A vehicle forward path prediction method, device, vehicle and storage medium

Abstract

This invention provides a method, apparatus, vehicle, and storage medium for predicting a vehicle's forward path. The method includes: establishing a world coordinate system with the center of the vehicle's rear axle as the origin; obtaining a path prediction expression and a predicted distance corresponding to the world coordinate system; calculating the discrete point coordinates of the predicted distance in the world coordinate system based on the path prediction expression; converting the discrete point coordinates into pixel coordinates in a preset image coordinate system; and connecting the pixel coordinates to generate a forward path for the vehicle. This invention allows for the prediction of the vehicle's forward path during remote driving, assisting the cloud-based driver in controlling the vehicle.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a vehicle forward path prediction method, a vehicle forward path prediction device, a vehicle, and a storage medium. Background Technology

[0002] Remote driving can assist vehicles in overcoming difficulties in vulnerable scenarios when their autonomous driving functions are not fully operational, achieving fully driverless operation. During remote driving, information needs to be transmitted to the cloud so that a cloud-based safety operator can react and take control of the vehicle. However, since the cloud-based safety operator is not physically present in the vehicle, their ability to accurately predict the vehicle's forward path is limited. Therefore, predictive path generation is needed to assist the cloud-based safety operator in controlling the vehicle. This enables remote driving of vehicles and improves the safety of remote driving. Summary of the Invention

[0003] In view of the above problems, embodiments of the present invention are proposed to provide a vehicle forward path prediction method, a vehicle forward path prediction device, a vehicle, and a storage medium that overcome or at least partially solve the above problems.

[0004] This invention discloses a method for predicting a vehicle's forward path, comprising:

[0005] Establish a world coordinate system with the center of the vehicle's rear wheel axle as the origin;

[0006] Obtain the path prediction expression and prediction distance corresponding to the world coordinate system;

[0007] Calculate the discrete point coordinates of the predicted distance in the world coordinate system based on the path prediction expression;

[0008] The discrete point coordinates are converted into pixel coordinates in a preset image coordinate system;

[0009] Connect the coordinates of the pixels to generate the vehicle's forward path.

[0010] Optionally, the step of calculating the coordinates of the discrete point in the world coordinate system based on the path prediction expression includes:

[0011] The arc angle is calculated by equidistant interpolation based on the predicted distance;

[0012] Within the domain of the path prediction expression, calculate the coordinates of the discrete point corresponding to the arc angle.

[0013] Optionally, after the step of establishing a world coordinate system with the center of the vehicle's rear wheel axle as the origin, the method further includes:

[0014] Obtain the current steering wheel angle of the vehicle, and the angle mapping relationship;

[0015] The front wheel steering angle corresponding to the current steering angle is determined based on the steering angle mapping relationship;

[0016] The turning radius of the vehicle's front axle center is calculated based on the front wheel steering angle; the turning radius of the front axle center is used to determine the path prediction expression.

[0017] Optionally, the step of calculating the arc angle by equidistant interpolation based on the predicted distance includes:

[0018] The predicted distance is interpolated at equal intervals to generate equal distance values;

[0019] Calculate the quotient of the equidistant distance value and the turning radius of the front wheel axle center;

[0020] The quotient is determined to be an arc angle.

[0021] Optionally, the step of calculating the coordinates of the discrete point corresponding to the arc angle within the domain of the path prediction expression includes:

[0022] Determine the corresponding trigonometric function value for the arc angle;

[0023] Calculate the trigonometric function value and the turning radius of the front wheel axle center to generate the first coordinate value;

[0024] Determine the second coordinate value within the defined domain of the first coordinate value;

[0025] The coordinates of the discrete points are determined based on the second coordinate value.

[0026] Optionally, the step of converting the discrete point coordinates into pixel coordinates in a preset image coordinate system includes:

[0027] Read the camera coordinate system, extrinsic parameter matrix, image plane coordinate system, intrinsic parameter matrix, and distortion coefficients;

[0028] The discrete point coordinates are transformed into camera point coordinates in the camera coordinate system using the extrinsic parameter matrix.

[0029] The camera point coordinates are transformed into imaging point coordinates in the imaging plane coordinate system using the intrinsic parameter matrix.

[0030] The distortion coefficient is used to convert the coordinates of the imaging point into the coordinates of the pixel point in the preset image coordinate system.

