Steering recognition method and device, electronic equipment and storage medium

Abstract

The invention provides a steering recognition method and device, electronic equipment and a storage medium. The method comprises the steps that a first track sequence of a target carrier is acquired; performing affine transformation on the first track sequence to obtain a second track sequence; determining a first change rate of the second track sequence in the vertical direction and a second change rate of the second track sequence in the horizontal direction; determining a bending point and a bending-in point based on the first change rate and the second change rate; according to the method, the entry and exit bending point can be calculated only depending on the trajectory information of the vehicle, additional high-precision map data is not needed, the calculation method is simple and efficient, and the calculation result is more accurate.

Description

Technical Field

[0001] The present application relates to the field of unmanned driving technology, and in particular to a steering recognition method, device, electronic device and storage medium. Background Art

[0002] With the rapid development of autonomous driving technology, end-to-end autonomous driving algorithms have gradually become a hot topic in research and application. These algorithms simplify the complex module division in traditional autonomous driving systems, such as perception, prediction, planning and control, by directly mapping sensor inputs to driving decisions or control outputs, aiming to achieve global optimal driving behavior. However, in the implementation of end-to-end autonomous driving technology, how to efficiently mine valuable and scarce data from massive amounts of data has become one of the key issues restricting its further development.

[0003] With regard to the turning recognition method, the existing technology has the following disadvantages: first, it relies on high-precision maps; second, the calculation process is complicated; and third, the recognition of the turning entry and exit moments is not accurate enough. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a turning recognition method, device, electronic device and storage medium, which can calculate the entry and exit points only by relying on the vehicle's trajectory (position and starting heading) information without the need for additional high-precision map data. The calculation method is simple and efficient, and the calculation results are more accurate.

[0005] The technical solution of the embodiment of the present application is implemented as follows:

[0006] In a first aspect, an embodiment of the present application provides a turn recognition method, the method comprising:

[0007] Obtaining a first trajectory sequence of the target vehicle;

[0008] Performing an affine transformation on the first trajectory sequence to obtain a second trajectory sequence;

[0009] determining a first change rate of the second trajectory sequence in a vertical direction and a second change rate of the second trajectory sequence in a horizontal direction;

[0010] A turning exit point and a turning entry point are determined based on the first change rate and the second change rate.

[0011] In a second aspect, an embodiment of the present application further provides a turn identification device, the device comprising:

[0012] An acquisition module, used to acquire a first trajectory sequence of a target vehicle;

[0013] A transformation module, used for performing an affine transformation on the first trajectory sequence to obtain a second trajectory sequence;

[0014] A first determining module, configured to determine a first change rate of the second trajectory sequence in a vertical direction and a second change rate in a horizontal direction;

[0015] The second determination module is used to determine a turning exit point and a turning entry point based on the first change rate and the second change rate.

[0016] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to execute the turning recognition method described in any one of the first aspects.

[0017] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steering recognition method described in any one of the first aspects is executed.

[0018] The embodiments of the present application have the following beneficial effects:

[0019] (1) Reduce dependence on high-precision maps: The system only relies on the vehicle's own trajectory information (including location and starting heading) without the need for additional high-precision map support, which greatly reduces the system's dependence on external data sources and improves the flexibility and popularity of the method.

[0020] (2) Simplify the calculation process and improve efficiency: By directly performing an affine transformation on the vehicle trajectory and determining the entry and exit points based on simple mathematical transformations (such as calculating tangent and cotangent values), the calculation process is greatly simplified and the execution efficiency of the algorithm is improved. This enables the method to respond to the vehicle's steering behavior more quickly, providing strong support for real-time navigation and driver assistance systems.

[0021] (3) Improve the accuracy of cornering and exiting recognition: By accurately calculating the rate of change of the trajectory in the vertical and horizontal directions and accurately determining the cornering and exiting points based on the extreme points, extremely accurate cornering and exiting recognition is achieved. This high-precision recognition capability is of great significance for improving driving safety, optimizing path planning, and reducing unnecessary driving operations.

[0022] (4) Enhanced system reliability and stability: It does not rely on external high-precision map data, and the calculation process is relatively simple, so it is less affected by changes in the external environment (such as weather, road conditions, etc.). This helps to improve the reliability and stability of the entire turn recognition system, ensuring that high recognition accuracy and performance can be maintained in various complex environments.

