Control method and device of vehicle, storage medium and vehicle

Abstract

The application discloses a control method and device of a vehicle, a storage medium and the vehicle. The method comprises the following steps: determining a driving state of the vehicle based on driving data of the vehicle; collecting to-be-processed data in the driving data in response to the driving state being a curve driving state, wherein the to-be-processed data comprises a road curvature of a driving road of the vehicle, a yaw angular velocity of the vehicle and a yaw tracking error of the vehicle; performing fuzzy processing on the to-be-processed data based on a fuzzy rule to obtain control data of the vehicle; and controlling the vehicle to drive on the curve based on the control data. The application solves the technical problem of poor curve driving performance of the vehicle.

Description

Technical Field

[0001] This invention relates to the field of vehicles, and more specifically, to a vehicle control method, apparatus, storage medium, and vehicle. Background Technology

[0002] Adaptive cruise control is an intelligent automatic control system that evolved from cruise control and can effectively reduce the driver's workload.

[0003] In related technologies, the cornering control method of adaptive cruise control mainly controls the vehicle speed by calculating information such as road curvature and vehicle speed. In this process, cameras, high-precision maps and global positioning systems are required to achieve cornering speed control. Since this method cannot take into account changes in actual conditions and cannot adapt to the driving style of the current driver, the technical problem of poor cornering performance of the vehicle still exists.

[0004] There is currently no effective solution to the technical problem of poor cornering performance of vehicles in the aforementioned related technologies. Summary of the Invention

[0005] This invention provides a vehicle control method, device, storage medium, and vehicle to at least solve the technical problem of poor cornering performance of vehicles.

[0006] According to one aspect of the present invention, a vehicle control method is provided. The method may include: determining the vehicle's driving state based on the vehicle's driving data; in response to the driving state being a curve driving state, acquiring data to be processed from the driving data, wherein the data to be processed includes: the road curvature of the vehicle's driving path, the vehicle's yaw rate, and the vehicle's yaw tracking error; performing fuzzy processing on the data to be processed based on fuzzy rules to obtain vehicle control data; and controlling the vehicle to perform curve driving based on the control data.

[0007] Optionally, fuzzy processing is performed on the data to be processed based on fuzzy rules to obtain control data, including: fuzzy processing of the data to be processed through a membership function to obtain fuzzified data; and fuzzy processing of the fuzzified data based on a preset correspondence between the fuzzified data and the control data to obtain control data.

[0008] Optionally, the fuzzy data is subjected to fuzzification processing to obtain control data, including: performing fuzzification processing on the fuzzy data to obtain a processing result; and decoding the processing result to obtain control data.

[0009] Optionally, the data to be processed is fuzzy processed through the membership function to obtain fuzzy data, including: in response to the membership function being a trigonometric function, the road curvature and yaw rate are converted through the trigonometric function to obtain fuzzy data.

[0010] Optionally, the data to be processed is fuzzy through the membership function to obtain fuzzy data, including: in response to the membership function being a bell function, the lateral tracking error is transformed through the bell function to obtain fuzzy data.

[0011] Optionally, determining the vehicle's driving state based on the vehicle's driving data includes: determining the vehicle's lane curvature equation based on the driving data; sampling curvature points on the lane curvature equation to obtain at least one curvature point; determining the average curvature of a target number of curvature points and the fluctuation between the target number of curvature points; and determining the driving state based on the average curvature and the fluctuation.

[0012] Optionally, the driving state is determined based on the average curvature and volatility, including: determining the driving state as a curve driving state in response to the average curvature being greater than a curvature threshold or the volatility being greater than a volatility threshold.

[0013] According to another aspect of the present invention, a vehicle control device is also provided. The device may include: a determining unit for determining the driving state of the vehicle based on driving data; a acquiring unit for acquiring data to be processed from the driving data in response to the driving state being a curve driving state, wherein the data to be processed includes: the road curvature of the driving path, the yaw rate of the vehicle, and the yaw tracking error of the vehicle; a processing unit for performing fuzzy processing on the data to be processed based on fuzzy rules to obtain control data for the vehicle; and a control unit for controlling the vehicle to perform curve driving based on the control data.

[0014] According to another aspect of the present invention, a computer-readable storage medium is also provided. The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the vehicle control method of the present invention.

[0015] According to another aspect of the present invention, a processor is also provided. The processor is used to run a program, wherein the program executes the vehicle control method of the present invention during runtime.

[0016] According to another aspect of the present invention, a vehicle is also provided. This vehicle is used to execute the vehicle control method of the present invention.

[0017] In this embodiment of the invention, the vehicle's driving state is determined based on the vehicle's driving data. In response to the driving state being a curve driving state, unprocessed data is collected from the driving data. This unprocessed data includes: the road curvature of the vehicle's driving path, the vehicle's yaw rate, and the vehicle's yaw tracking error. Fuzzy processing is performed on the unprocessed data based on fuzzy rules to obtain the vehicle's control data. The vehicle is then controlled to drive on the curve based on this control data. In other words, by analyzing the collected vehicle driving data, this invention can determine whether the vehicle's driving state is a curve driving state or a straight driving state. If the vehicle is in a curve driving state, fuzzy processing can be performed on the road curvature, yaw rate, and lateral tracking error of the currently driven path in the unprocessed data to determine the vehicle's control data and control the vehicle to drive on the curve. Because the unprocessed data is fuzzy processed according to fuzzy rules, it can simulate human reasoning and control when driving on a curve, enabling the vehicle to drive on a curve. In this case, it achieves the goal of driving on a curve in a manner consistent with human driving style, thereby solving the technical problem of poor vehicle curve driving performance and achieving the technical effect of improving vehicle curve driving performance. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0019] Figure 1 This is a flowchart of a vehicle control method according to an embodiment of the present invention;

[0020] Figure 2 This is a flowchart of a curve speed control method under adaptive cruise according to an embodiment of the present invention;

[0021] Figure 3 This is a schematic diagram of a vehicle body coordinate system according to an embodiment of the present invention;

[0022] Figure 4 This is a schematic diagram of a road curvature membership function according to an embodiment of the present invention;

[0023] Figure 5 This is a schematic diagram of a membership function for lateral tracking error according to an embodiment of the present invention;

[0024] Figure 6 This is a schematic diagram of a membership function for a vehicle yaw rate according to an embodiment of the present invention;

[0025] Figure 7 This is a schematic diagram of a membership function for a planned speed according to an embodiment of the present invention;

[0026] Figure 8 This is a schematic diagram of a vehicle control device according to an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] According to an embodiment of the present invention, an embodiment of a vehicle control method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] Figure 1 This is a flowchart of a vehicle control method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0032] Step S102: Determine the vehicle's driving status based on the vehicle's driving data.

