CN115526069B - Simulated driving scene generation method, device, equipment and computer readable medium - Google Patents
Simulated driving scene generation method, device, equipment and computer readable medium Download PDFInfo
- Publication number
- CN115526069B CN115526069B CN202211503473.4A CN202211503473A CN115526069B CN 115526069 B CN115526069 B CN 115526069B CN 202211503473 A CN202211503473 A CN 202211503473A CN 115526069 B CN115526069 B CN 115526069B
- Authority
- CN
- China
- Prior art keywords
- obstacle
- scene
- information
- driving
- elements
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Abstract
The embodiment of the disclosure discloses a method, a device, equipment and a computer readable medium for generating a simulation driving scene. One embodiment of the method comprises: acquiring scene data corresponding to an original scene of a target vehicle; constructing an initial simulation scene corresponding to the target vehicle according to the track information and the obstacle information set included in the scene data; determining primary behavior information of a corresponding target vehicle; for each barrier element in the barrier element set, inputting the main vehicle behavior information into a driving model of the barrier element in the initial simulation scene to obtain the barrier element with the driving state updated; and generating a simulated driving scene set corresponding to the target vehicle according to the initial simulated scene, the main vehicle element, the main vehicle behavior information and the obtained barrier elements after the running state is updated. The implementation method improves the accuracy of each determined simulation driving scene and the driving safety of the automatic driving technical scheme.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of computers, in particular to a method, a device, equipment and a computer readable medium for generating a simulation driving scene.
Background
And (4) driving scene simulation, namely constructing a plurality of simulation scenes for testing the related technical scheme of the automatic driving technology. At present, when each driving scene is constructed, the method generally adopted is as follows: according to the physical world layering of the simulation driving scene, the Cartesian product combination is carried out from different driving scene element angles, and then screening and removing are carried out through constraint conditions according to the driving scene requirements.
However, the inventors have found that when the respective driving scenes are constructed in the above manner, there are often technical problems as follows:
firstly, a large number of unrealistic driving scenes can be generated through simple combination of scene element Cartesian products, and whether the screened driving scenes are reasonable depends on completeness of constraint conditions, so that accuracy of each determined driving scene is low, accuracy of an automatic driving technical scheme tested according to each determined driving scene is low, and driving safety is poor.
Secondly, through a simple combination mode of scene element Cartesian products, the difference between the driving scene and the actual traffic flow state is large, the accuracy of each determined driving scene is low, the accuracy of an automatic driving technical scheme tested according to each determined driving scene is low, and the driving safety is poor.
The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art in this country.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose a simulated driving scenario generation method, apparatus, electronic device, and computer readable medium to solve one or more of the technical problems mentioned in the background section above.
In a first aspect, some embodiments of the present disclosure provide a method for generating a simulated driving scenario, the method including: acquiring scene data of an original scene corresponding to a target vehicle, wherein the scene data comprises track information and an obstacle information set of the target vehicle; constructing an initial simulation scene corresponding to the target vehicle according to trajectory information and an obstacle information set included in the scene data, wherein the initial simulation scene includes a main vehicle element and an obstacle element set corresponding to the target vehicle, an obstacle element in the obstacle element set corresponds to obstacle information in the obstacle information set, and an obstacle element in the obstacle element set corresponds to a driving model; determining the main vehicle behavior information corresponding to the target vehicle; for each barrier element in the barrier element set, inputting the host vehicle behavior information into a driving model of the barrier element in the initial simulation scene to obtain the barrier element with an updated driving state; and generating a simulated driving scene set corresponding to the target vehicle according to the initial simulated scene, the host vehicle element, the host vehicle behavior information and the obtained barrier elements after the driving states are updated.
In a second aspect, some embodiments of the present disclosure provide a simulated driving scenario generation apparatus, comprising: the system comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is configured to acquire scene data corresponding to an original scene of a target vehicle, and the scene data comprises track information and an obstacle information set of the target vehicle; a construction unit configured to construct an initial simulation scene corresponding to the target vehicle according to trajectory information and a set of obstacle information included in the scene data, wherein the initial simulation scene includes a host element corresponding to the target vehicle and a set of obstacle elements, an obstacle element in the set of obstacle elements corresponds to obstacle information in the set of obstacle information, and an obstacle element in the set of obstacle elements corresponds to a driving model; a determination unit configured to determine host behavior information corresponding to the target vehicle; an input unit configured to input the host vehicle behavior information to a driving model of the obstacle element in the initial simulation scene for each obstacle element in the set of obstacle elements, resulting in an updated driving state of the obstacle element; a generating unit configured to generate a set of simulated driving scenes corresponding to the target vehicle according to the initial simulated scene, the host vehicle element, the host vehicle behavior information, and the obtained respective updated-driving-state obstacle elements.
In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method described in any of the implementations of the first aspect.
In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in any of the implementations of the first aspect.
