Method and device for generating vehicle simulation trajectory, computer equipment and storage medium

Abstract

The embodiment of the present invention discloses a method and apparatus for generating a vehicle simulation trajectory, a computer device, and a storage medium. The method comprises: obtaining time data of a simulation trajectory of a target road; inputting the time data of the simulation trajectory into a random process model, obtaining position coordinate data of the simulation trajectory, the position coordinate data and the time data correspondingly forming a simulation trajectory; wherein the random process model is obtained by at least two drivers performing driving trajectory training on the target road. The technical solution of the embodiment of the present invention solves the technical defect in the prior art that the driving trajectory of a traffic vehicle is artificially set, so that the driving trajectory of the traffic vehicle does not conform to the vehicle dynamics constraints, resulting in difficulty in providing an effective test environment for unmanned vehicles. The driving trajectory of the traffic vehicle can be more consistent with the vehicle dynamics constraints, can be more humanized, and improves the correctness and effectiveness of the test results of the automatic driving simulation scenario of the unmanned vehicle.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of trajectory simulation technology, and in particular to a method and device for generating a vehicle simulation trajectory, a computer device, and a storage medium. Background Art

[0002] An unmanned vehicle is a new type of intelligent car that mainly uses various sensors to perceive the environment around the vehicle and the vehicle's own status information, and make corresponding decision plans. Ultimately, it sends control instructions to the vehicle's actuators to achieve fully automatic operation of the vehicle and achieve the purpose of unmanned driving.

[0003] Before leaving the factory, autonomous vehicles undergo rigorous testing, including testing their driving capabilities on real roads with other vehicles. This is known as autonomous driving simulation testing. The trajectory of other vehicles significantly impacts the accuracy of these tests. Currently, the trajectory of vehicles in autonomous driving simulations is typically fixed and manually set.

[0004] In the process of realizing the present invention, the inventors discovered that the existing technology has the following defects: artificially set trajectories sometimes do not conform to vehicle dynamics constraints, and traffic vehicles traveling along such trajectories are difficult to reflect the characteristics of human driving, and thus it is difficult to provide an effective testing environment for unmanned vehicles. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method and apparatus for generating a vehicle simulation trajectory, a computer device, and a storage medium to optimize the existing method for determining the simulation trajectory of a traffic vehicle.

[0006] In a first aspect, an embodiment of the present invention provides a method for generating a vehicle simulation trajectory, comprising:

[0007] Obtaining time data of the simulation trajectory of the target road;

[0008] Inputting the time data of the simulation trajectory into a random process model to obtain position coordinate data of the simulation trajectory, wherein the position coordinate data and the time data correspond to form a simulation trajectory;

[0009] The random process model is obtained by at least two drivers performing vehicle driving trajectory training on a target road.

[0010] In a second aspect, an embodiment of the present invention provides a device for generating a vehicle simulation trajectory, comprising:

[0011] A time data acquisition module, used to obtain time data of the simulation trajectory of the target road;

[0012] A simulation trajectory generation module is used to input the time data of the simulation trajectory into a random process model to obtain position coordinate data of the simulation trajectory, wherein the position coordinate data and the time data correspond to form a simulation trajectory;

[0013] The random process model is obtained by at least two drivers performing vehicle driving trajectory training on a target road.

[0014] In a third aspect, an embodiment of the present invention provides a computer device, comprising:

[0015] one or more processors;

[0016] a storage device for storing one or more programs;

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for generating a vehicle simulation trajectory described in any embodiment of the present invention.

[0018] In a fourth aspect, an embodiment of the present invention provides a storage medium comprising computer-executable instructions, which, when executed by a computer processor, are used to execute the method for generating a vehicle simulation trajectory described in any embodiment of the present invention.

