An adaptive cruise control method, system and vehicle

Abstract

The embodiment of the application provides a kind of adaptive cruise control method, system and vehicle, method includes: according to driving state, the risk degree value of the time interval between two vehicles and the risk degree value of collision are determined;According to the two values, the target fuzzy subset corresponding to the time interval between vehicles in the fuzzy set of time interval between vehicles and the target fuzzy subset corresponding to the risk degree value in the risk degree fuzzy set are determined;According to fuzzy rule, the first fuzzy subset corresponding to the target fuzzy subset in the first fuzzy set of first correction variable is determined, and the first correction variable is the correction variable corresponding to the first index weight;By defuzzification to first fuzzy subset, the corresponding target value is obtained;The first index weight is corrected by target value, and the first correction index weight is obtained;Adaptive cruise control is carried out based on the first correction index weight. It aims to improve the adaptability of adaptive cruise control, to improve the comfort and reliability of driving.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cruise control, in particular to an adaptive cruise control method, system and vehicle. BACKGROUND

[0002] The CACC system (Cooperative Adaptive Cruise Control) is a complex control system involving multiple fields, and the relationship among people, vehicles and roads needs to be fully considered to achieve effective vehicle following control and traffic management. When the traditional upper MPC controller in the CACC system operates, the weight distribution of safety, vehicle following and comfort of the CACC system is fixed and unchanged, which cannot well adapt to complex road conditions and will reduce the comfort and reliability of driving. SUMMARY

[0003] Therefore, the embodiments of the present application provide an adaptive cruise control method, system and vehicle. The adaptability of adaptive cruise control is improved to improve the comfort and reliability of driving.

[0004] The first aspect of the present application provides an adaptive cruise control method, the method comprising:

[0005] According to the vehicle driving state, the vehicle-to-vehicle time interval value and the risk degree value of collision between two vehicles are determined;

[0006] According to the vehicle-to-vehicle time interval value and the risk degree value, a target fuzzy subset corresponding to the vehicle-to-vehicle time interval value in a vehicle-to-vehicle time interval fuzzy set and a target fuzzy subset corresponding to the risk degree value in a risk degree fuzzy set are determined;

[0007] According to the fuzzy rule, a first fuzzy subset corresponding to the target fuzzy subset in a first fuzzy set corresponding to the first correction variable is determined, the first correction variable is a correction variable corresponding to a first index weight, and the first index weight is a safety index weight or a comfort index weight;

[0008] The first fuzzy subset is de-fuzzified by a de-fuzzification algorithm to obtain a target value corresponding to the first correction variable;

[0009] The first index weight is corrected by the target value corresponding to the first correction variable to obtain a first corrected index weight;

[0010] Adaptive cruise control is performed based on the first corrected index weight.

[0011] Optionally, before the adaptive cruise control based on the first corrected index weight, the method further comprises:

[0012] According to the fuzzy rule, a second fuzzy subset corresponding to the target fuzzy subset in a second fuzzy set corresponding to a second correction variable is determined, the second correction variable being a correction variable corresponding to a second index weight, the second index weight being an index weight different from the first index weight among the safety index weight and the comfort index weight;

[0013] The second correction variable corresponding to the target value is obtained by defuzzifying the second fuzzy subset through a defuzzification algorithm.

[0014] The second correction index weight is obtained by correcting the second index weight through the target value corresponding to the second correction variable.

[0015] The adaptive cruise control based on the first correction index weight comprises adaptive cruise control based on the first correction index weight and the second correction index weight.

[0016] Optionally, according to the inter-vehicle time interval value and the risk degree value, a target fuzzy subset in an inter-vehicle time interval fuzzy set corresponding to the inter-vehicle time interval value and a target fuzzy subset in a risk degree fuzzy set corresponding to the risk degree value are determined, comprising:

[0017] According to the inter-vehicle time interval value, the membership value under the inter-vehicle time interval value is calculated through the membership function of each fuzzy subset in the inter-vehicle time interval fuzzy set, and the fuzzy subset corresponding to the maximum membership value is determined as the target fuzzy subset corresponding to the inter-vehicle time interval value.

[0018] According to the risk degree value, the membership value under the risk degree value is calculated through the membership function of each fuzzy subset in the risk degree fuzzy set, and the fuzzy subset corresponding to the maximum membership value is determined as the target fuzzy subset corresponding to the risk degree value.

[0019] Optionally, according to the fuzzy rule, a first fuzzy subset corresponding to the target fuzzy subset in a first fuzzy set corresponding to a first correction variable is determined, comprising:

[0020] According to the fuzzy rule, a fuzzy subset in the first fuzzy set corresponding to the target fuzzy subset in the inter-vehicle time interval fuzzy set and the target fuzzy subset in the risk degree fuzzy set is determined, the fuzzy rule defining the corresponding relationship between the fuzzy subset in the first fuzzy set and the fuzzy subset in the inter-vehicle time interval fuzzy set and the fuzzy subset in the risk degree fuzzy set.

[0021] The determined target fuzzy subset corresponding to the target fuzzy subset corresponding to the inter-vehicle time interval value and the target fuzzy subset corresponding to the risk degree value in the first fuzzy set is determined as the first fuzzy subset corresponding to the first correction variable.

[0022] Optionally, according to the fuzzy rule, the second fuzzy subset corresponding to the second fuzzy subset corresponding to the target fuzzy subset in the second fuzzy set is determined, and the fuzzy rule defines the corresponding relationship between the fuzzy subset in the second fuzzy set and the fuzzy subset in the inter-vehicle time interval fuzzy set and the fuzzy subset in the risk degree fuzzy set.

[0023] According to the fuzzy rule, the second fuzzy subset corresponding to the second fuzzy subset corresponding to the target fuzzy subset corresponding to the inter-vehicle time interval value and the target fuzzy subset corresponding to the risk degree value in the first fuzzy set is determined, and the fuzzy rule defines the corresponding relationship between the fuzzy subset in the second fuzzy set and the fuzzy subset in the inter-vehicle time interval fuzzy set and the fuzzy subset in the risk degree fuzzy set.

[0024] The determined target fuzzy subset corresponding to the target fuzzy subset corresponding to the inter-vehicle time interval value and the target fuzzy subset corresponding to the risk degree value in the first fuzzy set is determined as the first fuzzy subset corresponding to the first correction variable.

[0025] Optionally, in the case that the first fuzzy subset includes multiple, before the first fuzzy subset is de-fuzzified by the de-fuzzification algorithm to obtain the target value corresponding to the first correction variable, the method further comprises:

[0026] According to the membership value of the target fuzzy subset corresponding to the first fuzzy subset, the minimum membership value is determined as the activation of the first fuzzy subset.

[0027] According to the activation of each first fuzzy subset, the final first fuzzy subset is obtained by weighted average of all first fuzzy subsets.

[0028] In the case that the second fuzzy subset includes multiple, before the second fuzzy subset is de-fuzzified by the de-fuzzification algorithm to obtain the target value corresponding to the second correction variable, the method further comprises:

[0029] According to the membership value of the target fuzzy subset corresponding to the second fuzzy subset, the minimum membership value is determined as the activation of the second fuzzy subset.

[0030] According to the activation of each second fuzzy subset, the final second fuzzy subset is obtained by weighted average of all second fuzzy subsets.

[0031] Optionally, before adaptive cruise control is performed based on the first correction index weight and the second correction index weight, the method further comprises:

[0032] The inter-vehicle distance is determined by a fusion distance strategy, and the expression of the fusion distance strategy is: Wherein, d exp represents the required inter-vehicle distance; d0 is the minimum safety distance between vehicles; d c is a correction term; t h and c are fixed constant coefficients; v is the speed of the ego vehicle; v head is the speed of the leading vehicle; v rel_head is the speed difference between the two vehicles.

