and environment data;

and determining an upper limit acceleration value and a lower limit acceleration value corresponding to the expected acceleration according to the vehicle data and the environment data, and taking the upper limit acceleration value and the lower limit acceleration value as boundary parameters of the expected acceleration.

In one embodiment, the obtaining the boundary parameters of the vehicle speed error and the vehicle distance error includes:

Acquiring a sensitivity setting parameter;

Determining boundary parameters of the vehicle speed error and the vehicle distance error according to the sensitivity setting parameters; the sensitivity setting parameter is inversely proportional to the range of boundary parameters of the vehicle speed error and the vehicle distance error.

In one embodiment, the acquiring the current vehicle distance error between the current vehicle distance and the expected vehicle distance and the current vehicle speed error between the current vehicle speed and the expected vehicle speed includes:

acquiring a current speed of the vehicle, a current distance between the vehicle and a front vehicle, a current speed of the front vehicle and an expected distance between the vehicle and the front vehicle;

And determining a difference between the current speed of the vehicle and the current speed of the front vehicle as a current speed error, and determining a difference between the current distance and the expected distance as a current distance error.

In a second aspect, the application further provides a vehicle distance maintenance speed planning device based on fuzzy reasoning true value evolution. The device comprises:

The acquisition module is used for acquiring a current vehicle distance error between a current vehicle distance and an expected vehicle distance and a current vehicle speed error between a current vehicle speed and an expected vehicle speed;

the membership degree determining module is used for determining the membership degree of the vehicle distance error corresponding to the current vehicle distance error according to the membership degree function corresponding to the vehicle distance error; determining the membership of the vehicle speed error corresponding to the current vehicle speed error according to the membership function corresponding to the vehicle speed error;

The acceleration determining module is used for determining acceleration which enables the value of the reasoning loss function to be at the minimum value as the expected acceleration of the vehicle according to the vehicle distance error membership degree, the vehicle speed error membership degree empirical function, the membership degree function corresponding to the acceleration and the reasoning loss function; the membership empirical function is used for reflecting the relation among the membership of the expected acceleration, the membership of the vehicle speed error and the membership of the vehicle distance error; the reasoning loss function is used for reflecting the degree of loss of the reasoning credibility of the expected acceleration reasoning to the vehicle speed error and the vehicle distance error.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:

According to the vehicle distance maintenance speed planning method, device, computer equipment, storage medium and computer program product based on the fuzzy reasoning true value evolution, the expected acceleration is obtained by reasoning in a mode which accords with the fuzzy reasoning true value non-increasing mode, and compared with the mode in the related technology, the determined expected acceleration accuracy is higher.

Drawings

FIG. 1 is a flow chart of a vehicle distance maintenance speed planning method based on fuzzy inference truth-value evolution in an embodiment;

FIG. 2 is a block diagram of a vehicle distance maintenance speed planning apparatus based on fuzzy inference truth-value evolution in one embodiment;

FIG. 3 is an internal block diagram of a computer device integrated with the interior of a vehicle in one embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

In the related art, an empirical running speed table is generally configured, and the empirical running speed table stores a plurality of conditions and corresponding expected accelerations, for example, the empirical running speed table stores a plurality of vehicle distance states and a plurality of vehicle speed states, any one of safety distance values, two-vehicle collision time values, and probability values of the own vehicle being in each vehicle distance state and probability values of the own vehicle being in each vehicle speed state corresponding to the expected vehicle speed values of the own vehicle. The empirical running speedometer also stores a plurality of vehicle working condition states, preset jerk values corresponding to the vehicle working condition states, vehicle distance states corresponding to the vehicle working condition states and vehicle speed states.

The equipment calculates the probability value of each vehicle working condition state of the own vehicle according to the probability value of each vehicle distance state of the own vehicle and the probability value of each vehicle speed state of the own vehicle through a preset vehicle working condition state probability algorithm, then determines the probability value of each vehicle distance state of the own vehicle and the probability value of each vehicle speed state of the own vehicle according to the safe distance value, the two-vehicle collision time value and the expected vehicle speed value by referring to an empirical running speed table, and then obtains the expected jerk value of the own vehicle according to the probability value of each vehicle working condition state and the preset acceleration value of each vehicle working condition state.

Specifically, among the following four conditions: 1. the distance between the vehicles in front is smaller than a preset distance value, which is a certain determined value between 5 and 20 meters. 2. The two-vehicle collision time value of the own vehicle and the front vehicle is smaller than a preset time value, and the preset time value is a certain determined value between 3 and 10 seconds. 3. The ratio of the distance between the vehicle in front and the safety distance value ds is smaller than a preset threshold value, which is a certain determined value between 30% and 45%. 4. The expected speed value of the host vehicle is smaller than the speed of the host vehicle, and the difference value is larger than or equal to a preset first difference value, wherein the preset first difference value is a certain determined value between 15 km/h and 25 km/h. If the vehicle reaches any one of four conditions, the probability that the vehicle is in a dangerous state is 1, the probability that the vehicle is in other four vehicle distance states is 0 or a certain probability value between 0 and 1, and the specific probability value is the number, so that the device can obtain the vehicle speed table by inquiring experience according to the safe distance value, the two-vehicle collision time value and the expected vehicle speed value.

