WO2020224462A1 - 驾驶仿真场景的处理方法、装置及存储介质 - Google Patents

驾驶仿真场景的处理方法、装置及存储介质 Download PDF

Info

Publication number
WO2020224462A1
WO2020224462A1 PCT/CN2020/087045 CN2020087045W WO2020224462A1 WO 2020224462 A1 WO2020224462 A1 WO 2020224462A1 CN 2020087045 W CN2020087045 W CN 2020087045W WO 2020224462 A1 WO2020224462 A1 WO 2020224462A1
Authority
WO
WIPO (PCT)
Prior art keywords
driving
vehicle
background
path
background vehicle
Prior art date
Application number
PCT/CN2020/087045
Other languages
English (en)
French (fr)
Inventor
杜海宁
Original Assignee
腾讯科技（深圳）有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Priority to EP20801543.8A priority Critical patent/EP3968001A4/en
Publication of WO2020224462A1 publication Critical patent/WO2020224462A1/zh
Priority to US17/378,432 priority patent/US11971723B2/en

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M17/00—Testing of vehicles
    • G01M17/007—Wheeled or endless-tracked vehicles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M17/00—Testing of vehicles
    • G01M17/007—Wheeled or endless-tracked vehicles
    • G01M17/06—Steering behaviour; Rolling behaviour
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B17/00—Systems involving the use of models or simulators of said systems
    • G05B17/02—Systems involving the use of models or simulators of said systems electric
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/80—Arrangements for reacting to or preventing system or operator failure
    • G05D1/81—Handing over between on-board automatic and on-board manual control
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/36—Preventing errors by testing or debugging software
    • G06F11/3668—Software testing
    • G06F11/3672—Test management
    • G06F11/3684—Test management for test design, e.g. generating new test cases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/36—Preventing errors by testing or debugging software
    • G06F11/3668—Software testing
    • G06F11/3672—Test management
    • G06F11/3688—Test management for test execution, e.g. scheduling of test suites
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/05—Type of road, e.g. motorways, local streets, paved or unpaved roads
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/10—Number of lanes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
    • B60W2555/60—Traffic rules, e.g. speed limits or right of way
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2720/00—Output or target parameters relating to overall vehicle dynamics
    • B60W2720/10—Longitudinal speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2720/00—Output or target parameters relating to overall vehicle dynamics
    • B60W2720/12—Lateral speed