[0033] The adaptive cruise control based on the first correction index weight and the second correction index weight comprises: performing adaptive cruise control based on the first correction index weight, the second correction index weight and the required inter-vehicle distance.

[0034] Optionally, according to the vehicle driving state, the inter-vehicle time distance value and the risk degree value of collision between the two vehicles are determined, comprising:

[0035] According to the vehicle driving state, the inter-vehicle time distance value between the two vehicles is obtained by calculating through an inter-vehicle time distance determination algorithm, and the expression of the inter-vehicle time distance determination algorithm is Wherein, T thw represents the inter-vehicle time distance, d represents the distance between the two vehicles, d c is a correction term, and v is the speed of the ego vehicle.

[0036] According to the vehicle driving state, the risk degree value of collision between the two vehicles is obtained by calculating through a risk degree determination algorithm, and the expression of the risk degree determination algorithm is Wherein, T ttc -1 represents the risk degree, v rel represents the speed difference between the two vehicles, d represents the distance between the two vehicles, and v p represents the speed of the leading vehicle.

[0037] The second aspect of the present application provides an adaptive cruise control system, and the system comprises:

[0038] A parameter determination module is configured to determine the inter-vehicle time distance value and the risk degree value of collision between the two vehicles according to the vehicle driving state.

[0039] A target fuzzy subset determination module is configured to determine, according to the inter-vehicle time distance value and the risk degree value, a target fuzzy subset in the inter-vehicle time distance fuzzy set corresponding to the inter-vehicle time distance value and a target fuzzy subset in the risk degree fuzzy set corresponding to the risk degree value.

[0040] The first fuzzy subset determination module is configured to determine, according to a fuzzy rule, a first fuzzy subset corresponding to the target fuzzy subset in a first fuzzy set corresponding to a first correction variable, the first correction variable being a correction variable corresponding to a first index weight, the first index weight being a safety index weight or a comfort index weight;

[0041] The de-fuzzification processing module is configured to de-fuzzify the first fuzzy subset by using a de-fuzzification algorithm to obtain a target value corresponding to the first correction variable;

[0042] The correction module is configured to correct the first index weight by using the target value corresponding to the first correction variable to obtain a first corrected index weight;

[0043] The cruise control module is configured to perform adaptive cruise control based on the first corrected index weight.

[0044] The third aspect of the present application provides a vehicle, which is provided with the adaptive cruise control system of the second aspect of the present application and is configured to perform the steps in the adaptive cruise control method of the first aspect of the present application.

[0045] The adaptive cruise control method provided by the present application has the following advantages:

[0046] The adaptive cruise control method provided by the embodiment of the application introduces fuzzy theory to optimize the MPC algorithm (Model Predictive Control) in the CACC system. Firstly, the vehicle-to-vehicle time interval value and the risk degree value of collision between two vehicles are determined according to the driving state of the vehicle. Meanwhile, a vehicle-to-vehicle time interval fuzzy set corresponding to the vehicle-to-vehicle time interval is established in advance, and the vehicle-to-vehicle time interval fuzzy set includes a plurality of fuzzy subsets. Meanwhile, a risk degree fuzzy set corresponding to the risk degree of collision is established in advance, and the risk degree fuzzy set includes a plurality of fuzzy subsets. According to the determined vehicle-to-vehicle time interval value and the risk degree value, a target fuzzy subset corresponding to the vehicle-to-vehicle time interval value in the vehicle-to-vehicle time interval fuzzy set is determined, and a target fuzzy subset corresponding to the risk degree value in the risk degree fuzzy set is determined. Meanwhile, a first fuzzy set corresponding to the first correction variable is established in advance, and the first fuzzy set includes a plurality of fuzzy subsets. According to the fuzzy rule, one fuzzy subset corresponding to the target fuzzy subset corresponding to the vehicle-to-vehicle time interval value and the target fuzzy subset corresponding to the risk degree value in the first fuzzy set corresponding to the first correction variable is determined, and the fuzzy subset is determined as the first fuzzy subset corresponding to the first correction variable. The first correction variable is a correction variable corresponding to the first index weight, and the first index weight is a safety index weight or a comfort index weight. The first fuzzy subset corresponding to the first correction variable is de-fuzzified through a de-fuzzification algorithm to obtain a target value corresponding to the first correction variable. Then, the first index weight is corrected through the target value corresponding to the first correction variable to obtain a first corrected index weight. Finally, the CACC system performs adaptive cruise control based on the first corrected index weight. In this way, by introducing fuzzy theory, the weight distribution of each performance index is dynamically adjusted based on the actual driving state of the vehicle instead of being fixed and unchangeable, so as to effectively improve the adaptability of adaptive cruise control and improve the comfort and reliability of driving. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings needed to be used in the description of the embodiments of the application will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0048] Figure 1 A system structure diagram of the CACC system in an adaptive cruise control method according to an embodiment of the application is shown.

[0049] Figure 2 A flowchart of an adaptive cruise control method according to an embodiment of the application is shown.

[0050] Figure 3 A flow chart of fuzzy control in an adaptive cruise control method according to an embodiment of the present application is shown.

[0051] Figure 4 A flow chart of adaptive cruise control in an adaptive cruise control method according to an embodiment of the present application is shown.

[0052] Figure 5 A schematic diagram of an adaptive cruise control system according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0054] Before the present application is described, the current background is described. The CACC system (Cooperative Adaptive Cruise Control) is a complex control system involving multiple fields, and the relationship among people, vehicles and roads should be fully considered to achieve effective vehicle following control and traffic management. As shown in Figure 1 Figure 1 ​A schematic diagram of a CACC system structure of an electric vehicle in a V2X environment is shown, the main components of the CACC system and the functions between the components are respectively: HMI human-computer interaction interface, which provides a platform for the driver to interact with the CACC system, including displaying the current vehicle speed, following vehicle distance and other information, and adjusting the CACC system parameters; driver priority control strategy, which allows the driver to control the vehicle speed and acceleration at any time by pressing the brake or accelerator pedal, ensuring the driver's control of the vehicle; cruise control / following mode switching strategy, which automatically adjusts the vehicle driving mode through logical judgment and sends the mode signal to the upper controller; following distance strategy, which transmits the expected following distance to the upper controller according to the vehicle state information, and controls the vehicle acceleration and braking force to maintain a safe distance from the front vehicle; lower controller, which performs inverse analysis on vehicle dynamics to obtain the control method of the driving and braking system, and combines the brake / drive switching control strategy to convert the expected acceleration signal from the upper layer into an expected drive torque and brake pressure signal that the actuator can accept, completing the longitudinal motion control of the vehicle; upper controller (core), which solves the most suitable expected acceleration according to vehicle information and driving mode, ensures vehicle safety, meets the needs of the driver's driving style, optimizes passenger comfort and queue following as much as possible, and transmits the corresponding signal to the lower controller; vehicle dynamics model group, which describes the dynamic characteristics of the vehicle during motion, including acceleration, braking force, turning radius and other parameters, and is an important part of the CACC system. For the MPC algorithm in the upper controller of the CACC system, the implementation mainly includes three basic steps: prediction model, rolling optimization and feedback correction, and the most core step is the establishment of the prediction model. In the final output comprehensive performance function equation, there is an index weight coefficient ω y , the matrix is where ω x = diag[ω safe ω vrel ω comf ], N p is the prediction time domain, ω safe is the safety index weight, ω vrel is the following index weight, and ω comf is the comfort index weight. When the traditional upper controller operates, the three performance index weights ω safe , ω vrel , and ω comfThe weight distribution of the adaptive cruise control method is fixed (generally set as a fixed value in the early stage), which cannot well adapt to complex road conditions and reduces the driving comfort and reliability. The application mainly optimizes the upper-layer control of the MPC algorithm in the CACC system, specifically dynamically adjusts the performance index weight based on the driving state of the vehicle, thereby effectively improving the adaptability of the adaptive cruise control and improving the driving comfort and reliability. In addition, the application also provides related other embodiments to optimize the following distance strategy in the CACC system, so that the vehicle can maintain the safety of following and the comfort of speed change under different working conditions.

