Post-processing method and system for predicted trajectory, electronic device, and storage medium

Abstract

The present invention provides a post-processing method and system, electronic device, and storage medium for a predicted trajectory, and belongs to the technical field of motion trajectory prediction. The post-processing method for a predicted trajectory includes: obtaining a predicted trajectory and a lane boundary mapped by the predicted trajectory, the two sides of the lane boundary are the inner side and the outer side respectively, and the starting point of the predicted trajectory is located on the inner side; comparing the predicted trajectory and the lane boundary, the part of the predicted trajectory located outside the lane boundary is an out-of-bounds trajectory; replacing the out-of-bounds trajectory of the predicted trajectory with the lane boundary mapped by the out-of-bounds trajectory to obtain a corrected trajectory. The present invention can replace the out-of-bounds trajectory of the predicted trajectory with the lane boundary mapped by the out-of-bounds trajectory to obtain a corrected trajectory. It avoids the situation where the predicted trajectory exceeds the lane boundary, reduces the deviation of the predicted trajectory, and improves the rationality and usability of the predicted trajectory.

Description

Technical Field

[0001] The present application relates to the technical field of motion trajectory prediction, and in particular to a post-processing method and system for predicted trajectories, an electronic device, and a storage medium. Background Art

[0002] Vehicle trajectory prediction is a key component of autonomous driving. By predicting the trajectories of other vehicles, vehicles can proactively identify potential safety incidents such as collisions and minor collisions, enabling them to automatically avoid them or alert the driver to avoid them, effectively improving driving safety. Therefore, the accuracy of vehicle trajectory prediction is crucial for autonomous driving. Currently, deep learning models are frequently used to predict vehicle trajectories in autonomous driving development. These prediction models are data-driven and offer significant potential for iterative improvement. While data-driven trajectory prediction models offer significant iterative improvement potential, they can still produce inappropriate predicted trajectories when insufficient training samples are available. Due to the characteristics of deep learning and the design of the objective optimization function, models tend to achieve a best fit to the training data. With a small sample size, these models are only applicable to specific scenarios and may perform poorly in untrained scenarios. This can lead to significant deviations in predicted trajectories, making them unsuitable for use. Summary of the Invention

[0003] In view of the above-mentioned shortcomings of the prior art, the present invention provides a post-processing method and system for predicted trajectory, an electronic device, and a storage medium to solve the above-mentioned technical problems.

[0004] The present invention provides a post-processing method for predicted trajectories, comprising:

[0005] Obtaining a predicted trajectory and a lane boundary mapped by the predicted trajectory, wherein the two sides of the lane boundary are an inner side and an outer side, respectively, and the starting point of the predicted trajectory is located on the inner side;

[0006] comparing the predicted trajectory with the lane boundary, where a portion of the predicted trajectory outside the lane boundary is an out-of-bounds trajectory;

[0007] The out-of-bounds trajectory of the predicted trajectory is replaced by the lane boundary mapped by the out-of-bounds trajectory to obtain a corrected trajectory.

[0008] In one embodiment of the present invention, the predicted trajectory includes position information of the predicted target, and obtaining the lane boundary mapped by the predicted trajectory includes:

[0009] Based on the location information of the predicted target, map data around the predicted target is obtained,

[0010] determining road information of the predicted target based on the map data and the location information of the predicted target;

[0011] The lane boundary is determined according to road information.

[0012] In one embodiment of the present invention, obtaining a predicted trajectory includes:

[0013] Acquire a motion trajectory data set, wherein the motion trajectory data set includes a motion trajectory;

[0014] Establishing a trajectory prediction model and using the motion trajectory dataset to train the prediction model;

[0015] The trained trajectory prediction model is used to process the predicted target information to obtain the predicted trajectory.

[0016] The present invention also provides a post-processing method for predicted trajectories, comprising:

[0017] Obtaining a predicted trajectory data packet, where the predicted trajectory data packet is generated based on the predicted target and the number of single-target predicted trajectories;

[0018] Determining, based on the predicted trajectories in the predicted trajectory data packet, lane boundaries mapped to the predicted trajectories, where the two sides of the lane boundary are an inner side and an outer side, respectively, and the starting point of the predicted trajectory is located on the inner side of the lane boundary;

[0019] Comparing each of the predicted trajectories and the lane boundaries mapped by each of the predicted trajectories, a portion of the predicted trajectory outside the lane boundary is an out-of-bounds trajectory;

[0020] The out-of-bounds trajectories in the predicted trajectory data packet are replaced with lane boundaries mapped by the out-of-bounds trajectories to obtain a corrected trajectory data packet.

