Vehicle turning angle determination method, terminal and storage medium

Abstract

The invention discloses a vehicle turning angle determination method, a terminal and a storage medium, the vehicle turning angle determination method comprises the following steps: obtaining a driving boundary corresponding to a current vehicle, the driving boundary having a collision risk with the current vehicle; a vehicle motion curve equation is constructed by combining a reference straight line corresponding to the driving boundary and the first position and the first orientation of the current vehicle, and a curve point corresponding to the first position is tangent to a target straight line corresponding to the first orientation; the distance between a curve formed by the vehicle motion curve equation and the reference straight line in the extension direction of the reference straight line is gradually reduced; solving the vehicle motion curve equation to obtain parameters in the vehicle motion curve equation; calculating the turning angle of the vehicle by using the parameters; wherein the vehicle corner is used for preventing the current vehicle from colliding with the driving boundary. According to the scheme, the driving safety of the current vehicle is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a method for determining a vehicle turning angle, a terminal, and a storage medium. Background Art

[0002] Intelligent driving technology can make vehicles drive more conveniently and safely. Anti-collision is an important part of the intelligent driving safety module, which identifies collision risks and gives avoidance or warning operations to avoid collisions. Summary of the invention

[0003] The present application provides a method, a terminal and a storage medium for determining a vehicle turning angle.

[0004] A technical solution adopted by the present application is to provide a method for determining a vehicle turning angle, the method comprising:

[0005] Get the driving boundary corresponding to the current vehicle. There is a risk of collision between the driving boundary and the current vehicle.

[0006] The vehicle motion curve equation is constructed by combining the reference straight line corresponding to the driving boundary, the first position and the first orientation of the current vehicle, wherein the curve point corresponding to the first position is tangent to the target straight line corresponding to the first orientation, and the distance between the curve formed by the vehicle motion curve equation and the reference straight line gradually decreases in the extension direction of the reference straight line;

[0007] Solve the vehicle motion curve equation to obtain the parameters in the vehicle motion curve equation;

[0008] The vehicle turning angle is calculated using the parameters; wherein the vehicle turning angle is used to prevent the current vehicle from colliding with the driving boundary.

[0009] Optionally, solving the vehicle motion curve equation to obtain parameters in the vehicle motion curve equation includes:

[0010] In combination with the vehicle motion curve equation, a first function related to the relative angle is constructed; wherein the relative angle represents the angle between the target straight line and the driving boundary;

[0011] Solve the first function within the domain of the relative angle;

[0012] When the absolute value of the first output result of the first function is less than a preset result, determining the relative angle used by the first function as the target independent variable;

[0013] The target independent variable is used to obtain the parameters in the vehicle motion curve equation.

[0014] Optionally, solving the first function within the definition domain of the relative angle includes:

[0015] Randomly select relative angles within the definition domain;

[0016] Inputting the relative angle into a first function to obtain a first output result; and inputting the relative angle into a second function to obtain a second output result, wherein the second function is a first-order derivative function of the first function;

[0017] In response to the absolute value of the first output result being greater than or equal to the preset result, and the absolute value of the second output result being less than the preset result, randomly selecting a relative angle again within the definition domain, and continuing to solve the first function;

[0018] In response to an absolute value of the first output result being greater than or equal to a preset result, and an absolute value of the second output result being greater than or equal to a preset result, iterating the relative angle using the first output result and the second output result to obtain an iterated relative angle;

[0019] In response to the relative angle after iteration being within the definition domain, continuing to solve the first function using the relative angle after iteration;

[0020] In response to the relative angle after iteration being outside the definition domain, a relative angle is randomly selected again from within the definition domain, and the first function is continued to be solved.

[0021] Optionally, in response to an absolute value of the first output result being greater than or equal to a preset result, and an absolute value of the second output result being greater than or equal to a preset result, iterating the relative angle using the first output result and the second output result to obtain the iterated relative angle, comprising:

[0022] In response to the absolute value of the first output result being greater than or equal to a preset result, calculating a quotient of the first output result and the second output result to obtain an iterative change amount;

[0023] Calculate the difference between the relative angle and the iterative change to get the relative angle after iteration.

[0024] Optionally, the relative angle is input into a second function to obtain a second output result, including:

[0025] Input the relative angle into the second function to obtain a candidate result;

[0026] In response to the candidate result being less than the target gradient and the candidate result being greater than or equal to the preset result, taking the target gradient as the second output result;

[0027] Or, in response to the candidate result being smaller than the negative value of the target gradient and the candidate result being smaller than or equal to the negative value of the preset result, the negative value of the target gradient is used as the second output result.

[0028] Optionally, the vehicle turning angle is calculated using parameters including:

[0029] Using the parameters, calculate the target curvature of the curve at the curve point;

[0030] Determine the rear wheel slip angle compensation angle of the current vehicle using the target curvature, the first distance from the center of mass to the front axle of the vehicle, the mass of the current vehicle, the current speed of the current vehicle, the equivalent cornering stiffness of the left and right wheels of the rear axle, and the wheelbase of the current vehicle;

[0031] Determine the understeering degree of the current vehicle using the first distance, mass, equivalent cornering stiffness of the left and right wheels on the rear axle, wheelbase, the second distance from the center of mass to the rear axle of the vehicle, and equivalent cornering stiffness of the left and right wheels on the front axle;

[0032] The vehicle turning angle is calculated using the turning angle coefficient, target curvature, wheelbase, understeering degree, current speed, and rear wheel sideslip angle compensation angle.

[0033] Optionally, the vehicle turning angle includes a vehicle left turning angle and a vehicle right turning angle;

[0034] The driving boundaries include a plurality of left driving boundaries and a plurality of right driving boundaries;

[0035] The vehicle turning angle is calculated using parameters including:

[0036] Utilizing the parameters of the vehicle motion curve equation corresponding to each left travel boundary, a plurality of candidate vehicle left turn angles are calculated, and the candidate vehicle left turn angles are positive numbers;

[0037] Using the parameters of the vehicle curve motion equation corresponding to each right driving boundary, multiple candidate vehicle right turning angles are calculated, and the candidate vehicle right turning angles are negative numbers;

[0038] From a plurality of candidate vehicle left turn angles, a smallest one is selected as the vehicle left turn angle; and from a plurality of candidate vehicle right turn angles, a largest one is selected as the vehicle right turn angle.

[0039] Optionally, obtaining the driving boundary corresponding to the current vehicle includes:

[0040] Obtaining a driving boundary according to a second position, a second orientation, and a running speed corresponding to the dynamic obstacle;

[0041] and / or,

[0042] Get at least one driving boundary corresponding to the road edge.

[0043] Another technical solution adopted by the present application is to provide a terminal device, the terminal device comprising a memory and a processor connected to the memory;

[0044] The memory is used to store program data, and the processor is used to execute the program data to implement the method for determining the vehicle turning angle as described above.

[0045] Another technical solution adopted by the present application is to provide a computer storage medium, wherein the computer storage medium is used to store program data, and when the program data is executed by a computer, it is used to implement the method for determining the vehicle turning angle as described above.