[0055] Reference Figure 2 , Figure 2 FIG. 1 is a schematic diagram of an adaptive cruise control method according to an embodiment of the application. As shown in FIG. 1, the application provides an adaptive cruise control method, which comprises the following steps. Figure 2

[0056] Step S1: determining the time distance between two vehicles and the risk degree of collision between the two vehicles according to the driving state of the vehicle.

[0057] In this embodiment, first, the time distance between the ego vehicle and the preceding vehicle and the risk degree of collision between the ego vehicle and the preceding vehicle are determined according to the driving state of the vehicle. The time distance between the two vehicles reflects the time length required for the ego vehicle to reach the position of the preceding vehicle at the current time, and the risk degree of collision reflects the possibility of the ego vehicle approaching the preceding vehicle, i.e. the possibility of collision.

[0058] Step S2: determining the target fuzzy subset of the time distance fuzzy set corresponding to the time distance value and the target fuzzy subset of the risk degree fuzzy set corresponding to the risk degree value according to the time distance value and the risk degree value.

[0059] In this embodiment, the application introduces fuzzy theory, and for the time distance parameter and the risk degree parameter, a large number of experimental calibrations are performed through prior expert knowledge to construct the time distance fuzzy set corresponding to the time distance parameter, and the risk degree fuzzy set corresponding to the risk degree parameter. The time distance fuzzy set includes a plurality of fuzzy subsets, and the risk degree fuzzy set includes a plurality of fuzzy subsets.

[0060] ​In the embodiment, after the time headway value and the risk degree value between the ego vehicle and the preceding vehicle are obtained by the calculation in step S1, the time headway value is calculated by a related algorithm, a fuzzy subset corresponding to the time headway value in the time headway fuzzy set is determined, and the fuzzy subset is determined as a target fuzzy subset corresponding to the time headway value. In addition, the risk degree value is calculated by a related algorithm, a fuzzy subset corresponding to the risk degree value in the risk degree fuzzy set is determined, and the fuzzy subset is determined as a target fuzzy subset corresponding to the risk degree value.

[0061] Step S3: According to the fuzzy rule, a first fuzzy subset corresponding to the target fuzzy subset in a first fuzzy set corresponding to a first correction variable is determined, the first correction variable is a correction variable corresponding to a first index weight, and the first index weight is a safety index weight or a comfort index weight.

[0062] In the present application, step S3 can specifically include: according to the fuzzy rule, a fuzzy subset corresponding to the target fuzzy subset corresponding to the time headway value and the target fuzzy subset corresponding to the risk degree value in a first fuzzy set corresponding to a first correction variable is determined, the fuzzy rule defines the corresponding relationship between the fuzzy subset in the first fuzzy set and the fuzzy subset in the time headway fuzzy set and the fuzzy subset in the risk degree fuzzy set; and the determined fuzzy subset corresponding to the target fuzzy subset corresponding to the time headway value and the target fuzzy subset corresponding to the risk degree value in the first fuzzy set is determined as the first fuzzy subset corresponding to the first correction variable.

[0063] In the embodiment, for the first correction variable, a first fuzzy set corresponding to the first correction variable is constructed by a large number of experimental calibrations through prior expert knowledge. The first fuzzy set includes a plurality of fuzzy subsets. Meanwhile, a fuzzy rule is preset, and the fuzzy rule defines the corresponding relationship between each fuzzy subset in the first fuzzy set of the first correction variable and each fuzzy subset in the time headway fuzzy set and the risk degree fuzzy set.

[0064] For example, it is assumed that the time headway fuzzy set T thw ={NB thw , NS thw , ZO thw , PS thw , PB thw} established in advance includes five fuzzy subsets, namely NB thw , NS thw , ZO thw , PS thw , and PB thw . The risk degree fuzzy set T ttc-1 ={NB ttc ,NS ttc ,ZO ttc ,PS ttc ,PB ttc} includes five fuzzy subsets, respectively NB ttc , NS ttc , ZO ttc , PS ttc , and PB ttc ; the first fuzzy set C1 = {NB1, NS1, ZO1, PS1, PB1} established in advance and corresponding to the first correction variable includes five fuzzy subsets, respectively NB1, NS1, ZO1, PS1, and PB1, and it is assumed that the first index weight corresponding to the first correction variable is the comfort index weight. Based on the pre-established inter-vehicle time interval fuzzy set, risk degree fuzzy set, and first fuzzy set, the corresponding fuzzy rules are established, which define the corresponding relationship between each fuzzy subset in the first fuzzy set of the first correction variable and each fuzzy subset in the inter-vehicle time interval fuzzy set and risk degree fuzzy set. As shown in Table 1, the corresponding relationship recorded in Table 1 is the established fuzzy rule, wherein NB represents negative big, i.e., shrinking; NS represents negative small, i.e., slightly shrinking; ZO represents zero, i.e., no correction; PS represents positive small, i.e., slightly expanding; and PB represents positive big, i.e., expanding.

[0065] Table 1

[0066]

[0067] In this embodiment, based on the fuzzy rule, the fuzzy subset in the first fuzzy set corresponding to the target fuzzy subset corresponding to the inter-vehicle time interval value and the target fuzzy subset corresponding to the risk degree value determined through step S2 is determined, and then the fuzzy subset is determined as the first fuzzy subset corresponding to the first correction variable. For example, continuing to use the above example, when the target fuzzy subset corresponding to the inter-vehicle time interval value is determined as NS thw and the target fuzzy subset corresponding to the risk degree value is determined as ZO ttc , through the fuzzy rule shown in Table 1, the fuzzy subset in the first fuzzy set corresponding to NS thw and ZO ttc is determined as NS1, and thus the NS1 fuzzy subset in the first fuzzy set is determined as the first fuzzy subset corresponding to the first correction variable. The first correction variable is the correction variable corresponding to the first index weight, and the first index weight can be the safety index weight or the comfort index weight. In the case where the first index weight is the safety index weight, the safety index weight is dynamically adjusted, and in the case where the first index weight is the comfort index weight, the comfort index weight is dynamically adjusted.

[0068] Step S4: Deblurring the first fuzzy subset by a deblurring algorithm to obtain a target value corresponding to the first correction variable.

[0069] In this embodiment, after obtaining the first fuzzy subset corresponding to the first correction variable through step S3, the first fuzzy subset is deblurred by a deblurring algorithm to obtain a determined target value corresponding to the first correction variable. It should be understood that this is only a preferred deblurring algorithm, and the deblurring algorithm can also be other deblurring algorithms, which are not limited here.

[0070] Step S5: Correcting the first index weight by the target value corresponding to the first correction variable to obtain a first corrected index weight.

[0071] In this embodiment, after the deblurring process of step S4, a clear output value (i.e. target value) corresponding to the first correction variable is obtained, and then the first index weight is corrected by the target value to obtain a corrected first index weight, which is the first corrected index weight.

