Parking scenario simulation method and device

Abstract

A parking scenario simulation method is provided, wherein the parking scenario includes a master vehicle and multiple environment vehicles. The parking algorithm of the master vehicle is to be verified in the parking scenario. The method includes: obtaining a scenario configuration file of the parking scenario, which includes scenario range information, static obstacle information, and parking space information; obtaining configuration parameters of each of the multiple environment vehicles, which at least include the parking point coordinates and motion control parameters of the environment vehicle; dividing the multiple environment vehicles into one or more groups based on the scenario configuration file and the parking point coordinates of the multiple environment vehicles; generating a corresponding planned driving path for each environment vehicle in each of the group or multiple groups of environment vehicles so that the environment vehicle can drive and park in the parking space corresponding to the parking point coordinates; and enabling the multiple environment vehicles to drive along the corresponding planned driving path according to the motion control parameters.

Description

Technical Field

[0001] This disclosure relates to the field of vehicles, and in particular to a parking scene simulation method, a parking scene simulation device, a computer device, a storage medium, and a computer program product. Background Technology

[0002] Parking is a common scenario that autonomous driving algorithms need to address. The way vehicles drive in parking lots differs significantly from that in highway driving scenarios. In parking lots, vehicle speeds are low, and interactions between vehicles are complex. Both forward and reverse driving behaviors can affect the behavior of surrounding vehicles.

[0003] The methods described in this section are not necessarily methods that had been previously conceived or adopted. Unless otherwise specified, no method described in this section should be assumed to be prior art simply because it is included in this section. Similarly, unless otherwise specified, the issues mentioned in this section should not be considered to be accepted in any prior art. Summary of the Invention

[0004] This disclosure provides a parking scene simulation method, a parking scene simulation device, a computer device, a storage medium, and a computer program product.

[0005] According to one aspect of this disclosure, a parking scene simulation method is provided for simulating a parking scene, which includes a master vehicle and multiple environment vehicles. The parking algorithm of the master vehicle is to be verified in the parking scene. The method includes: obtaining a scene configuration file for the parking scene, which includes scene range information, static obstacle information, and parking space information; obtaining configuration parameters for each of the multiple environment vehicles, which at least include the parking point coordinates and motion control parameters of the environment vehicle; dividing the multiple environment vehicles into one or more groups based on the scene configuration file and the parking point coordinates of the multiple environment vehicles; generating a corresponding planned driving path for each environment vehicle in the group or multiple groups so that the environment vehicle can drive and park in the parking space corresponding to the parking point coordinates; and causing the multiple environment vehicles to drive along the corresponding planned driving path according to the motion control parameters, so that the driving of the multiple environment vehicles in the parking scene is simulated, thereby generating a simulated parking scene for the master vehicle.

[0006] According to another aspect of this disclosure, a parking scene simulation device is provided for simulating parking scenes, including a main vehicle and multiple ambient vehicles. The parking algorithm of the main vehicle is to be verified in the parking scene. The device includes: a first module for acquiring a scene configuration file of the parking scene, the scene configuration file including scene range information, static obstacle information, and parking space information; a second module for acquiring configuration parameters of each of the multiple ambient vehicles, the configuration parameters including at least the parking point coordinates and motion control parameters of the ambient vehicle; and a third module. The first module is used to divide multiple environmental vehicles into one or more groups based on the scene configuration file and parking point coordinates of multiple environmental vehicles in the parking scenario; the second module is used to generate a corresponding planned driving path for each environmental vehicle in the group or multiple groups of environmental vehicles so that the environmental vehicles can drive and park in the parking space corresponding to the parking point coordinates; and the third module is used to make multiple environmental vehicles drive along the corresponding planned driving path according to motion control parameters, so that the driving of multiple environmental vehicles in the parking scenario is simulated, thereby generating a simulated parking scenario for the main vehicle.

[0007] According to another aspect of this disclosure, a computer device is provided, comprising: at least one processor; and at least one memory storing a computer program thereon, which, when executed by the at least one processor, causes the at least one processor to perform the method described above.

[0008] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided for storing a computer program including instructions that, when executed by a processor, cause the processor to perform the methods described above.

[0009] According to another aspect of this disclosure, a computer program product is provided, the computer program product including instructions that, when executed by a processor, cause the processor to perform the methods described above.

[0010] According to embodiments of this disclosure, by constructing a parking lot simulation scenario with multi-vehicle interaction and planning the entire driving and parking process of multiple environmental vehicles in the scenario from the starting point to the parking space, a complex and realistic parking lot simulation scenario can be provided for the main vehicle, thereby improving the reliability of the main vehicle's autonomous driving algorithm test.

[0011] These and other aspects of this disclosure will be apparent from the embodiments described below, and will be elucidated with reference to the embodiments described below. Attached Figure Description

[0012] Further details, features, and advantages of this disclosure are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings. The accompanying drawings exemplarily illustrate embodiments and form part of the specification, serving together with the textual description to explain exemplary implementations of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals refer to similar but not necessarily identical elements. In the drawings:

[0013] Figure 1 This is a flowchart illustrating a parking scenario simulation method according to an exemplary embodiment;

[0014] Figure 2 This is a flowchart illustrating a process for generating a corresponding planned driving path for each of a group of environmental vehicles, according to an exemplary embodiment.