[0033] In the technical solution provided in step S102 of the present invention, vehicle driving data can be acquired. By processing the driving data, the vehicle's driving state can be determined. The driving state can include driving in a curve and driving in a straight line. The driving data can include information such as the vehicle's speed, acceleration, and yaw angle. This is only an example and does not impose specific limitations on the driving data.

[0034] Optionally, vehicle driving data can be acquired through sensors and other data acquisition devices deployed throughout the vehicle. Based on the driving data, the lane curvature equation of the lane in which the vehicle is located can be determined, points on the lane curvature equation can be extracted, and the curvature and fluctuation degree of each point can be determined. The vehicle's driving status can be determined based on the curvature and fluctuation degree.

[0035] For example, a certain number of points can be extracted from the lane curvature equation to determine the curvature of all points, thus obtaining the average curvature. Alternatively, the degree of fluctuation of all points can be determined based on the curvature of all points. The driving state of the vehicle can be judged by comparing the average curvature with the maximum curvature under straight driving conditions, or by comparing the degree of fluctuation with the maximum degree of fluctuation under straight driving conditions.

[0036] For example, if the average curvature of all points is less than the maximum curvature under straight-line driving conditions, and the degree of fluctuation of all points is less than the maximum degree of fluctuation under straight-line driving conditions, then the vehicle is driving in a straight-line state. If the average curvature of all points is greater than or equal to the maximum curvature under straight-line driving conditions, or the degree of fluctuation of all points is greater than or equal to the maximum degree of fluctuation under straight-line driving conditions, then the vehicle is driving in a curved state. It should be noted that this is only an example and does not impose specific restrictions on the methods and processes for determining the vehicle's driving state.

[0037] Step S104: In response to the driving state being a curve driving state, collect the data to be processed from the driving data, wherein the data to be processed includes: the road curvature of the driving road, the yaw rate of the vehicle, and the yaw tracking error of the vehicle.

[0038] In the technical solution provided in step S104 of the present invention, the vehicle's driving state can be either a curve driving state or a straight driving state. When the driving state is determined to be a curve driving state, the required data to be processed can be collected from the driving data. This data to be processed may include, but is not limited to: the road curvature of the road the vehicle is traveling on, the vehicle's yaw rate, and the vehicle's yaw tracking error. The yaw tracking error can be used to characterize the lateral position error between the vehicle's current position and its future position. The yaw rate can be used to characterize the vehicle's stability. It should be noted that the above-mentioned data to be processed is only illustrative and does not constitute a specific limitation.

[0039] Step S106: Perform fuzzy processing on the data to be processed based on fuzzy rules to obtain vehicle control data.

[0040] In the technical solution of step S106 of the present invention, the data to be processed in the driving data can be fuzzy processed by fuzzy rules in the fuzzy rule base to determine the vehicle control data. The fuzzy rule base can contain multiple complete decision statements, for example, it can be a database containing multiple "IF-THEN" statements. The fuzzy rules can be the decision statements in the fuzzy rule base.

[0041] Optionally, road curvature, yaw rate, and yaw tracking error can each have their own universe of discourse and fuzzy language set. The corresponding fuzzy language can be determined for all points in their respective universes of discourse. For example, the universe of discourse for road curvature is [0, 0.05], and the fuzzy language set for road curvature can be {S, M, B}, where S represents large, M represents medium, and B represents small. All points in the universe of discourse for road curvature correspond to any one of the three fuzzy languages ​​in the fuzzy language set. Then, the fuzzy language can be fuzzy-processed using fuzzy rules to obtain the vehicle's control data. It should be noted that the method and process for determining the fuzzy data of the data to be processed here are only illustrative and do not impose specific limitations.

[0042] For example, when fuzzy data is obtained, the fuzzy data can be processed using the judgment statements in the fuzzy rule base to convert the fuzzy data into control data.

[0043] In related technologies, the speed of a vehicle when driving on a curve can be determined by analyzing driving data such as road curvature and vehicle yaw angle. However, since this does not take into account changes in actual conditions and cannot match the driver's driving style, the technical problem of poor comfort when driving on curves still exists. In the embodiments of this invention, the data to be processed is fuzzy processed to obtain control data. Compared with directly calculating the data to be processed to obtain specific control values, this can better match human driving habits when driving on curves, thereby achieving the technical effect of improving the comfort of the vehicle when driving on curves.

[0044] Step S108: Control the vehicle to drive on the curve based on the control data.

[0045] In the above-mentioned step S108 technical solution of the present invention, after fuzzy processing of the data to be processed based on fuzzy rules to obtain the vehicle control data, the vehicle can be controlled to drive on a curve based on the control data, wherein the control data may include the speed of the vehicle driving on a curve.

[0046] For example, by collecting vehicle driving status data, it can be determined whether the vehicle is in a curve or a straight line. If the vehicle is in a straight line, there is no need to control the vehicle for curve driving. If the vehicle is in a curve, the road curvature, yaw rate, and yaw tracking error can be extracted from the driving data. These three have their own universes of discourse and fuzzy language sets. By processing each of them separately, the fuzzy language corresponding to all points in each universe of discourse in the fuzzy language set can be obtained. By performing fuzzy processing on the fuzzy language according to fuzzy rules, the speed required for the vehicle to drive in a curve can be obtained, thereby controlling the vehicle to drive in a curve.