Definitions

  • This application relates to automatic driving technology, and in particular to a method, device and storage medium for processing a driving simulation scene.
  • Autonomous vehicles are also known as unmanned vehicles and computer-driven vehicles. Such vehicles can travel along the road autonomously under unmanned conditions. Usually, before the autonomous vehicle is put into use, a lot of tests are required to check its safety and stability.
  • related technologies provide driving simulation platforms to build simulation test scenarios to perform simulation tests on autonomous vehicles.
  • users need to manually add background vehicles and tests Therefore, for large-scale simulation test scenarios that require more background vehicles, this construction method has low processing efficiency.
  • the embodiments of the present application provide a method, device, and storage medium for processing a driving simulation scene, which can automatically construct a driving simulation scene for vehicle simulation with high processing efficiency.
  • the embodiment of the present application provides a method for processing a driving simulation scene, including:
  • Generate a background vehicle and control the background vehicle to drive into the road network model from the starting point, and drive out of the road network model when it reaches the stopping point.
  • the embodiment of the present application also provides a device for processing a driving simulation scene, including:
  • the acquiring unit is used to acquire multiple path endpoints in the road network model used for driving simulation
  • a determining unit configured to determine at least one first route end point among the plurality of route end points as a departure point, and at least one first route end point as a collection point;
  • the control unit is configured to control the background vehicle to drive into the road network model from the starting point, and drive out of the road network model when it reaches the stopping point.
  • the embodiment of the present application also provides a device for processing a driving simulation scene, including:
  • Memory used to store executable instructions
  • the processor is configured to execute the executable instructions stored in the memory to implement the aforementioned driving simulation scenario processing method provided in the embodiment of the present application.
  • the embodiment of the present application provides a storage medium that stores executable instructions, which are used to cause the processor to execute the method for processing the above-mentioned driving simulation scenario provided by the embodiment of the present application.
  • the background vehicle is generated at the departure point in the road network model. In this way, the automatic generation of the background vehicle during the driving simulation process is realized, and the processing efficiency of the driving simulation scene is improved;
  • FIG. 1 is a schematic diagram of the architecture of a driving simulation system provided by an embodiment of the present application
  • Fig. 2 is a schematic diagram of a simulation test principle of a driving simulation platform provided by an embodiment of the present application
  • FIG. 3 is a schematic diagram of the architecture of an automatic driving system provided by an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of a processing device for a driving simulation scene provided by an embodiment of the present application.
  • FIG. 5 is a schematic flowchart of a method for processing a driving simulation scene provided by an embodiment of the present application
  • FIG. 6 is a schematic diagram of the departure point and the collection point in the road network model provided by the embodiment of the present application.
  • FIG. 7 is a schematic diagram of generating a test vehicle and a background vehicle at a departure point according to an embodiment of the present application
  • FIG. 8 is a schematic diagram of a vehicle traveling to a path crossing position and a signal light position according to an embodiment of the present application
  • FIG. 9 is a schematic diagram of the steering ratio of the background vehicle at the path crossing position provided by an embodiment of the application.
  • FIG. 10 is a schematic diagram of a process of generating a test vehicle and a background vehicle according to an embodiment of the application
  • FIG. 11 is a schematic flowchart of a steering decision control of a background vehicle provided by an embodiment of the application.
  • first ⁇ second involved is only to distinguish similar objects, and does not represent a specific order for the objects. Understandably, “first ⁇ second” can be used if allowed The specific order or sequence is exchanged, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein.
  • Autonomous driving refers to the ability to guide and make decisions on vehicle driving tasks without the need for the test driver to perform physical driving operations, and replace the test driver's control behavior to enable the vehicle to complete the function of safe driving.
  • test vehicle is used to simulate the autonomous vehicle and its dynamic characteristics (such as power, torque, and acceleration from 100 kilometers) to replace the autonomous vehicle in the driving simulation, and the driving strategy applied to the autonomous vehicle (ie Autonomous driving algorithm) for safety and stability testing.
  • dynamic characteristics such as power, torque, and acceleration from 100 kilometers
  • Road network model based on map data, can be different levels of map data (city map, urban area map, etc.) of the real world, or custom virtual world map data for 3D or 2D construction.
  • a graphical mathematical model for the driving of the test vehicle and the background vehicle obtained by the simulation.
  • Path planning based on the current state of the vehicle (including position, speed and acceleration), the current driving scene (the characteristics of the vehicle's environment from different dimensions, such as the degree of congestion on the road, whether the driving position corresponds to the signal light Position/path crossing position, etc.), and the target state of the vehicle (including target position, speed and acceleration), and the calculated smooth path from the current position to the target position.
  • Speed planning the speed of each path point is calculated on the basis of the path obtained from the path planning, thereby forming a speed curve.
  • Pick-up point the location where the test vehicle and/or background vehicle disappear in the road network model, that is, the vehicle exits the road network model from this location.
  • the pick-up point can be the same location as the departure point (that is, the pick-up point is also Departure point), or a different location from the departure point.
  • the executed one or more operations can be real-time or have a set delay ; Unless otherwise specified, there is no restriction on the order of execution of multiple operations performed.
  • the driving simulation scene processing device provided in the embodiment of the application may adopt the form of software or a combination of software and hardware, such as the embodiment of the application.
  • the provided processing device for the driving simulation scene may be a sub-function of the driving simulation platform, so that it can be set in any type of driving simulation scene processing device, such as computer terminals, servers, and server clusters.
  • FIG. 1 is a schematic diagram of an optional architecture of a driving simulation system 100 provided by an embodiment of the present application.
  • various users of a terminal a terminal 200-1 and a terminal 200-2 are exemplarily shown
  • the terminal connects the terminal to the server 300 integrated with the driving simulation platform (including the driving simulation scenario processing device provided in the embodiment of the present application) through the network 400;
  • the network 400 may be a wide area network Or a local area network, or a combination of the two, use wireless links to achieve data transmission.
  • the terminal (such as the terminal 200-1) is used to send a simulation test request corresponding to the autonomous driving vehicle, the simulation test request carrying the driving strategy of the autonomous driving vehicle;
  • the server 300 is configured to respond to the simulation test request, obtain map data corresponding to the test road network of the autonomous driving vehicle, and establish a road network model for the simulation test of the autonomous vehicle based on the map data, and the starting point in the road network model , Generate background vehicles and test vehicles corresponding to autonomous vehicles, control the driving state of background vehicles, make background vehicles drive into the road network model from the starting point, and drive out of the road network model when they drive to the receiving point, and monitor the response of the test vehicle Based on the driving state of the background vehicle, path planning and/or speed planning based on the driving strategy, return the simulation test results of the test vehicle at different time points;
  • the terminal (such as the terminal 200-1) is also used to display the simulation test results of the test vehicle at different time points through a graphical interface (such as the graphical interface 210-1).
  • the terminal (such as the terminal 200-1) is provided with a driving simulation client, and the terminal (such as the terminal 200-1) realizes the simulation test of the autonomous vehicle based on the driving simulation client, and when the user triggers the simulation test instruction
  • the driving simulation client sends a simulation test request corresponding to the autonomous driving vehicle to the server 300, receives the simulation test result returned by the server 300, and displays the received simulation test result through the simulation test interface of the driving simulation client.
  • FIG. 2 is a schematic diagram of the simulation test principle of the driving simulation platform provided by the embodiment of the present application.
  • the server 300 when the server 300 performs a simulation test on the autonomous vehicle through the driving simulation platform, it obtains the information of the autonomous vehicle from the database 500 Test the map data corresponding to the road network, and then perform three-dimensional modeling based on the map data to obtain a road network model for simulation testing; in the road network model, a test vehicle that conforms to the dynamics model of the autonomous vehicle is generated, and the test vehicle conforms to the prediction Set at least one background vehicle with a dynamic model (which can be the same as or different from the dynamic model of the autonomous vehicle), control the background vehicle's driving in the road network model, and monitor the driving state of the test vehicle in response to the background vehicle, based on driving The path planning and/or speed planning made by the strategy (autonomous driving algorithm) to verify whether the decision of changing lanes, overtaking, following, parking and other decisions made by the test vehicle controlled by the automatic driving algorithm in response to different
  • the strategy autonomous driving
  • the automatic driving algorithm for controlling the test vehicle will be described.
  • the automatic driving algorithm is applied in the automatic driving system to realize the different levels of automatic driving functions of the vehicle. See Figure 3, which is the application
  • the embodiment provides a schematic diagram of the architecture of the automatic driving system.
  • the automatic driving system 30 includes an environment perception system 31, a decision planning system 32, and a vehicle control system 33. It is understandable that the aforementioned systems included in the automatic driving system 30 may also be referred to as subsystems or modules in some embodiments, which will be described separately below.
  • the environment perception system 31 is used to perceive environment information, including the position, speed, orientation of obstacles in the environment, and object classification (such as vehicles, pedestrians, bicycles).
  • object classification such as vehicles, pedestrians, bicycles.
  • a high-precision map of the vehicle's own state including speed, acceleration, and direction
  • the real-time location of the vehicle can also be sensed.
  • the decision-making and planning system 32 predicts the perceived obstacles based on the environmental information and the target location, combined with objective physical laws, obstacles and surrounding environment, and accumulated historical data knowledge, so as to make macroscopic decisions to ensure the smooth operation of the vehicle Reach the goal state.
  • the decision of the decision planning system 32 includes lane selection, reference vehicle speed, whether to normally follow obstacles (such as people, cars, etc.) on the road, whether to bypass obstacles (such as people, cars, etc.), whether to stop, Whether to wait for avoidance when encountering traffic lights and pedestrians, and to pass by other vehicles at intersections, etc.
  • the decision planning system 32 is also used for driving planning (including path planning and speed planning) based on the environmental perception information and the decisions made, including selecting the path points of the trajectory, and the speed, direction and direction of the vehicle when reaching each path point. Acceleration etc.
  • the waypoints not only maintain continuity in time and space, but also the speed, orientation, acceleration and other parameters of each waypoint are within the actual operational physical range of the vehicle.
  • the vehicle control system 33 receives the driving plan made by the decision planning system 32, performs dynamic calculations based on the attributes of the vehicle body and external physical factors, and converts it into the vehicle control parameters such as the throttle amount, brake amount, and steering wheel signal for electronic control of the vehicle and executes it .
  • FIG. 4 is a schematic structural diagram of a driving simulation scene processing device provided by an embodiment of the present application.
  • the driving simulation scene processing device 40 shown in FIG. 4 includes: at least one processor 410, a memory 450, and at least one network interface 420 and user interface 430.
  • the components in the processing device 40 of the driving simulation scene are coupled together through the bus system 440.
  • the bus system 440 is used to implement connection and communication between these components.
  • the bus system 440 also includes a power bus, a control bus, and a status signal bus. However, for clarity of description, various buses are marked as the bus system 440 in FIG. 4.
  • the processor 410 may be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware Components, etc., where the general-purpose processor may be a microprocessor or any conventional processor.
  • DSP Digital Signal Processor
  • the user interface 430 includes one or more output devices 431 that enable the presentation of media content, including one or more speakers and/or one or more visual display screens.
  • the user interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as a keyboard, a mouse, a microphone, a touch screen display, a camera, and other input buttons and controls.
  • the memory 450 includes volatile memory or nonvolatile memory, and may also include both volatile and nonvolatile memory.
  • the non-volatile memory may be a read only memory (ROM, Read Only Memory), and the volatile memory may be a random access memory (RAM, Random Access Memory).
  • the memory 450 described in the embodiment of the present application is intended to include any suitable type of memory.
  • the memory 450 optionally includes one or more storage devices that are physically remote from the processor 410.
  • the memory 450 can store data to support the operation of the processing device 40 of the driving simulation scene. Examples of these data include programs, modules, and data structures, or a subset or superset thereof, as illustrated below.
  • Operating system 451 including system programs for processing various basic system services and performing hardware-related tasks, such as framework layer, core library layer, driver layer, etc., for implementing various basic services and processing hardware-based tasks;
  • the network communication module 452 is used to reach other computing devices via one or more (wired or wireless) network interfaces 420.
  • Exemplary network interfaces 420 include: Bluetooth, wireless compatibility authentication (WiFi), and universal serial bus ( USB, Universal Serial Bus), etc.;
  • the display module 453 is used to enable the presentation of information via one or more output devices 431 (for example, a display screen, a speaker, etc.) associated with the user interface 430 (for example, a user interface for operating peripheral devices and displaying content and information) );
  • output devices 431 for example, a display screen, a speaker, etc.
  • the user interface 430 for example, a user interface for operating peripheral devices and displaying content and information
  • the input processing module 454 is configured to detect one or more user inputs or interactions from one of the one or more input devices 432 and translate the detected inputs or interactions.
  • the memory 450 may also include the driving simulation scene processing device 455 provided in the embodiment of the application; the driving simulation scene processing device 455 uses a software unit in Figure 4, including an acquisition unit 4551, a determination unit 4552, a generation unit 4553, and a control unit 4554; wherein the acquisition unit is used to acquire multiple paths in the road network model for driving simulation End point; determination unit, used to determine at least one route end point among the multiple route end points as the departure point, and at least one route end point as the collection point; generation unit, used to generate the background in the departure point in the road network model Vehicle; control unit, used to control the background vehicle to drive into the road network model from the starting point, and drive out of the road network model when it reaches the stopping point.
  • the driving simulation scene processing device 455 uses a software unit in Figure 4, including an acquisition unit 4551, a determination unit 4552, a generation unit 4553, and a control unit 4554; wherein the acquisition unit is used to acquire multiple paths in the road network model for driving simulation End point; determination unit, used
  • the driving simulation scene processing device 455 provided in the embodiment of this application can be implemented in a pure hardware form or a combination of software and hardware.
  • the driving simulation scene processing device 455 provided in the embodiment of the application using hardware implementation it can be
  • the processor 410 in the form of a hardware decoding processor is directly used to execute the processing method for completing the driving simulation scenario provided in the embodiment of the present application, for example, it is used by one or more application specific integrated circuits (ASIC, Application Specific Integrated Circuit), DSP, Programmable Logic Device (PLD, Programmable Logic Device), Complex Programmable Logic Device (CPLD, Complex Programmable Logic Device), Field-Programmable Gate Array (FPGA, Field-Programmable Gate Array) or other electronic components execute and implement the embodiments of this application Provide the processing method of driving simulation scene.
  • ASIC Application Specific Integrated Circuit
  • DSP Programmable Logic Device
  • PLD Programmable Logic Device
  • CPLD Complex Programmable Logic Device
  • FPGA Field-Programmable Gate Array
  • FIG. 5 is an optional flowchart of a method for processing a driving simulation scene provided by an embodiment of the present application. Take a server (such as the server 300 in FIG. 1) for processing a driving simulation scene as an example, in conjunction with FIG. And FIG. 5 illustrates the processing method of the driving simulation scene provided by the embodiment of the present application.
  • a server such as the server 300 in FIG. 1
  • FIG. 5 illustrates the processing method of the driving simulation scene provided by the embodiment of the present application.
  • Step 101 The server obtains multiple path endpoints in a road network model for driving simulation.
  • the server may obtain multiple path endpoints in the road network model for driving simulation in the following manner:
  • the server obtains the map data corresponding to the test road network of the autonomous driving vehicle, based on the map data, establishes the road network model for the simulation test of the autonomous vehicle, and determines the road network model for driving simulation based on the road network structure of the road network model Multiple path endpoints.
  • the server can obtain the stored map data from the database or receive the map data sent by the terminal.
  • the map data can include map types, which can be maps of different levels of the real world (city map, urban area map, etc.), or a customized virtual world map; area can be city level , City level and other levels. When the city/city area is not specified, the map of the default city will be used.
  • map types can be maps of different levels of the real world (city map, urban area map, etc.), or a customized virtual world map; area can be city level , City level and other levels. When the city/city area is not specified, the map of the default city will be used.
  • the map data may also include the type of lane, the width of the lane, the number of lanes, etc., where the types of lanes are closed highways, mixed roads with pedestrians and vehicles, one-way roads, and two-way roads.
  • the map data may also include traffic control facilities, such as the location and number of roadblocks, the setting of the path crossing position in the lane, and the setting of signal light status (including red, green and yellow lights) (such as Switching interval).
  • traffic control facilities such as the location and number of roadblocks, the setting of the path crossing position in the lane, and the setting of signal light status (including red, green and yellow lights) (such as Switching interval).
  • the map data may also include the number/density of background vehicles, the driving characteristics of the background vehicles, such as whether they are driving in violation of regulations, the response to traffic control facilities, etc., and the dynamic characteristics of the background vehicles, that is, the background vehicles conform to Kinetic model.
  • the map data may also include any map data required for simulation testing of autonomous vehicles.
  • the server 300 may adopt the default settings of the default items or as needed. To add.
  • the server may establish a road network model for simulation testing of autonomous vehicles in the following manner: the server performs three-dimensional modeling based on map data to obtain a graphical three-dimensional mathematical model for the driving of the test vehicle and the background vehicle.
  • Step 102 Determine at least one first route end point among the multiple route end points as a departure point, and at least one second route end point as a collection point.
  • the server can determine the departure point and the collection point in the following ways:
  • the server selects a first number of first route endpoints as departure points, and a second number of second route endpoints as pickup points.
  • the specific values of the first quantity and the second quantity can be set according to actual needs.
  • the first route end point and the second route end point can be different route end points.
  • the departure point of a vehicle can be The pick-up point of another vehicle is not limited in the embodiment of the application.
  • Step 103 Generate a background vehicle at the departure point in the road network model, and control the background vehicle to drive into the road network model from the departure point, and exit the road network model when driving to the stop point.
  • FIG. 6 is a schematic diagram of the departure point and the collection point in the road network model provided by an embodiment of the present application. See FIG. 6, in practical application.
  • the starting point can be the road on the outer edge of the map or the road where the map is interrupted.
  • the pick-up point can select the road on the outer edge of the map or the road where the map is interrupted for background vehicles and test vehicles to drive out of the road network model.
  • the aforementioned background vehicle can be used as the traffic flow of the test vehicle to simulate real road conditions.
  • the server can generate the background vehicle and the test vehicle in the following manner: the server obtains the departure point in the road network model; when the departure point is determined to meet the test vehicle generation conditions, generate Test vehicle; when it is determined that the starting point does not meet the conditions for generating the test vehicle, but meets the conditions for generating the background vehicle, a background vehicle is generated. In some embodiments, if it is determined that the starting point meets both the test vehicle generation conditions and the background vehicle generation conditions, the background vehicle is not generated, that is, the generation of the background vehicle is suspended, and the log record is performed.
  • the background vehicle and the test vehicle are not generated, that is, the generation of the background vehicle and the test vehicle is suspended, and the log record is performed.
  • the test vehicle may be generated at another starting point to determine whether to generate the test vehicle at this starting point, for example, If a test vehicle has been generated at any starting point, the test vehicle will not be generated at the starting point, but a background vehicle will be generated or the background vehicle generation will be suspended. If the test vehicle has not been generated at the starting point, the test vehicle will be generated at the starting point, It does not generate background vehicles.
  • the starting point for generating the test vehicle and the starting point for generating the background vehicle may be the same or different.
  • FIG. 7, is a schematic diagram of the starting point for generating the test vehicle and the background vehicle according to an embodiment of the present application. .
  • the number of departure points can be one or more.
  • the server first determines whether the departure point meets the test vehicle generation conditions, and determines that the departure point does not meet the test vehicle generation conditions. When the conditions are met, it is further judged whether the starting point meets the background vehicle generation conditions, and based on the judgment result, the background vehicle generation decision is made; that is, the generation priority of the test vehicle is higher than the generation priority of the background vehicle, so as to ensure The smooth generation of test vehicles during the simulation test avoids the failure of the automatic driving vehicle simulation test caused by the failure to generate the test vehicle.
  • the number of departure points is more than two.
  • the server judges whether the departure point meets the test vehicle generation conditions, it can traverse more than two departure points, and determine the current traversed departure point corresponding to two
  • two or more lanes are traversed to determine whether the departure point corresponding to each lane meets the test vehicle generation conditions.
  • the server determines that the departure point corresponding to the currently traversed lane arrives at the time to generate the test vehicle, and there are no other vehicles within a certain distance from the departure point, it determines that the test vehicle generation condition is satisfied.
  • a simulation clock is set in the server, and the server can obtain the generation schedule of the test vehicle.
  • the generation interval of the test vehicle can be a fixed time interval, or set according to actual needs;
  • the server judges whether the current time has reached the time to generate the test vehicle based on the generation schedule of the test vehicle.
  • it further determines whether there is a blocking vehicle in the current lane, that is, whether there are other vehicles within a certain distance.
  • the test vehicle is not generated, and corresponding log records are performed. In this way, further traffic congestion caused by the existence of blocked vehicles and the inability to drive normally even if the test vehicle is generated is avoided.
  • the server determines that the starting point does not meet the test vehicle generation conditions (the time to generate the test vehicle is not reached, and/or there are other vehicles within a certain distance from the starting point), the time to arrive at the background vehicle, and the vehicle is not within a certain distance.
  • the server determines that the starting point does not meet the test vehicle generation conditions (the time to generate the test vehicle is not reached, and/or there are other vehicles within a certain distance from the starting point), the time to arrive at the background vehicle, and the vehicle is not within a certain distance.
  • a background vehicle is generated, and the generated background vehicle conforms to the preset dynamic model, which corresponds to the preset vehicle model.
  • the server when the server determines that the starting point does not meet the test vehicle generation conditions, it will determine whether it meets the background vehicle generation conditions (the time to generate the background vehicle and there are no other vehicles within a certain distance from the starting point). The judgment of the time to generate the background vehicle. If the time to generate the background vehicle is not reached, the background vehicle generation is not performed and the corresponding log record is performed; if the time to generate the background vehicle is reached, it is further judged whether there is a blocking vehicle in the current lane, that is Whether there are other vehicles within a certain distance, when there are other vehicles within a certain distance, the background vehicle is not generated, and the corresponding log record is performed, so as to avoid blocking vehicles, even if the background vehicle is generated, it cannot drive normally. Caused further traffic congestion.
  • the server can obtain the generation schedule of background vehicles.
  • the generation time interval of background vehicles can be set to a fixed value or subject to a certain probability distribution, such as negative exponential distribution or even distribution. ;
  • each lane can be calculated independently, vehicles are generated at a certain time interval, and a time offset is superimposed on the initial time, that is, each lane has a