[0021] In one embodiment of the present invention, the predicted trajectory includes position information of the predicted target, and obtaining the lane boundary mapped by the predicted trajectory includes:

[0022] Based on the location information of the predicted target, map data around the predicted target is obtained,

[0023] determining road information of the predicted target based on the map data and the location information of the predicted target;

[0024] The lane boundary is determined according to road information.

[0025] In one embodiment of the present invention, before obtaining the predicted trajectory data packet, the following steps are included:

[0026] Acquire a motion trajectory data set, wherein the motion trajectory data set includes a motion trajectory;

[0027] Establishing a trajectory prediction model and using the motion trajectory dataset to train the prediction model;

[0028] The trained trajectory prediction model is used to process the predicted target data according to the preset number of single-target predicted trajectories to obtain a predicted trajectory data packet.

[0029] The present invention also provides a post-processing system for predicting trajectories, the system comprising:

[0030] an acquisition module, configured to acquire a predicted trajectory and a lane boundary mapped by the predicted trajectory, wherein the two sides of the lane boundary are an inner side and an outer side, respectively, and the starting point of the predicted trajectory is located on the inner side;

[0031] an analysis and comparison module, configured to compare the predicted trajectory with the lane boundary, wherein a portion of the predicted trajectory outside the lane boundary is an out-of-bounds trajectory;

[0032] The correction module is configured to replace the out-of-bounds trajectory of the predicted trajectory with the lane boundary mapped by the out-of-bounds trajectory to obtain a corrected trajectory.

[0033] The present invention also provides a post-processing system for predicting trajectories, the system comprising:

[0034] an acquisition module, configured to obtain a predicted trajectory data packet and, based on the predicted trajectories in the predicted trajectory data packet, determine the lane boundary to which each predicted trajectory is mapped, where the two sides of the lane boundary are an inner side and an outer side, respectively, and the starting point of the predicted trajectory is located on the inner side of the lane boundary. The predicted trajectory data packet is generated based on the number of predicted targets and single-target predicted trajectories;

[0035] an analysis and comparison module, respectively comparing each of the predicted trajectories and the lane boundaries mapped by each of the predicted trajectories, wherein a portion of the predicted trajectory outside the lane boundary is an out-of-bounds trajectory;

[0036] The correction module replaces the out-of-bounds trajectories of the predicted trajectory in the predicted trajectory data packet with lane boundaries mapped by the out-of-bounds trajectories to obtain a corrected trajectory data packet.

[0037] The present invention further provides an electronic device, characterized in that the electronic device comprises:

[0038] one or more processors;

[0039] A storage device is used to store one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device implements the post-processing method of the predicted trajectory as described in any one of the above.

[0040] The present invention also provides a computer-readable storage medium, characterized in that a computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the post-processing method of the predicted trajectory as described in any one of the above.

[0041] The present invention provides a post-processing method and system for predicted trajectories, as well as electronic equipment and storage media, that replaces any out-of-bounds trajectories in the predicted trajectory with the lane boundary mapped by the out-of-bounds trajectory, thereby obtaining a corrected trajectory. This prevents the predicted trajectory from exceeding lane boundaries, reduces deviations in the predicted trajectory, and improves the rationality and usability of the predicted trajectory.

[0042] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are incorporated into and constitute a part of the specification, illustrating embodiments consistent with the present application and, together with the specification, serving to explain the principles of the present application. It is obvious that the drawings described below are merely some embodiments of the present application, and a person of ordinary skill in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0044] Figure 1 This is a flowchart of a post-processing method for predicting trajectories according to an embodiment of the present application;

[0045] Figure 2 is a structural block diagram of a post-processing system for predicting trajectories according to an embodiment of the present application;

[0046] Figure 3 This is a logic block diagram of the post-processing method for predicting trajectories shown in an embodiment of the present application during actual implementation;

[0047] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0048] The following describes the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art will readily appreciate the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the various details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are intended only to illustrate the present invention and are not intended to limit the scope of protection of the present invention.

[0049] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0050] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the embodiments of the present invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring the embodiments of the present invention.