[0046] The beneficial effects of the present application are: obtaining a driving boundary with a risk of collision with the current vehicle; constructing a vehicle motion curve equation according to the position and orientation of the current vehicle and a reference straight line corresponding to the driving boundary; solving the vehicle motion curve equation to obtain parameters in the vehicle motion curve equation, and using the parameters to determine the turning angle used to prevent the current vehicle from colliding with the driving boundary. By constructing a vehicle motion curve equation in combination with the driving boundary, the control boundary can be planned in advance, and when the vehicle is driving at the vehicle turning angle determined by the vehicle turning angle determination method provided in the present application, the probability of collision with the driving boundary can be effectively reduced, thereby improving the driving safety of the current vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 It is a flow chart of an embodiment of a method for determining a vehicle turning angle provided by the present application;

[0049] Figure 2 It is a schematic diagram of an embodiment of a reference straight line and a curve provided by the present application;

[0050] Figure 3 is a schematic diagram of an embodiment of a road scene where a vehicle is currently located;

[0051] Figure 4 is a flow chart of another embodiment of the method for determining a vehicle turning angle provided by the present application;

[0052] Figure 5 is a schematic diagram of an embodiment of the Newton iteration method provided by the present application;

[0053] Figure 6 It is a schematic diagram of an embodiment of merging multiple road boundary corresponding curves provided by the present application;

[0054] Figure 7 It is a structural diagram of an embodiment of a terminal device provided by the present application;

[0055] Figure 8 It is a structural diagram of an embodiment of a computer storage medium provided by the present application. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] The terms "first", "second", etc. in this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods or devices.

[0058] In addition, although the terms "first", "second", etc. are used many times in this application to describe various data (or various applications or various instructions or various operations), etc., these data (or applications or instructions or operations) should not be limited by these terms. These terms are only used to distinguish one type of data (or application or instruction or operation) from another type of data (or application or instruction or operation).

[0059] The current vehicle control algorithm usually only follows the planned trajectory given by the planning layer. During the entire control process, the risk of collision with the environment is guaranteed by the rationality of the planned trajectory. However, in the current autonomous driving architecture, the planned operation cycle is usually much longer than the control cycle and perception cycle, and its system safety is restricted by the planned operation cycle.

[0060] The relevant vehicle control algorithm will comprehensively balance the smoothness and followability in combination with the comfort of the control body, and there will be reasonable errors in the actual control process. In most working conditions, the reasonable error of control following will not have serious consequences, but in some special scenarios, such as narrow roads or single-sided road boundaries, the control error should theoretically be strictly narrowed or unilaterally narrowed.

[0061] At present, a relatively simple approach is for the planning side to take the control error into account in the planned path and expand the obstacles, which will undoubtedly greatly reduce the success rate of trajectory planning and significantly reduce the vehicle's ability to pass through difficult scenarios.

[0062] The AEB (automatic emergency braking) and AES (automatic emergency steering) functions are only for front collision risk scenarios and are longitudinal collision avoidance functions and cannot handle lateral collision risks.

[0063] LKA (lane keeping assist) can only be triggered when the current vehicle is close to the lane line boundary and is not predictive. Therefore, the triggering conditions are relatively strict. It requires clear lane line assistance, the vehicle speed needs to be above 60kmh, and the angle between the front of the vehicle and the lane line cannot be too large. It is not universal.

[0064] Ultrasonic distance measurement collision avoidance is a trigger-type strategy and is only applicable to low-speed conditions. Limited by the location of ultrasonic sensors, the close-range braking function is usually more effective for longitudinal control, and it is difficult to effectively avoid collisions caused by side distances that are too close. Braking measures will inevitably cause functional interruption.

[0065] Please refer to Figure 1 , Figure 1 It is a flow chart of an embodiment of a method for determining a vehicle turning angle provided in the present application.

[0066] like Figure 1 As shown, the method for determining the vehicle turning angle of the embodiment of the present application may specifically include the following steps:

[0067] S1, obtain the driving boundary corresponding to the current vehicle.

[0068] Among them, there is a risk of collision between the driving boundary and the current vehicle.

[0069] The method for determining the vehicle turning angle provided in the present application is mainly performed by a turning angle determination device. In some embodiments, the turning angle determination device may be the domain controller itself. In some embodiments, the turning angle determination device may be a device that is communicatively connected to the domain controller. For example, the device may be a device for monitoring images, a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, and an autonomous vehicle, a robot, a security system, or any one or more products of glasses and helmets for augmented reality or virtual reality. In some possible implementations, the method for determining the vehicle turning angle may be implemented by a processor calling computer-readable instructions stored in a memory.

[0070] In some embodiments, the travel boundary is a line segment.

[0071] Exemplarily, the driving boundary may be formed by a dynamic obstacle (such as a pedestrian, a motor vehicle or a non-motor vehicle), and the turning angle determination device determines the driving boundary based on the current position, current direction, current speed, and a preset time.

[0072] Exemplarily, the driving boundary may be formed by a static obstacle (such as a road edge), and the turning angle determination device determines the turning angle based on polynomial fitting of the road edge and further performing a straightening operation on the obtained polynomial.

[0073] In some embodiments, the turning angle determination device determines the driving boundary through the vehicle-mounted sensor or perception map of the current vehicle. Optionally, the perception map can be a map collected in advance, or a map constructed in real time by the current vehicle. In some possible embodiments, the perception map is a high-precision map. Optionally, the vehicle-mounted sensor can be one or more of a vehicle-mounted camera, a millimeter-wave radar, a laser radar, and an ultrasonic radar.

[0074] In actual scenarios, the turning angle determination device can obtain several driving boundaries. It should be noted that some driving boundaries may be far away from the current vehicle in the lateral direction, and the current vehicle may not collide with these driving boundaries. In addition, considering the possibility of false alarms of vehicle-mounted sensors. In some embodiments, the turning angle determination device obtains several candidate driving boundaries, and screens out driving boundaries that have a risk of collision with the current vehicle based on the starting point, end point, and confidence level of the candidate driving boundaries. More specifically, the turning angle determination device determines the angle between the extension direction of the candidate driving boundary and the front direction of the current vehicle based on the starting point and end point of the candidate driving boundary, and determines the lateral distance between the candidate driving boundary and the current vehicle. If the lateral distance is less than a certain threshold distance and the angle is less than a certain threshold angle, the candidate driving boundary is determined to be a driving boundary. Among them, the confidence level is the detection confidence level of the sensor.

[0075] S2, constructing a vehicle motion curve equation by combining a reference straight line corresponding to the driving boundary, a first position and a first orientation of the current vehicle.

[0076] The curve point corresponding to the first position is tangent to the target straight line corresponding to the first orientation, and the distance between the curve formed by the vehicle motion curve equation and the reference straight line gradually decreases in the extension direction of the reference straight line.

[0077] It should be noted that the vehicle motion curve equation is constructed in the world coordinate system.

[0078] In some possible embodiments, the curve is infinitely close to the reference straight line in the extension direction of the reference straight line. That is, in this embodiment, if the current vehicle runs along the curve, it will not collide with the driving boundary.

[0079] Alternatively, the curve may be a hyperbolic spiral curve, an Archimedean spiral, a logarithmic spiral, or a hyperbola.

[0080] S3, solving the vehicle motion curve equation to obtain parameters in the vehicle motion curve equation.

[0081] Exemplarily, the turning angle determination device uses Newton's method or a variant of Newton's method to solve the vehicle motion curve equation to obtain parameters in the vehicle motion curve equation. Optionally, the variant of Newton's method can be a Gauss-Newton method or a gradient descent method. In some possible embodiments, the turning angle determination device can also use a neural network method to solve the vehicle motion curve equation.

[0082] S4, calculating the vehicle turning angle using the parameters.

[0083] Among them, the vehicle turning angle is used to prevent the current vehicle from colliding with the driving boundary.