  • the corresponding background vehicle generation timetable for example, the time when the background vehicle is generated on the first lane is 1 second, 4 seconds, 7 seconds..., and the time when the background vehicle is generated on the second lane is 2 seconds, 5 seconds, 8 Seconds... (Assuming that one is generated every 3 seconds at a fixed interval, and the deviation between lanes is 1 second), in this way, traffic jams caused by multiple background vehicles entering the road network model at the same time are avoided, or the accuracy of driving simulation decline.
  • the background vehicle is given certain vehicle attributes (such as vehicle type, initial speed, target state, etc.), and at the same time, the background vehicle conforms to the dynamic model corresponding to the vehicle type.
  • vehicle attributes such as vehicle type, initial speed, target state, etc.
  • the simulation warm-up period that is, the simulation test starts for a period of time (which can be set according to the actual situation, such as empirical values). Only background vehicles are generated to ensure that the number of background vehicles in the road network model and the corresponding distribution meet the requirements of the simulation test. Or, before generating the test vehicle, it is determined that a certain number of background vehicles (which can be set according to actual needs) already exist in the road network model.
  • the server can control the driving state of the background vehicle in the following ways:
  • the server obtains the driving position and driving direction of the background vehicle, and based on the driving position and driving direction, when determining that the background vehicle travels to at least one of the path crossing position and the signal light position, it plans at least one of the driving speed and driving path of the background vehicle .
  • FIG. 8 is a schematic diagram of the vehicle traveling to the path intersection position and the signal light position provided by the embodiment of the present application. See FIG. 8.
  • the background vehicle travels to the path intersection, it means that there is a path intersection ahead of the background vehicle's driving direction, and the distance between the background vehicle and the path intersection is within the set first distance range; the background vehicle travels to the signal light position, which refers to the background There is a signal light in front of the vehicle traveling direction, and the distance between the background vehicle and the signal light is within the set second distance range.
  • the server determines whether the background vehicle travels to the path intersection position based on the current driving position of the background vehicle, and when it is determined that the background vehicle travels to the path intersection position, it plans the driving path of the background vehicle, such as going straight, turning left , Turn right; here, in actual implementation, the steering ratio of the background vehicle driving to the path intersection position in each lane of the road network model can be set.
  • Figure 9 is the background vehicle at the path intersection position provided by the embodiment of the application
  • Figure 9 For a schematic diagram of the steering ratio, see Figure 9.
  • 25% of the background vehicles need to turn left, 15% of the background vehicles need to turn right, and 60% of the background vehicles The vehicle needs to go straight.
  • the server determines that the background vehicle has traveled to the path intersection position but has not traveled to the path intersection position, it judges whether it has traveled to the signal light position (that is, whether the current driving position corresponds to the signal light position), and if it is determined to drive to the signal light position, obtain the corresponding signal light color , That is, get the color of the signal light in the direction of travel, and control the speed of the background vehicle based on the color of the signal light.
  • the server can control the driving speed of the background vehicle based on the color of the signal light in the following ways: determine whether the color of the signal light is green, if the color of the signal light is green, keep the current speed unchanged and drive at a constant speed; if the color of the signal light is not green, and If the signal light is yellow, decelerate evenly and stop, or grab the yellow light at a constant speed; if the color of the signal light is not green, but red, decelerate and stop evenly.
  • a certain number of background vehicles can be controlled to run red lights, such as accelerating or Pass through with constant speed.
  • the server when the server determines that the background vehicle has traveled to the position of the route intersection, it further determines whether it has traveled to the signal light position (that is, whether there is a signal light at the route intersection), and if it is determined to drive to the signal light position, obtain the corresponding signal light color , Based on the color of the signal light, control the driving speed of the background vehicle; specifically, determine whether the color of the signal light is green or yellow, and if the color of the signal light is green or yellow, further determine whether there is a corresponding yield rule for the determined driving path, the yield Rules, indicating that the driving priority of the determined driving route is lower than that of vehicles that are not on the same lane as the test vehicle, such as transfer left to go straight, right transfer to turn left; if the determined driving path has corresponding yield
  • the rule based on the yield rule, controls the speed of the background vehicle, such as controlling the background vehicle to decelerate to a stop evenly.
  • the server when the server determines that the background vehicle travels to the path intersection position and does not travel to the signal light position, that is, when there is no signal light at the path intersection position, it further determines whether there is a corresponding yield rule for the determined driving path.
  • the passing rule keeps the current speed unchanged; if there is a corresponding yielding rule, based on the yielding rule, the driving speed of the background vehicle is controlled.
  • the road network model is also provided with speed bumps and yield signs.
  • the server determines whether to reach the speed bump and/or yield signs based on the driving position of the background vehicle, and based on the judgment result Control the speed of the background vehicle, such as determining that there is a deceleration zone in a certain distance in front of the driving position, control the speed of the background vehicle to uniformly decelerate to a certain speed, and determine the speed of the background vehicle when there is a yield sign in a certain distance in front of the driving position Decelerate evenly to a stop.
  • the server also monitors the driving state of the test vehicle in response to the background vehicle, and the driving plan based on the driving strategy.
  • the driving plan includes at least one of path planning and speed planning.
  • the server may monitor the driving plan of the test vehicle based on the driving strategy in response to the driving state of the background vehicle in the following manner:
  • the server obtains the driving parameters corresponding to the driving plan made by the test vehicle based on the driving strategy.
  • the driving parameters include at least one of speed parameters, position parameters, and direction parameters.
  • the driving strategy is used to obtain the driving state of the background vehicle, and the driving state includes At least one of the driving position, the driving direction and the driving speed; based on the driving state, the driving plan of the test vehicle is carried out.
  • the test vehicle determines that a traffic jam occurs at a certain distance in the driving direction based on the driving position, driving direction, and driving speed of the background vehicle in the road network model, and re-plans the path based on the target position (that is, the driving end position), as in Turn left or right when driving to the intersection of paths, and change the path to the target position to avoid congestion.
  • the target position that is, the driving end position
  • the road network model Before the driving simulation, the road network model needs to be constructed.
  • the road network model can be a two-dimensional or three-dimensional model.
  • the road network model is obtained based on a background map covering the test road network.
  • the background map can be A high-definition map made based on data collected in the real world can also be a custom map created by user editing.
  • the road network model is set with the departure point, that is, the exit point.
  • the exit point location is selected on the road at the outer edge of the map or at the head road of the map interruption for background vehicles and test vehicles to generate and drive into the road network model. , Can avoid the direct production of vehicles in the middle of the road, and then cause vehicle collisions, causing sudden changes in traffic conditions and visual abruptness.
  • the road network model also has a pick-up point for background vehicles and test vehicles to drive out of the road network model, that is, when the vehicle reaches the pick-up point, the vehicle will be removed from the road network model no matter which lane it is in;
  • the location of the vehicle point is selected on the road at the outer edge of the map or at the head of the map to avoid the sudden disappearance of the vehicle in the middle of the road, causing sudden changes in the traffic state and visual abruptness.
  • the processing method of the driving simulation scene may include four parts, namely: simulation test warm-up, test vehicle and background vehicle generation, background vehicle steering decision, test vehicle driving planning and monitoring, it should be noted that the test vehicle
  • the execution sequence of background vehicle generation, background vehicle steering decision, and test vehicle driving planning and monitoring is in no particular order, and can be implemented at the same time, as described below.
  • the simulation test is warmed up. At this stage, only background vehicles are generated, so that each lane in the road network model has sufficient background vehicle distribution to ensure that there are enough background vehicles in the road network model.
  • the test vehicle is subjected to simulation test. In actual implementation, a period of time (which can be set according to the actual situation) can be set as the preheating stage of the simulation test, or the number of background vehicles in the road network model can be determined to increase from zero to a certain number of stages. Warm-up phase for simulation test.
  • a background vehicle generation timetable is set, and the number of generation timetables is one or more. If there are multiple roads for a departure point, a background vehicle generation time can be set for each road Table, based on the generation schedule to generate background vehicles, while generating background vehicles, given certain vehicle attributes (such as vehicle type, initial speed, etc.), as the simulation clock advances into the road network model.
  • the generation interval of the background vehicle can be set to a fixed value (such as 3 seconds), or subject to a certain probability distribution, such as a negative exponential distribution or an average distribution.
  • each lane can be calculated independently, vehicles are generated at a certain interval, and a time offset is superimposed on the initial time to prevent multiple vehicles from entering the system at the same time, such as the background vehicle in the first
  • the time generated in one lane is the first second, 4 seconds, 7 seconds...
  • the time generated in the second lane is the second second, 5 seconds, 8 seconds... (assuming it is generated every 3 seconds at a fixed interval
  • the deviation between lanes is 1 second).
  • test vehicles After the simulation test is warmed up, not only background vehicles can be generated in the road network model, but test vehicles can be generated. Similarly, test vehicles also have corresponding generation schedules.
  • the generation interval of test vehicles can be set to a fixed value, or based on Actually need to be set. If the generation time of a certain test vehicle coincides with the generation time of the background vehicle, the generation of this background vehicle will be suspended until the next time the background vehicle is to be generated in the lane and then resume the vehicle generation.
  • the exit time is extended by a simulation step ⁇ t until the location meets the generation conditions and then the test vehicle is generated.
  • the generation priority of the test vehicle to be higher than the generation priority of the background vehicle, that is, for a certain starting point, if the starting point has the conditions for generating the test vehicle at the same time (the generation time arrives and there is no blocking vehicle in the corresponding lane ) And the conditions for generating the background vehicle (the generation time is reached and there is no blocking vehicle in the corresponding lane), the test vehicle is generated but the background vehicle is not generated, and the log record is performed at the same time.
  • there are multiple departure points in the road network model and there are Take the departure points corresponding to multiple roads as an example to illustrate the generation of test vehicles and background vehicles.
  • FIG. 10 is a schematic diagram of the process of generating a test vehicle and a background vehicle provided by an embodiment of the application.
  • the generation of a test vehicle and a background vehicle includes:
  • Step 201 The server traverses the departure points in the road network model.
  • Step 202 The server judges whether all the departure points have been traversed, if all the departure points have not been traversed, step 203 is executed, and if all the departure points have been traversed, step 217 is executed.
  • Step 203 The server sets the next exit point as the current exit point, and traverses the lane corresponding to the current exit point.
  • Step 204 The server determines whether the lanes corresponding to the current exit point have been traversed, and if they have all been traversed, step 202 is executed; if there are untraversed lanes, step 205 is executed.
  • Step 205 The server selects the next lane as the current lane.
  • Step 206 The server judges whether the time for generating the test vehicle is reached, if it has arrived, execute step 207; if it has not arrived, execute step 210.
  • Step 207 The server judges whether the generation time of the background vehicle is reached, if it has not arrived, execute step 208; if it has not arrived, execute step 214.
  • Step 208 The server judges whether a test vehicle can be generated at this location, if it can, execute step 209; if not, execute step 215.
  • test vehicle it is determined whether a test vehicle can be generated at this location, that is, whether there is a blocked vehicle in the current lane.
  • Step 209 The server generates a test vehicle at the exit point corresponding to the current road, and step 204 is executed.
  • Step 210 The server judges whether it has reached the generation time of the background vehicle, if it has arrived, execute step 211; if it has not arrived, execute step 204.
  • Step 211 The server judges whether a background vehicle can be generated at this location, if it is possible, execute step 212; if not, execute step 213.
  • Step 212 The server generates a background vehicle at the exit point corresponding to the current road, and step 204 is executed.
  • the generated background vehicle conforms to the dynamic model and is given certain vehicle attributes (such as vehicle type, initial speed, etc.).
  • Step 213 The server performs error log recording, and step 204 is executed.
  • Step 214 The server suspends the generation of the background vehicle and performs log recording.
  • Step 215 The server suspends the generation of the test vehicle, moves its generation time backward by one time step, and executes step 204.
  • a time step is ⁇ t, which can be specifically set according to actual needs.
  • Step 216 The server advances the simulation clock equidistantly by one time step.
  • Step 217 The server judges whether the total simulation test time has arrived, if it has arrived, execute step 218; if it has not arrived, execute step 216.
  • Step 218 The server ends the simulation operation.
  • the road network model is equipped with route intersections, such as crossroads, T-junctions, and signal lights.
  • route intersections such as crossroads, T-junctions, and signal lights.
  • the background vehicles in the driving are organized and regulated. For example, when the background vehicle travels to a certain distance from the route intersection and/or the position of the signal light, the travel path (straight, left turn, right turn) and travel speed of the background vehicle are controlled.
  • the color of the signal light includes red, yellow and green.
  • the reaction of the background vehicle to the color of the signal light can be as follows: green: keep the speed unchanged and advance at a constant speed; red: decelerate to stop; yellow: decelerate and stop with a certain probability, or grab a uniform speed The yellow light passed the intersection.
  • concession rules For driving to a route intersection, when a left or right turn involving a background vehicle is involved, corresponding concession rules can be set, such as transfer left to go straight, and right transfer to turn left.
  • the steering decision point For multiple background vehicles traveling to a route intersection, set the steering decision point at a certain distance (such as 30 meters) before the route intersection. When the vehicle reaches the decision point (ie, the aforementioned path intersection position), set it in advance The ratio of will be assigned a driving direction (such as turn left, go straight or turn right), and then the background vehicle will change to the corresponding downstream lane according to the driving direction and drive according to the corresponding signal lights.
  • a driving direction such as turn left, go straight or turn right
  • FIG. 11 is a schematic flowchart of a steering decision control of a background vehicle provided by an embodiment of the application.
  • the steering decision control of a background vehicle includes:
  • Step 301 The server traverses the background vehicles and selects the background vehicles.
  • the background vehicle in the road network model can carry a corresponding identifier to uniquely identify the background vehicle.
  • Step 302 The server judges whether the background vehicle has reached the steering decision point, if it does, execute step 303; if it does not, execute step 304.
  • Step 303 The server determines whether the background vehicle is driving in the corresponding lane, if it is in the corresponding lane, execute step 304; if it is not in the corresponding lane, execute step 312.
  • judging whether the background vehicle is driving in the corresponding lane refers to judging whether the background vehicle is driving. Lane has been re-planned.
  • Step 304 The server controls the background vehicle to drive normally.
  • the background vehicle is controlled to drive normally, that is, the background vehicle is controlled to drive in the corresponding lane at the current speed.
  • Step 305 The server judges whether there is a signal light within the line of sight, if it exists, execute step 306; if it does not exist, execute step 316.
  • the size of the viewing distance can be set according to actual conditions or empirical values.
  • Step 306 The server judges whether the signal light is green, if it is not green, go to step 307; if it is green, go to step 316.
  • Step 307 The server determines whether the signal light is yellow, if it is not yellow, go to step 308; if it is yellow, go to step 315.
  • Step 308 The server determines that the signal light is red.
  • Step 309 The server controls the background vehicle to decelerate to a stop.
  • Step 310 The server determines whether all background vehicles have been traversed, if all background vehicles have been traversed, step 311 is executed; if all background vehicles have not been traversed, step 317 is executed.
  • Step 311 The server judges whether the total simulation time has arrived, if it has arrived, execute step 318; if it has not arrived, execute step 314.
  • Step 312 The server controls the background vehicle to change lanes to the corresponding lanes.
  • Step 313 The server selects the next background vehicle.
  • Step 314 The server advances the simulation clock equidistantly by a time step, and executes step 301.
  • Step 315 The server judges whether it needs to decelerate to a stop, if necessary, execute step 309; if not, execute step 316.
  • Step 316 The server determines whether there is a yield rule, if it exists, execute step 309; if it does not exist, execute step 317.
  • Step 317 The server controls the background vehicle to drive normally.
  • Step 318 The server ends the simulation operation.
  • the driving simulation process it is necessary to monitor the driving parameters of the test vehicle, including the acquisition of the driving speed, driving position and driving direction of the test vehicle, to determine the response of the test vehicle based on the driving state of the background vehicle, such as avoidance, Change lanes, overtake, follow, stop, etc.
  • the background vehicle and the test vehicle corresponding to the autonomous driving vehicle are generated. In this way, the automatic generation of the background vehicle and the test vehicle during the driving simulation process is realized, and the processing efficiency of the driving simulation scene is improved .
  • Control the driving state of the background vehicle make the background vehicle drive into the road network model from the starting point, and drive out of the road network model when it reaches the stopping point. In this way, by controlling the driving state of the background vehicle, the test is achieved The purpose of verification of the vehicle's driving strategy.
  • the generation of the test vehicle does not generate the background vehicle, that is, the generation priority of the test vehicle is higher than the generation priority of the background vehicle, so that it is guaranteed to be in the simulation
  • the smooth generation of the test vehicle during the test avoids the failure of the simulation test of the autonomous vehicle caused by the failure to generate the test vehicle.
  • the embodiment of the present application also provides a device for processing a driving simulation scene, including:
  • the acquiring unit is used to acquire multiple path endpoints in the road network model used for driving simulation
  • a determining unit configured to determine at least one first route end point among the plurality of route end points as a departure point, and at least one second route end point as a collection point;
  • the generating unit is used to generate a background vehicle; for example, it is used to generate a background vehicle at the departure point in the road network model.
  • the control unit is configured to control the background vehicle to drive into the road network model from the starting point, and drive out of the road network model when it reaches the stopping point.
  • the acquisition unit is also used to acquire map data corresponding to the test road network of the autonomous vehicle, and based on the map data, establish a road network model for simulation testing of the autonomous vehicle, and the road network model based on the road network model Network structure to determine multiple path endpoints in the road network model used for driving simulation.
  • the determining unit is further configured to select a first number of first path end points as departure points and a second number of second path end points as pick-up points based on the distribution of the multiple path end points in the road network model point.
  • the generating unit is also used to obtain the departure point in the road network model
  • test vehicle is generated
  • the background vehicle is generated.
  • the generating unit is further configured to traverse the at least two departure points in response to the number of the departure points being at least two;
  • the departure point corresponding to the currently traversed lane arrives at the time when the test vehicle is generated, and there is no other vehicle within a certain distance, and the test vehicle is generated.
  • the generating unit is further configured to generate the background vehicle when it is determined that the starting point does not meet the test vehicle generating conditions, the time to generate the background vehicle, and there are no other vehicles within a certain distance;
  • the background vehicle conforms to a preset dynamic model, and the dynamic model corresponds to a preset vehicle model.
  • control unit is also used to obtain the driving position and driving direction of the background vehicle
  • control unit is further configured to determine the travel path of the background vehicle when the background vehicle travels to a path intersection position
  • the driving speed of the background vehicle is controlled.
  • control unit is further configured to control the traffic of the background vehicle based on the yield rule when there is no signal light at the path intersection and the travel path has a corresponding yield rule. Driving speed;
  • the yield rule indicates that the driving priority of the driving path is lower than the driving priority of a vehicle that is not on the same lane as the test vehicle.
  • control unit is further configured to control the traffic of the background vehicle based on the yield rule when the color of the signal light is green or yellow and the travel path has a corresponding yield rule. Driving speed.
  • control unit is further configured to determine the corresponding signal light color when the driving position does not correspond to the path crossing position but corresponds to the signal light position;
  • the driving speed of the background vehicle is controlled.
  • it further includes:
  • the monitoring unit is used to monitor the driving plan of the test vehicle based on the driving strategy in response to the driving state of the background vehicle, and the driving plan includes at least one of path planning and speed planning.
  • the monitoring unit is further configured to obtain driving parameters corresponding to a driving plan made by the test vehicle based on a driving strategy, and the driving parameters include at least one of a speed parameter, a position parameter, and a direction parameter;
  • the driving strategy is used to obtain the driving state of the background vehicle, where the driving state includes at least one of a driving position, a driving direction, and a driving speed; based on the driving state, the driving plan is performed on the test vehicle .
  • the embodiment of the present application provides a storage medium storing executable instructions, and the executable instructions are stored therein.
  • the processor will cause the processor to execute the driving simulation scenario processing method provided by the embodiments of the present application For example, the following steps of the method for processing a driving simulation scene as shown in FIG. 5:
  • Generate a background vehicle control the background vehicle to drive into the road network model from the starting point, and drive out of the road network model when it reaches the stopping point.
  • the processor is further configured to implement the following steps:
  • test vehicle is generated
  • the processor is also used to implement the following steps:
  • the background vehicle is generated.
  • the processor is further configured to implement the following steps:
  • the departure point corresponding to the currently traversed lane arrives at the time when the test vehicle is generated, and there is no other vehicle within a certain distance, and the test vehicle is generated.
  • the processor is further configured to implement the following steps:
  • the background vehicle conforms to a preset dynamic model, and the dynamic model corresponds to a preset vehicle model.
  • the processor is further configured to implement the following steps:
  • the processor is further configured to implement the following steps:
  • the driving speed of the background vehicle is controlled.
  • the processor is further configured to implement the following steps:
  • the yield rule indicates that the driving priority of the driving path is lower than the driving priority of a vehicle that is not on the same lane as the test vehicle.
  • the processor is further configured to implement the following steps:
  • the driving speed of the background vehicle is controlled based on the yield rule.
  • Project planning including:
  • the driving speed of the background vehicle is controlled.
  • the processor is further configured to implement the following steps:
  • the driving plan including at least one of path planning and speed planning.
  • the processor is further configured to implement the following steps:
  • the driving parameters include at least one of a speed parameter, a position parameter, and a direction parameter;
  • the driving strategy is used to obtain the driving state of the background vehicle, where the driving state includes at least one of a driving position, a driving direction, and a driving speed; based on the driving state, the driving plan is performed on the test vehicle .
  • the processor is further configured to implement the following steps:
  • a first number of first route endpoints are selected as departure points, and a second number of second route endpoints are selected as receiving points.
  • All or part of the steps of the embodiments can be completed by a program instructing relevant hardware.
  • the aforementioned program can be stored in a computer readable storage medium. When the program is executed, it executes the steps including the aforementioned method embodiments; and the aforementioned Storage media include: removable storage devices, random access memory (RAM, Read-Only Memory), read-only memory (ROM, Read-Only Memory), magnetic disks or optical disks and other media that can store program codes.
  • the above-mentioned integrated unit of this application is implemented in the form of a software function module and sold or used as an independent product, it may also be stored in a computer readable storage medium.
  • the computer software products are stored in a storage medium and include several instructions to enable A computer device (which may be a personal computer, a server, or a network device, etc.) executes all or part of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: removable storage devices, RAM, ROM, magnetic disks, or optical disks and other media that can store program codes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • General Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Computer Hardware Design (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Mechanical Engineering (AREA)
  • Transportation (AREA)
  • Human Computer Interaction (AREA)
  • Traffic Control Systems (AREA)
  • Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Medical Informatics (AREA)

