A driving intention determination method, device, equipment and readable storage medium

Abstract

The application discloses a driving intention determination method, device and equipment and a readable storage medium, and applies to the technical field of intelligent driving, and comprises the following steps: determining a turning membership degree corresponding to each turning intention information and a lane-changing membership degree corresponding to each lane-changing intention information based on a fuzzy membership method; combining fuzzy relations by using a defuzzification function based on all the turning membership degrees to determine a left-turning probability and a right-turning probability; the defuzzification function is a function for determining an intention probability based on a membership degree and a weight coefficient; combining fuzzy relations by using the defuzzification function based on all the lane-changing membership degrees to determine a left-lane-changing probability and a right-lane-changing probability; and determining a target driving intention based on the left-turning probability, the right-turning probability, the left-lane-changing probability and the right-lane-changing probability. The application determines the membership degrees corresponding to multiple types of intention information, combines all the membership degrees based on the defuzzification function, determines the target driving intention, and improves the accuracy of driving intention determination.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving, and particularly relates to a driving intention determination method and device, equipment and a readable storage medium. BACKGROUND

[0002] The current behavior of evaluating driving intention mainly qualitatively determines the driving intention of the driver from several indicators or a single indicator. This method of measuring the behavior of the driver has great uncertainty. Because in the actual driving process, there is great difference and non-standard driving behavior of each driver, such as not turning on the turn signal to change lanes and turn, turning on the left turn signal but changing lanes to the right, turning on the turn signal but not turning, and other behaviors, so that the driving intention cannot be accurately identified.

[0003] It can be seen that how to improve the accuracy of driving intention determination is a technical problem that needs to be solved by those skilled in the art. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a driving intention determination method, device, equipment and readable storage medium, which solves the technical problem of inaccurate driving intention determination in the prior art.

[0005] To solve the above technical problems, the present application provides a driving intention determination method, comprising:

[0006] determining the turning membership degree corresponding to each turning intention information and the lane-changing membership degree corresponding to each lane-changing intention information based on a fuzzy membership degree method; wherein the vehicle motion state information and the active intention information are included in the turning intention information and the lane-changing intention information; the fuzzy membership degree method is a method for determining the membership degree corresponding to each intention information based on the first membership degree information and the second membership degree information corresponding to each intention information set;

[0007] combining the fuzzy relationships based on all the turning membership degrees by using a defuzzification function to determine the left-turning probability and the right-turning probability; wherein the defuzzification function is a function for determining the intention probability based on the membership degree and the weight coefficient;

[0008] combining the fuzzy relationships based on all the lane-changing membership degrees by using the defuzzification function to determine the left-lane-changing probability and the right-lane-changing probability;

[0009] determining the target driving intention based on the left-turning probability, the right-turning probability, the left-lane-changing probability and the right-lane-changing probability.

[0010] Optionally, the method for determining the turning membership degree corresponding to each turning intention information and the lane-changing membership degree corresponding to each lane-changing intention information based on the fuzzy membership degree method comprises:

[0011] If the greater the value of the current intention information is, the closer the membership is to zero, then determine the membership corresponding to the current intention information based on a fuzzy small membership method; wherein, the input of the fuzzy small membership method is the value x of the current intention information, a first membership parameter M1 and a second membership parameter M2; when the input x is greater than M2, the membership is 0; when the input x is less than M1, the membership is 1, and when the input is between M1 and M2, the membership is (M2-x) / (M2-M1), M1<M2;

[0012] If the greater the value of the current intention information is, the closer the membership is to one, then determine the membership corresponding to the current intention information based on a fuzzy large membership method; wherein, the input of the fuzzy large membership method is the value y of the current intention information, a third membership parameter M3 and a fourth membership parameter M4; when the input y is less than M3, the membership is 0; when y is greater than M4, the membership is 1; when y is between M3 and M4, the membership is (y-M3) / (M4-M3), M3<M4;

[0013] If the current turning intention information is a turn signal switch, then determine that the membership corresponding to the turn signal being on is 1, and the membership corresponding to the turn signal being off is 0;

[0014] If the current turning intention information is a brake pedal of the ego vehicle, then determine that the membership corresponding to the pedal being braked is 1, and the membership corresponding to the pedal not being braked is 0.

[0015] Optionally, the fuzzy membership method determines the turning membership corresponding to each turning intention information, and determines the lane-changing membership corresponding to each lane-changing intention information, comprising:

[0016] If the current turning intention information is any one of a steering wheel angle, a yaw rate of the ego vehicle, a trajectory curvature of the ego vehicle, a longitudinal acceleration of the ego vehicle, a throttle pedal opening of the ego vehicle, and a turn signal on duration of the ego vehicle, then determine the membership corresponding to the current turning intention information based on the fuzzy large membership method;

[0017] If the current turning intention information is a vehicle speed signal of the ego vehicle, then in calculating the membership of the vehicle speed signal, distinguish a lowest level speed, a middle level speed, and a highest level speed, and determine the membership corresponding to the current turning intention information based on the fuzzy small membership method; wherein, the highest level speed is greater than the middle level speed, and the middle level speed is greater than the lowest level speed.

[0018] Optionally, the fuzzy membership method determines the turning membership corresponding to each turning intention information, and determines the lane-changing membership corresponding to each lane-changing intention information, comprising:

[0019] If the current lane-changing intention information is any one of the steering wheel angle, the steering light switch signal, the angle of human eye rotation, the rate of change of the distance from the ego vehicle to the lane boundary, the curvature of the ego vehicle trajectory, and the steering light on duration, the membership degree corresponding to the current lane-changing intention information is determined based on the fuzzy large membership degree method;

[0020] If the current lane-changing intention information is the standard deviation of the rate of change of the distance from the ego vehicle to the lane boundary, the membership degree corresponding to the current lane-changing intention information is determined based on the fuzzy small membership degree method.

[0021] Optionally, the left-turning probability and the right-turning probability are determined by using a defuzzification function to combine the fuzzy relationships based on all the turning membership degrees, including:

[0022] The left-turning probability and the right-turning probability are determined by using a fuzzy and defuzzification function or a fuzzy or defuzzification function to combine the fuzzy relationships based on all the turning membership degrees;

[0023] The input of the fuzzy and defuzzification function is the first membership degree L1, the second membership degree L2, and the weight coefficient K1, when L1 is less than or equal to L2, the probability value is K1*L1+(1-K1)*((L1+L2) / 2); when L1 is greater than L2, the probability value is K1*L2+(1-K1)*((L1+L2) / 2);

[0024] The input of the fuzzy or defuzzification function is the first membership degree L1, the second membership degree L2, and the weight coefficient K1, when L1 is less than or equal to L2, the probability value is K1*L2+(1-K1)*((L1+L2) / 2); when L1 is greater than L2, the probability value is K1*L1+(1-K1)*((L1+L2) / 2).

[0025] Optionally, the left-turning probability and the right-turning probability are determined by using a defuzzification function to combine the fuzzy relationships based on all the turning membership degrees, including:

[0026] The fuzzy and defuzzification function is used to combine the turning membership degrees corresponding to the first type of turning intention information to obtain the initial left-turning probability and the initial right-turning probability;

[0027] The fuzzy or defuzzification function, the initial left-turning probability, and the initial right-turning probability are used to combine the turning membership degrees corresponding to the second type of turning intention information to obtain the final left-turning probability and the right-turning probability; wherein the second type of turning intention information includes the longitudinal acceleration of the ego vehicle and the brake pedal of the ego vehicle, and the first type of turning intention is the turning intention information other than the second type of turning intention information.

[0028] Optionally, the left lane-changing probability and the right lane-changing probability are determined by combining the fuzzy relations based on all the lane-changing membership degrees using the defuzzification function, comprising:

[0029] determining whether there is a change in the lane sequence value;

[0030] when there is a change in the lane sequence value, determining that if the self lane sequence value switches from the middle lane sequence value to the left lane sequence value, the left lane-changing probability is 1; if the self lane sequence value switches from the middle lane sequence value to the right lane sequence value, the right lane-changing probability is 1;

[0031] when there is no change in the lane sequence value, determining to perform the step of combining the fuzzy relations based on all the lane-changing membership degrees using the defuzzification function to determine the left lane-changing probability and the right lane-changing probability.

[0032] Optionally, the target driving intention is determined based on the left-turning probability, the right-turning probability, the left lane-changing probability and the right lane-changing probability, comprising:

[0033] determining the maximum value of the probabilities in the left-turning probability, the right-turning probability, the left lane-changing probability and the right lane-changing probability;

[0034] determining whether the maximum value of the probabilities is greater than a minimum probability threshold value;

[0035] when the maximum value of the probabilities is greater than the minimum probability threshold value, determining that the intention corresponding to the maximum value of the probabilities is the target driving intention;

[0036] when the maximum value of the probabilities is not greater than the minimum probability threshold value, determining that the target driving intention is straight driving.

[0037] The application also provides a driving intention determination device, comprising:

[0038] a membership degree determination module, configured to determine the turning membership degrees corresponding to each turning intention information and the lane-changing membership degrees corresponding to each lane-changing intention information based on a fuzzy membership degree method; wherein the vehicle motion state information and the active intention information are included in the turning intention information and the lane-changing intention information; the fuzzy membership degree method is a method for determining the membership degrees corresponding to each intention information based on the set first membership degree information and the second membership degree information corresponding to each intention information;

[0039] a turning probability determination module, configured to combine the fuzzy relations based on all the turning membership degrees using a defuzzification function to determine the left-turning probability and the right-turning probability; wherein the defuzzification function is a function for determining the intention probability based on the membership degrees and the weight coefficients;

[0040] a lane changing probability determination module configured to determine a left lane changing probability and a right lane changing probability by using the defuzzification function to combine fuzzy relations based on all of the lane changing membership degrees;

[0041] a driving intention determination module configured to determine a target driving intention based on the left turning probability, the right turning probability, the left lane changing probability, and the right lane changing probability.

[0042] The application further provides a driving intention determination device, comprising:

[0043] a memory configured to store a computer program;

[0044] a processor configured to execute the computer program to implement the steps of the driving intention determination method.

[0045] The application further provides a readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of the driving intention determination method.

[0046] The application further provides a computer program product comprising computer programs / instructions, the computer programs / instructions being executed by a processor to implement the steps of the driving intention determination method.

