Method, device, electronic device and storage medium for determining vehicle track

Abstract

Embodiments of the present disclosure disclose a method, apparatus, electronic device, and storage medium for determining a vehicle trajectory. The method includes: determining a first angular velocity corresponding to a current frame based on chassis signals; determining a current angular velocity offset based on the first angular velocity, a first lane line perception result corresponding to the current frame, and a second lane line perception result corresponding to a previous frame; correcting the first angular velocity based on the current angular velocity offset to obtain a corrected second angular velocity; and determining the vehicle trajectory based on the second angular velocity. Embodiments of the present disclosure estimate the angular velocity offset through the perception of lane lines, correct the angular velocity based on the angular velocity offset, and thus perform vehicle dead reckoning based on the corrected angular velocity, effectively improving the accuracy of the dead reckoning result and solving problems such as poor accuracy of vehicle dead reckoning results in sections without effective reference objects in the prior art.

Description

Technical Field

[0001] The present disclosure relates to autonomous driving technology, and in particular to a method, apparatus, electronic device, and storage medium for determining a vehicle trajectory. Background Art

[0002] Vehicle trajectory estimation based on chassis signals is one of the odometer sources in autonomous driving scenarios, and its accuracy directly affects the effects of downstream parts. To improve the accuracy of the trajectory, vehicle manufacturers usually calibrate signals such as the speed and angular velocity of the vehicle chassis. Trajectory estimation mainly calculates the driving distance of the vehicle and the change in the yaw angle (yaw angle) between two frames of chassis signals, and then continuously accumulates to obtain the vehicle trajectory estimation result. As the accumulation continues, the errors of the chassis sensors continue to accumulate, which easily leads to inaccurate estimation results. To address this problem, existing technologies usually correct the estimation results through the perception of effective reference objects (such as road signs) to improve the accuracy of the final results. However, the method of correcting the estimation results based on reference objects cannot correct the estimation results when there are no reference objects or the reference objects cannot be perceived, resulting in a low accuracy of the determined vehicle trajectory. Summary of the Invention

[0003] To solve the above technical problems such as the low accuracy of the estimation results, the present disclosure is proposed. Embodiments of the present disclosure provide a method, apparatus, electronic device, and storage medium for determining a vehicle trajectory.

[0004] According to one aspect of the embodiments of the present disclosure, a method for determining a vehicle trajectory is provided, including: determining a first angular velocity corresponding to a current frame based on chassis signals; determining a current angular velocity offset based on the first angular velocity, a first lane line perception result corresponding to the current frame, and a second lane line perception result corresponding to a previous frame; correcting the first angular velocity based on the current angular velocity offset to obtain a corrected second angular velocity; and determining the vehicle trajectory based on the second angular velocity.

[0005] According to another aspect of the embodiments of the present disclosure, a device for determining a vehicle trajectory is provided, including: a first determination module for determining a first angular velocity corresponding to a current frame based on chassis signals; a first processing module for determining a current angular velocity offset based on the first angular velocity, a first lane line perception result corresponding to the current frame, and a second lane line perception result corresponding to a previous frame; a second processing module for correcting the first angular velocity based on the current angular velocity offset to obtain a corrected second angular velocity; and a third processing module for determining the vehicle trajectory based on the second angular velocity.

[0006] According to another aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program for executing the method for determining a vehicle trajectory according to any one of the above embodiments of the present disclosure.

[0007] According to yet another aspect of the embodiments of the present disclosure, there is provided an electronic device including: a processor; a memory for storing executable instructions executable by the processor; and the processor for reading the executable instructions from the memory and executing the instructions to implement the method for determining a vehicle trajectory according to any one of the above embodiments of the present disclosure.

[0008] Based on the method, device, electronic device, and storage medium for determining a vehicle trajectory provided in the above embodiments of the present disclosure, the angular velocity bias is estimated by sensing lane lines, the angular velocity is corrected based on the angular velocity bias, and then vehicle dead reckoning is performed based on the corrected angular velocity, effectively improving the accuracy of the dead reckoning result and enabling the vehicle dead reckoning result to have a high accuracy even on a section without effective reference objects.

[0009] The technical solution of the present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. Description of the Drawings

[0010] By describing the embodiments of the present disclosure in more detail with reference to the accompanying drawings, the above and other objects, features, and advantages of the present disclosure will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation to the present disclosure. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0011] Figure 1 is an exemplary application scenario of the method for determining a vehicle trajectory provided by the present disclosure;

[0012] Figure 2 is a flowchart of the method for determining a vehicle trajectory provided by an exemplary embodiment of the present disclosure;

[0013] Figure 3 is a flowchart of the method for determining a vehicle trajectory provided by another exemplary embodiment of the present disclosure;

[0014] Figure 4 is a flowchart of step 202 provided by an exemplary embodiment of the present disclosure;

[0015] Figure 5 is a schematic diagram of the relationship between the current frame and the lane lines of the vehicle and the target lane in the previous frame provided by an exemplary embodiment of the present disclosure;

[0016] Figure 6It is a schematic structural diagram of a vehicle trajectory determination device provided by an exemplary embodiment of the present disclosure;

[0017] Figure 7 It is a schematic structural diagram of a vehicle trajectory determination device provided by an exemplary embodiment of the present disclosure;

[0018] Figure 8 It is a schematic structural diagram of the first processing module 502 provided by an exemplary embodiment of the present disclosure;

[0019] Figure 9 It is a schematic structural diagram of an application embodiment of an electronic device of the present disclosure. Detailed implementation manners

[0020] Next, exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all embodiments of the present disclosure. It should be understood that the present disclosure is not limited by the exemplary embodiments described herein.

[0021] It should be noted that: unless otherwise specifically stated, the relative arrangements, numerical expressions, and numerical values of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0022] Those skilled in the art can understand that the terms "first", "second", etc. in the embodiments of the present disclosure are only used to distinguish different steps, devices, or modules, etc., and do not represent any specific technical meaning, nor do they represent an inevitable logical order between them.