For another example, the probability that the own vehicle is in a distance dangerous state is not 1 in the following 2 conditions. 2. The expected speed value of the host vehicle is smaller than the speed of the host vehicle, and the difference value is larger than or equal to a preset second difference value which is a certain determined value between 3 km/h and 10 km/h. If the vehicle of the vehicle reaches the two conditions simultaneously, the probability that the vehicle of the vehicle is in a stable distance deceleration state is 1, the probability that the vehicle of the vehicle is in other four vehicle distance states is 0 or a certain probability value between 0 and 1, and the specific probability value is obtained by inquiring an empirical running speedometer according to the safe distance value, the two-vehicle collision time value and the expected vehicle speed value of the vehicle.

Therefore, a large number of manually set conditions and results exist in the empirical running speed table in the related art, on one hand, the rules set by different people are different, the obtained empirical running speed table is different, and on the other hand, the running speed determined according to the uncertain rules is low in accuracy.

Based on the method, the application provides a vehicle distance maintenance speed planning method based on fuzzy reasoning true value evolution.

In order to facilitate understanding of the present application, first, a description will be given of the principle followed by the vehicle distance maintenance speed planning method based on the fuzzy inference truth-value evolution of the present application. In an efficient reasoning process, the true value should be non-increasing, i.e. the result of the next reasoning is based on the previous reasoning, whereas the reasoning process cannot create new knowledge (true value), only an equal amount of knowledge (true value) can be kept or a part of knowledge (true value) is left out, so that the knowledge (true value) which is contained in the next reasoning cannot be more than in the previous reasoning process, should be non-increasing.

Specifically, for a continuous reasoning process T ₁,T₂,T₃,…,T_n, where T _k (k=1, 2,3, …, n) is a conditional proposition in the form of "If a, then B", the true value of which is given by fuzzy implication (Fuzzy Implication) I (a _k,b_k), where a _k is the true value of conditional proposition front a and B _k is the true value of conditional proposition back B, then in the efficient reasoning process the true value I (a _k,b_k) should not be increased.

According to the vehicle distance maintenance speed planning method based on fuzzy reasoning true value evolution, under the condition that a vehicle is taken as an expected acceleration, a vehicle speed error and a vehicle distance error are reduced and tend to be 0 as reasoning targets. First, a current vehicle distance error between a current vehicle distance and an expected vehicle distance and a current vehicle speed error between a current vehicle speed and an expected vehicle speed are obtained. And determining the membership of the vehicle distance error corresponding to the current vehicle distance error according to the membership function corresponding to the vehicle distance error, and determining the membership of the vehicle speed error corresponding to the current vehicle speed error according to the membership function corresponding to the vehicle speed error. And determining the acceleration which enables the value of the reasoning loss function to be at the minimum value as the expected acceleration according to the vehicle distance error membership degree, the vehicle speed error membership degree, the membership degree experience function, the membership degree function corresponding to the acceleration and the reasoning loss function. The membership empirical function is used for reflecting the relation among the membership of the expected acceleration, the membership of the vehicle speed error and the membership of the vehicle distance error, and the reasoning loss function is used for reflecting the reasoning of the expected acceleration to the loss degree of the reasoning credibility of the vehicle speed error and the vehicle distance error. Finally, the vehicle running acceleration is adjusted to the desired acceleration.

According to the vehicle distance maintenance speed planning method based on fuzzy reasoning true value evolution, the value of the reasoning loss function is at the minimum value due to the determined expected acceleration, so that the process of determining the expected acceleration meets the effective reasoning condition that the true value is not increased, namely, the true value is not increased in the effective reasoning process, the determined expected acceleration is more accurate than that in the related technology, and the accuracy of vehicle speed planning is higher when the vehicle speed planning is carried out based on the determined expected acceleration.

The vehicle distance maintenance speed planning method based on fuzzy reasoning true value evolution provided by the embodiment of the application can be applied to computer equipment integrated on a vehicle, and can also be computer equipment on other automatic driving equipment, such as a bicycle, an electric bicycle, automatic driving Internet of things equipment, an unmanned aerial vehicle, an unmanned vehicle and the like.

The application provides a vehicle distance maintenance speed planning method based on fuzzy reasoning true value evolution, a vehicle distance maintenance speed planning device, equipment, a computer readable storage medium and a computer program product based on fuzzy reasoning true value evolution, which correspond to the vehicle distance maintenance speed planning method based on fuzzy reasoning true value evolution. Firstly, the vehicle distance maintenance speed planning method based on fuzzy reasoning true value evolution provided by the application is described in detail.

In one embodiment, as shown in fig. 1, a vehicle distance maintenance speed planning method based on fuzzy inference truth-value evolution is provided, which includes the following steps:

Step 101, acquiring a current vehicle distance error between a current vehicle distance and an expected vehicle distance and a current vehicle speed error between a current vehicle speed and an expected vehicle speed.

The current distance is the distance between the vehicle and the front vehicle. The expected distance is the safe distance the vehicle is expected to maintain from the former. The current vehicle speed is the current running speed of the vehicle. The expected vehicle speed is the desired running vehicle speed of the vehicle, i.e. the running speed of the vehicle to which the vehicle should last be adjusted, typically the current running vehicle speed of the preceding vehicle.

In one embodiment, the apparatus first obtains an expected distance from the vehicle and a current distance from the vehicle ahead, and then obtains a current distance error between the current distance and the expected distance from a difference between the current distance and the expected distance between the vehicle and the vehicle ahead.

Specifically, the device may obtain an expected vehicle distance between the vehicle and the former through an expected vehicle speed input by a user, or determine a safe vehicle distance between the device and the former according to a vehicle speed of the preceding vehicle, and determine the determined safe vehicle distance as the expected vehicle speed. The equipment can determine the distance between the current vehicle and the front vehicle through a shooting system, an infrared system and the like of the vehicle, and obtain the current distance.