Abstract

一种驾驶仿真场景的处理方法，包括：确定用于驾驶仿真的路网模型中的多个路径端点（101）；从所述多个路径端点中，选取至少一个路径端点作为发车点，以及选取至少一个路径端点作为收车点（102）；在所述路网模型中的发车点生成背景车辆，并控制所述背景车辆从所述发车点驶入所述路网模型，在行驶至所述收车点时驶出所述路网模型（103）。还公开了一种驾驶仿真装置，包括：获取单元，用于获取用于驾驶仿真的路网模型中的多个路径端点；确定单元，用于确定所述多个路径端点中的至少一个路径端点作为发车点，以及至少一个路径端点作为收车点；生成单元，用于在所述路网模型中的发车点生成背景车辆；控制单元，用于控制所述背景车辆从所述发车点驶入所述路网模型，并在行驶至所述收车点时驶出所述路网模型。还公开了一种存储介质实现驾驶仿真场景的处理方法，能够自动构建用于车辆仿真的驾驶仿真场景，处理效率高。

Description

驾驶仿真场景的处理方法、装置及存储介质
本申请要求于2019年5月9日提交的申请号为2019103864944、发明名称为“驾驶仿真场景的处理方法、装置及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及自动驾驶技术，尤其涉及一种驾驶仿真场景的处理方法、装置及存储介质。
背景技术
自动驾驶车辆又称无人驾驶车辆、电脑驾驶车辆，这类车辆能够在无人状态下自主沿道路行进。通常，在自动驾驶车辆投入使用之前，需要进行大量测试，以检测其安全性及稳定性。
出于道路安全的考虑，相关技术中提供驾驶仿真平台，来构建仿真测试场景，以对自动驾驶车辆进行仿真测试，然而，相关技术中在搭建仿真测试场景时，需要用户手动添加背景车辆及测试车辆，因此，对于需求较多背景车辆的大规模仿真测试场景来说，这种搭建方法的处理效率低。
发明内容
本申请实施例提供一种驾驶仿真场景的处理方法、装置及存储介质，能够自动构建用于车辆仿真的驾驶仿真场景，处理效率高。
本申请实施例的技术方案是这样实现的：
本申请实施例提供一种驾驶仿真场景的处理方法，包括：
获取用于驾驶仿真的路网模型中的多个路径端点；
确定所述多个路径端点中的至少一个第一路径端点作为发车点，以及至少一个第二路径端点作为收车点；
生成背景车辆，并控制所述背景车辆从所述发车点驶入所述路网模型，并在行驶至收车点时驶出所述路网模型。
本申请实施例还提供一种驾驶仿真场景的处理装置，包括：
获取单元，用于获取用于驾驶仿真的路网模型中的多个路径端点；
确定单元，用于确定所述多个路径端点中的至少一个第一路径端点作为发车点，以及至少一个第一路径端点作为收车点；
生成单元，用于生成背景车辆；
控制单元，用于控制所述背景车辆从所述发车点驶入所述路网模型，并在行驶至所述收车点时驶出所述路网模型。
本申请实施例还提供一种驾驶仿真场景的处理装置，包括：
存储器，用于存储可执行指令；
处理器，用于执行所述存储器中存储的可执行指令时，实现本申请实施例提供的上述驾驶仿真场景的处理方法。
本申请实施例提供一种存储介质，存储有可执行指令，用于引起处理器执行时，实现本申请实施例提供的上述驾驶仿真场景的处理方法。
本申请实施例具有以下有益效果：
1)、确定多个路径端点中的至少一个路径端点作为发车点，以及至少一个路径端点作为收车点，如此，路网模型中发车点及收车点的位置均对应路径端点，避免了背景车辆在路径中间产生所造成的交通状态的突然变化，以及视觉上的突兀感；
2)、在路网模型中的发车点生成背景车辆，如此，实现了驾驶仿真过程中，背景车辆的自动生成，提高了驾驶仿真场景的处理效率；
3)、控制背景车辆从发车点驶入路网模型，并在行驶至收车点时驶出路网模型，如此，由于路网模型中背景车辆的驶入及驶出分别对应特定的发车点及收车点，使得背景车辆的生成及消失更具备合理性，避免了仿真过程中显示效果的突兀。
附图说明
图1是本申请实施例提供的驾驶仿真系统的架构示意图；
图2是本申请实施例提供的驾驶仿真平台的仿真测试原理示意图；
图3是本申请实施例提供的自动驾驶系统的架构示意图；
图4是本申请实施例提供的驾驶仿真场景的处理装置的结构示意图；
图5是本申请实施例提供的驾驶仿真场景的处理方法的流程示意图；
图6是本申请实施例提供的路网模型中发车点及收车点的示意图；
图7是本申请实施例提供的发车点生成测试车辆与背景车辆的示意图；
图8是本申请实施例提供的车辆行驶至路径交叉位置及信号灯位置的示意图；
图9为本申请实施例提供的路径交叉位置的背景车辆的转向比例的示意图；
图10为本申请实施例提供的生成测试车辆及背景车辆的流程示意图；
图11为本申请实施例提供的背景车辆的转向决策控制的流程示意图。
具体实施方式
为了使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请作进一步地详细描述，所描述的实施例不应视为对本申请的限制，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本申请保护的范围。
在以下的描述中，涉及到“一些实施例”，其描述了所有可能实施例的子集，但是可以理解,“一些实施例”可以是所有可能实施例的相同子集或不同子集，并且可以在不冲突的情况下相互结合。
在以下的描述中，所涉及的术语“第一\第二”仅仅是是区别类似的对象，不代表针对对象的特定排序，可以理解地，“第一\第二”在允许的情况下可以互换特定的顺序或先后次序，以使这里描述的本申请实施例能够以除了在这里图示或描述的以外的顺序实施。
除非另有定义，本文所使用的所有的技术和科学术语与属于本申请的技术领域的技术人员通常理解的含义相同。本文中所使用的术语只是为了描述本申请实施例的目的，不是旨在 限制本申请。
对本申请实施例进行进一步详细说明之前，对本申请实施例中涉及的名词和术语进行说明，本申请实施例中涉及的名词和术语适用于如下的解释。
1)、自动驾驶，是指不需要测试驾驶员执行物理性驾驶操作的情况下，能够对车辆行驶任务进行指导与决策，并代替测试驾驶员的操控行为，使车辆完成安全行驶的功能。
2)、测试车辆，用于对自动驾驶车辆及其动力学特性(如功率、扭矩、百公里加速)进行模拟，以在驾驶仿真中代替自动驾驶车辆，对自动驾驶车辆应用的行驶策略(即自动驾驶算法)进行安全性及稳定性的测试。
3)、背景车辆，在自动驾驶车辆的驾驶仿真中，构成测试车辆的行驶背景的符合动力学模型的车辆，用于触发测试车辆的反应，例如跟车、超车和停车等。
4)、路网模型，基于地图数据，既可以是现实世界的不同级别的地图(城市地图、市区地图等)数据，也可以是自定义的虚拟世界的地图数据，进行三维或二维建模所得到的、供测试车辆及背景车辆行驶的图形化的数学模型。
5)、路径规划，基于车辆的当前的状态(包括位置、速度和加速度)、当前的驾驶场景(车辆所处环境从不同维度表现出来的特性，如行驶道路的拥堵程度、行驶位置是否对应信号灯位置/路径交叉位置等)，以及车辆的目标状态(包括目标位置、速度和加速度)，计算出的从当前位置到目标位置的平滑的路径。
6)、速度规划，在路径规划所得路径的基础上计算出的每个路径点的速度，从而形成一条速度曲线。
7)、发车点，路网模型中生成测试车辆和/或背景车辆的位置(即出现测试车辆和/或背景车辆的位置)，所生成的车辆从该位置出发驶入路网模型。
8)、收车点，路网模型中测试车辆和/或背景车辆消失的位置，即车辆从该位置驶出路网模型，收车点可以和发车点为同一位置(即收车点亦是发车点)，也可以和发车点为不同位置。
9)、响应于，用于表示所执行的操作所依赖的条件或者状态，当满足所依赖的条件或状态时，所执行的一个或多个操作可以是实时的，也可以具有设定的延迟；在没有特别说明的情况下，所执行的多个操作不存在执行先后顺序的限制。
下面说明本申请实施例提供的驾驶仿真场景的处理方法和装置的示例性应用，本申请实施例提供的驾驶仿真场景的处理装置可以采用软件形式、或软硬件结合的形式，例如本申请实施例提供的驾驶仿真场景的处理装置可以是驾驶仿真平台的子功能，从而能够设置到任意类型的驾驶仿真场景的处理装置中，例如电脑终端、服务器和服务器集群等。
接下来以服务器实施驾驶仿真场景的处理方法为例，说明涵盖该服务器的驾驶仿真系统。
图1是本申请实施例提供的驾驶仿真系统100的一个可选的架构示意图，参见图1，终端(示例性示出了终端200-1和终端200-2)的各种用户(例如自动驾驶算法开发者、车辆生产商、车辆检测机构等)，通过网络400将终端连接到集成有驾驶仿真平台(包括本申请实施例提供的驾驶仿真场景的处理装置)的服务器300；网络400可以是广域网或者局域网，又或者是二者的组合，使用无线链路实现数据传输。
终端(如终端200-1)，用于发送对应自动驾驶车辆的仿真测试请求，所述仿真测试请求携带自动驾驶车辆的行使策略；
服务器300，用于响应所述仿真测试请求，获取自动驾驶车辆的测试路网对应的地图数据，基于地图数据，建立对自动驾驶车辆进行仿真测试的路网模型，在路网模型中的发车点，生成背景车辆及对应自动驾驶车辆的测试车辆，控制背景车辆的行驶状态，使背景车辆从发车点驶入路网模型，并在行驶至收车点时驶出路网模型，监测测试车辆响应于背景车辆的行驶状态，基于行驶策略作出的路径规划和/或速度规划，返回测试车辆在不同时间点的仿真测试结果；
终端(如终端200-1)，还用于通过图形界面(如图形界面210-1)显示测试车辆在不同时间点的仿真测试结果。
在一些实施例中，终端(如终端200-1)上设置有驾驶仿真客户端，终端(如终端200-1)基于驾驶仿真客户端实现自动驾驶车辆的仿真测试，当用户触发仿真测试指令时，驾驶仿真客户端发送对应自动驾驶车辆的仿真测试请求给服务器300，接收服务器300返回的仿真测试结果，并通过驾驶仿真客户端的仿真测试界面显示接收的仿真测试结果。
接下来对驾驶仿真系统100中服务器300所运行的驾驶仿真平台进行说明。
图2是本申请实施例提供的驾驶仿真平台的仿真测试原理示意图，参见图2，示例性地，服务器300通过驾驶仿真平台，对自动驾驶车辆进行仿真测试时，从数据库500获取自动驾驶车辆的测试路网对应的地图数据，然后基于地图数据进行三维建模，得到用于仿真测试的路网模型；在该路网模型中，生成符合自动驾驶车辆的动力学模型的测试车辆，以及符合预设动力学模型(可以和自动驾驶车辆的动力学模型相同或不同)的至少一台背景车辆，控制背景车辆在路网模型中的行驶，并监测测试车辆响应于背景车辆的行驶状态，基于行驶策略(自动驾驶算法)作出的路径规划和/或速度规划，以验证自动驾驶算法控制的测试车辆在应对不同路况时，所作出的变换车道、超车、跟车、停车等决策是否符合预期，例如供车辆检测机构判断自动驾驶算法是否符合安全标准，供车辆生产商决定是否需要就自动驾驶算法进行实际的路测等。
接下来对控制测试车辆的自动驾驶算法进行说明，在自动驾驶车辆中，在自动驾驶系统中应用自动驾驶算法，用于实现车辆的不同级别的自动驾驶功能，参见图3，图3是本申请实施例提供的自动驾驶系统的架构示意图，自动驾驶系统30包括：环境感知系统31、决策规划系统32和车辆控制系统33。可以理解地，自动驾驶系统30包括的上述系统在一些实施例中也可以被称为子系统或模块，将在下面分别进行说明。
环境感知系统31用于感知环境信息，包括环境中障碍物的位置、速度，朝向以及物体分类(如车辆，行人，自行车)。在一些实施例中，还可以感知车辆自身的状态(包括速度、加速度和方向)以及车辆的实时位置的高精度地图。
决策规划系统32根据环境信息和目标位置，结合客观的物理规律，结合障碍物和周边环境以及积累的历史数据知识，对感知到的障碍物做出预测以便做出宏观地决策，保证车辆能够顺利到达目标状态。
在一些实施例中，决策规划系统32的决策包括车道选择、参考车速、道路上是否正常跟随障碍物(例如人、车等)、是否绕过障碍物(例如人、车等)、是否停车、遇到交通灯和行人时是否等待避让、以及在路口和其他车辆的交互通过等。
决策规划系统32还用于根据环境感知信息及所作出的决策，进行行驶规划(包括路径规划及速度规划)，包括选择轨迹途经的路径点，以及到达每个路径点时车辆的速度、朝向和加速度等。路径点不仅在时空上保持连续性，而且每个路径点的速度、朝向和加速度等参数，都在车辆的实际可操作的物理范围之内。
车辆控制系统33接收决策规划系统32做作出的行驶规划，结合车身属性和外界物理因素进行动力学计算，转换成对车辆电子化控制的油门量、刹车量、以及方向盘信号等车辆控制参数并执行。
继续说明本申请实施例提供的驾驶仿真场景的处理装置的示例性结构，驾驶仿真场景的处理装置可以实施于如图1示出的服务器300，也可以通过各种终端实施，例如笔记本电脑、台式电脑等。参见图4，图4是本申请实施例提供的驾驶仿真场景的处理装置的结构示意图，图4所示的驾驶仿真场景的处理装置40包括：至少一个处理器410、存储器450、至少一个网络接口420和用户接口430。驾驶仿真场景的处理装置40中的各个组件通过总线系统440耦合在一起。可理解，总线系统440用于实现这些组件之间的连接通信。总线系统440除包括数据总线之外，还包括电源总线、控制总线和状态信号总线。但是为了清楚说明起见，在图4中将各种总线都标为总线系统440。
处理器410可以是一种集成电路芯片，具有信号的处理能力，例如通用处理器、数字信号处理器(DSP，Digital Signal Processor)，或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等，其中，通用处理器可以是微处理器或者任何常规的处理器等。
用户接口430包括使得能够呈现媒体内容的一个或多个输出装置431，包括一个或多个扬声器和/或一个或多个视觉显示屏。用户接口430还包括一个或多个输入装置432，包括有助于用户输入的用户接口部件，比如键盘、鼠标、麦克风、触屏显示屏、摄像头、其他输入按钮和控件。
存储器450包括易失性存储器或非易失性存储器，也可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(ROM，Read Only Memory)，易失性存储器可以是随机存取存储器(RAM，Random Access Memory)。本申请实施例描述的存储器450旨在包括任意适合类型的存储器。存储器450可选地包括在物理位置上远离处理器410的一个或多个存储设备。
在一些实施例中，存储器450能够存储数据以支持驾驶仿真场景的处理装置40的操作，这些数据的示例包括程序、模块和数据结构或者其子集或超集，下面示例性说明。
操作系统451，包括用于处理各种基本系统服务和执行硬件相关任务的系统程序，例如框架层、核心库层、驱动层等，用于实现各种基础业务以及处理基于硬件的任务；
网络通信模块452，用于经由一个或多个(有线或无线)网络接口420到达其他计算设备，示例性的网络接口420包括：蓝牙、无线相容性认证(WiFi)、和通用串行总线(USB，Universal Serial Bus)等；
显示模块453，用于经由一个或多个与用户接口430相关联的输出装置431(例如，显示屏、扬声器等)使得能够呈现信息(例如，用于操作外围设备和显示内容和信息的用户接口)；
输入处理模块454，用于对一个或多个来自一个或多个输入装置432之一的一个或多个用户输入或互动进行检测以及翻译所检测的输入或互动。
在一些实施例中，作为本申请实施例提供的驾驶仿真场景的处理方法采用软件实施的示 例，存储器450还可以包括本申请实施例提供的驾驶仿真场景的处理装置455；驾驶仿真场景的处理装置455在图4中采用了软件单元的方式，包括获取单元4551、确定单元4552、生成单元4553、控制单元4554；其中，获取单元，用于获取用于驾驶仿真的路网模型中的多个路径端点；确定单元，用于确定所述多个路径端点中的至少一个路径端点作为发车点，以及至少一个路径端点作为收车点；生成单元，用于在路网模型中的发车点，生成背景车辆；控制单元，用于控制背景车辆从发车点驶入路网模型，并在行驶至收车点时驶出路网模型。