[0047] It can be seen that the application determines the turning membership degrees corresponding to each turning intention information and the lane changing membership degrees corresponding to each lane changing intention information based on a fuzzy membership degree method, wherein the turning intention information and the lane changing intention information comprise vehicle motion state information and active intention information; the fuzzy membership degree method is a method for determining the membership degrees corresponding to each intention information based on first membership degree information and second membership degree information corresponding to each intention information; the left turning probability and the right turning probability are determined by using a defuzzification function to combine fuzzy relations based on all of the turning membership degrees; the defuzzification function is a function for determining intention probabilities based on membership degrees and weight coefficients; the left lane changing probability and the right lane changing probability are determined by using the defuzzification function to combine fuzzy relations based on all of the lane changing membership degrees; and the target driving intention is determined based on the left turning probability, the right turning probability, the left lane changing probability, and the right lane changing probability.

[0048] The beneficial effects of the present application are that, compared with the current direct measurement of driving intention based on a single type of variable, the present application determines turning intention information based on vehicle motion state information and active intention information, corresponding turning membership degrees, determines lane changing intention information based on vehicle motion state information and active intention information, corresponding lane changing membership degrees, determines left turning probability and right turning probability based on fuzzy relationship combination of multiple turning membership degrees, determines left lane changing probability and right lane changing probability based on fuzzy relationship combination of multiple lane changing membership degrees, and finally determines the target driving intention based on left turning probability, right turning probability, left lane changing probability and right lane changing probability. Since the present application uses multiple types of turning intention information and lane changing intention information in the process of determining the target driving intention, the subsequent fuzzy membership degree method designed based on various types of intention information in the present application can perform more accurate membership degree calculation, and the de-fuzzification function can perform more accurate fuzzy relationship combination, thereby improving the accuracy of target driving intention determination.

[0049] In addition, the present application also provides a driving intention determination device, equipment and readable storage medium, which also have the beneficial effects described above. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the provided drawings.

[0051] Figure 1 A flowchart of a driving intention determination method provided for an embodiment of the present application;

[0052] Figure 2 A logic diagram of a fuzzy small membership degree method provided for an embodiment of the present application;

[0053] Figure 3 A logic diagram of a fuzzy large membership degree method provided for an embodiment of the present application;

[0054] Figure 4 A schematic diagram of a self-vehicle turning light opening duration membership degree determination logic provided for an embodiment of the present application;

[0055] Figure 5 A self-vehicle trajectory trend in a lane changing process provided for an embodiment of the present application;

[0056] Figure 6 A schematic diagram of a lane sequence value provided for an embodiment of the present application;

[0057] Figure 7 A schematic diagram of a fuzzy and de-fuzzy function provided for an embodiment of the present application;

[0058] Figure 8 A schematic diagram of a fuzzy or de-fuzzy function provided for an embodiment of the present application;

[0059] Figure 9 A flowchart of a driving intention determination method provided for an embodiment of the present application;

[0060] Figure 10 A structural schematic diagram of a driving intention determination apparatus provided for an embodiment of the present application;

[0061] Figure 11 A structural schematic diagram of a driving intention determination device provided for an embodiment of the present application. DETAILED DESCRIPTION

[0062] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0063] Reference should be made to Figure 1 , Figure 1 A flowchart of a driving intention determination method provided for an embodiment of the present application. The method can include:

[0064] S101, determining a turning membership degree corresponding to each turning intention information and determining a lane-changing membership degree corresponding to each lane-changing intention information based on a fuzzy membership degree method; wherein the turning intention information and the lane-changing intention information include vehicle motion state information and active intention information; the fuzzy membership degree method is a method for determining a membership degree corresponding to each intention information based on a set first membership degree parameter and a second membership degree parameter corresponding to each intention information.

[0065] The electronic device in the embodiment is not limited to a specific electronic device, and can be a computer, a tablet computer, or the like. The turning intention information in the embodiment includes vehicle motion state information related to turning and active turning intention information corresponding to active driver operation information. The lane-changing intention information in the embodiment includes vehicle motion state information related to lane changing and active lane-changing intention information corresponding to active driver operation. The turning intention information in the embodiment is not limited to a specific type. For example, the vehicle motion state information in the turning intention information in the embodiment can be at least one of a vehicle speed signal, a vehicle yaw rate, a vehicle trajectory curvature, a vehicle longitudinal acceleration, and a steering lamp on duration. The active intention information in the turning intention information in the embodiment can be at least one of a steering wheel angle, a vehicle brake pedal, a vehicle accelerator pedal, and a steering lamp switch. The steering wheel angle refers to the angle at which the driver turns the steering wheel. The non-front wheel angle is the front wheel angle divided by the transmission ratio of the steering mechanism. The vehicle brake pedal refers to whether the driver steps on the brake pedal. The vehicle accelerator pedal refers to the accelerator pedal opening degree. When the accelerator pedal is fully open, the accelerator pedal opening degree is 100%. When the accelerator pedal is half open, the accelerator pedal opening degree is 50%. The steering lamp switch refers to the left turn signal and the right turn signal. The vehicle speed signal refers to the vehicle speed information of the vehicle itself. The vehicle yaw rate refers to the rotational speed of the vehicle around its vertical axis (i.e., the vertical line passing through the vehicle center of gravity) when the vehicle is turning. This speed describes the speed of the overall rotation of the vehicle and is an important indicator for measuring the stability of the vehicle. The vehicle trajectory curvature refers to the rate of rotation of the tangent direction angle to the arc length at a certain point on the vehicle trajectory. The longitudinal acceleration refers to the forward driving acceleration.

[0066] The lane-changing intention information in the embodiment includes vehicle motion state information related to lane changing and active lane-changing intention information. The vehicle motion state information related to lane changing in the embodiment can be at least one of a change rate of a distance from the vehicle to a lane boundary, a standard deviation of the change rate of the distance from the vehicle to the lane boundary, a vehicle trajectory curvature, and a steering lamp on duration. The active lane-changing intention information in the embodiment includes at least one of a steering wheel angle, a steering lamp switch signal, and an angle of eye rotation. The steering lamp switch information is a left turn signal or a right turn signal. The angle of eye rotation is a left turn angle or a right turn angle. The change rate of the distance from the vehicle to the lane boundary includes a change rate of a distance from the vehicle to a left lane boundary and a change rate of a distance from the vehicle to a right lane boundary. The standard deviation of the distance from the vehicle to the lane boundary includes a standard deviation of the distance from the vehicle to the left lane boundary and a standard deviation of the distance from the vehicle to the right lane boundary. The lane sequence value is, for example, 0 for a left lane, 1 for a middle lane, and 2 for a right lane. The steering lamp on duration includes a left turn lamp on duration and a right turn lamp on duration.

[0067] The fuzzy membership degree method in this embodiment is a method for determining the membership degree corresponding to each intention information based on the set first membership degree parameter and second membership degree parameter corresponding to each intention information. The first membership degree parameter in this embodiment is the minimum value corresponding to the current intention information, and the second membership degree parameter is the maximum value corresponding to the current intention information. The fuzzy membership degree method in this embodiment is a method for comparing the current intention information with the first membership degree parameter and the second membership degree parameter, and determining the specific membership degree calculation method according to the comparison result. The comparison result includes that the current intention information is less than the first membership degree parameter, the first membership degree parameter is greater than the second membership degree parameter, and the current intention information is between the first membership degree parameter and the second membership degree parameter.

[0068] It needs to be further explained that, in order to improve the accuracy of determining the membership degree based on the fuzzy membership degree method, the above-mentioned fuzzy membership degree method for determining the turning membership degree corresponding to each turning intention information and determining the lane-changing membership degree corresponding to each lane-changing intention information can include:

[0069] S1012, if the current intention information is the value of the intention information, the greater the value, the closer the membership degree is to zero, then the fuzzy small membership degree method is determined to determine the membership degree corresponding to the current intention information; wherein the input of the fuzzy small membership degree method is the value x of the current intention information, the first membership degree parameter M1 and the second membership degree parameter M2; when the input x is greater than M2, the membership degree is 0; when the input x is less than M1, the membership degree is 1, when the input is between M1 and M2, the membership degree is (M2-x) / (M2-M1), M1

[0070] The first membership degree information in this embodiment is the first membership degree parameter, and the second membership degree information is the second membership degree parameter. Please refer to Figure 2 , Figure 2 The logic diagram of the fuzzy small membership degree method provided in the embodiment of the application.

[0071] S1013, if the current intention information is the value of the intention information, the greater the value, the closer the membership degree is to one, then the fuzzy large membership degree method is determined to determine the membership degree corresponding to the current intention information; wherein the input of the fuzzy large membership degree method is the value y of the current intention information, the third membership degree parameter M3 and the fourth membership degree parameter M4, when the input y is less than M3, the membership degree is 0; when y is greater than M4, the membership degree is 1; when y is between M3 and M4, the membership degree is (y-M3) / (M4-M3), M3

[0072] The first membership degree information in this embodiment is the third membership degree parameter, and the second membership degree information in this embodiment is the fourth membership degree parameter. For the convenience of understanding, please refer to Figure 3 , Figure 3A logic diagram of a fuzzy large membership degree method provided for an embodiment of the present application.

[0073] S1014, if the current turning intention information is a turn signal switch, it is determined that the membership degree corresponding to the turn signal being on is 1, and the membership degree corresponding to the turn signal being off is 0.

[0074] S1015, if the current turning intention information is a brake pedal of the ego vehicle, it is determined that the membership degree corresponding to the pedal braking is 1, and the membership degree corresponding to the pedal not braking is 0.

[0075] The embodiment gives a specific method for determining the membership degrees corresponding to various intention information, which improves the accuracy of membership degree determination.

[0076] It should be further explained that the above-mentioned determination of the turning membership degree corresponding to each turning intention information based on the fuzzy membership degree method, and the determination of the lane-changing membership degree corresponding to each lane-changing intention information, can include: if the current turning intention information is any one of a steering wheel angle, a yaw rate of the ego vehicle, a trajectory curvature of the ego vehicle, a longitudinal acceleration of the ego vehicle, a throttle pedal opening degree of the ego vehicle, and a turn signal on duration of the ego vehicle, the membership degree corresponding to the current turning intention information is determined based on the fuzzy large membership degree method; if the current turning intention information is a vehicle speed signal of the ego vehicle, when calculating the membership degree of the vehicle speed signal, the lowest speed, the medium speed, and the highest speed are distinguished, and the membership degree corresponding to the current turning intention information is determined based on the fuzzy small membership degree method; wherein the highest speed is greater than the medium speed, and the medium speed is greater than the lowest speed.