[0047] In steps S102 to S108 of this application, the driving state of the vehicle is determined based on the vehicle's driving data; in response to the driving state being a curve driving state, data to be processed in the driving data is collected, wherein the data to be processed includes: the road curvature of the driving road, the yaw rate of the vehicle, and the yaw tracking error of the vehicle; the data to be processed is fuzzy processed based on fuzzy rules to obtain the vehicle's control data; and the vehicle is controlled to drive on the curve based on the control data. In other words, by analyzing the collected vehicle driving data, this invention can determine whether the vehicle is driving in a curve or a straight line. If the vehicle is driving in a curve, the road curvature, yaw rate, and lateral tracking error of the current road in the data to be processed can be fuzzy-processed to determine the vehicle's control data and control the vehicle to drive in a curve. Since the data to be processed is fuzzy-processed according to fuzzy rules, it can simulate human reasoning and control when driving in a curve, enabling the vehicle to drive in a curve. In this case, it achieves the goal of driving in a curve in a way that conforms to human driving style, thereby solving the technical problem of poor vehicle curve driving performance and achieving the technical effect of improving vehicle curve driving performance.

[0048] The method described in this embodiment will be further described below.

[0049] As an optional embodiment, step S106, which involves performing fuzzy processing on the data to be processed based on fuzzy rules to obtain control data, includes: performing fuzzy processing on the data to be processed using a membership function to obtain fuzzified data; and performing fuzzy processing on the fuzzified data based on a preset correspondence between the fuzzified data and the control data to obtain control data.

[0050] In this embodiment, the data to be processed can be fuzzy-processed using a membership function to obtain fuzzy data. The control data corresponding to the fuzzy data can be obtained based on a preset correspondence between the fuzzy data and control data. The membership function can be used to determine the membership degree of the data to be processed to the fuzzy data, and can be a trigonometric function, a Gaussian function, or a bell function. The fuzzy data can be a set of fuzzy languages, which may include multiple fuzzy languages. It should be noted that the membership function here is only illustrative and is not specifically limited.

[0051] Optionally, road curvature, yaw rate, and lateral tracking error each have their own universe of discourse, and the three data to be processed have their own fuzzy language sets. The data to be processed can be fuzzy processed separately using membership functions. For example, trigonometric functions can be used to fuzzify road curvature, which can determine the fuzzy language corresponding to all points in the universe of discourse of road curvature; bell-shaped functions can be used to fuzzify lateral tracking error, which can determine the fuzzy language corresponding to all points in the universe of discourse of lateral tracking error; and trigonometric functions can be used to fuzzify yaw rate, which can determine the fuzzy language corresponding to all points in the universe of discourse of yaw rate.

[0052] Optionally, the preset fuzzy data for road curvature can be {S, M, B}, representing large, medium, and small, respectively; the preset fuzzy data for lateral tracking error can be {S, M, B}, representing large, medium, and small, respectively; the fuzzy data for yaw rate can be {S, B}, representing large and small, respectively. Each preset fuzzy data for the data to be processed can correspond to a control data. Based on the correspondence between the preset fuzzy data and the control data, the fuzzy data can be fuzzy processed to obtain the corresponding control data.

[0053] For example, fuzzy rules can be generated based on the driver's road driving experience and stored in a database. Data to be processed can be obtained, and fuzzy processing can be performed on the data to be processed based on the fuzzy rules stored in the database to obtain control data.

[0054] For another example, since road curvature has a significant impact on vehicle comfort and lateral stability, it can be set as the primary input for fuzzy control. When a vehicle is driving on a curve, the lateral tracking error can be large depending on the chosen turning position, and this error gradually decreases to zero after exiting the curve. Therefore, on curves with greater curvature, the impact of lateral tracking error on the vehicle is less than on curves with less curvature. Yaw rate directly reflects the vehicle's stability during driving; a larger value indicates greater instability.

[0055] If a vehicle is traveling on a curve, centrifugal force may occur at high speeds, resulting in a poor riding experience and potential safety hazards. In this embodiment of the invention, to address the technical problem of poor vehicle stability on curves and to make vehicle curve driving more in line with human driving habits, fuzzy processing can be performed on data such as road curvature, yaw rate, and lateral tracking difference to obtain control data for controlling the vehicle to travel on curves, thereby improving the vehicle's stability on curves.

[0056] As an optional embodiment, step S106, which involves fuzzing the fuzzy data to obtain control data, includes: fuzzing the fuzzy data to obtain a processing result; and decoding the processing result to obtain control data.

[0057] In this embodiment, the data to be processed is fuzzed through a membership function to obtain fuzzy data. After obtaining fuzzy data, the fuzzy data can be further fuzzed to obtain a processing result. Based on the decoding of the processing result, control data can be obtained. The processing result can be a fuzzy quantity.

[0058] Optionally, the fuzzy data of the vehicle can be fuzzified using a fuzzy controller through fuzzy rules. Based on the fuzzy rules, a preset correspondence between the fuzzy data and the control data can be determined. In the fuzzy controller, the vehicle data to be processed can be used as input data, and the control data can be used as output data. The database of fuzzy rules can be generated based on expert experience and control engineering knowledge. It should be noted that this is only an example and does not impose specific limitations on the fuzzy rule library and fuzzy rules. Any steps and methods for fuzzifying the vehicle data to obtain control data are within the protection scope of this invention.

[0059] In this embodiment of the invention, since the result obtained after fuzzy processing of the fuzzy data is a fuzzy quantity, it cannot be used to directly control the vehicle in curves. The processing result needs to be decoded. For example, it can be decoded using methods such as the center of gravity method, the maximum membership method, or the area bisector method, converting the fuzzy result into control data, thereby solving the technical problem of poor curve handling performance of the vehicle. It should be noted that this is merely an illustrative example and does not impose specific limitations on the decoding methods and processes.