In one embodiment, the device may first obtain the current vehicle speed and the expected vehicle speed, and then obtain a vehicle speed error between the current vehicle speed and the expected vehicle speed according to a difference between the current vehicle speed and the expected vehicle speed.

Specifically, the device determines the current running speed of the vehicle through the acceleration sensor of the vehicle, and the current running speed of the vehicle is used as the current speed, or can determine the moving distance of the vehicle in unit time according to the GPS running track, so as to calculate the current speed of the vehicle. The device can determine the change rate of the distance between the vehicle and the front vehicle through a shooting system and the like, then obtain the current running speed of the front vehicle according to the current running speed of the vehicle, and take the current running speed of the front vehicle as the expected speed of the vehicle.

Step 103, determining the membership of the vehicle distance error corresponding to the current vehicle distance error according to the membership function corresponding to the vehicle distance error, and determining the membership of the vehicle speed error corresponding to the current vehicle speed error according to the membership function corresponding to the vehicle speed error.

Wherein, the membership belongs to the concept in the fuzzy evaluation function: fuzzy comprehensive evaluation is a very effective multi-factor decision method for comprehensively evaluating things influenced by multiple factors, and is characterized in that the evaluation result is not absolutely positive or negative, but is represented by a fuzzy set. If there is a number A (x) ∈0,1 corresponding to any element x in the universe (study range) U, then A is referred to as the fuzzy set on U, and A (x) is referred to as the membership of x to A. When x varies in U, A (x) is a function called the membership function of A. The closer the membership A (x) is to 1, the higher the degree that x belongs to A, and the closer A (x) is to 0, the lower the degree that x belongs to A. In the application, the membership function corresponding to the vehicle distance error is used for reflecting the corresponding relation between the vehicle distance error and the vehicle distance error fuzzy set, and the larger the vehicle distance error is, the larger the probability of being affiliated to the vehicle distance error fuzzy set (namely, the larger the membership corresponding to the vehicle distance error is). The membership function corresponding to the vehicle speed error is used for reflecting the corresponding relation between the vehicle speed error and the vehicle speed error fuzzy set, and the greater the vehicle speed error is, the greater the probability of being affiliated to the vehicle speed error fuzzy set (namely, the greater the membership corresponding to the vehicle speed error is). The membership function corresponding to the expected acceleration is used for reflecting the corresponding relation between the acceleration and the acceleration fuzzy set, and the larger the acceleration is, the larger the probability of being affiliated to the acceleration fuzzy set is (namely, the larger the membership of the acceleration to the acceleration is).

Specifically, after the device obtains the current vehicle distance error and the current vehicle speed error, substituting the current vehicle distance error into a membership function corresponding to the vehicle distance error to obtain a membership of the vehicle distance error corresponding to the current vehicle distance error, substituting the current vehicle speed error into a membership function corresponding to the vehicle speed error to obtain a membership of the vehicle speed error corresponding to the current vehicle speed error.

And 105, determining the acceleration which enables the value of the reasoning loss function to be at the minimum value as the expected acceleration of the vehicle according to the membership degree of the vehicle distance error, the membership degree of the vehicle speed error, the membership degree experience function, the membership degree function corresponding to the acceleration and the reasoning loss function.

The membership empirical function is used for reflecting the relation among the membership of the expected acceleration, the membership of the vehicle speed error and the membership of the vehicle distance error, the reasoning loss function is used for reflecting the degree of loss of the reasoning credibility of the expected acceleration reasoning to the vehicle speed error and the vehicle distance error, when the reasoning loss function is at the minimum value, the degree of loss of the reasoning credibility is minimum, and the higher the accuracy of the reasoning result is.

The reasoning loss function is generally a function of the true value of the front part and the true value of the rear part of the reasoning condition proposition, in the application, the reasoning condition is named as "If vehicle acceleration is a, the thenn vehicle interval error e _x and the vehicle speed error e _v are reduced and tend to be 0", the true value function corresponding to the front part of the "vehicle acceleration is a" is mu _F (a), the true value function corresponding to the rear part of the "vehicle interval error e _x and the vehicle speed error e _v are reduced and tend to be 0" is f (x), so as to blur the true value contained as the "If-thenn" condition proposition, and Lukasiewicz fuzzy implications are selected, namely, the true value of the "If-thenn" condition proposition is z=I (x, f (x))=1-x+xf (x).

Specifically, after determining the membership degree of the vehicle speed error and the membership degree of the vehicle distance error, the equipment substitutes the membership degree of the vehicle speed error and the membership degree of the vehicle distance error into a membership degree empirical function to obtain the acceleration membership degree of the expected acceleration, substitutes the membership degree of the vehicle speed error, the membership degree of the vehicle distance error and the membership degree of the acceleration into an inference loss function at the moment, so that the inference loss function is at a minimum value, substitutes the acceleration membership degree into a membership degree function of the expected acceleration, and determines the obtained acceleration as the expected acceleration of the vehicle.

In one embodiment, after determining the vehicle speed error membership corresponding to the current vehicle speed error and the vehicle distance error membership corresponding to the current vehicle distance error, the device determines the acceleration membership corresponding to the expected acceleration through the correspondence (the membership experience function) among the vehicle speed error membership, the vehicle distance error membership and the acceleration membership, and then substitutes the determined acceleration membership into the membership function corresponding to the expected acceleration to obtain the expected acceleration of the vehicle, and at the moment, substitutes the acceleration membership of the expected acceleration, the vehicle speed error membership corresponding to the current vehicle speed error and the vehicle distance error membership corresponding to the current vehicle distance error into the reasoning loss function to enable the reasoning loss function to be at the minimum.