当然，本申请实施例提供的驾驶仿真场景的处理装置455可以实施为纯硬件的形式或软硬件结合的形式，作为本申请实施例提供的驾驶仿真场景的处理装置455采用硬件实施的示例，可以直接采用硬件译码处理器形式的处理器410来执行完成本申请实施例提供的驾驶仿真场景的处理方法，例如，被一个或多个应用专用集成电路(ASIC，Application Specific Integrated Circuit)、DSP、可编程逻辑器件(PLD，Programmable Logic Device)、复杂可编程逻辑器件(CPLD，Complex Programmable Logic Device)、现场可编程门阵列(FPGA，Field-Programmable Gate Array)或其他电子元件执行实现本申请实施例提供的驾驶仿真场景的处理方法。
接下来结合前述的实现本申请实施例的驾驶仿真系统及驾驶仿真场景的处理装置的示例性应用实施，说明实现本申请实施例的驾驶仿真场景的处理方法。
参见图5，图5是本申请实施例提供的驾驶仿真场景的处理方法的一个可选的流程示意图，以服务器(如图1中服务器300)实现驾驶仿真场景的处理方法为例，结合图1及图5对本申请实施例提供的驾驶仿真场景的处理方法进行说明。
步骤101：服务器获取用于驾驶仿真的路网模型中的多个路径端点。
在一些实施例中，服务器可通过如下方式获取用于驾驶仿真的路网模型中的多个路径端点：
服务器获取自动驾驶车辆的测试路网对应的地图数据，基于地图数据，建立对自动驾驶车辆进行仿真测试的路网模型，基于路网模型的路网结构，确定用于驾驶仿真的路网模型中的多个路径端点。
在实际实施时，服务器可以从数据库获取存储的地图数据，或者接收终端发送的地图数据。
在一些实施例中，地图数据中可包括地图类型，可以是现实世界的不同级别的地图(城市地图、市区地图等)，也可以是自定义的虚拟世界的地图；区域，可以是城市级别、市区级别和其他级别，当城市/市区未被指定时，默认城市的地图将被采用。
在一些实施例中，地图数据中还可包括车道类型、车道的宽度、车道数量等，其中车道类型如封闭高速路、人车混行路、单行行驶道路、双向行驶道路。
在一些实施例中，地图数据中还可包括交通控制设施，如路障的设置位置和数量、车道中路径交叉位置的设定、信号灯状态(包括红灯、绿灯和黄灯)的设定(如切换间隔)。
在一些实施例中，地图数据中还可包括背景车辆的数量/密度、背景车辆的行驶特性，如是否违规行驶，对交通控制设施的响应方式等，以及背景车辆的动力特性，即背景车辆符合的动力学模型。
可以理解地，地图数据中还可包括任何对自动驾驶车辆进行仿真测试所需的地图数据，对于本申请实施例地图数据中未提及的项目，服务器300可以采用默认项目的默认设置或根据需要进行添加。
在一些实施例中，服务器可通过如下方式建立对自动驾驶车辆进行仿真测试的路网模型：服务器基于地图数据，进行三维建模，得到供测试车辆及背景车辆行驶的图形化的三维数学模型。
步骤102：确定多个路径端点中的至少一个第一路径端点作为发车点，以及至少一个第二路径端点作为收车点。
在一些实施例中，服务器可通过如下方式进行发车点及收车点的确定：
服务器基于多个路径端点在路网模型中的分布，选取第一数量的第一路径端点作为发车点，选取第二数量的第二路径端点作为收车点。其中，第一数量及第二数量的具体数值可依据实际需要进行设定。其中，第一路径端点和第二路径端点可以是不同的路径端点，对于一个车辆来说，其发车点和收车点为不同的路径端点，而对于不同车辆来说，一个车辆的出发点可以为另一个车辆的收车点，本申请实施例对此不作限定。
步骤103：在路网模型中的发车点生成背景车辆，并控制背景车辆从发车点驶入路网模型，在行驶至收车点时驶出路网模型。
这里，首先对路网模型中发车点及收车点的设定进行说明，图6是本申请实施例提供的路网模型中发车点及收车点的示意图，参见图6，在实际应用中，为了避免车辆在路网中间直接产生，造成交通状态的突然变化(如引起车辆碰撞)以及视觉上的突兀感，在实际实施时，发车点可以选取地图外侧边缘处道路或者地图中断头路处，供背景车辆和测试车辆驶入路网模型；类似的，为了避免车辆在路网模型的车道中突然消失，造成交通状态的突然变化(如引起车辆碰撞)以及视觉上的突兀感，在实际实施时，收车点可以选取地图外侧边缘处道路或者地图中断头路处，供背景车辆和测试车辆驶出路网模型。在本申请实施例中，上述背景车辆可以作为测试车辆的交通流，来模拟真实的路况。
在一些实施例中，在路网模型中的发车点，服务器可通过如下方式进行背景车辆及测试车辆的生成：服务器获取路网模型中的发车点；确定发车点符合测试车辆生成条件时，生成测试车辆；确定发车点不符合测试车辆生成条件，但符合背景车辆生成条件时，生成背景车辆。在一些实施例中，若确定发车点既符合测试车辆生成条件，又符合背景车辆生成条件时，不生成背景车辆，即暂停对背景车辆的生成，并进行日志记录。在一些实施例中，若确定发车点既符合测试车辆生成条件，又符合背景车辆生成条件时，不生成背景车辆以及测试车辆，即暂停对背景车辆和测试车辆的生成，并进行日志记录。在一些实施例中，若确定发车点既符合测试车辆生成条件，又符合背景车辆生成条件时，可以基于是否已经在其他发车点生成测试车辆来确定是否在这个发车点进行测试车辆的生成，例如，若已经有任一发车点生成测试车辆，则在该发车点不生成测试车辆，而生成背景车辆或者暂停生成背景车辆，若未有发车点生成测试车辆，则在该发车点生成测试车辆，而不生成背景车辆。
在实际应用中，生成测试车辆的发车点与生成背景车辆的发车点可以相同或不同，示例性地，参见图7，图7是本申请实施例提供的发车点生成测试车辆与背景车辆的示意图。
在实际实施时，发车点的数量可以为一个或多个，对于某个特定的发车点来说，服务器首先判断该发车点是否符合测试车辆生成条件，并在确定该发车点不符合测试车辆生成条件 时，进一步判断该发车点是否符合背景车辆生成条件，并基于判断结果进行背景车辆生成与否的决定；也就是说，测试车辆的生成优先级高于背景车辆的生成优先级，如此，保证在仿真测试过程中测试车辆的顺利生成，避免无法生成测试车辆所导致的自动驾驶车辆仿真测试的失败。
在一些实施例中，发车点的数量为两个以上，服务器在对发车点是否符合测试车辆生成条件进行判断时，可以对两个以上发车点进行遍历，并在确定当前遍历的发车点对应两个以上车道时，对两个以上车道进行遍历，以判断每个车道对应的发车点是否符合测试车辆生成条件。
在一些实施例中，服务器确定当前遍历的车道所对应的发车点到达生成测试车辆的时间，且该发车点一定距离内不存在其他车辆时，确定测试车辆生成条件得到满足。
在实际实施时，服务器中设置有仿真时钟，服务器可获取测试车辆的生成时间表，在一些实施例中，测试车辆的生成间隔可以为固定时间间隔，或依据实际需要进行设定；在实际实施时，服务器基于测试车辆的生成时间表判断当前时刻是否到达生成测试车辆的时间，当确定到达生成测试车辆的时间时，进一步判断当前车道是否存在阻塞车辆，即一定距离内是否存在其他车辆，当一定距离内存在其他车辆时，不进行测试车辆的生成，并进行相应的日志记录，如此，避免了由于存在阻塞车辆，即使生成了测试车辆也无法正常行驶而造成的交通进一步的阻塞。
在一些实施例中，服务器确定发车点不符合测试车辆生成条件(未到达生成测试车辆的时间，和/或发车点一定距离内存在其他车辆)、到达生成背景车辆的时间、且一定距离内不存在其他车辆时，生成背景车辆，所生成的背景车辆符合预设的动力学模型，该动力学模型对应预设车型。
这里，在实际实施时，服务器确定发车点不符合测试车辆生成条件时，进行是否符合背景车辆生成条件(到达生成背景车辆的时间且发车点一定距离内不存在其他车辆)的判断，首先进行是否到达生成背景车辆的时间的判断，若未到生成背景车辆的时间，不进行背景车辆的生成，并进行相应的日志记录；若到达生成背景车辆的时间，进一步判断当前车道是否存在阻塞车辆，即一定距离内是否存在其他车辆，当一定距离内存在其他车辆时，不进行背景车辆的生成，并进行相应的日志记录，如此，避免了由于存在阻塞车辆，即使生成了背景车辆也无法正常行驶而造成的交通进一步的阻塞。
对生成背景车辆的时间进行说明，在实际实施时，服务器可获取背景车辆的生成时间表，背景车辆的生成时间间隔可以设置为固定数值，或者服从一定的概率分布，如负指数分布或者平均分布；在一些实施例中，当出车点处有多条车道时，可以每条车道独立计算，按一定的时间间隔产生车辆，并在初始时间上叠加一个时间偏差，即每条车道都有一个相应的背景车辆生成时间表，如背景车辆在第一条车道上产生的时刻为第1秒，4秒，7秒…，在第二条车道上产生的时刻为第2秒，5秒，8秒…(假设都是按固定间隔每3秒产生一辆，车道间的偏差为1秒)，如此，避免了多辆背景车辆同时进入路网模型所造成的交通阻塞，或驾驶仿真准确度的下降。
在实际实施时，生成背景车辆后，该背景车辆被赋予一定的车辆属性(如车型、初速度、目的状态等)，同时，该背景车辆符合对应所述车型的动力学模型。
在一些实施例中，为了更准确的对自动驾驶车辆进行仿真测试，在路网模型中生成测试 车辆前，需要确保背景车辆在路网模型中充分分布，因此，在生成测试车辆前存在一定时间的仿真预热期，即仿真测试开始一段时间(可依据实际情况如经验值设定)内只进行背景车辆的生成，以确保路网模型中背景车辆的数量及相应的分布满足仿真测试需求，或者，在生成测试车辆前确定路网模型中已经存在一定数量(可依据实际需要进行设定)的背景车辆。
在一些实施例中，服务器可通过如下方式控制背景车辆的行驶状态：
服务器获取背景车辆的行驶位置及行驶方向，基于行驶位置及行驶方向，确定背景车辆行驶至路径交叉位置和信号灯位置中至少一个位置时，对背景车辆的行驶速度和行驶路径中至少一项进行规划。
这里，对背景车辆行驶至路径交叉位置及背景车辆行驶至信号灯位置进行说明，图8是本申请实施例提供的车辆行驶至路径交叉位置及信号灯位置的示意图，参见图8，在实际实施时，背景车辆行驶至路径交叉位置，是指背景车辆行驶方向前方存在路径交叉口，且背景车辆与该路径交叉口的距离在设定的第一距离范围内；背景车辆行驶至信号灯位置，是指背景车辆行驶方向前方存在信号灯，且背景车辆与信号灯的距离在设定的第二距离范围内。
在一些实施例中，服务器基于背景车辆当前的行驶位置，判断背景车辆是否行驶至路径交叉位置，当确定背景车辆行驶至路径交叉位置时，对背景车辆的行驶路径进行规划，如直行、左转、右转；这里，在实际实施时，可对路网模型的各个车道中行驶至路径交叉位置的背景车辆的转向比例进行设定，图9为本申请实施例提供的路径交叉位置的背景车辆的转向比例的示意图，参见图9，行驶至图9中示出的路径交叉位置的多个背景车辆中，25％的背景车辆需要左转，15％的背景车辆需要右转，60％的背景车辆需要直行。
服务器确定背景车辆行驶至路径交叉位置但未行驶至路径交叉位置时，对是否行驶至信号灯位置(即当前行驶位置是否对应信号灯位置)进行判断，若确定驶至信号灯位置时，获取相应的信号灯颜色，即获取行驶方向上信号灯的颜色，基于信号灯颜色，控制背景车辆的行驶速度。
在实际应用中，服务器可通过如下方式实现基于信号灯颜色，控制背景车辆的行驶速度：判断信号灯颜色是否为绿色，若信号灯颜色为绿色，保持当前车速不变匀速行驶；若信号灯颜色非绿色，而是黄色，均匀减速并停止，或者匀速抢黄灯驶过；若信号灯颜色非绿色，而是红色，均匀减速并停止，当然，在实际实施时，可控制一定数量的背景车辆闯红灯，如加速或保持速度不变的通过。
在一些实施例中，服务器当确定背景车辆行驶至路径交叉位置时，进一步对是否行驶至信号灯位置(即路径交叉口是否存在信号灯)进行判断，若确定驶至信号灯位置时，获取相应的信号灯颜色，基于信号灯颜色，控制背景车辆的行驶速度；具体地，判断信号灯颜色是否为绿色或黄色，若信号灯颜色为绿色或黄色，进一步判断确定的行驶路径是否存在相应的让行规则，所述让行规则，指示所确定的行驶路径的行驶优先级低于与测试车辆未处于同一道车上的车辆的行驶优先级，如左转让直行，右转让左转；若确定的行驶路径存在相应的让行规则，基于让行规则，控制背景车辆的行驶速度，如控制背景车辆均匀减速至停止。
在一些实施例中，服务器确定背景车辆行驶至路径交叉位置，且未行驶至信号灯位置，即路径交叉位置不存在信号灯时，进一步判断确定的驶路径是否存在相应的让行规则，若不存在让行规则，保持当前的车速不变；若存在相应的让行规则时，基于让行规则，控制背景车辆的行驶速度。
在一些实施例中，所述路网模型中还设置有减速带及让行牌，相应的，服务器基于背景车辆的行驶位置判断是否到达减速带位置和/或让行牌位置，并基于判断结果对背景车辆的速度进行控制，如确定行驶位置前方一定距离内存在减速带时，控制背景车辆的速度均匀减速至一定速度，确定行驶位置前方一定距离内存在让行牌时，控制背景车辆的速度均匀减速至停止。
在一些实施例中，服务器还监测测试车辆响应于背景车辆的行驶状态，基于行驶策略作出的行驶规划，行驶规划包括：路径规划及速度规划中至少之一。
在一些实施例中，服务器可通过如下方式监测测试车辆响应于背景车辆的行驶状态，基于行驶策略作出的行驶规划：
服务器获取测试车辆基于行驶策略作出的行驶规划对应的行驶参数，行驶参数包括：速度参数、位置参数及方向参数中至少之一；其中，行驶策略，用于获取背景车辆的行驶状态，行驶状态包括行驶位置、行驶方向及行驶速度中至少之一；基于行驶状态，对测试车辆进行行驶规划。
示例性地，测试车辆基于路网模型中背景车辆的行驶位置、行驶方向及行驶速度，确定行驶方向一定距离处发生交通阻塞，基于目标位置(即行驶终点位置)，重新进行路径规划，如在行驶至路径交叉位置时左转或右转，变换到达目标位置的路径，以躲避拥堵。
继续对本申请实施例提供的驾驶仿真场景的处理方法进行说明。
在进行驾驶仿真之前，需要进行路网模型的构建，在一些实施例中，路网模型可以为二维或三维模型，该路网模型基于涵盖测试路网的背景地图得到，该背景地图可以是根据现实世界中采集数据所制作的高清地图，也可以是用户编辑创建的自定义地图。
路网模型中设置有发车点，即出车点，出车点位置选择在地图外侧边缘处道路上或者地图中断头路处，供背景车辆及测试车辆生成并由此驶入路网模型，如此，可避免车辆在道路中间直接产生，进而引起车辆碰撞，造成交通状态的突然变化以及视觉上的突兀感。
路网模型中还设置有收车点，供背景车辆及测试车辆由此驶出路网模型，即当车辆行驶至收车点处时，车辆无论在哪个车道都会被移除出路网模型；收车点位置选择在地图外侧边缘处道路上或者地图中断头路处，以避免车辆在道路中间突然消失，造成交通状态的突然变化以及视觉上的突兀感。
在一些实施例中，驾驶仿真场景的处理方法可以包括四部分，分别为：仿真测试预热、测试车辆及背景车辆生成、背景车辆转向决策、测试车辆行驶规划监测，需要说明的是，测试车辆及背景车辆生成、背景车辆转向决策、测试车辆行驶规划监测的执行顺序不分先后，可同时实施，以下分别进行说明。
一、仿真测试预热。
驾驶仿真开始之前，进行仿真测试预热，在该阶段，仅进行背景车辆的生成，使得路网模型中各个车道都有充分的背景车辆分布，以确保路网模型中有足够多的背景车辆供测试车辆进行仿真测试，在实际实施时，可设定一段时间(可根据实际情况进行设定)为仿真测试预热阶段，或者确定路网模型中背景车辆的数量从零增长至一定数量的阶段，为仿真测试预热阶段。
对仿真测试预热阶段中背景车辆的生成进行说明。在实际实施时，设置有背景车辆的生 成时间表，该生成时间表的数量为一个或多个，如对于一个发车点存在多条道路的情况，可对应每一条道路设置一个背景车辆的生成时间表，基于该生成时间表进行背景车辆的生成，在背景车辆生成的同时，赋予一定的车辆属性(如车型、初速度等)，随着仿真时钟的推进而驶入路网模型。
这里，背景车辆的生成间隔可以设置为固定数值(如3秒)，或者服从一定的概率分布，如负指数分布或者平均分布。当出车点处有多条车道时，可以每条车道独立计算，按一定的间隔分布产生车辆，并在初始时间上叠加一个时间偏差以避免多辆车同时进入系统，如背景车辆在第一条车道上产生的时刻为第1秒，4秒，7秒…，在第二条车道上产生的时刻为第2秒，5秒，8秒…(假设都是按固定间隔每3秒产生一辆，车道间的偏差为1秒)。