[0060] As an optional embodiment, step S106 involves performing fuzzy processing on the data to be processed using a membership function to obtain fuzzy data. This includes: in response to the membership function being a trigonometric function, converting the road curvature and yaw rate using a trigonometric function to obtain fuzzy data.

[0061] In this embodiment, when the membership function is a trigonometric function, the road curvature and yaw rate in the data to be processed can be transformed by the trigonometric function to obtain fuzzy data of road curvature and fuzzy data of yaw rate.

[0062] Optionally, the road curvature can be fuzzed using trigonometric functions, converting all points in the universe of discourse of the road curvature into corresponding fuzzified data; the yaw rate can be fuzzified using trigonometric functions, converting all points in the universe of discourse of the yaw rate into corresponding fuzzified data.

[0063] For example, the universe of discourse for road curvature can be [0, 0.05], and its fuzzy language set can be {S, M, B}. Road curvature can be used as the independent variable, and the membership degree of the fuzzy data can be used as the dependent variable. The trigonometric function in the membership function is used to determine the membership degree of each point in the universe of discourse of road curvature to S, M, and B in the fuzzy language set. Based on the membership degree, all points in the universe of discourse of road curvature can be converted into the corresponding fuzzy data. For example, if the road curvature is 0.05, the membership degree of S is 0, the membership degree of M is 0, and the membership degree of B is 1, so the road curvature can be converted into fuzzy data B; if the road curvature is 0, the membership degree of S is 1, the membership degree of M is 0, and the membership degree of B is 0, so the road curvature can be converted into fuzzy data S.

[0064] For another example, the universe of discourse for the yaw rate can be [-5, 5], and its fuzzy language set can be {S, B}. The yaw rate can be used as the independent variable, and the membership degree of the fuzzy data can be used as the dependent variable. The trigonometric function in the membership function is used to determine the membership degree of each point in the universe of discourse of the yaw rate to S and B in the fuzzy language set. Based on the membership degree, all points in the universe of discourse of the yaw rate can be converted into the corresponding fuzzy data. For example, if the yaw rate is 5, the membership degree of S is 1, and the membership degree of B is 0. The yaw rate can be converted into fuzzy data S.

[0065] It should be noted that the above-mentioned fuzzy language set and the method and process for converting the data to be processed into fuzzy data are only illustrative examples and are not subject to specific limitations.

[0066] As an optional embodiment, step S106 involves performing fuzzy processing on the data to be processed using a membership function to obtain fuzzy data, including: in response to the membership function being a bell-shaped function, converting the lateral tracking error using the bell-shaped function to obtain fuzzy data.

[0067] In this embodiment, when the membership function is a bell function, the lateral tracking error in the data to be processed can be transformed by the bell function to obtain fuzzy data of the lateral tracking error.

[0068] For example, the universe of discourse for the lateral tracking error can be [0, 0.8], and its fuzzy language set can be {S, M, B}. The lateral tracking error can be used as the independent variable, and the membership degree of the fuzzy data can be used as the dependent variable. The bell function in the membership function is used to determine the membership degree of each point in the universe of discourse of the lateral tracking error to S, M and B in the fuzzy language set. Based on the membership degree, all points in the universe of discourse of the lateral tracking error can be converted into the corresponding fuzzy data. For example, if the lateral tracking error is 0.6, the membership degree of S is 0, the membership degree of M is 0, and the membership degree of B is 1. The lateral tracking error can be converted into fuzzy data B.

[0069] As an optional embodiment, step S102, determining the vehicle's driving state based on the vehicle's driving data, includes: determining the vehicle's lane curvature equation based on the driving data; sampling curvature points on the lane curvature equation to obtain at least one curvature point; determining the average curvature of a target number of curvature points and the fluctuation between the target number of curvature points; and determining the driving state based on the average curvature and the fluctuation.

[0070] In this embodiment, vehicle driving data is acquired. Based on this data, the lane curvature equation of the vehicle can be determined. By sampling the points on the lane curvature equation, a target number of curvature points can be obtained. The average curvature and volatility of all curvature points are then determined. Based on the average curvature and volatility, the vehicle's driving state can be determined. Volatility characterizes the degree of fluctuation of the curvature points; the larger the value, the greater the fluctuation. The target number can be a preset value or user-defined data. This is merely an example and no specific limit is imposed on the target number.

[0071] Alternatively, using vehicle driving data, such as vehicle speed, vehicle acceleration, and vehicle yaw angle, the lane trajectory equation can be determined using the following formula:

[0072] y = c0 + c1x + c2x 2 +c3x 3

[0073] Where y can be used to represent the trajectory equation of the lane line, c0 can be used to represent the current position of the starting point, c1 can be used to represent the current speed of the starting point, c2 can be used to represent the curvature, c3 can be used to represent the rate of change of the curvature, and x can be used to represent the horizontal coordinate of the vehicle's position.

[0074] Alternatively, based on the lane line trajectory equation, the lane line curvature equation can be calculated using the following formula:

[0075] y”=2c2+6c3x

[0076] Here, y” can be used to represent the lane curvature equation.

[0077] Optionally, curvature points can be sampled from the lane curvature equation. A target number of curvature points can be selected, for example, 100 curvature points k1, k2, k3…k can be extracted. 100 Each curvature point can be spaced 0.5m apart. It should be noted that this is only an example and does not impose specific restrictions on the method and process of sampling curvature points.

[0078] Optionally, based on the sampled curvature points, the average curvature of the target number of curvature points can be calculated using the following formula:

[0079]

[0080] Among them, κ ave It can be used to represent the mean curvature, κ a It can be used to represent the curvature of the a-th curvature point, and 'a' can be used to represent the target quantity.