[0023] It should also be understood that in the embodiments of the present disclosure, "a plurality" may refer to two or more, and "at least one" may refer to one, two, or more.

[0024] It should also be understood that for any component, data, or structure mentioned in the embodiments of the present disclosure, without clear limitation or contrary indication in the context, it can generally be understood as one or more.

[0025] In addition, the term "and / or" in the present disclosure is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present disclosure generally represents an "or" relationship between the associated objects before and after.

[0026] It should also be understood that the present disclosure emphasizes the differences between the various embodiments. The same or similar parts can be referred to each other. For the sake of brevity, they will not be described one by one.

[0027] Meanwhile, it should be understood that, for the sake of description convenience, the dimensions of the various parts shown in the drawings are not drawn in actual proportional relationship.

[0028] The following description of at least one exemplary embodiment is in fact merely illustrative and in no way restrictive of the present disclosure, its application, or its use.

[0029] Techniques, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be regarded as part of the specification.

[0030] It should be noted that: like reference numerals and letters denote like items in the following drawings, and thus, once an item is defined in one drawing, further discussion thereof is not required in subsequent drawings.

[0031] Embodiments of the present disclosure can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the above systems, and so on.

[0032] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system-executable instructions (such as program modules) executed by a computer system. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. The computer system / server can be implemented in a distributed cloud computing environment where tasks are executed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0033] Overview of the present disclosure

[0034] In the process of implementing the present disclosure, the inventors found that vehicle odometry based on chassis signals is one of the sources of odometers in the autonomous driving scenario, and its accuracy has a direct impact on the effects of downstream components. To improve the accuracy of the odometry, vehicle manufacturers usually calibrate signals such as the speed and angular velocity of the vehicle chassis. Odometry mainly calculates the driving distance of the vehicle and the change in the yaw angle (yaw angle) between two frames of chassis signals, and then continuously accumulates to obtain the odometry result of the vehicle. As the accumulation continues, the errors of the chassis sensors accumulate continuously, which easily leads to inaccurate calculation results. To address this problem, the prior art usually corrects the calculation results through the perception of effective reference objects to improve the accuracy of the final results. However, the method of correcting the calculation results based on reference objects cannot correct the calculation results when there is no reference object or the reference object cannot be perceived, resulting in a low accuracy of the determined vehicle odometry.

[0035] Exemplary overview

[0036] Figure 1 is an exemplary application scenario of the method for determining a vehicle odometry provided by the present disclosure.

[0037] In the autonomous driving scenario, by executing the method for determining a vehicle odometry of the present disclosure through a vehicle odometry determination device, after determining the first angular velocity corresponding to the current frame based on the chassis signals, the current angular velocity offset can be determined based on the first angular velocity, the first lane line perception result corresponding to the current frame, and the second lane line perception result corresponding to the previous frame. Then, based on the current angular velocity offset, the first angular velocity is corrected to obtain the corrected second angular velocity. Based on the second angular velocity, the vehicle odometry is determined. By realizing the determination of the angular velocity offset through the lane lines perceived in different frames, and then realizing the correction of the angular velocity, even on sections without effective reference objects, the accuracy of the vehicle odometry can be effectively improved.

[0038] Exemplary method

[0039] Figure 2 is a schematic flowchart of the method for determining a vehicle odometry provided by an exemplary embodiment of the present disclosure. This embodiment can be applied to an electronic device, specifically, for example, on an in-vehicle computing platform, as Figure 2 shown, and includes the following steps:

[0040] Step 201, determine the first angular velocity corresponding to the current frame based on the chassis signals.

[0041] Among them, the chassis signals may include vehicle speed signals, wheel speed meter signals, angular velocity signals, etc. The current frame is the frame corresponding to the current moment, and the first angular velocity corresponding to the current frame can be determined based on the angular velocity signal in the currently collected chassis signals of the current frame.

[0042] Step 202: Determine the current angular velocity bias based on the first angular velocity, the first lane line perception result corresponding to the current frame, and the second lane line perception result corresponding to the previous frame.

[0043] Among them, the first lane line perception result corresponding to the current frame is the lane line perception result obtained by perceiving the currently collected road image data. Specifically, the first lane line perception result can be obtained through a preset perception algorithm or a pre-trained perception model (such as a lane line detection model). The first lane line perception result can include the relevant information of one or more lane lines obtained based on the current frame road image data, such as the pixel information of the lane lines in the road image data, which can be specifically set according to actual needs. The previous frame can be any frame before the current frame, such as the previous frame of the current frame, or a frame that is separated from the current frame by a preset number of frames before the current frame, and the specific is not limited. The second lane line perception result corresponding to the previous frame is the lane line perception result obtained by perceiving the road image data collected at the corresponding time of the previous frame. The current angular velocity bias can be obtained by comparing the projection of the lane line in the first lane line perception result onto the previous frame with the direction angle of the same lane line in the second lane line perception result of the previous frame. For example, the lane line in the first lane line perception result and the lane line in the second lane line perception result are converted into the vehicle coordinate system of the corresponding frame to obtain the first lane line equation and the second lane line equation in the vehicle coordinate system respectively corresponding to them, and the yaw angle change amount from the previous frame to the current frame is determined based on the first angular velocity. Based on this yaw angle change amount, the direction angle of the first lane line equation in the current frame is reversely offset, so as to project the lane line corresponding to the first lane line equation onto the previous frame to obtain the projection direction angle. By comparing the projection direction angle with the direction angle of the lane line corresponding to the second lane line equation in the previous frame, the direction angle error can be obtained. Combining the time difference between the previous frame and the current frame, the current angular velocity bias can be determined.

[0044] Step 203: Correct the first angular velocity based on the current angular velocity bias to obtain the corrected second angular velocity.