[0077] For the convenience of understanding, the embodiment gives a method for determining the membership degrees corresponding to various turning intention information. When the turning intention information is a steering wheel angle, the membership degrees of the steering wheel angle to the turning intention when turning left and right are respectively:

[0078] A(x_alpWheeLAnglekorrLeft=FuzzyLarge(m alpWheelAnelekorr , PagwheeLAngleLeft1, PagwheeLAngleLeft2) and

[0079] A(x_alpWheeLAnglekorrRight=FuzzyLarge(m alpWheelAnglekorrwherein PagwheelAngleLeftl and PagwheelAngleLeft2 represent the first and second steering wheel angle threshold values for left turning (reference threshold values are 0.0125 rad and 0.0325 rad, respectively); and PagwheelAngleRightl and PagwheelAngleRight2 represent the first and second steering wheel angle threshold values for right turning (reference threshold values are 0.0125 rad and 0.0325 rad, respectively). For example, if the current steering wheel angle is 0.01 rad, the membership degree is 0; if the steering wheel angle is 0.04 rad, the membership degree is 1; if the steering wheel angle is 0.015 rad, the calculated membership degree is: (0.015-0.0125) / (0.0325-0.0125) = 0.125.

[0080] When the turning intention information is the turn signal switch, the method for determining the membership degree of left turning is The method for determining the membership degree of right turning is The turn signal switch is a special fuzzy element in this embodiment. When the turn signal is on, the membership degree of the turn signal switch is 1; when the turn signal is off, the membership degree of the turn signal switch is 0.

[0081] When the turning intention information is the vehicle speed, the vehicle speed range is wide, so three speed segments are distinguished when calculating the membership degree of the vehicle speed: low speed (corresponding to the lowest level speed in the foregoing), medium speed, and high speed (corresponding to the highest level speed in the foregoing). For the medium speed segment, the membership degree is calculated as follows:

[0082] A(egpVelocityMedium) = FuzzySmall(megoVelocity, PAGeoVelocityMediuml, PAGeoVelocityMedium2); wherein PAGeoVelocityMediuml, PAGeoVelocityMedium2 represent the first and second speed threshold values for medium speed (reference threshold values are 15 m / s and 16.7 m / s), according to the definition of the fuzzy small membership function, if the current vehicle speed is 14 m / s, the calculated membership is 1; if the current vehicle speed is 18 m / s, the calculated membership is 0; if the current vehicle speed is 15.8 m / s, the calculated membership is: (16.7-15.8) / (16.7-15) = 0.53. For high speed, considering the turning radius and driving safety, it is considered that the steering intention is not obvious or there is no steering intention at all, so its membership can be considered as zero or no steering intention. A(egpVelocityHigh) = FuzzySmall(megoVelocity, PAGeoVelocityHighl, PAGeoVelocityHigh2); wherein PAGeoVelocityHighl, PAGeoVelocityHigh2 represent the first and second speed threshold values for high speed (reference threshold values are 8.3 m / s and 11.1 m / s). For low speed, its membership is calculated as follows: A(egpVelocityLow) = FuzzySmall(megoVelocity, PAGeoVelocityLowl, PAGeoVelocityLow2); wherein PAGeoVelocityLowl, PAGeoVelocityLow2 represent the first and second speed threshold values for low speed (reference threshold values are 3.5 m / s and 5.0 m / s).

[0083] When the steering intention information is the lateral acceleration of the ego vehicle, the method for determining the membership is as follows: A(yawrateLeft) = FuzzyLarge(megoYawrate, PAGyawrateLeftl, PAGyawrateLeft2), A(yawrateRight) = FuzzyLarge(megoYawrate, PAGyawrateRighl, PAGyawrateRight2); wherein PAGyawrateLeftl, PAGyawrateLeft2 represent the first and second yaw rate threshold values for left turn (reference threshold values are 0.5 rad / s and 0.7 rad / s), PAGyawrateRighl, PAGyawrateRight2 represent the first and second yaw rate threshold values for right turn (reference threshold values are 0.5 rad / s and 0.7 rad / s). yawrate yawrate ​, PAGyawrateRightl, PAGyawrateRigh2); wherein PAGyawrateLeftl, PAGyawrateLeft2 represent the first and second yaw rate threshold values for left steering respectively; PAGyawrateRightl, PAGyawrateRigh2 represent the first and second yaw rate threshold values for right steering respectively (reference threshold values are 0.1 rad / s and 0.25 rad / s). For example, when the yaw rate is 0.15 rad / s, the method for calculating the membership degree is: (0.15-0.1) / (0.25-0.1) = 0.33.

[0084] When the turning intention information is the trajectory curvature of the ego vehicle, the method for determining the membership degree is:

[0085] A(kapTrajectoryLeft) = FuzzyLarge(m kapTrajectory , PAGKapTrajectoryLeftl, PAGKapTrajectoryLeft2);

[0086] A(kapTrajectoryRight) = FuzzyLarge(m kapTrrajectory , PAGKapTrajectoryRightl, PAGKapTrajectoryRight2). Wherein: PAGKapTrajectoryLeftl, PAGKapTrajectoryLeft2 represent the first and second threshold values for the trajectory curvature of the ego vehicle when steering left; PAGKapTrajectoryRightl, PAGKapTrajectoryRight2 represent the first and second threshold values for the trajectory of the ego vehicle when steering right (reference threshold values are 0.02 / m and 0.06 / m). For example: when the trajectory curvature of the ego vehicle is 0.01, the membership degree is 0; when it is 0.08, the membership degree is 1; when it is 0.04, the membership degree is (0.04-0.02) / (0.06-0.02) = 0.5.

[0087] When the turning intention information is the longitudinal acceleration of the ego vehicle, the method for determining the membership degree is: A(egoAccelerate) = FuzzyLarge(m Accelerate, PAGegoAccelerate1, PAGegoAccelerate2); wherein, AGegoAcceleratel, AGegoAccelerate2 represent the first longitudinal acceleration threshold and the second longitudinal acceleration threshold (reference threshold is -0.98 m / s2 and 0.98 m / s2) respectively. According to the definition of fuzzy large function, when the longitudinal acceleration of ego vehicle is -1.2 m / s 2 , the membership degree is 0; when the longitudinal acceleration of ego vehicle is 1.2 m / s 2 , the membership degree is 1; when the longitudinal acceleration of ego vehicle is 0.5 m / s 2 , the membership degree is calculated as: (0.98-0.5) / (0.98-(-0.98))=0.24.

[0088] When the turning intention information is the brake pedal of ego vehicle, the method for determining the membership degree is: wherein, when the driver steps on the brake pedal, the membership degree of the brake pedal is 1, and when the driver does not step on the brake pedal, the membership degree of the brake pedal is 0.

[0089] When the turning intention information is the accelerator pedal opening of ego vehicle, A(egoGasPedalPostion) = FuzzyLarge(m GasPedalPostion , PAGegoGasPedalPostion1, egoGasPedalPostion2); wherein, m GasPedalPostion represents the accelerator pedal opening of ego vehicle, PAGegoGasPedalPostion1, PAGegoGasPedalPostion2 represent the first accelerator pedal position threshold and the second accelerator pedal position threshold (reference threshold is 0.075 and 0.125) respectively. The accelerator pedal refers to the accelerator pedal opening, when the accelerator pedal is fully opened, the accelerator pedal opening value is 100%, when the accelerator pedal opening is half, it is 50%, and there is no unit.

[0090] When the turning intention information is the duration of the vehicle's turn signal, the membership degree is determined as follows: The turn signal duration signal is calculated based on the turn signal's on state. The calculation function, FuzzyCounter, is as follows: It acquires parameters x, B1, B2, K1, and K2, where x represents the turn signal's on state, B1 represents the previous turn signal's on state, B2 is a flag, K1 represents the turn signal's on time, and K2 represents a time threshold. The calculation logic of this function is as follows: If the turn signal was off in the previous moment and is on in the current moment, or the turn signal's on time is greater than zero, and the flag is false, the calculation result is zero if none of these conditions are met. If all these conditions are met, the following conditions are further evaluated: If the turn signal was off in the previous moment and is on in the current moment, the calculation result is the current program's running cycle; if the current turn signal is on or the current turn signal's on time is less than the time threshold, the calculation result is incremented by one timer cycle for each running cycle; otherwise, the calculation result is zero. For easier understanding, please refer to [reference needed]. Figure 4 , Figure 4 This is a schematic diagram illustrating the logic for determining the membership degree of a vehicle's turn signal activation duration, provided in an embodiment of the present invention. Here, t_cycletime represents the timing cycle (0.02s per program execution). The activation time of the left and right turn signals is calculated separately based on the turn signal activation status.

[0091] m_timeofIndLeff=FuzzyCounter(egoLeftInd,m timeofIndLeftK1 , false, m timeofIndLeft ,0); where egoLeftInd represents the state of the left turn signal, m timeofIndLeffK1 Indicates the left turn signal status in the previous cycle: m_timeofIndRight = FuzzyCounter(egoRightInd, m timeofIndRightK1 , false, m timeofIndRight ,0)

[0092] Where egoRightInd represents the status of the right turn signal, m timeofIndRightK1 This indicates the status of the right turn signal in the previous cycle. The membership degrees of the left and right turn signal activation durations are obtained from the above:

[0093] A(timeLeftCounter)=FuzzyLarge(m timeofindLeftPAGLeftCounterTime1, PAGLeftCounterTime2) ; wherein, PAGLeftCounterTime1, PAGLeftCounterTime2 represent the first left turn signal opening time threshold and the second left turn signal opening time threshold (reference threshold values are 0.1 and 1) respectively.

[0094] A(timeRightCounter) = FuzztyLarge(m timeofindRightt PAGRightCounterTime1, PAGRightCounterTime2)

[0095] PAGRightCounterTime1, PAGRightCounterTime2 represent the first right turn signal opening time threshold and the second right turn signal opening time threshold (reference threshold values are 0.1 and 1) respectively. For example, if the turn signal switch is turned on in the current period, the turn signal is turned off in the last period, the condition for calculating the turn signal opening time is met, the next condition calculation will be performed, if this condition is continuously met, it indicates that the turn signal is turned on once, and the calculated time is only 0.02s, if this condition is not met, it indicates that the turn signal is turned on in the last period, that is, the turn signal is turned on from the last period, and a 0.02s will be added, and the next period is judged to add multiple calculation periods; if the timing result is less than a certain value such as 0.12s, it is considered that the turn signal opening time cannot represent an effective time length; or the turn signal is turned off, and the calculation result is directly cleared.

[0096] It needs to be further explained that, in order to improve the accuracy of the determination of the lane changing membership degree, the above-mentioned fuzzy membership degree method for determining the turning membership degree corresponding to each turning intention information and determining the lane changing membership degree corresponding to each lane changing intention information can include: if the current lane changing intention information is any one of the steering wheel turning angle, the turn signal switch signal, the angle of the human eye turning, the rate of change of the distance from the vehicle to the lane boundary, the curvature of the vehicle trajectory and the turn signal opening time, the membership degree corresponding to the current lane changing intention information is determined based on the fuzzy large membership degree method; if the current lane changing intention information is the standard deviation of the rate of change of the distance from the vehicle to the lane boundary, the membership degree corresponding to the current lane changing intention information is determined based on the fuzzy small membership degree method.