[0084] In some embodiments, the turning angle determining device determines the front wheel turning angle of the current vehicle according to the parameters. Further, the current vehicle will not collide with the driving boundary when driving according to the front wheel turning angle.

[0085] The above scheme obtains the driving boundary with the risk of collision with the current vehicle; constructs the vehicle motion curve equation according to the position and orientation of the current vehicle and the reference straight line corresponding to the driving boundary; solves the vehicle motion curve equation to obtain the parameters in the vehicle motion curve equation, and uses the parameters to determine the turning angle used to prevent the current vehicle from colliding with the driving boundary. By constructing the vehicle motion curve equation in combination with the driving boundary, the control boundary can be planned in advance, and when the current vehicle is driving at the vehicle turning angle determined by the vehicle turning angle determination method provided in this application, the probability of collision with the driving boundary can be effectively reduced, thereby improving the driving safety of the current vehicle.

[0086] Another embodiment of the method for determining a vehicle turning angle provided by the present application may specifically include the following steps:

[0087] S11, obtaining the driving boundary corresponding to the current vehicle.

[0088] S12, constructing a vehicle motion curve equation by combining a reference straight line corresponding to the driving boundary, a first position and a first orientation of the current vehicle.

[0089] S13, constructing a first function related to the relative angle in combination with the vehicle motion curve equation.

[0090] The relative angle represents the angle between the target straight line and the driving boundary.

[0091] like Figure 2As shown, the equation of the straight line corresponding to the driving boundary is y=a, and the relative angle between the target straight line and the driving boundary is θ0.

[0092] It can be understood that the relative angle is a pre-obtained value.

[0093] Exemplarily, the curve corresponding to the vehicle motion curve equation is a hyperbolic helix. Then, in the world coordinate system, the vehicle motion curve equation satisfies the following relationship:

[0094]

[0095] Among them, a is the curve parameter to be calculated, is the first parameter equation, is the second parameter equation.

[0096] In order to ensure curvature continuity, the first orientation of the current vehicle is tangent to the hyperbolic helix, so the position of the curve point on the curve is indirectly determined.

[0097] In some possible embodiments, the relative angle between the current vehicle and the driving boundary also satisfies the following relationship:

[0098]

[0099] Furthermore, the turning angle determining device constructs a first function according to the tangent value of the relative angle and the vehicle motion curve equation.

[0100] In some embodiments, the first function satisfies the following relationship:

[0101] f(θ)=θcosθ-sinθ+tanθ0(θsinθ+cosθ)

[0102] It can be understood that the rotation angle determination device needs to calculate θ when f(θ)=0.

[0103] S14, solving the first function within the definition domain of the relative angle.

[0104] It should be noted that f(θ) is a nonlinear equation and is difficult to solve using conventional methods. Therefore, the rotation angle determination device can use Newton's method or its variants, or other nonlinear solution methods to solve f(θ).

[0105] S15: When the absolute value of the first output result of the first function is smaller than a preset result, the relative angle used by the first function is determined as a target independent variable.

[0106] Specifically, when |f(θ)|<ε is satisfied, θ at this time is the target independent variable.

[0107] Among them, ε is the preset result, and f(θ) is the first output result.

[0108] In some embodiments, the preset result ε is a number slightly greater than 0. Exemplarily, ε is 1e-5.

[0109] It should be noted that the target independent variable is the angle value of the target vehicle in the polar coordinate system at the current moment.

[0110] S16, using the target independent variable to obtain the parameters in the vehicle motion curve equation.

[0111] In some embodiments, such as Figure 2 As shown, the turning angle determination device obtains the distance c0 between the curve point and the driving boundary. Further, the turning angle determination device uses the target independent variable and the distance c0 to determine the parameter a in the vehicle motion curve equation.

[0112] Specifically, according to the Cartesian coordinate system equation, the parameter a satisfies the following relationship:

[0113]

[0114] After sorting, we can get:

[0115]

[0116] S17, calculating the vehicle turning angle using the parameters.

[0117] The above scheme obtains the driving boundary with the risk of collision with the current vehicle; constructs the vehicle motion curve equation according to the position and orientation of the current vehicle and the reference straight line corresponding to the driving boundary; solves the vehicle motion curve equation to obtain the parameters in the vehicle motion curve equation, and uses the parameters to determine the turning angle used to prevent the current vehicle from colliding with the driving boundary. By constructing the vehicle motion curve equation in combination with the driving boundary, the control boundary can be planned in advance, and when the vehicle is driving at the vehicle turning angle determined by the vehicle turning angle determination method provided in this application, the probability of collision with the driving boundary can be effectively reduced, thereby improving the driving safety of the current vehicle.

[0118] Another embodiment of the method for determining a vehicle turning angle provided by the present application may specifically include the following steps:

[0119] S21, obtaining the driving boundary corresponding to the current vehicle.

[0120] S22, constructing a vehicle motion curve equation by combining a reference straight line corresponding to the driving boundary, a first position and a first orientation of the current vehicle.

[0121] S23, constructing a first function related to the relative angle in combination with the vehicle motion curve equation.

[0122] S24, randomly selecting the relative angle within the definition domain.

[0123] The rotation angle determination device randomly selects an initial value within the definition domain as the relative angle.

[0124] Among them, the target domain is (0, π / 2).

[0125] S25, inputting the relative angle into the first function to obtain the first output result, and inputting the relative angle into a second function to obtain a second output result.

[0126] The second function is a first-order derivative function of the first function.

[0127] In some embodiments, the first output result can be expressed as f(θ), and the second output result can be expressed as Here, θ is the relative angle.

[0128] S26, in response to the absolute value of the first output result being greater than or equal to the preset result, and the absolute value of the second output result being less than the preset result, the relative angle is randomly selected again within the definition domain, and the first function is continued to be solved.

[0129] In some embodiments, when |f(θ)|≥ε is satisfied, and This means that the problem may have fallen into a saddle point, which may cause the solution of the first function to diverge or converge too slowly.

[0130] Based on this, by reselecting the relative angle, we can avoid falling into the saddle point and improve the accuracy or efficiency of the solution.

[0131] S27, in response to the absolute value of the first output result being greater than or equal to the preset result, and the absolute value of the second output result being greater than or equal to the preset result, the relative angle is iterated using the first output result and the second output result to obtain an iterated relative angle.

[0132] In some embodiments, when |f(θ)|≥ε is satisfied, and The rotation angle determination device uses f(θ) and The value of θ is iterated to obtain the relative angle θ′ after iteration.

[0133] In some embodiments, S27 may specifically include the following sub-steps:

[0134] S271, in response to the absolute value of the first output result being greater than or equal to the preset result, calculating the quotient of the first output result and the second output result to obtain an iterative change amount.

[0135] Specifically, when |f(Ω)|≥ε, and When the angle determination device calculates the quotient of the first output result and the second output result, the iterative change amount is obtained.

[0136] Among them, the iterative change amount satisfies the following relationship:

[0137]

[0138] Among them, () is the first output result, is the second output result.

[0139] S272, calculating the difference between the relative angle and the iterative change amount to obtain the relative angle after the iteration.

[0140] Specifically, the rotation angle determination device calculates the difference between the relative angle and the iterative change amount to obtain the relative angle after iteration.

[0141] Among them, the relative angle after iteration satisfies the following relationship:

[0142]

[0143] Among them, Ω′ is the relative angle after iteration, and Ω is the relative angle.

[0144] S28, in response to the relative angle after iteration being within the definition domain, continue to solve the first function using the relative angle after iteration.