[0045] Among them, the corrected second angular velocity can be obtained by adding the first angular velocity and the current angular velocity bias.

[0046] Step 204: Determine the vehicle's trajectory based on the second angular velocity.

[0047] Among them, the vehicle's trajectory includes the driving trajectory of the vehicle, which specifically may include the pose of the vehicle in each frame (which may include the position (such as the X, Y, and Z coordinates in the world coordinate system) and the attitude (which may include the yaw angle)). After determining the corrected second angular velocity, the change amount of the yaw angle of the vehicle in the current frame relative to the yaw angle in the previous frame can be determined based on the second angular velocity. Furthermore, based on the yaw angle of the vehicle determined in the previous frame and the change amount of the yaw angle of the current frame relative to the previous frame, the yaw angle of the vehicle in the current frame can be determined. Combining the driving distance of the current frame relative to the previous frame and the position of the vehicle in the previous frame, the vehicle's trajectory can be determined. The driving distance of the current frame relative to the previous frame can be obtained based on the speed of the vehicle determined from the chassis signal and the time interval between the current frame and the previous frame, and the details will not be elaborated here.

[0048] The method for determining the vehicle trajectory provided in this embodiment determines the angular velocity offset through the lane line perception results of different front and rear frames, realizes the correction of the angular velocity. Even on sections without effective reference objects, a more accurate vehicle trajectory can be determined, effectively improving the accuracy of the determined vehicle trajectory.

[0049] Figure 3 It is a schematic flowchart of the method for determining the vehicle trajectory provided in another exemplary embodiment of the present disclosure.

[0050] In an optional example, step 202 may specifically include the following steps:

[0051] Step 2021, based on the first angular velocity and the first time between the current frame and the previous frame, determine the first yaw angle change amount of the current frame relative to the previous frame.

[0052] Among them, the first yaw angle change amount refers to the change amount of the current yaw angle of the vehicle relative to the yaw angle of the vehicle in the previous frame after moving for the first time. The change in the yaw angle is caused by the accumulation of the angular velocity over time. Therefore, based on the first angular velocity and the first time, the first yaw angle change amount can be determined.

[0053] Step 2022, based on the first lane line perception result, determine the first lane line equation of the target lane in the vehicle coordinate system corresponding to the current frame.

[0054] Among them, the target lane can be the lane where the vehicle is currently located. The first lane line equation can include the lane line equation on the first side (such as the left side) and / or the second side (such as the right side) of the target lane, or the first lane line equation can also be the equation corresponding to the center line of the target lane, which can be specifically set according to actual requirements. The first lane line perception result includes the pixel information of the lane lines in the current frame of road image data. By converting the lane line pixel information into the vehicle coordinate system corresponding to the current frame, the corresponding lane line coordinate points in the vehicle coordinate system can be obtained, and then the first lane line equation in the vehicle coordinate system can be obtained through fitting. For example, the first lane line equation is a straight line equation, expressed as y = kx + b, where k and b are the coefficients of the linear equation. The specific type of the first lane line equation can be determined according to the actual lane line situation.

[0055] Step 2023: Based on the second lane line perception result, determine the second lane line equation of the target lane in the vehicle coordinate system corresponding to the previous frame.

[0056] Among them, the principle of determining the second lane line equation in the vehicle coordinate system corresponding to the previous frame is similar to that of the aforementioned first lane line equation, which will not be elaborated here.

[0057] In practical applications, if the second lane line equation has been determined and stored in the processing flow corresponding to the previous frame, it can be directly obtained from the corresponding storage area in the processing flow of the current frame without further processing. The determination of the lane lines that belong to the target lane in both the current frame and the previous frame can be determined through lane line target tracking, which will not be elaborated here.

[0058] Steps 2021, 2022, and 2023 have no sequence.

[0059] Step 2024: Based on the first yaw angle change amount, the first lane line equation, and the second lane line equation, determine the current angular velocity bias.

[0060] Among them, the first yaw angle variation characterizes the change in the vehicle's yaw angle. The first lane line equation and the second lane line equation can represent the direction angles of the lane lines in the vehicle coordinate system of the current frame and the previous frame. Since the time interval between the current frame and the previous frame is very short, for a straight lane line, if the vehicle's yaw angle in the current frame has not changed relative to the previous frame and there is no error in the angular velocity, the direction angles of the lane lines perceived in the two frames should be the same. When the vehicle's yaw angle has changed by a certain amount (such as the first yaw angle variation), the direction angle of this straight lane line in the vehicle coordinate system relative to the vehicle coordinate system also changes by a certain amount. Based on this change, the first lane line equation of the current frame is projected backward to the previous frame. If there is no error in the angular velocity, it should be the same as the direction angle in the previous frame. Or there is an overlapping part of the same lane line in the perception results of the two frames. When the overlapping part in the two frames is unified into the same coordinate system, the direction angles of the overlapping part should be the same. The overlapping part can be determined by feature matching. Based on this principle, the first lane line equation can be projected to the previous frame based on the first yaw angle variation to determine the direction angle error between the two, and this direction angle error can characterize the accumulation of the angular velocity error. Therefore, the current angular velocity bias can be determined based on this.

[0061] The present disclosure determines the first yaw angle variation of the current frame relative to the previous frame through the first angular velocity of the current frame, and then based on the first yaw angle variation, the first lane line equation and the second lane line equation are unified into the same coordinate system for comparison to determine the current angular velocity bias, realizing the angular velocity correction based on lane line perception, effectively improving the accuracy of the determined vehicle trajectory. Even on sections without effective reference objects such as road signs, a more accurate vehicle trajectory can still be obtained, improving the versatility.

[0062] Figure 4 It is a schematic flowchart of step 202 provided by an exemplary embodiment of the present disclosure.