[0097] In this embodiment, when the lane changing intention information is the rate of change of the distance from the vehicle to the lane boundary, the corresponding lane changing trend is as shown in Figure 5 Figure 5 ​The trend of the self-vehicle trajectory in a lane changing process provided by the embodiment of the present application is determined according to the distance difference of the self-vehicle from the left and right lane boundary lines in the previous and next two times. LeftBorderDescend=(m LeftBorder -mLeftBorderk1) / t_cycletime;

[0098] RightBorderDescend=(m RightBorder -mRightBorderk1) / t_cycletime; wherein m LeftBorder is the distance of the current self-vehicle from the left lane boundary line, mLeftBorderk1 is the distance of the self-vehicle from the left lane boundary line in the previous cycle, m RightBorder is the distance of the current self-vehicle from the right lane boundary line, and mRightBorderk1 is the distance of the self-vehicle from the right lane boundary line in the previous cycle. The membership degrees of the self-vehicle to the lane boundary line in the left and right lane changing processes are respectively calculated as follows:

[0099] A(LeftBorderDescend)=FuzzyLarge(LeftBorderDescend,PAGLeftBorder1,PAGLeftBorder2); A(RightBorderDescend)=FuzzyLarge(RightBorderDescend,PAGRightBorder1,PAGRightBorder2); wherein PAGLeftBorder1 and PAGLeftBorder2 respectively represent the first self-vehicle distance change rate threshold from the left lane boundary line and the second self-vehicle distance change rate threshold from the left lane boundary line in the left lane changing process, and PAGRightBorder1 and PAGRightBorder2 respectively represent the first self-vehicle distance change rate threshold from the right lane boundary line and the second self-vehicle distance change rate threshold from the right lane boundary line in the right lane changing process (the reference threshold is 0.15 m / s and 0.33 m / s).

[0100] When the current lane changing intention information is the standard deviation of the self-vehicle distance from the lane boundary, the calculation formula of the membership degree is as follows: A(LeftBorderStd)=FuzzySmall(m stdLeftBorder, PAGLeftBorderStd1,LeftBorderStd2), and A(RightBorderStd)=FuzzySmall(m stdRightBorder,PAGRightBorderStd1, RightBorderStd2); where PAGRightBorderStd1 and PAGRightBorderStd2 represent the standard deviations of the rate of change of the distance between the first vehicle and the left lane edge when turning left, respectively; PAGRightBorderStd1 and PAGRightBorderStd2 represent the standard deviations of the rate of change of the distance between the first vehicle and the right lane edge when turning right, respectively (reference thresholds are 0.4 and 1.44).

[0101] When the lane change intention information is the curvature of the vehicle's trajectory, the method for determining the membership degree is as follows:

[0102] A(kap TrajectoryChangeLeft)=FuzzyLarge(m kapTrajectory ,PAGChang eLeft3,PAGChangeLeft4);

[0103] A(kapTrajectoryChangeRight)=FuzzyL arge(m kapTrajectory , PAGChangeRight3, PAGChangeRight4); where PAGChangeLeft3 and PAGChangeLeft4 represent the third and fourth curvature thresholds for the vehicle when changing lanes to the left, respectively; PAGChangeRight3 and PAGChangeRight4 represent the third and fourth curvature thresholds for the vehicle when changing lanes to the right, respectively (reference thresholds are 0.015 and 0.016).

[0104] When the lane change intention information is the vehicle's lane sequence value, changes in the lane sequence value can directly reflect the driver's driving intention. By detecting the switching between the current lane sequence value and the previous cycle's lane sequence value, it can be determined whether a lane change is taking place. (See below.) Figure 3 As shown, 0 represents the left lane, 1 represents the current lane, and 2 represents the right lane. If the vehicle was in lane 1 in the previous cycle and is currently in lane 0, it indicates a lane change to the left; if the vehicle is currently in lane 2 and was in lane 1 in the previous cycle, it indicates a lane change to the right. Figure 6 As shown, Figure 6 This is a schematic diagram of a lane sequence value provided in an embodiment of the present invention.

[0105]

[0106] When the lane change intention information is the steering wheel angle, the method for determining the membership degree is as follows:

[0107] A(LeftWheelAngle) = FuzzyLarge(m alpWheelAnglekorr , PAGWheelAngleLeft3, PAGWheelAngleLeft4);

[0108] A(RightWheelAngle) = FuzzyLarge(m alpWheelAnglekorr , PAGWheelAngleRight3, PAGWheelAngleRight4). Wherein, PAGWheelAngleLeft3, PAGWheelAngleLeft4 represent the third and fourth steering wheel angle threshold value when changing lane to left respectively; PAGWheelAngleRight3, PAGWheelAngleRight4 represent the third and fourth steering wheel angle threshold value when changing lane to right respectively (reference threshold value is 0.0125 rad and 0.0325 rad). For example: if the current steering angle is 0.01 rad, the membership degree is 0; if the current steering wheel angle is 0.04 rad, the calculated membership degree is 1; if the steering wheel angle is 0.02 rad, the membership degree is: (0.02-0.0125) / (0.0325-0.0125) = 0.375.

[0109] When the lane change intention information is the steering lamp switch, the method for determining the membership degree is:

[0110] A(leftIndicator) = FuzzyLarge(m_leftIndicator, PAGleffIndicator3, PAGleffIndicator4);

[0111] A(rightIndicator) = FuzzyLarge(m_rightIndicator, PAGrightIndicator3, PAGrightIndicator4). Wherein, PAGleffIndicator3, PAGleftIndicator4 represent the third and fourth steering lamp switch threshold value when changing lane to left respectively; PAGrightIndicator3, PAGrightIndicator4 represent the third and fourth steering lamp switch threshold value when changing lane to right respectively. (reference threshold value is 1)

[0112] When the lane change intention information is the steering lamp on duration, the method for determining the membership degree is: according to the steering lamp on state, the left and right steering lamp on time is calculated respectively,

[0113] m_timeofindChangeLeft=FuzzyCountel'(egoLeftInd,m timeoflndLeftKl , false, m timeoflndLeft ,0).

[0114] Where egoLeftInd represents the status of the left turn signal, m timeoflndLeftK1 This indicates the status of the left turn signal in the previous cycle.

[0115] m_timeofindChangeRight=FuzzyCounter(egoRightlnd, m timeofIndRightK1 ,false,m timeoflndRight ,0).

[0116] Where egoRightlnd represents the status of the right turn signal, m timeofIndRightK1 This indicates the status of the right turn signal in the previous cycle. The membership degrees of the left and right turn signal activation durations are obtained from the above:

[0117] A(timeChangeLeftCounter)=FuzzvLarge(m timeoflndChangeLeft ,PAGleftCounterTime3,PAGleftCounterTime4);

[0118] Among them, PAGleftCounterTime3 and PAGleftCounterTime4 represent the third left turn signal activation duration threshold and the fourth left turn signal activation duration threshold, respectively.

[0119] A(timeChangeRigilttCounter)=FuzzvLarge(m timeoflndCh a ngeRight ,PAGRightCounterTime3,PAGRightCounterTime4).

[0120] Wherein, PAGrightCounterTime3 and PAGrightCounterTime4 represent the third and fourth right turn signal activation duration thresholds, respectively (reference thresholds of 2.0s and 2.5s). For example: when the turn signal activation duration is 1.5s, the membership degree is 0; if the turn signal activation duration is 3s, the membership degree is 1; if the turn signal activation duration is 2.2s, the membership degree is (2.2-2) / (2.5-2) = 0.4.

[0121] When the lane-changing intention information is the angle of human eye rotation, the membership degree includes the angle of left turning m_eyeRotationLeft and the angle of right turning m_eyeRotationRight.

[0122] A(rotationLeft) = FuzzyLarge(rotationAngle, RotationLeftl, RotationLeft2);

[0123] A(rotationRight) = FuzzyLarge(-rotationAngle, RotationRightl, RotationRight2).

[0124] wherein RotationLeftl and RotationLeft2 respectively represent the first human eye rotation angle threshold and the second human eye rotation angle threshold when changing lane to the left; and RotationRightl and RotationRight2 respectively represent the first human eye rotation angle threshold and the second human eye rotation angle threshold when changing lane to the right (reference thresholds 0.69 rad and 1.39 rad).

[0125] S102, based on all the turning membership degrees, a defuzzification function is used to combine the fuzzy relations to determine the left turning probability and the right turning probability; wherein the defuzzification function is a function for determining the intention probability based on the membership degree and the weight coefficient.

[0126] The defuzzification function in this embodiment can include a fuzzy or defuzzification function and a fuzzy and defuzzification function, and a specific defuzzification function corresponding to the current turning intention can be determined. For example, the method for combining the fuzzy relations between the brake pedal of the ego vehicle and other turning intentions (or the obtained combined turning intention probability) is a fuzzy or defuzzification function, and the method for combining the fuzzy relations between the turn signal and other turning intentions is a fuzzy and defuzzification function. The weight coefficient in this embodiment is a value set based on the demand, for example, the value can be 0.9, 0.8, etc.

[0127] It should be further explained that, in order to improve the accuracy of determining the turning probability, the above-mentioned method of determining the left turn probability and right turn probability by combining fuzzy relations using a defuzzification function based on all turning membership degrees can include: determining the left turn probability and right turn probability by combining fuzzy relations using a fuzzy and defuzzification function, or a fuzzy or defuzzification function, based on all turning membership degrees; wherein, the input of the fuzzy and defuzzification function is the first membership degree L1, the second membership degree L2, and the weight coefficient K1. When L1 is less than or equal to L2, the probability value is K1*L1+(1-K1)*((L1+L2) / 2); when L1 is greater than L2, the probability value is K1*L2+(1-K1)*((L1+L2) / 2). The input to the fuzzy or defuzzification function is the first membership degree L1, the second membership degree L2, and the weight coefficient K1. When L1 is less than or equal to L2, the probability value is K1*L2+(1-K1)*((L1+L2) / 2); when L1 is greater than L2, the probability value is...

[0128] K1*L1+(1-K1)*((L1+L2) / 2). The two main functions for deblurring defined in this invention are: FuzzyAnd (fuzzing and deblurring function) and FuzzyOr (fuzzing or deblurring function). The input to the deblurring function FuzzyAnd is X2 (corresponding to L1 above) and X3 (corresponding to L2 above), with K1 being the weight coefficient. The calculation process is as follows: when X2 is less than or equal to X3, the result is K1*X2+(1-K1)*((X2+X3) / 2); when X2 is greater than X3, the result is K1*X3+(1-K1)*((X2+X3) / 2). Figure 7 This is a schematic diagram of a fuzzing and defuzzifying function provided in an embodiment of the present invention; the inputs to the defuzzing function FuzzyOr are X2 and X3, and K1 is a weighting coefficient. Its calculation process is as follows: when X2 is less than or equal to X3, the calculation result is...