In one embodiment, after determining the expected acceleration of the vehicle, the device sends an instruction corresponding to the expected acceleration to the connected steer-by-wire, throttle, brake, etc., so that the running acceleration of the vehicle is adjusted to the expected acceleration in cooperation with the steer-by-wire, throttle, brake, etc.

According to the vehicle distance maintenance speed planning method based on fuzzy reasoning true value evolution, provided by the application, the expected acceleration which enables the value of a reasoning loss function to be at the minimum value is determined by establishing a reasonable reasoning process instead of relying on an empirical running speed table, so that the process of determining the expected acceleration accords with the effective reasoning condition of true value non-increment, namely, the true value is not increased in the effective reasoning process, and therefore, the determined expected acceleration is more accurate relative to the vehicle speed planning in the related art, and the accuracy of vehicle speed planning is higher when the vehicle speed planning is performed based on the expected acceleration.

In one embodiment, the apparatus may periodically perform steps 101 to 105 described above, for example, acquire a current vehicle distance error between a current vehicle distance and an expected vehicle distance and a current vehicle speed error between a current vehicle speed and an expected vehicle speed every 1s, and then perform steps 103 and 105. As the vehicle adjusts acceleration and travels in accordance with the desired acceleration, the vehicle speed, the vehicle distance error from the preceding vehicle, and the vehicle speed error from the desired vehicle speed will vary, as will the desired acceleration of the device plan.

In one embodiment, before executing step 105, the vehicle distance maintenance speed planning method based on the fuzzy inference truth-value evolution further includes:

Step 109, acquiring historical driving experience data of the vehicle.

Wherein, the historical experience data comprises acceleration, vehicle distance error and vehicle speed error.

In one embodiment, the device may collect relevant data from an experienced driver driving the vehicle and process the collected relevant data to obtain historical driving experience data.

Specifically, the apparatus collects the vehicle acceleration, the vehicle speed, the distance between the vehicle and the preceding vehicle, and the speed of the preceding vehicle every 1 s. Then, the device processes one piece of running data acquired in each period, determines a vehicle speed error from a difference between the vehicle speed and the vehicle speed of the front vehicle, and determines a difference between the vehicle distance between the front vehicle and the finally maintained vehicle distance as a vehicle distance error, so as to obtain one piece of running experience data comprising acceleration, vehicle distance error and vehicle speed error.

And step 111, determining historical acceleration membership degrees, historical distance error membership degrees and historical vehicle speed error membership degrees of acceleration, distance error and vehicle speed error in the historical driving experience data according to the membership degree function corresponding to the distance error, the membership degree function corresponding to the vehicle speed error and the membership degree function corresponding to the acceleration.

The membership function corresponding to the vehicle distance error, the membership function corresponding to the vehicle speed error, and the membership function corresponding to the acceleration may be described in step 103.

Specifically, after the device obtains the running experience data, substituting the acceleration in the historical running experience data into a membership function corresponding to the expected acceleration to obtain the historical acceleration membership corresponding to the acceleration in the historical running experience data, substituting the vehicle distance error in the historical running experience data into a membership function corresponding to the vehicle distance error to obtain the historical vehicle distance error membership corresponding to the historical running data, substituting the vehicle speed error in the historical running experience data into a membership function corresponding to the vehicle speed error to obtain the historical vehicle speed error membership corresponding to the vehicle speed error in the historical running experience data.

And 113, fitting to obtain a membership empirical function for reflecting the relationship among the membership of the expected acceleration, the membership of the vehicle speed error and the membership of the vehicle distance error according to the historical acceleration membership, the historical vehicle distance error membership and the historical vehicle speed error membership.

Specifically, the device acquires a historical acceleration membership degree, a historical vehicle distance error membership degree and a historical vehicle speed error membership degree corresponding to each piece of historical experience driving data, and obtains membership degree data corresponding to each piece of historical experience driving data. Then, the equipment performs interpolation fitting on the multiple sets of membership data by means of polynomial interpolation to obtain membership empirical functions for reflecting the relation among membership of expected acceleration, membership of vehicle speed error and membership of vehicle distance error.

For example, each empirical data is (e _v,e_x, a), and the corresponding three membership functions μ _F(a),μ_G(e_x),μ_H(e_v), the membership data (μ _F(a),μ_G(e_x),μ_H(e_v) corresponding to each empirical function is obtained, then the multiple sets (μ _F(a),μ_G(e_x),μ_H(e_v)) are interpolated by polynomial interpolation, and the interpolated continuous function μ _F(a)＝h(μ_G(e_x),μ_H(e_v) is given by the following function h (·,):

h(x,y)＝P₀₀+P₁₀x+P₀₁y+P₁₁xy+P₂₀x²+P₀₂y²+P₂₁x²y+P₁₂xy²+P₃₀x³+P₀₃y³

in this embodiment, the membership empirical function is fitted according to the historical driving experience driving data, so that the membership degree of the expected acceleration conforming to the historical empirical driving data is inferred according to the membership empirical function.

In one embodiment, before performing step 103, the method further comprises:

and 115, respectively acquiring boundary parameters of the expected acceleration, the vehicle speed error and the vehicle distance error.