[0081] Optionally, based on the sampled curvature points, the variability of the target number of curvature points can be calculated using the following formula:

[0082]

[0083] Here, s can represent volatility.

[0084] Optionally, the vehicle's driving state can be determined based on the average curvature and volatility. For example, if the value of the average curvature is κ... ave The maximum value κ of curvature less than that of a straight line str_max Furthermore, the volatility value s is less than the maximum linear volatility value s. str_max This indicates that the vehicle is traveling in a straight line. It should be noted that this is only an example and does not impose specific restrictions on the methods and processes for determining the vehicle's driving state.

[0085] As an optional embodiment, S102, determining the driving state based on the average curvature and volatility includes: in response to the average curvature being greater than a curvature threshold, or the volatility being greater than a volatility threshold, determining the driving state as a curve driving state.

[0086] In this embodiment, after obtaining the average curvature and volatility of the curvature points, the relationship between the average curvature and the curvature threshold, and the relationship between the volatility and the volatility threshold, can be determined. When the average curvature is greater than the curvature threshold, or the volatility is greater than the volatility threshold, the vehicle's driving state can be determined to be a straight-line driving state. The curvature threshold can be the maximum value of the straight-line curvature, and the volatility threshold can be the maximum value of the straight-line volatility. The curvature threshold and volatility threshold can be preset values ​​or user-defined data; this is merely an example and no specific limit is placed on the target number.

[0087] For example, when the average curvature is less than the curvature threshold and the volatility is less than the volatility threshold, the vehicle's driving state can be determined to be a straight-line driving state.

[0088] For example, when the average curvature is greater than or equal to the curvature threshold and the volatility is less than the volatility threshold, the vehicle's driving state can be determined to be a curve driving state; when the average curvature is less than the curvature threshold and the volatility is greater than or equal to the volatility threshold, the vehicle's driving state can be determined to be a curve driving state; when the average curvature is greater than or equal to the curvature threshold and the volatility is greater than or equal to the volatility threshold, the vehicle's driving state can be determined to be a curve driving state.

[0089] In this embodiment of the invention, the vehicle's driving state is determined based on the vehicle's driving data. In response to the driving state being a curve driving state, unprocessed data is collected from the driving data. This unprocessed data includes: the road curvature of the vehicle's driving path, the vehicle's yaw rate, and the vehicle's yaw tracking error. Fuzzy processing is performed on the unprocessed data based on fuzzy rules to obtain the vehicle's control data. The vehicle is then controlled to drive on the curve based on this control data. In other words, by analyzing the collected vehicle driving data, this invention can determine whether the vehicle's driving state is a curve driving state or a straight driving state. If the vehicle is in a curve driving state, fuzzy processing can be performed on the road curvature, yaw rate, and lateral tracking error of the currently driven path in the unprocessed data to determine the vehicle's control data and control the vehicle to drive on the curve. Because the unprocessed data is fuzzy processed according to fuzzy rules, it can simulate human reasoning and control when driving on a curve, enabling the vehicle to drive on a curve. In this case, it achieves the goal of driving on a curve in a manner consistent with human driving style, thereby solving the technical problem of poor curve driving performance and achieving the technical effect of improving the vehicle's curve driving performance.

[0090] Example 2

[0091] The technical solutions of the embodiments of the present invention will be illustrated below with reference to preferred embodiments.

[0092] Adaptive cruise control is an intelligent automatic control system that evolved from cruise control and can effectively reduce the driver's workload.

[0093] In related technologies, the cornering control method of adaptive cruise control mainly controls the vehicle speed by calculating information such as road curvature and vehicle speed. In this process, cameras, high-precision maps and global positioning systems are required to achieve cornering speed control. Since this method does not conform to human driving style, there is still a technical problem of poor cornering performance of the vehicle.

[0094] In one related technology, a fusion-based adaptive cruise control curve control method and device are provided. This method utilizes GPS and electronic maps to pre-acquire road and curve information ahead, calculates the safe speed for navigating curves based on the curve information, and then detects in real-time whether the vehicle is entering a curve. The vehicle speed is controlled based on steering information, steering wheel angle information, and lane detection information. This method integrates map information and lane detection information. By combining information from maps, GPS, and lane detection units within a standard adaptive cruise control system, it anticipates when the vehicle is about to enter a curve and uses the curve curvature provided by the map to control the vehicle to navigate curves at a safe and comfortable speed. This significantly protects user safety, improves the usability and comfort of the adaptive cruise control system, and effectively reduces speeding violations.

[0095] In another related technology, a vehicle cornering control compensation method, device, computer equipment, and computer-readable storage medium are provided. The method includes: determining whether the vehicle's current center of gravity sideslip angle and current yaw rate exceed the vehicle's center of gravity sideslip angle threshold or yaw rate threshold; if they exceed, calculating the optimal feedback gain using a quadratic optimal control algorithm, wherein the spatial state equation of the quadratic optimal control algorithm is established based on a two-degree-of-freedom model of the steering system; determining the state deviation based on the vehicle's current state and the vehicle's ideal state; and determining the vehicle's front wheel compensation angle based on the optimal feedback gain and the state deviation, so that when the vehicle does not meet the steady-state control threshold, the compensated front wheel angle is calculated using the quadratic optimal control algorithm to avoid understeering or imbalance of the vehicle.

[0096] However, none of the above methods take into account human control habits when driving on curves, thus the technical problem of poor curve driving performance of vehicles still exists.

[0097] To address the aforementioned problems, this invention proposes a curve speed control method under adaptive cruise control. This method may include the following steps: acquiring the vehicle's current driving state information, such as the lane trajectory equation of the road ahead, vehicle speed, vehicle acceleration, and vehicle yaw angle; calculating the curvature equation corresponding to the trajectory equation of the vehicle ahead; determining whether the current road is a curve; and if so, outputting the current vehicle speed based on a fuzzy controller. This solves the technical problem of poor curve driving performance and achieves the technical effect of improving the vehicle's curve driving performance.