[0072] Step S6: Adaptive cruise control based on the first corrected index weight.

[0073] In this embodiment, after obtaining the first corrected index weight based on the vehicle driving state through step S5, the CACC system will perform cooperative adaptive cruise control on the ego vehicle based on the first corrected index weight. Compared with the previous cooperative adaptive cruise control on the ego vehicle based on the first index weight with a fixed value, the application dynamically adjusts the first index weight based on the vehicle driving state to improve the adaptability of the cooperative adaptive cruise control, thereby achieving the purpose of improving the comfort and reliability of driving.

[0074] The adaptive cruise control method provided by the embodiments of the present application introduces fuzzy theory to optimize the MPC algorithm (Model Predictive Control) in the CACC system. First, the vehicle-to-vehicle time interval value and the risk degree value of collision between two vehicles are determined according to the driving state of the vehicle. Meanwhile, a vehicle-to-vehicle time interval fuzzy set corresponding to the vehicle-to-vehicle time interval is established in advance, and the vehicle-to-vehicle time interval fuzzy set includes a plurality of fuzzy subsets. Meanwhile, a risk degree fuzzy set corresponding to the risk degree of collision is established in advance, and the risk degree fuzzy set includes a plurality of fuzzy subsets. According to the determined vehicle-to-vehicle time interval value and the risk degree value, a target fuzzy subset corresponding to the vehicle-to-vehicle time interval value in the vehicle-to-vehicle time interval fuzzy set is determined, and a target fuzzy subset corresponding to the risk degree value in the risk degree fuzzy set is determined. Meanwhile, a first fuzzy set corresponding to the first correction variable is established in advance, and the first fuzzy set includes a plurality of fuzzy subsets. According to the fuzzy rule, a fuzzy subset corresponding to the target fuzzy subset corresponding to the vehicle-to-vehicle time interval value and the target fuzzy subset corresponding to the risk degree value in the first fuzzy set corresponding to the first correction variable is determined, and the fuzzy subset is determined as the first fuzzy subset corresponding to the first correction variable. The first correction variable is a correction variable corresponding to the first index weight, and the first index weight is a safety index weight or a comfort index weight. The first fuzzy subset corresponding to the first correction variable is de-fuzzified through a de-fuzzification algorithm to obtain a target value corresponding to the first correction variable. Then, the first index weight is corrected through the target value corresponding to the first correction variable to obtain a first corrected index weight. Finally, the CACC system performs adaptive cruise control based on the first corrected index weight. Thus, by introducing fuzzy theory, the weight distribution of each performance index is dynamically adjusted based on the actual driving state of the vehicle instead of being fixed and unchangeable, which effectively improves the adaptability of adaptive cruise control and improves the comfort and reliability of driving.

[0075] In combination with the above embodiments, in an implementation manner, the embodiments of the present application further provide an adaptive cruise control method. In the adaptive cruise control method, before step S6, the method further includes steps S01 to S03:

[0076] Step S01: According to the fuzzy rule, determine a second fuzzy subset corresponding to the target fuzzy subset in a second fuzzy set corresponding to a second correction variable, wherein the second correction variable is a correction variable corresponding to a second index weight, and the second index weight is an index weight different from the first index weight among the safety index weight and the comfort index weight.

[0077] In the present application, step S01 can specifically include: determining, according to a fuzzy rule, a fuzzy subset in a second fuzzy set corresponding to the second correction variable, the fuzzy subset corresponding to a target fuzzy subset in the second fuzzy set corresponding to the inter-vehicle time interval value and a target fuzzy subset corresponding to the risk degree value, the fuzzy rule defining a corresponding relationship between the fuzzy subset in the second fuzzy set and a fuzzy subset in an inter-vehicle time interval fuzzy set and a fuzzy subset in a risk degree fuzzy set; and determining the fuzzy subset in the second fuzzy set corresponding to the second correction variable as the second fuzzy subset corresponding to the second correction variable.

[0078] In the present embodiment, the previous embodiment of the present application only dynamically adjusts one of the safety index weight and the comfort index weight. In order to simultaneously improve the comfort and reliability of driving in the adaptive cruise process, another embodiment of the present application dynamically adjusts both the safety index weight and the comfort index weight.

[0079] Specifically: for the second correction variable, a second fuzzy set corresponding to the second correction variable is constructed by a large number of test calibrations through prior expert knowledge. The second fuzzy set includes a plurality of fuzzy subsets. Meanwhile, a fuzzy rule is preset, the fuzzy rule defining a corresponding relationship between each fuzzy subset in the second fuzzy set of the second correction variable and each fuzzy subset in an inter-vehicle time interval fuzzy set and a risk degree fuzzy set.

[0080] For example, it is assumed that the pre-established inter-vehicle time interval fuzzy set T thw ={NB thw ,NS thw ,ZO thw ,PS thw ,PB thw} includes five fuzzy subsets, namely NB thw , NS thw , ZO thw , PS thw , and PB thw ; and the pre-established risk degree fuzzy set T ttc -1 ={NB ttc ,NS ttc ,ZO ttc ,PS ttc ,PB ttc} includes five fuzzy subsets, namely NB ttc , NS ttc , ZO ttc , PS ttc , and PB ttc; a second fuzzy set C2 = {NB2, NS2, ZO2, PS2, PB2} corresponding to the second correction variable is pre-established, and includes five fuzzy subsets, i.e., NB2, NS2, ZO2, PS2, and PB2, and it is assumed that a second index weight corresponding to the second correction variable is a safety index weight. Based on the pre-established inter-vehicle time fuzzy set, the risk degree fuzzy set, and the second fuzzy set, a corresponding fuzzy rule is established, which defines the corresponding relationship between each fuzzy subset in the second fuzzy set of the second correction variable and each fuzzy subset in the inter-vehicle time fuzzy set and the risk degree fuzzy set. As shown in Table 2, the corresponding relationship recorded in Table 2 is the established fuzzy rule.

[0081] Table 2

[0082]

[0083] In this embodiment, based on the fuzzy rule, a fuzzy subset in the second fuzzy set corresponding to the target fuzzy subset corresponding to the inter-vehicle time value and the target fuzzy subset corresponding to the risk degree value determined through step S2 is determined in the fuzzy rule, and then the fuzzy subset is determined as the second fuzzy subset corresponding to the second correction variable. For example, continuing to use the above example, when the target fuzzy subset corresponding to the inter-vehicle time value is determined as NS thw and the target fuzzy subset corresponding to the risk degree value is determined as ZO ttc , through the fuzzy rule shown in Table 2, the fuzzy subset in the second fuzzy set corresponding to NS thw and ZO ttc is determined as PS2, and thus the PS2 fuzzy subset in the second fuzzy set is determined as the second fuzzy subset corresponding to the second correction variable. The second correction variable is a correction variable corresponding to the second index weight, and the second index weight is one index weight different from the first index weight among the safety index weight and the comfort index weight. For example, when the first index weight is the comfort index weight, the second index weight is the safety index weight; when the first index weight is the safety index weight, the second index weight is the comfort index weight.

[0084] Step S02: defuzzifying the second fuzzy subset through a defuzzification algorithm to obtain a target value corresponding to the second correction variable.

[0085] In the embodiment, after the second fuzzy subset corresponding to the second correction variable is obtained through step S01, the second fuzzy subset is disambiguated through a disambiguation algorithm to obtain a determined target value corresponding to the second correction variable. The disambiguation algorithm is preferably a barycenter method disambiguation, and it should be understood that this is only a preferred disambiguation algorithm, and the disambiguation algorithm can also be other disambiguation algorithms, which are not limited here.