The above embodiments of the present disclosure have the following beneficial effects: according to the simulated driving scene generation method of some embodiments of the disclosure, the accuracy of each determined simulated driving scene and the driving safety of the automatic driving technical scheme are improved. Specifically, the reasons for the determined driving scenes are that the accuracy is low and the driving safety is poor are as follows: a large number of unrealistic driving scenes can be generated through simple combination of scene element Cartesian products, whether the screened driving scenes are reasonable depends on completeness of constraint conditions, accuracy of each determined driving scene is low, accuracy of an automatic driving technical scheme tested according to each determined driving scene is low, and accordingly driving safety is poor. Based on this, the simulated driving scene generation method of some embodiments of the present disclosure first acquires scene data corresponding to an original scene of the target vehicle. The scene data includes track information and an obstacle information set of the target vehicle. Therefore, the scene data of the original scene can be used as the collected data in the real traffic state. And then, constructing an initial simulation scene corresponding to the target vehicle according to the track information and the obstacle information set included in the scene data. The initial simulation scene comprises a main vehicle element and an obstacle element set corresponding to the target vehicle. The obstacle elements in the obstacle element set correspond to the obstacle information in the obstacle information set. The obstacle elements in the obstacle element set correspond to a driving model. Therefore, the simulation scene can be constructed by taking the real traffic state as a prototype. Next, the host behavior information corresponding to the target vehicle is determined. Thus, the host behavior information may characterize the current behavior of the target vehicle. Then, for each barrier element in the set of barrier elements, the host behavior information is input to a driving model of the barrier element in the initial simulation scene, and the barrier element with the driving state updated is obtained. Thus, the change in the running state of the obstacle element made to the current behavior of the target vehicle can be determined by the running model. And finally, generating a simulated driving scene set corresponding to the target vehicle according to the initial simulated scene, the host vehicle element, the host vehicle behavior information and the obtained barrier elements after the driving states are updated. Therefore, different simulated driving scenes can be generalized on the basis of the initial simulation scene according to the driving state change of different barrier elements aiming at the current behavior of the target vehicle. And because each generated simulated driving scene is generalized on the basis of the initial simulated scene, and the initial simulated scene is a prototype of a real traffic state, each generated simulated driving scene accords with the actual logic and is not required to be further screened or eliminated through constraint conditions, the accuracy of each determined simulated driving scene is improved, the accuracy of the automatic driving technical scheme tested according to each determined simulated driving scene is further improved, and the driving safety is improved. Therefore, the accuracy of each determined simulation driving scene and the driving safety of the automatic driving technical scheme are improved.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.
FIG. 1 is a flow diagram of some embodiments of a simulated driving scenario generation method according to the present disclosure;
FIG. 2 is a schematic block diagram of some embodiments of a simulated driving scenario generation apparatus according to the present disclosure;
FIG. 3 is a schematic block diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
FIG. 1 illustrates a flow 100 of some embodiments of a simulated driving scenario generation method in accordance with the present disclosure. The method for generating the simulated driving scene comprises the following steps:
In some embodiments, an executing subject (e.g., a computing device) of the simulated driving scenario generation method may obtain scenario data corresponding to an original scenario of the target vehicle from the terminal through a wired connection manner or a wireless connection manner. The target vehicle may be any vehicle. The original scene may be a real driving scene of the target vehicle that needs to be generalized. The scene data can be various collected data in a real driving scene. The scene data may include trajectory information and an obstacle information set of the target vehicle. The track information may be information for recording coordinates of the target vehicle during traveling. The set of obstacle information may be information on each freely movable obstacle that hinders the travel of the target vehicle. Here, the obstacle that impedes the travel of the target vehicle may be, but is not limited to, at least one of: vehicles and pedestrians. The obstacle information in the above obstacle information set may include, but is not limited to: obstacle type, obstacle size, obstacle coordinates. Here, the coordinates may be geographical coordinates.
It is noted that the wireless connection means may include, but is not limited to, a 3G/4G connection, a WiFi connection, a bluetooth connection, a WiMAX connection, a Zigbee connection, a UWB (ultra wideband) connection, and other wireless connection means now known or developed in the future.
And 102, constructing an initial simulation scene corresponding to the target vehicle according to the track information and the obstacle information set included in the scene data.
In some embodiments, the execution subject may construct an initial simulation scenario corresponding to the target vehicle according to the trajectory information and the set of obstacle information included in the scenario data. The initial simulation scene may include a set of host elements and barrier elements corresponding to the target vehicle. The master vehicle element may be a scene element corresponding to the target vehicle in the simulation model. The set of obstacle elements may be scene elements corresponding to obstacles in the simulation model. The obstacle elements in the obstacle element set correspond to the obstacle information in the obstacle information set. The corresponding relationship between the obstacle elements in the obstacle element set and the obstacle information in the obstacle information set may be a one-to-one correspondence. The obstacle elements in the obstacle element set correspond to a driving model. The driving model may be a virtual driving decision model of a scene element in a simulation model, and may be used to simulate how the scene element updates the driving state (i.e., how to drive) for a changing scene.