[0129] K1*X3+(1-K1)*((X2+X3) / 2); When X2 is greater than X3, the calculation result is K1*X2+(1-K1)*((X2+X3) / 2). Figure 8A schematic diagram of a fuzzy or defuzzification function is provided for the embodiment of the present application. For the selection of the fuzzy and or fuzzy or defuzzification function, the contribution of the description of the turning intention or lane change intention from different dimensions is mainly considered. For example, a large steering wheel angle and the driver stepping on the brake pedal can better represent that the driver is currently turning. This combination is mainly adjusted based on actual driving habits and experience. When the embodiment is combined, the combination can be grouped based on the type of intention information, and finally the overall combination is performed, that is, the membership degrees corresponding to the active intention information can be combined first, then the membership degrees corresponding to the vehicle motion state information are combined, and finally the two results are integrated to obtain the left turn probability and the right turn probability or to obtain the left lane change probability and the right lane change probability.

[0130] It needs to be further explained that the above combination of fuzzy relationships based on all turning membership degrees using the defuzzification function to determine the left turn probability and the right turn probability can include: combination of the turning membership degrees corresponding to the first type of turning intention information based on the fuzzy and defuzzification function to obtain the initial left turn probability and the initial right turn probability; combination of the turning membership degrees corresponding to the second type of turning intention information based on the fuzzy or defuzzification function, the initial left turn probability and the initial right turn probability to obtain the final left turn probability and the right turn probability; wherein the second type of turning intention information includes the longitudinal acceleration of the ego vehicle and the brake pedal of the ego vehicle, and the first type of turning intention is the turning intention information other than the second type of turning intention information. In order to facilitate understanding, the embodiment gives the specific process of the combination of the fuzzy relationship: combination of the membership degrees corresponding to the active intention information: ① fuzzy relationship combination of the steering wheel angle and the steering light on time to obtain the probability of the corresponding left turn and right turn intention:

[0131] m probIntentionLeft1 = FuzzyAnd(p0, A(timeLeftCounter), A(X_alpWheelAnglekorrLeft));

[0132] m probIntentionRight1FuzzyAnd(p0, A(timeLeftCounter), A(X_alpWheelAnglekorrLeft)). Wherein p0 is a first weight coefficient, the reference value is 0.5. A(timeLeftCounter) represents the membership degree of the left turn signal opening time length, A(X_alpWheelAnglekorrLeft) represents the membership degree of the left steering wheel turning angle, A(timeRightCounter) represents the membership degree of the right turn signal opening time length, and A(X_alpWheelAnglekorrRight) represents the membership degree of the right steering wheel turning angle. For example, the membership degree of the turn signal opening time length is 0.4, and the membership degree of the steering wheel turning angle is 0.3. According to the definition of the defuzzification function, the probability of the intention is 0.5*0.3+(1-0.5)*((0.4+0.3) / 2)=0.325. 2) The probability obtained by combining the above 1) is combined with the fuzzy relationship of the turn signal to obtain the probability of the corresponding left turn and right turn intentions: m probIntentionLeft2 = FuzzyAnd(p0, A(dirIndicatorLeft), m probIntentionLeft1 ); m probIntentionRight2 = FuzzyAnd(p0, A(dirIndicatorRight), m probIntentionRight1 ). Wherein A(dirIndicatorLeft) represents the membership degree of the left turn signal, and A(dirIndicatorRight) represents the membership degree of the right turn signal. 3) The probability obtained by combining the above 2) is combined with the speed of the ego vehicle (the lowest speed level, the medium speed) to obtain the probability of the corresponding left turn and right turn intentions:

[0133] m probIntentionLeft3 = FuzzyAnd(p0, A(egoVelocityMedium), m probIntentionLeft2 ); m

[0134] m probIntentionRight3 = FuzzyAnd(p0, A(egoVelocityMedium), m probIntentionRight2 ). Wherein,

[0135] A (egoVelocityMedium) represents the membership degree corresponding to the vehicle's speed. It's understandable that when the vehicle speed exceeds a certain value (the threshold is 16.7 m / s (60 km / h)), the first part of the driver's intention evaluation is no longer performed. This is because, based on daily driving experience, when making left and right turns, the vehicle will maintain a relatively reasonable low to medium speed while ensuring safe driving; excessively high speeds render the evaluation meaningless. For example, when the membership degree of vehicle speed is 0.8, the defuzzified probabilities of turn signal duration and steering wheel angle are 0.325, and the combined probability of the intention is: 0.5 * 0.325 + (1 - 0.5) *

[0136] ((0.8+0.325) / 2)=0.44375. The combination of vehicle motion state information and corresponding membership degrees: ④ Combining the yaw rate and the curvature of the vehicle trajectory for the fourth time to obtain the probabilities of the corresponding left and right turn intentions: m probIntentionLeft4 =FuzzyAnd(p0,A(kapTrajectory),A(yawrateLeft));m probIntentionRight4 =FuzzyAnd(p0, A(kapTrajectory), A(yawrateRight)). Where A(kapTrajectory) represents the membership degree corresponding to the curvature of the vehicle's trajectory, A(yawrateLeft) represents the membership degree of the yaw rate for left turns, and A(yawrateRight) represents the membership degree of the yaw rate for right turns. For example, if the membership degree of the yaw angle is 0.25 and the membership degree of the vehicle's trajectory curvature is 0.5, then the defuzzified probabilities of the yaw angle and the vehicle's trajectory curvature are: 0.5*0.25+(1-0.5)*((0.25+0.5) / 2)=0.5. ⑤ Combining the low speed and the vehicle's accelerator pedal opening for the fifth time yields the probability of low-speed driving:

[0137] m probIntention5 =FuzzyAnd(p0, A(egoGasPedalPositon), A(egoVelocityLow)); where A(egoGasPedalPositon) represents the membership degree of the accelerator pedal opening, and A(egoVelocityLow) represents the membership degree of low speed. For example, if the membership degree of low speed is 0.35 and the membership degree of accelerator pedal opening is 0.4, then the defuzzified probability obtained by superimposing the speed and accelerator pedal opening is 0.5*0.35+(1-0.5)*((0.35+0.4) / 2)=0.55. ⑥ Combining the probability obtained in ⑤ above with the vehicle's brake pedal for the sixth time, we obtain the probability of low-speed driving: m probIntention6= FuzzyOr(p0, A(brakePedal), m probIntention5 ); where A(brakePedal) denotes the membership of the brake pedal of the ego vehicle. For example, the membership of the brake pedal is 0.1, and the probability calculated in ⑤ is 0.55, thus the de-fuzzified probability of the brake pedal is: 0.5*0.1 + (1-0.5)*((0.1+0.55) / 2) = 0.2125. ⑥ The probability obtained in ⑤ and the on duration of the turn signal are combined for the seventh time, and the probability of the corresponding left or right turn is:

[0138] m probIntentionLeft7 = FuzzyAnd(p0, A(timeLeftCounter), mprob Intention6 ); m probIntentionRight7 = FuzzyAnd(p0, A(timeRightCounter), m probIntention6 ). Where A(timeLeftCounter) denotes the membership of the on duration of the left turn signal, and A(timeRightCounter) denotes the membership of the on duration of the right turn signal. The membership of the on duration of the turn signal is 0.6, and the probability calculated in ⑤ is 0.2125, thus the de-fuzzified probability of the on duration of the turn signal is: 0.2125*0.5 + (1-0.5)*((0.2125+0.6) / 2) = 0.309. ⑦ The probability obtained in ⑤ and the trajectory curvature of the ego vehicle are combined for the eighth time, and the probability of the corresponding left or right turn is:

[0139] m probIntentionLeft8 = FuzzyAnd(p0, A(kapTrajectoryLeft), m probIntentionLeft7 );

[0140] m probIntentionRight8 = FuzzyAnd(p0, A(kapTrajectoryRight), m probIntentionTight7 ). Where A(kapTrajectoryLeft) denotes the membership of the trajectory curvature of the ego vehicle in the left turn, and A(kapTrajectoryRight) denotes the membership of the trajectory curvature of the ego vehicle in the right turn. For example, the membership of the trajectory curvature of the ego vehicle is 0.8, and the probability calculated in ⑤ is 0.309, thus the de-fuzzified probability of the trajectory curvature of the ego vehicle is: 0.5*0.309 + (1-0.5)*((0.8+0.309) / 2) = 0.432. ⑧ The probability obtained in ⑤ and the steering wheel angle of the ego vehicle are combined for the ninth time, and the probability of the corresponding left or right turn is:

[0141] m probIntentionLeft9= FuzzyAnd (p0, A (X_alpWheelAnglekorrLeft), m prob I ntentionLeft8 ) ;

[0142] m probIntentionRight9 = FuzzyAnd (p0, A (X_alpWheelAnglekorrRight), m probIntentionRight8 ). For example, the steering wheel angle membership is 0.7 and the probability calculated in ⑧ is 0.432, thus the superimposed steering wheel angle, the de-fuzzified probability is: 0.432*0.5 + (1-0.5)*((0.432+0.7) / 2) = 0.499. ⑩ combine the probability obtained in ⑨ above and the probability obtained in ④ above, the probability of corresponding left and right turns is: m probIntentionLeft10 = FuzzyOr (p0, m probIntentionLeft4 , m probIntentionLeft9 ), m probIntentionRight10 = FuzzyOr (p0, m probIntentionRight4 , m probIntentionRight9 ). For example, the probability calculated in ⑨ is 0.499 and the probability calculated in ④ is 0.5, the superimposed de-fuzzified probability of ⑨ and ④ is: 0.5*0.499 + (1-0.5)*((0.5+0.499) / 2) = 0.4992. The determination of the driver's turning intention: Combine the probabilities calculated in ⑩ and ③ above to obtain the final left and right turn probabilities:

[0143] m probIntentionLeft = FuzzyAnd (p0, m probIntentionLeft3 , m probIntentionLeft10 ), m probIntentionRight = FuzzyAnd (p0, m probIntentionRight3 , m probIntentionRight10 ). For example, the result calculated in ⑩ and the result calculated in ③, the superimposed de-fuzzified turning intention probability is: 0.444*0.5 + (1-0.5)*((0.444+0.4992) / 2) = 0.46. Here, it is not specified whether it is the probability of left turn or right turn, which should be determined according to the actual situation.