[0015] Figure 3 This is a flowchart illustrating a process for determining whether a collision will occur between any two environmental vehicles in a group of environmental vehicles, according to an exemplary embodiment.

[0016] Figure 4 This is a block diagram illustrating a parking scenario simulation device according to an exemplary embodiment; and

[0017] Figure 5 This is a block diagram illustrating an exemplary computer device that can be applied to an exemplary embodiment. Detailed Implementation

[0018] In this disclosure, unless otherwise stated, the use of terms such as "first," "second," etc., to describe various elements is not intended to limit the positional, temporal, or importance relationships of these elements; such terms are merely used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of that element, while in other cases, based on the context, they may refer to different instances.

[0019] The terminology used in the description of the various examples described in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context explicitly indicates otherwise, an element may be one or more unless the number of elements is specifically limited. As used herein, the term "multiple" means two or more, and the term "based on" should be interpreted as "at least partially based on". Furthermore, the terms "and / or" and "at least one of..." cover any one of the listed items and all possible combinations thereof.

[0020] Parking is a common scenario that autonomous driving algorithms need to address. The way vehicles drive in parking lots differs significantly from that in highway driving scenarios. In parking lots, vehicle speeds are low, and interactions between vehicles are complex. Both forward and reverse driving behaviors can affect the behavior of surrounding vehicles.

[0021] The inventors observed that current simulation platforms focus on scenarios involving highway or urban road driving environments, neglecting scenarios involving parking environments. Considering that such parking lot interaction scenarios are common for vehicles, and that the impact of multi-vehicle interactions in parking environments on the driver's behavior is significant, simulating multi-vehicle interaction scenarios in parking lots is of considerable value for testing the driver's autonomous driving algorithms, especially parking algorithms. Therefore, building a multi-vehicle interaction parking lot simulation scenario is a crucial step in improving autonomous driving products.

[0022] In view of this, a parking scenario simulation method is proposed according to one or more embodiments of this disclosure. This method groups the environmental vehicles based on the acquired parking scenario configuration file and the configuration parameters of the environmental vehicles, and plans a driving path for each group of environmental vehicles, thereby simulating the driving of the environmental vehicles in the parking scenario, making the simulation scenario faced by the main vehicle undergoing autonomous driving algorithm verification more realistic. By using the above method, by constructing a multi-vehicle interactive parking lot simulation scenario and planning the entire driving and parking process of multiple environmental vehicles in the scenario from the starting point to the parking space, a complex and realistic parking lot simulation scenario can be provided to the main vehicle, thereby improving the reliability of the main vehicle's autonomous driving algorithm testing. Exemplary embodiments of this disclosure are described in detail below with reference to the accompanying drawings.

[0023] Figure 1 This is a flowchart illustrating a parking scenario simulation method 100 according to an exemplary embodiment. Figure 1 As shown, method 100 includes:

[0024] Step S110: Obtain the scene configuration file for the parking scene. The scene configuration file includes the scene range information, static obstacle information, and parking space information of the parking scene.

[0025] Step S120: Obtain the configuration parameters of each of the multiple environmental vehicles. The configuration parameters include at least the parking point coordinates and motion control parameters of the environmental vehicle.

[0026] Step S130: Based on the scene configuration file of the parking scene and the parking point coordinates of multiple environmental vehicles, divide the multiple environmental vehicles into one or more groups of environmental vehicles.

[0027] Step S140: For each group of environmental vehicles in one or more groups, generate a corresponding planned driving path for each environmental vehicle in that group so that the environmental vehicle can drive and park in the parking space corresponding to the parking point coordinates; and

[0028] In step S150, multiple environmental vehicles are driven along the corresponding planned driving paths according to motion control parameters, so that the driving of multiple environmental vehicles in the parking scenario is simulated, thereby generating a simulated parking scenario for the main vehicle.

[0029] The steps of method 100 are described in detail below.

[0030] In step S110, a scene configuration file for the parking scenario can be obtained first. In embodiments of this disclosure, the scene configuration file may include scene range information, static obstacle information, and parking space information for the parking scenario.

[0031] In the example, scene extent information can be used to determine the extent of the scene to be simulated (e.g., a parking scene to be simulated), which may include corner information (e.g., corner coordinates), boundary information (e.g., information related to the lines connecting adjacent corners), etc. In the example, static obstacle information may include information related to static obstacles within the scene to be simulated (e.g., walls, pillars, wheel stops, crash barriers, trash cans, stationary vehicles, etc.), such as the size and location (e.g., coordinates) of the static obstacles. In the example, parking space information may include information related to parking spaces within the scene to be simulated, such as the size, shape, orientation, and coordinates of the parking space (e.g., for a symmetrical parking space, the coordinates may be its center of symmetry, while for an asymmetrical parking space, the coordinates may be specified as a specific point within its area, as needed), etc.