[0031] Optionally, the method further includes:

[0032] Visualize the vehicle's forward path.

[0033] This invention discloses a vehicle forward path prediction device, comprising:

[0034] Establish a module to create a world coordinate system with the center of the vehicle's rear wheel axle as the origin;

[0035] The acquisition module is used to acquire the path prediction expression corresponding to the world coordinate system, as well as the prediction distance;

[0036] The calculation module is used to calculate the coordinates of discrete points in the world coordinate system based on the path prediction expression;

[0037] The conversion module is used to convert the discrete point coordinates into pixel coordinates in a preset image coordinate system;

[0038] A connection module is used to connect the pixel coordinates to generate the vehicle's forward path.

[0039] This invention also discloses a vehicle, including: a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps of the vehicle forward path prediction method as described above.

[0040] This invention also discloses a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the vehicle forward path prediction method as described above.

[0041] The embodiments of the present invention have the following advantages:

[0042] This invention establishes a world coordinate system with the center of the vehicle's rear axle as the origin; it establishes the world coordinate system from the vehicle's actual environment, facilitating the establishment of the coordinate system; it obtains the path prediction expression and the predicted distance corresponding to the world coordinate system; it obtains the path prediction expression and the distance to be predicted, reducing the amount of data in the calculation process; it calculates the discrete point coordinates of the predicted distance in the world coordinate system based on the path prediction expression; it determines the specific location of the predicted position point in the actual environment, and converts the discrete point coordinates into pixel coordinates in a preset image coordinate system; it then converts the coordinates of the actual position point into pixel coordinates in the image coordinate system; it connects the pixel coordinates to generate the vehicle's forward path, which can be displayed on the image, assisting cloud-based safety operators in operating the vehicle and improving the safety of remote driving. Attached Figure Description

[0043] Figure 1This is a flowchart illustrating the steps of an embodiment of the vehicle forward path prediction method of the present invention;

[0044] Figure 2 This is a flowchart illustrating the steps of another embodiment of the vehicle forward path prediction method of the present invention;

[0045] Figure 3 This is a flowchart illustrating a coordinate transformation example of a vehicle forward path prediction method according to the present invention;

[0046] Figure 4 This is a structural block diagram of an embodiment of a vehicle forward path prediction device according to the present invention. Detailed Implementation

[0047] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] During remote driving, multiple cameras on the vehicle collect information about the surrounding environment and send it to the cloud. The cloud then displays the surrounding environment as images, simulating the actual driving environment. The cloud-based safety operator then operates the vehicle based on these images. However, since the driving environment is only simulated through images, the cloud-based safety operator cannot determine the vehicle's position after a preset time or distance. This means that judging the vehicle's position during remote driving requires the cloud-based safety operator's experience, resulting in low safety. Therefore, it is necessary to display the vehicle's current status on the cloud and predict its forward path to assist the cloud-based safety operator in controlling the vehicle to reach the target position, thereby improving the safety of remote driving.

[0049] Reference Figure 1 The flowchart illustrates an embodiment of the vehicle forward path prediction method of the present invention, which may specifically include the following steps:

[0050] Step 101: Establish a world coordinate system with the center of the vehicle's rear wheel axle as the origin;

[0051] A world coordinate system is established with the center of the vehicle's rear axle as the origin, the vehicle's longitudinal direction as the x-axis, the vehicle's height as the z-axis, and the vehicle's lateral direction as the y-axis. The world coordinate system is the coordinate system of the actual environment in which the vehicle is located. This world coordinate system is a Cartesian coordinate system.

[0052] Step 102: Obtain the path prediction expression and prediction distance corresponding to the world coordinate system;

[0053] The path prediction expression and predicted distance for the forward path in the world coordinate system are retrieved from the vehicle's own storage space or from a cloud server. It should be noted that the path prediction expression is pre-determined based on the vehicle's driving parameters, and the predicted distance is determined by the prediction accuracy; higher accuracy results in a larger predicted distance, and vice versa.

[0054] Step 103: Calculate the coordinates of the discrete point of the predicted distance in the world coordinate system according to the path prediction expression;

[0055] Based on the path prediction expression, the coordinates of discrete points in the world coordinate system at different prediction distances are calculated one by one to obtain the coordinates of multiple discrete points.