Specifically, the user can directly preset boundary parameters of the expected acceleration, the vehicle speed error and the vehicle distance error in the device, and the device respectively reads the boundary parameters of the expected acceleration, the vehicle speed error and the vehicle distance error set by the user to obtain the boundary parameters of the expected acceleration, the vehicle speed error and the vehicle distance error. The device can also determine the boundary parameters of the expected acceleration by acquiring vehicle data and environment data and utilizing the corresponding relation between the vehicle data, the environment data and the acceleration boundary parameters. The device can also acquire sensitivity parameters, and determine the boundary parameters of the vehicle speed error and the vehicle distance error through the corresponding relation between the sensitivity parameters and the boundary parameters of the vehicle speed error and the vehicle distance error.

Step 117, constructing a function with boundary parameters corresponding to the vehicle speed error as a membership function of the vehicle speed error.

Specifically, the device obtains a function that the vehicle speed error accords with the boundary parameter corresponding to the vehicle speed error and the vehicle speed error is in direct proportion to the membership degree, for example, when the vehicle speed error is greater than 4m/s, the vehicle speed error is necessarily subordinate to the vehicle speed error fuzzy set, when the vehicle speed error is less than minus 4m/s, the vehicle speed error is necessarily not subordinate to the vehicle speed error fuzzy set, the vehicle speed error is in direct proportion to the membership degree, and then the membership degree function of the vehicle speed error is mu _H(e_v), and then mu _H(e_v) can be:

wherein, mu _H(e_v) can be other forms, and only needs to be a function which accords with the boundary parameters of 4m/s to-4 m/s and has the vehicle speed error in direct proportion to the membership degree.

And 119, constructing a function of which the boundary parameters conform to the boundary parameters corresponding to the vehicle distance error, and taking the function as a membership function of the vehicle distance error.

Specifically, the device obtains that the vehicle distance error accords with the boundary parameter that the construction boundary parameter accords with the vehicle distance error and is in direct proportion to the membership degree, for example, when the vehicle distance error is greater than 10m, the vehicle distance error is necessarily subordinate to the vehicle distance error fuzzy set, when the vehicle distance error is less than minus 10m, the vehicle distance error is necessarily not subordinate to the vehicle distance error fuzzy set, the vehicle distance error is in direct proportion to the membership degree, then the membership degree function of the vehicle distance error is μ _G(e_x), then μ _G(e_x) may be:

wherein, mu _G(e_x) can be other forms, and only needs to be a function which accords with the boundary parameter of 10 to-10 m and has the vehicle distance error in direct proportion to the membership degree.

Step 121, constructing a function of which the boundary parameters conform to the boundary parameters corresponding to the expected acceleration, and taking the function as a membership function corresponding to the expected acceleration.

Specifically, the device obtains that the expected acceleration accords with the boundary parameter corresponding to the expected acceleration and the expected acceleration is in direct proportion to the membership degree, for example, when the expected acceleration is greater than 5m/s ², the expected acceleration is necessarily affiliated to the acceleration fuzzy set, when the expected acceleration is less than minus 5m/s ², the expected acceleration is necessarily not affiliated to the acceleration fuzzy set, the expected acceleration is in direct proportion to the membership degree, then the membership degree function of the vehicle speed error is μ _F (a), and μ _F (a) can be:

The function form of mu _F (a) can be other forms, and only needs to be a function which accords with the boundary parameters of 5m/s ² to-5 m/s ² and has acceleration in direct proportion to membership.

In this embodiment, according to the boundary parameter, a function conforming to the boundary parameter is determined, and membership functions corresponding to the desired acceleration, the vehicle speed error, and the vehicle distance error are respectively constructed.

In one embodiment, the boundary parameters for acquiring the desired acceleration in the step 115 specifically include:

and A1, acquiring vehicle data and environment data.

The vehicle data may include parameters related to the safe acceleration, such as vehicle weight, maximum acceleration, among others. The environmental data may include environmental data about the safe acceleration of the vehicle, such as road humidity, weather visibility, acceleration speed limit of the road being travelled, etc.

Specifically, the device may query the corresponding relationship between the locally stored vehicle signal and the vehicle data, and query to obtain the vehicle data corresponding to the vehicle, or the server requests the vehicle data corresponding to the vehicle model, and after the server queries to obtain the vehicle data, the server sends the vehicle data to the device. The device may send the current geographic location information of the vehicle to a server, and the server queries the environmental data corresponding to the geographic location information and then sends the queried environmental data to the device. The device can also shoot the surrounding environment of the vehicle through a shooting system of the vehicle, and then determine the surrounding environment data of the vehicle by utilizing a preset recognition algorithm.

And A2, determining an upper limit acceleration value and a lower limit acceleration value corresponding to the expected acceleration according to the vehicle data and the environment data, and taking the upper limit acceleration value and the lower limit acceleration value as boundary parameters of the expected acceleration.

Specifically, after acquiring the vehicle data and the environment data, the device queries the corresponding relation between the vehicle data and the environment data and the upper limit acceleration and the lower limit acceleration, and determines the upper limit acceleration and the lower limit acceleration of the vehicle. Wherein, the vehicle is driven in the range between the upper limit acceleration and the lower limit acceleration, so that the safety of the vehicle can be ensured.

In this embodiment, the user may set the boundary parameters of the vehicle acceleration according to the actual situation, or the apparatus determines the boundary parameters that make the vehicle within the safe acceleration according to the vehicle data and the environment data.

In one embodiment, the boundary parameters of the vehicle speed error and the vehicle distance error obtained in the step 115 specifically include:

And B1, acquiring sensitivity setting parameters.