[0051] First, it's important to note that vehicle trajectory prediction is a crucial component of autonomous driving. By predicting the trajectories of other vehicles, vehicles can proactively identify potential safety incidents such as collisions and minor collisions, enabling them to automatically avoid them or alert the driver to them, effectively improving driving safety. Therefore, the accuracy of vehicle trajectory prediction is crucial for autonomous driving. Currently, deep learning models are frequently used to predict vehicle trajectories in autonomous driving development. These prediction models are data-driven and offer significant potential for iterative improvement. While data-driven trajectory prediction models offer significant iterative improvement potential, they can still produce inappropriate predicted trajectories when insufficient training samples are available. Due to the characteristics of deep learning and the design of the objective optimization function, models tend to achieve a best fit to the training data. When the sample size is small, the model is only adaptable to specific scenarios and may perform poorly in untrained scenarios. This can lead to significant deviations in predicted trajectories, making them unsuitable for use.

[0052] See also Figure 1 , this embodiment provides a post-processing method for predicted trajectories, comprising the following steps:

[0053] S10: Acquire a predicted trajectory and a lane boundary mapped by the predicted trajectory, wherein the two sides of the lane boundary are an inner side and an outer side respectively, and the starting point of the predicted trajectory is located on the inner side;

[0054] S20: comparing the predicted trajectory with the lane boundary, and determining that a portion of the predicted trajectory outside the lane boundary is an out-of-bounds trajectory;

[0055] S30: Replacing the out-of-bounds trajectory of the predicted trajectory with the lane boundary mapped by the out-of-bounds trajectory to obtain a corrected trajectory.

[0056] In step S10, the predicted trajectory includes the position information of the predicted target, and the step of obtaining the lane boundary mapped by the predicted trajectory includes the following sub-steps:

[0057] S11: Based on the location information of the predicted target, obtain map data around the predicted target,

[0058] S12: Determining road information of the predicted target based on the map data and the location information of the predicted target;

[0059] S13: Determine the lane boundary according to the road information.

[0060] Step S10, i.e., the step of obtaining the predicted trajectory, includes the following sub-steps:

[0061] S14: Acquire a motion trajectory dataset, where the motion trajectory dataset includes a motion trajectory;

[0062] S15: Establishing a trajectory prediction model, and using the motion trajectory dataset to train the prediction model;

[0063] S16: Process the predicted target information using the trained trajectory prediction model to obtain a predicted trajectory.

[0064] This embodiment also provides a post-processing method for predicted trajectories, comprising the following steps:

[0065] S100: Obtain a predicted trajectory data packet, the predicted trajectory data packet being generated based on the number of predicted targets and single-target predicted trajectories, and determining a lane boundary mapped by each predicted trajectory based on the predicted trajectories in the predicted trajectory data packet, where the two sides of the lane boundary are an inner side and an outer side, respectively, and the starting point of the predicted trajectory is located on the inner side of the lane boundary;

[0066] S200: comparing each of the predicted trajectories and the lane boundaries mapped by each of the predicted trajectories, and determining that a portion of the predicted trajectory outside the lane boundary is an out-of-bounds trajectory;

[0067] S300: Replacing all the out-of-bounds trajectories in the predicted trajectory data packet with lane boundaries mapped by the out-of-bounds trajectories to obtain a corrected trajectory data packet.

[0068] The predicted trajectory includes the position information of the predicted target. Step S100, i.e., obtaining the lane boundary mapped by the predicted trajectory, includes the following sub-steps:

[0069] S110: Based on the location information of the predicted target, map data around the predicted target is acquired.

[0070] S120: Determining road information of the predicted target based on the map data and the location information of the predicted target;

[0071] S130: Determine the lane boundary according to the road information.

[0072] In one embodiment, before step S100, that is, before obtaining the predicted trajectory data packet, the following steps are included:

[0073] S101: Acquire a motion trajectory dataset, where the motion trajectory dataset includes a motion trajectory;

[0074] S102: Establishing a trajectory prediction model, and using the motion trajectory dataset to train the prediction model;

[0075] S103: Using the trained trajectory prediction model to process the predicted target data according to a preset number of single-target predicted trajectories, to obtain a predicted trajectory data packet.