[0086] Step S03: correcting the second index weight through the target value corresponding to the second correction variable to obtain a second corrected index weight.

[0087] In the embodiment, after the disambiguation processing of step S02, a clear output value (i.e., a target value) corresponding to the second correction variable is obtained, and then the target value is used to correct the second index weight to obtain a corrected second index weight, which is the second corrected index weight.

[0088] In the present application, in the case where the adaptive cruise control method further includes steps S01 to S03, step S6 includes: performing adaptive cruise control based on the first corrected index weight and the second corrected index weight.

[0089] In the embodiment, after the first corrected index weight based on the vehicle driving state is obtained through step S5 and the second corrected index weight based on the vehicle driving state is obtained through step S03, the CACC system will perform cooperative adaptive cruise control on the ego vehicle based on the first corrected index weight and the second corrected index weight. Thus, compared with the previous cooperative adaptive cruise control on the ego vehicle based on the first index weight and the second index weight with fixed values, the present application dynamically adjusts the first index weight and the second index weight based on the vehicle driving state to improve the adaptability of the cooperative adaptive cruise control, thereby achieving the purpose of improving the comfort and reliability of driving.

[0090] In combination with the above embodiments, in an implementation manner, the present embodiment further provides an adaptive cruise control method. In the adaptive cruise control method, step S2 can include steps S21 to S22:

[0091] Step S21: according to the inter-vehicle time interval value, respectively calculating the membership value under the inter-vehicle time interval value through the membership function of each fuzzy subset in the inter-vehicle time interval fuzzy set, and determining the fuzzy subset corresponding to the maximum membership value as the target fuzzy subset corresponding to the inter-vehicle time interval value.

[0092] In the embodiment, each fuzzy subset in the pre-established workshop time interval fuzzy set has a corresponding membership function. After obtaining the current workshop time interval value through step S1, the workshop time interval value is respectively brought into the corresponding membership function of each fuzzy subset for calculation, and each membership function obtains a membership value. Then, the maximum membership value is screened out from all the obtained membership values, and the fuzzy subset to which the maximum membership value corresponds is determined as the target fuzzy subset corresponding to the workshop time interval value. Preferably, the membership function corresponding to each fuzzy subset in the workshop time interval fuzzy set is a Gaussian membership function.

[0093] Step S22: According to the risk degree value, the membership value under the risk degree value is respectively calculated through the membership function of each fuzzy subset in the risk degree fuzzy set, and the fuzzy subset corresponding to the maximum membership value is determined as the target fuzzy subset corresponding to the risk degree value.

[0094] In the embodiment, each fuzzy subset in the pre-established risk degree fuzzy set has a corresponding membership function. After obtaining the current risk degree value through step S1, the risk degree value is respectively brought into the corresponding membership function of each fuzzy subset for calculation, and each membership function obtains a membership value. Then, the maximum membership value is screened out from all the obtained membership values, and the fuzzy subset to which the maximum membership value corresponds is determined as the target fuzzy subset corresponding to the risk degree value. Preferably, the membership function corresponding to each fuzzy subset in the risk degree fuzzy set is a Gaussian membership function.

[0095] In combination with the above embodiments, in an implementation, the embodiments of the present application further provide a self-adaptive cruise control method. In the self-adaptive cruise control method, when the first fuzzy subset includes multiple fuzzy subsets, before step S4, the method further includes steps S041 to S042:

[0096] Step S041: According to the membership value of the target fuzzy subset corresponding to the first fuzzy subset, the minimum membership value is determined as the activation degree of the first fuzzy subset.

[0097] In the embodiment, when the first fuzzy subset corresponding to the target fuzzy subset corresponding to the workshop time interval value and the target fuzzy subset corresponding to the risk degree value is determined based on the pre-established fuzzy rule, and the first fuzzy subset includes multiple fuzzy subsets, in order to improve the optimization effect, the multiple first fuzzy subsets are weighted and averaged, and then a final first fuzzy subset after the weighted averaging is used for subsequent defuzzification.

[0098] Specifically: for each determined first fuzzy subset, there are two corresponding target fuzzy subsets, and each of the two target fuzzy subsets calculates a membership value when it is determined as a target fuzzy subset. The present application determines the minimum of the two membership values corresponding to the two target fuzzy subsets corresponding to each first fuzzy subset as the activation degree of the first fuzzy subset.

[0099] Step S042: according to the activation degree of each first fuzzy subset, the weighted average of all first fuzzy subsets is obtained to obtain the final first fuzzy subset.

[0100] In this embodiment, based on the activation degrees of the determined multiple first fuzzy subsets, the weighted average processing is performed on the multiple first fuzzy subsets to obtain a final comprehensive first fuzzy subset, and finally the comprehensive first fuzzy subset participates in the subsequent defuzzification. The higher the activation degree of the first fuzzy subset, the higher the influence on the final comprehensive first fuzzy subset obtained.

[0101] In combination with the above embodiments, in an implementation manner, the present application further provides an adaptive cruise control method. In the adaptive cruise control method, when the second fuzzy subset includes multiple second fuzzy subsets, before step S02, the method further includes steps S0021 to S0022:

[0102] Step S0021: according to the membership values of the target fuzzy subsets corresponding to the second fuzzy subset, the minimum membership value is determined as the activation degree of the second fuzzy subset.

[0103] In this embodiment, for each determined second fuzzy subset, there are two corresponding target fuzzy subsets, and each of the two target fuzzy subsets calculates a membership value when it is determined as a target fuzzy subset. The present application determines the minimum of the two membership values corresponding to the two target fuzzy subsets corresponding to each second fuzzy subset as the activation degree of the second fuzzy subset.

[0104] Step S0022: according to the activation degree of each second fuzzy subset, the weighted average of all second fuzzy subsets is obtained to obtain the final second fuzzy subset.

[0105] In this embodiment, based on the activation degrees of the determined multiple second fuzzy subsets, the weighted average processing is performed on the multiple second fuzzy subsets to obtain a final comprehensive second fuzzy subset, and finally the comprehensive second fuzzy subset participates in the subsequent defuzzification. The higher the activation degree of the second fuzzy subset, the higher the influence on the final comprehensive second fuzzy subset obtained.

[0106] In combination with the above embodiments, in an implementation, the embodiments of the present application further provide a self-adaptive cruise control method. In the self-adaptive cruise control method, step S1 can include: obtaining a time headway value between two vehicles according to a vehicle driving state by calculation through a time headway determination algorithm, and the time headway determination algorithm is expressed as wherein, T thw represents the time headway, d represents a distance between two vehicles, d c is a correction term, and v is a vehicle speed; obtaining a risk degree value of collision between two vehicles according to the vehicle driving state by calculation through a risk degree determination algorithm, and the risk degree determination algorithm is expressed as wherein, T ttc -1 represents the risk degree, v rel represents a speed difference between two vehicles, d represents a distance between two vehicles, v p represents a front vehicle speed.

[0107] In the present embodiment, a time headway value between two vehicles is obtained according to a vehicle driving state obtained by current monitoring by calculation through a time headway determination algorithm, and the time headway determination algorithm is expressed as wherein, T thw represents the time headway, d represents a distance between two vehicles, d c is a correction term, and v is a vehicle speed. Meanwhile, a risk degree value of collision between two vehicles is obtained according to the vehicle driving state obtained by current monitoring by calculation through a risk degree determination algorithm, and the risk degree determination algorithm is expressed as wherein, T ttc -1 represents the risk degree, v rel represents a speed difference between two vehicles, d represents a distance between two vehicles, v p represents a front vehicle speed.