[0098] The embodiments of the present invention will be further described below.

[0099] Figure 2 This is a flowchart of a curve speed control method under adaptive cruise control according to an embodiment of the present invention, such as... Figure 2 As shown, the method may include the following steps:

[0100] Step S202: Obtain the vehicle's driving status information.

[0101] In the technical solution provided in step S202 of the present invention, the driving status information of the vehicle can be obtained. This driving status information may include driving status on curves and driving status on straight roads. Driving data may include information such as the vehicle's speed, acceleration, and yaw angle; these are merely illustrative examples and do not impose specific limitations on the driving data.

[0102] Optionally, by using sensors and other data acquisition devices deployed throughout the vehicle, driving data of the vehicle can be acquired. Based on the driving data, the lane curvature equation of the lane in which the vehicle is located can be determined, points on the lane curvature equation can be extracted, and the curvature and fluctuation degree of each point can be determined. The driving status of the vehicle can be determined based on the curvature and fluctuation degree.

[0103] For example, a certain number of points can be extracted from the lane curvature equation to determine the curvature of all points, thus obtaining the average curvature. The degree of fluctuation of all points can also be determined. By comparing the average curvature and the degree of fluctuation with the maximum curvature and the maximum degree of fluctuation under straight driving conditions, the driving state of the vehicle can be judged.

[0104] For example, if the average curvature is less than the maximum curvature under straight-line driving conditions, and the fluctuation value is less than the maximum fluctuation under straight-line driving conditions, then the vehicle is driving in a straight-line state. If the average curvature is greater than or equal to the maximum curvature under straight-line driving conditions, and the fluctuation value is greater than or equal to the maximum fluctuation under straight-line driving conditions, then the vehicle is driving in a curved state. It should be noted that this is only an example and does not impose specific restrictions on the methods and processes for determining the vehicle's driving state.

[0105] Step S204: Calculate the lane curvature equation corresponding to the lane trajectory equation.

[0106] In the technical solution provided by step S204 of the present invention, the lane trajectory equation can be determined by the following formula:

[0107] y = c0 + c1x + c2x 2 +c3x 3

[0108] Where y can be used to represent the trajectory equation of the lane line, c0 can be used to represent the current position of the starting point, c1 can be used to represent the current speed of the starting point, c2 can be used to represent the curvature, c3 can be used to represent the rate of change of the curvature, and x can be used to represent the horizontal coordinate of the vehicle's position.

[0109] Optionally, Figure 3 This is a schematic diagram of a vehicle body coordinate system according to an embodiment of the present invention, such as... Figure 3 As shown, a coordinate system can be established with the vehicle body as the origin, with the center of the vehicle's front bumper as the origin, the x-axis parallel to the ground and pointing directly in front of the vehicle, the y-axis pointing to the driver's right, and the z-axis can be ignored.

[0110] Alternatively, based on the lane line trajectory equation, the lane line curvature equation can be calculated using the following formula:

[0111] y”=2c2+6c3x

[0112] Here, y” can be used to represent the lane curvature equation.

[0113] Optionally, curvature points can be sampled from the lane curvature equation. A target number of curvature points can be selected, for example, 100 curvature points k1, k2, k3…k can be extracted. 100 Each curvature point can be spaced 0.5m apart. It should be noted that this is only an example and does not impose specific restrictions on the method and process of sampling curvature points.

[0114] Optionally, based on the sampled curvature points, the average curvature of the target number of curvature points can be calculated using the following formula:

[0115]

[0116] Among them, κ ave It can be used to represent the mean curvature, κ a It can be used to represent the curvature of the a-th curvature point, and 'a' can be used to represent the target quantity.

[0117] Optionally, based on the sampled curvature points, the variability of the target number of curvature points can be calculated using the following formula:

[0118]

[0119] Here, s can represent volatility.

[0120] Step S206: Determine the current driving status of the vehicle.

[0121] In the technical solution provided in step S206 of the present invention, after obtaining the average curvature and volatility of the curvature points, the relationship between the average curvature and the curvature threshold, and the relationship between the volatility and the volatility threshold, can be determined. When it is determined that the average curvature is less than the curvature threshold and the volatility is less than the volatility threshold, the vehicle's driving state can be determined to be a straight-line driving state. The curvature threshold can be the maximum value of the straight-line curvature, and the volatility threshold can be the maximum value of the straight-line volatility. The curvature threshold and volatility threshold can be preset values ​​or user-defined data; this is merely an example and no specific limit is placed on the target number.

[0122] Optionally, except for the cases mentioned above where the average curvature is less than the curvature threshold and the fluctuation is less than the fluctuation threshold, the vehicle's driving state can be determined as a curve driving state.

[0123] For example, when the average curvature is greater than or equal to the curvature threshold and the volatility is less than the volatility threshold, the vehicle's driving state can be determined to be a curve driving state; when the average curvature is less than the curvature threshold and the volatility is greater than or equal to the volatility threshold, the vehicle's driving state can be determined to be a curve driving state; when the average curvature is greater than or equal to the curvature threshold and the volatility is greater than or equal to the volatility threshold, the vehicle's driving state can be determined to be a curve driving state.

[0124] Optionally, the vehicle's driving state can be determined based on the average curvature and volatility. For example, if the value of the average curvature is κ... ave The maximum value κ of curvature less than that of a straight line str_max Furthermore, the volatility value s is less than the maximum linear volatility value s. str_max This indicates that the vehicle is traveling in a straight line. It should be noted that this is only an example and does not impose specific restrictions on the methods and processes for determining the vehicle's driving state.

[0125] Step S208: Output the vehicle's cornering speed based on the fuzzy controller.

[0126] In the technical solution provided by step S208 of the present invention, after fuzzy processing of the data to be processed based on fuzzy rules to obtain the vehicle control data, the vehicle can be controlled to drive on a curve based on the control data, wherein the control data may include the speed of the vehicle driving on a curve.