[0056] Step 104: Convert the discrete point coordinates into pixel coordinates in a preset image coordinate system;

[0057] The coordinates of discrete points in the world coordinate system are transformed into pixel coordinates in the preset image coordinate system. The specific location points in the actual environment are transformed into a pixel in the image. The preset image coordinate system can be the corresponding image coordinate system on the display component that displays the forward path of the vehicle.

[0058] Step 105: Connect the pixel coordinates to generate the vehicle's forward path.

[0059] In this embodiment of the invention, a forward path for the vehicle is generated by connecting the coordinates of multiple pixels.

[0060] This invention establishes a world coordinate system with the center of the vehicle's rear axle as the origin; it establishes the world coordinate system from the vehicle's actual environment, facilitating the establishment of the coordinate system; it obtains the path prediction expression and the predicted distance corresponding to the world coordinate system; it obtains the path prediction expression and the distance to be predicted, reducing the amount of data in the calculation process; it calculates the discrete point coordinates of the predicted distance in the world coordinate system based on the path prediction expression; it determines the specific location of the predicted position point in the actual environment, and converts the discrete point coordinates into pixel coordinates in a preset image coordinate system; it then converts the coordinates of the actual position point into pixel coordinates in the image coordinate system; it connects the pixel coordinates to generate the vehicle's forward path, which can be displayed on the image, assisting cloud-based safety operators in operating the vehicle and improving the safety of remote driving.

[0061] Reference Figure 2 The flowchart illustrates another embodiment of the vehicle forward path prediction method of the present invention, which may specifically include the following steps:

[0062] Step 201: Obtain the current steering wheel angle of the vehicle and the angle mapping relationship;

[0063] In practical applications, the vehicle terminal can obtain the current steering wheel angle through an angle sensor. It should be noted that the current steering wheel angle should have both direction and angle values, such as a 90-degree left turn. The vehicle terminal can read the angle mapping relationship from its own storage space; this mapping relationship is the mapping between the current steering wheel angle and the front wheel angle.

[0064] Step 202: Determine the front wheel steering angle corresponding to the current steering angle based on the steering angle mapping relationship;

[0065] Turning the steering wheel of a vehicle at a certain angle causes the front wheels to rotate via a linkage mechanism between the steering wheel and the front wheels. Therefore, the steering angle of the front wheels can be determined by the angle of the steering wheel.

[0066] The corresponding front wheel steering angle is determined based on the current steering wheel angle in the steering angle mapping relationship.

[0067] Step 203: Calculate the turning radius of the front axle center of the vehicle based on the front wheel steering angle; the turning radius of the front axle center is used to determine the path prediction expression;

[0068] The front axle center of the vehicle is determined based on the front wheel steering angle, and then the turning radius of the front axle center is determined based on the centers of the front and rear axles. The turning radius of the front axle center is used to determine the path prediction expression.

[0069] Step 204: Establish a world coordinate system with the center of the vehicle's rear wheel axle as the origin;

[0070] With the center of the vehicle's rear axle as the origin, the vehicle's longitudinal direction as the x-axis, the vehicle's height as the z-axis, and the vehicle's lateral direction as the y-axis, a three-dimensional Cartesian coordinate system is established as the world coordinate system.

[0071] Step 205: Obtain the path prediction expression and prediction distance corresponding to the world coordinate system;

[0072] The path prediction expression in the world coordinate system is obtained based on the turning radius of the front wheel axle center, and the prediction distance is obtained based on the prediction accuracy.

[0073] Step 206: Calculate the coordinates of the discrete point of the predicted distance in the world coordinate system according to the path prediction expression;

[0074] The forward path of the vehicle is calculated based on the path prediction expression, and the coordinates of the discrete point in the world coordinate system corresponding to the predicted distance are obtained.

[0075] In an optional embodiment of the present invention, the step of calculating the coordinates of the discrete point in the world coordinate system based on the path prediction expression includes:

[0076] Sub-step S2061: Calculate the arc angle by equidistant interpolation based on the predicted distance;

[0077] In an optional embodiment of the present invention, the step of calculating the arc angle by equidistant interpolation based on the predicted distance includes:

[0078] Sub-step S20611: Perform equidistant interpolation on the predicted distance to generate equidistant distance values;

[0079] Based on the obtained predicted distance, perform equidistant interpolation to generate discrete equidistant distance values. For example, if the predicted distance is 5 meters, perform equidistant interpolation, and the interpolated value is 1 meter, then generate equidistant distance values ​​of 1 meter, 2 meters, 3 meters, 4 meters, and 5 meters.