[0108] In combination with the above embodiments, in an implementation, the embodiments of the present application further provide a self-adaptive cruise control method. In the self-adaptive cruise control method, before step S6, the method further includes step S061: determining a vehicle distance by fusion distance strategy, and the fusion distance strategy is expressed as: wherein, d exp represents a required vehicle distance to be maintained; d0 is a minimum safety distance between vehicles; d c is a correction term; t h and c are fixed constant coefficients; v is a vehicle speed; v head is a lead vehicle speed; v rel_head is a speed difference between two vehicles.

[0109] In the adaptive cruise control of the CACC system, the following vehicle distance strategy is also involved in the present embodiment, and the current following vehicle distance strategy mainly includes a fixed distance (CTH Constant Time Headway) strategy and a variable distance (VTH Variable Time Headway) strategy. The performance difference of the two mainly lies in convergence and self-adaptation. The CTH strategy refers to that the time distance between the vehicle heads is fixed and unchanged, and the expected distance is only related to the vehicle speed. The VTH strategy refers to that the time distance between the vehicle heads changes with the change of the surrounding environment, and the expected distance is not only related to the vehicle speed, but also related to the acceleration and speed of the front vehicle. Although the VTH strategy has the advantages of more flexibility, safety, comfort and efficiency, the CTH strategy has higher stability and reliability, is closer to the driving habit of the driver, and has less communication demand. The two have different advantages and disadvantages in different scenarios. In order to make the vehicle maintain the safety of following and the comfort of speed change in different working conditions, a new fusion distance strategy considering the fixed distance (CTH Constant Time Headway) strategy and the variable distance (VTH Variable Time Headway) strategy is proposed.

[0110] Specifically, the expression of the new fusion distance strategy is wherein d exp represents the required vehicle distance to be maintained; d0 is the minimum safe distance between vehicles; d c is a correction term; t h and c are fixed constant factors; v is the vehicle speed; v head is the speed of the leading vehicle (that is, the speed of the front vehicle followed by the cruise); v rel_head is the speed difference between the two vehicles. The lower limit value of d c is d0, so as to prevent the following distance from being too small, and the value is preferably 7m. The vehicle distance is determined by the fusion distance strategy. The fusion distance strategy takes into account the overall movement trend of the vehicle and the vehicle group, retains the good convergence of the CTH strategy, introduces the characteristics of the VTH strategy to dynamically adjust the expected following distance, and meets the condition that a p → 0 when Δd → 0 (a p is the acceleration of the front vehicle, and Δd is the following distance error), the stability of the fusion distance strategy is deduced, and it can be determined that the fusion distance strategy has higher stability when the vehicle group is stably driven.

[0111] In the present application, in the case that the method further comprises the step S061, the step S6 comprises: performing adaptive cruise control based on the first correction index weight, the second correction index weight and the required inter-vehicle distance to be maintained, or performing adaptive cruise control based on the first correction index weight and the required inter-vehicle distance to be maintained.

[0112] In the present embodiment, in the case that the present application introduces a new fusion spacing strategy, the CACC system performs adaptive cruise control based on the first correction index weight, the second correction index weight and the determined required inter-vehicle distance to be maintained, or performs adaptive cruise control based on the first correction index weight and the determined required inter-vehicle distance to be maintained.

[0113] In the present embodiment, the present application corrects the first index weight by the target value corresponding to the first correction variable to obtain the first correction index weight. One optional implementation of obtaining the first correction index weight by the target value corresponding to the first correction variable is: calculating by bringing the target value corresponding to the first correction variable into the expression , and calculating by bringing the obtained w1 value into the expression ω′1=a·w1 to obtain the corresponding first correction index weight. In the calculation, ω1 represents the first index weight, which is a known quantity in the CACC system; ω′1 represents the first correction index weight; C1 represents the target value corresponding to the first correction variable; a is a constant term, and in the case that the first index weight is a safety index weight, a is preferably 2, and in the case that the first index weight is a comfort index weight, a is preferably 0.6. The present application corrects the second index weight by the target value corresponding to the second correction variable to obtain the second correction index weight. One optional implementation of obtaining the second correction index weight by the target value corresponding to the second correction variable is: calculating by bringing the target value corresponding to the second correction variable into the expression , and calculating by bringing the obtained w2 value into the expression ω′2=b·w2 to obtain the corresponding second correction index weight. In the calculation, ω2 represents the second index weight, which is a known quantity in the CACC system; ω′2 represents the second correction index weight; C2 represents the target value corresponding to the second correction variable; b is a constant term, and in the case that the second index weight is a safety index weight, b is preferably 2, and in the case that the second index weight is a comfort index weight, b is preferably 0.6. In the present embodiment, by the implementation, the index weight ω x =diag[ω safe ω vrel ω comf ] which is fixed in the prior art becomes the index weight ω x =diag[ω′ safe ω vrel ω′ comf ] which is dynamically adjusted based on the vehicle driving state.

[0114] In this embodiment, the basic domain T of input and output is preferably limited according to general experience thw is [0, 3]; T ttc -1 is [-0.3, 0.3]; C safe and C comf is [-5, 5].

[0115] In this embodiment, as shown in Figure 3 and Figure 4 , a specific implementation of the adaptive cruise control method provided by the application can be to set a fuzzy controller on the input side of the upper controller of the CACC system, which is used to perform the steps in the adaptive cruise control method provided by the first aspect of the application, specifically: based on the inputs (i.e., the vehicle-to-vehicle time interval value T thw and the risk level value T ttc -1 ), the target fuzzy subsets corresponding to the two inputs are obtained through fuzzification; then based on the pre-established fuzzy rules, the first fuzzy subset corresponding to the first correction variable and / or the second fuzzy subset corresponding to the second correction variable are determined, and then the first fuzzy subset and / or the second fuzzy subset are de-fuzzified to obtain the target value of the first correction variable and / or the target value of the second correction variable, and the target value of the first correction variable is brought into the expression for calculation to obtain the corresponding w1 value and / or the target value of the second correction variable is brought into the expression for calculation to obtain the corresponding w2 value; then the obtained w1 value and / or the obtained w2 value are input into the upper controller, and the first correction index weight corresponding to the first correction variable is obtained by the upper controller through the expression ω'1=a·w1 and / or the second correction index weight corresponding to the second correction variable is obtained by the expression ω'2=b·w2; finally, adaptive cruise control is performed based on the obtained first correction index weight and / or second correction index weight.

[0116] Based on the same inventive concept, an embodiment of the application provides an adaptive cruise control system, as shown in Figure 5 , the system 500 comprises:

[0117] A parameter determination module 501 is configured to determine the vehicle-to-vehicle time interval value and the risk level value of collision occurrence according to the vehicle driving state.

[0118] A target fuzzy subset determination module 502 is configured to determine the target fuzzy subset in the vehicle-to-vehicle time interval fuzzy set corresponding to the vehicle-to-vehicle time interval value and the target fuzzy subset in the risk level fuzzy set corresponding to the risk level value according to the vehicle-to-vehicle time interval value and the risk level value.

[0119] The first fuzzy subset determination module 503 is configured to determine, according to a fuzzy rule, a first fuzzy subset corresponding to the target fuzzy subset in a first fuzzy set corresponding to the first correction variable, the first correction variable being a correction variable corresponding to a first index weight, the first index weight being a safety index weight or a comfort index weight.

[0120] The defuzzification processing module 504 is configured to defuzzify the first fuzzy subset by using a defuzzification algorithm to obtain a target value corresponding to the first correction variable.

[0121] The correction module 505 is configured to correct the first index weight by using the target value corresponding to the first correction variable to obtain a first corrected index weight.