[0076] like Figure 2 As shown, this embodiment also provides a post-processing system for predicting trajectories, the system comprising:

[0077] an acquisition module, configured to acquire a predicted trajectory and a lane boundary mapped by the predicted trajectory, wherein the two sides of the lane boundary are an inner side and an outer side, respectively, and the starting point of the predicted trajectory is located on the inner side;

[0078] an analysis and comparison module, configured to compare the predicted trajectory with the lane boundary, wherein a portion of the predicted trajectory outside the lane boundary is an out-of-bounds trajectory;

[0079] The correction module is configured to replace the out-of-bounds trajectory of the predicted trajectory with the lane boundary mapped by the out-of-bounds trajectory to obtain a corrected trajectory.

[0080] This embodiment also provides a post-processing system for predicted trajectories, the system comprising:

[0081] an acquisition module, configured to obtain a predicted trajectory data packet and, based on the predicted trajectories in the predicted trajectory data packet, determine the lane boundary to which each predicted trajectory is mapped, where the two sides of the lane boundary are an inner side and an outer side, respectively, and the starting point of the predicted trajectory is located on the inner side of the lane boundary. The predicted trajectory data packet is generated based on the number of predicted targets and single-target predicted trajectories;

[0082] an analysis and comparison module, respectively comparing each of the predicted trajectories and the lane boundaries mapped by each of the predicted trajectories, wherein a portion of the predicted trajectory outside the lane boundary is an out-of-bounds trajectory;

[0083] The correction module replaces the out-of-bounds trajectories of the predicted trajectory in the predicted trajectory data packet with lane boundaries mapped by the out-of-bounds trajectories to obtain a corrected trajectory data packet.

[0084] The system can be applicable to different exemplary implementation environments and can be specifically configured in its devices. This embodiment does not limit the implementation environment to which the device is applicable.

[0085] It should be noted that the post-processing system for the predicted trajectory provided in the above embodiment and the post-processing method for the predicted trajectory provided in the above embodiment are based on the same concept. The specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here. In actual applications, the road condition refresh device provided in the above embodiment can, as needed, allocate the above functions to different functional modules, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0086] like Figure 3 As shown, the specific steps of post-processing of the predicted trajectory in this embodiment are as follows:

[0087] 1. Load the model prediction trajectory. You can read it from a disk file or receive the incoming trajectory parameters online.

[0088] 2. Obtain a high-precision map within a specified radius centered on the target vehicle.

[0089] 3. Find the lane centerline closest to the target

[0090] 4. Find the road boundary line corresponding to the lane centerline based on the lane centerline

[0091] 5. Filter points whose distance from the target exceeds a certain threshold

[0092] 6. Construct a vector based on the predicted trajectory and the beginning and end points of the lane boundary to determine the intersection

[0093] 7. If the predicted trajectory intersects the lane line, find the coordinates of the intersection point. Using the intersection point as the boundary, replace the points on the predicted trajectory on the opposite side of the starting point with the lane boundary to obtain the corrected trajectory.

[0094] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device implements the post-processing system refresh method for the predicted trajectory provided in the above-mentioned embodiments.

[0095] Figure 4The following is a schematic diagram showing the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application. Figure 4 The computer system 1200 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0096] like Figure 4 As shown, the computer system 1200 includes a central processing unit (CPU) 1201, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1202 or the program loaded from the storage part 1208 to the random access memory (RAM) 1203, such as executing the method described in the above embodiment. Various programs and data required for system operation are also stored in the RAM 1203. The CPU 1201, ROM 1202 and RAM 1203 are connected to each other via a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0097] The following components are connected to the I / O interface 1205: an input section 1206 including a keyboard, a mouse, and the like; an output section 1207 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 1208 including a hard disk; and a communication section 1209 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 1209 performs communication processing via a network such as the Internet. A drive 1210 is also connected to the I / O interface 1205 as needed. Removable media 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 1210 as needed, so that computer programs read from the removable media can be installed in the storage section 1208 as needed.

[0098] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 1209, and / or installed from a removable medium 1211. When the computer program is executed by the central processing unit (CPU) 1201, the various functions defined in the system of the present application are executed.

[0099] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a 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. In the present application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable computer program. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0100] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0101] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.

[0102] Another aspect of the present application provides a computer-readable storage medium having a computer program stored thereon. When executed by a computer processor, the computer program causes the computer to perform the post-processing method for predicting the trajectory as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently and not be incorporated into the electronic device.

[0103] Another aspect of the present application provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the post-processing method for the predicted trajectory provided in each of the above embodiments.