[0019] An embodiment of the present invention provides a method and apparatus for generating a vehicle simulation trajectory, a computer device, and a storage medium. By using a random process model obtained by training the driving trajectory of a vehicle on a target road by at least two drivers, and the time data of the simulation trajectory, the position coordinate data of the simulation trajectory is obtained and the simulation trajectory is determined. This solves the technical defect in the prior art of manually setting the driving trajectory of a traffic vehicle, which makes the driving trajectory of the traffic vehicle inconsistent with the vehicle dynamics constraints and makes it difficult to provide an effective testing environment for unmanned vehicles. The driving trajectory of the traffic vehicle can be more consistent with the vehicle dynamics constraints and can be more humanized, thereby improving the correctness and effectiveness of the test results of the automatic driving simulation scenario of the unmanned vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of a method for generating a vehicle simulation trajectory provided by the first embodiment of the present invention;

[0021] Figure 2 This is a flow chart of a method for generating a vehicle simulation trajectory provided by the second embodiment of the present invention;

[0022] Figure 3 This is a structural diagram of a device for generating a vehicle simulation trajectory provided by a third embodiment of the present invention;

[0023] Figure 4 This is a structural diagram of a computer device provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following is a further detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention.

[0025] It should also be noted that, for ease of description, only the part relevant to the present invention, rather than all of the content, is shown in the accompanying drawings. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processing or methods depicted as flow charts. Although flow charts describe various operations (or steps) as sequential processing, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of various operations can be rearranged. When its operation is completed, the processing can be terminated, but can also have additional steps not included in the accompanying drawings. The processing can correspond to methods, functions, procedures, subroutines, subprograms, etc.

[0026] Example 1

[0027] Figure 1 This is a flowchart of a method for generating a vehicle simulation trajectory provided in a first embodiment of the present invention. The method of this embodiment can be executed by a vehicle simulation trajectory generation device, which can be implemented in hardware and / or software and generally integrated into a computer device. The method of this embodiment specifically includes:

[0028] S101: Obtain time data of a simulation trajectory of a target road.

[0029] It is known that when an unmanned vehicle is conducting an autonomous driving simulation scenario test, multiple unmanned vehicles are set up on the test road as traffic vehicles, and each traffic vehicle will drive according to a pre-entered driving trajectory. Since the role of the traffic vehicle is to provide a realistic driving environment for the unmanned vehicle being tested, if the driving trajectory of the traffic vehicle is closer to the driving trajectory of a human, then a more effective road test of the unmanned vehicle being tested can be performed. The simulation trajectory generated by steps 101 and 102 in this embodiment is relatively close to the driving trajectory of a human. When applied to the traffic vehicle, this simulation trajectory can provide a more realistic driving environment for the unmanned vehicle being tested.

[0030] In this embodiment, the target road specifically refers to a road that can be used for simulated scenario testing of an unmanned vehicle. Depending on the specific test items for the unmanned vehicle, the target road can be a curved road, a straight road, a road with roundabouts, intersections, and bridges, or a rural dirt road.

[0031] Furthermore, the target road can be a specific road or a group of roads with the same attributes. Roads with the same attributes specifically refer to roads with similar road conditions and driving scenarios. For example, the target roads can specifically be multiple straight roads of similar width, or multiple curved roads with similar curvature and width.

[0032] It can be understood that a simulation trajectory is generally composed of multiple simulation trajectory points at different positions, and the connection order of the simulation trajectory points is generally determined by the time of each simulation trajectory point, where the time of each simulation trajectory point specifically refers to the absolute time or relative time when the vehicle arrives at the simulation trajectory point.

[0033] Similarly, in this embodiment, the simulation trajectory is also composed of multiple different simulation trajectory points, and each simulation trajectory point has both a time value and a position coordinate value. The time data of the simulation trajectory specifically refers to the collection of time values ​​of each simulation trajectory point in the simulation trajectory, and this collection of time values ​​can reflect the order in which the traffic vehicle arrives at each simulation trajectory point in the simulation trajectory.

[0034] S102. Input the time data of the simulation trajectory into a random process model to obtain position coordinate data of the simulation trajectory. The position coordinate data and the time data correspond to form a simulation trajectory, wherein the random process model is obtained by at least two drivers performing vehicle driving trajectory training on a target road.