二、测试车辆及背景车辆生成。
在仿真测试预热之后，路网模型中不止能够生成背景车辆，可以进行测试车辆的生成，类似的，测试车辆也存在对应的生成时间表，测试车辆的生成间隔可以设置为固定数值，或者依据实际需要进行设定。若对于某个测试车辆的生成时刻，正好与背景车辆产生的时刻冲突，则此背景车辆的生成将暂停，直至该车道下一个要产生背景车辆的时刻到来再恢复产生车辆。当测试车辆无法在预先设定的时刻产生时(如被溢流车辆堵住)，则将此出车时刻顺延一个仿真步长Δt，直至该地点满足生成条件再产生测试车辆。
设定测试车辆的生成优先级高于背景车辆的生成优先级，也即，对于某个发车点来说，若该发车点同时具备生成测试车辆的条件(生成时间到达且相应车道不存在阻塞车辆)及生成背景车辆的条件(生成时间到达且相应车道不存在阻塞车辆)，生成测试车辆但不生成背景车辆，同时进行日志记录，具体地，以路网模型中存在多个发车点，且存在对应多个道路的发车点为例，对测试车辆及背景车辆的生成进行说明。
图10为本申请实施例提供的生成测试车辆及背景车辆的流程示意图，参见图10，测试车辆及背景车辆的生成包括：
步骤201：服务器对路网模型中的出车点进行遍历。
步骤202：服务器判断是否已经遍历所有出车点，如果未遍历所有出车点，执行步骤203，如果已遍历所有出车点，执行步骤217。
步骤203：服务器将下一个出车点设置为当前出车点，对当前出车点对应的车道进行遍历。
步骤204：服务器判断当前出车点对应的车道是否均已遍历，如果均已遍历，执行步骤202；如果存在未遍历的车道，执行步骤205。
步骤205：服务器选定下一条车道为当前车道。
步骤206：服务器判断是否到达测试车辆的生成时刻，如果到达，执行步骤207；如果未到达，执行步骤210。
步骤207：服务器判断是否到达背景车辆的生成时刻，如果未到达，执行步骤208；如果未到达，执行步骤214。
步骤208：服务器判断此位置是否可以生成测试车辆，如果可以，执行步骤209；如果不可以，执行步骤215。
这里，判断此位置是否可以生成测试车辆，即判断当前车道是否存在阻塞车辆。
步骤209：服务器在当前道路对应的出车点生成测试车辆，执行步骤204。
步骤210：服务器判断是否到达背景车辆的生成时刻，如果到达，执行步骤211；如果未到达，执行步骤204。
步骤211：服务器判断此位置是否可以生成背景车辆，如果可以，执行步骤212；如果不可以，执行步骤213。
这里，判断此位置是否可以生成背景车辆，即判断当前车道是否存在阻塞车辆。
步骤212：服务器在当前道路对应的出车点生成背景车辆，执行步骤204。
在实际实施时，生成的背景车辆符合动力学模型，被赋予一定的车辆属性(如车型、初速度等)。
步骤213：服务器进行错误日志记录，执行步骤204。
步骤214：服务器暂停背景车辆的生成，并进行日志记录。
步骤215：服务器暂停测试车辆的生成，并将其生成时间向后推移一个时间步长，并执行步骤204。
这里，一个时间步长即Δt，具体可依据实际需要进行设定。
步骤216：服务器将仿真时钟等距推进一个时间步长。
步骤217：服务器判断总仿真测试时间是否已到达，如果到达，执行步骤218；如果未到达，执行步骤216。
步骤218：服务器结束仿真运行。
三，背景车辆转向决策。
路网模型中设置有路径交叉口，如十字路口、丁字路口，还设置有信号灯，通过设置转向决策，对行驶中的背景车辆进行组织及调控。如当背景车辆行驶至距路径交叉口和/或信号灯位置一定距离时，对背景车辆的行驶路径(直行、左转、右转)及行驶速度进行控制。
其中，信号灯的颜色包括红色、黄色及绿色，背景车辆对信号灯颜色的反应可以如下：绿色：保持速度不变，匀速前进；红色：减速至停止；黄色：以一定概率减速并停止，或者匀速抢黄灯驶过路口。
对于行驶至路径交叉口，涉及背景车辆的左转或右转时，可设定相应的让行规则，如左转让直行，右转让左转。
对于行驶至路径交叉口的多个背景车辆，在路径交叉口前一定距离(如30米)设置转向决策点，当车辆行驶至决策点(即前述的路径交叉位置)时，按一定事先设置好的比例会被赋予一个行驶方向(如左转、直行或者右转)，然后背景车辆将按行驶方向换到相应的下游车道，并按照相应信号灯行驶。
图11为本申请实施例提供的背景车辆的转向决策控制的流程示意图，参见图11，背景车辆的转向决策控制包括：
步骤301：服务器对背景车辆进行遍历，选取背景车辆。
在实际应用中，路网模型中的背景车辆可携带相应的标识，以唯一的标识该背景车辆。
步骤302：服务器判断背景车辆是否到达转向决策点，如果到达，执行步骤303；如果未到达，执行步骤304。
步骤303：服务器判断背景车辆是否行驶在相应车道，如果在相应车道，执行步骤304；如果未在相应车道，执行步骤312。
这里，当背景车辆行驶至转向决策点时，对背景车辆的行驶路径重新进行规划，如直行、 左转、右转，相应的，判断背景车辆是否行驶在相应车道，指的是判断背景车辆是否已在重新规划后的车道。
步骤304：服务器控制背景车辆正常行驶。
这里，控制背景车辆正常行驶，即控制背景车辆以当前速度在相应车道行驶。
步骤305：服务器判断视距内是否存在信号灯，如果存在，执行步骤306；如果不存在，执行步骤316。
这里，视距的大小可以依据实际情况或经验值进行设定。
步骤306：服务器判断信号灯是否为绿色，如果不为绿色，执行步骤307；如果为绿色，执行步骤316。
步骤307：服务器判断信号灯是否为黄色，如果不为黄色，执行步骤308；如果为黄色，执行步骤315。
步骤308：服务器确定信号灯为红色。
步骤309：服务器控制背景车辆减速至停止。
步骤310：服务器判断是否已遍历所有背景车辆，如果已遍历所有背景车辆，执行步骤311；如果未遍历所有背景车辆，执行步骤317。
步骤311：服务器判断总仿真时间是否已到达，如果到达，执行步骤318；如果未到达，执行步骤314。
步骤312：服务器控制背景车辆变换车道至相应的车道。
步骤313：服务器选取下一个背景车辆。
步骤314：服务器将仿真时钟等距推进一个时间步长，并执行步骤301。
步骤315：服务器判断是否需要减速至停止，如果需要，执行步骤309；如果不需要，执行步骤316。
步骤316：服务器判断是否存在让行规则，如果存在，执行步骤309；如果不存在，执行步骤317。
步骤317：服务器控制背景车辆正常行驶。
步骤318：服务器结束仿真运行。
四、测试车辆行驶规划监测。
在驾驶仿真过程中，需要对测试车辆的行驶参数进行监测，包括对测试车辆的行驶速度、行驶位置及行驶方向的获取，以确定测试车辆基于背景车辆的行驶状态所作出的反应，如避让、变换车道、超车、跟车、停车等。
应用本申请实施例具备以下有益技术效果：
1)、在路网模型中设置发车点及收车点，使得车辆的产生及消失在特定位置，避免了车辆在不定位置产生及消失所造成的交通状态的突然变化(如引起车辆碰撞)以及视觉上的突兀感。
2)、在路网模型中的发车点，生成背景车辆及对应自动驾驶车辆的测试车辆，如此，实现了驾驶仿真过程中，背景车辆及测试车辆的自动生成，提高了驾驶仿真场景的处理效率。
3)、控制背景车辆的行驶状态，使背景车辆从发车点驶入路网模型，并在行驶至收车点时驶出路网模型，如此，通过对背景车辆行驶状态的控制，达到对测试车辆的行驶策略进行验证的目的。
4)、当发出点同时满足测试车辆的生成条件及背景车辆的生成条件时，生成测试车辆不生成背景车辆，即测试车辆的生成优先级高于背景车辆的生成优先级，如此，保证在仿真测试过程中测试车辆的顺利生成，避免无法生成测试车辆所导致的自动驾驶车辆仿真测试的失败。
本申请实施例还提供一种驾驶仿真场景的处理装置，包括：
获取单元，用于获取用于驾驶仿真的路网模型中的多个路径端点；
确定单元，用于确定所述多个路径端点中的至少一个第一路径端点作为发车点，以及至少一个第二路径端点作为收车点；
生成单元，用于生成背景车辆；例如，用于在所述路网模型中的发车点生成背景车辆。
控制单元，用于控制所述背景车辆从所述发车点驶入所述路网模型，并在行驶至所述收车点时驶出所述路网模型。
在一些实施例中，所述获取单元，还用于获取自动驾驶车辆的测试路网对应的地图数据，基于地图数据，建立对自动驾驶车辆进行仿真测试的路网模型，基于路网模型的路网结构，确定用于驾驶仿真的路网模型中的多个路径端点。
所述确定单元，还用于基于所述多个路径端点在所述路网模型中的分布，选取第一数量的第一路径端点作为发车点，选取第二数量的第二路径端点作为收车点。
所述生成单元，还用于获取所述路网模型中的发车点；
确定所述发车点符合测试车辆生成条件时，生成测试车辆；
确定所述发车点不符合测试车辆生成条件，但符合背景车辆生成条件时，生成所述背景车辆。
在一些实施例中，所述生成单元，还用于响应于所述发车点的数量为至少两个，对所述至少两个发车点进行遍历；
确定当前遍历的发车点对应至少两个车道时，对所述至少两个车道进行遍历；
确定当前遍历的车道所对应的发车点到达生成测试车辆的时间，且一定距离内不存在其他车辆，生成所述测试车辆。
在一些实施例中，所述生成单元，还用于确定所述发车点不符合测试车辆生成条件、到达生成背景车辆的时间、且一定距离内不存在其他车辆时，生成所述背景车辆；
所述背景车辆符合预设的动力学模型，所述动力学模型对应预设车型。
在一些实施例中，所述控制单元，还用于获取所述背景车辆的行驶位置及行驶方向；
基于所述行驶位置及行驶方向，确定所述背景车辆行驶至路径交叉位置和信号灯位置中至少一个位置时，对所述背景车辆的行驶速度和行驶路径中至少一项进行规划。
在一些实施例中，所述控制单元，还用于当所述背景车辆行驶至路径交叉位置时，确定所述背景车辆的行驶路径；
当所述路径交叉位置存在信号灯时，基于所述行驶路径确定相应的信号灯颜色；
基于所确定的信号灯颜色，控制所述背景车辆的行驶速度。
在一些实施例中，所述控制单元，还用于当所述路径交叉位置不存在信号灯、且所述行驶路径存在相应的让行规则时，基于所述让行规则，控制所述背景车辆的行驶速度；
其中，所述让行规则，指示所述行驶路径的行驶优先级低于与所述测试车辆未处于同一道车上的车辆的行驶优先级。
在一些实施例中，所述控制单元，还用于当所述信号灯颜色为绿色或黄色、且所述行驶路径存在相应的让行规则时，基于所述让行规则，控制所述背景车辆的行驶速度。
在一些实施例中，所述控制单元，还用于当所述行驶位置未对应路径交叉位置、但对应信号灯位置时，确定相应的信号灯颜色；
基于所述信号灯颜色，控制所述背景车辆的行驶速度。
在一些实施例中，还包括：
监测单元，用于监测测试车辆响应于所述背景车辆的行驶状态，基于行驶策略作出的行驶规划，所述行驶规划包括：路径规划及速度规划中至少之一。
在一些实施例中，所述监测单元，还用于获取所述测试车辆基于行驶策略作出的行驶规划对应的行驶参数，所述行驶参数包括：速度参数、位置参数及方向参数中至少之一；
所述行驶策略，用于获取所述背景车辆的行驶状态，所述行驶状态包括行驶位置、行驶方向及行驶速度中至少之一；基于所述行驶状态，对所述测试车辆进行所述行驶规划。
本申请实施例提供一种存储有可执行指令的存储介质，其中存储有可执行指令，当可执行指令被处理器执行时，将引起处理器执行本申请实施例提供的驾驶仿真场景的处理方法，例如，如图5示出的驾驶仿真场景的处理方法的如下步骤：
获取用于驾驶仿真的路网模型中的多个路径端点；
确定所述多个路径端点中的至少一个第一路径端点作为发车点，以及至少一个第二路径端点作为收车点；
生成背景车辆，控制所述背景车辆从所述发车点驶入所述路网模型，在行驶至所述收车点时驶出所述路网模型。
在一些实施例中，所述处理器还用于实现下述步骤：
获取所述路网模型中的发车点；
确定所述发车点符合测试车辆生成条件时，生成测试车辆；
所述处理器还用于实现下述步骤：
确定所述发车点不符合测试车辆生成条件，但符合背景车辆生成条件时，生成所述背景车辆。
在一些实施例中，所述处理器还用于实现下述步骤：
响应于所述发车点的数量为两个以上，对所述两个以上发车点进行遍历；
确定当前遍历的发车点对应两个以上车道时，对所述两个以上车道进行遍历；
确定当前遍历的车道所对应的发车点到达生成测试车辆的时间，且一定距离内不存在其他车辆，生成所述测试车辆。
在一些实施例中，所述处理器还用于实现下述步骤：
确定所述发车点不符合测试车辆生成条件、到达生成背景车辆的时间、且一定距离内不存在其他车辆时，生成所述背景车辆；
所述背景车辆符合预设的动力学模型，所述动力学模型对应预设车型。
在一些实施例中，所述处理器还用于实现下述步骤：
获取所述背景车辆的行驶位置及行驶方向；
基于所述行驶位置及行驶方向，确定所述背景车辆行驶至路径交叉位置和信号灯位置中至少一个位置时，对所述背景车辆的行驶速度和行驶路径中至少一项进行规划。
在一些实施例中，所述处理器还用于实现下述步骤：
当所述背景车辆行驶至路径交叉位置时，确定所述背景车辆的行驶路径；
当所述路径交叉位置存在信号灯时，基于所述行驶路径确定相应的信号灯颜色；
基于所确定的信号灯颜色，控制所述背景车辆的行驶速度。
在一些实施例中，所述处理器还用于实现下述步骤：
当所述路径交叉位置不存在信号灯、且所述行驶路径存在相应的让行规则时，基于所述让行规则，控制所述背景车辆的行驶速度；
其中，所述让行规则，指示所述行驶路径的行驶优先级低于与所述测试车辆未处于同一道车上的车辆的行驶优先级。
在一些实施例中，所述处理器还用于实现下述步骤：
当所述信号灯颜色为绿色或黄色、且所述行驶路径存在相应的让行规则时，基于所述让行规则，控制所述背景车辆的行驶速度。
在一些实施例中，所述基于所述行驶位置及行驶方向，确定所述背景车辆行驶至路径交叉位置和信号灯位置中至少一个位置时，对所述背景车辆的行驶速度和行驶路径中至少一项进行规划，包括：
当所述行驶位置未对应路径交叉位置、但对应信号灯位置时，确定相应的信号灯颜色；
基于所述信号灯颜色，控制所述背景车辆的行驶速度。
在一些实施例中，所述处理器还用于实现下述步骤：
在所述路网模型中的发车点生成测试车辆；
监测所述测试车辆响应于所述背景车辆的行驶状态，基于行驶策略作出的行驶规划，所述行驶规划包括：路径规划及速度规划中至少之一。
在一些实施例中，所述处理器还用于实现下述步骤：
获取所述测试车辆基于行驶策略作出的行驶规划对应的行驶参数，所述行驶参数包括：速度参数、位置参数及方向参数中至少之一；
所述行驶策略，用于获取所述背景车辆的行驶状态，所述行驶状态包括行驶位置、行驶方向及行驶速度中至少之一；基于所述行驶状态，对所述测试车辆进行所述行驶规划。
在一些实施例中，所述处理器还用于实现下述步骤：
基于所述多个路径端点在所述路网模型中的分布，选取第一数量的第一路径端点作为发车点，选取第二数量的第二路径端点作为收车点。
这里需要指出的是：以上涉及驾驶仿真场景的处理装置的描述，与上述方法描述是类似的，同方法的有益效果描述，不做赘述，对于本申请实施例所述驾驶仿真场景的处理装置中未披露的技术细节，请参照本申请方法实施例的描述。
实施例的全部或部分步骤可以通过程序指令相关的硬件来完成，前述的程序可以存储于一计算机可读取存储介质中，该程序在执行时，执行包括上述方法实施例的步骤；而前述的存储介质包括：移动存储设备、随机存取存储器(RAM，Random Access Memory)、只读存储器(ROM，Read-Only Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
或者，本申请上述集成的单元如果以软件功能模块的形式实现并作为独立的产品销售或 使用时，也可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实施例的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行本申请各个实施例所述方法的全部或部分。而前述的存储介质包括：移动存储设备、RAM、ROM、磁碟或者光盘等各种可以存储程序代码的介质。以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (15)