[0104] In summary, the present invention provides a post-processing method and system for predicted trajectories, an electronic device, and a storage medium. This method replaces the predicted trajectory's out-of-bounds trajectory with the lane boundary mapped by the out-of-bounds trajectory, yielding a corrected trajectory. This prevents the predicted trajectory from exceeding lane boundaries, reduces predicted trajectory deviation, and improves the rationality and usability of the predicted trajectory.

[0105] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, any equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical principles disclosed herein are intended to be covered by the claims of the present invention.

Claims

1. A post-processing method for predicted trajectories, characterized in that: include: Obtaining a predicted trajectory and a lane boundary mapped by the predicted trajectory, wherein the two sides of the lane boundary are an inner side and an outer side, respectively, and the starting point of the predicted trajectory is located on the inner side; comparing the predicted trajectory with the lane boundary, where a portion of the predicted trajectory outside the lane boundary is an out-of-bounds trajectory; Replacing the out-of-bounds trajectory of the predicted trajectory with the lane boundary mapped by the out-of-bounds trajectory to obtain a corrected trajectory; The method of loading the model predicted trajectory and the lane boundary mapped by the predicted trajectory includes: obtaining map data within a preset radius centered on the target vehicle; finding the lane centerline closest to the target, and finding the road boundary corresponding to the lane centerline based on the lane centerline; Comparing the predicted trajectory with the lane boundary includes: filtering points whose distance from the target exceeds a preset threshold; constructing a vector based on the predicted trajectory and the first and last points of the lane boundary to determine whether the predicted trajectory intersects the lane boundary, and if the predicted trajectory intersects the lane boundary, calculating the coordinates of the intersection of the predicted trajectory and the lane boundary; Replacing the out-of-bounds trajectory of the predicted trajectory with the lane boundary mapped by the out-of-bounds trajectory includes: Using the intersection as a boundary, points in the predicted trajectory that are on different sides of the lane centerline from the starting point of the predicted trajectory are replaced with lane boundaries to obtain a corrected trajectory.

2. The post-processing method of predicted trajectory according to claim 1, characterized in that: The predicted trajectory includes position information of the predicted target, and obtaining the lane boundary mapped by the predicted trajectory includes: Based on the location information of the predicted target, map data around the predicted target is obtained, determining road information of the predicted target based on the map data and the location information of the predicted target; The lane boundary is determined according to road information.

3. The post-processing method of predicted trajectory according to claim 1, characterized in that: Get the predicted trajectory, including: Acquire a motion trajectory data set, wherein the motion trajectory data set includes a motion trajectory; Establishing a trajectory prediction model and using the motion trajectory dataset to train the prediction model; The trained trajectory prediction model is used to process the predicted target information to obtain the predicted trajectory.

4. A post-processing method for predicted trajectories, characterized in that: include: Obtaining a predicted trajectory data packet, where the predicted trajectory data packet is generated based on the predicted target and the number of single-target predicted trajectories; Determining, based on the predicted trajectories in the predicted trajectory data packet, lane boundaries mapped to the predicted trajectories, where the two sides of the lane boundary are an inner side and an outer side, respectively, and the starting point of the predicted trajectory is located on the inner side of the lane boundary; Comparing each of the predicted trajectories and the lane boundaries mapped by each of the predicted trajectories, a portion of the predicted trajectory outside the lane boundary is an out-of-bounds trajectory; Replacing the out-of-bounds trajectories in the predicted trajectory data packet with lane boundaries mapped by the out-of-bounds trajectories to obtain a corrected trajectory data packet; The method of loading the model predicted trajectory and the lane boundary mapped by the predicted trajectory includes: obtaining map data within a preset radius centered on the target vehicle; finding the lane centerline closest to the target, and finding the road boundary corresponding to the lane centerline based on the lane centerline; Comparing the predicted trajectory with the lane boundary includes: filtering points whose distance from the target exceeds a preset threshold; constructing a vector based on the predicted trajectory and the first and last points of the lane boundary to determine whether the predicted trajectory intersects the lane boundary, and if the predicted trajectory intersects the lane boundary, calculating the coordinates of the intersection of the predicted trajectory and the lane boundary; Replacing the out-of-bounds trajectory of the predicted trajectory with the lane boundary mapped by the out-of-bounds trajectory includes: Using the intersection as a boundary, points in the predicted trajectory that are on different sides of the lane centerline from the starting point of the predicted trajectory are replaced with lane boundaries to obtain a corrected trajectory.