[0035] In this embodiment, the simulation trajectory is obtained through a random process model, wherein the random process model can typically be a Gaussian process model or the like.

[0036] Furthermore, the random process model used in this embodiment is trained through the following process:

[0037] A. Obtain driving trajectories of at least two drivers on a target road.

[0038] In this embodiment, the target road corresponding to the driver's driving trajectory can be the same road or different roads in a group of roads with the same attributes (the meaning of roads with the same attributes is the same as that described in step 101), etc. This embodiment does not limit this.

[0039] Since there are conventional, aggressive, and conservative types of drivers, the random process model can be trained using the driving trajectories of the same type of drivers so that the simulation trajectories determined by the trained random process model have the same and clear driving attributes (i.e., conventional, aggressive, or conservative). Furthermore, the random process model can be trained separately using the driving trajectories of different types of drivers to obtain multiple random process models that can respectively determine the simulation trajectories of different driving attributes. Then, the simulation trajectories of different driving attributes can be obtained separately according to actual needs to provide a more realistic driving environment for the unmanned vehicle. Therefore, in this embodiment, at least two drivers can be drivers of the same type.

[0040] In this embodiment, the driving trajectory is also formed by connecting multiple driving trajectory points at different locations, and each driving trajectory point has both a time value and a position coordinate value. The time values ​​of different driving trajectory points can reflect the order in which the driver drove the vehicle to reach different driving trajectory points. The position coordinate value can specifically be the two-dimensional plane coordinate value corresponding to the road position where the driving trajectory point is located.

[0041] B. Using the time values ​​and position coordinate values ​​of trajectory points in at least two driving trajectories as input and output of a random process model, respectively, to train the random process model, wherein the time values ​​of the trajectory points used to train the random process model include at least a starting time value, at least one intermediate time value, and an end time value.

[0042] In this embodiment, after obtaining the driving trajectory, the time values ​​and position coordinate values ​​of the driving trajectory points in the driving trajectory are used to train the random process model. The training process can be specifically as follows: the time values ​​and position coordinate values ​​of all the driving trajectory points in all the driving trajectories are used as the input and output of the random process model respectively, so as to complete the training of the random process model.

[0043] Furthermore, when training the random process model, to reduce the amount of computation, only a portion of all driving trajectory points can be selected as samples for training the random process model. However, in order for the simulated trajectory determined by the trained random process model to be a complete trajectory, that is, the trajectory should pass through the entire target road, the time values ​​of the selected trajectory points should at least include a starting time value, at least one intermediate time value, and an end time value. Specifically, the starting time value refers to the time value of the starting trajectory point of any driving trajectory, the end time value refers to the time value of the ending trajectory point of any driving trajectory, and the intermediate time value refers to the time values ​​of all driving trajectory points other than the starting time value and the end time value.

[0044] The training of the random process model is completed through the above steps A and B, and a trained random process model is obtained.

[0045] In this embodiment, the method for obtaining a simulation trajectory through a trained random process model can specifically be to input the time data of the simulation trajectory into the random process model in sequence, thereby obtaining a position coordinate value corresponding to each time value in the time data, and then connecting the trajectory points corresponding to each position coordinate value according to the order of the time values, thereby obtaining a simulation trajectory.

[0046] An embodiment of the present invention provides a method for generating a vehicle simulation trajectory. By using a random process model obtained by training the driving trajectory of at least two drivers on a target road, and the time data of the simulation trajectory, the position coordinate data of the simulation trajectory is obtained and then the simulation trajectory is determined. This solves the technical defect in the prior art of manually setting the driving trajectory of a traffic vehicle, which makes the driving trajectory of the traffic vehicle inconsistent with the vehicle dynamics constraints and makes it difficult to provide an effective testing environment for unmanned vehicles. The driving trajectory of the traffic vehicle can be more consistent with the vehicle dynamics constraints and can be more humanized, thereby improving the correctness and effectiveness of the test results of the automatic driving simulation scenario of the unmanned vehicle.