[0023] (5) Reduce costs and facilitate promotion: It does not require expensive data sources such as high-precision maps, and the calculation method is simple and efficient, so it can significantly reduce the system's R&D and deployment costs. It is easy to promote and apply on various vehicles, providing strong technical support for the development of autonomous driving, intelligent driving assistance and other fields.

[0024] In summary, this steering recognition method has brought significant beneficial effects in improving driving safety, optimizing driving experience and promoting the development of autonomous driving technology by reducing dependence on high-precision maps, simplifying the calculation process, improving recognition accuracy and enhancing system reliability and stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 It is a flowchart of steps S101-S104 provided in an embodiment of the present application;

[0027] Figure 2 It is a flowchart of steps S201-S203 provided in an embodiment of the present application;

[0028] Figure 3 It is a flowchart of steps S301-S302 provided in an embodiment of the present application;

[0029] Figure 4 It is a flowchart of steps S401-S402 provided in an embodiment of the present application;

[0030] Figure 5 It is a flowchart of steps S501-S502 provided in an embodiment of the present application;

[0031] Figure 6 is a schematic diagram of the structure of a turning identification device provided in an embodiment of the present application;

[0032] Figure 7 It is a schematic diagram of the composition structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0033] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0034] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0035] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0036] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0037] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0039] See also Figure 1 , Figure 1is a flow chart of steps S101-S104 of the turn identification method provided in the embodiment of the present application, which will be combined with Figure 1 Steps S101-S104 are shown for explanation.

[0040] In step S101 , a first trajectory sequence of a target vehicle is obtained.

[0041] This step is the basis of the method, which requires collecting the target vehicle's driving trajectory data over a period of time. This data usually contains a series of location coordinates (such as longitude and latitude, X / Y coordinates) and timestamps, reflecting the vehicle's movement path. This data can be obtained through GPS positioning systems, inertial measurement units (IMUs) or other sensors.

[0042] In addition to GPS and IMU, auxiliary processing can also be performed through sensors such as lidar and cameras.

[0043] LiDAR can construct a three-dimensional point cloud map around the vehicle by emitting laser beams into the surrounding environment and receiving the reflected signals. These point cloud data contain the precise location and shape information of roads, obstacles, other vehicles, etc. The point cloud scanned by LiDAR can be matched with a pre-drawn high-precision map, and the position of the vehicle in the current map can be determined by comparing feature points (such as road edges, building outlines, etc.). In the absence of a high-precision map, LiDAR can use algorithms (such as ICP, NDT, etc.) to infer the relative movement and position changes of the vehicle by continuously scanning and comparing the point cloud data of adjacent frames.

[0044] The camera captures images or videos in front of the vehicle, providing rich visual information, including lane lines, traffic signs, pedestrians, other vehicles, etc. Through image processing technology, the camera can identify the lane lines and calculate the vehicle's heading based on the direction of the lane lines. This usually corresponds to the direction of the vehicle's travel and can be used as a reference for the starting heading data.

[0045] In some embodiments, see Figure 2 , Figure 2 is a flow chart of steps S201-S203 provided in an embodiment of the present application, wherein the first trajectory sequence includes vehicle position information and starting heading sequence information of the target vehicle; Figure 1 The illustrated step S101 can be implemented through steps S201 - S203 , which will be described in conjunction with each step.

[0046] In step S201, a data source is determined; wherein the data source includes GPS and IMU.

[0047] First, you need to determine the sensors or systems used to collect data. In this scenario, the main data sources are GPS and IMU. GPS can provide precise location information of the vehicle in the global coordinate system (latitude and longitude or X / Y coordinates), while IMU can measure the acceleration, angular velocity and possible magnetic declination of the vehicle, so as to calculate the heading and attitude of the vehicle.

[0048] In step S202, the vehicle position information is acquired through the GPS, and the starting heading sequence information is acquired through the IMU.

[0049] The GPS receiver continuously receives signals from multiple satellites and uses these signals to calculate the vehicle's current location. This location information is usually expressed in the form of coordinates, and each coordinate point has a corresponding timestamp to record the exact time when the location information was captured.

[0050] The IMU measures the acceleration and angular velocity of the vehicle to calculate the vehicle's heading at a certain moment (i.e. the direction the vehicle is traveling). The IMU data is relative to its internal reference system, so it needs to be calibrated and integrated to obtain the heading in the global coordinate system. The starting heading refers to the heading when the vehicle starts traveling.

[0051] In step S203, trajectory points are constructed based on the vehicle position information and the corresponding timestamps, heading information of the trajectory points is calculated using the IMU data, and the trajectory points are sorted in chronological order to obtain the first trajectory sequence.