[0063] In an optional example, determining the current angular velocity bias based on the first yaw angle variation, the first lane line equation, and the second lane line equation in step 2024 includes:

[0064] Step 20241, in response to both the first lane line equation and the second lane line equation being straight line equations, based on the first yaw angle variation, project the lane line of the target lane described by the first lane line equation to the previous frame to obtain the first direction angle corresponding to the lane line of the target lane in the previous frame. The first direction angle is the included angle between the lane line of the target lane and the longitudinal axis of the vehicle coordinate system corresponding to the previous frame.

[0065] Among them, when both the first lane line equation and the second lane line equation are straight lines, it indicates that the lane line of the target lane is a straight lane line, and its direction is determined. Corresponding to the previous frame and the current frame, due to the change in the vehicle's yaw angle, the direction angles of the first lane line equation and the second lane line equation in the vehicle coordinate system of their corresponding frames are different. That is to say, it is considered that the current direction angle of the first lane line equation in the vehicle coordinate system of the current frame is obtained by offsetting the direction angle of the second lane line equation in the previous frame by the first yaw angle change amount relative to the vehicle coordinate system. Therefore, based on the first yaw angle change amount of the vehicle, the lane line of the target lane described by the first lane line equation in the current frame can be projected onto the previous frame to obtain the first direction angle of this lane line in the previous frame. For example, by reversely offsetting the direction angle of the first lane line in the current frame by the first yaw angle change amount to make it return to the state at the corresponding moment in the previous frame, the first direction angle can be obtained. If the angular velocity has no error, this first direction angle should be the same as the second direction angle of the first lane line equation. The difference between the first direction angle and the second direction angle characterizes the angular velocity error.

[0066] Step 20242: Based on the second lane line equation, determine the second direction angle corresponding to the lane line of the target lane in the previous frame.

[0067] Among them, the second lane line equation is, for example, y = k2x + b2, where (x, y) represents the coordinates in the vehicle coordinate system corresponding to the previous frame, and k2 (slope) and b2 (intercept) represent the first-order equation coefficients of the second lane line equation. Its second direction angle can be calculated using the inverse trigonometric function arctan through the slope k2 of the second lane line equation, and the specific principle will not be elaborated here.

[0068] Step 20243: Based on the first direction angle and the second direction angle, determine the direction angle error.

[0069] Among them, the direction angle error can be determined by the difference between the second direction angle and the first direction angle.

[0070] Step 20244: Based on the direction angle error and the first time, determine the first angular velocity offset.

[0071] Among them, as described above, if there is an error between the first direction angle and the second direction angle, it characterizes the angular velocity error. Therefore, based on the direction angle error and the first time between the current frame and the previous frame, the first angular velocity offset can be determined, and the first angular velocity offset characterizes the angular velocity error of the current frame relative to the previous frame.

[0072] Step 20245: Based on the first angular velocity offset and the Kalman filter algorithm, determine the current angular velocity offset.

[0073] Among them, in order to further improve the accuracy of the angular velocity bias, after obtaining the first angular velocity bias, the first angular velocity bias can also be optimized based on the Kalman filter algorithm to determine the optimized angular velocity bias as the current angular velocity bias.

[0074] Exemplarily, the first angular velocity bias can be used as the initial state quantity of the Kalman filter algorithm. Assuming that there is a certain noise influence on the angular velocity sensor, the state quantity is iteratively updated according to the observation results until the updated state quantity can meet the preset conditions, and the optimized angular velocity bias is obtained as the current angular velocity bias. Among them, the preset condition can be that the error between the lane line direction angle predicted based on the updated state quantity and the perceived lane line direction angle is the smallest. The specific preset conditions can be set according to actual needs and will not be elaborated here.

[0075] After determining the first angular velocity bias based on the direction angle error between the first direction angle and the second direction angle, the present disclosure optimizes the first angular velocity bias based on the Kalman filter to obtain the optimized angular velocity bias as the current angular velocity bias, further improving the accuracy of the current angular velocity bias.

[0076] In an alternative example, the step 202 of determining the current angular velocity bias based on the first angular velocity, the first lane line perception result corresponding to the current frame, and the second lane line perception result corresponding to the previous frame further includes:

[0077] Step 2025, in response to the first lane line equation or the second lane line equation being a non-linear equation, or in response to not perceiving a lane line, use the angular velocity bias obtained in the previous frame as the current angular velocity bias.

[0078] Among them, in the case where the corresponding angular velocity bias has been obtained in the previous frame, if the first lane line equation and / or the second lane line equation of the current frame is a non-linear equation, or no lane line is perceived in the current frame, since the angular velocity bias is relatively stable in a short period of time, the angular velocity bias obtained in the previous frame can also be used as the current angular velocity bias to correct the current first angular velocity, obtaining the corrected second angular velocity, so as to ensure the accuracy of the determined vehicle trajectory.

[0079] The present disclosure determines the angular velocity bias based on the perception of straight lane lines. Due to the stability of the angular velocity bias in a short period of time, when the vehicle is in a turning state or cannot perceive the lane line in the current frame, the angular velocity bias determined under the straight lane line in the previous frame can also be used as the current angular velocity bias to correct the first angular velocity of the current frame, realizing the accurate calculation of the vehicle trajectory. When entering the straight lane line area again, the online estimation of the angular velocity bias is restored, so that the angular velocity correction of the entire road section can be realized, ensuring the accurate calculation of the vehicle trajectory of the entire road section.

[0080] In an alternative example, based on the first yaw angle change amount, projecting the lane line of the target lane described by the first lane line equation onto the previous frame to obtain the first direction angle corresponding to the lane line of the target lane in the previous frame includes:

[0081] Determining a third direction angle corresponding to the lane line of the target lane in the current frame based on the first lane line equation; determining a first offset direction of the lane line of the target lane relative to the vehicle based on the yaw direction of the first yaw angle change amount; reversely offsetting the third direction angle by the first yaw angle change amount based on the first offset direction to obtain a fourth direction angle of the projected lane line of the lane line of the target lane described by the first lane line equation projected onto the previous frame; and using the fourth direction angle as the first direction angle.