  1. 一种驾驶仿真场景的处理方法，其特征在于，包括：
    获取用于驾驶仿真的路网模型中的多个路径端点；
    确定所述多个路径端点中的至少一个第一路径端点作为发车点，以及至少一个第二路径端点作为收车点；
    生成背景车辆，控制所述背景车辆从所述发车点驶入所述路网模型，在行驶至所述收车点时驶出所述路网模型。
  2. 如权利要求1所述的方法，其特征在于，所述方法还包括：
    获取所述路网模型中的发车点；
    确定所述发车点符合测试车辆生成条件时，生成测试车辆；
    所述生成背景车辆包括：
    确定所述发车点不符合测试车辆生成条件，但符合背景车辆生成条件时，生成所述背景车辆。
  3. 如权利要求2所述的方法，其特征在于，所述确定所述发车点符合测试车辆生成条件时，生成测试车辆，包括：
    响应于所述发车点的数量为两个以上，对所述两个以上发车点进行遍历；
    确定当前遍历的发车点对应两个以上车道时，对所述两个以上车道进行遍历；
    确定当前遍历的车道所对应的发车点到达生成测试车辆的时间，且一定距离内不存在其他车辆，生成所述测试车辆。
  4. 如权利要求2或3所述的方法，其特征在于，所述确定所述发车点不符合测试车辆生成条件，但符合背景车辆生成条件时，生成所述背景车辆，包括：
    确定所述发车点不符合测试车辆生成条件、到达生成背景车辆的时间、且一定距离内不存在其他车辆时，生成所述背景车辆；
    所述背景车辆符合预设的动力学模型，所述动力学模型对应预设车型。
  5. 如权利要求1所述的方法，其特征在于，所述方法还包括：
    获取所述背景车辆的行驶位置及行驶方向；
    基于所述行驶位置及行驶方向，确定所述背景车辆行驶至路径交叉位置和信号灯位置中至少一个位置时，对所述背景车辆的行驶速度和行驶路径中至少一项进行规划。
  6. 如权利要求5所述的方法，其特征在于，所述确定所述背景车辆行驶至路径交叉位置和信号灯位置中至少一个位置时，对所述背景车辆的行驶速度和行驶路径中至少一项进行规划，包括：
    当所述背景车辆行驶至路径交叉位置时，确定所述背景车辆的行驶路径；
    当所述路径交叉位置存在信号灯时，基于所述行驶路径确定相应的信号灯颜色；
    基于所确定的信号灯颜色，控制所述背景车辆的行驶速度。
  7. 如权利要求6所述的方法，其特征在于，所述方法还包括：
    当所述路径交叉位置不存在信号灯、且所述行驶路径存在相应的让行规则时，基于所述让行规则，控制所述背景车辆的行驶速度；
    其中，所述让行规则，指示所述行驶路径的行驶优先级低于与所述测试车辆未处于同一道车上的车辆的行驶优先级。
  8. 如权利要求6所述的方法，其特征在于，所述基于所确定的信号灯颜色，控制所述背景车辆的行驶速度，包括：
    当所述信号灯颜色为绿色或黄色、且所述行驶路径存在相应的让行规则时，基于所述让行规则，控制所述背景车辆的行驶速度。
  9. 如权利要求5所述的方法，其特征在于，所述基于所述行驶位置及行驶方向，确定所述背景车辆行驶至路径交叉位置和信号灯位置中至少一个位置时，对所述背景车辆的行驶速度和行驶路径中至少一项进行规划，包括：
    当所述行驶位置未对应路径交叉位置、但对应信号灯位置时，确定相应的信号灯颜色；
    基于所述信号灯颜色，控制所述背景车辆的行驶速度。
  10. 如权利要求1所述的方法，其特征在于，所述方法还包括：
    在所述路网模型中的发车点生成测试车辆；
    监测所述测试车辆响应于所述背景车辆的行驶状态，基于行驶策略作出的行驶规划，所述行驶规划包括：路径规划及速度规划中至少之一。
  11. 如权利要求10所述的方法，其特征在于，所述监测所述测试车辆响应于所述背景车辆的行驶状态，基于行驶策略作出的行驶规划，包括：
    获取所述测试车辆基于行驶策略作出的行驶规划对应的行驶参数，所述行驶参数包括：速度参数、位置参数及方向参数中至少之一；
    所述行驶策略，用于获取所述背景车辆的行驶状态，所述行驶状态包括行驶位置、行驶方向及行驶速度中至少之一；基于所述行驶状态，对所述测试车辆进行所述行驶规划。
  12. 如权利要求1所述的方法，其特征在于，所述确定所述多个路径端点中的至少一个路径端点作为发车点，以及至少一个路径端点作为收车点，包括：
    基于所述多个路径端点在所述路网模型中的分布，选取第一数量的第一路径端点作为发车点，选取第二数量的第二路径端点作为收车点。
  13. 一种驾驶仿真场景的处理装置，其特征在于，包括：
    获取单元，用于获取用于驾驶仿真的路网模型中的多个路径端点；
    确定单元，用于确定所述多个路径端点中的至少一个第一路径端点作为发车点，以及至少一个第二路径端点作为收车点；
    生成单元，用于生成背景车辆；
    控制单元，用于控制所述背景车辆从所述发车点驶入所述路网模型，并在行驶至所述收车点时驶出所述路网模型。
  14. 一种驾驶仿真场景的处理装置，其特征在于，包括：
    存储器，用于存储可执行指令；
    处理器，用于执行所述存储器中存储的可执行指令时，实现权利要求1至12任一项所述的方法。
  15. 一种存储介质，其特征在于，存储有可执行指令，用于引起处理器执行时，实现权利要求1至12任一项所述的方法。
PCT/CN2020/087045 2019-05-09 2020-04-26 驾驶仿真场景的处理方法、装置及存储介质 WO2020224462A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP20801543.8A EP3968001A4 (en) 2019-05-09 2020-04-26 DRIVING SCENE PROCESSING METHOD AND APPARATUS AND STORAGE MEDIUM
US17/378,432 US11971723B2 (en) 2019-05-09 2021-07-16 Processing method and apparatus for driving simulation scene, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910386494.4A CN110118661B (zh) 2019-05-09 2019-05-09 驾驶仿真场景的处理方法、装置及存储介质
CN201910386494.4 2019-05-09