[0052] Combining the vehicle position information provided by GPS with the corresponding timestamps can construct a series of track points that record not only the vehicle's position, but also the time sequence in which these positions were captured.

[0053] Using the data provided by the IMU, the heading information corresponding to each trajectory point can be calculated. This usually involves filtering (such as Kalman filtering) and integrating the IMU data to remove noise and estimate the real-time heading of the vehicle.

[0054] Since the data of GPS and IMU are generated in time sequence, the constructed track points should also be in order. However, in practical applications, due to various reasons (such as signal loss, data delay, etc.), the track points may be out of order. Therefore, the track points need to be sorted by timestamp to ensure that they can accurately reflect the vehicle's driving path.

[0055] After the above steps, the first trajectory sequence containing the vehicle position information and heading information can be obtained. This sequence will serve as the basic data for subsequent analysis (such as affine transformation, change rate calculation, etc.).

[0056] In step S102, an affine transformation is performed on the first trajectory sequence to obtain a second trajectory sequence.

[0057] Here, the affine transformation is a linear transformation from two-dimensional coordinates to two-dimensional coordinates, and maintains the "straightness" (i.e., a straight line remains a straight line after transformation) and "parallelism" (i.e., parallel lines remain parallel lines after transformation) of the two-dimensional graphics. In this step, by performing an affine transformation on the original trajectory sequence, some linear offsets or rotations in the trajectory can be removed, making subsequent analysis more accurate. For example, if the vehicle deviates slightly from the direction during driving, the affine transformation can help correct this deviation and make the trajectory closer to the actual driving path.

[0058] In some embodiments, see Figure 3 , Figure 3 is a flowchart of steps S301-S302 provided in an embodiment of the present application, Figure 1 The illustrated step S102 can be implemented through steps S301 - S302 , which will be described in conjunction with each step.

[0059] In step S301, a trajectory starting point in the first trajectory sequence is obtained, and an initial orientation of the first trajectory sequence is determined.

[0060] The start of a track is the first point in the first track sequence, which represents the position where the vehicle starts to travel. The initial heading is the direction the vehicle is traveling at the start of the track. This information can usually be estimated from IMU data or combined with consecutive points in GPS data. The initial heading can be expressed as an angle, which is the angle between the vehicle's direction of travel and a fixed direction (such as true north).

[0061] In step S302, the first trajectory sequence is rotated and translated to a coordinate system with the trajectory starting point as the origin and the initial orientation as the y-axis to obtain the second trajectory sequence.

[0062] Here, a new coordinate system needs to be constructed, and the starting point of the trajectory is selected as the origin of the new coordinate system. Define the initial heading direction as the positive direction of the y-axis of the new coordinate system. This means that if the vehicle is heading north at the starting point, the y-axis of the new coordinate system will point to due north; if the vehicle is heading in another direction, the y-axis will point in that direction accordingly. The x-axis can be determined by the y-axis and the right-hand rule. Specifically, if the y-axis is horizontal (that is, parallel to the ground), then the x-axis will be perpendicular to the y-axis and point to the right; if the y-axis is not horizontal (for example, the vehicle is traveling on a slope), then the x-axis will remain perpendicular to the y-axis, but the direction may need to be adjusted according to actual conditions.

[0063] After that, all points in the first trajectory sequence are translated so that the starting point of the trajectory moves to the origin of the new coordinate system. Next, all points are rotated around the origin so that the tangent direction of the trajectory at the starting point coincides with the y-axis. This rotation operation can be achieved through trigonometric functions and rotation matrices in linear algebra.

[0064] After the above rotation and translation operations, a second trajectory sequence in a new coordinate system can be obtained. Each point in this sequence is repositioned relative to the new origin (i.e., the trajectory starting point) and the new y-axis (i.e., the initial orientation).

[0065] In step S103, a first change rate of the second trajectory sequence in the vertical direction and a second change rate in the horizontal direction are determined.

[0066] After the affine transformation, the position changes of the second trajectory sequence in the vertical (usually Y-axis) and horizontal (usually X-axis) directions can be further analyzed. Calculating the rate of change of position in these two directions (i.e., the approximate value of velocity or acceleration) can reveal the changes in the vehicle's motion state at different time points. Especially during the turning process, these rates of change will fluctuate significantly.

[0067] In some embodiments, see Figure 4 , Figure 4 is a flowchart of steps S401-S402 provided in an embodiment of the present application, Figure 1 The illustrated step S103 can be implemented through steps S401 - S402 , which will be described in conjunction with each step.