[0082] Wherein, the first lane line equation can be expressed as y = k1x + b1, (x, y) represents the coordinates in the vehicle coordinate system corresponding to the current frame, k1 (slope) and b1 (intercept) represent the first-order equation coefficients of the second lane line equation. The third direction angle corresponding to the lane line of the target lane in the current frame can be obtained through the slope of the first lane line equation, and the specific principle is similar to that of the aforementioned second direction angle, which will not be elaborated here. The yaw direction of the first yaw angle change amount is the yaw direction of the vehicle yaw angle, and the first offset direction is the offset direction of the lane line relative to the longitudinal axis of the vehicle coordinate system. It can be seen that the first offset direction is opposite to the vehicle offset direction. Therefore, based on the yaw direction of the first yaw angle change amount, its reverse direction can be determined as the first offset direction. In order to restore the lane line of the target lane to the previous frame state, it is necessary to offset the third direction angle in the current frame back by the first yaw angle change amount along the reverse direction of the first offset direction to obtain the included angle (fourth direction angle) between the lane line at the previous frame moment and the longitudinal axis of the previous frame vehicle coordinate system, which is the first direction angle.

[0083] Exemplarily, Figure 5It is a schematic diagram showing the relationship between the current frame and the lane lines of the vehicle and the target lane in the previous frame provided by an exemplary embodiment of the present disclosure. In this example, when the vehicle is at the moment corresponding to the previous frame, the lane where the vehicle is located is the target lane. The angle (the second direction angle) between the first side lane line of the perceived target lane (such as the left lane line of the vehicle) and the longitudinal axis (x) of the vehicle coordinate system corresponding to the previous frame is 0. After driving for the first time interval between the current frame and the previous frame, the yaw angle of the vehicle at the moment of the current frame changes by a first yaw angle change amount relative to the previous frame. Since the actual direction of the first side lane line remains unchanged while the vehicle's yaw angle changes by the first yaw angle change amount, it causes the direction of the first side lane line to have an offset in the direction opposite to the offset direction of the vehicle's yaw angle relative to the longitudinal axis (x-axis) of the vehicle coordinate system corresponding to the current frame, such that the direction of the first side lane line and the longitudinal axis of the vehicle coordinate system corresponding to the current frame have a third direction angle θ. Due to the angular velocity cumulative error, the magnitude of the third direction angle may not be equal to the magnitude of the first yaw angle change amount. The offset direction of the third direction angle (the first offset direction, the arrow direction of the θ angle in the figure) is opposite to the offset direction of the first yaw angle change amount. To obtain the first direction angle of the lane line of the target lane projected onto the previous frame for the first lane line equation, it is necessary to reverse the offset of the third direction angle of the lane line in the current frame along the first offset direction of θ by the first yaw angle change amount, and the first direction angle projected onto the previous frame can be obtained. Due to the cumulative error of the angular velocity sensor, there is an error between the first direction angle offset back and the second direction angle perceived in the previous frame. For example, in this example, the angle between the first direction angle offset back and the x-axis is not 0. Therefore, by dividing the direction angle error between the first direction angle and the second direction angle by the first time interval, the angular velocity bias within the first time interval from the previous frame to the current frame can be obtained, which is the current angular velocity bias.

[0084] The present disclosure offsets the direction angle of the lane line in the vehicle coordinate system of the current frame back to the state of the previous frame based on the change amount of the vehicle's yaw angle, compares it with the direction angle of the same lane line perceived in the previous frame, determines the direction angle error to characterize the angular velocity error, and thus determines the current angular velocity bias, realizing the effective online determination of the angular velocity bias. Since what is determined is the angular velocity bias, and the angular velocity bias is relatively stable in a short period of time, in a section where no effective reference object is detected or the lane line cannot be perceived, the angular velocity bias estimated online from the previous frame can be used for angular velocity correction, and the accurate determination of the vehicle's track can still be ensured.

[0085] In an alternative example, for a section of a non - straight lane line (such as a cubic curve, a quadratic curve, etc.), it is also possible to determine the lane lines in the overlapping section in the previous frame and the current frame based on feature matching, and determine the current angular velocity offset based on the direction consistency of the corresponding points of the lane lines in the overlapping section. The direction of the corresponding points can be determined by the tangential direction of the corresponding curve at that point. After determining the direction of the corresponding points, the principle of determining the current angular velocity offset based on the direction of the corresponding points is similar to that of the aforementioned straight lane lines, and will not be elaborated here.

[0086] In an alternative example, step 203 of correcting the first angular velocity based on the current angular velocity offset to obtain the corrected second angular velocity includes:

[0087] Step 2031, taking the sum of the first angular velocity and the current angular velocity offset as the corrected second angular velocity.

[0088] Among them, the current angular velocity offset can have a directionality, for example, it is represented by positive and negative signs, and its sign can be specifically determined according to the difference (direction angle error) between the first direction angle and the second direction angle. When the difference between the first direction angle and the second direction angle is positive, the current angular velocity offset is positive, and when the direction angle error is negative, the current angular velocity offset is negative.

[0089] In an alternative example, step 204 of determining the vehicle's trajectory based on the second angular velocity includes:

[0090] Step 2041, determining the second yaw angle change amount of the current frame relative to the previous frame based on the second angular velocity and the first time between the current frame and the previous frame.

[0091] Among them, the second yaw angle change amount is the product of the second angular velocity and the first time.

[0092] Step 2042, determining the first speed of the vehicle corresponding to the current frame based on the chassis signal.

[0093] Among them, the first speed can be determined based on the speed signal in the chassis signal, and the principle of determining the specific vehicle speed will not be elaborated here.

[0094] Step 2043, determining the driving distance of the current frame relative to the previous frame based on the first speed and the first time.