Specifically, the device may acquire a default sensitivity setting parameter, or the user sets a sensitivity parameter when the vehicle is automatically driven on the device, and the device may read the sensitivity parameter set by the user.

And B2, determining boundary parameters of the vehicle speed error and the vehicle distance error according to the sensitivity setting parameters.

The sensitivity setting parameter is inversely proportional to the range of boundary parameters of the vehicle speed error and the vehicle distance error, the smaller the range of the boundary parameters of the vehicle distance error is, the same degree of membership of the vehicle speed error is changed, and the larger the change of the vehicle speed error is, so that the vehicle is controlled more sensitively, and the vehicle distance error is the same.

Specifically, the device may store a correspondence between the sensitivity parameter and boundary parameters of the vehicle speed error and the vehicle distance error, and after the device obtains the sensitivity parameter, query the correspondence between the sensitivity parameter and the boundary parameters of the vehicle speed error and the vehicle distance error, to obtain the boundary parameters of the vehicle speed error and the vehicle distance error. The device can also store the conversion relation between the sensitivity parameter and the boundary parameters of the vehicle speed error and the vehicle distance error in advance, and after the device acquires the sensitivity parameter, the conversion relation between the sensitivity parameter and the boundary parameters of the vehicle speed error and the vehicle distance error is utilized to obtain the boundary parameters of the vehicle speed error and the vehicle distance error in a conversion way.

In this embodiment, the sensitivity parameter can be flexibly set to change the boundary parameters of the vehicle speed error and the vehicle distance error.

In one embodiment, the step 101 specifically includes:

Step 101a, obtaining a current speed of the vehicle, a current distance between the vehicle and the front vehicle, a current speed of the front vehicle and a desired distance between the vehicle and the front vehicle.

Specifically, the device measures the distance between the current vehicle and the tail of the front vehicle through vehicle-mounted sensors such as a shooting system, infrared induction, sonar induction, millimeter wave radar and the like of the vehicle integration, and obtains the current vehicle distance. The device calculates the running speed of the front vehicle through the change rate of the distance between the device and the front vehicle and the current speed of the vehicle. The device obtains the current running speed of the vehicle through the vehicle integrated acceleration sensor or a self-contained velocimeter and the like, and obtains the current speed of the vehicle. The device obtains the expected vehicle distance between the vehicle and the front vehicle according to the input of the user or the calculation of the safe vehicle distance.

Step 101b, determining a difference between a current speed of the vehicle and a current speed of a preceding vehicle as a current speed error, and determining a difference between a current distance and an expected distance as a current distance error.

Specifically, after the device obtains the current speed of the vehicle and the current speed of the preceding vehicle, the device subtracts the current speed of the vehicle and the current speed of the preceding vehicle to obtain a current speed error. After the equipment acquires the current vehicle distance and the expected vehicle distance, subtracting the current vehicle distance from the expected vehicle distance to obtain the current vehicle distance error.

A specific embodiment of the present application will be described in detail.

The longitudinal distance dt between the preceding vehicles is noted, the desired vehicle distance to be maintained is ds, the vehicle distance error ex is defined as ex=dt-ds, the vehicle speed of the preceding vehicle is noted as v1, the vehicle speed of the host vehicle is noted as v2, and the vehicle speed error ev is defined as ev=v2-v 1.

The "if-then" condition defining fuzzy reasoning is titled:

"If host vehicle acceleration is a, then vehicle distance error e _x and vehicle speed error e _v will decrease and tend to be 0".

Where the need for planning, i.e. acceleration (equivalent to vehicle speed), is described in the if front piece and the planning target is described in the then back piece.

The truth function corresponding to the front piece 'own vehicle acceleration is a' is mu _F (a), the truth function corresponding to the rear piece 'vehicle distance error e _x and the vehicle speed error e _v are reduced and tend to 0' is f (x), so that the ambiguity implication is taken as the truth value of an 'if-then' condition proposition, and Lukasiewicz type ambiguity implication is selected, namely the truth value of the 'if-then' condition proposition is z=i (x, f (x))=1-x+xf (x).

The expected acceleration blur set F is noted as "positive" for the expected acceleration a, i.e., the greater the acceleration a, the greater the probability of the acceleration a membership to the acceleration blur combination F, and the membership function of the acceleration a to the acceleration blur set F is noted as μ _F (a). The greater the probability that the vehicle distance error is combined with the vehicle distance error fuzzy set G is that the vehicle distance error e _x is 'positive', the greater the vehicle distance error e _x is, and the membership function that the vehicle distance error e _x is affiliated to the fuzzy set G is recorded as mu _G(e_x. The greater the probability that the vehicle speed error ambiguity set H is the "positive" of the vehicle speed error e _v, the greater the probability that the vehicle speed error e _v belongs to the vehicle speed error ambiguity combination H, and the membership function that the vehicle speed error e _v belongs to the ambiguity set H is recorded as mu _H(e_v).