[0122] The cruise control module 506 is configured to perform adaptive cruise control based on the first corrected index weight.

[0123] Optionally, the system 500 further includes:

[0124] The second fuzzy subset determination module is configured to determine, according to a fuzzy rule, a second fuzzy subset corresponding to the target fuzzy subset in a second fuzzy set corresponding to a second correction variable, the second correction variable being a correction variable corresponding to a second index weight, the second index weight being an index weight different from the first index weight among the safety index weight and the comfort index weight.

[0125] The defuzzification processing module is configured to defuzzify the second fuzzy subset by using a defuzzification algorithm to obtain a target value corresponding to the second correction variable.

[0126] The correction module is configured to correct the second index weight by using the target value corresponding to the second correction variable to obtain a second corrected index weight.

[0127] The first cruise control module is configured to perform adaptive cruise control based on the first corrected index weight and the second corrected index weight.

[0128] Optionally, the target fuzzy subset determination module 502 includes:

[0129] The first target fuzzy subset determination module is configured to calculate, according to the inter-vehicle time interval value, a membership value under the inter-vehicle time interval value by using a membership function of each fuzzy subset in an inter-vehicle time interval fuzzy set, and determine a fuzzy subset corresponding to a maximum membership value as a target fuzzy subset corresponding to the inter-vehicle time interval value.

[0130] The second target fuzzy subset determination module is configured to calculate membership values corresponding to the risk degree value respectively according to membership functions of each fuzzy subset in the risk degree fuzzy set according to the risk degree value, and determine a fuzzy subset corresponding to a maximum membership value as a target fuzzy subset corresponding to the risk degree value.

[0131] Optionally, the first fuzzy subset determination module 503 is configured to determine a fuzzy subset in the first fuzzy set corresponding to the target fuzzy subset corresponding to the inter-vehicle time interval value and the target fuzzy subset corresponding to the risk degree value according to a fuzzy rule, and determine the fuzzy subset in the first fuzzy set as a first fuzzy subset corresponding to the first correction variable.

[0132] Optionally, the second fuzzy subset determination module is configured to determine a fuzzy subset in the second fuzzy set corresponding to the target fuzzy subset corresponding to the inter-vehicle time interval value and the target fuzzy subset corresponding to the risk degree value according to a fuzzy rule, and determine the fuzzy subset in the second fuzzy set as a second fuzzy subset corresponding to the second correction variable.

[0133] Optionally, the system 500 further comprises:

[0134] The first activation degree determination module is configured to determine a minimum membership value as an activation degree of the first fuzzy subset according to the membership values of the target fuzzy subsets corresponding to the first fuzzy subsets when the first fuzzy subset comprises a plurality of fuzzy subsets.

[0135] The first fuzzy subset determination module 503 is configured to obtain a final first fuzzy subset by weighted averaging all the first fuzzy subsets according to the activation degrees of the first fuzzy subsets.

[0136] The second activation degree determination module is configured to determine a minimum membership value as an activation degree of the second fuzzy subset according to the membership values of the target fuzzy subsets corresponding to the second fuzzy subsets when the second fuzzy subset comprises a plurality of fuzzy subsets.

[0137] The second fuzzy subset determination module is configured to obtain a final second fuzzy subset by weighted averaging of all the second fuzzy subsets according to the activation degrees of each second fuzzy subset.

[0138] Optionally, the system 500 further comprises:

[0139] The inter-vehicle distance determination module is configured to determine the inter-vehicle distance by using a fusion distance strategy expressed as: wherein d exp represents the required inter-vehicle distance; d0 represents the minimum safety distance between vehicles; d c represents a correction term; t h and c represent fixed constant coefficients; v represents the speed of the ego vehicle; v head represents the speed of the leading vehicle; v rel_head represents the speed difference between the two vehicles.

[0140] The second cruise control module is configured to perform adaptive cruise control based on the first correction index weight, the second correction index weight, and the required inter-vehicle distance.

[0141] Optionally, the parameter determination module 501 comprises:

[0142] The inter-vehicle time interval value determination module is configured to obtain the inter-vehicle time interval value between the two vehicles by using an inter-vehicle time interval determination algorithm according to the vehicle driving state, the inter-vehicle time interval determination algorithm being expressed as: wherein T thw represents the inter-vehicle time interval, d represents the distance between the two vehicles, and d c represents a correction term, and v represents the speed of the ego vehicle.

[0143] The risk degree value determination module is configured to obtain the risk degree value of collision between the two vehicles by using a risk degree determination algorithm according to the vehicle driving state, the risk degree determination algorithm being expressed as: wherein T ttc -1 represents the risk degree, v rel represents the speed difference between the two vehicles, d represents the distance between the two vehicles, and v p represents the speed of the leading vehicle.

[0144] Based on the same inventive concept, an embodiment of the present application provides a vehicle provided with the adaptive cruise control system according to the second aspect of the present application, and configured to perform the steps in the adaptive cruise control method according to the first aspect of the present application.

[0145] For the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the related parts can be referred to the part of the system embodiment.

[0146] It should be noted that, for the method embodiments, the operations performed are described in sequence for simplicity and clarity, but those skilled in the art will appreciate that some steps can be performed in other sequence or in parallel. Furthermore, those skilled in the art will appreciate that the examples described in the specification are preferred examples only and are not the only way in which the application can be practised.

[0147] Each embodiment described in the specification is described using a progressive approach. Each embodiment focuses on the differences from other embodiments, and parts that are the same or similar between embodiments can be mutually referred to.

[0148] Those skilled in the art will appreciate that embodiments of the application can be provided as a method, a system, or a computer program product. Accordingly, embodiments of the application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the application can be embodied in the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk memory, CD-ROM, optical memory, etc.) having computer usable program code embodied therein.

[0149] Embodiments of the application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal devices to produce a machine, so that the instructions, which are executed via the processor of the computer or other programmable data processing terminal devices, generate a device implemented in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that carries out the function specified in the flow or flows and / or block or blocks.

[0150] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing terminal devices to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction apparatus, which implements the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that carries out the function specified in the flow or flows and / or block or blocks.

[0151] These computer program instructions can also be loaded into a computer or other programmable data processing terminal device, so that a series of operational steps are performed on the computer or other programmable terminal device to generate a computer-implemented process, thus the instructions executed on the computer or other programmable terminal device provide a process for implementing the functions specified in the flowchart Figure 1 one flow or multiple flows and / or the functions specified in the block Figure 1 one block or multiple blocks.

[0152] Although the preferred embodiments of the present application have been described, those skilled in the art who understand the basic inventive concept after getting to know the present application can make additional changes and modifications to the embodiments. Therefore, the appended claims are intended to cover the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present application.

[0153] Finally, it should also be noted that, in this document, the relational terms such as first and second and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any such actual relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof are intended to cover a non-exclusive inclusion, so that a process, method, article, or terminal device including a series of elements includes not only those elements but also other elements not explicitly listed or other elements inherent to such process, method, article, or terminal device. Without more limitations, an element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article, or terminal device including the element.

[0154] The above provides a detailed description of the adaptive cruise control method, system and vehicle of the present application. The principles and implementation modes of the present application are described by using specific examples. The above description of the embodiments is only used to help understand the method of the present application and its core idea; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation modes and application ranges will be changed; in summary, the content of the present description should not be understood as a limitation of the present application.