[0144] S103, based on all the lane changing membership degrees, use the de-fuzzification function to combine the fuzzy relationship to determine the left lane changing probability and the right lane changing probability.

[0145] It needs to be further explained that, in order to improve the accuracy of the lane change probability determination, the above-mentioned combination of the fuzzy relationship of all lane change membership degrees using the defuzzification function to determine the left lane change probability and the right lane change probability can include: S1031, judging whether there is a change in the lane sequence value; S1032, when there is a change in the lane sequence value, determining that if the self-lane sequence value is switched from the middle lane sequence value to the left lane sequence value, the left lane change probability is 1; if the self-lane sequence value is switched from the middle lane sequence value to the right lane sequence value, the right lane change probability is 1; S1033, when there is no change in the lane sequence value, determining to execute the step of combining the fuzzy relationship of all lane change membership degrees using the defuzzification function to determine the left lane change probability and the right lane change probability. It can be understood that generally, the lane sequence value switching intuitively reflects the driving intention of the driver, such as the self-lane sequence value switching from 1 to 0 indicating left lane change, and the self-lane sequence value switching from 1 to 2 indicating right lane change (i.e. the probability of right lane change is 100%).

[0146] The process of determining the lane change intention in this embodiment can include: combination of the membership degrees of the vehicle motion state information, combination of the self-vehicle trajectory curvature and the self-vehicle distance to the border distance change rate to obtain the corresponding left and right lane change probabilities as follows:

[0147] m proIntentionChangeLeft1 = FuzzyAnd(p1, A(kapTrajectoryChangeLeft), A(leftBorderDescend)),

[0148] m probltentionChangeRight1 = FuzzyAnd(p1, g(kapTrajectoryChangeRight), A(RightBorderDescend)). Wherein, A(kapTrajectoryChange) represents the membership degree corresponding to the self-vehicle trajectory curvature, and A(BorderDescend) represents the membership degree corresponding to the self-vehicle distance to the border distance change rate. Wherein, p1 is a second weight coefficient, and the reference coefficient is 1.0. ②The second combination of the above-mentioned calculated probability and the standard deviation of the self-vehicle distance to the border distance change rate is obtained as follows:

[0149] m proIntentionChangeLeft2 = FuzzyOr(p1, A(leftBorderStd), m proIntentionChangeLeft1 ), m probmmtionChangeRight2 = FuzzyOr(p1, A(RightBorderStd), m proIntentionChangeRight1); wherein, A (BorderStd) represents the membership degree corresponding to the standard deviation of the rate of change of the distance from the vehicle to the boundary line. Active lane change intention: ③ combine the steering wheel angle and the turn signal opening time to obtain the probability of the corresponding left and right lane change: m probaentionChangeLqft3 = FuzzyAnd (p1, A (timeChangeLeftCounter), A (leftWheelAngel)), m probntentionChangeRight3 = FuzzyAnd (p1, A (timeChangeRightCounter), A (RightWheelAngel)); wherein, A (timeChangeLeftCounter) represents the membership degree corresponding to the left turn signal opening time, and A (leftWheelAngel) represents the membership degree corresponding to the left steering wheel angle. ④ combine the probability calculated in the above ③ with the turn signal to obtain the probability of the corresponding left and right lane change: m

[0150] m probltentionChangeLeft4 = FuzzyAnd (p1, A (leftIndicator), m proIntentionChangeLeft3 ), m proIntentionChangeRight4 = FuzzyAnd (p1, A (RightIndicator), m prvIntentionChangeRightt3 ). ⑤ combine the probability calculated in the above ④ with the driver's eye rotation angle to obtain the probability of the corresponding left and right lane change: m probltentionChangeLefi 5 = FuzzyAnd (p1, A (rotationLeft), m probztentionChangeLefi4) , m proIntentionChangeRight5 = FuzzyAnd (p1, A (rotationRight), m probttentionChangeRight4 ). The combination of the membership degrees corresponding to the active lane change intention information: ⑥ combine the probability calculated in the above ⑤ with the probability calculated in the above ② to obtain the final probability of the corresponding left and right lane change: m

[0151] m proIntentionChangeLeft = FuzzyAnd (p1, m proIntentionChangeLqft2 , m proIntentionChangeLqft5 ), m proIntentionChangeRight = FuzzyAnd (p1, m proIntentionChangeRight2 , m proIntentionChangeRight5 ).

[0152] S104, determine the target driving intention based on the left turn probability, the right turn probability, the left lane change probability and the right lane change probability.

[0153] This embodiment does not limit the specific method for determining the target driving intention based on the probabilities of left turn, right turn, left lane change, and right lane change. For example, this embodiment can determine the target driving intention by determining the highest probability value among the probabilities of left turn, right turn, left lane change, and right lane change; or, when it is determined that there is no change in the lane sequence value, this embodiment determines the target driving intention based on the probabilities of left turn, right turn, left lane change, and right lane change; when there is a change in the lane sequence value...

[0154] During the process, the target driving intention is determined based on changes in lane sequence values. When only a left turn probability exists, the right turn probability is 0; or when only a left lane change probability exists, the right lane change probability is 0. This embodiment can determine the target driving intention based solely on the left turn and left lane change probabilities; or it can also determine the target driving intention based on the right turn and left lane change probabilities; or it can also determine the target driving intention based on the left turn and right lane change probabilities; or it can also determine the target driving intention based on the right turn and right lane change probabilities. The target driving intention in this embodiment mainly includes the driver's driving intention, which primarily includes lane keeping in the same lane, lane changing in adjacent lanes, and turning at intersections.

[0155] It should be further explained that, in order to improve the accuracy of determining the target driving intention, determining the target driving intention based on the probability of left turn, right turn, left lane change, and right lane change can include:

[0156] S1041, determine the maximum probability among the probability of turning left, turning right, changing lanes to the left, and changing lanes to the right;

[0157] S1042, Determine whether the maximum probability is greater than the minimum probability threshold;

[0158] S1043, when the maximum probability is greater than the minimum probability threshold, determine the intention corresponding to the maximum probability as the target driving intention;

[0159] S1044, when the maximum probability is not greater than the minimum probability threshold, the target driving intention is determined to be to go straight.

[0160] The embodiments of the present invention provide a specific method for determining the target driving intention, thereby improving the accuracy of the determination of the target driving intention.

[0161] The driving intention determination method provided by the embodiment of the present application can comprise: S101, determining the turning membership degree corresponding to each turning intention information and determining the lane-changing membership degree corresponding to each lane-changing intention information based on a fuzzy membership method; wherein the turning intention information and the lane-changing intention information comprise vehicle motion state information and active intention information; the fuzzy membership method is a method for determining the membership degree corresponding to each intention information based on the first membership parameter and the second membership parameter corresponding to each intention information; S102, determining the left-turning probability and the right-turning probability by combining the fuzzy relationships of all the turning membership degrees by using a defuzzification function; wherein the defuzzification function is a function for determining the intention probability based on the membership degree and the weight coefficient; S103, determining the left-lane-changing probability and the right-lane-changing probability by combining the fuzzy relationships of all the lane-changing membership degrees by using the defuzzification function; S104, determining the target driving intention based on the left-turning probability, the right-turning probability, the left-lane-changing probability and the right-lane-changing probability. Compared with the current driving intention determination method based on a single variable, the present application determines the membership degree corresponding to the intention information based on the multi-parameter intention information composed of the vehicle motion state information and the active intention, and finally combines all the membership degrees by using the defuzzification function to determine the target driving intention, thereby improving the accuracy of the driving intention determination.

[0162] The current behavior of evaluating the driving intention qualitatively determines the driving intention of the driver from several single indicators, such as determining whether the current driver is keeping in the lane by the steering wheel angle or the hand torque, determining whether the current driver is changing lanes by the turn signal, and determining whether the current driver is turning by the turn signal, the steering wheel angle and the yaw angle. The behavior of measuring the driver's behavior by a single variable has great uncertainty. Because in the actual driving process, there is great difference and non-standard driving behavior in each driving behavior, such as changing lanes without turning on the turn signal and turning, turning right with the left turn signal on, and turning without turning on the turn signal, which is not conducive to the accurate identification of the driving intention.

[0163] In order to make the present application more convenient to understand, please refer to Figure 9 , Figure 9 The flowchart of the driving intention determination method provided by the embodiment of the present application can specifically comprise:

[0164] S201: obtaining a turning intention information set; wherein the turning intention information set comprises the vehicle motion state information related to turning and the active turning intention information.

[0165] The turning intention information set in this embodiment comprises the steering wheel angle, the turn signal switch, the vehicle speed signal, the vehicle yaw angular velocity, the vehicle trajectory curvature, the vehicle longitudinal acceleration, the vehicle brake pedal, the vehicle throttle pedal opening degree, and the turn signal opening time of the vehicle.

[0166] S202: Obtain a lane-changing intention information set; wherein the lane-changing intention information set comprises vehicle motion state information related to lane-changing and active lane-changing intention information.

[0167] The lane-changing intention information set in this embodiment comprises a rate of change of the distance from the vehicle to the lane boundary, a standard deviation of the rate of change of the distance from the vehicle to the lane boundary, a curvature of the vehicle trajectory, a vehicle lane sequence value, a steering wheel angle, a turn signal switch signal, a turn signal on duration, and an angle of eye rotation.

[0168] S203: Determine a turning intention information set corresponding to each turning intention information in the turning intention information set based on a fuzzy small membership method and a fuzzy large membership method.

[0169] S204: According to each turning membership, perform fuzzy relationship combination based on a fuzzy and defuzzification function and a fuzzy or defuzzification function to obtain a left-turn probability and a right-turn probability corresponding to the turning intention.

[0170] S205: Determine a lane-changing membership of each lane-changing intention information in the lane-changing intention information set based on the fuzzy small membership method and the fuzzy large membership method.

[0171] S206: According to each lane-changing membership, perform fuzzy relationship combination based on a fuzzy and defuzzification function and a fuzzy or defuzzification function to obtain a left-lane-changing probability and a right-lane-changing probability corresponding to the lane-changing intention.

[0172] S207: Determine a target driving intention based on the left-turn probability, the right-turn probability, the left-lane-changing probability, and the right-lane-changing probability; wherein the target driving intention is one of straight driving, turning, and lane-changing.

[0173] The embodiment of the present application provides an accurate quantitative calculation to evaluate the driving intention of a driver during driving, is relatively stable and reliable compared with single variable measurement of driving intention, can reduce the requirement for domain controller computing power compared with multi-input neural network model calculation, and is a low-computing-power and low-cost evaluation method.

[0174] The driving intention determination device provided by the embodiment of the present application will be described below. The driving intention determination device described below can be correspondingly referred to the driving intention determination method described above.