In some optional implementations of some embodiments, the executing entity may construct an initial simulation scenario corresponding to the target vehicle according to the trajectory information and the set of obstacle information included in the scenario data by:
firstly, selecting track coordinates meeting a preset time condition from all track coordinates included in the track information as current position coordinates of the target vehicle. The preset time condition may be that, in each acquisition time corresponding to each track coordinate, the time interval between the acquisition time corresponding to the track coordinate and the current time is the minimum.
And secondly, acquiring the road network elements corresponding to the current position coordinates according to the current position coordinates. The road network element may be road network data of a position where the current position coordinate is located. Here, the road network data may be road network data in a buffer area constructed with the current position coordinates as a center, or road network data of a road on which the current position coordinates are located and each road topologically connected to the road. In practice, the execution subject may obtain the road network element corresponding to the current position coordinate through a map application interface.
And thirdly, constructing an obstacle element corresponding to the obstacle information for each obstacle information in the obstacle information set.
And fourthly, constructing a main vehicle element corresponding to the target vehicle according to the vehicle information of the target vehicle. The vehicle information may be vehicle attribute-related information corresponding to the target vehicle. The vehicle information may include, but is not limited to, at least one of: vehicle type, vehicle size. In practice, the execution subject described above may construct, as the host elements, virtual vehicles whose vehicle types and vehicle sizes are the vehicle types and vehicle sizes included in the vehicle information described above, respectively.
And fifthly, placing the constructed main vehicle elements and the constructed barrier elements in the road network elements to obtain an initial simulation scene corresponding to the target vehicle.
Optionally, the obstacle information in the obstacle information set may include an obstacle type. The type of obstacle may be a type of obstacle. Here, the obstacle type may be an obstacle vehicle type or a pedestrian. The obstacle vehicle type may be a model to which the obstacle vehicle belongs.
In some optional implementations of some embodiments, the executing body may construct the obstacle element corresponding to the obstacle information by:
first, barrier elements corresponding to the types of barriers are constructed. In practice, the execution subject may construct a virtual obstacle as an obstacle element, where the obstacle type and the obstacle size are the obstacle type and the obstacle size included in the obstacle information, respectively. It is understood that when the obstacle type is an obstacle vehicle type, the obstacle size may be a vehicle size. When the obstacle type is a pedestrian, the obstacle size may be a pedestrian height.
And a second step of determining a driving model corresponding to the type of the obstacle as a driving model of the obstacle element. In practice, the executing body may determine a preset driving model corresponding to the obstacle type in the preset driving model set as the driving model of the obstacle element. The preset driving model set may be each driving model trained in advance. Each preset driving model in the preset driving model set corresponds to an obstacle type.
Optionally, the obstacle information in the obstacle information set may include obstacle coordinates.
In some optional implementations of some embodiments, the executing entity may place the constructed host vehicle element and the constructed obstacle elements in the road network element to obtain an initial simulation scenario corresponding to the target vehicle by:
first, the main vehicle element is placed in a position corresponding to the current position coordinates in the road network element.
A second step of, for each obstacle element constructed, performing the following steps:
a first substep of determining obstacle information corresponding to the obstacle element in the obstacle information set as target obstacle information.
And a second substep of determining obstacle coordinates included in the target obstacle information as placement coordinates.
A third substep of placing said barrier elements in positions of said road network elements corresponding to said placement coordinates.
And thirdly, determining the road network elements in which the main vehicle elements and the constructed barrier elements are placed as initial simulation scenes corresponding to the target vehicles.
In some optional implementations of some embodiments, the executing body may determine a driving model corresponding to the obstacle type as the driving model of the obstacle element by:
in response to determining that the obstacle type characterizes an obstacle vehicle, a virtual driver model corresponding to the obstacle type is determined as a driving model corresponding to the obstacle element. The virtual driver model may be a virtual driving decision model of the obstacle vehicle in the simulation model, and may be used to simulate how the obstacle vehicle updates the driving state (i.e., how to drive) for a changing scene. The virtual driver model corresponds to a driver avoidance mode. The driver avoidance mode may be an avoidance strategy. In practice, the executing body may determine a virtual driver model corresponding to the type of the obstacle vehicle as a running model corresponding to the obstacle element.
And a second step of determining the virtual pedestrian model as a driving model corresponding to the obstacle element in response to determining that the obstacle type represents a pedestrian. The virtual pedestrian model corresponds to a pedestrian avoidance mode. The virtual pedestrian model may be a virtual driving decision model of a pedestrian in the simulation model, and may be used to simulate how the pedestrian updates the driving state (i.e., how to walk) for a changing scene.