[0032] In step S120, the configuration parameters of each of the multiple environmental vehicles can then be obtained. In embodiments of this disclosure, the configuration parameters of the environmental vehicles may include at least the parking point coordinates and motion control parameters of the environmental vehicles.

[0033] In the example, the parking point coordinates of the environmental vehicle can be selected from the coordinates of parking spaces within the simulation scenario. Those skilled in the art will understand that in the field of autonomous driving, vehicle control aims to propel the vehicle along a desired path to its destination using transmission mechanisms such as steering wheel, brakes, and accelerator. Generally, the algorithm used to control the vehicle is called a controller. The Proportional-Integral-Derivative (PID) controller is one of the most common types of such controllers. A PID controller contains a set of parameters (i.e., PID parameters) that determine the performance of the PID controller, such as oscillation amplitude and damping magnitude. In the example, the motion control parameters of the environmental vehicle may include the PID parameters. In other examples, the configuration parameters of the environmental vehicle may also include the vehicle's size, minimum turning radius, a specified driving speed, a specified starting point, and so on.

[0034] In step S130, multiple environmental vehicles can be divided into one or more groups based on the scene configuration file of the parking scenario and the parking point coordinates of multiple environmental vehicles. In the embodiments of this disclosure, multiple environmental vehicles can be grouped using a clustering algorithm based on the parking point coordinates of the environmental vehicles and the aforementioned scene configuration file, so that vehicles with adjacent parking point coordinates are grouped together.

[0035] It is worth noting that the reason why the scene configuration file of the parking scenario needs to be considered in addition to the parking point coordinates of the environmental vehicles when grouping multiple environmental vehicles is that, in actual parking scenarios, there are situations where the parking point coordinates of environmental vehicles are close, but there are physical barriers between these parking points (e.g., walls or guardrails between these adjacent parking points), so that the driving trajectories of these environmental vehicles to their respective corresponding parking point coordinates (e.g., parking spaces) are significantly different (e.g., the driving trajectories do not overlap at all). Such situations are unsuitable for planning feasible driving paths for multiple environmental vehicles. In actual parking scenarios, the driving trajectories of vehicles destined for adjacent and barrier-free parking spaces can at least partially overlap, thus reducing the computational power (e.g., computing resources) invested in planning driving paths for these vehicles. Therefore, grouping the environmental vehicles through the above steps can make the group parking behavior of the environmental vehicles more closely resemble the actual parking scenario, avoiding planning failures caused by planning timing issues (i.e., planning feasible driving paths for each ungrouped environmental vehicle individually), thereby reducing unnecessary computing power invested in the process of planning driving paths for environmental vehicles.

[0036] In this example, the clustering algorithm could be the K-means algorithm, where the value of k can be set by the user. However, those skilled in the art will understand that any suitable clustering algorithm can be used to group multiple environmental vehicles, such as the DBSCAN algorithm, Gaussian Mixture Model (GMM), spectral clustering, and so on.

[0037] In step S140, a corresponding planned driving path can be generated for each environmental vehicle in each group of environmental vehicles so that the environmental vehicles can drive and park in the parking space corresponding to the parking point coordinates.

[0038] Compared to planning feasible routes for each ungrouped environmental vehicle individually, grouping multiple environmental vehicles and planning routes for each group avoids failures caused by planning timing issues. Specifically, given the parking coordinates of each of the multiple environmental vehicles, planning feasible routes for each ungrouped vehicle individually may fail to generate feasible routes for vehicles later in the planning sequence. For example, collision assessment might show that all planned routes for later-planned vehicles collide with routes planned for earlier-planned vehicles, making it impossible to plan feasible routes for those later-planned vehicles. This necessitates attempting to plan new feasible routes for each vehicle individually, unnecessarily increasing the computational power required for environmental vehicle route planning. In this regard, planning the driving path of each group of environmental vehicles in groups can ensure that the planned feasible driving paths of each group of environmental vehicles will not be replanned along with the driving paths of one or more groups of environmental vehicles planned later due to collisions with them. This can significantly reduce the unnecessary computing power invested in the process of planning the driving path of environmental vehicles, as described above.

[0039] In step S150, multiple environmental vehicles can be driven along corresponding planned driving paths according to motion control parameters, so that the driving of multiple environmental vehicles in the parking scenario is simulated, thereby generating a simulated parking scenario for the main vehicle.

[0040] According to embodiments of this disclosure, the method 100 overcomes the deficiency in related technologies that only simulate scenarios involving high-speed or urban road driving environments to provide simulation scenarios for autonomous driving algorithms. Method 100 groups environmental vehicles based on the acquired parking scenario configuration file and the configuration parameters of the environmental vehicles, and plans driving paths for each group of environmental vehicles. This provides a parking lot interaction scenario where multiple environmental vehicles autonomously drive, making the simulation scenario faced by the main vehicle for verifying autonomous driving algorithms, especially parking algorithms, more realistic.

[0041] By using the above method 100, a parking lot simulation scenario with multi-vehicle interaction can be built and the entire driving and parking process of multiple environmental vehicles in the scenario from the starting point to the parking space can be planned to provide the main vehicle with a complex and realistic parking lot simulation scenario, thereby improving the reliability of the main vehicle's autonomous driving algorithm test.

[0042] Figure 2 This is a flowchart illustrating a process 200 for generating a corresponding planned driving path for each of a group of environmental vehicles, according to an exemplary embodiment. Process 200 can be further described as step S140 of the method 100 described above. Figure 2 As shown, process 200 includes:

[0043] Step S210: For the nth group of environmental vehicles in one or more groups of environmental vehicles, using the initial driving paths of the first to the (n-1)th groups of environmental vehicles as constraints, a path planning algorithm is used to search for the corresponding initial driving path for each environmental vehicle in the nth group of environmental vehicles, where 1≤n≤N, N is the number of one or more groups of environmental vehicles, and n is an integer.

[0044] Step S220: Based on the corresponding initial driving paths of each environmental vehicle in the nth group of environmental vehicles, determine whether a collision will occur between any two environmental vehicles in the nth group of environmental vehicles.

[0045] Step S230: In response to determining that no collision will occur between any two environmental vehicles in the nth group of environmental vehicles, the corresponding initial driving path of each environmental vehicle in the nth group of environmental vehicles is used as the corresponding planned driving path; and

[0046] Step S240: In response to determining that at least two environmental vehicles in the nth group of environmental vehicles will collide, a path planning algorithm is used to re-search the initial driving path for each environmental vehicle in the nth group of environmental vehicles until no collision occurs between any two environmental vehicles in the nth group of environmental vehicles, and the re-searched initial driving path for each environmental vehicle in the nth group of environmental vehicles is used as the corresponding planned driving path.

[0047] In the example, the constraint may refer to using the planned initial driving paths of the environmental vehicles in the earlier planning sequence as exclusive driving paths. Therefore, when planning the initial driving paths for one or more environmental vehicles in the later planning sequence, these exclusive driving paths need to be excluded. However, those skilled in the art will understand that the term "constrained by..." can also mean that the initial driving paths planned for one or more environmental vehicles in the later planning sequence can only overlap with exclusive driving paths by no more than a certain proportion (e.g., the overlapping path segments do not exceed a certain distance, the time the vehicle spends on the overlapping path segments based on a preset driving speed does not exceed a certain time period), and the initial driving paths planned for one or more environmental vehicles in the later planning sequence need to be at a certain safe distance from exclusive driving paths, etc. This disclosure does not impose any restrictions in this regard.

[0048] In the example, the path planning algorithm can be any suitable path planning algorithm known to those skilled in the art, including search algorithms (e.g., A* algorithm, hybrid A* algorithm), random sampling algorithms, curve interpolation algorithms, artificial potential field methods, etc., and this disclosure does not impose any limitations on it.

[0049] By planning the driving paths of each group of environmental vehicles in a group format, it is ensured that no collisions occur between the groups of environmental vehicles. Therefore, process 200 focuses on evaluating the collision between any two environmental vehicles within a group. If a collision occurs between at least two environmental vehicles within a group, a new initial driving path is searched for each environmental vehicle in that group using a path planning algorithm until no collisions occur within that group.

[0050] Figure 3 This is a flowchart illustrating a process 300 for determining whether a collision will occur between any two environmental vehicles in a group of environmental vehicles, according to an exemplary embodiment. In embodiments of this disclosure, the configuration parameters of each environmental vehicle in the group of environmental vehicles further include vehicle information, a preset starting point, and a preset speed, and the vehicle information includes vehicle dimensions and a minimum turning radius. Process 300 can be considered a further description of step S220 of process 200 described above. Figure 3 As shown, process 300 includes:

[0051] Step S310: Based on the preset driving speed of each environmental vehicle in the nth group of environmental vehicles, obtain the position that the environmental vehicle has traveled from the preset driving starting point along the corresponding initial driving path at each simulation time.

[0052] Step S320: For any simulation time, determine whether the distance between the position of the environmental vehicle and the positions of other environmental vehicles in the nth group of environmental vehicles at that simulation time is less than the safe distance, wherein the safe distance is determined by vehicle information;

[0053] Step S330: In response to determining that at any simulation moment, the distance between the position of the environmental vehicle and the positions of other environmental vehicles in the nth group of environmental vehicles is not less than a safe distance, it is determined that no collision will occur between any two environmental vehicles in the nth group of environmental vehicles; and

[0054] Step S340: In response to determining that the distance between the position of the environmental vehicle and the positions of other environmental vehicles in the nth group of environmental vehicles at a given simulation time is less than a safe distance, it is determined that at least two environmental vehicles in the nth group of environmental vehicles will collide.

[0055] In the example, simulation time can refer to the smallest time unit of the simulation platform refresh. It can be based on the concept of absolute time or relative time, and this disclosure does not impose any restrictions on it.

[0056] In the example, a collision can be defined as two vehicles whose body sections overlap at the same moment (e.g., at the simulation moment) and / or the minimum safe distance between the two vehicles does not take into account the minimum turning radius of the vehicles. Therefore, a no-collision situation can be considered as two vehicles whose body sections do not overlap at all at the same moment and the minimum safe distance between the two vehicles has taken into account the minimum turning radius of the vehicles.

[0057] According to embodiments of this disclosure, re-searching initial driving paths for each environmental vehicle in the nth group of environmental vehicles using a path planning algorithm includes: using the environmental vehicles involved in the collision and the given simulation time of the collision as constraints, searching for corresponding initial driving paths for each environmental vehicle in the nth group of environmental vehicles using a path planning algorithm.

[0058] In the above embodiments, the initial driving path re-searched for the environmental vehicle involved in the collision and the given simulation time of the collision as constraints can at least partially overlap with the corresponding initial driving path that previously included the collision (e.g., the re-searched initial driving path bypasses the collision point in the previous initial driving path), completely overlap (e.g., the re-searched initial driving path additionally stipulates that at least one of the vehicles that collided in the previous collision assessment stops or decelerates at a certain distance before the collision point, thereby effectively avoiding the collision without changing the initial planned path), or not overlap. This disclosure does not impose any limitations in this regard.

[0059] As a supplement to the above methods, processes, or embodiments, in the generated simulated parking scenario, the master vehicle can execute an automatic parking process according to the parking algorithm to be verified. Thus, by setting the interaction method between the environmental vehicle and the master vehicle in the parking lot simulation scenario, the simulation scenario faced by the master vehicle is made more realistic, improving the testing value of the master vehicle's autonomous driving algorithm, especially the automatic parking algorithm.

[0060] According to embodiments of this disclosure, for each of the multiple environmental vehicles, in response to determining that the distance between the position of the environmental vehicle and the position of the host vehicle at any simulation moment is not less than a preset distance, the environmental vehicle maintains its movement along the corresponding planned driving path according to motion control parameters; and in response to determining that the distance between the position of the environmental vehicle and the position of the host vehicle at any simulation moment is less than a preset distance, a new planned driving path is generated for the environmental vehicle, starting from its position at that simulation moment, to avoid the distance between the position of the environmental vehicle and the position of the host vehicle being less than the preset distance at any simulation moment, and the environmental vehicle moves along the new planned driving path according to motion control parameters. Thus, by adding interaction between the environmental vehicles and the host vehicle of the algorithm to be verified, each environmental vehicle in the parking lot simulation scenario is no longer limited to the function of acting as a background vehicle, but can autonomously avoid the host vehicle in the event of a potential collision, thereby increasing the realism of the simulation scenario and ensuring and improving the reliability of the autonomous driving algorithm test.

[0061] In the example, the preset distance can be set by the parking lot simulation scenario designer or the autonomous driving algorithm tester of the main vehicle, or it can be automatically set by the simulation platform based on the scenario configuration file and / or the environmental vehicle configuration parameters, and so on.

[0062] According to embodiments of this disclosure, for each of a plurality of environment vehicles, in response to determining that at any simulation moment the master vehicle is parked in the parking space corresponding to the parking point coordinates of the environment vehicle but the environment vehicle has not yet moved to the parking space, a new planned driving path is generated for the environment vehicle, starting from the position of the environment vehicle at that simulation moment and ending at the coordinates of the parking space adjacent to the parking space. The environment vehicle then drives along the new planned driving path according to motion control parameters. This removes the constraint on the master vehicle's autonomous selection of parking spaces, giving the master vehicle's right to choose parking spaces priority over the environment vehicle's right to choose parking spaces in the simulation scenario. This allows the simulation scenario to better serve the testing and verification of the master vehicle's autonomous driving algorithm (e.g., automatic parking algorithm).

[0063] Figure 4This is a schematic block diagram illustrating a parking scene simulation device 400 according to an exemplary embodiment. The device 400 includes: a first module 410 for acquiring a scene configuration file for a parking scene, the scene configuration file including scene range information, static obstacle information, and parking space information; a second module 420 for acquiring configuration parameters for each of a plurality of environmental vehicles, the configuration parameters including at least the parking point coordinates and motion control parameters of the environmental vehicle; a third module 430 for dividing the plurality of environmental vehicles into one or more groups of environmental vehicles based on the scene configuration file and the parking point coordinates of the plurality of environmental vehicles; a fourth module 440 for generating a corresponding planned driving path for each environmental vehicle in each of the group of environmental vehicles, allowing the environmental vehicle to drive and park in the parking space corresponding to the parking point coordinates; and a fifth module 450 for causing the plurality of environmental vehicles to drive along the corresponding planned driving path according to the motion control parameters, thereby simulating the driving of the plurality of environmental vehicles in the parking scene and generating a simulated parking scene for the main vehicle.

[0064] It should be understood that Figure 4 The various modules of the device 400 shown can be connected to the reference. Figure 1 The steps in method 100 described correspond to each other. Therefore, the operation, features and advantages described above for method 100 also apply to device 400 and its included modules.

[0065] According to embodiments of this disclosure, the device 400 overcomes the deficiency in related technologies that only simulate scenarios involving high-speed or urban road driving environments to provide simulation scenarios for autonomous driving algorithms. The device 400 groups the environmental vehicles based on the acquired parking scenario configuration file and the configuration parameters of the environmental vehicles, and plans driving paths for each group of environmental vehicles. This provides a parking lot interaction scenario where multiple environmental vehicles autonomously drive, making the simulation scenario faced by the main vehicle for verifying autonomous driving algorithms, especially parking algorithms, more realistic.

[0066] While specific functions have been discussed above with reference to specific modules, it should be noted that the functions of the modules discussed herein can be divided into multiple modules, and / or at least some functions of multiple modules can be combined into a single module. For example, the first module 410 and the second module 420 can be combined into a single module to obtain both the parking scenario configuration file and the environmental vehicle configuration parameters. The specific module actions discussed herein include the specific module itself performing the action, or alternatively, the specific module calling or otherwise accessing another component or module that performs the action (or performing the action in conjunction with the specific module). Therefore, the specific module performing the action can include the specific module performing the action itself and / or another module that performs the action, called or otherwise accessed by the specific module.

[0067] As used in this article, the phrase “perform action Z based on A, B, and C” can mean performing action Z based on A only, based on B only, based on C only, based on A and B, based on A and C, based on B and C, or based on A, B, and C.

[0068] It should also be understood that this article can describe various technologies in the general context of software and hardware components or program modules. The above regarding... Figure 4 The various modules described can be implemented in hardware or in hardware in combination with software and / or firmware. For example, these modules can be implemented as computer program code / instructions configured to execute in one or more processors and stored in a computer-readable storage medium. Alternatively, these modules can be implemented as hardware logic / circuit. For example, in some embodiments, one or more of the first modules 410 to the fifth modules 450 can be implemented together in a System on Chip (SoC). The SoC may include an integrated circuit chip (which includes a processor (e.g., a Central Processing Unit (CPU), microcontroller, microprocessor, digital signal processor (DSP), etc.), memory, one or more communication interfaces, and / or one or more components of other circuitry) and may optionally execute received program code and / or include embedded firmware to perform functions.

[0069] According to one aspect of this disclosure, a computer device is provided. The computer device includes at least one memory, at least one processor, and a computer program stored on the at least one memory. The at least one processor is configured to execute the computer program to implement the steps of any of the methods, processes, and / or embodiments described above.

[0070] According to one aspect of this disclosure, a non-transitory computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps of any of the methods, processes, and / or embodiments described above.

[0071] According to one aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the steps of any of the methods, processes, and / or embodiments described above.

[0072] In the following text, combined with Figure 5 Illustrative examples describing such computer devices, non-transitory computer-readable storage media, and computer program products.

[0073] Figure 5An example configuration of a computer device 500 that can be used to implement the methods described herein is shown. The aforementioned apparatus 400 may also be implemented wholly or at least partially by the computer device 500 or similar devices or systems.

[0074] Computer device 500 may include at least one processor 502, memory 504, multiple communication interfaces 506, display device 508, other input / output (I / O) devices 510, and one or more mass storage devices 512 capable of communicating with each other, such as via system bus 514 or other suitable connections.

[0075] Processor 502 may be a single processing unit or multiple processing units, and all processing units may include single or multiple computing units or multiple cores. Processor 502 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuits, and / or any device that manipulates signals based on operating instructions. Among other capabilities, processor 502 may be configured to acquire and execute computer-readable instructions stored in memory 504, mass storage device 512, or other computer-readable media, such as program code of operating system 516, program code of application program 518, program code of other program 520, etc.

[0076] Memory 504 and mass storage device 512 are examples of computer-readable storage media for storing instructions executed by processor 502 to perform the various functions described above. For example, memory 504 may generally include both volatile and non-volatile memory (e.g., RAM, ROM, etc.). Furthermore, mass storage device 512 may generally include hard disk drives, solid-state drives, removable media, including external and removable drives, memory cards, flash memory, floppy disks, optical disks (e.g., CDs, DVDs), storage arrays, network-attached storage, storage area networks, etc. Both memory 504 and mass storage device 512 may be collectively referred to herein as memory or computer-readable storage media, and may be non-transitory media capable of storing computer-readable, processor-executable program instructions as computer program code, which may be executed by processor 502 as a specific machine configured to perform the operations and functions described in the examples herein.

[0077] Multiple programs may be stored on mass storage device 512. These programs include operating system 516, one or more application programs 518, other programs 520, and program data 522, and they may be loaded into memory 504 for execution. Examples of such application programs or program modules may include, for example, computer program logic (e.g., computer program code or instructions) for implementing the functions of method steps / components: method 100, process 200, process 300, and optional additional embodiments, apparatus 400, and / or other embodiments described herein.

[0078] Although Figure 5 The modules 516, 518, 520, and 522, or portions thereof, are illustrated as being stored in memory 504 of computer device 500; however, modules 516, 518, 520, and 522 may be implemented using any form of computer-readable medium accessible by computer device 500. As used herein, “computer-readable medium” includes at least two types of computer-readable media: computer-readable storage media and communication media.

[0079] Computer-readable storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, DVD, or other optical storage devices, magnetic cassettes, magnetic tapes, disk storage devices or other magnetic storage devices, or any other non-transmission medium that can be used to store information for access by a computer device. In contrast, communication media can embody computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms. Computer-readable storage media as defined herein do not include communication media.

[0080] One or more communication interfaces 506 are used for exchanging data with other devices, such as via a network, direct connection, etc. Such communication interfaces can be one or more of the following: any type of network interface (e.g., a network interface card (NIC)), wired or wireless (such as IEEE 802.11 Wireless LAN (WLAN)) wireless interface, Wi-MAX interface, Ethernet interface, Universal Serial Bus (USB) interface, cellular network interface, Bluetooth. TMInterfaces include near-field communication (NFC) interfaces. Communication interface 506 facilitates communication across various network and protocol types, including wired networks (e.g., LAN, cable, etc.) and wireless networks (e.g., WLAN, cellular, satellite, etc.), the Internet, etc. Communication interface 506 can also provide communication with external storage devices (not shown) such as storage arrays, network-attached storage, storage area networks, etc.

[0081] In some examples, a display device 508, such as a monitor, may be included for displaying information and images to the user. Other I / O devices 510 may be devices that receive various inputs from the user and provide various outputs to the user, and may include touch input devices, gesture input devices, cameras, keyboards, remote controls, mice, printers, audio input / output devices, and so on.

[0082] The technologies described herein can be supported by these various configurations of computer device 500, and are not limited to specific examples of the technologies described herein. For example, the functionality can also be implemented wholly or partially on a “cloud” using a distributed system. A cloud includes and / or represents a platform for resources. The platform abstracts the underlying functionality of the cloud’s hardware (e.g., servers) and software resources. Resources may include applications and / or data that can be used when performing computational processing on servers remote from computer device 500. Resources may also include services provided via the Internet and / or via subscriber networks such as cellular or Wi-Fi networks. The platform can abstract resources and functionality to connect computer device 500 to other computer devices. Therefore, the implementation of the functionality described herein can be distributed throughout the cloud. For example, the functionality may be implemented partly on computer device 500 and partly through the platform that abstracts the functionality of the cloud.

[0083] Although this disclosure has been described and illustrated in detail in the accompanying drawings and the foregoing description, such description and illustration should be considered illustrative and suggestive, not restrictive; this disclosure is not limited to the disclosed embodiments. By studying the drawings, the disclosure, and the appended claims, those skilled in the art will be able to understand and implement variations of the disclosed embodiments in practice with respect to the claimed subject matter. In the claims, the word "comprising" does not exclude other elements or steps not listed, the indefinite article "a" or "an" does not exclude a plurality, the term "a plurality" means two or more, and the term "based on" should be interpreted as "at least partially based on". The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be beneficial.

Claims

1. A parking scenario simulation method for simulating a parking scenario, wherein the parking scenario includes a master vehicle and multiple ambient vehicles, and the parking algorithm of the master vehicle is to be verified in the parking scenario, the method comprising: Obtain the scene configuration file of the parking scene, which includes scene range information, static obstacle information and parking space information of the parking scene; The configuration parameters of each of the multiple environmental vehicles are obtained. The configuration parameters include at least the parking point coordinates and motion control parameters of the environmental vehicle. The parking point coordinates of the environmental vehicle are selected from the coordinates of the parking spaces in the parking scene to be simulated. Based on the scenario configuration file of the parking scenario and the parking point coordinates of the multiple environmental vehicles, the multiple environmental vehicles are divided into one or more groups of environmental vehicles. For each of the one or more groups of environmental vehicles, a corresponding planned driving path is generated for each environmental vehicle in that group so that it can drive and park in the parking space corresponding to the parking point coordinates, thereby simulating the driving of the environmental vehicle in the parking scenario; and The multiple environmental vehicles are made to drive along the corresponding planned driving paths according to the motion control parameters, so that the driving of the multiple environmental vehicles in the parking scenario is simulated, thereby generating a simulated parking scenario for the main vehicle.

2. The parking scenario simulation method according to claim 1, wherein, For each of the one or more groups of environmental vehicles, generating a corresponding planned driving path for each environmental vehicle in that group includes: For the nth group of environmental vehicles in one or more groups of environmental vehicles, the initial driving paths of the first to the (n-1)th groups of environmental vehicles are used as constraints. A path planning algorithm is used to search for the corresponding initial driving path for each environmental vehicle in the nth group of environmental vehicles, where 1≤n≤N, N is the number of the one or more groups of environmental vehicles, and n is an integer. Based on the initial driving paths of each environmental vehicle in the nth group, determine whether a collision will occur between any two environmental vehicles in the nth group. In response to determining that no collision will occur between any two environmental vehicles in the nth group, the corresponding initial driving path of each environmental vehicle in the nth group is used as the corresponding planned driving path; and In response to determining that a collision will occur between at least two environmental vehicles in the nth group of environmental vehicles, the path planning algorithm is used to re-search an initial driving path for each environmental vehicle in the nth group of environmental vehicles until no collision occurs between any two environmental vehicles in the nth group of environmental vehicles, and the re-searched initial driving path for each environmental vehicle in the nth group of environmental vehicles is taken as the corresponding planned driving path.

3. The parking scenario simulation method according to claim 2, wherein, The configuration parameters for each of the multiple environmental vehicles also include the vehicle information, preset starting point, and preset speed. The vehicle information includes the vehicle dimensions and minimum turning radius. Specifically, determining whether a collision will occur between any two environmental vehicles in the nth group, based on the initial driving paths of each environmental vehicle in the nth group, includes: Based on the preset driving speed of each environmental vehicle in the nth group of environmental vehicles, obtain the position that the environmental vehicle has traveled from the preset driving starting point along the corresponding initial driving path at each simulation time. For any given simulation moment, determine whether the distance between the position of the environmental vehicle and the positions of other environmental vehicles in the nth group of environmental vehicles at that simulation moment is less than a safe distance, wherein the safe distance is determined by the vehicle information; In response to determining that at any simulation moment, the distance between the position of the environmental vehicle and the positions of other environmental vehicles in the nth group of environmental vehicles is not less than the safety distance, it is determined that no collision will occur between any two environmental vehicles in the nth group of environmental vehicles; and In response to determining that at a given simulation moment, the distance between the position of the environmental vehicle and the positions of other environmental vehicles in the nth group of environmental vehicles is less than the safe distance, it is determined that a collision will occur between at least two environmental vehicles in the nth group of environmental vehicles.

4. The parking scenario simulation method according to claim 3, wherein, The path planning algorithm is used to re-search the initial driving path for each environmental vehicle in the nth group of environmental vehicles, including: Using the environmental vehicles involved in the collision and the given simulation time at which the collision occurred as constraints, the path planning algorithm is used to search for the corresponding initial driving path for each environmental vehicle in the nth group of environmental vehicles.

5. The parking scenario simulation method according to any one of the preceding claims further includes: In the generated simulated parking scenario, the master vehicle executes an automatic parking process according to the parking algorithm to be verified.

6. The parking scenario simulation method according to claim 5 further includes: For each of the plurality of environmental vehicles, In response to determining that the distance between the position of the environmental vehicle and the position of the main vehicle is not less than a preset distance at any simulation moment, the environmental vehicle is made to keep traveling along the corresponding planned driving path according to the motion control parameters. as well as In response to determining that the distance between the position of the environmental vehicle and the position of the host vehicle is less than the preset distance at any simulation moment, a new planned driving path is generated for the environmental vehicle, starting from the position of the environmental vehicle at the simulation moment, to avoid the distance between the position of the environmental vehicle and the position of the host vehicle being less than the preset distance at any simulation moment, and the environmental vehicle is made to drive along the new planned driving path according to the motion control parameters.

7. The parking scene simulation method according to claim 5 further includes: For each of the plurality of environmental vehicles, In response to determining that at any simulation moment the master vehicle is parked in the parking space corresponding to the parking point coordinates of the environment vehicle but the environment vehicle has not yet moved to the parking space, a new planned driving path is generated for the environment vehicle, starting from the position of the environment vehicle at the simulation moment and ending at the coordinates of the parking space adjacent to the parking space, and the environment vehicle drives along the new planned driving path according to the motion control parameters.

8. A parking scenario simulation device for simulating parking scenarios involving multiple vehicle interactions, the parking scenario including multiple environmental vehicles and a main vehicle whose algorithm is to be verified in the parking scenario, the device comprising: The first module is used to obtain the scene configuration file of the parking scene, which includes scene range information, static obstacle information and parking space information of the parking scene; The second module is used to obtain the configuration parameters of each of the multiple environmental vehicles. The configuration parameters include at least the parking point coordinates and motion control parameters of the environmental vehicle. The parking point coordinates of the environmental vehicle are selected from the coordinates of the parking spaces in the parking scenario to be simulated. The third module is used to divide the multiple environmental vehicles into one or more groups of environmental vehicles based on the scene configuration file of the parking scene and the parking point coordinates of the multiple environmental vehicles. The fourth module is used to generate a corresponding planned driving path for each environmental vehicle in each of the one or more groups of environmental vehicles, so that the environmental vehicle can drive and park in the parking space corresponding to the parking point coordinates, thereby simulating the driving of the environmental vehicle in the parking scenario; and The fifth module is used to enable the multiple environmental vehicles to drive along the corresponding planned driving path according to the motion control parameters, so that the driving of the multiple environmental vehicles in the parking scenario is simulated, thereby generating a simulated parking scenario for the main vehicle.

9. A computer device, said computer device comprising: At least one processor; as well as At least one memory on which a computer program is stored, When the computer program is executed by the at least one processor, it causes the at least one processor to perform the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, causes the processor to perform the method of any one of claims 1-7.

11. A computer program product comprising a computer program that, when executed by a processor, causes the processor to perform the method of any one of claims 1-7.

Images