[0095] Among them, the product of the first speed and the first time can be used as the driving distance of the current frame relative to the previous frame. The principle of determining the specific vehicle driving distance will not be elaborated here.

[0096] Step 2044, determining the vehicle's trajectory based on the second yaw angle change amount and the driving distance.

[0097] Among them, the second yaw angle change amount characterizes the yaw angle change of the vehicle in the current frame relative to the previous frame, and the driving distance characterizes the position change of the current frame relative to the previous frame. Furthermore, based on the vehicle pose at the previous frame moment in the vehicle trajectory determined based on the previous frame, combined with the second yaw angle change amount and the driving distance, the vehicle pose of the current frame can be determined. Then, based on the vehicle pose of the current frame and the vehicle trajectory of the previous frame, the vehicle trajectory of the current frame can be determined. The method for determining the pose of the vehicle in the current frame can adopt any implementable method, which is not limited herein. For example, by performing rotations and translations corresponding to the second yaw angle change amount and the driving distance on the vehicle pose of the previous frame, the vehicle pose of the current frame is obtained, and the specific principle will not be elaborated further.

[0098] The present disclosure determines the corrected yaw angle change amount based on the corrected second angular velocity, and combines it with the vehicle driving distance for vehicle dead reckoning, effectively improving the accuracy of the vehicle trajectory and providing a more accurate speculation result for subsequent applications.

[0099] In an optional example, before determining the current angular velocity offset based on the first angular velocity, the first lane line perception result corresponding to the current frame, and the second lane line perception result corresponding to the previous frame in step 202, it further includes:

[0100] Step 301, based on the first image data corresponding to the current frame, determine the first lane line perception result, where the first lane line perception result includes pixel information belonging to the lane line in the first image data.

[0101] Among them, the first image data can be the current frame road image data collected by an image sensor provided on the vehicle, and the first lane line perception result can be obtained through a preset perception algorithm or a pre-trained perception model, such as a pre-trained deep learning-based lane line detection model for detecting pixel information belonging to the lane line in the first image data.

[0102] Step 302, based on the second image data corresponding to the previous frame, determine the second lane line perception result, where the second lane line perception result includes pixel information belonging to the lane line in the second image data.

[0103] Among them, the second image data can be the road image data collected at the previous frame moment, and the principle of obtaining the second lane line perception result is similar to that of the first lane line perception result, which will not be elaborated one by one herein.

[0104] In practical applications, the second lane line perception result can be obtained and stored in the processing flow at the previous frame moment, and can be directly obtained from the corresponding storage area at the current moment, which can be specifically set according to actual needs.

[0105] The present disclosure can achieve angular velocity correction for the entire road section through lane line perception for determining angular velocity bias, ensuring the accuracy of dead reckoning results. It effectively solves the problem that the accuracy of dead reckoning results is poor in road sections without effective reference objects in the prior art.

[0106] The methods of the above embodiments or optional examples of the present disclosure can be implemented separately or in any combination without conflict, and can be specifically set according to actual needs.

[0107] Any method for determining a vehicle's trajectory provided by an embodiment of the present disclosure can be executed by any suitable device with data processing capabilities, including but not limited to: terminal devices and servers, etc. Alternatively, any method for determining a vehicle's trajectory provided by an embodiment of the present disclosure can be executed by a processor. For example, the processor executes any method for determining a vehicle's trajectory mentioned in an embodiment of the present disclosure by calling corresponding instructions stored in a memory. This will not be elaborated further below.

[0108] Exemplary device

[0109] Figure 6 It is a schematic structural diagram of a device for determining a vehicle's trajectory provided by an exemplary embodiment of the present disclosure. The device of this embodiment can be used to implement the corresponding method embodiment of the present disclosure, such as Figure 6 The shown device includes: a first determination module 501, a first processing module 502, a second processing module 503, and a third processing module 504.

[0110] The first determination module 501 is used to determine a first angular velocity corresponding to the current frame based on chassis signals; the first processing module 502 is used to determine a current angular velocity bias based on the first angular velocity determined by the first determination module 501, the first lane line perception result corresponding to the current frame, and the second lane line perception result corresponding to the previous frame; the second processing module 503 is used to correct the first angular velocity based on the current angular velocity bias determined by the first processing module 502 to obtain a corrected second angular velocity; the third processing module 504 is used to determine the trajectory of the vehicle based on the second angular velocity obtained by the second processing module 503.

[0111] Figure 7 It is a schematic structural diagram of a device for determining a vehicle's trajectory provided by an exemplary embodiment of the present disclosure.

[0112] In an optional example, the first processing module 502 includes: a first determination unit 5021, a second determination unit 5022, a third determination unit 5023, and a fourth determination unit 5024.

[0113] The first determination unit 5021 is configured to determine a first yaw angle change amount of the current frame relative to the previous frame based on the first angular velocity and a first time between the current frame and the previous frame; a second determination unit 5022 is configured to determine a first lane line equation of a target lane in a vehicle coordinate system corresponding to the current frame based on the first lane line perception result; a third determination unit 5023 is configured to determine a second lane line equation of the target lane in a vehicle coordinate system corresponding to the previous frame based on the second lane line perception result; a fourth determination unit 5024 is configured to determine the current angular velocity offset based on the first yaw angle change amount, the first lane line equation, and the second lane line equation.

[0114] In an alternative example, Figure 8 is a schematic structural diagram of a first processing module 502 provided by an exemplary embodiment of the present disclosure. In this example, the fourth determination unit 5024 includes: a first processing subunit 50241, a second processing subunit 50242, a third processing subunit 50243, a fourth processing subunit 50244, and a fifth processing subunit 50245.

[0115] The first processing subunit 50241 is configured to, in response to both the first lane line equation and the second lane line equation being straight line equations, project the lane line of the target lane described by the first lane line equation into the previous frame based on the first yaw angle change amount, and obtain a first direction angle of the lane line of the target lane corresponding to the previous frame, where the first direction angle is an included angle between the lane line of the target lane and the longitudinal axis of the vehicle coordinate system corresponding to the previous frame; the second processing subunit 50242 is configured to determine a second direction angle of the lane line of the target lane corresponding to the previous frame based on the second lane line equation; the third processing subunit 50243 is configured to determine a direction angle error based on the first direction angle and the second direction angle; the fourth processing subunit 50244 is configured to determine a first angular velocity offset based on the direction angle error and the first time; the fifth processing subunit 50245 is configured to determine the current angular velocity offset based on the first angular velocity offset and a Kalman filtering algorithm.

[0116] In an alternative example, the first processing module 502 further includes: a first processing unit 5025, configured to use the angular velocity offset obtained in the previous frame as the current angular velocity offset in response to the first lane line equation or the second lane line equation being a non - straight line equation, or in response to no lane line being perceived.

[0117] In an alternative example, the first processing subunit 50241 is specifically configured to: determine a third direction angle corresponding to the lane line of the target lane in the current frame based on the first lane line equation; determine a first offset direction of the lane line of the target lane relative to the vehicle based on the yaw direction of the first yaw angle change; reverse-offset the third direction angle by the first yaw angle change based on the first offset direction to obtain a fourth direction angle of the lane line of the target lane described by the first lane line equation projected onto the projected lane line in the previous frame; and use the fourth direction angle as the first direction angle.

[0118] In an alternative example, the second processing module 503 includes: a second processing unit 5031, configured to use the sum of the first angular velocity and the offset of the current angular velocity as the corrected second angular velocity.

[0119] In an alternative example, the third processing module 504 includes: a third processing unit 5041, a fourth processing unit 5042, a fifth processing unit 5043, and a sixth processing unit 5044.

[0120] The third processing unit 5041 is configured to determine a second yaw angle change of the current frame relative to the previous frame based on the second angular velocity and a first time between the current frame and the previous frame; the fourth processing unit 5042 is configured to determine a first speed of the vehicle corresponding to the current frame based on a chassis signal; the fifth processing unit 5043 is configured to determine a driving distance of the current frame relative to the previous frame based on the first speed and the first time; and the sixth processing unit 5044 is configured to determine a track of the vehicle based on the second yaw angle change and the driving distance.

[0121] In an alternative example, the apparatus of the present disclosure further includes: a fifth processing module 505 and a sixth processing module 506.

[0122] The fifth processing module 505 is configured to determine the first lane line perception result based on the first image data corresponding to the current frame, where the first lane line perception result includes pixel information belonging to the lane line in the first image data; the sixth processing module 506 is configured to determine the second lane line perception result based on the second image data corresponding to the previous frame, where the second lane line perception result includes pixel information belonging to the lane line in the second image data.

[0123] Exemplary electronic device

[0124] An embodiment of the present disclosure further provides an electronic device, including: a memory for storing a computer program;

[0125] A processor for executing a computer program stored in the memory, and when the computer program is executed, implementing the method for determining a vehicle trajectory according to any one of the above embodiments of the present disclosure.

[0126] Figure 9 FIG. 4 is a schematic structural diagram of an application embodiment of the electronic device of the present disclosure. In this embodiment, the electronic device 10 includes one or more processors 11 and a memory 12.

[0127] The processor 11 may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0128] The memory 12 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the methods of the various embodiments of the present disclosure described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0129] In one example, the electronic device 10 may further include: an input device 13 and an output device 14, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0130] For example, the input device 13 may be the above-mentioned microphone or microphone array for capturing the input signal of the sound source.

[0131] In addition, the input device 13 may further include, for example, a keyboard, a mouse, etc.

[0132] The output device 14 may output various information to the outside, including the determined distance information, direction information, etc. The output device 14 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0133] Of course, for simplicity, Figure 9 only some of the components related to the present disclosure in the electronic device 10 are shown in FIG. 4, and components such as buses, input / output interfaces, etc. are omitted. In addition, according to specific application scenarios, the electronic device 10 may further include any other appropriate components.

[0134] Exemplary computer program product and computer-readable storage medium

[0135] In addition to the above methods and devices, embodiments of the present disclosure may also be computer program products, which include computer program instructions that, when run on a processor, cause the processor to execute the steps in the methods according to various embodiments of the present disclosure described in the above "Exemplary Methods" section of this specification.

[0136] The computer program product may be written in any combination of one or more programming languages for programming code to perform the operations of the embodiments of the present disclosure. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The programming code may be executed entirely on the user's computing device, partially on the user's device, executed as an independent software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0137] Furthermore, embodiments of the present disclosure may also be computer-readable storage media, on which computer program instructions are stored, and when the computer program instructions are run on a processor, cause the processor to execute the steps in the methods according to various embodiments of the present disclosure described in the above "Exemplary Methods" section of this specification.

[0138] The computer-readable storage medium may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0139] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present disclosure. In addition, the above specific details are only for the purpose of illustration and easy understanding, rather than limitations. The above details do not limit the present disclosure to necessarily adopt the above specific details for implementation.

[0140] In the present specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments, and the same or similar parts among the embodiments can be referred to each other. For system embodiments, since they basically correspond to method embodiments, they are described relatively simply, and the relevant parts can be referred to the corresponding descriptions in the method embodiments.

[0141] The block diagrams of devices, apparatuses, equipment, and systems involved in the present disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open-ended terms, meaning "including but not limited to", and can be used interchangeably with each other. The word "or" and "and" used herein refer to the word "and / or" and can be used interchangeably with it, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to" and can be used interchangeably with it.

[0142] The methods and apparatuses of the present disclosure can be implemented in many ways. For example, the methods and apparatuses of the present disclosure can be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of the steps for the method is only for illustration, and the steps of the method of the present disclosure are not limited to the specific order described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure can also be implemented as a program recorded in a recording medium, and these programs include machine-readable instructions for implementing the methods according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0143] It should also be noted that in the apparatuses, equipment, and methods of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present disclosure.