In some embodiments, the executing entity may determine the host behavior information corresponding to the target vehicle. The host behavior information may represent a behavior change made by the target vehicle. The primary behavior information may include, but is not limited to, at least one of: speed change information, driving mode change information, traveling direction change information, and traveling position change information. The speed change information may include a pre-change speed and a post-change speed. The driving style change information may include a driving style before the change and a driving style after the change. Here, the driving style may represent a driving style of the driver. The driving style may include, but is not limited to, at least one of: common style, aggressive style, conservative style. The traveling direction change information may include a before-change traveling direction and a after-change traveling direction. The travel position change information may include a before-change travel position and a after-change travel position. In practice, the executing body determines the received host behavior information of the target vehicle as the host behavior information corresponding to the target vehicle. In practice, the executing body may determine preset host behavior information as the host behavior information corresponding to the target vehicle.
And 104, inputting the main vehicle behavior information into the driving model of the barrier elements in the initial simulation scene for each barrier element in the barrier element set to obtain the barrier elements with updated driving states.
In some embodiments, for each barrier element in the set of barrier elements, the executing agent may input the host behavior information to a driving model of the barrier element in the initial simulation scene, resulting in the barrier element after updating the driving state. In practice, the executing body may input the host vehicle behavior information to a driving model of the obstacle element in the initial simulation scene, so as to obtain the obstacle element with an updated driving state.
Alternatively, the driving model of the obstacle element in the above-described set of obstacle elements may correspond to a set of driving manners. The set of driving styles may include, but is not limited to, at least one of: common style, aggressive style, conservative style.
In some optional implementation manners of some embodiments, the executing body may input the host vehicle behavior information into a driving model of the obstacle element in the initial simulation scene to obtain the obstacle element after updating the driving state by:
firstly, selecting a preset number of driving modes from the driving mode set to obtain each driving mode. The preset number can be any number greater than 0 and less than or equal to the target number. The target number may be the number of the respective driving manners included in the driving manner set. In practice, the execution subject may randomly select a preset number of driving manners from the driving manner set to obtain each driving manner.
And secondly, for each driving mode in the driving modes, inputting the main vehicle behavior information and the driving mode into a driving model of the barrier element in the initial simulation scene to obtain the barrier element with an updated driving state. Therefore, random parameter scattering can be carried out on the driving modes to simulate different driving styles of drivers in the real world, so that different driving strategies of obstacle vehicles are caused, secondary generalization of driving scenes is realized through the random scattering points of the driving styles, further double generalization of original scenes in the real world is realized, and all simulated driving scenes obtained through generalization can be guaranteed to be reasonable scenes.
The technical scheme is taken as an invention point of the embodiment of the disclosure, and solves the technical problems mentioned in the background technology, namely, the technical problem that the driving safety is poor due to the fact that the accuracy of each determined driving scene is low and the accuracy of the automatic driving technical scheme tested according to each determined driving scene is low in the mode of simply combining scene element Cartesian products and the difference between the scene element Cartesian products and the actual traffic flow state is large. Factors that lead to low accuracy and poor driving safety of each determined driving scene are as follows: through a simple combination mode of scene element Cartesian products, the difference with the actual traffic flow state is large, the accuracy of each determined driving scene is low, the accuracy of an automatic driving technical scheme tested according to each determined driving scene is low, and the driving safety is poor. If the factors are solved, the effects of reducing the difference between the simulated driving scene and the actual traffic flow state and improving the accurate determination and driving safety of the simulated driving scene can be achieved. In order to achieve the effect, the method for secondarily generalizing the driving mode is introduced, random parameter points scattering can be carried out on the driving mode to simulate different driving strategies of obstacle vehicles caused by different driving styles of drivers in the real world, secondary generalization of the driving scene is achieved through the random points scattering of the driving styles, and then double generalization of the original scene of the real world is achieved. All the simulated driving scenes obtained through generalization can be guaranteed to be reasonable scenes. Thereby reducing the simulation driving scene the difference in the actual traffic flow status, the accurate determination and the driving safety of the simulation driving scene are improved.
And 105, generating a simulated driving scene set corresponding to the target vehicle according to the initial simulated scene, the main vehicle element, the main vehicle behavior information and the obtained barrier elements after the driving state is updated.
In some embodiments, the executing entity may generate a set of simulated driving scenes corresponding to the target vehicle according to the initial simulated scene, the host vehicle element, the host vehicle behavior information, and the obtained barrier elements after each updated driving state.
In some optional implementations of some embodiments, the executing entity may generate the set of simulated driving scenes corresponding to the target vehicle according to the initial simulated scene, the host vehicle element, the host vehicle behavior information, and the obtained barrier elements after each updated driving state by:
first, determining current position information of the target vehicle according to the host behavior information. In practice, the executing body may determine the post-alteration travel position included in the host behavior information as the current position information of the target vehicle. The post-change traveling position may be represented by coordinates.