[0068] In step S401, for each point in the second trajectory sequence, the difference between each point and the previous point in the x and y directions is calculated respectively.

[0069] Here, for each point in the second trajectory sequence (except the first point, since it has no previous point to compare to), its difference with the previous point in the x and y directions is calculated.

[0070] In step S402, the tangent value and cotangent value of each point are calculated based on the difference to obtain a tangent value sequence and a cotangent value sequence; wherein the tangent value sequence represents a first change rate of the second trajectory sequence in a vertical direction, and the cotangent value sequence represents a second change rate of the second trajectory sequence in a horizontal direction.

[0071] For each point, the difference in the x and y directions is used to calculate the tangent value (the difference in the y direction divided by the difference in the x direction) and the cotangent value (the difference in the x direction divided by the difference in the y direction). The tangent value sequence and the cotangent value sequence can be obtained by calculating the tangent value and the cotangent value sequence, and used for subsequent calculations.

[0072] In step S104, a turning exit point and a turning entry point are determined based on the first change rate and the second change rate.

[0073] Here, by analyzing the rate of change of position in the vertical and horizontal directions, it is possible to identify points where the speed or acceleration of the vehicle changes significantly during driving. During the turning process, especially when entering a curve (turn-in point) and leaving a curve (turn-out point), these rates of change usually have peaks or valleys due to the need to adjust the driving direction and speed. Therefore, by detecting the extreme points of these rates of change, the positions of the turn-out point and turn-in point can be determined more accurately.

[0074] In some embodiments, see Figure 5 , Figure 5 is a flowchart of steps S501-S502 provided in an embodiment of the present application, Figure 1 The illustrated step S104 can be implemented through steps S501 - S502 , which will be described in conjunction with each step.

[0075] In step S501, determine the first extreme point in the tangent value sequence, and determine the second extreme point in the cotangent value sequence; wherein, there is at least one first extreme point, and there is one second extreme point, the first extreme point represents a tangent point in a numerical direction, and the second extreme point represents a tangent point in a horizontal direction.

[0076] Here, we can find the extreme points in the tan / cot value sequence respectively. The extreme value of cot indicates that there is only one tangent point in the horizontal direction, and the extreme value of tan indicates that there may be multiple tangent points in the vertical direction.

[0077] In step S502, the turning exit point and the turning entry point are determined based on the first extreme point and the second extreme point.

[0078] Based on the first extreme point and the second extreme point, we can infer the specific positions of the turning point and the turning point in combination with the overall shape of the track and the driving direction. Specifically, determining the turning exit point and the turning entry point based on the first extreme point and the second extreme point includes:

[0079] Determine the first extreme point closest to the front as the turning point based on the index of the second extreme point;

[0080] Based on the index of the second extreme point, the first extreme point closest to the back is determined as the turning exit point. If there is no first extreme point backward, the second mechanism is used to determine the turning exit point.

[0081] Here, according to the index of the cot extreme point, the nearest extreme point in the tan value sequence is found forward. This tan extreme point is considered to be the entry point because it marks the beginning of the trajectory entering the curve from a straight line. Also according to the index of the cot extreme point, the nearest extreme point is found backward in the tan value sequence. If such a tan extreme point is found, it is considered to be the exit point, marking that the trajectory comes out of the curve and approaches straight line again. However, if there is no tan extreme point backward (this usually happens at the end of the trajectory or there are no more turns immediately after the cot extreme point), the current cot extreme point itself is determined as the exit point.

[0082] In some embodiments, before performing affine transformation on the first trajectory sequence, the method further includes:

[0083] The first trajectory sequence is smoothed by a trajectory smoother; wherein the trajectory smoother includes at least one of the following smoothers:

[0084] Cubic spline smoother, Kalman filter.

[0085] Here, the main purpose of trajectory smoothing is to reduce the noise and irregularities in the data, making subsequent analysis (such as affine transformation, calculation of tan and cot values, finding extreme points, etc.) more accurate and reliable.

[0086] The advantage of the cubic spline smoother is that it can generate smooth and continuous curves, especially when there are many data points and the distribution is relatively uniform. The disadvantage is that it may not be robust enough to outliers or noise in the data, and the computational complexity is relatively high. The advantage of the Kalman filter is that it can combine predicted and observed data to optimally estimate the state of the dynamic system and has good processing capabilities for noise and outliers. The disadvantage is that the dynamic model of the system (i.e., the state transfer equation and the observation equation) needs to be known in advance, and for nonlinear systems, variants such as the extended Kalman filter (EKF) or the unscented Kalman filter (UKF) need to be used.

