CN113946902A - Method, device and equipment for creating dynamic traffic flow scene and storage medium - Google Patents
Method, device and equipment for creating dynamic traffic flow scene and storage medium Download PDFInfo
- Publication number
- CN113946902A CN113946902A CN202010686442.1A CN202010686442A CN113946902A CN 113946902 A CN113946902 A CN 113946902A CN 202010686442 A CN202010686442 A CN 202010686442A CN 113946902 A CN113946902 A CN 113946902A
- Authority
- CN
- China
- Prior art keywords
- traffic
- scene
- traffic flow
- special
- creating
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides a method, a device, equipment and a storage medium for creating a dynamic traffic flow scene, wherein the method comprises the following steps: establishing a traffic flow participant model library, a special traffic scene library and a traffic obstacle scene library in a simulation system, wherein the traffic flow participant model comprises a vehicle model and a pedestrian model; creating a basic traffic flow complying with traffic rules in a simulation system based on a high-precision map and the traffic flow participant model library; creating a special traffic scene and/or creating a traffic obstacle scene; and generating a dynamic traffic flow scene based on the basic traffic flow and the created special traffic scene and/or traffic obstacle scene. The method generates random or fixed traffic flow meeting the requirements by utilizing the established model base, does not need to acquire traffic flow video of a real road, and has better portability and expansibility.
Description
Technical Field
The present application relates to the field of automatic driving test technologies, and in particular, to a method, an apparatus, a device, and a storage medium for creating a dynamic traffic flow scenario.
Background
With the continuous development of the automatic driving technology, the automatic driving computer simulation system is a basic key technology of automatic driving vehicle testing and experiment and also a basic tool for defining the related development process and the technical access standard of the automatic driving vehicle in the future industry. The automatic driving simulation test can replace the actual road test to a certain extent, and the test efficiency is improved. The establishment of the traffic flow is an indispensable part of automatic driving simulation, and the establishment of the traffic flow can enable an automatic driving algorithm to have a real road scene, various complex traffic flow scenes and the like during testing.
The existing method for establishing the traffic flow on the simulation platform needs to acquire traffic flow information on a real road, so that the difficulty and the cost of establishing the traffic flow are correspondingly increased, and the expandability is poor.
Disclosure of Invention
In view of this, the present application provides a scheme for creating a dynamic traffic flow scene, and aims to establish a dynamic traffic flow for simulation without using traffic flow information on a real road.
In order to achieve the purpose, the technical scheme adopted by the application is as follows:
in a first aspect, the present application provides a method of creating a dynamic traffic flow scenario, comprising:
establishing a traffic flow participant model library, a special traffic scene library and a traffic obstacle scene library in a simulation system, wherein the traffic flow participant model comprises a vehicle model and a pedestrian model, the special traffic scene is a scene in which an emergent traffic incident occurs, and the traffic obstacle scene is a scene in which obstacles exist on a road;
creating a basic traffic flow complying with traffic rules in a simulation system based on a high-precision map and the traffic flow participant model library;
creating a special traffic scene and/or creating a traffic obstacle scene;
and generating a dynamic traffic flow scene based on the basic traffic flow and the created special traffic scene and/or traffic obstacle scene.
Optionally, the model is a 3D model or a vector space model; the vehicle model comprises an automobile model and a non-automobile model; the traffic participant model comprises in particular spatial and movement parameters of the traffic participants.
Optionally, the special traffic scene library includes a plurality of special traffic scene models and a trigger condition of each special traffic scene, where the trigger condition is a condition for triggering occurrence of the special traffic scene, and the special traffic scene includes a front vehicle sudden stop scene, a pedestrian break-in scene, and a rear vehicle overtaking scene;
the traffic barrier scene library comprises a plurality of traffic barrier scene models, the traffic barrier scene models comprise scene occupation field sizes and corresponding motion parameters of different traffic participants entering the traffic barrier scene, and the traffic barrier scene comprises a road surface collapse scene, a road surface enclosure scene, a road surface projection scene, a sanitation cleaning scene, a manhole cover loss scene and a traffic light fault scene.
Optionally, the specific method for creating a basic traffic flow complying with the traffic rules in the simulation system based on the high-precision map and the traffic flow participant model library is as follows:
obtaining map parameters based on a high-precision map, and planning a traffic flow path, wherein the map parameters comprise road positions, widths, gradients, curvatures, traffic sign information and signal lamp information;
setting basic traffic flow parameters based on the traffic flow participant model library, wherein the basic traffic flow parameters comprise vehicle type proportion, driving behavior proportion, vehicle density, pedestrian density and pedestrian type proportion, the driving behavior comprises radical type and steady type, and the pedestrian type comprises walking pedestrians and running pedestrians;
and generating a basic traffic flow complying with traffic rules according to the planned path and the set basic traffic flow parameters.
Optionally, the specific method for creating a special traffic scene is to select a special traffic scene based on the special traffic scene library, set a special traffic scene density, and determine participants of the special traffic scene; the specific method for creating the traffic obstacle scene is to select the traffic obstacle scene based on the traffic obstacle scene library, determine the random generation density of the traffic obstacle scene and the fixed generation position of the traffic obstacle scene.
In a second aspect, the present application provides an apparatus for creating a dynamic traffic flow scenario, comprising:
the system comprises a database building module, a simulation system and a traffic flow participant model database, a special traffic scene database and a traffic obstacle scene database, wherein the database building module is used for building a traffic flow participant model database, the special traffic scene database and a traffic obstacle scene database in the simulation system, the traffic flow participant comprises vehicles and pedestrians, the special traffic scene is a scene in which an emergent traffic incident occurs, and the traffic obstacle scene is a scene in which obstacles exist on a road;
the first creating module is used for creating a basic traffic flow which complies with traffic rules in a simulation system based on a high-precision map and the traffic flow participant model base;
the second creation module is used for creating a special traffic scene and/or creating a traffic obstacle scene;
and the first generation module is used for generating a dynamic traffic flow scene based on the basic traffic flow and the created special traffic scene and/or traffic obstacle scene.
Optionally, the special traffic scene library includes a plurality of special traffic scene models and a trigger condition of each special traffic scene, where the trigger condition is a condition for triggering occurrence of the special traffic scene, and the special traffic scene includes a front vehicle sudden stop scene, a pedestrian break-in scene, and a rear vehicle overtaking scene;
the traffic barrier scene library comprises a plurality of traffic barrier scene models, the traffic barrier scene models comprise scene occupation field sizes and corresponding motion parameters of different traffic participants entering the traffic barrier scene, and the traffic barrier scene comprises a road surface collapse scene, a road surface enclosure scene, a road surface projection scene, a sanitation cleaning scene, a manhole cover loss scene and a traffic light fault scene.
Optionally, the first creating module specifically includes:
the route planning module is used for acquiring map parameters based on a high-precision map and planning a traffic flow path, wherein the map parameters comprise road positions, widths, slopes, curvatures, traffic sign information and signal lamp information;
a first parameter setting module, configured to set basic traffic flow parameters based on the traffic flow participant model library, where the basic traffic flow parameters include vehicle type proportion, driving behavior proportion, vehicle density, pedestrian density, and pedestrian type proportion, the driving behavior includes aggressive type and steady type, and the pedestrian type includes walking pedestrians and running pedestrians;
and the second generation module is used for generating a basic traffic flow complying with the traffic rule according to the planned path and the set basic traffic flow parameters.
In a third aspect, an embodiment of the present application further provides an apparatus, including: a processor, a memory and a communication unit;
the memory stores machine-readable instructions executable by the processor, the processor and the memory communicating through the communication unit when the device is operating;
wherein the processor executes the machine-readable instructions to perform the methods of the various aspects described above.
In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the method in the above aspects.
The beneficial effect of this application is:
1. the method generates random or fixed traffic flow meeting the requirements by utilizing the established model base, does not need to acquire traffic flow video of a real road, and has better portability and expansibility.
2. According to the method and the system, rich and various traffic flow scenes can be combined by extracting scenes in the model base, concurrent tasks are various, the formed scenes are random, and a large number of test scene schemes can be provided for unmanned vehicles.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
FIG. 1 is a flow chart of a method for creating a dynamic traffic flow scenario according to the present application;
FIG. 2 is a block diagram of an apparatus for creating a dynamic traffic flow scenario according to the present application;
FIG. 3 is a block diagram of a first creation module of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments.
The automatic driving simulation test can replace the actual road test to a certain extent, and the test efficiency is improved. The establishment of the traffic flow is an indispensable part of automatic driving simulation, and the establishment of the traffic flow can enable an automatic driving algorithm to have a real road scene, various complex traffic flow scenes and the like during testing. The existing method for establishing the traffic flow on the simulation platform needs to acquire traffic flow information on a real road, so that the difficulty and the cost of establishing the traffic flow are correspondingly increased, and the expandability is poor.
To solve the above problem, in a first aspect, the present application provides a method for creating a dynamic traffic flow scenario, as shown in fig. 1, the method including:
s101: establishing a traffic flow participant model library, a special traffic scene library and a traffic obstacle scene library in a simulation system, wherein the traffic flow participant model comprises a vehicle model and a pedestrian model, the special traffic scene is a scene in which an emergent traffic incident occurs, and the traffic obstacle scene is a scene in which obstacles exist on a road;
the model is a 3D model or a vector space model; the vehicle model comprises an automobile model and a non-automobile model; the traffic participant model comprises in particular spatial and movement parameters of the traffic participants. Specifically, the vehicle model may include vehicle parameters such as vehicle length, width, height, vehicle weight, driving type, maximum wheel rotation angle, vehicle finishing torque, brake pedal torque, running vehicle speed, vehicle acceleration, vehicle deceleration and the like; the pedestrian model comprises parameters such as the length, the width and the height of the pedestrian, walking speed, running speed, reaction time and the like. In addition, the traffic flow participant model in the application can also comprise an animal model, and the animal is added into the traffic flow participant, so that the scene on a real traffic road can be simulated more truly, and a more vivid automatic driving simulation test environment is provided. Similarly, the animal model may specifically include parameters such as length, width and height of the animal, walking speed, running speed, reaction time and the like.
The motor vehicles can comprise commercial vehicles such as buses, minibuses, light trucks and heavy trucks, non-commercial vehicles such as cars, motorcycles and commercial vehicles, and special vehicles such as ambulances and police cars; the pedestrians comprise common groups and special groups, wherein the special groups comprise the old, children and the disabled; the animal includes pets such as cats, dogs, etc.
Specifically, the special traffic scene library includes a plurality of special traffic scene models and a trigger condition of each special traffic scene, where the trigger condition is a condition that triggers occurrence of the special traffic scene, and the special traffic scene includes a front sudden stop scene, a pedestrian intrusion scene, and a rear overtaking scene, and in addition, may also include a side vehicle driving into a front lane, a front vehicle driving in opposite directions, and the like, and the special traffic scene includes, but is not limited to, the listed examples. Each scenario includes a trigger condition and a traffic participant model type. For example, if the traffic participant is a vehicle in a sudden stop before a scene, any vehicle or fixed vehicle in the traffic participant model library can be selected, and assuming that the vehicle before the sudden stop is a, the triggering condition may include: firstly, stopping the front vehicle A when the rear vehicle B is 3 meters away from the front vehicle A; and secondly, the front vehicle A stops suddenly when the front vehicle A is 5 meters away from the front vehicle C, and the like. For example, a pedestrian enters a scene, a traffic participant is a pedestrian, any pedestrian or child in the traffic participant model library can be selected, and at the moment, the triggering condition can be that the vehicle drives to a school road section or a road section with more pedestrians. When the system is in motion, the system records and stores vehicle position data in real time, calculates the position difference between vehicles according to the stored vehicle position data and judges the section where the vehicles are located.
Specifically, the traffic obstacle scene library includes a plurality of traffic obstacle scene models, the traffic obstacle scene models include scene occupation field sizes and corresponding motion parameters of different traffic participants entering the traffic obstacle scene, the traffic obstacle scene includes a road surface collapse scene, a road surface enclosure scene, a road surface protrusion scene, an environmental sanitation cleaning scene, a manhole cover loss scene, a traffic light fault scene and the like, and the traffic obstacle scene includes but is not limited to the enumerated examples.
For example: for the road surface enclosure scene, the area range of the road surface enclosure is the size of the occupied site of the scene, and the passing modes selected by different traffic participants aiming at the road surface enclosure scene are the corresponding motion parameters of the different traffic participants entering the traffic barrier scene. Examples are: the area of the road surface enclosure is 3m2And large vehicles such as buses, minibuses, light trucks and heavy trucks are selected to stop, and small and medium vehicles such as cars and motorcycles are selected to detour.
Another example is: for a scene with a protrusion on the road surface, the size of the protrusion is the size of the occupied field of the scene. Examples are: the length, width and height of the road surface projection are respectively 20cm, the vehicles with the minimum height of less than 20cm are selected to go around or stop, and the vehicles with the minimum height of more than 20cm are selected to go on.
It should be noted that the models or scenes in the traffic flow participant model library, the special traffic scene library and the traffic obstacle scene library can be expanded according to the requirements.
The step realizes that the traffic flow video of a real road does not need to be acquired by establishing a module library, so that the method has better portability and expansibility.
S102: creating a basic traffic flow complying with traffic rules in a simulation system based on a high-precision map and the traffic flow participant model library;
the specific method can be as follows:
(1) obtaining map parameters based on a high-precision map, and planning a traffic flow path, wherein the map parameters comprise road positions, widths, gradients, curvatures, traffic sign information and signal lamp information;
the high-precision map is an electronic map with higher precision and more data dimensions. The accuracy is higher, and the data dimension is more embodied by the fact that the data dimension comprises surrounding static information which is related to traffic besides road information. The high-precision map stores a large amount of driving assistance information as structured data, and the information can be divided into two types. The first type is road data such as lane information such as the position, type, width, gradient, and curvature of a lane line. The second type is fixed object information around a lane, such as traffic signs, traffic lights, etc., lane limits, junctions, obstacles and other road details, and further includes infrastructure information such as overhead objects, guard rails, number, road edge types, roadside landmarks, etc. The two types of data are map parameters described in the present application.
When the map parameters are obtained, the global map parameters or the map parameters of the main task nodes can be obtained, the global traffic flow path can be planned based on the obtained global map parameters, the point-to-point traffic flow path can be planned based on the obtained map parameters of the main task nodes, and each path is planned at a lane level. For example, if the simulation test is to be performed on the autonomous vehicles in the range of the whole Shanghai city, the high-precision global map parameters of the whole Shanghai city are acquired, and the traffic flow path of the whole Shanghai city can be planned in the system based on the acquired global map parameters; however, if only the periphery of the Shanghai transportation university in Shanghai city is subjected to simulation test on the automatically driven vehicle, the map parameters of the periphery of the Shanghai transportation university are only required to be acquired, and a traffic flow path from one place to another place of the periphery of the Shanghai transportation university can be planned in the system based on the map parameters of the periphery of the Shanghai transportation university.
(2) Setting basic traffic flow parameters based on the traffic flow participant model library, wherein the basic traffic flow parameters comprise vehicle type proportion, driving behavior proportion, vehicle density, pedestrian density and pedestrian type proportion, the driving behavior comprises radical type and steady type, and the pedestrian type comprises walking pedestrians and running pedestrians;
in specific implementation, a traffic flow participant model is obtained from the traffic flow participant model library, and corresponding parameter setting is carried out on the traffic flow participant model. For example: the vehicle type ratio is set to be 20% of commercial vehicle ratio, 70% of non-commercial vehicle ratio and 10% of special vehicle ratio, wherein the aggressive type ratio is 40%, the steady type ratio is 60% and the vehicle density is 50%. Assume that a global route can generate 100 vehicles according to vehicle density, wherein 20 vehicles are available for commercial vehicle types, 70 vehicles are available for non-commercial vehicle types, 10 vehicles are available for special vehicles, 40 vehicles are available for aggressive driving, and 60 vehicles are available for steady driving. The maximum speed of the aggressive vehicle exceeds a certain value, usually about 20%, of the preset maximum speed in the model base, and the maximum speed of the steady-weight vehicle does not exceed the preset maximum speed.
(3) And generating a basic traffic flow complying with traffic rules according to the planned path and the set basic traffic flow parameters.
After a traffic flow path is planned in the system and basic traffic flow parameters are set, the system can select corresponding traffic flow participants from the model base and generate a basic traffic flow according to the set basic traffic flow parameters and the planned path, and the basic traffic flow can simulate a real traffic flow and follow preset traffic rules to drive.
S103: creating a special traffic scene and/or creating a traffic obstacle scene;
specifically, the method for creating a special traffic scene is to select a special traffic scene and a trigger condition of the selected special traffic scene based on the special traffic scene library, set a special traffic scene density based on the generated basic traffic flow, and determine participants of the special traffic scene; the method for creating the traffic obstacle scene is to select the traffic obstacle scene based on the traffic obstacle scene library, determine the randomly generated density of the traffic obstacle scene and the fixed generation position of the traffic obstacle scene based on the generated basic traffic flow.
For example: selecting two scenes of pedestrian intrusion and front vehicle sudden stop in a special traffic scene, wherein the density accounts for 20% and 40% respectively, and the generation modes are random and fixed selection respectively, wherein traffic participants of pedestrians intruding into the scene are pedestrians, and assuming that the total number of the pedestrians in the generated basic traffic flow is 100, 20 pedestrians are randomly selected to execute the pedestrian intrusion scene; the traffic participants are vehicles in the front stop scene, and 40 vehicles are selected to execute the front stop scene, assuming that the total number of vehicles in the basic traffic flow is 100. It should be noted that the selected special traffic flow participant only has the attribute of participating in the special traffic scene, but needs to actually realize the special traffic scene and simultaneously satisfy the trigger condition of the special traffic scene.
Another example is: and randomly selecting a traffic obstacle scene generation mode, and setting the density of the traffic obstacle scene generation mode to be 50%, and randomly generating an obstacle scene in a region with the vehicle area accounting for 50% of the area of the travelable region of the road, such as the loss of a manhole cover or the collapse of a road surface. When the traffic participants enter the obstacle scene area, the traffic participants make corresponding movement reactions to detour or stop.
S104: and generating a dynamic traffic flow scene based on the basic traffic flow and the created special traffic scene and/or traffic obstacle scene.
After the basic traffic flow, the special traffic scene and the traffic obstacle scene are created, the special traffic scene or the traffic obstacle scene can be randomly combined on the basis of the basic traffic flow according to needs to obtain a dynamic traffic flow. And avoiding generating the positions of the master control vehicle, the road intersection and the occupied position when the dynamic traffic flow is created. When the traffic flow runs, information intercommunication is carried out among all traffic participants, and real traffic flow restoration is realized.
According to the method and the system, rich and various traffic flow scenes can be combined by extracting scenes in the model base, concurrent tasks are various, the formed scenes are random, and a large number of test scene schemes can be provided for unmanned vehicles.
In a second aspect, the present application provides an apparatus for creating a dynamic traffic flow scenario, as shown in fig. 2, including:
the database building module 210 is configured to build a traffic flow participant model database, a special traffic scene database and a traffic obstacle scene database in the simulation system, where the traffic flow participants include vehicles and pedestrians, the special traffic scene is a scene where an emergency traffic event occurs, and the traffic obstacle scene is a scene where an obstacle is present on a road;
the model is a 3D model or a vector space model; the vehicle model comprises an automobile model and a non-automobile model; the traffic participant model comprises in particular spatial and movement parameters of the traffic participants. Specifically, the vehicle model may include vehicle parameters such as vehicle length, width, height, vehicle weight, driving type, maximum wheel rotation angle, vehicle finishing torque, brake pedal torque, running vehicle speed, vehicle acceleration, vehicle deceleration and the like; the pedestrian model comprises parameters such as the length, the width and the height of the pedestrian, walking speed, running speed, reaction time and the like.
Specifically, the special traffic scene library comprises a plurality of special traffic scene models and a triggering condition of each special traffic scene, the triggering condition is a condition for triggering the special traffic scene to appear, and the special traffic scene comprises a front vehicle sudden stop scene, a pedestrian break-in scene and a rear vehicle overtaking scene, and in addition, the special traffic scene library also comprises a side vehicle running into a front lane, a front vehicle running in opposite directions and the like. Each scene comprises a triggering condition and a traffic participant model type
Specifically, the traffic barrier scene library comprises a plurality of traffic barrier scene models, the traffic barrier scene models comprise scene occupation field sizes and corresponding motion parameters of different traffic participants entering the traffic barrier scene, and the traffic barrier scene comprises a road surface collapse scene, a road surface enclosure scene, a road surface protruded object scene, an environmental sanitation cleaning scene, a manhole cover loss scene and a traffic light fault scene.
The library building module 210 realizes that the traffic flow video of the real road does not need to be collected by building a module library, so that the method has better portability and expansibility.
A first creating module 220 for creating a basic traffic flow complying with traffic rules in a simulation system based on a high-precision map and the traffic flow participant model library;
as an optional implementation manner, as shown in fig. 3, the first creating module 220 specifically includes:
the route planning module 221 is configured to obtain map parameters based on a high-precision map, and plan a traffic flow path, where the map parameters include road position, width, gradient, curvature, traffic sign information, and signal light information;
when the map parameters are obtained, the global map parameters or the map parameters of the main task nodes can be obtained, the global traffic flow path can be planned based on the obtained global map parameters, the point-to-point traffic flow path can be planned based on the obtained map parameters of the main task nodes, and each path is planned at a lane level. For example, if the simulation test is to be performed on the autonomous vehicles in the range of the whole Shanghai city, the high-precision global map parameters of the whole Shanghai city are acquired, and the traffic flow path of the whole Shanghai city can be planned in the system based on the acquired global map parameters; however, if only the periphery of the Shanghai transportation university in Shanghai city is subjected to simulation test on the automatically driven vehicle, the map parameters of the periphery of the Shanghai transportation university are only required to be acquired, and a traffic flow path from one place to another place of the periphery of the Shanghai transportation university can be planned in the system based on the map parameters of the periphery of the Shanghai transportation university.
A first parameter setting module 222, configured to set basic traffic flow parameters, where the basic traffic flow parameters include a vehicle type ratio, a driving behavior ratio, a vehicle density, a pedestrian density, and a pedestrian type ratio, the driving behavior includes an aggressive type and a steady type, and the pedestrian types include walking pedestrians and running pedestrians;
setting basic traffic flow parameters, wherein the basic traffic flow parameters comprise vehicle type proportion, driving behavior proportion, vehicle density, pedestrian density and pedestrian type proportion, the driving behavior comprises aggressive type and steady type, and the pedestrian type comprises walking pedestrians and running pedestrians;
for example: the vehicle type ratio is set to be 20% of commercial vehicle ratio, 70% of non-commercial vehicle ratio and 10% of special vehicle ratio, wherein the aggressive type ratio is 40%, the steady type ratio is 60% and the vehicle density is 50%. Assume that a global route can generate 100 vehicles according to vehicle density, wherein 20 vehicles are available for commercial vehicle types, 70 vehicles are available for non-commercial vehicle types, 10 vehicles are available for special vehicles, 40 vehicles are available for aggressive driving, and 60 vehicles are available for steady driving. The maximum speed of the aggressive vehicle exceeds a certain value, usually about 20%, of the preset maximum speed in the model base, and the maximum speed of the steady-weight vehicle does not exceed the preset maximum speed.
And a second generating module 223, configured to generate a basic traffic flow complying with the traffic rule according to the planned path and the set basic traffic flow parameter.
After the traffic flow path is planned and the basic traffic flow parameters are set, the second generation module 223 can select corresponding traffic flow participants from the model base, and generate a basic traffic flow according to the set basic traffic flow parameters and the planned path, wherein the basic traffic flow can simulate a real traffic flow and follow preset traffic rules.
A second creation module 230 for creating a special traffic scene and/or creating a traffic obstacle scene;
specifically, the second creating module 230 selects a special traffic scene and a trigger condition of the selected special traffic scene based on the special traffic scene library, sets a special traffic scene density based on the generated basic traffic flow, and determines participants of the special traffic scene; the second creation module 230 selects a traffic obstacle scene based on the library of traffic obstacle scenes, determines a randomly generated density of traffic obstacle scenes based on the generated base traffic flow, and a fixedly generated location of the traffic obstacle scenes.
For example: selecting two scenes of pedestrian intrusion and front vehicle sudden stop in a special traffic scene, wherein the density accounts for 20% and 40% respectively, and the generation modes are random and fixed selection respectively, wherein traffic participants of pedestrians intruding into the scene are pedestrians, and assuming that the total number of the pedestrians in the generated basic traffic flow is 100, 20 pedestrians are randomly selected to execute the pedestrian intrusion scene; the traffic participants are vehicles in the front stop scene, and 40 vehicles are selected to execute the front stop scene, assuming that the total number of vehicles in the basic traffic flow is 100. It should be noted that the selected special traffic flow participant only has the attribute of participating in the special traffic scene, but needs to actually realize the special traffic scene and simultaneously satisfy the trigger condition of the special traffic scene.
Another example is: and randomly selecting a traffic obstacle scene generation mode, and setting the density of the traffic obstacle scene generation mode to be 50%, and randomly generating an obstacle scene in a region with the vehicle area accounting for 50% of the area of the travelable region of the road, such as the loss of a manhole cover or the collapse of a road surface. When the traffic participants enter the obstacle scene area, the traffic participants make corresponding movement reactions to detour or stop.
A first generating module 240 for generating a dynamic traffic flow scenario based on the base traffic flow and the created special traffic scenario and/or traffic obstacle scenario.
After creating the basic traffic flow, the special traffic scene and the traffic obstacle scene, the first generating module 240 may optionally combine the special traffic scene or the traffic obstacle scene on the basis of the basic traffic flow to obtain the dynamic traffic flow. And avoiding generating the positions of the master control vehicle, the road intersection and the occupied position when the dynamic traffic flow is created. When the traffic flow runs, information intercommunication is carried out among all traffic participants, and real traffic flow restoration is realized.
According to the method and the system, rich and various traffic flow scenes can be combined by extracting scenes in the model base, concurrent tasks are various, the formed scenes are random, and a large number of test scene schemes can be provided for unmanned vehicles.
In a third aspect, an embodiment of the present application further provides an apparatus, including: a processor, a memory and a communication unit;
the memory stores machine-readable instructions executable by the processor, the processor and the memory communicating through the communication unit when the device is operating;
wherein the processor executes the machine-readable instructions to perform the methods of the various aspects described above.
The memory may be used to store instructions for execution by the processor and may be implemented by any type of volatile or non-volatile memory terminal or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. The execution instructions in the memory, when executed by the processor, enable the apparatus to perform some or all of the steps in the method embodiments described below.
The processor is a control center of the storage terminal, connects various parts of the whole electronic terminal by using various interfaces and lines, and executes various functions of the electronic terminal and/or processes data by operating or executing software programs and/or modules stored in the memory and calling data stored in the memory. The processor may be composed of an Integrated Circuit (IC), for example, a single packaged IC, or a plurality of packaged ICs connected with the same or different functions. For example, a processor may include only a Central Processing Unit (CPU). In the embodiments of the present application, the CPU may be a single arithmetic core or may include multiple arithmetic cores.
A communication unit for establishing a communication channel so that the storage device can communicate with other terminals. And receiving user data sent by other terminals or sending the user data to other terminals.
In a fourth aspect, embodiments of the present application further provide a computer storage medium, where the computer storage medium may store a program, and the program may include some or all of the steps in the embodiments provided in the present application when executed. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a Random Access Memory (RAM).
The method generates random or fixed traffic flow meeting the requirements by utilizing the established model base, does not need to acquire traffic flow video of a real road, and has better portability and expansibility; in addition, rich and diverse traffic flow scenes can be combined by extracting scenes in the model library, concurrent tasks of the traffic flow scenes are diverse, the combined scenes are random, and a large number of test scene schemes can be provided for the unmanned vehicles.
In the embodiments provided in the present application, it should be understood that the disclosed system and method may be implemented in other ways. For example, the above-described node embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another device, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The modules described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, each functional module in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method of creating a dynamic traffic flow scenario, comprising:
establishing a traffic flow participant model library, a special traffic scene library and a traffic obstacle scene library in a simulation system, wherein the traffic flow participant model comprises a vehicle model and a pedestrian model, the special traffic scene is a scene in which an emergent traffic incident occurs, and the traffic obstacle scene is a scene in which obstacles exist on a road;
creating a basic traffic flow complying with traffic rules in a simulation system based on a high-precision map and the traffic flow participant model library;
creating a special traffic scene and/or creating a traffic obstacle scene;
and generating a dynamic traffic flow scene based on the basic traffic flow and the created special traffic scene and/or traffic obstacle scene.
2. A method of creating a dynamic traffic flow scenario as claimed in claim 1, wherein the model is a 3D model or a vector space model; the vehicle model comprises an automobile model and a non-automobile model; the traffic participant model comprises in particular spatial and movement parameters of the traffic participants.
3. The method of creating a dynamic traffic flow scenario according to claim 2, wherein the special traffic scenario library includes a plurality of special traffic scenario models and a trigger condition for each special traffic scenario, the trigger condition being a condition that triggers the occurrence of the special traffic scenario, the special traffic scenario including a front sudden stop scenario, a pedestrian intrusion scenario, and a rear overtaking scenario;
the traffic barrier scene library comprises a plurality of traffic barrier scene models, the traffic barrier scene models comprise scene occupation field sizes and corresponding motion parameters of different traffic participants entering the traffic barrier scene, and the traffic barrier scene comprises a road surface collapse scene, a road surface enclosure scene, a road surface projection scene, a sanitation cleaning scene, a manhole cover loss scene and a traffic light fault scene.
4. The method for creating a dynamic traffic flow scene according to claim 1, wherein the specific method for creating the basic traffic flow complying with the traffic rules in the simulation system based on the high-precision map and the traffic flow participant model library is as follows:
obtaining map parameters based on a high-precision map, and planning a traffic flow path, wherein the map parameters comprise road positions, widths, gradients, curvatures, traffic sign information and signal lamp information;
setting basic traffic flow parameters based on the traffic flow participant model library, wherein the basic traffic flow parameters comprise vehicle type proportion, driving behavior proportion, vehicle density, pedestrian density and pedestrian type proportion, the driving behavior comprises radical type and steady type, and the pedestrian type comprises walking pedestrians and running pedestrians;
and generating a basic traffic flow complying with traffic rules according to the planned path and the set basic traffic flow parameters.
5. The method for creating a dynamic traffic flow scene according to claim 1, wherein the specific method for creating a special traffic scene is to select a special traffic scene based on the special traffic scene library, set a special traffic scene density, and determine the special traffic scene participants; the specific method for creating the traffic obstacle scene is to select the traffic obstacle scene based on the traffic obstacle scene library, determine the random generation density of the traffic obstacle scene and the fixed generation position of the traffic obstacle scene.
6. An apparatus for creating a dynamic traffic flow scenario, comprising:
the system comprises a database building module, a simulation system and a traffic flow participant model database, a special traffic scene database and a traffic obstacle scene database, wherein the database building module is used for building a traffic flow participant model database, the special traffic scene database and a traffic obstacle scene database in the simulation system, the traffic flow participant comprises vehicles and pedestrians, the special traffic scene is a scene in which an emergent traffic incident occurs, and the traffic obstacle scene is a scene in which obstacles exist on a road;
the first creating module is used for creating a basic traffic flow which complies with traffic rules in a simulation system based on a high-precision map and the traffic flow participant model base;
the second creation module is used for creating a special traffic scene and/or creating a traffic obstacle scene;
and the first generation module is used for generating a dynamic traffic flow scene based on the basic traffic flow and the created special traffic scene and/or traffic obstacle scene.
7. The apparatus for creating a dynamic traffic flow scenario according to claim 6, wherein the special traffic scenario library includes a plurality of special traffic scenario models and a trigger condition for each special traffic scenario, the trigger condition is a condition for triggering occurrence of the special traffic scenario, and the special traffic scenarios include a front sudden stop scenario, a pedestrian intrusion scenario and a rear overtaking scenario;
the traffic barrier scene library comprises a plurality of traffic barrier scene models, the traffic barrier scene models comprise scene occupation field sizes and corresponding motion parameters of different traffic participants entering the traffic barrier scene, and the traffic barrier scene comprises a road surface collapse scene, a road surface enclosure scene, a road surface projection scene, a sanitation cleaning scene, a manhole cover loss scene and a traffic light fault scene.
8. The apparatus for creating a dynamic traffic flow scenario of claim 6, wherein the first creation module specifically comprises:
the route planning module is used for acquiring map parameters based on a high-precision map and planning a traffic flow path, wherein the map parameters comprise road positions, widths, slopes, curvatures, traffic sign information and signal lamp information;
the first parameter setting module is used for setting basic traffic flow parameters, wherein the basic traffic flow parameters comprise vehicle type proportion, driving behavior proportion, vehicle density, pedestrian density and pedestrian type proportion, the driving behaviors comprise radical type and steady type, and the pedestrian types comprise walking pedestrians and running pedestrians;
and the second generation module is used for generating a basic traffic flow complying with the traffic rule according to the planned path and the set basic traffic flow parameters.
9. An apparatus, comprising: a processor, a memory and a communication unit;
the memory stores machine-readable instructions executable by the processor, the processor and the memory communicating through the communication unit when the device is operating;
wherein the processor executes the machine readable instructions to perform the method of any of claims 1 to 5.
10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, performs the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010686442.1A CN113946902A (en) | 2020-07-16 | 2020-07-16 | Method, device and equipment for creating dynamic traffic flow scene and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010686442.1A CN113946902A (en) | 2020-07-16 | 2020-07-16 | Method, device and equipment for creating dynamic traffic flow scene and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113946902A true CN113946902A (en) | 2022-01-18 |
Family
ID=79326376
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010686442.1A Pending CN113946902A (en) | 2020-07-16 | 2020-07-16 | Method, device and equipment for creating dynamic traffic flow scene and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113946902A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115240409A (en) * | 2022-06-17 | 2022-10-25 | 上海智能网联汽车技术中心有限公司 | Method for extracting dangerous scene based on driver model and traffic flow model |
| CN115376306A (en) * | 2022-08-22 | 2022-11-22 | 南京工业大学 | Intelligent traffic dynamic marking method |
| CN116933509A (en) * | 2023-07-07 | 2023-10-24 | 西安深信科创信息技术有限公司 | Automatic driving traffic flow simulation method, system, equipment and storage medium |
-
2020
- 2020-07-16 CN CN202010686442.1A patent/CN113946902A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115240409A (en) * | 2022-06-17 | 2022-10-25 | 上海智能网联汽车技术中心有限公司 | Method for extracting dangerous scene based on driver model and traffic flow model |
| CN115240409B (en) * | 2022-06-17 | 2024-02-06 | 上智联(上海)智能科技有限公司 | Method for extracting dangerous scene based on driver model and traffic flow model |
| CN115376306A (en) * | 2022-08-22 | 2022-11-22 | 南京工业大学 | Intelligent traffic dynamic marking method |
| CN116933509A (en) * | 2023-07-07 | 2023-10-24 | 西安深信科创信息技术有限公司 | Automatic driving traffic flow simulation method, system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113946902A (en) | Method, device and equipment for creating dynamic traffic flow scene and storage medium | |
| CN109215433B (en) | Vision-based driving scenario generator for automated driving simulation | |
| CN113486531B (en) | Vehicle driving path planning method, device and system | |
| CN113032285B (en) | High-precision map testing method and device, electronic equipment and storage medium | |
| US11385991B1 (en) | Collision evaluation for log-based simulations | |
| CN110910673B (en) | Method and system for reminding pedestrian to collide with vehicle, camera and mobile terminal | |
| Chen et al. | Mixed test environment-based vehicle-in-the-loop validation-a new testing approach for autonomous vehicles | |
| CN110147085B (en) | Test method, test device and test system for automatic driving | |
| CN114746323A (en) | Simulation with modified factors for testing autonomous vehicle software | |
| RU2601133C2 (en) | Simulation model of traffic and pedestrian flows in urban conditions based on agent-oriented approach | |
| Berger et al. | Model-based, composable simulation for the development of autonomous miniature vehicles | |
| JPH11272158A (en) | Road traffic system evaluation simulation device | |
| CN113867367B (en) | Processing method and device for test scene and computer program product | |
| US20230031130A1 (en) | Open door reconstruction for sensor simulation | |
| JP2024513666A (en) | Instantiating objects in a simulated environment based on log data | |
| US20230339513A1 (en) | Method for testing autonomous-driving algorithm, and related device | |
| CN117413257A (en) | Method and system for testing driver assistance system for vehicle | |
| CN114906170A (en) | Motion planning method and device, electronic equipment and storage medium | |
| Sabir et al. | PrOMor: A proposed prototype of V2V and V2I for crash prevention in the Moroccan case | |
| US20240060788A1 (en) | Map simulation services | |
| US20240232476A1 (en) | Simulation test validation | |
| Narvaez et al. | CARLA-based Simulation Environment for Testing and Developing Autonomous Vehicles in the Linden Residential Area | |
| US20240232457A1 (en) | Test validation | |
| Schulze et al. | Vulnerable Road User protection using Collective Perception | |
| CN111381517B (en) | Simulation method, system and storage medium |
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 |