[0127] Optionally, Figure 4 This is a schematic diagram of a road curvature membership function according to an embodiment of the present invention, such as... Figure 4 As shown, the universe of discourse for road curvature can be [0, 0.05], and the fuzzy data for road curvature can be {S, M, B}, representing large, medium, and small, respectively. Road curvature can be used as the independent variable, and the membership degree of the fuzzy data can be used as the dependent variable. The trigonometric function in the membership function is used to determine the membership degree of each point in the universe of discourse for road curvature to S, M, and B in the fuzzy language set. Based on the membership degree, all points in the universe of discourse for road curvature can be converted into the corresponding fuzzy data. For example, if the road curvature is 0.05, the membership degree of S is 0, the membership degree of M is 0, and the membership degree of B is 1, so the road curvature can be converted into the fuzzy data B; if the road curvature is 0, the membership degree of S is 1, the membership degree of M is 0, and the membership degree of B is 0, so the road curvature can be converted into the fuzzy data S.

[0128] Optionally, Figure 5 This is a schematic diagram of a membership function for lateral tracking error according to an embodiment of the present invention, as shown below. Figure 5 As shown, the universe of discourse for the lateral tracking error can be [0, 0.8], and the fuzzy data for the lateral tracking error can be {S, M, B}, representing large, medium, and small, respectively. The lateral tracking error can be used as the independent variable, and the membership degree of the fuzzy data can be used as the dependent variable. The bell function in the membership function is used to determine the membership degree of each point in the universe of discourse of the lateral tracking error to S, M, and B in the fuzzy language set. Based on the membership degree, all points in the universe of discourse of the lateral tracking error can be converted into the corresponding fuzzy data. For example, if the lateral tracking error is 0.6, the membership degree of S is 0, the membership degree of M is 0, and the membership degree of B is 1. This lateral tracking error can be converted into fuzzy data B.

[0129] Optionally, Figure 6 This is a schematic diagram of a membership function for a vehicle yaw rate according to an embodiment of the present invention, as shown below. Figure 6 As shown, the universe of discourse for the yaw rate can be [-5, 5], and the fuzzy data for the yaw rate can be {S, B}, representing large and small respectively. The yaw rate can be used as the independent variable, and the membership degree of the fuzzy data can be used as the dependent variable. The trigonometric function in the membership function is used to determine the membership degree of each point in the universe of discourse of the yaw rate to S and B in the fuzzy language set. Based on the membership degree, all points in the universe of discourse of the yaw rate can be converted into the corresponding fuzzy data. For example, if the yaw rate is 5, the membership degree of S is 1, and the membership degree of B is 0. The yaw rate can be converted into fuzzy data S.

[0130] Optionally, Figure 7This is a schematic diagram of a membership function for a planned velocity according to an embodiment of the present invention, as shown below. Figure 7 As shown, the universe of discourse for the planned velocity is set to [30, 70], and the fuzzy data can be set to {VS, S, M, B, VB}, representing very small, small, medium, large and very large, respectively. The membership function of the planned velocity can be a trigonometric function.

[0131] For example, by collecting vehicle driving status data, it can be determined whether the vehicle is driving in a curve or a straight line. If the vehicle is driving in a straight line, the next steps are unnecessary. If the vehicle is driving in a curve, the road curvature, yaw rate, and yaw tracking error can be extracted from the driving data. These three parameters can be processed separately using membership functions to obtain their respective fuzzy data. By performing fuzzy processing on the fuzzy data according to fuzzy rules, the speed required for the vehicle to drive in a curve can be obtained, thereby controlling the vehicle to drive in a curve.

[0132] This invention analyzes the collected vehicle driving data to determine whether the vehicle is driving in a curve or a straight line. If the vehicle is driving in a curve, the road curvature, yaw rate, and lateral tracking error of the current road in the data to be processed can be fuzzy-processed to determine the vehicle's control data and control the vehicle to drive in a curve. Because the data to be processed is fuzzy-processed according to fuzzy rules, it can simulate human reasoning and control when driving in a curve, enabling the vehicle to drive in a curve. In this case, it achieves the goal of driving in a curve in a way that conforms to human driving style, thereby solving the technical problem of poor vehicle curve driving performance and achieving the technical effect of improving vehicle curve driving performance.

[0133] Example 3

[0134] According to an embodiment of the present invention, a vehicle control device is also provided. It should be noted that this vehicle control device can be used to execute the vehicle control method of Embodiment 1.

[0135] Figure 8 This is a schematic diagram of a vehicle control device according to an embodiment of the present invention. Figure 8 As shown, the vehicle control device 800 may include: a determination unit 802, a data acquisition unit 804, a processing unit 806, and a control unit 808.

[0136] The determining unit 802 is used to determine the driving status of the vehicle based on the vehicle's driving data.

[0137] The acquisition unit 804 is used to acquire data to be processed from the driving data in response to the driving state being a curve driving state. The data to be processed includes: the road curvature of the driving road, the yaw rate of the vehicle, and the yaw tracking error of the vehicle.

[0138] The processing unit 806 is used to perform fuzzy processing on the data to be processed based on fuzzy rules to obtain the control data of the vehicle. The third determination module 208 is used to determine the target score based on multiple matching results, wherein the target score is used to characterize the accuracy of the detection result.

[0139] Control unit 808 is used to control the vehicle to drive on curves based on control data.

[0140] Optionally, the processing unit 806 may include: a first fuzzy processing module, used to perform fuzzy processing on the data to be processed through a membership function to obtain fuzzified data; and a second fuzzy processing module, used to perform fuzzy processing on the fuzzified data based on a preset correspondence between the fuzzified data and the control data to obtain the control data.

[0141] Optionally, the processing unit 806 may include: a third fuzzing processing module for performing fuzzing processing on the fuzzy data to obtain a processing result; and a decoding processing module for performing decoding processing on the processing result to obtain control data.