[0087] Smoothing can be achieved by following the steps below:

[0088] Data preprocessing: Check the validity of the data and remove obvious errors or outliers.

[0089] Select a smoother: Select an appropriate smoother based on data characteristics and application scenarios.

[0090] Configuration parameters: Configure necessary parameters for the selected smoother, such as smoothness, number of iterations, noise covariance, etc.

[0091] Perform smoothing: Input the first trajectory sequence into the smoother and perform smoothing.

[0092] Result evaluation: Evaluate whether the smoothing result meets expectations, and adjust parameters or select other smoothers if necessary.

[0093] In summary, the embodiments of the present application have the following beneficial effects:

[0094] (1) Reduce dependence on high-precision maps: The system only relies on the vehicle's own trajectory information (including location and starting heading) without the need for additional high-precision map support, which greatly reduces the system's dependence on external data sources and improves the flexibility and popularity of the method.

[0095] (2) Simplify the calculation process and improve efficiency: By directly performing an affine transformation on the vehicle trajectory and determining the entry and exit points based on simple mathematical transformations (such as calculating tangent and cotangent values), the calculation process is greatly simplified and the execution efficiency of the algorithm is improved. This enables the method to respond to the vehicle's steering behavior more quickly, providing strong support for real-time navigation and driver assistance systems.

[0096] (3) Improve the accuracy of cornering and exiting recognition: By accurately calculating the rate of change of the trajectory in the vertical and horizontal directions and accurately determining the cornering and exiting points based on the extreme points, extremely accurate cornering and exiting recognition is achieved. This high-precision recognition capability is of great significance for improving driving safety, optimizing path planning, and reducing unnecessary driving operations.

[0097] (4) Enhanced system reliability and stability: It does not rely on external high-precision map data, and the calculation process is relatively simple, so it is less affected by changes in the external environment (such as weather, road conditions, etc.). This helps to improve the reliability and stability of the entire turn recognition system, ensuring that high recognition accuracy and performance can be maintained in various complex environments.

[0098] (5) Reduce costs and facilitate promotion: It does not require expensive data sources such as high-precision maps, and the calculation method is simple and efficient, so it can significantly reduce the system's R&D and deployment costs. It is easy to promote and apply on various vehicles, providing strong technical support for the development of autonomous driving, intelligent driving assistance and other fields.

[0099] In summary, this steering recognition method has brought significant beneficial effects in improving driving safety, optimizing driving experience and promoting the development of autonomous driving technology by reducing dependence on high-precision maps, simplifying the calculation process, improving recognition accuracy and enhancing system reliability and stability.

[0100] Based on the same inventive concept, an embodiment of the present application also provides a steering identification device corresponding to the steering identification method in the first embodiment. Since the principle of solving the problem by the device in the embodiment of the present application is similar to that of the above-mentioned steering identification method, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0101] like Figure 6 As shown, Figure 6 : is a schematic diagram of the structure of a turning identification device 600 provided in an embodiment of the present application. The turning identification device 600 includes:

[0102] An acquisition module 601 is used to acquire a first trajectory sequence of a target vehicle;

[0103] A transformation module 602, configured to perform an affine transformation on the first trajectory sequence to obtain a second trajectory sequence;

[0104] A first determining module 603, configured to determine a first change rate of the second trajectory sequence in a vertical direction and a second change rate in a horizontal direction;

[0105] The second determination module 604 is configured to determine a turning exit point and a turning entry point based on the first change rate and the second change rate.

[0106] Those skilled in the art should understand that Figure 6 The implementation functions of each unit in the steering recognition device 600 shown can be understood by referring to the relevant description of the steering recognition method mentioned above. Figure 6 The functions of the various units in the turning recognition device 600 shown can be implemented by a program running on a processor, or can be implemented by a specific logic circuit.

[0107] In a possible implementation, the first trajectory sequence includes the vehicle position information and the starting heading sequence information of the target vehicle, and the acquisition module 601 acquires the first trajectory sequence of the target vehicle, including:

[0108] Determine a data source; wherein the data source includes GPS and IMU;

[0109] Acquire the vehicle position information through the GPS, and acquire the starting heading sequence information through the IMU;

[0110] Trajectory points are constructed based on the vehicle position information and corresponding timestamps, heading information of the trajectory points is calculated using the IMU data, and the trajectory points are sorted in chronological order to obtain the first trajectory sequence.