Definition μ _F(a)、μ_G(e_x)、μ_H(e_v) is the following three formulas:

Each empirical data is (e _v,e_x, a), and the corresponding three membership functions μ _F(a),μ_G(e_x),μ_H(e_v), resulting in corresponding membership data (μ _F(a),μ_G(e_x),μ_H(e_v) for each empirical function, then interpolating the multiple sets (μ _F(a),μ_G(e_x),μ_H(e_v) by polynomial interpolation, the interpolated continuous functions:

mu _F(a)＝h(μ_G(e_x),μ_H(e_v), the form of the function h (·,) is:

Defining a conditional proposition then back-piece truth function as follows:

Then the true value of the conditional proposition is z=i (x, f (x))=1-x+xf (x), which can be obtained:

when x=h (mu _G(e_x),μ_H(e_v)),

A controller with lyapunov stability is designed:

u (t) controls the change rate of x (t), so that the true value of the fuzzy reasoning process based on the "if-then" condition proposition is not increased, namely the true value z is not increased, the fuzzy reasoning process is controlled to stop after the true value z reaches the local minimum, and the situation that the true value is increased due to continuous reasoning is avoided (at the local minimum, the continuous reasoning can enable the true value to reach a point larger than the local minimum).

Specifically, let the

u(t)＝h(μ_G(e_x),μ_H(e_v))-x

This control u (t) can prove to be able to control z to z _min, i.e. the whole z course of change is non-increasing. Specifically, it proves that z needs to be subjected to a state transformation, and bounded z is mapped to unbounded w, namely:

Wherein,

Convergence of z to z _min is equivalent to convergence of w to 0, and by proving the lyapunov stability of w=0 is equivalent to proving the stability at z=z _min, the basic scientific basis for reasoning true value non-increase is also proving.

The time derivative can be obtained:

Selecting Lyapunov function as:

V(w)＝e^w-w-1

The time derivative can be obtained:

Is prepared through finishing

Thus, the first and second substrates are bonded together,And/>If and only if x=h (μ _G(e_x),μ_H(e_v)), i.e. z=z _min. Thus prove/>Negative qualitative, i.e. stability at z=z _min. The effect of controlling u (t) is that x is controlled to h (mu _G(e_x),μ_H(e_v)), and the basic scientific basis of true value non-increment of the reasoning process is met through the Lyapunov stability guarantee.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a vehicle distance maintenance speed planning device based on the fuzzy reasoning true value evolution, which is used for realizing the vehicle distance maintenance speed planning method based on the fuzzy reasoning true value evolution. The implementation scheme of the solution provided by the device is similar to the implementation scheme recorded in the method, so the specific limitation in the embodiment of one or more vehicle distance maintenance speed planning devices based on fuzzy reasoning true value evolution can be referred to above for the limitation of a vehicle distance maintenance speed planning method based on fuzzy reasoning true value evolution, which is not repeated here.

In one embodiment, as shown in fig. 2, there is provided a vehicle distance maintenance speed planning apparatus based on fuzzy inference truth-value evolution, including:

An obtaining module 201, configured to obtain a current vehicle distance error between a current vehicle distance and an expected vehicle distance, and a current vehicle speed error between a current vehicle speed and an expected vehicle speed;

The membership determining module 203 is configured to determine a membership of a distance error corresponding to the current distance error according to a membership function corresponding to the distance error; determining the membership of the vehicle speed error corresponding to the current vehicle speed error according to the membership function corresponding to the vehicle speed error;

the acceleration determining module 205 is configured to determine, as an expected acceleration, an acceleration that makes the value of the inference loss function be at a minimum value according to the vehicle distance error membership, the vehicle speed error membership, the membership empirical function, the membership function corresponding to the acceleration, and the inference loss function; the membership empirical function is used for reflecting the relation among the membership of the expected acceleration, the membership of the vehicle speed error and the membership of the vehicle distance error; the reasoning loss function is used for reflecting the degree of loss of the reasoning credibility of the expected acceleration reasoning to the vehicle speed error and the vehicle distance error.

In one embodiment, the apparatus further comprises:

An experience data acquisition module 209 (not shown) for acquiring the vehicle history running experience data; the historical experience data comprises acceleration, vehicle distance error and vehicle speed error;

a membership acquisition module 211 (not shown in the figure) configured to determine a historical acceleration membership degree, a historical distance error membership degree, and a historical vehicle speed error membership degree for the acceleration, the distance error, and the vehicle speed error in the historical driving experience data according to the membership function corresponding to the distance error, the membership function corresponding to the vehicle speed error, and the membership function corresponding to the acceleration, respectively;

An empirical function construction function 213 (not shown in the figure) is configured to fit a membership empirical function reflecting a relationship among the membership of the desired acceleration, the membership of the vehicle speed error, and the membership of the vehicle distance error according to the historical acceleration membership, the historical vehicle distance error membership, and the historical vehicle speed error membership.

In one embodiment, the apparatus further comprises:

a boundary parameter acquiring module 215 (not shown in the figure) for acquiring boundary parameters of the desired acceleration, the vehicle speed error, and the vehicle distance error, respectively;

A vehicle speed error membership construction function 217 (not shown) for constructing a function whose boundary parameters conform to the boundary parameters corresponding to the vehicle speed error as a membership function of the vehicle speed error;

a distance error membership construction function 219 (not shown in the figure), which constructs a function whose boundary parameters conform to the boundary parameters corresponding to the distance error as a membership function of the distance error;

An acceleration membership construction function 221 (not shown in the figure) constructs a function whose boundary parameters conform to the boundary parameters corresponding to the desired acceleration as a membership function corresponding to the desired acceleration.

In one embodiment, the boundary parameter obtaining module 215 is specifically configured to:

Acquiring vehicle data and environment data; and determining an upper limit acceleration value and a lower limit acceleration value corresponding to the expected acceleration according to the vehicle data and the environment data, and taking the upper limit acceleration value and the lower limit acceleration value as boundary parameters of the expected acceleration.