[0175] For details, please refer to Figure 10 , Figure 10 The structure diagram of the driving intention determination device provided by the embodiment of the present application can include:

[0176] The membership determination module 100 is configured to determine a turning membership corresponding to each turning intention information and determine a lane-changing membership corresponding to each lane-changing intention information based on a fuzzy membership method; wherein the turning intention information and the lane-changing intention information comprise vehicle motion state information and active intention information; the fuzzy membership method is a method of determining a membership corresponding to each intention information based on set first membership information and second membership information corresponding to each intention information;

[0177] The turning probability determination module 200 is configured to determine a left-turning probability and a right-turning probability by combining fuzzy relationships of all turning memberships using a defuzzification function; wherein the defuzzification function is a function of determining an intention probability based on a membership and a weight coefficient;

[0178] The lane-changing probability determination module 300 is configured to determine a left-lane-changing probability and a right-lane-changing probability by combining fuzzy relationships of all lane-changing memberships using the defuzzification function.

[0179] The driving intention determination module 400 is configured to determine a target driving intention based on the left-turning probability, the right-turning probability, the left-lane-changing probability and the right-lane-changing probability.

[0180] It needs to be further explained that the above-mentioned membership determination module 100 can comprise:

[0181] The membership determination unit based on a fuzzy small function is configured to determine a membership corresponding to a current intention information based on a fuzzy small membership method if the membership is closer to zero as the value of the intention information is larger; wherein the input of the fuzzy small membership method comprises a value x of the current intention information, a first membership parameter M1 and a second membership parameter M2; when the input x is greater than M2, the membership is 0; when the input x is less than M1, the membership is 1; when the input is between M1 and M2, the membership is (M2-x) / (M2-M1), and M1M2;

[0182] The membership determination unit based on a fuzzy large function is configured to determine a membership corresponding to a current intention information based on a fuzzy large membership method if the membership is closer to one as the value of the intention information is larger; wherein the input of the fuzzy large membership method comprises a value y of the current intention information, a third membership parameter M3 and a fourth membership parameter M4; when the input y is less than M3, the membership is 0; when y is greater than M4, the membership is 1; when y is between M3 and M4, the membership is (y-M3) / (M4-M3), and M3M4;

[0183] The turn signal membership degree determination unit is configured to determine that the membership degree corresponding to the turn signal is 1 when the turn signal is on and 0 when the turn signal is off if the current turning intention information is the turn signal switch;

[0184] The self-vehicle brake pedal membership degree determination unit is configured to determine that the membership degree corresponding to the brake pedal is 1 when the brake pedal is pressed and 0 when the brake pedal is not pressed if the current turning intention information is the self-vehicle brake pedal.

[0185] Further, based on the above-mentioned embodiments, the membership degree determination module 100 can include:

[0186] The first turning membership degree method determination unit is configured to determine the membership degree corresponding to the current turning intention information based on the fuzzy large membership degree method if the current turning intention information is any one of the steering wheel rotation angle, the self-vehicle yaw rate, the self-vehicle trajectory curvature, the self-vehicle longitudinal acceleration, the self-vehicle throttle pedal opening degree, and the self-vehicle turn signal on duration.

[0187] The second turning membership degree method determination unit is configured to distinguish the lowest speed, the medium speed, and the highest speed when calculating the membership degree of the self-vehicle speed signal and determine the membership degree corresponding to the current turning intention information based on the fuzzy small membership degree method if the current turning intention information is the self-vehicle speed signal; wherein the highest speed is greater than the medium speed, and the medium speed is greater than the lowest speed.

[0188] Further, based on the above-mentioned embodiments, the membership degree determination module 100 can include:

[0189] The first lane-changing membership degree determination unit is configured to determine the membership degree corresponding to the current lane-changing intention information based on the fuzzy large membership degree method if the current lane-changing intention information is any one of the steering wheel rotation angle, the turn signal switch signal, the angle of the human eye rotation, the rate of change of the distance from the self-vehicle to the lane boundary, the curvature of the self-vehicle trajectory, and the turn signal on duration.

[0190] The second lane-changing membership degree determination unit is configured to determine the membership degree corresponding to the current lane-changing intention information based on the fuzzy small membership degree method if the current lane-changing intention information is the standard deviation of the rate of change of the distance from the self-vehicle to the lane boundary.

[0191] Further, based on any of the above-mentioned embodiments, the turning probability determination module 200 can include:

[0192] The turning probability determination unit is configured to determine the left turning probability and the right turning probability by combining the fuzzy relationship of all the turning membership degrees using the fuzzy and defuzzification function, the fuzzy or defuzzification function.

[0193] The input of the fuzzy or defuzzification function is the first membership degree L1, the second membership degree L2 and the weight coefficient K1. When L1 is less than or equal to L2, the probability value is K1*L2+(1-K1)*((L1+L2) / 2); when L1 is greater than L2, the probability value is K1*L1+(1-K1)*((L1+L2) / 2).

[0194] The input of the fuzzy or defuzzification function is the first membership degree L1, the second membership degree L2 and the weight coefficient K1. When L1 is less than or equal to L2, the probability value is K1*L2+(1-K1)*((L1+L2) / 2); when L1 is greater than L2, the probability value is K1*L1+(1-K1)*((L1+L2) / 2).

[0195] Further, based on the above-mentioned embodiments, the turning probability determination module 200 can comprise:

[0196] An initial turning probability determination unit is configured to combine the fuzzy relationship of the turning membership degrees corresponding to the first type of turning intention information based on the fuzzy and defuzzification function, to obtain the initial left turning probability and the initial right turning probability.

[0197] A final turning probability determination unit is configured to combine the fuzzy relationship of the turning membership degrees corresponding to the second type of turning intention information based on the fuzzy or defuzzification function, the initial turning probability and the initial right turning probability, to obtain the final left turning probability and the right turning probability. The second type of turning intention information comprises the longitudinal acceleration of the ego vehicle and the brake pedal of the ego vehicle, and the first type of turning intention is the turning intention information other than the second type of turning intention information.

[0198] Further, based on any of the above-mentioned embodiments, the lane change probability determination module 300 can comprise:

[0199] A judgment unit is configured to judge whether there is a change in the lane sequence value.

[0200] A first lane change probability determination unit is configured to, when there is a change in the lane sequence value, determine the left lane change probability as 1 if the lane sequence value of the ego vehicle switches from the middle lane sequence value to the left lane sequence value, and determine the right lane change probability as 1 if the lane sequence value of the ego vehicle switches from the middle lane sequence value to the right lane sequence value.

[0201] A second lane change probability determination unit is configured to, when there is no change in the lane sequence value, determine the steps of performing the fuzzy relationship combination based on all the lane change membership degrees using the defuzzification function to determine the left lane change probability and the right lane change probability.

[0202] Further, based on any of the above-mentioned embodiments, the driving intention determination device can further comprise:

[0203] a sequence value determining unit configured to determine the left lane-changing probability as 1 if the self vehicle lane sequence value switches from the middle lane sequence value to the left lane sequence value;

[0204] a 0 probability determining unit configured to determine the left lane-changing probability and the right lane-changing probability as 0 if the self vehicle lane sequence value does not switch;

[0205] a 1 probability determining unit configured to determine the right lane-changing probability as 1 if the self vehicle lane sequence value switches from the middle lane sequence value to the right lane sequence value.

[0206] Further, based on any of the above embodiments, the driving intention determining module 400 can comprise:

[0207] a maximum probability determining unit configured to determine a maximum probability among the left-turn probability, the right-turn probability, the left lane-changing probability and the right lane-changing probability;

[0208] a judging unit configured to determine whether the maximum probability is greater than a minimum probability threshold;

[0209] a first target driving intention determining unit configured to determine the maximum probability corresponding intention as the target driving intention when the maximum probability is greater than the minimum probability threshold;

[0210] a second target driving intention determining unit configured to determine the target driving intention as straight driving when the maximum probability is not greater than the minimum probability threshold.

[0211] It should be noted that the order of the modules and units in the driving intention determining device above can be changed without affecting the logic.

[0212] The driving intention determination device provided by the embodiment of the present application can comprise: a membership determination module 100, configured to determine a turning membership corresponding to each turning intention information and determine a lane-changing membership corresponding to each lane-changing intention information based on a fuzzy membership method; wherein the vehicle motion state information and the active intention information are included in the turning intention information and the lane-changing intention information; the fuzzy membership method is a method for determining the membership corresponding to each intention information based on the set first membership information and the second membership information corresponding to each intention information; a turning probability determination module 200, configured to determine a left turning probability and a right turning probability by combining the fuzzy relationships of all the turning memberships by using a defuzzification function; wherein the defuzzification function is a function for determining the intention probability based on the membership and the weight coefficient; a lane-changing probability determination module 300, configured to determine a left lane-changing probability and a right lane-changing probability by combining the fuzzy relationships of all the lane-changing memberships by using the defuzzification function; and a driving intention determination module 400, configured to determine a target driving intention based on the left turning probability, the right turning probability, the left lane-changing probability and the right lane-changing probability. Compared with directly determining the driving intention based on a single variable, the present application determines the membership corresponding to the intention information based on the multi-parameter intention information composed of the vehicle motion state information and the active intention, and finally combines all the memberships by using the defuzzification function to determine the target driving intention, thereby improving the accuracy of the driving intention determination.

[0213] The driving intention determination device provided by the embodiment of the present application will be described below. The driving intention determination device described below can be referred to in correspondence with the driving intention determination method described above.

[0214] Please refer to Figure 11 , Figure 11 The structure diagram of the driving intention determination device provided by the embodiment of the present application can comprise:

[0215] The memory 10 is configured to store a computer program.

[0216] The processor 20 is configured to execute the computer program to implement the driving intention determination method described above.

[0217] The memory 10, the processor 20 and the communication interface 30 can communicate with each other through the communication bus 40.

[0218] In the embodiment of the present application, the memory 10 stores one or more programs, and the program can comprise program code including computer operation instructions. In the embodiment of the present application, the memory 10 can store programs for implementing the following functions:

[0219] The turning membership degree corresponding to each turning intention information and the lane-changing membership degree corresponding to each lane-changing intention information are determined based on a fuzzy membership method; wherein, the vehicle motion state information and the active intention information are included in the turning intention information and the lane-changing intention information; the fuzzy membership method is a method for determining the membership degree corresponding to each intention information based on the first membership parameter and the second membership parameter corresponding to each intention information;

[0220] The left-turning probability and the right-turning probability are determined based on the fuzzy relationship combination of all the turning membership degrees by using a defuzzification function; wherein, the defuzzification function is a function for determining the intention probability based on the membership degree and the weight coefficient;

[0221] The left-lane-changing probability and the right-lane-changing probability are determined based on the fuzzy relationship combination of all the lane-changing membership degrees by using a defuzzification function;

[0222] The target driving intention is determined based on the left-turning probability, the right-turning probability, the left-lane-changing probability and the right-lane-changing probability.