And secondly, updating the main vehicle elements in the initial simulation scene according to the main vehicle behavior information to obtain updated main vehicle elements. In practice, the executing agent may replace the speed information, the driving style, the traveling direction, and the traveling position corresponding to the host vehicle element with the changed speed, the changed driving style, the changed traveling direction, and the changed traveling position, respectively, to update the host vehicle element.
And thirdly, determining the road network elements corresponding to the current position information as updated road network elements according to the current position information. In practice, the execution subject may obtain, through the map application interface, a road network element corresponding to the current location information as an updated road network element.
Fourthly, for each obtained obstacle element with the updated driving state, executing the following steps:
the first substep is to update the road network elements in the initial simulation scene to the updated road network elements.
And a second substep of placing the updated host vehicle element in the updated road network element.
A third substep of placing the obstacle element, the driving state of which has been updated, in the updated road network element.
A fourth substep of determining the initial simulated scene in which the updated host vehicle element and the updated travel state of the obstacle element are placed as a simulated driving scene.
And fifthly, determining each determined simulated driving scene as a simulated driving scene set.
Optionally, the executing body may further store the set of simulated driving scenes in a scene library corresponding to the original scene. The scene library may be a database for storing generalized simulated driving scenes. Therefore, when the automatic driving technical scheme needs to be tested by utilizing the simulated driving scene set of the original scene, the simulated driving scene set can be directly obtained from the database.
The above embodiments of the present disclosure have the following advantages: by the aid of the simulated driving scene generation method of some embodiments, accuracy of each determined simulated driving scene and driving safety of the automatic driving technical scheme are improved. Specifically, the reasons for the determined driving scenes are that the accuracy is low and the driving safety is poor: a large number of unrealistic driving scenes can be generated through simple combination of scene element Cartesian products, whether the screened driving scenes are reasonable depends on completeness of constraint conditions, accuracy of each determined driving scene is low, accuracy of an automatic driving technical scheme tested according to each determined driving scene is low, and accordingly driving safety is poor. Based on this, the simulated driving scene generation method of some embodiments of the present disclosure first obtains scene data corresponding to an original scene of the target vehicle. The scene data includes track information and an obstacle information set of the target vehicle. Therefore, the scene data of the original scene can be used as the collected data in the real traffic state. And then, constructing an initial simulation scene corresponding to the target vehicle according to the track information and the obstacle information set included in the scene data. The initial simulation scene comprises a main vehicle element and an obstacle element set corresponding to the target vehicle. The obstacle elements in the obstacle element set correspond to the obstacle information in the obstacle information set. The obstacle elements in the obstacle element set correspond to a driving model. Therefore, the simulation scene can be constructed by taking the real traffic state as a prototype. Next, the host behavior information corresponding to the target vehicle is determined. Thus, the host behavior information may characterize the current behavior of the target vehicle. Then, for each barrier element in the set of barrier elements, the host behavior information is input to a driving model of the barrier element in the initial simulation scene, and the barrier element with the driving state updated is obtained. Thus, the change in the travel state of the obstacle element with respect to the current behavior of the target vehicle can be determined by the travel model. And finally, generating a simulated driving scene set corresponding to the target vehicle according to the initial simulated scene, the host vehicle element, the host vehicle behavior information and the obtained barrier elements after the driving states are updated. Therefore, different simulated driving scenes can be generalized on the basis of the initial simulation scene according to the driving state change of different barrier elements aiming at the current behavior of the target vehicle. And because each generated simulated driving scene is generalized on the basis of the initial simulated scene, and the initial simulated scene is a prototype of a real traffic state, each generated simulated driving scene accords with the actual logic and is not required to be further screened or eliminated through constraint conditions, the accuracy of each determined simulated driving scene is improved, the accuracy of the automatic driving technical scheme tested according to each determined simulated driving scene is further improved, and the driving safety is improved. Therefore, the accuracy of each determined simulation driving scene and the driving safety of the automatic driving technical scheme are improved.
With further reference to fig. 2, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a simulated driving scenario generation apparatus, which correspond to those shown in fig. 1, and which may be applied in various electronic devices in particular.
As shown in fig. 2, the simulated driving scenario generation apparatus 200 of some embodiments includes: an acquisition unit 201, a construction unit 202, a determination unit 203, an input unit 204, and a generation unit 205. The acquiring unit 201 is configured to acquire scene data corresponding to an original scene of a target vehicle, wherein the scene data includes trajectory information and an obstacle information set of the target vehicle; the construction unit 202 is configured to construct an initial simulation scene corresponding to the target vehicle according to the trajectory information and a set of obstacle information included in the scene data, where the initial simulation scene includes a host vehicle element and a set of obstacle elements corresponding to the target vehicle, the obstacle elements in the set of obstacle elements correspond to the obstacle information in the set of obstacle information, and the obstacle elements in the set of obstacle elements correspond to the driving model; the determination unit 203 is configured to determine the host behavior information corresponding to the above-described target vehicle; the input unit 204 is configured to input the host vehicle behavior information to a driving model of the obstacle element in the initial simulation scene for each obstacle element in the set of obstacle elements, resulting in an updated driving state of the obstacle element; the generating unit 205 is configured to generate a set of simulated driving scenes corresponding to the target vehicle based on the initial simulated scene, the host vehicle element, the host vehicle behavior information, and the obtained respective updated driving state obstacle elements.