[0145] In order to prevent the relative angle Ω′ after iteration from being outside the definition domain, the rotation angle determination device also needs to verify it. Specifically, when When , the rotation angle determination device uses θ′ to continue solving the first function.

[0146] S29, in response to the relative angle after iteration being outside the definition domain, randomly reselecting the relative angle from within the definition domain, and continuing to solve the first function.

[0147] Specifically, in response to the relative angle after iteration being outside (0, π / 2), the rotation angle determination device randomly re-selects a relative angle within (0, π / 2), and continues to solve the first function using the selected relative angle.

[0148] By checking the independent variables after iteration, it is possible to avoid solving the target independent variables outside the target definition domain.

[0149] S30: When the absolute value of the first output result of the first function is smaller than a preset result, the relative angle used by the first function is determined as a target independent variable.

[0150] S31, using the target independent variable to obtain parameters in the vehicle motion curve equation.

[0151] S32: Calculate the vehicle turning angle using the parameters.

[0152] The above scheme obtains the driving boundary with the risk of collision with the current vehicle; constructs the vehicle motion curve equation according to the position and orientation of the current vehicle and the reference straight line corresponding to the driving boundary; solves the vehicle motion curve equation to obtain the parameters in the vehicle motion curve equation, and uses the parameters to determine the turning angle used to prevent the current vehicle from colliding with the driving boundary. By constructing the vehicle motion curve equation in combination with the driving boundary, the control boundary can be planned in advance, and when the vehicle is driving at the vehicle turning angle determined by the vehicle turning angle determination method provided in this application, the probability of collision with the driving boundary can be effectively reduced, thereby improving the driving safety of the current vehicle.

[0153] Another embodiment of the method for determining a vehicle turning angle provided by the present application may specifically include the following steps:

[0154] S41, obtaining a driving boundary corresponding to the current vehicle.

[0155] S42, constructing a vehicle motion curve equation by combining a reference straight line corresponding to the driving boundary, a first position and a first orientation of the current vehicle.

[0156] S43, constructing a first function related to the relative angle in combination with the vehicle motion curve equation.

[0157] S44, randomly selecting the relative angle within the definition domain.

[0158] S45, inputting the relative angle into the first function to obtain the first output result.

[0159] S46, inputting the relative angle into the second function to obtain a candidate result.

[0160] The second function is the first-order derivative function of the first function.

[0161] In this embodiment, the candidate results are represented as

[0162] S47: In response to the candidate result being smaller than a target gradient and the candidate result being greater than or equal to the preset result, taking the target gradient as the second output result.

[0163] In some embodiments, the target gradient is represented by k min , where the target gradient is greater than 0.

[0164] In some embodiments, when and When , the turning angle determination device takes the target gradient as the second output result, that is:

[0165]

[0166] in, is the second output result.

[0167] S48, in response to the absolute value of the first output result being greater than or equal to the preset result, and the absolute value of the second output result being less than the preset result, the relative angle is randomly selected again within the definition domain, and the first function is continued to be solved.

[0168] S49, in response to the absolute value of the first output result being greater than or equal to the preset result, and the absolute value of the second output result being greater than or equal to the preset result, the relative angle is iterated using the first output result and the second output result to obtain an iterated relative angle.

[0169] S50: In response to the relative angle after iteration being within the definition domain, continue to solve the first function using the relative angle after iteration.

[0170] S51, in response to the relative angle after iteration being outside the definition domain, randomly reselecting the relative angle from within the definition domain, and continuing to solve the first function.

[0171] S52: When the absolute value of the first output result of the first function is smaller than a preset result, the relative angle used by the first function is determined as a target independent variable.

[0172] S53, using the target independent variable to obtain the parameters in the vehicle motion curve equation.

[0173] S54, calculating the vehicle turning angle using the parameters.

[0174] The above scheme obtains the driving boundary with the risk of collision with the current vehicle; constructs the vehicle motion curve equation according to the position and orientation of the current vehicle and the reference straight line corresponding to the driving boundary; solves the vehicle motion curve equation to obtain the parameters in the vehicle motion curve equation, and uses the parameters to determine the turning angle used to prevent the current vehicle from colliding with the driving boundary. By constructing the vehicle motion curve equation in combination with the driving boundary, the control boundary can be planned in advance, and when the vehicle is driving at the vehicle turning angle determined by the vehicle turning angle determination method provided in this application, the probability of collision with the driving boundary can be effectively reduced, thereby improving the driving safety of the current vehicle.

[0175] Another embodiment of the method for determining a vehicle turning angle provided by the present application may specifically include the following steps:

[0176] S61, obtaining a driving boundary corresponding to the current vehicle.

[0177] S62, constructing a vehicle motion curve equation by combining a reference straight line corresponding to the driving boundary, a first position and a first orientation of the current vehicle.

[0178] S63, constructing a first function related to the relative angle in combination with the vehicle motion curve equation.

[0179] S64, randomly selecting the relative angle within the definition domain.

[0180] S65: Input the relative angle into the first function to obtain the first output result.

[0181] S66: Input the relative angle into the second function to obtain a candidate result.

[0182] The second function is the first-order derivative function of the first function.

[0183] In this embodiment, the candidate results are represented as

[0184] S67: In response to the candidate result being smaller than a target gradient and the candidate result being greater than or equal to the preset result, taking the target gradient as the second output result.

[0185] Specifically, satisfy and When , the turning angle determination device uses the negative value of the target gradient as the second output result. is the candidate result. That is:

[0186]

[0187] in, is the second output result.

[0188] S68, in response to the absolute value of the first output result being greater than or equal to the preset result, and the absolute value of the second output result being less than the preset result, the relative angle is randomly selected again within the definition domain, and the first function is continued to be solved.

[0189] S69, in response to the absolute value of the first output result being greater than or equal to the preset result, and the absolute value of the second output result being greater than or equal to the preset result, the relative angle is iterated using the first output result and the second output result to obtain an iterated relative angle.

[0190] S70: In response to the relative angle after iteration being within the definition domain, continue to solve the first function using the relative angle after iteration.

[0191] S71, in response to the relative angle after iteration being outside the definition domain, randomly reselecting the relative angle from within the definition domain, and continuing to solve the first function.

[0192] S72: When the absolute value of the first output result of the first function is smaller than a preset result, determine the relative angle used by the first function as a target independent variable.

[0193] S73, using the target independent variable to obtain parameters in the vehicle motion curve equation.

[0194] S74, calculating the vehicle turning angle using the parameters.

[0195] The above scheme obtains the driving boundary with the risk of collision with the current vehicle; constructs the vehicle motion curve equation according to the position and orientation of the current vehicle and the reference straight line corresponding to the driving boundary; solves the vehicle motion curve equation to obtain the parameters in the vehicle motion curve equation, and uses the parameters to determine the turning angle used to prevent the current vehicle from colliding with the driving boundary. By constructing the vehicle motion curve equation in combination with the driving boundary, the control boundary can be planned in advance, and when the vehicle is driving at the vehicle turning angle determined by the vehicle turning angle determination method provided in this application, the probability of collision with the driving boundary can be effectively reduced, thereby improving the driving safety of the current vehicle.

[0196] Another embodiment of the method for determining a vehicle turning angle provided by the present application may specifically include the following steps:

[0197] S81, obtaining the driving boundary corresponding to the current vehicle.

[0198] Among them, there is a risk of collision between the driving boundary and the current vehicle.

[0199] S82, constructing a vehicle motion curve equation by combining a reference straight line corresponding to the driving boundary, a first position and a first orientation of the current vehicle.

[0200] The curve point corresponding to the first position is tangent to the target straight line corresponding to the first orientation, and the distance between the curve formed by the vehicle motion curve equation and the reference straight line gradually decreases in the extension direction of the reference straight line.

[0201] S83, solving the vehicle motion curve equation to obtain parameters in the vehicle motion curve equation.

[0202] S84, using the parameters, calculating the target curvature of the curve at the curve point.

[0203] In some embodiments, the vehicle motion curve equation is a hyperbolic helix equation, and the curve formed by the vehicle motion curve equation is a hyperbolic helix. Further, the parameter obtained in S83 is the target parameter a.

[0204] In some embodiments, the target curvature satisfies the following relationship:

[0205]

[0206] in, is the first derivative of the first parametric equation, is the first derivative of the second parametric equation, is the second-order derivative of the first parametric equation, is the second derivative of the second parametric equation.

[0207] Furthermore, the first derivative of the first parametric equation is First derivative of the second parametric equation The following relations are satisfied:

[0208]

[0209] Second derivative of the first parametric equation Second Derivative of the Second Parametric Equation The following relations are satisfied:

[0210]

[0211] Similarly, if the vehicle motion curve equation is an Archimedean spiral, a logarithmic spiral, or a hyperbola, the target curvature of the curve at the curve point can also be determined according to the above method.

[0212] S85, determining a rear wheel slip angle compensation angle of the current vehicle by using the target curvature, a first distance from the center of mass to the front axle of the vehicle, the mass of the current vehicle, the current speed of the current vehicle, the equivalent cornering stiffness of the left and right wheels on the rear axle, and the wheelbase of the current vehicle.

[0213] Specifically, the rear wheel slip angle compensation angle of the current vehicle satisfies the following relationship:

[0214]

[0215] Among them, δ β is the rear wheel slip angle compensation angle, l f is the first distance from the center of mass of the current vehicle to the front axle of the current vehicle, m is the mass of the current vehicle (the mass of the entire vehicle), v is the current speed, C r is the equivalent cornering stiffness of the left and right wheels on the rear axle, and l is the wheelbase of the current vehicle.

[0216] Among them, the rear wheel slip angle compensation angle, the first distance, the equivalent cornering stiffness of the left and right wheels of the rear axle, and the wheelbase can be calibrated in advance.

[0217] S86, determining the understeering degree of the current vehicle by using the first distance, mass, equivalent cornering stiffness of the left and right wheels on the rear axle, wheelbase, a second distance from the center of mass to the rear axle of the vehicle, and equivalent cornering stiffness of the left and right wheels on the front axle.

[0218] Specifically, the understeer degree of the current vehicle satisfies the following relationship:

[0219]

[0220] Among them, K v is the understeer degree, C f It is the second distance from the center of mass of the current vehicle to the rear axle of the current vehicle.

[0221] Among them, the second distance and the equivalent cornering stiffness of the left and right wheels of the front axle can be calibrated in advance.

[0222] S87, calculating the vehicle turning angle by using the turning angle effect coefficient, the target curvature, the wheelbase, the understeering degree, the current speed, and the rear wheel side slip angle compensation angle.

[0223] Specifically, the vehicle turning angle satisfies the following relationship:

[0224] δ=K(kl+K v kv 2 +δ β )

[0225] Wherein, δ is the vehicle turning angle. K is the turning angle effect coefficient, which can be calibrated in advance.

[0226] It should be noted that the vehicle turning angle is the theoretical front wheel turning angle of the current vehicle.

[0227] The above scheme obtains the driving boundary with the risk of collision with the current vehicle; constructs the vehicle motion curve equation according to the position and orientation of the current vehicle and the reference straight line corresponding to the driving boundary; solves the vehicle motion curve equation to obtain the parameters in the vehicle motion curve equation, and uses the parameters to determine the turning angle used to prevent the current vehicle from colliding with the driving boundary. By constructing the vehicle motion curve equation in combination with the driving boundary, the control boundary can be planned in advance, and when the vehicle is driving at the vehicle turning angle determined by the vehicle turning angle determination method provided in this application, the probability of collision with the driving boundary can be effectively reduced, thereby improving the driving safety of the current vehicle.

[0228] Another embodiment of the method for determining a vehicle turning angle provided by the present application may specifically include the following steps:

[0229] S91, obtaining a driving boundary corresponding to the current vehicle.

[0230] There is a collision risk between the driving boundary and the current vehicle. The driving boundary includes a plurality of left driving boundaries and a plurality of right driving boundaries. The vehicle turning angle includes a vehicle left turning angle and a vehicle right turning angle.

[0231] S92, constructing a vehicle motion curve equation by combining a reference straight line corresponding to the driving boundary, a first position and a first orientation of the current vehicle.

[0232] The curve point corresponding to the first position is tangent to the target straight line corresponding to the first orientation, and the distance between the curve formed by the vehicle motion curve equation and the reference straight line gradually decreases in the extension direction of the reference straight line.

[0233] S93, solving the vehicle motion curve equation to obtain parameters in the vehicle motion curve equation.

[0234] S94, using the parameters of the vehicle motion curve equation corresponding to each of the left driving boundaries, calculate a plurality of candidate vehicle left turn angles.

[0235] Among them, the left turn angle of the candidate vehicle is a positive number.

[0236] In some embodiments, multiple candidate vehicle left turn angles may be represented as:

[0237]

[0238] in, is the candidate vehicle left turn angle, i=1,…,m, m is a positive integer greater than 1.

[0239] It should be noted that the left driving boundary is a driving boundary relative to the left side of the current vehicle.

[0240] S95, using the parameters of the vehicle curve motion equation corresponding to each of the right driving boundaries, calculate a plurality of candidate vehicle right turn angles.

[0241] Wherein, the right turn angle of the candidate vehicle is a negative number.

[0242] In some embodiments, the candidate vehicle right turn angle satisfies the following relationship:

[0243]

[0244] in, is the candidate vehicle right turn angle, i=1,...,n, where n is a positive integer greater than 1.

[0245] Likewise, the right driving boundary is a driving boundary relative to the right side of the current vehicle.

[0246] S96, selecting a smallest one from the plurality of candidate left-turn angles of the vehicle as the left-turn angle of the vehicle.

[0247] In order to avoid the current vehicle from colliding with any left driving boundary, the turning angle determination device selects the smallest candidate vehicle left turning angle from multiple candidate vehicle left turning angles as the vehicle left turning angle

[0248] In some embodiments, at the current position (time), the vehicle left turn angle of the current vehicle satisfies the following relationship:

[0249]

[0250] In some application scenarios, the left turn angle of the vehicle at each moment may have a small discontinuity in curvature due to the minimization operation. The turning angle determination device filters the left turn angle of the vehicle obtained at each moment to ensure a smooth curve.

[0251] That is, the left turn angle of the vehicle at each moment satisfies the following relationship:

[0252] δ l =filter(δ l )

[0253] Exemplarily, the filtering operation may be a Kalman filter, a fastest tracking filter, etc., which is not limited here.

[0254] S97, selecting a largest one from the plurality of candidate right turn angles of the vehicle as the right turn angle of the vehicle.

[0255] Since the candidate vehicle right turn angle is a negative number, in order to avoid the current vehicle from colliding with any right driving boundary, the turning angle determination device selects the largest candidate vehicle right turn angle from multiple candidate vehicle right turn angles as the vehicle right turn angle.

[0256] In some embodiments, at the current position (time), the right turn angle of the current vehicle satisfies the following relationship:

[0257]

[0258] Among them, δ r The vehicle turns right.

[0259] Similarly, the right turn angle of the vehicle at each moment may have a small discontinuous curvature problem due to the maximum operation. The turning angle determination device filters the right turn angle of the vehicle obtained at each moment to ensure a smooth curve.

[0260] That is, the right turn angle of the vehicle at each moment satisfies the following relationship:

[0261] δ r=filter(δ r )

[0262] Exemplarily, the filtering operation may be a Kalman filter, a fastest tracking filter, etc., which is not limited here.

[0263] The above scheme obtains the driving boundary with the risk of collision with the current vehicle; constructs the vehicle motion curve equation according to the position and orientation of the current vehicle and the reference straight line corresponding to the driving boundary; solves the vehicle motion curve equation to obtain the parameters in the vehicle motion curve equation, and uses the parameters to determine the turning angle used to prevent the current vehicle from colliding with the driving boundary. By constructing the vehicle motion curve equation in combination with the driving boundary, the control boundary can be planned in advance, and when the vehicle is driving at the vehicle turning angle determined by the vehicle turning angle determination method provided in this application, the probability of collision with the driving boundary can be effectively reduced, thereby improving the driving safety of the current vehicle.

[0264] Another embodiment of the method for determining a vehicle turning angle provided by the present application may specifically include the following steps:

[0265] S101, obtaining a driving boundary according to a second position, a second orientation and a running speed corresponding to the dynamic obstacle.

[0266] Optionally, the dynamic obstacle may be at least one of a motor vehicle, a pedestrian, and a non-motor vehicle.

[0267] like Figure 3 As shown, Figure 3 The side car in the figure is a dynamic obstacle. The side car is located on the right side of the current vehicle. Therefore, the position of the left rear side of the side car is taken as the second position, and the current direction of the side car is taken as the second direction. According to the running speed of the side car, a certain time domain is extended forward to obtain the driving boundary. Among them, "forward" here means along the second direction. Exemplarily, the length of the driving boundary is the product of the running speed and the preset time length. For example, the preset time can be between 1s and 10s.

[0268] exist Figure 3 In the figure, the driving boundary corresponding to the adjacent vehicle is boundary 3.

[0269] The driving boundary is a line segment.

[0270] S102, constructing a vehicle motion curve equation by combining a reference straight line corresponding to the driving boundary, a first position and a first orientation of the current vehicle.

[0271] S103, solving the vehicle motion curve equation to obtain parameters in the vehicle motion curve equation.

[0272] S104, calculating the vehicle turning angle using the parameters.

[0273] The above scheme obtains the driving boundary with the risk of collision with the current vehicle; constructs the vehicle motion curve equation according to the position and orientation of the current vehicle and the reference straight line corresponding to the driving boundary; solves the vehicle motion curve equation to obtain the parameters in the vehicle motion curve equation, and uses the parameters to determine the turning angle used to prevent the current vehicle from colliding with the driving boundary. By constructing the vehicle motion curve equation in combination with the driving boundary, the control boundary can be planned in advance, and when the vehicle is driving at the vehicle turning angle determined by the vehicle turning angle determination method provided in this application, the probability of collision with the driving boundary can be effectively reduced, thereby improving the driving safety of the current vehicle.

[0274] Another embodiment of the method for determining a vehicle turning angle provided by the present application may specifically include the following steps:

[0275] S111, obtaining at least one driving boundary corresponding to a road edge.

[0276] like Figure 3 As shown, the road edge is a curve. The turning angle determination device obtains a polynomial equation for representing the road edge. Further, the turning angle determination device divides the curve into two segmented line segments. Each segmented line segment corresponds to a driving boundary.

[0277] In some possible embodiments, if the road edge is a straight line, the turning angle determination device obtains a driving boundary corresponding to the road edge. In some possible application scenarios, the length of a single driving boundary is not greater than a certain length threshold. The turning angle determination device can divide the driving boundary greater than the length threshold into multiple driving boundaries.

[0278] S112, constructing a vehicle motion curve equation by combining a reference straight line corresponding to the driving boundary, a first position and a first orientation of the current vehicle.

[0279] S113, solving the vehicle motion curve equation to obtain parameters in the vehicle motion curve equation.

[0280] S114, calculating the vehicle turning angle using the parameters.

[0281] The above scheme obtains the driving boundary with the risk of collision with the current vehicle; constructs the vehicle motion curve equation according to the position and orientation of the current vehicle and the reference straight line corresponding to the driving boundary; solves the vehicle motion curve equation to obtain the parameters in the vehicle motion curve equation, and uses the parameters to determine the turning angle used to prevent the current vehicle from colliding with the driving boundary. By constructing the vehicle motion curve equation in combination with the driving boundary, the control boundary can be planned in advance, and when the vehicle is driving at the vehicle turning angle determined by the vehicle turning angle determination method provided in this application, the probability of collision with the driving boundary can be effectively reduced, thereby improving the driving safety of the current vehicle.

[0282] Another embodiment of the method for determining a vehicle turning angle provided by the present application may specifically include the following steps:

[0283] S121, obtaining a driving boundary according to a second position, a second orientation, and a running speed corresponding to the dynamic obstacle.

[0284] S122: Obtain at least one driving boundary corresponding to a road edge.

[0285] S123, constructing a vehicle motion curve equation by combining a reference straight line corresponding to the driving boundary, a first position and a first orientation of the current vehicle.

[0286] S124, solving the vehicle motion curve equation to obtain parameters in the vehicle motion curve equation.

[0287] S125, calculating the vehicle turning angle using the parameters.

[0288] The above scheme obtains the driving boundary with the risk of collision with the current vehicle; constructs the vehicle motion curve equation according to the position and orientation of the current vehicle and the reference straight line corresponding to the driving boundary; solves the vehicle motion curve equation to obtain the parameters in the vehicle motion curve equation, and uses the parameters to determine the turning angle used to prevent the current vehicle from colliding with the driving boundary. By constructing the vehicle motion curve equation in combination with the driving boundary, the control boundary can be planned in advance, and when the vehicle is driving at the vehicle turning angle determined by the vehicle turning angle determination method provided in this application, the probability of collision with the driving boundary can be effectively reduced, thereby improving the driving safety of the current vehicle.

[0289] See also Figure 4 , Figure 4 It is a flowchart diagram of another embodiment of the method for determining a vehicle turning angle provided in the present application.

[0290] like Figure 4 As shown, another embodiment of the method for determining a vehicle turning angle provided by the present application may specifically include the following steps:

[0291] S201, determine the road boundary using the vehicle-mounted sensor.

[0292] In some embodiments, the vehicle-mounted sensors include but are not limited to cameras, millimeter wave radars, laser radars, and ultrasonic radars. In some embodiments, the turning angle determination device can output obstacle targets and polynomial boundaries corresponding to the roadside (i.e., the roadside is represented in the form of a polynomial) by sensing the map.

[0293] like Figure 3As shown, after obtaining the obstacle target and the polynomial boundary, the turning angle determination device constructs the obstacle target in the form of a piecewise straight line, and converts the polynomial boundary into multiple piecewise straight lines. Taking the obstacle vehicle as an example, the starting point of the position of the adjacent vehicle and the speed of the adjacent vehicle are obtained, and according to the direction of the adjacent vehicle and the above information, a certain time domain is extended forward to obtain the line segment corresponding to the adjacent vehicle.

[0294] Furthermore, the turning angle determination device determines whether the line segment will interfere with the driving path of the vehicle based on the starting point, end point, and detection confidence of the adjacent vehicle of the line segment. Furthermore, the turning angle determination device retains the boundary line segment that has recently interfered with the driving of the vehicle. Figure 2 In the scene, boundary 1, boundary 2, and boundary 3 are screened and retained. Then, based on the angle relationship and lateral position relationship between the screened line segment and the vehicle, boundaries with potential collision risks are screened, such as boundary 1 and boundary 3. Boundary 1 and boundary 3 are road boundaries. Furthermore, road boundaries correspond to the driving boundaries mentioned above.

[0295] S202, taking the road boundary as a reference straight line, constructing a hyperbolic helix equation, and determining a constructor using the hyperbolic helix equation.

[0296] Specifically, the polar coordinate expression of the hyperbolic helix is ​​as follows:

[0297]

[0298] Where ρ represents the polar diameter, which is the distance from a certain point on the hyperbolic spiral line to the origin, a is the curve parameter, and θ is the angle between the point on the curve and the positive x-axis, with a value range of (0, 2π).

[0299] Hyperbolic helix curve Figure 4 As shown in the middle curve, it contains two significant features:

[0300] 1. In the process from 2π to 0 in the domain, it is infinitely close to the reference line y=a, and the reference line is Figure 3 The straight line in .

[0301] 2. In the process from 2π to 0 within the definition domain, the curvature continues to decrease.

[0302] Therefore, if the road boundary is represented by a straight line, the curve is the optimal vehicle motion boundary where vehicles will not collide in theory.

[0303] like Figure 2 As shown, in order to ensure the curvature continuity, the orientation of the vehicle should be tangent to the hyperbolic helix, so the position of the vehicle on the curve is indirectly determined. c0 and θ0 are known values.

[0304] The Cartesian coordinate system expression of the hyperbolic helix is ​​as follows:

[0305]

[0306] Its first-order derivative expression is as follows:

[0307]

[0308] Combining the angle between the vehicle and the road boundary, we get the equation:

[0309]

[0310] Constructing the constructor:

[0311] f(θ)=θcosθ-sinθ+tanθ0(θsinθ+cosθ)

[0312] That is, f(θ)=0 is satisfied, and we can solve for θ.

[0313] S203, solving the constructor to determine the parameters of the hyperbolic spiral curve.

[0314] However, f(θ) is a nonlinear equation and is difficult to solve using traditional methods, so the Newton iteration method or its variants are designed to solve it.

[0315] The principle of Newton iteration method is as follows Figure 5 As shown in the figure, take any point on the curve in the definition domain as the initial solution, make an auxiliary straight line along the tangent direction of the curve through the initial solution, and take the intersection with the x-axis as the new initial solution. After several iterations, the initial solution will gradually converge to the real solution. Figure 5 Taking point 1 as the starting point, after 4 iterations, the solution obtained is very close to the true solution. The iteration order is 1->2->3->4.

[0316] Specifically, the Newton iteration method requires the first-order derivative of the constructor, which is expressed as follows:

[0317]

[0318] The curve passes through the point (θ, f(θ)) and the slope is The coordinates of the intersection of the straight line and the x-axis are:

[0319]

[0320] In actual use, f(θ) may have a saddle point, or the solution may diverge or converge too slowly due to unreasonable initial value selection. Therefore, a saddle point escape mechanism and an iterative value verification mechanism are added. If the verification fails, random sampling is performed within the definition domain to reselect the initial value. Since the angle determination method provided in this application is mainly to solve the side collision problem, the θ definition domain can be determined as

[0321] The pseudo code of the entire solution process is as follows:

[0322] Select any initial value θ in the definition domain, set the minimum value ε (ε>0), and set the minimum gradient k min (k min >0).

[0323] for i in iteration_num:

[0324] if abs(f(θ))<ε:

[0325] break;

[0326] if

[0327] Random sampling within the domain redefines θ,

[0328] Continue;

[0329] if and

[0330]

[0331] if and

[0332]

[0333] Update iteration value

[0334] If θ is out of domain:

[0335] Random sampling within the domain redefines θ,

[0336] Continue;

[0337] After several Newton iterations, the current vehicle position θ in the polar coordinate system can be obtained, and then according to the Cartesian coordinate system equation:

[0338]

[0339] The hyperbolic spiral curve parameter a can be solved:

[0340]

[0341] S204, solving the curvature of the hyperbolic spiral curve at the position of the vehicle, and using the curvature to determine the front wheel turning angle of the vehicle.

[0342] The calculation of the theoretical front wheel steering angle requires the construction of the second-order derivative function, which is expressed as follows:

[0343]

[0344] The curvature of the hyperbolic helix at the vehicle position satisfies the following relationship:

[0345]

[0346] The curvature is the target curvature.

[0347] Furthermore, the front wheel turning angle satisfies the following relationship:

[0348]

[0349] Among them l f is the distance from the center of mass to the front axle, l r is the distance from the center of mass to the rear axle, l is the wheelbase, C f is the equivalent cornering stiffness of the left and right wheels of the front axle, C r is the equivalent cornering stiffness of the left and right wheels of the rear axle, m is the vehicle mass, v is the vehicle speed, δ β is the rear wheel slip angle compensation angle, K v is the understeering degree. K is the steering angle effect coefficient, which is a real vehicle calibration value and is used to correct the model error introduced by inaccurate vehicle parameters. Further, the front wheel steering angle corresponds to the wheel steering angle mentioned above.

[0350] S205, performing effective value judgment on the obtained front wheel turning angle, and performing post-processing on the front wheel turning angle to obtain a front wheel left turning angle and a front wheel right turning angle.

[0351] Since the Newton iteration method is used for solving, there is a very small possibility that no valid solution may be iterated. And the parameter a has a clear physical meaning, indicating the lateral position distance of the asymptote. By judging the rationality of the calculation of a, some calculations brought in by abnormal boundary conditions can be filtered out. For unilateral constraints, there may be multiple road edges, so there are multiple valid turning angle values, such as Figure 6 Take the left boundary as an example, in the left positive and right negative coordinate system, take the minimum value in the left boundary corner set:

[0352]

[0353] The final boundary is Figure 6 At the intersection of the two hyperbolic spirals, due to the minimization operation, there will be a small discontinuity in curvature, so filtering is required to ensure that the boundary is always smooth.

[0354] δ l =filter(δ l )

[0355] Similarly, the right corner boundary should take the maximum value in the right corner boundary set:

[0356]

[0357] δ r =filter(δ r )

[0358] When the current vehicle turns on the intelligent driving function, the turning angle determination device takes a cutoff value based on the calculated steering wheel angle and the constraint control amount boundary, that is, satisfies the following relationship:

[0359] δ work =min(δ work ,δ l )

[0360] δ work =max(δ work ,δ r )

[0361] Among them, δ work is the steering wheel angle.

[0362] When a person is driving a vehicle, if it is determined that the current steering wheel angle exceeds the constraint boundary, the angle determination device will emit a warning sound to remind the driver to drive safely.

[0363] The above scheme obtains the driving boundary with the risk of collision with the current vehicle; constructs the vehicle motion curve equation according to the position and orientation of the current vehicle and the reference straight line corresponding to the driving boundary; solves the vehicle motion curve equation to obtain the parameters in the vehicle motion curve equation, and uses the parameters to determine the turning angle used to prevent the current vehicle from colliding with the driving boundary. By constructing the vehicle motion curve equation in combination with the driving boundary, the control boundary can be planned in advance, and when the vehicle is driving at the vehicle turning angle determined by the vehicle turning angle determination method provided in this application, the probability of collision with the driving boundary can be effectively reduced, thereby improving the driving safety of the current vehicle.

[0364] Furthermore, the method for determining the wheel turning angle provided by the present application obtains the road boundary in the form of a line segment. A parameterized hyperbolic spiral curve is constructed by utilizing the characteristics of a hyperbolic spiral curve that gradually fits a straight line and has continuous curvature. This hyperbolic spiral curve is determined as the maximum motion boundary of the current vehicle that conforms to the Ackerman motion and can avoid collision. The parameters of the hyperbolic spiral curve are solved according to the positional relationship between the vehicle and the boundary conditions, including the angle and the lateral position. The parameters are brought into the hyperbolic spiral curve, the curvature of the position of the hyperbolic spiral curve vehicle is solved, and the theoretical front wheel turning angle of the current vehicle moving along the current hyperbolic spiral curve is calculated in combination with the vehicle body parameters. The calculated value is then judged for validity and post-processed to make the value more in line with engineering use requirements. Finally, the constraint value is used to realize the anti-collision protection and collision warning functions.

[0365] Please continue to see Figure 7 , Figure 7 The terminal device 500 of the embodiment of the present application includes a processor 51 and a memory 52 .

[0366] The processor 51 and the memory 52 are connected to the bus. The memory 52 stores program data. The processor 51 is used to execute the program data to implement the method for determining the vehicle turning angle described in the above embodiment.

[0367] In the embodiment of the present application, the processor 51 may also be referred to as a CPU (Central Processing Unit). The processor 51 may be an integrated circuit chip having the ability to process signals. The processor 51 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or the processor 51 may also be any conventional processor, etc.

[0368] This application also provides a computer storage medium, please continue to refer to Figure 8 , Figure 8 It is a structural diagram of an embodiment of a computer storage medium provided in the present application. The computer storage medium 600 stores program data 61. When the program data 61 is executed by a processor, it is used to implement the method for determining the vehicle turning angle of the above embodiment.

[0369] When the embodiments of the present application are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0370] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Equivalent structures or equivalent process changes made by utilizing the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for determining a vehicle turning angle, characterized in that: The method comprises: Acquire a driving boundary corresponding to a current vehicle, where there is a collision risk between the driving boundary and the current vehicle; In combination with the reference straight line corresponding to the driving boundary, the first position and the first orientation of the current vehicle, a vehicle motion curve equation is constructed, wherein the curve point corresponding to the first position is tangent to the target straight line corresponding to the first orientation, and the distance between the curve formed by the vehicle motion curve equation and the reference straight line gradually decreases in the extension direction of the reference straight line; Solving the vehicle motion curve equation to obtain parameters in the vehicle motion curve equation; The vehicle turning angle is calculated using the parameters; wherein the vehicle turning angle is used to prevent the current vehicle from colliding with the driving boundary.

2. The method according to claim 1, characterized in that The step of solving the vehicle motion curve equation to obtain parameters in the vehicle motion curve equation includes: In combination with the vehicle motion curve equation, a first function related to a relative angle is constructed; wherein the relative angle represents an angle between the target straight line and the driving boundary; Solving the first function within the definition domain of the relative angle; When the absolute value of the first output result of the first function is less than a preset result, determining the relative angle used by the first function as the target independent variable; The target independent variable is used to obtain the parameters in the vehicle motion curve equation.

3. The method according to claim 2, characterized in that Solving the first function within the definition domain of the relative angle comprises: Randomly select the relative angle within the definition domain; Inputting the relative angle into the first function to obtain the first output result; and inputting the relative angle into a second function to obtain a second output result, wherein the second function is a first-order derivative function of the first function; In response to the absolute value of the first output result being greater than or equal to the preset result, and the absolute value of the second output result being less than the preset result, randomly selecting the relative angle again within the definition domain, and continuing to solve the first function; In response to an absolute value of the first output result being greater than or equal to the preset result, and an absolute value of the second output result being greater than or equal to the preset result, iterating the relative angle using the first output result and the second output result to obtain an iterated relative angle; In response to the relative angle after iteration being within the definition domain, continuing to solve the first function using the relative angle after iteration; In response to the relative angle after the iteration being outside the definition domain, the relative angle is randomly selected again from within the definition domain, and the first function is continued to be solved.

4. The method according to claim 3, characterized in that In response to the absolute value of the first output result being greater than or equal to the preset result, and the absolute value of the second output result being greater than or equal to the preset result, iterating the relative angle using the first output result and the second output result to obtain the iterated relative angle, comprising: In response to the absolute value of the first output result being greater than or equal to the preset result, calculating the quotient of the first output result and the second output result to obtain an iterative change amount; The difference between the relative angle and the iterative change amount is calculated to obtain the relative angle after the iteration.

5. The method according to claim 3, characterized in that: The step of inputting the relative angle into a second function to obtain a second output result comprises: Inputting the relative angle into the second function to obtain a candidate result; In response to the candidate result being less than a target gradient and the candidate result being greater than or equal to the preset result, taking the target gradient as the second output result; Or, in response to the candidate result being smaller than the negative value of the target gradient and the candidate result being smaller than or equal to the negative value of the preset result, the negative value of the target gradient is used as the second output result.

6. The method according to claim 1, characterized in that The step of calculating the vehicle turning angle by using the parameters comprises: Calculating a target curvature of the curve at the curve point using the parameters; Determine a rear wheel slip angle compensation angle of the current vehicle by using the target curvature, a first distance from the center of mass to the front axle of the vehicle, the mass of the current vehicle, the current speed of the current vehicle, the equivalent cornering stiffness of the left and right wheels of the rear axle, and the wheelbase of the current vehicle; Determine the understeering degree of the current vehicle by using the first distance, the mass, the equivalent cornering stiffness of the left and right wheels of the rear axle, the wheelbase, the second distance from the center of mass to the rear axle of the vehicle, and the equivalent cornering stiffness of the left and right wheels of the front axle; The vehicle turning angle is calculated using the turning angle action coefficient, the target curvature, the wheelbase, the understeering degree, the current speed, and the rear wheel sideslip angle compensation angle.

7. The method according to claim 1, characterized in that The vehicle turning angle includes a vehicle left turning angle and a vehicle right turning angle; The driving boundaries include a plurality of left driving boundaries and a plurality of right driving boundaries; The step of calculating the vehicle turning angle by using the parameters comprises: Calculating a plurality of candidate vehicle left turn angles using the parameters of the vehicle motion curve equation corresponding to each of the left travel boundaries, wherein the candidate vehicle left turn angles are positive numbers; Calculating a plurality of candidate vehicle right turn angles using the parameters of the vehicle curve motion equation corresponding to each of the right travel boundaries, wherein the candidate vehicle right turn angles are negative numbers; From the multiple candidate vehicle left turn angles, select the smallest one as the vehicle left turn angle; and from the multiple candidate vehicle right turn angles, select the largest one as the vehicle right turn angle.

8. The method according to claim 1, characterized in that The obtaining of the driving boundary corresponding to the current vehicle includes: Acquire the driving boundary according to the second position, the second orientation and the running speed corresponding to the dynamic obstacle; and / or, At least one driving boundary corresponding to a road edge is obtained.

9. A terminal device, characterized in that: The terminal device includes a processor and a memory connected to the processor, wherein: The memory stores program instructions; The processor is configured to execute program instructions stored in the memory to implement the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed, the method according to any one of claims 1 to 8 is implemented.

Images