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/378,432 Continuation US11971723B2 (en) 2019-05-09 2021-07-16 Processing method and apparatus for driving simulation scene, and storage medium

Publications (1)

Publication Number Publication Date
WO2020224462A1 true WO2020224462A1 (zh) 2020-11-12

Family

ID=67522088

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/087045 WO2020224462A1 (zh) 2019-05-09 2020-04-26 驾驶仿真场景的处理方法、装置及存储介质

Country Status (4)

Country Link
US (1) US11971723B2 (zh)
EP (1) EP3968001A4 (zh)
CN (1) CN110118661B (zh)
WO (1) WO2020224462A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112560253A (zh) * 2020-12-08 2021-03-26 中国第一汽车股份有限公司 驾驶场景的重构方法、装置、设备及存储介质
CN113721592A (zh) * 2021-09-03 2021-11-30 吉林大学 一种用于实现自动驾驶有效干扰测试的装置及方法
WO2023198016A1 (zh) * 2022-04-12 2023-10-19 腾讯科技（深圳）有限公司 虚拟场景中添加车辆的方法、装置、计算机设备、存储介质及程序产品
US11971723B2 (en) 2019-05-09 2024-04-30 Tencent Technology (Shenzhen) Company Limited Processing method and apparatus for driving simulation scene, and storage medium

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102019209535A1 (de) * 2019-06-28 2020-12-31 Robert Bosch Gmbh Verfahren zum Bereitstellen einer digitalen Straßenkarte
CN110597088B (zh) * 2019-09-25 2020-07-28 西南交通大学 一种极坐标系下的车辆动力学仿真方法
CN112748719A (zh) * 2019-10-16 2021-05-04 北京京东乾石科技有限公司 用于控制运输车的方法和装置
CN111681435B (zh) * 2020-03-27 2022-06-28 北京世纪互联宽带数据中心有限公司 基于边缘计算的交通控制方法、装置、电子设备及存储介质
CN111625927B (zh) * 2020-04-27 2023-05-12 腾讯科技（深圳）有限公司 仿真车辆的控制方法及相关设备
CN112286206B (zh) * 2020-11-17 2024-01-23 苏州智加科技有限公司 自动驾驶的模拟方法、系统、设备、可读存储介质及平台
CN112527632B (zh) * 2020-11-20 2021-09-28 北京赛目科技有限公司 一种交通测试方法及装置
CN112269325B (zh) * 2020-12-21 2021-03-16 腾讯科技（深圳）有限公司 自动驾驶仿真方法和装置、存储介质及电子设备
CN112579464A (zh) * 2020-12-25 2021-03-30 北京百度网讯科技有限公司 自动驾驶算法的校验方法、装置、设备以及存储介质
CN114185330A (zh) * 2021-12-12 2022-03-15 蜂联智能（深圳）有限公司 基于多场景交互的控制方法及控制装置
CN114743385B (zh) * 2022-04-12 2023-04-25 腾讯科技（深圳）有限公司 车辆处理方法、装置及计算机设备
CN114936515B (zh) * 2022-04-25 2023-09-19 北京宾理信息科技有限公司 一种生成仿真交通场景文件的方法及系统

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101281661A (zh) * 2008-05-29 2008-10-08 上海交通大学 汽车与两轮车碰撞事故再现系统
CN105808315A (zh) * 2014-12-31 2016-07-27 中国移动通信集团公司 一种高层体系结构协同交通安全仿真方法及装置
CN106777747A (zh) * 2016-12-29 2017-05-31 广西航程威特科技有限公司 一种三维交通仿真模拟系统
CN106934107A (zh) * 2017-02-20 2017-07-07 北京百度网讯科技有限公司 交通出行场景构建方法、装置、设备及存储介质
US20180086344A1 (en) * 2016-09-28 2018-03-29 Baidu Usa Llc Physical model and machine learning combined method to simulate autonomous vehicle movement
CN108829087A (zh) * 2018-07-19 2018-11-16 山东省科学院自动化研究所 一种自动驾驶汽车的智能测试系统及测试方法
CN109521748A (zh) * 2017-09-19 2019-03-26 成都鼎桥通信技术有限公司 无人驾驶车辆的测试方法
CN110118661A (zh) * 2019-05-09 2019-08-13 腾讯科技（深圳）有限公司 驾驶仿真场景的处理方法、装置及存储介质

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6117007A (en) * 1996-08-09 2000-09-12 Konami Corporation Driving game machine and a storage medium for storing a driving game program
CN101807224B (zh) * 2010-03-24 2011-07-20 上海交通大学 中微观一体化交通仿真车流加载方法
US8942964B2 (en) * 2010-06-08 2015-01-27 Southwest Research Institute Optical state estimation and simulation environment for unmanned aerial vehicles
US8894413B2 (en) * 2010-09-22 2014-11-25 Telcordia Technologies, Inc. Architecture, method, and program for generating realistic vehicular mobility patterns
AT510101B1 (de) * 2011-09-21 2014-01-15 Avl List Gmbh Verfahren zur computerbasierten Erzeugung eines Fahrzyklus-Datensatzes und eines Längsprofil-Datensatzes sowie Verfahren zum Testen eines Kraftfahrzeuges
US20160314224A1 (en) * 2015-04-24 2016-10-27 Northrop Grumman Systems Corporation Autonomous vehicle simulation system
CN104834776B (zh) * 2015-04-30 2019-01-18 吉林大学 一种微观交通仿真中交通车辆建模仿真系统及方法
US11138349B2 (en) * 2015-12-04 2021-10-05 International Business Machines Corporation System and method for simulating traffic flow distributions with approximated vehicle behavior near intersections
KR101832593B1 (ko) * 2016-02-02 2018-02-27 국방과학연구소 다수의 지상무인체계 임무통제와 통신기능 점검을 위한 개발용 시뮬레이터 구축방법 및 시스템
CN107992016A (zh) * 2016-10-26 2018-05-04 法乐第(北京)网络科技有限公司 一种无人驾驶车辆模拟测试方法
US10353393B2 (en) * 2016-12-29 2019-07-16 Baidu Usa Llc Method and system for improving stability of autonomous driving vehicles
CN108459588B (zh) * 2017-02-22 2020-09-11 腾讯科技（深圳）有限公司 自动驾驶方法及装置、车辆
AU2018282316B2 (en) * 2017-06-19 2020-07-16 Beijing Didi Infinity Technology And Development Co., Ltd. Systems and methods for displaying movement of vehicle on map
CN109211574A (zh) * 2017-07-05 2019-01-15 百度在线网络技术（北京）有限公司 无人驾驶汽车的场地测试方法、装置、设备及可读介质
WO2019051834A1 (en) * 2017-09-18 2019-03-21 Baidu.Com Times Technology (Beijing) Co., Ltd. DRIVING GUIDELINES BASED ON DRIVING SCENARIOS FOR PLANNING SELF-CONTAINED VEHICLE TRACKS
CN109670620A (zh) * 2017-10-16 2019-04-23 北京航空航天大学 一种车联网环境下出行信息服务策略与仿真验证系统
US10877476B2 (en) * 2017-11-30 2020-12-29 Tusimple, Inc. Autonomous vehicle simulation system for analyzing motion planners
CN108931927B (zh) * 2018-07-24 2019-07-30 百度在线网络技术（北京）有限公司 无人驾驶仿真场景的创建方法及装置

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101281661A (zh) * 2008-05-29 2008-10-08 上海交通大学 汽车与两轮车碰撞事故再现系统
CN105808315A (zh) * 2014-12-31 2016-07-27 中国移动通信集团公司 一种高层体系结构协同交通安全仿真方法及装置
US20180086344A1 (en) * 2016-09-28 2018-03-29 Baidu Usa Llc Physical model and machine learning combined method to simulate autonomous vehicle movement
CN106777747A (zh) * 2016-12-29 2017-05-31 广西航程威特科技有限公司 一种三维交通仿真模拟系统
CN106934107A (zh) * 2017-02-20 2017-07-07 北京百度网讯科技有限公司 交通出行场景构建方法、装置、设备及存储介质
CN109521748A (zh) * 2017-09-19 2019-03-26 成都鼎桥通信技术有限公司 无人驾驶车辆的测试方法
CN108829087A (zh) * 2018-07-19 2018-11-16 山东省科学院自动化研究所 一种自动驾驶汽车的智能测试系统及测试方法
CN110118661A (zh) * 2019-05-09 2019-08-13 腾讯科技（深圳）有限公司 驾驶仿真场景的处理方法、装置及存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3968001A4 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11971723B2 (en) 2019-05-09 2024-04-30 Tencent Technology (Shenzhen) Company Limited Processing method and apparatus for driving simulation scene, and storage medium
CN112560253A (zh) * 2020-12-08 2021-03-26 中国第一汽车股份有限公司 驾驶场景的重构方法、装置、设备及存储介质
CN112560253B (zh) * 2020-12-08 2023-02-24 中国第一汽车股份有限公司 驾驶场景的重构方法、装置、设备及存储介质
CN113721592A (zh) * 2021-09-03 2021-11-30 吉林大学 一种用于实现自动驾驶有效干扰测试的装置及方法
WO2023198016A1 (zh) * 2022-04-12 2023-10-19 腾讯科技（深圳）有限公司 虚拟场景中添加车辆的方法、装置、计算机设备、存储介质及程序产品

Also Published As

Publication number Publication date
CN110118661A (zh) 2019-08-13
EP3968001A1 (en) 2022-03-16
EP3968001A4 (en) 2022-06-22
US20210341935A1 (en) 2021-11-04
US11971723B2 (en) 2024-04-30
CN110118661B (zh) 2024-03-26

Similar Documents

Publication Publication Date Title
WO2020224462A1 (zh) 驾驶仿真场景的处理方法、装置及存储介质
WO2020224434A1 (zh) 一种驾驶仿真方法、装置、电子设备及计算机存储介质
KR102034009B1 (ko) 차량들의 감독 제어
CN113032285B (zh) 一种高精地图测试方法、装置、电子设备及存储介质
US10518770B2 (en) Hierarchical motion planning for autonomous vehicles
US20210191394A1 (en) Systems and methods for presenting curated autonomy-system information of a vehicle
CN110562258B (zh) 一种车辆自动换道决策的方法、车载设备和存储介质
Dresner et al. Traffic intersections of the future
GB2543647A (en) Formulating lane level routing plans
KR20200095365A (ko) 자율 주행 모드와 수동 주행 모드 사이의 주행 모드를 변경하는 리모트 컨트롤 자율 주행 자동차를 위한 방법 및 장치
Wang et al. Augmented reality-based advanced driver-assistance system for connected vehicles
Shladover et al. Using cooperative adaptive cruise control (CACC) to form high-performance vehicle streams
Krupitzer et al. Towards infrastructure-aided self-organized hybrid platooning
Zhang et al. A discrete-event and hybrid traffic simulation model based on SimEvents for intelligent transportation system analysis in Mcity
Khayatian et al. Cooperative driving of connected autonomous vehicles using responsibility-sensitive safety (RSS) rules
Zhang et al. Review on the impacts of cooperative automated driving on transportation and environment
Chuprov et al. Optimization of autonomous vehicles movement in urban intersection management system
CN114964286A (zh) 轨迹规划信息生成方法、装置、电子设备以及存储介质
Ren et al. Improve generalization of driving policy at signalized intersections with adversarial learning
Čakija et al. Autonomous intersection management: A short review
WO2023274284A1 (zh) 一种车辆控制方法、装置及系统
US20220340167A1 (en) Predicted Moving Trajectory Processing Method And Apparatus, And Constraint Barrier Display Method And Apparatus
CN112286188B (zh) 车辆行驶的控制方法、装置、设备及计算机可读存储介质
Papelis et al. Scenario definition and control for the national advanced driving simulator
WO2021102958A1 (zh) 一种交通拥堵辅助驾驶方法、系统、车载设备和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20801543

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020801543

Country of ref document: EP

Effective date: 20211209