[0047] Example 2

[0048] Figure 2 This is a flow chart of a method for generating a vehicle simulation trajectory provided by Example 2 of the present invention. This embodiment is optimized based on the above embodiment. In this embodiment, a specific implementation method for adding a simulation trajectory verification process and adding a random process model retraining step is provided.

[0049] Accordingly, the method of this embodiment specifically includes:

[0050] S201: Obtain time data of a simulation trajectory of a target road.

[0051] S202. Input the time data of the simulation trajectory into a random process model to obtain position coordinate data of the simulation trajectory. The position coordinate data and the time data correspond to form a simulation trajectory, wherein the random process model is obtained by at least two drivers performing vehicle driving trajectory training on a target road.

[0052] S203: Obtain vehicle control data corresponding to the simulation trajectory according to a trajectory following algorithm.

[0053] It is understandable that the simulation trajectory determined by steps 201 and 202 may not satisfy the vehicle dynamics constraints and may also exceed the drivable range corresponding to the target road. Therefore, in this embodiment, steps 203 to 207 are first used to determine whether the simulation trajectory satisfies the vehicle dynamics constraints, and then steps 208 to 210 are used to determine whether the simulation trajectory that satisfies the vehicle dynamics constraints is within the drivable range.

[0054] In this embodiment, for example, whether the simulated trajectory satisfies the vehicle dynamics constraints is first determined, and then whether the simulated trajectory falls within the drivable range is determined. Alternatively, whether the simulated trajectory falls within the drivable range is first determined, and then whether the simulated trajectory satisfies the vehicle dynamics constraints is determined.

[0055] In this embodiment, the process of determining whether the simulation trajectory satisfies the vehicle dynamics constraints is to first use a trajectory following algorithm to calculate the vehicle control data corresponding to the simulation trajectory, where the vehicle control data may specifically include steering wheel angle, accelerator pedal data, brake pedal data, etc.

[0056] S204: Input the vehicle control data into the vehicle dynamics model to obtain vehicle simulation driving data corresponding to the simulation trajectory.

[0057] In this embodiment, after obtaining the vehicle control data, each set of vehicle control data (corresponding to a simulation trajectory) is sequentially input into the vehicle dynamics model to obtain the vehicle simulated driving data corresponding to each simulation trajectory. Specifically, the vehicle simulated driving data may include lateral acceleration and following error.

[0058] S205 , determining whether all vehicle simulation driving data corresponding to each simulation trajectory point in the simulation trajectory meets a set value range; if so, executing step 206 ; if not, executing step 207 .

[0059] In this embodiment, the simulated trajectory is confirmed to be correct only when the vehicle driving data corresponding to the simulated trajectory meets the set data range. Among them, the lateral acceleration should be less than 0.5g and the maximum following error should be less than 0.7m.

[0060] S206: Determine that the simulation trajectory is a correct simulation trajectory.

[0061] S207: Determine that the simulation trajectory is an incorrect simulation trajectory, and discard the incorrect simulation trajectory.

[0062] S208: Obtain a drivable range corresponding to the target road.

[0063] In this embodiment, the feasible range corresponding to the target road can be specifically determined by a high-precision map. For example, for a straight road, the high-precision map includes the centerline data and road width data of the straight road. Based on the centerline data and road width data, it can be determined whether the simulation trajectory exceeds the range.

[0064] S209: Determine whether the simulation trajectory is a qualified simulation trajectory based on the simulation trajectory points and the drivable range in the correct simulation trajectory.

[0065] In this embodiment, a simulation trajectory is determined to be a qualified simulation trajectory only when all simulation trajectory points in the simulation trajectory are within the drivable range.

[0066] S210. Determine whether the random process model is qualified according to the proportion of unqualified simulation trajectories.

[0067] In this embodiment, the qualification of the random process model is determined based on the percentage of unqualified simulation trajectories. If the percentage of unqualified simulation trajectories is greater than a set percentage threshold, the random process model is determined to be unqualified. The set percentage threshold may typically be 80%.