[0142] Optionally, the first fuzzy processing module may include: a first conversion submodule, used to convert the road curvature and yaw rate through trigonometric functions in response to the membership function being a trigonometric function, to obtain fuzzy data;

[0143] Optionally, the first fuzzy processing module may include: a second transformation submodule, used to transform the lateral tracking error through the bell-shaped function in response to the membership function being a bell-shaped function, to obtain fuzzy data.

[0144] Optionally, the determining unit 802 may include: a first determining module, used to determine the lane curvature equation of the vehicle based on driving data; a sampling module, used to sample the curvature points of the lane curvature equation to obtain at least one curvature point; a second determining module, used to determine the average curvature of a target number of curvature points and the fluctuation between the target number of curvature points; and a third determining module, used to determine the driving state based on the average curvature and the fluctuation.

[0145] Optionally, the third determining module may include: a determining submodule, used to determine the driving state as a curve driving state in response to the average curvature being greater than a curvature threshold or the volatility being greater than a volatility threshold.

[0146] In this embodiment of the invention, a determining unit determines the vehicle's driving state based on the vehicle's driving data; a collecting unit, in response to the driving state being a curve driving state, collects data to be processed from the driving data, wherein the data to be processed includes: the road curvature of the vehicle's driving path, the vehicle's yaw rate, and the vehicle's yaw tracking error; a processing unit performs fuzzy processing on the data to be processed based on fuzzy rules to obtain the vehicle's control data; and a control unit controls the vehicle to perform curve driving based on the control data, thereby solving the technical problem of poor curve driving performance of the vehicle and achieving the technical effect of improving the vehicle's curve driving performance.

[0147] Example 4

[0148] According to an embodiment of the present invention, a computer-readable storage medium is also provided, the storage medium including a stored program, wherein the program executes the vehicle control method described in Embodiment 1.

[0149] Example 5

[0150] According to an embodiment of the present invention, a processor is also provided for running a program, wherein the program executes the vehicle control method described in Embodiment 1 when it runs.

[0151] Example 6

[0152] According to an embodiment of the present invention, a vehicle is also provided for performing the vehicle control method of the present invention.

[0153] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0154] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0155] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0156] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0157] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0158] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0159] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for controlling a vehicle, characterized in that, include: The vehicle's driving data is acquired by sensors deployed on the vehicle, wherein the driving data includes at least the vehicle's speed, acceleration, and yaw angle. Based on the driving data, the driving state of the vehicle is determined, wherein the driving state includes: driving on a curve and driving in a straight line; In response to the driving state being a curve driving state, unprocessed data is collected from the driving data, wherein the unprocessed data includes: the road curvature of the driving road of the vehicle, the yaw rate of the vehicle, and the lateral tracking error of the vehicle. The data to be processed is fuzzy processed based on fuzzy rules to obtain the control data of the vehicle, wherein the control data includes at least the speed of the vehicle when it is driving on a curve. Based on the control data, the vehicle is controlled to navigate a curve. The method of determining the driving state of the vehicle includes: determining the lane curvature equation of the vehicle based on the driving data; sampling the curvature points of the lane curvature equation to obtain at least one curvature point; determining the average curvature of a target number of the curvature points and the fluctuation between the target number of the curvature points, wherein the fluctuation is used to characterize the degree of fluctuation of the curvature points; and determining the driving state as a curve driving state in response to the average curvature being greater than a curvature threshold or the fluctuation being greater than a fluctuation threshold.

2. The method according to claim 1, characterized in that, The control data is obtained by performing fuzzy processing on the data to be processed based on the fuzzy rules, including: The data to be processed is fuzzy by using a membership function to obtain fuzzy data; Based on a preset correspondence between the fuzzy data and the control data, the fuzzy data is fuzzified to obtain the control data.

3. The method according to claim 2, characterized in that, The control data is obtained by performing fuzzification processing on the fuzzified data, including: The blurred data is then subjected to blurring processing to obtain the processing result; The processing result is decoded to obtain the control data.

4. The method according to claim 2, characterized in that, The data to be processed is fuzzy through the membership function to obtain the fuzzified data, including: Since the membership function is a trigonometric function, the road curvature and the yaw rate are converted using the trigonometric function to obtain the fuzzy data.

5. The method according to claim 2, characterized in that, The data to be processed is fuzzy through the membership function to obtain the fuzzified data, including: In response to the membership function being a bell-shaped function, the lateral tracking error is transformed using the bell-shaped function to obtain the fuzzy data.

6. A vehicle control device, characterized in that, The device includes: A determining unit is configured to acquire driving data of the vehicle using sensors deployed on the vehicle, wherein the driving data includes at least: the vehicle's speed, acceleration, and yaw angle; and based on the driving data, determine the driving state of the vehicle, wherein the driving state includes: a curve driving state and a straight driving state. The acquisition unit is used to acquire data to be processed from the driving data in response to the vehicle's driving state being a curve driving state. The data to be processed includes: the road curvature of the driving road of the vehicle, the yaw rate of the vehicle, and the lateral tracking error of the vehicle. The processing unit is used to perform fuzzy processing on the data to be processed based on preset fuzzy rules to obtain the control data of the vehicle, wherein the control data includes at least the speed of the vehicle when it is driving on a curve. A control unit, used to control the vehicle to perform curve driving based on the control data; The determining unit is further configured to determine the lane curvature equation of the vehicle based on the driving data; sample the curvature points of the lane curvature equation to obtain at least one curvature point; determine the average curvature of a target number of the curvature points and the fluctuation between a target number of the curvature points, wherein the fluctuation is used to characterize the degree of fluctuation of the curvature points; and determine the driving state as a curve driving state in response to the average curvature being greater than a curvature threshold or the fluctuation being greater than a fluctuation threshold.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 5.

8. A vehicle, characterized in that, Used to perform the method according to any one of claims 1 to 5.

Images