[0111] In a possible implementation, the transformation module 602 performs an affine transformation on the first trajectory sequence to obtain a second trajectory sequence, including:

[0112] Obtaining a trajectory starting point in the first trajectory sequence, and determining an initial orientation of the first trajectory sequence;

[0113] The first trajectory sequence is rotated and translated to a coordinate system with the trajectory starting point as the origin and the initial orientation as the y-axis to obtain the second trajectory sequence.

[0114] In a possible implementation, the first determining module 603 determines a first change rate in a vertical direction and a second change rate in a horizontal direction of the second trajectory sequence, including:

[0115] For each point in the second trajectory sequence, respectively calculate the difference between each point and the previous point in the x and y directions;

[0116] The tangent value and cotangent value of each point are calculated based on the difference to obtain a tangent value sequence and a cotangent value sequence; wherein the tangent value sequence represents a first change rate of the second trajectory sequence in a vertical direction, and the cotangent value sequence represents a second change rate of the second trajectory sequence in a horizontal direction.

[0117] In a possible implementation manner, the second determination module 604 determines the turning exit point and the turning entrance point based on the first change rate and the second change rate, including:

[0118] Determine a first extreme point in the tangent value sequence, and determine a second extreme point in the cotangent value sequence; wherein the first extreme point is at least one, the second extreme point is one, the first extreme point represents a tangent point in a numerical direction, and the second extreme point represents a tangent point in a horizontal direction;

[0119] The turning exit point and the turning entry point are determined based on the first extreme point and the second extreme point.

[0120] In a possible implementation manner, the second determining module 604 determines the turning exit point and the turning entry point based on the first extreme point and the second extreme point, including:

[0121] Determine the first extreme point closest to the front as the turning point based on the index of the second extreme point;

[0122] Based on the index of the second extreme point, the first extreme point closest to the back is determined as the turning exit point. If there is no first extreme point backward, the second mechanism is used to determine the turning exit point.

[0123] In a possible implementation, before the transformation module 602 performs affine transformation on the first trajectory sequence, the method further includes:

[0124] The first trajectory sequence is smoothed by a trajectory smoother; wherein the trajectory smoother includes at least one of the following smoothers:

[0125] Cubic spline smoother, Kalman filter.

[0126] The above-mentioned turning recognition device has the following beneficial effects:

[0127] (1) Reduce dependence on high-precision maps: The system only relies on the vehicle's own trajectory information (including location and starting heading) without the need for additional high-precision map support, which greatly reduces the system's dependence on external data sources and improves the flexibility and popularity of the method.

[0128] (2) Simplify the calculation process and improve efficiency: By directly performing an affine transformation on the vehicle trajectory and determining the entry and exit points based on simple mathematical transformations (such as calculating tangent and cotangent values), the calculation process is greatly simplified and the execution efficiency of the algorithm is improved. This enables the method to respond to the vehicle's steering behavior more quickly, providing strong support for real-time navigation and driver assistance systems.

[0129] (3) Improve the accuracy of cornering and exiting recognition: By accurately calculating the rate of change of the trajectory in the vertical and horizontal directions and accurately determining the cornering and exiting points based on the extreme points, extremely accurate cornering and exiting recognition is achieved. This high-precision recognition capability is of great significance for improving driving safety, optimizing path planning, and reducing unnecessary driving operations.

[0130] (4) Enhanced system reliability and stability: It does not rely on external high-precision map data, and the calculation process is relatively simple, so it is less affected by changes in the external environment (such as weather, road conditions, etc.). This helps to improve the reliability and stability of the entire turn recognition system, ensuring that high recognition accuracy and performance can be maintained in various complex environments.

[0131] (5) Reduce costs and facilitate promotion: It does not require expensive data sources such as high-precision maps, and the calculation method is simple and efficient, so it can significantly reduce the system's R&D and deployment costs. It is easy to promote and apply on various vehicles, providing strong technical support for the development of autonomous driving, intelligent driving assistance and other fields.

[0132] In summary, this steering recognition method has brought significant beneficial effects in improving driving safety, optimizing driving experience and promoting the development of autonomous driving technology by reducing dependence on high-precision maps, simplifying the calculation process, improving recognition accuracy and enhancing system reliability and stability.