[0223] In a possible implementation, the memory 10 can include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required by a function, etc.; and the data storage area can store data created in the use process.

[0224] In addition, the memory 10 can include a read-only memory and a random access memory, and provide instructions and data for the processor. A part of the memory can also include an NVRAM. The memory stores an operating system and operation instructions, executable modules or data structures, or a subset or an extended set thereof, wherein the operation instructions can include various operation instructions for implementing various operations. The operating system can include various system programs for implementing various basic tasks and processing hardware-based tasks.

[0225] The processor 20 can be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field programmable gate array or other programmable logic device, and the processor 20 can be a microprocessor or any conventional processor, etc. The processor 20 can invoke the program stored in the memory 10.

[0226] The communication interface 30 can be an interface of a communication module, used for connecting with other devices or systems.

[0227] Of course, it should be noted that, Figure 11 The structures shown do not constitute a limitation on the driving intention determination device in the embodiments of the present application, and in actual applications, the driving intention determination device can include more or fewer components than those shown. Figure 11more or less components, or combinations of certain components.

[0228] The readable storage medium provided by the embodiments of the present application is described as follows, and the readable storage medium described below can be referred to the driving intention determination method described above.

[0229] The present application also provides a readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the driving intention determination method.

[0230] The readable storage medium can include a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various storage medium that can store program codes.

[0231] The embodiments in the present specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and the same or similar parts of each embodiment can be referred to each other. For the device disclosed by the embodiments, since it corresponds to the method disclosed by the embodiments, the description is relatively simple, and the related parts can be referred to the method part.

[0232] The skilled person can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in the present text can be realized by electronic hardware, computer software or combination of the two. In order to clearly show the interchangeability of hardware and software, the composition and steps of each example have been described in general in the above description. Whether the functions are realized by hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0233] Finally, it should be noted that in the present text, the relationship such as first and second belongs to distinguish one entity or operation from another entity or operation, and does not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the term "include", "contain" or any other variant is intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or equipment.

[0234] The driving intention determination method, device, equipment and readable storage medium provided by the present application are described in detail above, the principle and implementation mode of the present application are described by applying specific examples in this paper, and the above example description is only used to help understand the method of the present application and its core idea; at the same time, for the general technical personnel in the art, according to the idea of the present application, the specific implementation mode and application range will be changed, and the above description should not be understood as the limitation of the present application.

Claims

1. A method for determining driving intent, characterized in that, include: The turning membership degree corresponding to each turning intention information and the lane change membership degree corresponding to each lane change intention information are determined based on the fuzzy membership degree method; wherein, the turning intention information and the lane change intention information include vehicle motion state information and active intention information; the fuzzy membership degree method is a method for determining the membership degree corresponding to each intention information based on the set first membership degree information and second membership degree information corresponding to each intention information. Based on all turning membership degrees, a fuzzy relationship combination is performed using a defuzzification function to determine the left turn probability and the right turn probability; wherein, the defuzzification function is a function that determines the intention probability based on membership degree and weight coefficient; Based on all lane change membership degrees, the defuzzification function is used to combine fuzzy relationships to determine the left lane change probability and the right lane change probability. The target driving intention is determined based on the left turn probability, the right turn probability, the left lane change probability, and the right lane change probability.

2. The driving intention determination method according to claim 1, characterized in that, The method for determining the turning membership degree corresponding to each turning intention information and the lane change membership degree corresponding to each lane change intention information based on the fuzzy membership degree method includes: If the current intent information is such that the larger the value of the intent information, the closer the membership degree is to zero, then the membership degree corresponding to the current intent information is determined based on the fuzzy small membership degree method. The input to the fuzzy small membership degree method is the value x of the current intent information, the first membership degree parameter M1, and the second membership degree parameter M2. When the input x is greater than M2, the membership degree is 0; when the input x is less than M1, the membership degree is 1; when the input is between M1 and M2, the membership degree is (M2-x) / (M2-M1), where M1... <M2; If the current intent information is such that the larger the value of the intent information and the closer the membership degree is to one, then the membership degree corresponding to the current intent information is determined based on the fuzzy large membership degree method. The input of the fuzzy large membership degree method is the value y of the current intent information, the third membership degree parameter M3, and the fourth membership degree parameter M4. When the input y is less than M3, the membership degree is 0; when y is greater than M4, the membership degree is 1; when y is between M3 and M4, the membership degree is (y-M3) / (M4-M3), where M3... <M4; If the current turning intention information is a turn signal switch, then the membership degree corresponding to the turn signal being on is determined to be 1, and the membership degree corresponding to the turn signal being off is determined to be 0. If the current steering intention information is the vehicle's brake pedal, then the membership degree corresponding to when the pedal is braking is determined to be 1, and the membership degree corresponding to when the pedal is not braking is determined to be 0.

3. The method for determining driving intent according to claim 2, characterized in that, The method for determining the turning membership degree corresponding to each turning intention information and the lane change membership degree corresponding to each lane change intention information based on the fuzzy membership degree method includes: If the current turning intention information is any one of the following: steering wheel angle, vehicle yaw rate, vehicle trajectory curvature, vehicle longitudinal acceleration, vehicle accelerator pedal opening, and vehicle turn signal duration, the membership degree corresponding to the current turning intention information is determined based on the fuzzy large membership degree method. If the current turning intention information is the vehicle speed signal, when calculating the membership degree of the vehicle speed signal, the lowest level speed, medium speed and the highest level speed are distinguished, and the membership degree corresponding to the current turning intention information is determined based on the fuzzy small membership degree method; wherein, the highest level speed is greater than the medium speed, and the medium speed is greater than the lowest level speed.

4. The method for determining driving intent according to claim 2, characterized in that, The method for determining the turning membership degree corresponding to each turning intention information and the lane change membership degree corresponding to each lane change intention information based on the fuzzy membership degree method includes: If the current lane change intention information is any one of the following: steering wheel angle, turn signal switch signal, eye rotation angle, rate of change of distance from the vehicle to the lane boundary, curvature of the vehicle trajectory, and turn signal duration, the membership degree corresponding to the current lane change intention information is determined based on the fuzzy large membership degree method. If the current lane change intention information is the standard deviation of the rate of change of distance from the vehicle to the lane boundary, then the membership degree corresponding to the current lane change intention information is determined based on the fuzzy small membership degree method.

5. The method for determining driving intent according to any one of claims 1 to 4, characterized in that, The process of determining the left turn probability and right turn probability by combining fuzzy relations using a defuzzification function based on all turning membership degrees includes: Based on all turning membership degrees, fuzzy relationships are combined using fuzzy and defuzzification functions, or fuzzy or defuzzification functions, to determine the left turn probability and the right turn probability; The inputs to the fuzzing and defuzzifying functions are the first membership degree L1, the second membership degree L2, and the weight coefficient K1. When L1 is less than or equal to L2, the probability value is K1*L1+(1-K1)*((L1+L2) / 2); when L1 is greater than L2, the probability value is K1*L2+(1-K1)*((L1+L2) / 2). The input to the fuzzing or defuzzifying function is the first membership degree L1, the second membership degree L2, and the weight coefficient K1. When L1 is less than or equal to L2, the probability value is K1*L2+(1-K1)*((L1+L2) / 2); when L1 is greater than L2, the probability value is K1*L1+(1-K1)*((L1+L2) / 2).

6. The method for determining driving intent according to claim 5, characterized in that, The process of determining the left turn probability and right turn probability by combining fuzzy relations using a defuzzification function based on all turning membership degrees includes: Based on the fuzzy and defuzzy functions, the turning membership degree corresponding to the first type of turning intention information is combined with fuzzy relations to obtain the initial left turn probability and the initial right turn probability. Based on the fuzzy or defuzzification function, the initial left turn probability, and the initial right turn probability, the turning membership degree corresponding to the second type of turning intention information is combined using fuzzy relations to obtain the final left turn probability and right turn probability; wherein, the second type of turning intention information includes the vehicle's longitudinal acceleration and the vehicle's brake pedal, and the first type of turning intention is turning intention information other than the second type of turning intention information.

7. The method for determining driving intent according to claim 1, characterized in that, Based on all lane change membership degrees, the defuzzification function is used to combine fuzzy relationships to determine the left lane change probability and the right lane change probability, including: Determine if there are any changes in lane sequence values; When there is a change in the lane sequence value, if the lane sequence value changes from the middle lane sequence value to the left lane sequence value, the probability of changing lanes to the left is determined to be 1; if the lane sequence value changes from the middle lane sequence value to the right lane sequence value, the probability of changing lanes to the right is determined to be 1. When there is no change in lane sequence values, the step of determining the left lane change probability and the right lane change probability is performed by combining fuzzy relationships based on all lane change membership degrees using the defuzzification function.

8. The method for determining driving intent according to claim 1, characterized in that, Determining the target driving intention based on the left turn probability, the right turn probability, the left lane change probability, and the right lane change probability includes: Determine the maximum probability among the left turn probability, the right turn probability, the left lane change probability, and the right lane change probability; Determine whether the maximum probability value is greater than the minimum probability threshold; When the maximum probability value is greater than the minimum probability threshold, the intention corresponding to the maximum probability value is determined as the target driving intention. When the maximum probability value is not greater than the minimum probability threshold, the target driving intention is determined to be to go straight.

9. A driving intention determination device, characterized in that, include: The membership determination module is used to determine the turning membership degree corresponding to each turning intention information and the lane change membership degree corresponding to each lane change intention information based on the fuzzy membership degree method; wherein, the turning intention information and the lane change intention information include vehicle motion state information and active intention information; the fuzzy membership degree method is a method for determining the membership degree corresponding to each intention information based on the set first membership degree information and second membership degree information corresponding to each intention information; The turning probability determination module is used to determine the left turn probability and the right turn probability by combining fuzzy relationships based on all turning membership degrees using a defuzzification function; wherein, the defuzzification function is a function that determines the intention probability based on membership degree and weight coefficient; The lane change probability determination module is used to combine fuzzy relationships based on all lane change membership degrees using the defuzzification function to determine the left lane change probability and the right lane change probability. The driving intention determination module is used to determine the target driving intention based on the left turn probability, the right turn probability, the left lane change probability, and the right lane change probability.

10. A driving intention determination device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the driving intention determination method as described in any one of claims 1 to 8.

11. A readable storage medium, characterized in that, The readable storage medium stores a computer program that, when executed by a processor, implements the steps of the driving intention determination method as described in any one of claims 1 to 8.

Images