[0068] S211: If it is determined that the random process model is unqualified, a curvature value group corresponding to the driving trajectory is obtained.

[0069] In this embodiment, if it is determined that the random process model is unqualified, the random process model will be retrained through steps 211 to 213.

[0070] First, through steps 211 and 212, trajectories with unqualified curvature are screened out from the original trajectories used to train the random process model and discarded. Specifically, unqualified trajectories are trajectories whose corresponding curvature values ​​include a curvature greater than a set curvature threshold.

[0071] S212: Determine the driving trajectories corresponding to the curvature threshold group including the curvature greater than the set curvature threshold as unqualified driving trajectories, and determine the trajectories other than the unqualified driving trajectories as qualified driving trajectories.

[0072] S213: Using the time value and the position coordinate value of the trajectory point in the qualified driving trajectory as the input and output of the random process model respectively, and retraining the random process model.

[0073] An embodiment of the present invention provides a method for generating vehicle age simulation trajectories. This method adds a simulation trajectory verification process, which can accurately screen out simulation trajectories that do not meet vehicle dynamics constraints and exceed the drivable range. It also adds a random process model retraining step to further improve the effectiveness of the simulation trajectory determined by the random process model.

[0074] Example 3

[0075] Figure 3 This is a structural diagram of a vehicle simulation trajectory generation device provided by the third embodiment of the present invention. Figure 3 As shown, the device includes: a time data acquisition module 301 and a simulation trajectory generation module 302, wherein:

[0076] A time data acquisition module 301 is used to acquire time data of a simulation trajectory of a target road;

[0077] The simulation trajectory generation module 302 is used to input the time data of the simulation trajectory into the random process model to obtain the position coordinate data of the simulation trajectory, and the position coordinate data and the time data correspond to form the simulation trajectory;

[0078] The random process model is obtained by training at least two drivers on vehicle driving trajectories on a target road.

[0079] An embodiment of the present invention provides a device for generating a vehicle simulation trajectory. The device first obtains the time data of the simulation trajectory of a target road through a time data acquisition module 301, and then inputs the time data of the simulation trajectory into a random process model through a simulation trajectory generation module 302 to obtain the position coordinate data of the simulation trajectory. The position coordinate data and the time data correspond to form a simulation trajectory; wherein the random process model is obtained by at least two drivers performing vehicle driving trajectory training on the target road.

[0080] The device solves the technical defect in the prior art of manually setting the driving trajectory of traffic vehicles, which makes the driving trajectory of traffic vehicles inconsistent with vehicle dynamics constraints, making it difficult to provide an effective testing environment for unmanned vehicles. The device makes the driving trajectory of traffic vehicles more consistent with vehicle dynamics constraints and more anthropomorphic, thereby improving the correctness and effectiveness of the test results of autonomous driving simulation scenarios of unmanned vehicles.

[0081] Based on the above embodiments, the training process of the stochastic process model may include:

[0082] Obtaining driving trajectories of at least two drivers on a target road;

[0083] Using the time values ​​and position coordinate values ​​of the trajectory points in at least two driving trajectories as the input and output of the random process model, respectively, to train the random process model;

[0084] The time values ​​of the trajectory points used to train the random process model include at least a starting time value, at least one intermediate time value and an end time value.

[0085] Based on the above embodiments, at least two drivers may belong to the same type of driver.

[0086] Based on the above embodiments, the same type of drivers may specifically be:

[0087] Aggressive driver, conservative driver or conventional driver.

[0088] Based on the above embodiments, the random process model may be a Gaussian process model.

[0089] On the basis of the above embodiments, the following may also be included:

[0090] A vehicle control data acquisition module is used to obtain vehicle control data corresponding to the simulation trajectory based on the trajectory following algorithm;

[0091] A vehicle simulation driving data acquisition module is used to input vehicle control data into a vehicle dynamics model to obtain vehicle simulation driving data corresponding to a simulation trajectory;

[0092] A judgment module, used to judge whether the vehicle simulation driving data meets a set value range;

[0093] The correct simulation trajectory determination module is used to determine whether the simulation trajectory is a correct simulation trajectory according to the judgment result.