[0133] like Figure 7 As shown, Figure 7The present invention provides a schematic diagram of the structure of an electronic device 700, wherein the electronic device 700 includes:

[0134] A processor 701, a storage medium 702 and a bus 703, wherein the storage medium 702 stores machine-readable instructions executable by the processor 701. When the electronic device 700 is running, the processor 701 communicates with the storage medium 702 via the bus 703, and the processor 701 executes the machine-readable instructions to perform the steps of the steering recognition method described in the embodiment of the present application.

[0135] In actual application, the components in the electronic device 700 are coupled together via the bus 703. It is understood that the bus 703 is used to realize the connection and communication between these components. In addition to the data bus, the bus 703 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Figure 7 Various buses are labeled as bus 703.

[0136] The above electronic device has the following beneficial effects:

[0137] (1) Reduce dependence on high-precision maps: The system only relies on the vehicle's own trajectory information (including location and starting heading) without the need for additional high-precision map support, which greatly reduces the system's dependence on external data sources and improves the flexibility and popularity of the method.

[0138] (2) Simplify the calculation process and improve efficiency: By directly performing an affine transformation on the vehicle trajectory and determining the entry and exit points based on simple mathematical transformations (such as calculating tangent and cotangent values), the calculation process is greatly simplified and the execution efficiency of the algorithm is improved. This enables the method to respond to the vehicle's steering behavior more quickly, providing strong support for real-time navigation and driver assistance systems.

[0139] (3) Improve the accuracy of cornering and exiting recognition: By accurately calculating the rate of change of the trajectory in the vertical and horizontal directions and accurately determining the cornering and exiting points based on the extreme points, extremely accurate cornering and exiting recognition is achieved. This high-precision recognition capability is of great significance for improving driving safety, optimizing path planning, and reducing unnecessary driving operations.

[0140] (4) Enhanced system reliability and stability: It does not rely on external high-precision map data, and the calculation process is relatively simple, so it is less affected by changes in the external environment (such as weather, road conditions, etc.). This helps to improve the reliability and stability of the entire turn recognition system, ensuring that high recognition accuracy and performance can be maintained in various complex environments.

[0141] (5) Reduce costs and facilitate promotion: It does not require expensive data sources such as high-precision maps, and the calculation method is simple and efficient, so it can significantly reduce the system's R&D and deployment costs. It is easy to promote and apply on various vehicles, providing strong technical support for the development of autonomous driving, intelligent driving assistance and other fields.

[0142] In summary, this steering recognition method has brought significant beneficial effects in improving driving safety, optimizing driving experience and promoting the development of autonomous driving technology by reducing dependence on high-precision maps, simplifying the calculation process, improving recognition accuracy and enhancing system reliability and stability.

[0143] The embodiment of the present application further provides a computer-readable storage medium, which stores executable instructions. When the executable instructions are executed by at least one processor 701, the steering recognition method described in the embodiment of the present application is implemented.

[0144] In some embodiments, the storage medium can be a magnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface storage, an optical disk, or a compact disc read-only memory (CD ROM); it can also be various devices including one or any combination of the above memories.

[0145] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0146] As an example, executable instructions may, but do not necessarily, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, for example, in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (for example, files storing one or more modules, subroutines, or code portions).

[0147] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0148] The computer-readable storage medium has the following advantages:

[0149] (1) Reduce dependence on high-precision maps: The system only relies on the vehicle's own trajectory information (including location and starting heading) without the need for additional high-precision map support, which greatly reduces the system's dependence on external data sources and improves the flexibility and popularity of the method.

[0150] (2) Simplify the calculation process and improve efficiency: By directly performing an affine transformation on the vehicle trajectory and determining the entry and exit points based on simple mathematical transformations (such as calculating tangent and cotangent values), the calculation process is greatly simplified and the execution efficiency of the algorithm is improved. This enables the method to respond to the vehicle's steering behavior more quickly, providing strong support for real-time navigation and driver assistance systems.

[0151] (3) Improve the accuracy of cornering and exiting recognition: By accurately calculating the rate of change of the trajectory in the vertical and horizontal directions and accurately determining the cornering and exiting points based on the extreme points, extremely accurate cornering and exiting recognition is achieved. This high-precision recognition capability is of great significance for improving driving safety, optimizing path planning, and reducing unnecessary driving operations.

[0152] (4) Enhanced system reliability and stability: It does not rely on external high-precision map data, and the calculation process is relatively simple, so it is less affected by changes in the external environment (such as weather, road conditions, etc.). This helps to improve the reliability and stability of the entire turn recognition system, ensuring that high recognition accuracy and performance can be maintained in various complex environments.