[0080] Sub-step S20612: Calculate the quotient of the equidistant distance value and the turning radius of the front wheel axle center;

[0081] Calculate the quotient of each equidistant distance value with the turning radius of the front axle center, that is, the quotient obtained by dividing the equidistant distance value by the turning radius of the front axle center.

[0082] Sub-step S20613: Determine that the quotient is an arc angle.

[0083] The quotient is determined to be the arc angle, and the corresponding arc angle is determined for each equidistant distance value.

[0084] Sub-step S2062: Within the domain of the path prediction expression, calculate the coordinates of the discrete point corresponding to the arc angle.

[0085] Since the vehicle has left and right sides, there will be two discrete point coordinates calculated based on the arc angle. However, the path only has one forward direction. Therefore, it is necessary to calculate the discrete point coordinates corresponding to the arc angle within the domain of the path prediction expression to determine the unique discrete point coordinates within the domain corresponding to the arc angle.

[0086] In an optional embodiment of the present invention, the step of calculating the coordinates of the discrete point corresponding to the arc angle within the domain of the path prediction expression includes:

[0087] Sub-step S20621: Determine the trigonometric function value corresponding to the arc angle;

[0088] In practical applications, the first step is to calculate the trigonometric function values ​​corresponding to the arc angle, that is, to calculate the sine and cosine values ​​corresponding to the arc angle.

[0089] Sub-step S20622: Calculate the trigonometric function value and the turning radius of the front wheel axle center to generate the first coordinate value;

[0090] The first coordinate value is determined by multiplying the trigonometric function value by the turning radius of the front wheel axle center; specifically, the horizontal coordinate value of the first coordinate value is determined by multiplying the sine value of the arc angle by the turning radius of the front wheel axle center, and the vertical coordinate value of the first coordinate value is determined by multiplying the cosine value of the arc angle by the turning radius of the front wheel axle center.

[0091] Sub-step S20623: Determine the second coordinate value within the defined domain of the first coordinate value;

[0092] Based on the limitation of the domain, the first coordinate value within the domain is determined as the second coordinate value from the two first coordinate values.

[0093] Sub-step S20624: Determine the coordinates of the discrete point based on the second coordinate value.

[0094] The second coordinate value is determined as the coordinate value of the discrete point, thereby determining the coordinates of the discrete point.

[0095] Step 207: Convert the discrete point coordinates into pixel coordinates in a preset image coordinate system;

[0096] Convert the coordinates of discrete points in the world coordinate system into the coordinates of pixels in the preset image coordinate system that can be displayed on the preset display component.

[0097] In an optional embodiment of the present invention, the step of converting the discrete point coordinates into pixel coordinates in a preset image coordinate system includes:

[0098] Sub-step S2071: Read the camera coordinate system, extrinsic parameter matrix, image plane coordinate system, intrinsic parameter matrix, and distortion coefficients;

[0099] First, the camera coordinate system used by the vehicle's vision sensor to acquire images, the imaging plane coordinate system corresponding to the vision sensor's imaging plane, the transformed extrinsic parameter matrix, the intrinsic parameter matrix, and the distortion coefficients of the image distortion are read. These parameters can be read from the vehicle terminal's storage space or from a third-party server; this embodiment of the invention does not specifically limit this.

[0100] Sub-step S2072: The discrete point coordinates are transformed into camera point coordinates in the camera coordinate system using the extrinsic parameter matrix;

[0101] In practical applications, the extrinsic parameter matrix is ​​a 3x4 matrix that transforms discrete point coordinates into camera point coordinates in the camera coordinate system. In other words, the extrinsic parameter matrix converts the discrete point positions in the real environment into position points acquired by the vision sensor.

[0102] Sub-step S2073: The camera point coordinates are transformed into imaging point coordinates in the imaging plane coordinate system using the intrinsic parameter matrix;

[0103] In practical applications, the intrinsic parameter matrix is ​​a 3x3 matrix that transforms the camera point coordinates into the imaging point coordinates in the imaging plane coordinate system. In other words, the intrinsic parameter matrix transforms the position points acquired by the visual sensor into their positions on the imaging plane.

[0104] Sub-step S2074: The coordinates of the imaging point are converted into pixel coordinates in the preset image coordinate system using the distortion coefficient.

[0105] After obtaining the imaging point coordinates, the imaging point coordinates of the imaging surface are transformed into pixel coordinates in the preset image coordinate system through the distortion coefficient. That is, the position of the imaging surface is converted into the pixel position on the image display surface through the distortion coefficient.

[0106] See also Figure 3 The flowchart illustrates a coordinate transformation example for a vehicle forward path prediction method.

[0107] The obtained discrete point coordinates are first transformed into camera point coordinates in the camera coordinate system through the extrinsic parameter matrix, and the discrete point coordinates are projected from the three-dimensional space of the world coordinate system to the camera coordinate system. Then, the camera point coordinates are transformed into imaging point coordinates in the imaging plane coordinate system through the intrinsic parameter matrix, and the camera point in the camera coordinate system is projected into the two-dimensional space of the imaging plane. Finally, the corresponding pixels of the imaging points on the imaging plane in the image are corrected through distortion coefficients.

[0108] Step 208: Connect the pixel coordinates to generate the vehicle's forward path.

[0109] By connecting the pixel coordinates at the beginning and end, a forward path for the vehicle is generated on the image.

[0110] In an optional embodiment of the present invention, the method further includes:

[0111] Step S1: Visualize the vehicle's forward path.

[0112] The vehicle's forward path is visualized so that it can be displayed on a display component.

[0113] This invention establishes a world coordinate system with the center of the vehicle's rear axle as the origin; it establishes the world coordinate system from the vehicle's actual environment, facilitating the establishment of the coordinate system; it obtains the path prediction expression and predicted distance corresponding to the world coordinate system; it obtains the path prediction expression and the distance to be predicted, reducing the amount of data in the calculation process; it calculates the discrete point coordinates of the predicted distance in the world coordinate system based on the path prediction expression; it determines the specific location of the predicted position point in the actual environment, and reads the camera coordinate system, extrinsic parameter matrix, imaging plane coordinate system, intrinsic parameter matrix, and distortion coefficient; it converts the discrete point coordinates into camera point coordinates in the camera coordinate system using the extrinsic parameter matrix; it converts the camera point coordinates into imaging point coordinates in the imaging plane coordinate system using the intrinsic parameter matrix; it converts the imaging point coordinates into pixel coordinates in the preset image coordinate system using the distortion coefficient; it then converts the coordinates of the actual position into pixel coordinates in the image coordinate system; it connects the pixel coordinates to generate the vehicle's forward path, which can be displayed on the image, assisting the cloud-based safety operator in operating the vehicle and improving the safety of remote driving.

[0114] To enable those skilled in the art to better understand the embodiments of the present invention, an example is provided below:

[0115] Obtain the current steering wheel angle of the vehicle, and obtain the front wheel angle δ based on the mapping relationship between the steering wheel angle and the front wheel angle;

[0116] Calculate the turning radius R of the rear axle center of the vehicle based on a simplified two-degree-of-freedom, two-wheeled model of the car:

[0117]

[0118] Where L is the vehicle wheelbase;

[0119] Establish a coordinate system at the center of the rear wheel, with the direction of the front of the vehicle as the X-axis and the left side of the vehicle as the Y-axis. Then the coordinates of the center of the circle (x0, y0) are (0, R) or (0, - R).

[0120] The coordinates of the front wheel axle center (x) are obtained in the above coordinate system. f ,y f Let (L, 0) be the coordinates of the circle. Calculate the straight-line distance between the coordinates of the circle and the center of the circle to obtain the turning radius R of the front wheel axle center. f ;

[0121] Based on the preset predicted distance (d1, d2, ..., d n ) and R f The corresponding arc angles (Δθ1, Δθ2, ..., Δθ) can be obtained. n ):

[0122]

[0123] Based on the vehicle width w, obtain the coordinates (x) of the outer edge points of the left and right front wheels. fl ,y fl ) and (x fr ,y fr ) are respectively and

[0124] Establish a coordinate system at the center of the circle, with the coordinate axes aligned with the vehicle coordinate system. Then, the polar coordinate angles of the left and right outer points in the central coordinate system can be calculated as follows:

[0125]

[0126] Combining the arc angle corresponding to the predicted distance mentioned above, the predicted path turning angle θ of the front wheel edge at the desired position can be obtained:

[0127] θ = θ0 + Δθ

[0128] The turning radius R can be obtained by calculating the distance between the outer edge point and the center of the circle. l and R r This allows us to obtain its path information in the vehicle coordinate system, where the domain is θ. t ∈[θ0,θ], the discrete coordinate points are:

[0129] x lt =R l *cos(θ t )+x0

[0130] y lt =R l *sin(θ t )+y0

[0131] x rt =R r *cos(θ t )+x0

[0132] y rt =R r *sin(θ t )+y0

[0133] The process involves transforming discrete point coordinates into camera point coordinates in the camera coordinate system using an extrinsic parameter matrix; transforming camera point coordinates into imaging point coordinates in the imaging plane coordinate system using an intrinsic parameter matrix; transforming imaging point coordinates into pixel coordinates in a preset image coordinate system using distortion coefficients; and connecting the pixel coordinates to form a forward path.

[0134] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0135] Reference Figure 4 The diagram illustrates a structural block diagram of an embodiment of a vehicle forward path prediction device according to the present invention, which may specifically include the following modules:

[0136] Establish module 401 to establish a world coordinate system with the center of the vehicle's rear wheel axle as the origin;

[0137] The first acquisition module 402 is used to acquire the path prediction expression corresponding to the world coordinate system, and the prediction distance;

[0138] Calculation module 403 is used to calculate the coordinates of discrete points in the world coordinate system based on the path prediction expression;

[0139] The conversion module 404 is used to convert the discrete point coordinates into pixel coordinates in a preset image coordinate system;

[0140] The connection module 405 is used to connect the pixel coordinates to generate the vehicle's forward path.

[0141] In an optional embodiment of the present invention, the computing module 403 includes:

[0142] An equidistant interpolation submodule is used to calculate the arc angle by equidistant interpolation based on the predicted distance;

[0143] The discrete point coordinate determination submodule is used to calculate the discrete point coordinates corresponding to the arc angle within the domain of the path prediction expression.

[0144] In an optional embodiment of the present invention, the device further includes:

[0145] The second acquisition module is used to acquire the current steering wheel angle of the vehicle and the angle mapping relationship;

[0146] A front wheel steering angle determination module is used to determine the front wheel steering angle corresponding to the current steering angle based on the steering angle mapping relationship;

[0147] The front axle center turning radius determination module is used to calculate the front axle center turning radius of the vehicle based on the front wheel turning angle; the front axle center turning radius is used to determine the path prediction expression.

[0148] In an optional embodiment of the present invention, the equidistant interpolation submodule includes:

[0149] An equidistant interpolation unit is used to perform equidistant interpolation on the predicted distance to generate equidistant distance values.

[0150] The first calculation unit is used to calculate the quotient of the equidistant distance value and the turning radius of the front wheel axle center;

[0151] The arc angle determination unit is used to determine the quotient as an arc angle.

[0152] In an optional embodiment of the present invention, the discrete point coordinate determination submodule includes:

[0153] A trigonometric function value determination unit is used to determine the corresponding trigonometric function value of the arc angle;

[0154] The second calculation unit is used to calculate the trigonometric function value and the turning radius of the front wheel axle center; and generate the first coordinate value.

[0155] The second coordinate value determination unit is used to determine the second coordinate value of the first coordinate value within the defined domain;

[0156] The discrete point coordinate determination unit is used to determine the discrete point coordinates based on the second coordinate value.

[0157] In an optional embodiment of the present invention, the conversion module 404 includes:

[0158] The read submodule is used to read the camera coordinate system, extrinsic parameter matrix, image plane coordinate system, intrinsic parameter matrix, and distortion coefficients.

[0159] The first transformation submodule is used to transform the discrete point coordinates into camera point coordinates in the camera coordinate system through the extrinsic parameter matrix.

[0160] The second transformation submodule is used to transform the camera point coordinates into imaging point coordinates in the imaging plane coordinate system through the intrinsic parameter matrix.

[0161] The third transformation submodule is used to transform the imaging point coordinates into pixel coordinates in the preset image coordinate system using the distortion coefficient.

[0162] In an optional embodiment of the present invention, the device further includes:

[0163] A visualization module is used to visualize the vehicle's forward path.

[0164] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0165] This application also provides a vehicle, including: a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the various processes of the above-described vehicle forward path prediction method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0166] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described vehicle forward path prediction method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0167] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0168] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0169] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0170] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 a process or multiple processes and / or boxes Figure 1The function specified in one or more boxes.