[0094] Based on the above embodiments, the vehicle control data may include at least: steering wheel angle, accelerator pedal data and brake pedal data;

[0095] The vehicle simulation driving data at least includes: lateral acceleration and following error.

[0096] On the basis of the above embodiments, the following may also be included:

[0097] Get the drivable range corresponding to the target road;

[0098] The qualified simulation trajectory determination module is used to determine whether the simulation trajectory is a qualified simulation trajectory based on the simulation trajectory points and the drivable range in the simulation trajectory.

[0099] On the basis of the above embodiments, the following may also be included:

[0100] The model qualification determination module is used to determine whether the random process model is qualified based on the proportion of unqualified simulation trajectories.

[0101] On the basis of the above embodiments, the following may also be included:

[0102] a curvature acquisition module, configured to determine whether the random process model is qualified based on the proportion of unqualified simulation trajectories, and if the random process model is determined to be unqualified, obtain a curvature value group corresponding to the driving trajectory;

[0103] a curvature judgment module, configured to determine a driving trajectory corresponding to a curvature value group including a curvature greater than a set curvature threshold as an unqualified driving trajectory, and to determine a trajectory other than the unqualified driving trajectory in the driving trajectory as a qualified driving trajectory;

[0104] The model training module is used to use the time value and position coordinate value of the trajectory point in the qualified driving trajectory as the input and output of the random process model respectively, and re-train the random process model.

[0105] The device for generating a vehicle simulation trajectory provided by an embodiment of the present invention can be used to execute the method for generating a vehicle simulation trajectory provided by any embodiment of the present invention, and has corresponding functional modules to achieve the same beneficial effects.

[0106] Example 4

[0107] Figure 4 A schematic diagram of the structure of a computer device provided in Example 4 of the present invention. Figure 4 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 4 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0108] like Figure 4 As shown, computer device 12 is implemented as a general-purpose computing device. Components of computer device 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and a bus 18 that connects various system components (including system memory 28 and processing unit 16).

[0109] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0110] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0111] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be configured to read and write to a non-removable, non-volatile magnetic medium (not shown, typically referred to as a "hard drive"). Although not shown, a magnetic disk drive may be provided for reading and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), as well as an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media). In these cases, each drive may be connected to the bus 18 via one or more data media interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present invention.

[0112] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 42 generally implement the functions and / or methods of the embodiments described herein.

[0113] The computer device 12 can also communicate with one or more external devices 14 (e.g., a keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication can occur via an input / output (I / O) interface 22. Furthermore, the computer device 12 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via a bus 18. It should be understood that, although not shown, other hardware and / or software modules can be used in conjunction with the computer device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0114] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the method for generating a simulated vehicle trajectory provided by an embodiment of the present invention. Specifically, the method comprises: obtaining time data of a simulated trajectory of a target road; inputting the time data of the simulated trajectory into a stochastic process model to obtain position coordinate data of the simulated trajectory; the position coordinate data and the time data correspondingly forming a simulated trajectory; wherein the stochastic process model is obtained by training at least two drivers to perform vehicle driving trajectory training on the target road.

[0115] Example 5

[0116] The fifth embodiment of the present invention further provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the method for generating a vehicle simulation trajectory described in the embodiment of the present invention. Specifically, the method comprises: obtaining time data of a simulation trajectory of a target road; inputting the time data of the simulation trajectory into a random process model to obtain position coordinate data of the simulation trajectory, wherein the position coordinate data and the time data correspond to form a simulation trajectory; wherein the random process model is obtained by at least two drivers performing vehicle driving trajectory training on the target road.

[0117] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: 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 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 thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0118] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. 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 conjunction with an instruction execution system, apparatus, or device.