[0144] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be very apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

[0145] The foregoing description has been presented for purposes of illustration and description. In addition, the description is not intended to limit embodiments of the disclosure to the form disclosed herein. Although several example aspects and embodiments have been discussed above, those of skill in the art will recognize some variations, modifications, alterations, additions, and subcombinations thereof.

Claims

1. A method for determining a vehicle's trajectory, comprising: Determining a first angular velocity corresponding to a current frame based on chassis signals; Determining a current angular velocity offset based on the first angular velocity, a first lane line perception result corresponding to the current frame, and a second lane line perception result corresponding to a previous frame; Correcting the first angular velocity based on the current angular velocity offset to obtain a corrected second angular velocity; Determining the vehicle's trajectory based on the second angular velocity; Wherein, the determining the current angular velocity offset based on the first angular velocity, a first lane line perception result corresponding to the current frame, and a second lane line perception result corresponding to a previous frame includes: Determining a first yaw angle change amount of the current frame relative to the previous frame based on the first angular velocity and a first time between the current frame and the previous frame; Determining a first lane line equation of a target lane in a vehicle coordinate system corresponding to the current frame based on the first lane line perception result; Determining a second lane line equation of the target lane in a vehicle coordinate system corresponding to the previous frame based on the second lane line perception result; Determining the current angular velocity offset based on the first yaw angle change amount, the first lane line equation, and the second lane line equation.

2. The method according to claim 1, wherein, The determining the current angular velocity offset based on the first yaw angle change amount, the first lane line equation, and the second lane line equation includes: In response to both the first lane line equation and the second lane line equation being straight line equations, projecting the lane line of the target lane described by the first lane line equation into the previous frame based on the first yaw angle change amount to obtain a first direction angle of the lane line of the target lane corresponding to the previous frame, where the first direction angle is the angle between the lane line of the target lane and the longitudinal axis of the vehicle coordinate system corresponding to the previous frame; Determining a second direction angle of the lane line of the target lane corresponding to the previous frame based on the second lane line equation; Determining a direction angle error based on the first direction angle and the second direction angle; Determining a first angular velocity offset based on the direction angle error and the first time; Determining the current angular velocity offset based on the first angular velocity offset and a Kalman filter algorithm.

3. The method according to claim 2, further comprising: In response to the first lane line equation or the second lane line equation being a non - straight line equation, or in response to no lane line being perceived, using the angular velocity offset obtained in the previous frame as the current angular velocity offset.

4. The method according to claim 2, wherein, The projecting the lane line of the target lane described by the first lane line equation into the previous frame based on the first yaw angle change amount to obtain a first direction angle of the lane line of the target lane corresponding to the previous frame includes: Determining a third direction angle of the lane line of the target lane corresponding to the current frame based on the first lane line equation; Determining a first offset direction of the lane line of the target lane relative to the vehicle based on the yaw direction of the first yaw angle change amount; Based on the first offset direction, reverse-offset the third direction angle by the first yaw angle change amount to obtain the fourth direction angle of the projected lane line of the target lane described by the first lane line equation onto the projected lane line in the previous frame; Use the fourth direction angle as the first direction angle.

5. The method according to claim 1, wherein, The correcting the first angular velocity based on the current angular velocity offset to obtain a corrected second angular velocity includes: Using the sum of the first angular velocity and the current angular velocity offset as the corrected second angular velocity.

6. The method according to claim 1, wherein, The determining the vehicle's trajectory based on the second angular velocity includes: Based on the second angular velocity and the first time between the current frame and the previous frame, determining the second yaw angle change amount of the current frame relative to the previous frame; Determining the first speed of the vehicle corresponding to the current frame based on the chassis signal; Based on the first speed and the first time, determining the driving distance of the current frame relative to the previous frame; Based on the second yaw angle change amount and the driving distance, determining the vehicle's trajectory.

7. According to the method as claimed in any one of claims 1-6, wherein, Before determining the current angular velocity offset based on the first angular velocity, the first lane line perception result corresponding to the current frame, and the second lane line perception result corresponding to the previous frame, further includes: Based on the first image data corresponding to the current frame, determining the first lane line perception result, where the first lane line perception result includes pixel information belonging to the lane line in the first image data; Based on the second image data corresponding to the previous frame, determining the second lane line perception result, where the second lane line perception result includes pixel information belonging to the lane line in the second image data.

8. A device for determining a vehicle's trajectory, comprising: A first determination module, configured to determine a first angular velocity corresponding to a current frame based on a chassis signal; A first processing module, configured to determine a current angular velocity offset based on the first angular velocity, the first lane line perception result corresponding to the current frame, and the second lane line perception result corresponding to the previous frame; A second processing module, configured to correct the first angular velocity based on the current angular velocity offset to obtain a corrected second angular velocity; A third processing module, configured to determine the vehicle's trajectory based on the second angular velocity; Wherein, the first processing module includes: A first determination unit, configured to determine a first yaw angle change amount of the current frame relative to the previous frame based on the first angular velocity and the first time between the current frame and the previous frame; A second determination unit, configured to determine a first lane line equation of the target lane in the vehicle coordinate system corresponding to the current frame based on the first lane line perception result; A third determination unit, configured to determine a second lane line equation of the target lane in the vehicle coordinate system corresponding to the previous frame based on the second lane line perception result; A fourth determination unit, configured to determine the current angular velocity offset based on the first yaw angle change amount, the first lane line equation, and the second lane line equation.

9. A computer-readable storage medium storing a computer program for executing the method for determining a vehicle trajectory according to any one of claims 1-7 above.

10. An electronic device, comprising: a processor; a memory for storing executable instructions executable by the processor; the processor for reading the executable instructions from the memory and executing the instructions to implement the method for determining a vehicle trajectory according to any one of claims 1-7 above.

Images