5. The post-processing method of predicted trajectory according to claim 4, characterized in that: The predicted trajectory includes position information of the predicted target, and obtaining the lane boundary mapped by the predicted trajectory includes: Based on the location information of the predicted target, map data around the predicted target is obtained, determining road information of the predicted target based on the map data and the location information of the predicted target; The lane boundary is determined according to road information.

6. The post-processing method of predicted trajectory according to claim 4, characterized in that: Before obtaining the predicted trajectory data package, include: Acquire a motion trajectory data set, wherein the motion trajectory data set includes a motion trajectory; Establishing a trajectory prediction model and using the motion trajectory dataset to train the prediction model; The trained trajectory prediction model is used to process the predicted target data according to the preset number of single-target predicted trajectories to obtain a predicted trajectory data packet.

7. A post-processing system for predicting trajectories, characterized in that: The system comprises: an acquisition module, configured to acquire a predicted trajectory and a lane boundary mapped by the predicted trajectory, wherein the two sides of the lane boundary are an inner side and an outer side, respectively, and the starting point of the predicted trajectory is located on the inner side; an analysis and comparison module, configured to compare the predicted trajectory with the lane boundary, wherein a portion of the predicted trajectory outside the lane boundary is an out-of-bounds trajectory; a correction module, configured to replace the out-of-bounds trajectory of the predicted trajectory with the lane boundary mapped by the out-of-bounds trajectory to obtain a corrected trajectory; The method of loading the model predicted trajectory and the lane boundary mapped by the predicted trajectory includes: obtaining map data within a preset radius centered on the target vehicle; finding the lane centerline closest to the target, and finding the road boundary corresponding to the lane centerline based on the lane centerline; Comparing the predicted trajectory with the lane boundary includes: filtering points whose distance from the target exceeds a preset threshold; constructing a vector based on the predicted trajectory and the first and last points of the lane boundary to determine whether the predicted trajectory intersects the lane boundary, and if the predicted trajectory intersects the lane boundary, calculating the coordinates of the intersection of the predicted trajectory and the lane boundary; Replacing the out-of-bounds trajectory of the predicted trajectory with the lane boundary mapped by the out-of-bounds trajectory includes: Using the intersection as a boundary, points in the predicted trajectory that are on different sides of the lane centerline from the starting point of the predicted trajectory are replaced with lane boundaries to obtain a corrected trajectory.

8. A post-processing system for predicting trajectories, characterized in that: The system comprises: an acquisition module, configured to obtain a predicted trajectory data packet and, based on the predicted trajectories in the predicted trajectory data packet, determine the lane boundary to which each predicted trajectory is mapped, where the two sides of the lane boundary are an inner side and an outer side, respectively, and the starting point of the predicted trajectory is located on the inner side of the lane boundary. The predicted trajectory data packet is generated based on the number of predicted targets and single-target predicted trajectories; an analysis and comparison module, respectively comparing each of the predicted trajectories and the lane boundaries mapped by each of the predicted trajectories, wherein a portion of the predicted trajectory outside the lane boundary is an out-of-bounds trajectory; a correction module, which replaces all out-of-bounds trajectories in the predicted trajectory data packet with lane boundaries mapped by the out-of-bounds trajectories to obtain a corrected trajectory data packet; The method of loading the model predicted trajectory and the lane boundary mapped by the predicted trajectory includes: obtaining map data within a preset radius centered on the target vehicle; finding the lane centerline closest to the target, and finding the road boundary corresponding to the lane centerline based on the lane centerline; Comparing the predicted trajectory with the lane boundary includes: filtering points whose distance from the target exceeds a preset threshold; constructing a vector based on the predicted trajectory and the first and last points of the lane boundary to determine whether the predicted trajectory intersects the lane boundary, and if the predicted trajectory intersects the lane boundary, calculating the coordinates of the intersection of the predicted trajectory and the lane boundary; Replacing the out-of-bounds trajectory of the predicted trajectory with the lane boundary mapped by the out-of-bounds trajectory includes: Using the intersection as a boundary, points in the predicted trajectory that are on different sides of the lane centerline from the starting point of the predicted trajectory are replaced with lane boundaries to obtain a corrected trajectory.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the post-processing method of the predicted trajectory as described in any one of claims 1 to 3.

10. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the post-processing method of the predicted trajectory according to any one of claims 1 to 3.

Images