Claims

1. An adaptive cruise control method, characterized in that: The method comprises: According to the driving status of the vehicles, the time distance between the two vehicles and the risk level of collision are determined; According to the workshop time distance value and the risk level value, determining a target fuzzy subset corresponding to the workshop time distance value in the workshop time distance fuzzy set and a target fuzzy subset corresponding to the risk level value in the risk level fuzzy set; Determining, according to a fuzzy rule, a first fuzzy subset corresponding to the target fuzzy subset in a first fuzzy set corresponding to a first correction variable, wherein the first correction variable is a correction variable corresponding to a first indicator weight, and the first indicator weight is a safety indicator weight or a comfort indicator weight; Defuzzifying the first fuzzy subset using a defuzzification algorithm to obtain a target value corresponding to the first correction variable; Correcting the first indicator weight by using the target value corresponding to the first correction variable to obtain a first corrected indicator weight; Adaptive cruise control is performed based on the first correction index weight.

2. The adaptive cruise control method according to claim 1, characterized in that: Before performing adaptive cruise control based on the first correction index weight, the method further includes: determining, according to the fuzzy rule, a second fuzzy subset corresponding to the target fuzzy subset in a second fuzzy set corresponding to a second correction variable, wherein the second correction variable is a correction variable corresponding to a second indicator weight, and the second indicator weight is an indicator weight different from the first indicator weight among the safety indicator weight and the comfort indicator weight; Defuzzifying the second fuzzy subset using a defuzzification algorithm to obtain a target value corresponding to the second correction variable; Correcting the second indicator weight by the target value corresponding to the second correction variable to obtain a second corrected indicator weight; The performing adaptive cruise control based on the first correction index weight includes: performing adaptive cruise control based on the first correction index weight and the second correction index weight.

3. The adaptive cruise control method according to claim 2, characterized in that: Determining, according to the time headway value and the risk level value, a target fuzzy subset corresponding to the time headway value in the time headway fuzzy set and a target fuzzy subset corresponding to the risk level value in the risk level fuzzy set, including: According to the time headway value, the membership value under the time headway value is calculated respectively by using the membership function of each fuzzy subset in the time headway fuzzy set, and the fuzzy subset corresponding to the maximum membership value is determined as the target fuzzy subset corresponding to the time headway value; According to the risk level value, the membership value under the risk level value is calculated respectively through the membership function of each fuzzy subset in the risk level fuzzy set, and the fuzzy subset corresponding to the maximum membership value is determined as the target fuzzy subset corresponding to the risk level value.

4. The adaptive cruise control method according to claim 1, characterized in that: Determining, according to the fuzzy rule, a first fuzzy subset corresponding to the target fuzzy subset in the first fuzzy set corresponding to the first correction variable, comprising: Determining, according to a fuzzy rule, a fuzzy subset in a first fuzzy set corresponding to the first correction variable that corresponds to both a target fuzzy subset corresponding to the time headway value and a target fuzzy subset corresponding to the risk level value, wherein the fuzzy rule defines a correspondence between the fuzzy subsets in the first fuzzy set and both the fuzzy subsets in the time headway fuzzy set and the fuzzy subsets in the risk level fuzzy set; The fuzzy subset corresponding to both the target fuzzy subset corresponding to the time headway value and the target fuzzy subset corresponding to the risk level value in the determined first fuzzy set is determined as the first fuzzy subset corresponding to the first correction variable.

5. The adaptive cruise control method according to claim 2, characterized in that: Determining, according to the fuzzy rule, a second fuzzy subset corresponding to the target fuzzy subset in the second fuzzy set corresponding to the second correction variable, comprising: Determining, according to a fuzzy rule, a fuzzy subset in a second fuzzy set corresponding to the second correction variable that corresponds to both a target fuzzy subset corresponding to the time headway value and a target fuzzy subset corresponding to the risk level value, wherein the fuzzy rule defines a correspondence between the fuzzy subsets in the second fuzzy set and both the fuzzy subsets in the time headway fuzzy set and the fuzzy subsets in the risk level fuzzy set; The fuzzy subset corresponding to both the target fuzzy subset corresponding to the time headway value and the target fuzzy subset corresponding to the risk level value in the determined second fuzzy set is determined as the second fuzzy subset corresponding to the second correction variable.

6. The adaptive cruise control method according to claim 3, characterized in that: In the case where the first fuzzy subset includes a plurality of fuzzy subsets, before defuzzifying the first fuzzy subset using a defuzzification algorithm to obtain a target value corresponding to the first correction variable, the method further includes: According to the membership value of the target fuzzy subset corresponding to the first fuzzy subset, the minimum membership value is determined as the activation degree of the first fuzzy subset; According to the activation degree of each first fuzzy subset, all first fuzzy subsets are weighted averaged to obtain the final first fuzzy subset; In the case where the second fuzzy subset includes a plurality of fuzzy subsets, before defuzzifying the second fuzzy subset using a defuzzification algorithm to obtain a target value corresponding to the second correction variable, the method further includes: According to the membership value of the target fuzzy subset corresponding to the second fuzzy subset, the minimum membership value is determined as the activation degree of the second fuzzy subset; According to the activation degree of each second fuzzy subset, all the second fuzzy subsets are weighted averaged to obtain the final second fuzzy subset.

7. The adaptive cruise control method according to claim 2, characterized in that: Before performing adaptive cruise control based on the first correction index weight and the second correction index weight, the method further includes: The vehicle distance is determined by integrating the spacing strategy, and the integration spacing strategy expression is: ,in, Indicates the vehicle distance that needs to be maintained; It is the minimum safe distance in the workshop; is the correction item; and c are fixed constant coefficients; v is the vehicle speed; is the speed of the pilot vehicle; is the speed difference between the two vehicles; The performing of the adaptive cruise control based on the first correction index weight and the second correction index weight includes: performing the adaptive cruise control based on the first correction index weight, the second correction index weight and the required vehicle distance to be maintained.

8. The adaptive cruise control method according to claim 1, characterized in that: According to the driving status of the vehicles, the time interval between the two vehicles and the risk level of collision are determined, including: According to the vehicle driving status, the time distance between the two vehicles is calculated by the time distance determination algorithm. The time distance determination algorithm expression is: ,in, represents the time interval between vehicles, d represents the distance between two vehicles, is the correction term, v is the vehicle speed; According to the driving status of the vehicles, the risk level of collision between the two vehicles is calculated by the risk level determination algorithm. The risk level determination algorithm expression is: ,in, Indicates the degree of risk, represents the speed difference between the two vehicles, d represents the distance between the two vehicles, Indicates the speed of the vehicle ahead.

9. An adaptive cruise control system, characterized in that: The system comprises: A parameter determination module is used to determine the time interval between two vehicles and the risk level of collision according to the driving status of the vehicles; A target fuzzy subset determination module is configured to determine, based on the time headway value and the risk level value, a target fuzzy subset corresponding to the time headway value in the time headway fuzzy set and a target fuzzy subset corresponding to the risk level value in the risk level fuzzy set; a first fuzzy subset determination module, configured to determine, according to a fuzzy rule, a first fuzzy subset corresponding to the target fuzzy subset in a first fuzzy set corresponding to a first correction variable, wherein the first correction variable is a correction variable corresponding to a first indicator weight, and the first indicator weight is a safety indicator weight or a comfort indicator weight; a defuzzification processing module, configured to defuzzify the first fuzzy subset using a defuzzification algorithm to obtain a target value corresponding to the first correction variable; a correction module, configured to correct the first indicator weight according to the target value corresponding to the first correction variable to obtain a first corrected indicator weight; A cruise control module is configured to perform adaptive cruise control based on the first correction index weight.

10. A vehicle, characterized in that: The vehicle is provided with an adaptive cruise control system according to claim 9, which is used to execute the steps of an adaptive cruise control method according to any one of claims 1 to 8.

Images