[0171] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0172] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0173] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0174] The foregoing has provided a detailed description of the vehicle forward path prediction method, apparatus, vehicle, and storage medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for predicting the forward path of a vehicle, characterized in that, include: Establish a world coordinate system with the center of the vehicle's rear wheel axle as the origin; Obtain the path prediction expression and prediction distance corresponding to the world coordinate system; The path prediction expression is determined based on the turning radius of the front axle center, which is calculated based on the front wheel angle, which is determined based on the angle mapping relationship. Calculate the discrete point coordinates of the predicted distance in the world coordinate system based on the path prediction expression; The discrete point coordinates are converted into pixel coordinates in a preset image coordinate system; Connect the coordinates of the pixels to generate the vehicle's forward path; The step of calculating the coordinates of a discrete point in the world coordinate system based on the path prediction expression includes: The arc angle is calculated by equidistant interpolation based on the predicted distance; Within the domain of the path prediction expression, calculate the coordinates of the discrete point corresponding to the arc angle; The step of calculating the discrete point coordinates corresponding to the arc angle within the domain of the path prediction expression includes: Determine the corresponding trigonometric function value for the arc angle; Calculate the trigonometric function value and the turning radius of the front wheel axle center to generate the first coordinate value; Determine the second coordinate value within the defined domain of the first coordinate value; The coordinates of the discrete points are determined based on the second coordinate value.

2. The method according to claim 1, characterized in that, After the step of establishing a world coordinate system with the center of the vehicle's rear wheel axle as the origin, the method further includes: Obtain the current steering wheel angle of the vehicle, and the angle mapping relationship; The front wheel steering angle corresponding to the current steering angle is determined based on the steering angle mapping relationship; The turning radius of the vehicle's front axle center is calculated based on the front wheel steering angle; the turning radius of the front axle center is used to determine the path prediction expression.

3. The method according to claim 2, characterized in that, The step of calculating the arc angle by equidistant interpolation based on the predicted distance includes: The predicted distance is interpolated at equal intervals to generate equal distance values; Calculate the quotient of the equidistant distance value and the turning radius of the front wheel axle center; The quotient is determined to be an arc angle.

4. The method according to claim 1, characterized in that, The step of converting the discrete point coordinates into pixel coordinates in a preset image coordinate system includes: Read the camera coordinate system, extrinsic parameter matrix, image plane coordinate system, intrinsic parameter matrix, and distortion coefficients; The discrete point coordinates are transformed into camera point coordinates in the camera coordinate system using the extrinsic parameter matrix. The camera point coordinates are transformed into imaging point coordinates in the imaging plane coordinate system using the intrinsic parameter matrix. The distortion coefficient is used to convert the coordinates of the imaging point into the coordinates of the pixel point in the preset image coordinate system.

5. The method according to claim 1, characterized in that, The method further includes: Visualize the vehicle's forward path.

6. A vehicle forward path prediction device, characterized in that, include: Establish a module to create a world coordinate system with the center of the vehicle's rear wheel axle as the origin; The acquisition module is used to acquire the path prediction expression corresponding to the world coordinate system and the prediction distance; the path prediction expression is determined based on the turning radius of the front wheel axle center, the turning radius of the front wheel axle center is calculated based on the front wheel angle, and the front wheel angle is determined based on the angle mapping relationship; The calculation module is used to calculate the coordinates of discrete points in the world coordinate system based on the path prediction expression; The conversion module is used to convert the discrete point coordinates into pixel coordinates in a preset image coordinate system; A connection module is used to connect the pixel coordinates to generate the vehicle's forward path; The computing module includes: An equidistant interpolation submodule is used to calculate the arc angle by equidistant interpolation based on the predicted distance; The discrete point coordinate determination submodule is used to calculate the discrete point coordinates corresponding to the arc angle within the domain of the path prediction expression; The discrete point coordinate determination submodule includes: A trigonometric function value determination unit is used to determine the corresponding trigonometric function value of the arc angle; The second calculation unit is used to calculate the trigonometric function value and the turning radius of the front wheel axle center; and generate the first coordinate value. The second coordinate value determination unit is used to determine the second coordinate value of the first coordinate value within the defined domain; The discrete point coordinate determination unit is used to determine the discrete point coordinates based on the second coordinate value.

7. A vehicle, characterized in that, include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps of the vehicle forward path prediction method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the steps of the vehicle forward path prediction method as described in any one of claims 1 to 5.

Images