[0119] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0120] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0121] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the concept of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for generating a vehicle simulation trajectory, characterized in that: include: Obtaining time data of the simulation trajectory of the target road; Inputting the time data of the simulation trajectory into a random process model to obtain position coordinate data of the simulation trajectory, wherein the position coordinate data and the time data correspond to form a simulation trajectory; The simulation trajectory is obtained by connecting the trajectory points corresponding to the position coordinate data according to the sequence of the time data; the random process model is obtained by training the driving trajectory of a vehicle on a target road by at least two drivers; Obtaining vehicle control data corresponding to the simulation trajectory according to a trajectory following algorithm; Inputting the vehicle control data into a vehicle dynamics model to obtain vehicle simulated driving data corresponding to the simulated trajectory; Determining whether the vehicle simulation driving data meets a set value range; Determine whether the simulation trajectory is a correct simulation trajectory based on the judgment result.

2. The method according to claim 1, characterized in that The training process of the stochastic process model includes: Obtaining driving trajectories of at least two drivers on a target road; Using the time values ​​and position coordinate values ​​of trajectory points in at least two driving trajectories as input and output of the random process model, respectively, to train the random process model; The time values ​​of the trajectory points used to train the random process model include at least a starting time value, at least one intermediate time value and an end time value.

3. The method according to claim 2, characterized in that The at least two drivers are of the same type of driver.

4. The method according to claim 3, characterized in that The same type of drivers are specifically: Aggressive driver, conservative driver or conventional driver.

5. The method according to any one of claims 1 to 4, characterized in that The random process model is a Gaussian process model.

6. The method according to claim 1, wherein The vehicle control data includes at least: steering wheel angle, accelerator pedal data and brake pedal data; The vehicle simulation driving data at least includes: lateral acceleration and following error.

7. The method according to claim 1, characterized in that Also includes: Obtaining a drivable range corresponding to the target road; Determine whether the simulation trajectory is a qualified simulation trajectory according to the simulation trajectory points and the drivable range in the simulation trajectory.

8. The method according to claim 7, characterized in that Also includes: Whether the random process model is qualified is determined based on the proportion of the number of unqualified simulation trajectories.

9. The method according to claim 8, characterized in that After determining whether the random process model is qualified according to the proportion of unqualified simulation trajectories, the method further includes: If it is determined that the random process model is unqualified, obtaining a curvature value group corresponding to the driving trajectory; Determining a driving trajectory corresponding to a curvature value group including a curvature greater than a set curvature threshold as an unqualified driving trajectory, and determining a trajectory other than the unqualified driving trajectory in the driving trajectory as a qualified driving trajectory; The time value and the position coordinate value of the trajectory point in the qualified driving trajectory are respectively used as the input and output of the random process model, and the random process model is retrained.

10. A device for generating a vehicle simulation trajectory, characterized in that: include: A time data acquisition module, used to obtain time data of the simulation trajectory of the target road; A simulation trajectory generation module is used to input the time data of the simulation trajectory into a random process model to obtain position coordinate data of the simulation trajectory, wherein the position coordinate data and the time data correspond to form a simulation trajectory; The simulation trajectory is obtained by connecting the trajectory points corresponding to the position coordinate data according to the sequence of the time data; the random process model is obtained by training the driving trajectory of a vehicle on a target road by at least two drivers; A vehicle control data acquisition module, configured to acquire vehicle control data corresponding to the simulation trajectory according to a trajectory following algorithm; A vehicle simulation driving data acquisition module is used to input the vehicle control data into a vehicle dynamics model to obtain vehicle simulation driving data corresponding to the simulation trajectory; A judgment module, used to judge whether the vehicle simulation driving data meets a set value range; The correct simulation trajectory determination module is used to determine whether the simulation trajectory is a correct simulation trajectory according to the judgment result.

11. A computer device, characterized in that: The computer device comprises: one or more processors; a storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for generating a vehicle simulation trajectory according to any one of claims 1 to 9.

12. A storage medium comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a computer processor, are used to execute the method for generating a vehicle simulation trajectory according to any one of claims 1 to 9.

Images