It will be understood that the units described in the apparatus 200 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 200 and the units included therein, and are not described herein again.
Referring now to FIG. 3, a block diagram of an electronic device 300 (e.g., a server) suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 3, the electronic device 300 may include a processing means 301 (e.g., a central processing unit, a graphics processor, etc.) that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data necessary for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.
Generally, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 308 including, for example, magnetic tape, hard disk, etc.; and a communication device 309. The communication means 309 may allow the electronic device 300 to communicate wirelessly or by wire with other devices to exchange data. While fig. 3 illustrates an electronic device 300 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 3 may represent one device or may represent multiple devices, as desired.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. The computer program, when executed by the processing apparatus 301, performs the above-described functions defined in the methods of some embodiments of the present disclosure.
It should be noted that the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring scene data of an original scene corresponding to a target vehicle, wherein the scene data comprises track information and an obstacle information set of the target vehicle; constructing an initial simulation scene corresponding to the target vehicle according to trajectory information and an obstacle information set included in the scene data, wherein the initial simulation scene includes a main vehicle element and an obstacle element set corresponding to the target vehicle, an obstacle element in the obstacle element set corresponds to obstacle information in the obstacle information set, and an obstacle element in the obstacle element set corresponds to a driving model; determining the main vehicle behavior information corresponding to the target vehicle; for each barrier element in the barrier element set, inputting the host vehicle behavior information into a driving model of the barrier element in the initial simulation scene to obtain the barrier element with an updated driving state; and generating a simulated driving scene set corresponding to the target vehicle according to the initial simulated scene, the host vehicle element, the host vehicle behavior information and the obtained barrier elements after the driving states are updated.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of 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 the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit, a construction unit, a determination unit, an input unit, and a generation unit. Here, the names of these units do not constitute a limitation to the unit itself in some cases, and for example, the acquisition unit may also be described as a "unit that acquires scene data of an original scene of the corresponding subject vehicle".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems on a chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combinations of the above-mentioned features, and other embodiments in which the above-mentioned features or their equivalents are combined arbitrarily without departing from the spirit of the invention are also encompassed. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.
Claims (7)
1. A simulated driving scenario generation method comprises the following steps:
acquiring scene data of an original scene corresponding to a target vehicle, wherein the scene data comprises track information of the target vehicle and an obstacle information set, and obstacle information in the obstacle information set comprises obstacle coordinates;
constructing an initial simulation scene corresponding to the target vehicle according to the trajectory information and the set of obstacle information included in the scene data, wherein the initial simulation scene includes a host element and a set of obstacle elements corresponding to the target vehicle, the obstacle elements in the set of obstacle elements correspond to the obstacle information in the set of obstacle information, the obstacle elements in the set of obstacle elements correspond to a driving model, and the constructing the initial simulation scene corresponding to the target vehicle according to the trajectory information and the set of obstacle information included in the scene data includes:
selecting track coordinates meeting a preset time condition from the track coordinates included in the track information as current position coordinates of the target vehicle;
acquiring road network elements corresponding to the current position coordinates according to the current position coordinates;
for each obstacle information in the obstacle information set, constructing an obstacle element corresponding to the obstacle information;
constructing a main vehicle element corresponding to the target vehicle according to the vehicle information of the target vehicle;
placing the constructed host vehicle elements and the constructed barrier elements in the road network elements to obtain an initial simulation scene corresponding to the target vehicle, wherein the placing the constructed host vehicle elements and the constructed barrier elements in the road network elements to obtain an initial simulation scene corresponding to the target vehicle comprises:
placing the main vehicle element at a position corresponding to the current position coordinate in the road network element;
for each obstacle element constructed, the following steps are performed:
determining obstacle information corresponding to the obstacle elements in the obstacle information set as target obstacle information;
determining obstacle coordinates included in the target obstacle information as placement coordinates;
placing the barrier elements in the road network elements at positions corresponding to the placement coordinates;
determining the road network elements with the main vehicle elements and the constructed barrier elements as initial simulation scenes corresponding to the target vehicles;
determining primary behavior information corresponding to the target vehicle;
for each barrier element in the barrier element set, inputting the main vehicle behavior information into a driving model of the barrier element in the initial simulation scene to obtain the barrier element with an updated driving state;
generating a set of simulated driving scenes corresponding to the target vehicle according to the initial simulated scene, the host element, the host behavior information and the obtained barrier elements after each updated driving state, wherein the generating the set of simulated driving scenes corresponding to the target vehicle according to the initial simulated scene, the host element, the host behavior information and the obtained barrier elements after each updated driving state comprises:
determining current position information of the target vehicle according to the master behavior information;
updating the host vehicle element in the initial simulation scene according to the host vehicle behavior information to obtain an updated host vehicle element;
determining the road network elements corresponding to the current position information as updated road network elements according to the current position information;
for each resulting obstacle element after updating the driving status, performing the following steps:
updating the road network elements in the initial simulation scene into the updated road network elements;
placing the updated main vehicle element in the updated road network element;
placing the barrier elements with updated driving states in the updated road network elements;
determining the initial simulation scene in which the updated main vehicle elements and the updated obstacle elements in the driving state are placed as a simulation driving scene;
and determining each determined simulated driving scene as a set of simulated driving scenes.