Acquiring a sensitivity setting parameter; determining boundary parameters of the vehicle speed error and the vehicle distance error according to the sensitivity setting parameters; the sensitivity setting parameter is inversely proportional to the range of boundary parameters of the vehicle speed error and the vehicle distance error.

In one embodiment, the obtaining module 201 is specifically configured to:

Acquiring a current speed of the vehicle, a current distance between the vehicle and a front vehicle, a current speed of the front vehicle and an expected distance between the vehicle and the front vehicle; and determining a difference between the current speed of the vehicle and the current speed of the front vehicle as a current speed error, and determining a difference between the current distance and the expected distance as a current distance error.

The above-mentioned vehicle distance maintenance speed planning device based on the fuzzy inference true value evolution can be implemented by all or part of software, hardware and their combination. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a computer device integrated with a vehicle, and an internal structural diagram thereof may be as shown in fig. 3. The computer device includes a processor, a memory, and a communication interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program, when executed by the processor, implements a vehicle distance maintenance speed planning method based on fuzzy inference truth-value evolution.

It will be appreciated by those skilled in the art that the structure shown in FIG. 3 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.

In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

The user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magneto-resistive random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (PHASE CHANGE Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims

1. A vehicle distance maintenance speed planning method based on fuzzy reasoning true value evolution is characterized by comprising the following steps:

Determining acceleration which enables the value of the reasoning loss function to be at the minimum value as the expected acceleration of the vehicle according to the vehicle distance error membership, the vehicle speed error membership, the membership empirical function, the membership function corresponding to the acceleration and the reasoning loss function; the membership empirical function is used for reflecting the relation among the membership of expected acceleration, the membership of the vehicle speed error and the membership of the vehicle distance error; the reasoning loss function is used for reflecting the degree of loss of the reasoning credibility of the expected acceleration reasoning to the vehicle speed error and the vehicle distance error;

Before determining the acceleration which enables the value of the reasoning loss function to be at the minimum value according to the vehicle distance error membership degree, the vehicle speed error membership degree, the membership degree experience function, the membership degree function corresponding to the acceleration and the reasoning loss function as the expected acceleration of the vehicle, the method further comprises:

Fitting according to the historical acceleration membership, the historical vehicle distance error membership and the historical vehicle speed error membership to obtain a membership empirical function for reflecting the relationship among the membership of the expected acceleration, the membership of the vehicle speed error and the membership of the vehicle distance error;

Determining a vehicle distance error membership corresponding to the current vehicle distance error according to a membership function corresponding to the vehicle distance error; before determining the membership of the vehicle speed error corresponding to the current vehicle speed error according to the membership function corresponding to the vehicle speed error, the method further comprises:

2. The method of claim 1, wherein the obtaining boundary parameters of the desired acceleration comprises:

Acquiring vehicle data and environment data;

3. The method according to claim 1, wherein the obtaining boundary parameters of the vehicle speed error and the vehicle distance error includes:

Acquiring a sensitivity setting parameter;

4. The method of claim 1, wherein the obtaining a current distance error between a current distance and an expected distance, and a current speed error between a current speed and an expected speed, comprises:

5. A vehicle distance maintenance speed planning device based on fuzzy inference true value evolution, which is characterized by comprising:

The acceleration determining module is used for determining acceleration which enables the value of the reasoning loss function to be at the minimum value as the expected acceleration of the vehicle according to the vehicle distance error membership degree, the vehicle speed error membership degree empirical function, the membership degree function corresponding to the acceleration and the reasoning loss function; the membership empirical function is used for reflecting the relation among the membership of expected acceleration, the membership of the vehicle speed error and the membership of the vehicle distance error; the reasoning loss function is used for reflecting the degree of loss of the reasoning credibility of the expected acceleration reasoning to the vehicle speed error and the vehicle distance error;

The experience data acquisition module is used for acquiring the historical driving experience data of the vehicle; the historical experience data comprises acceleration, vehicle distance error and vehicle speed error;

The membership acquisition module is used for respectively determining historical acceleration membership of acceleration, vehicle distance error and vehicle speed error, historical vehicle distance error membership and historical vehicle speed error membership in the historical driving experience data according to the membership function corresponding to the vehicle distance error, the membership function corresponding to the vehicle speed error and the membership function corresponding to the acceleration;

An empirical function construction function, which is used for fitting to obtain a membership empirical function used for reflecting the relationship among the membership of the expected acceleration, the membership of the vehicle speed error and the membership of the vehicle distance error according to the historical acceleration membership, the historical vehicle distance error membership and the historical vehicle speed error membership;

the boundary parameter acquisition module is used for respectively acquiring boundary parameters of expected acceleration, vehicle speed error and vehicle distance error;

a vehicle speed error membership degree construction function, which is used for constructing a function with boundary parameters conforming to boundary parameters corresponding to the vehicle speed error and used as a membership degree function of the vehicle speed error;

A vehicle distance error membership degree construction function is used for constructing a function with boundary parameters conforming to boundary parameters corresponding to the vehicle distance error as a membership degree function of the vehicle distance error;

And constructing a function of the acceleration membership degree, wherein boundary parameters are consistent with the functions of the boundary parameters corresponding to the expected acceleration, and the function is used as the membership degree function corresponding to the expected acceleration.

6. The apparatus of claim 5, wherein the boundary parameter acquisition module is specifically configured to:

7. The apparatus of claim 5, wherein the boundary parameter acquisition module is specifically configured to:

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 4 when the computer program is executed.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 4.

10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method of any of claims 1 to 4.