[0153] (5) Reduce costs and facilitate promotion: It does not require expensive data sources such as high-precision maps, and the calculation method is simple and efficient, so it can significantly reduce the system's R&D and deployment costs. It is easy to promote and apply on various vehicles, providing strong technical support for the development of autonomous driving, intelligent driving assistance and other fields.

[0154] In summary, this steering recognition method has brought significant beneficial effects in improving driving safety, optimizing driving experience and promoting the development of autonomous driving technology by reducing dependence on high-precision maps, simplifying the calculation process, improving recognition accuracy and enhancing system reliability and stability.

[0155] In the several embodiments provided in the present application, it should be understood that the disclosed methods and electronic devices can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

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

[0157] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0158] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a platform server, or a network device, etc.) 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 USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0159] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A turning identification method, characterized in that: The method comprises: Obtaining a first trajectory sequence of the target vehicle; Performing an affine transformation on the first trajectory sequence to obtain a second trajectory sequence; determining a first change rate of the second trajectory sequence in a vertical direction and a second change rate of the second trajectory sequence in a horizontal direction; A turning exit point and a turning entry point are determined based on the first change rate and the second change rate.

2. The method according to claim 1, characterized in that The first trajectory sequence includes the vehicle position information and the starting heading sequence information of the target vehicle; the first trajectory sequence of the target vehicle is obtained, including: Determine a data source; wherein the data source includes GPS and IMU; Acquire the vehicle position information through the GPS, and acquire the starting heading sequence information through the IMU; Trajectory points are constructed based on the vehicle position information and corresponding timestamps, heading information of the trajectory points is calculated using the IMU data, and the trajectory points are sorted in chronological order to obtain the first trajectory sequence.

3. The method according to claim 1, characterized in that The step of performing an affine transformation on the first trajectory sequence to obtain a second trajectory sequence includes: Obtaining a trajectory starting point in the first trajectory sequence, and determining an initial orientation of the first trajectory sequence; The first trajectory sequence is rotated and translated to a coordinate system with the trajectory starting point as the origin and the initial orientation as the y-axis to obtain the second trajectory sequence.

4. The method according to claim 1, characterized in that: The determining of a first change rate of the second trajectory sequence in a vertical direction and a second change rate in a horizontal direction includes: For each point in the second trajectory sequence, respectively calculate the difference between each point and the previous point in the x and y directions; The tangent value and cotangent value of each point are calculated based on the difference to obtain a tangent value sequence and a cotangent value sequence; wherein the tangent value sequence represents a first change rate of the second trajectory sequence in a vertical direction, and the cotangent value sequence represents a second change rate of the second trajectory sequence in a horizontal direction.

5. The method according to claim 4, characterized in that The determining of a turning exit point and a turning entry point based on the first change rate and the second change rate comprises: Determine a first extreme point in the tangent value sequence, and determine a second extreme point in the cotangent value sequence; wherein the first extreme point is at least one, the second extreme point is one, the first extreme point represents a tangent point in a numerical direction, and the second extreme point represents a tangent point in a horizontal direction; The turning exit point and the turning entry point are determined based on the first extreme point and the second extreme point.

6. The method according to claim 5, characterized in that The determining the cornering point and the cornering point based on the first extreme point and the second extreme point comprises: Determine the first extreme point closest to the front as the turning point based on the index of the second extreme point; Based on the index of the second extreme point, the first extreme point closest to the back is determined as the turning exit point. If there is no first extreme point backward, the second mechanism is used to determine the turning exit point.

7. The method according to claim 1, characterized in that Before performing affine transformation on the first trajectory sequence, the method further includes: The first trajectory sequence is smoothed by a trajectory smoother; wherein the trajectory smoother includes at least one of the following smoothers: Cubic spline smoother, Kalman filter.

8. A turning recognition device, characterized in that: The device comprises: An acquisition module, used to acquire a first trajectory sequence of a target vehicle; A transformation module, used for performing an affine transformation on the first trajectory sequence to obtain a second trajectory sequence; A first determining module, configured to determine a first change rate of the second trajectory sequence in a vertical direction and a second change rate in a horizontal direction; The second determination module is used to determine a turning exit point and a turning entry point based on the first change rate and the second change rate.

9. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the storage medium communicate via the bus, and the processor executes the machine-readable instructions to perform the steering recognition method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the turning identification method according to any one of claims 1 to 7 is executed.

Images