2. The method of claim 1, wherein the obstacle information in the set of obstacle information further comprises an obstacle type; and
the constructing of the obstacle element corresponding to the obstacle information includes:
constructing an obstacle element corresponding to the obstacle type;
determining a driving model corresponding to the type of the obstacle as a driving model of the obstacle element.
3. The method of claim 2, wherein the determining a driving model corresponding to the type of obstacle as the driving model of the obstacle element comprises:
in response to determining that the type of the obstacle represents an obstacle vehicle, determining a virtual driver model corresponding to the type of the obstacle as a driving model corresponding to the obstacle element, wherein the virtual driver model corresponds to a driver avoidance mode;
and in response to the fact that the obstacle type represents the pedestrian, determining a virtual pedestrian model as a driving model corresponding to the obstacle element, wherein the virtual pedestrian model corresponds to a pedestrian avoidance mode.
4. The method according to one of claims 1-3, wherein the method further comprises:
and storing the simulation driving scene set to a scene library corresponding to the original scene.
5. A simulated driving scenario generation apparatus, comprising:
the system comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is configured to acquire scene data of an original scene corresponding to a target vehicle, the scene data comprises track information of the target vehicle and an obstacle information set, and obstacle information in the obstacle information set comprises obstacle coordinates;
a construction unit configured to construct an initial simulation scene corresponding to the target vehicle according to trajectory information and a set of obstacle information included in the scene data, wherein the initial simulation scene includes a host element corresponding to the target vehicle and a set of obstacle elements, an obstacle element in the set of obstacle elements corresponds to obstacle information in the set of obstacle information, an obstacle element in the set of obstacle elements corresponds to a driving model, and the initial simulation scene corresponding to the target vehicle is constructed according to trajectory information and a set of obstacle information included in the scene data, including:
selecting track coordinates meeting a preset time condition from the track coordinates included in the track information as current position coordinates of the target vehicle;
acquiring road network elements corresponding to the current position coordinates according to the current position coordinates;
for each obstacle information in the obstacle information set, constructing an obstacle element corresponding to the obstacle information;
constructing a main vehicle element corresponding to the target vehicle according to the vehicle information of the target vehicle;
placing the constructed host vehicle elements and the constructed barrier elements in the road network elements to obtain an initial simulation scene corresponding to the target vehicle, wherein the placing the constructed host vehicle elements and the constructed barrier elements in the road network elements to obtain an initial simulation scene corresponding to the target vehicle comprises:
placing the main vehicle element at a position corresponding to the current position coordinate in the road network element;
for each obstacle element constructed, the following steps are performed:
determining obstacle information corresponding to the obstacle elements in the obstacle information set as target obstacle information;
determining obstacle coordinates included in the target obstacle information as placement coordinates;
placing the barrier elements in the road network elements at positions corresponding to the placement coordinates;
determining the road network elements in which the main vehicle elements and the constructed barrier elements are placed as initial simulation scenes corresponding to the target vehicles;
a determination unit configured to determine host behavior information corresponding to the target vehicle;
an input unit configured to input the host vehicle behavior information to a driving model of the barrier element in the initial simulation scene for each barrier element in the set of barrier elements, resulting in an updated driving state of the barrier element;
a generating unit configured to generate a set of simulated driving scenes corresponding to the target vehicle according to the initial simulated scene, the host element, the host behavior information, and the obtained respective updated-driving-state obstacle elements, wherein the generating of the set of simulated driving scenes corresponding to the target vehicle according to the initial simulated scene, the host element, the host behavior information, and the obtained respective updated-driving-state obstacle elements comprises:
determining current position information of the target vehicle according to the master behavior information;
updating the host vehicle element in the initial simulation scene according to the host vehicle behavior information to obtain an updated host vehicle element;
determining the road network elements corresponding to the current position information as updated road network elements according to the current position information;
for each resulting obstacle element after updating the driving status, performing the following steps:
updating the road network elements in the initial simulation scene into the updated road network elements;
placing the updated main vehicle element in the updated road network element;
placing the barrier elements with updated driving states in the updated road network elements;
determining the initial simulation scene in which the updated main vehicle elements and the updated obstacle elements in the driving state are placed as a simulation driving scene;
and determining each determined simulated driving scene as a set of simulated driving scenes.
6. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-4.
7. A computer-readable medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, carries out the method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211503473.4A CN115526069B (en) | 2022-11-29 | 2022-11-29 | Simulated driving scene generation method, device, equipment and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211503473.4A CN115526069B (en) | 2022-11-29 | 2022-11-29 | Simulated driving scene generation method, device, equipment and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115526069A CN115526069A (en) | 2022-12-27 |
| CN115526069B true CN115526069B (en) | 2023-03-07 |
Family
ID=84705182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211503473.4A Active CN115526069B (en) | 2022-11-29 | 2022-11-29 | Simulated driving scene generation method, device, equipment and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115526069B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115876493B (en) * | 2023-01-18 | 2023-05-23 | 禾多科技（北京）有限公司 | Test scene generation method, device, equipment and medium for automatic driving |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005037491A (en) * | 2003-07-16 | 2005-02-10 | Soichi Nomura | Information control system for map course or the like |
| CN108931927A (en) * | 2018-07-24 | 2018-12-04 | 百度在线网络技术（北京）有限公司 | The creation method and device of unmanned simulating scenes |
| CN109884916A (en) * | 2019-02-26 | 2019-06-14 | 初速度（苏州）科技有限公司 | A kind of automatic Pilot Simulation Evaluation method and device |
| CN114239301A (en) * | 2021-12-21 | 2022-03-25 | 北京京东乾石科技有限公司 | Simulation scene generation method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11073597B2 (en) * | 2018-05-11 | 2021-07-27 | Continental Automotive Systems, Inc. | Three-dimensional point cloud generated by high-resolution flash LIDAR |
-
2022
- 2022-11-29 CN CN202211503473.4A patent/CN115526069B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005037491A (en) * | 2003-07-16 | 2005-02-10 | Soichi Nomura | Information control system for map course or the like |
| CN108931927A (en) * | 2018-07-24 | 2018-12-04 | 百度在线网络技术（北京）有限公司 | The creation method and device of unmanned simulating scenes |
| CN109884916A (en) * | 2019-02-26 | 2019-06-14 | 初速度（苏州）科技有限公司 | A kind of automatic Pilot Simulation Evaluation method and device |
| CN114239301A (en) * | 2021-12-21 | 2022-03-25 | 北京京东乾石科技有限公司 | Simulation scene generation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115526069A (en) | 2022-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107063711B (en) | Method and apparatus for testing unmanned vehicles | |
| US20220032933A1 (en) | Systems and methods for generating a task offloading strategy for a vehicular edge-computing environment | |
| US20210304900A1 (en) | Method and apparatus for predicting transmission of an infectious disease, computer apparatus and storage medium | |
| CN112150490B (en) | Image detection method, device, electronic equipment and computer readable medium | |
| CN115167182B (en) | Automatic driving simulation test method, device, equipment and computer readable medium | |
| CN115526069B (en) | Simulated driving scene generation method, device, equipment and computer readable medium | |
| CN115616937B (en) | Automatic driving simulation test method, device, equipment and computer readable medium | |
| CN114021330A (en) | Simulated traffic scene building method and system and intelligent vehicle control method | |
| CN115540893B (en) | Vehicle path planning method and device, electronic equipment and computer readable medium | |
| CN115534939B (en) | Vehicle control method, device, electronic equipment and computer readable medium | |
| JP2021517670A (en) | Methods and equipment for generating maps | |
| CN110457407B (en) | Method and apparatus for processing point cloud data | |
| JP2023015230A (en) | High-precision map generation method and device, electronic equipment and storage medium | |
| WO2012103308A1 (en) | Architecture and method for realistic vehicular networking and applications visualization | |
| CN113377030B (en) | Method for determining intersection signal control model and related device | |
| CN115544817B (en) | Driving scene generation method and device, electronic equipment and computer readable medium | |
| US11585667B2 (en) | Systems and methods for simulating edge-computing deployment in diverse terrains | |
| CN111688717B (en) | Method and device for controlling vehicle traffic | |
| CN115937352B (en) | Mine scene simulation method, system, electronic equipment and storage medium | |
| CN115366919A (en) | Trajectory prediction method, system, electronic device and storage medium | |
| CN113008246B (en) | Map matching method and device | |
| CN114417607A (en) | Traffic simulation method and system and electronic equipment | |
| CN113406962B (en) | Method and device for determining test information of automatic driving vehicle and electronic equipment | |
| CN114582124B (en) | Scene editing method, device, medium and electronic equipment | |
| CN115048015B (en) | Automatic driving simulation scene construction method and system based on high-precision map |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |