Vehicle simulation control method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a kind of vehicle simulation control method, device, electronic equipment and storage medium, at least applied to automatic driving field, traffic simulation field and vehicle-mounted scene, wherein, method includes: on the simulation lane of simulation road network, target simulation vehicle and simulation signal lamp with countdown timer are displayed;When the distance between target simulation vehicle and simulation signal lamp is less than or equal to the preset reaction sight distance, the current color of simulation signal lamp and the current countdown value of countdown timer are acquired;Based on current color and current countdown value, the acceleration of target simulation vehicle is determined;Based on acceleration, control target simulation vehicle to carry out automatic driving simulation on simulation lane.By the present application, in the process of traffic simulation, the various decision-making processes of vehicle facing with countdown timer in real world can be accurately simulated, so as to improve the authenticity and accuracy of simulation result.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and includes, but is not limited to, a vehicle simulation control method, device, electronic device, and storage medium. Background Technology

[0002] Autonomous vehicles are intelligent cars that achieve driverless operation through computer systems. They can bring benefits such as reducing traffic accidents, saving energy, and giving people more free time, and represent the future direction of automobile development.

[0003] In the development of autonomous vehicles, autonomous driving simulation testing systems are needed to test and verify the developed decision-making algorithms. Testing and verification first require building a simulated traffic environment. Several background vehicles and a simulated traffic network are set up around the test vehicle, and the driving behaviors of the background vehicles are defined. During the simulation, the background vehicles drive on the road according to predefined driving behaviors. Certain driving behaviors and the simulated traffic network environment will influence the driving decision-making behavior of the test vehicle, thus verifying the decision-making algorithm for the test vehicle's navigation in traffic flow.

[0004] Current traffic simulations present a limited range of responses from simulated vehicles to traffic lights. They fail to simulate the complex decision-making processes that real-world vehicles face when encountering countdown timers, such as rushing to turn green or waiting for red lights due to inattention. Consequently, the simulated vehicles' responses to traffic light countdowns do not align with reality, resulting in distorted simulation results. Summary of the Invention

[0005] This application provides a vehicle simulation control method, device, electronic device, and storage medium, which can be applied to at least the fields of autonomous driving, traffic simulation, and in-vehicle scenarios. It can accurately simulate various decision-making processes of vehicles facing countdown timers in the real world during traffic simulation, thereby improving the realism and accuracy of simulation results.

[0006] The technical solution of this application embodiment is implemented as follows:

[0007] This application provides a vehicle simulation control method, the method comprising: displaying a target simulated vehicle and a simulated traffic light with a countdown timer on a simulated lane of a simulated road network; when the distance between the target simulated vehicle and the simulated traffic light is less than or equal to a preset reaction line of sight, acquiring the current color of the simulated traffic light and the current countdown value of the countdown timer; determining the acceleration of the target simulated vehicle based on the current color and the current countdown value; and controlling the target simulated vehicle to perform autonomous driving simulation on the simulated lane based on the acceleration.

[0008] This application provides a vehicle simulation control device, comprising: a display module for displaying a target simulated vehicle and a simulated traffic light with a countdown timer on a simulated lane of a simulated road network; an acquisition module for acquiring the current color of the simulated traffic light and the current countdown value of the countdown timer when the distance between the target simulated vehicle and the simulated traffic light is less than or equal to a preset reaction line of sight; a determination module for determining the acceleration of the target simulated vehicle based on the current color and the current countdown value; and a simulation control module for controlling the target simulated vehicle to perform autonomous driving simulation on the simulated lane based on the acceleration.

[0009] In some embodiments, the apparatus further includes: a reaction distance acquisition module, configured to acquire a preset reaction distance corresponding to the target simulated vehicle; the preset reaction distance includes a traffic light reaction distance and a countdown reaction distance; the traffic light reaction distance is greater than or equal to the countdown reaction distance; a detection module, configured to continuously detect the distance between the target simulated vehicle and the simulated traffic light when the distance between the target simulated vehicle and the simulated traffic light is detected to be less than or equal to the traffic light reaction distance; and a condition determination module, configured to determine that the distance between the target simulated vehicle and the simulated traffic light is less than or equal to the preset reaction distance when the distance between the target simulated vehicle and the simulated traffic light is detected to be less than or equal to the countdown reaction distance.

[0010] In some embodiments, the reaction distance acquisition module is further configured to: acquire vehicle attribute parameters of the target simulated vehicle, driver attribute parameters of the simulated driver corresponding to the target simulated vehicle, and environmental parameters of the simulated road network; determine the acuity coefficient of the target simulated vehicle based on the vehicle attribute parameters, the driver attribute parameters, and the environmental parameters; acquire the road inherent parameters corresponding to the simulated lane; and determine the preset reaction distance based on the road inherent parameters and the acuity coefficient.

[0011] In some embodiments, the determining module is further configured to: determine a first travel time corresponding to the target simulated vehicle, wherein the first travel time is the time it takes for the target simulated vehicle to travel from its current position to the stop line position of the simulated lane at its current speed; when the current color is red and the current countdown value is a first countdown value, if the first travel time is greater than the first countdown value, determine a first difference between the first travel time and the first countdown value; when the first difference is greater than a preset red light advance margin threshold, select the acceleration of the target simulated vehicle as a first acceleration according to a first aggressive probability, or select the acceleration of the target simulated vehicle as zero according to a first conservative probability; wherein the sum of the first aggressive probability and the first conservative probability is 1, the first aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle, and the first acceleration is greater than zero.

[0012] In some embodiments, the first acceleration is positively correlated with the aggressiveness parameter of the simulated driver; the first acceleration is less than or equal to the maximum acceleration of the target simulated vehicle, and the first acceleration is less than the target uniform acceleration of the target simulated vehicle, wherein the target uniform acceleration refers to the uniform acceleration adopted by the target simulated vehicle when it travels from the current position to the stop line position with the current speed as the initial speed, the first countdown value as the travel time.

[0013] In some embodiments, the determining module is further configured to: when the first difference is less than or equal to the red light advance margin threshold, select the acceleration of the target simulated vehicle as zero according to a second aggressive probability, or select the acceleration of the target simulated vehicle as a second acceleration according to a second conservative probability; wherein the sum of the second aggressive probability and the second conservative probability is 1, the second aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle, and the second acceleration is less than zero.

[0014] In some embodiments, the determining module is further configured to: determine a first travel time corresponding to the target simulated vehicle, wherein the first travel time is the time it takes for the target simulated vehicle to travel from its current position to the stop line position of the simulated lane at its current speed; when the current color is red and the current countdown value is a first countdown value, if the first travel time is less than or equal to the first countdown value, determine a second difference between the first countdown value and the first travel time; when the second difference is less than or equal to a preset red light lag margin threshold, select the acceleration of the target simulated vehicle according to a third aggressive probability. The third acceleration, or the acceleration of the target simulated vehicle selected according to the third conservative probability, is the fourth acceleration; wherein the sum of the third aggressive probability and the third conservative probability is 1, and the third aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle; both the third acceleration and the fourth acceleration are less than zero; the absolute value of the third acceleration is less than the absolute value of the fourth acceleration; when the target simulated vehicle is traveling with the third acceleration, when the target simulated vehicle reaches the stop line position of the simulated lane, the speed of the target simulated vehicle is greater than a preset comfort speed threshold.

[0015] In some embodiments, the third acceleration is positively correlated with the aggressiveness parameter of the simulated driver; the absolute value of the third acceleration is less than or equal to the absolute value of the maximum deceleration of the target simulated vehicle, and the absolute value of the third acceleration is less than or equal to the absolute value of the target uniform deceleration of the target simulated vehicle, wherein the target uniform deceleration refers to the uniform deceleration adopted by the target simulated vehicle when it travels from the current position to the stop line position with the current speed as the initial speed, the first countdown value as the travel time.

[0016] In some embodiments, the determining module is further configured to: when the second difference is greater than the red light lag margin threshold, determine the acceleration of the target simulated vehicle as a first vehicle deceleration based on the distance between the current position and the stop line position; wherein, when the target simulated vehicle travels at the first vehicle deceleration, the speed of the target simulated vehicle is zero when it reaches the stop line position.

[0017] In some embodiments, the determining module is further configured to: determine a first travel time corresponding to the target simulated vehicle, wherein the first travel time is the time it takes for the target simulated vehicle to travel from its current position to the stop line position of the simulated lane at its current speed; when the current color is green and the current countdown value is a second countdown value, if the first travel time is greater than the second countdown value, determine a third difference between the first travel time and the second countdown value; when the third difference is less than or equal to a preset green light advance margin threshold, select the acceleration of the target simulated vehicle as a fifth acceleration according to a fourth aggressive probability, or according to a fourth conservative probability. The acceleration of the target simulated vehicle is selected as the sixth acceleration based on probability; wherein the sum of the fourth aggressive probability and the fourth conservative probability is 1, and the fourth aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle; the fifth acceleration is greater than zero, and the sixth acceleration is less than zero; the fifth acceleration is positively correlated with the aggressiveness parameter of the simulated driver; the fifth acceleration is less than or equal to the maximum acceleration of the target simulated vehicle; when the third difference is greater than the green light advance margin threshold, the acceleration of the target simulated vehicle is determined as the second vehicle deceleration based on the distance between the current position and the stop line position.

[0018] In some embodiments, the determining module is further configured to: determine a first travel time corresponding to the target simulated vehicle, wherein the first travel time is the time it takes for the target simulated vehicle to travel from its current position to the stop line position of the simulated lane at its current speed; when the current color is green and the current countdown value is a second countdown value, if the first travel time is less than or equal to the second countdown value, determine a fourth difference between the second countdown value and the first travel time; when the fourth difference is less than or equal to a preset green light lag margin threshold, select the target simulated vehicle according to a fifth aggressive probability. The acceleration of the real vehicle is the seventh acceleration, or the acceleration of the target simulated vehicle is selected as zero according to the fifth conservative probability; wherein, the sum of the fifth aggressive probability and the fifth conservative probability is 1, the fifth aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle; the seventh acceleration is greater than zero; the seventh acceleration is positively correlated with the aggressiveness parameter of the simulated driver; the seventh acceleration is less than or equal to the maximum acceleration of the target simulated vehicle; when the fourth difference is greater than the green light lag margin threshold, the acceleration of the target simulated vehicle is determined to be zero.

[0019] In some embodiments, the apparatus further includes: a historical color acquisition module, configured to acquire the historical color of the simulated traffic light one second before the current moment when the target simulated vehicle stops at the stop line position of the simulated lane; the determination module is further configured to: if the historical color is red and the current color is green, select the start reaction time of the simulated driver corresponding to the target simulated vehicle according to a first acuity probability; the start reaction time is negatively correlated with the acuity parameter of the simulated driver; the first acuity probability is a function value conforming to a normal distribution; and determine that the acceleration of the target simulated vehicle is zero within the start reaction time starting from the current moment, and the acceleration is greater than zero after the start reaction time.

[0020] In some embodiments, the apparatus further includes: a following vehicle determination module, configured to determine other simulated vehicles located in the same simulated lane as the target simulated vehicle, adjacent to the target simulated vehicle, and located in front of the target simulated vehicle as following vehicles when there is at least one other simulated vehicle between the target simulated vehicle and the simulated traffic light; a driving parameter determination module, configured to determine the driving speed and driving acceleration of the following vehicles; a following acceleration determination module, configured to determine the following acceleration of the target simulated vehicle based on the driving speed and the driving acceleration; and the simulation control module, further configured to control the target simulated vehicle to perform autonomous driving simulation on the simulated lane based on the following acceleration.

[0021] This application provides an electronic device, including: a memory for storing executable instructions; and a processor for executing the executable instructions stored in the memory to implement the above-described vehicle simulation control method.

[0022] This application provides a computer program product, which includes a computer program or executable instructions stored in a computer-readable storage medium; wherein, when the processor of an electronic device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the above-mentioned vehicle simulation control method is implemented.

[0023] This application provides a computer-readable storage medium storing executable instructions, which, when executed by a processor, implement the above-described vehicle simulation control method.

[0024] The embodiments of this application have the following beneficial effects: A target simulated vehicle and a simulated traffic light with a countdown timer are displayed on the simulated lanes of the simulated road network; the simulation conditions at the current moment are judged, and if the distance between the target simulated vehicle and the simulated traffic light is less than or equal to a preset reaction line of sight, the acceleration of the target simulated vehicle is determined based on the current color of the simulated traffic light and the current countdown value of the timer, thereby performing autonomous driving simulation based on this acceleration. Thus, during traffic simulation, simulated traffic lights and countdown timers are considered, and the acceleration of the target simulated vehicle is determined based on the current color of the simulated traffic light and the current countdown value of the timer. This allows for an accurate modeling of real-world scenarios and accurate simulation of various decision-making processes when vehicles face countdown timers in the real world, thereby improving the realism and accuracy of the simulation results. Attached Figure Description

[0025] Figure 1 This is a schematic diagram of an optional architecture of the vehicle simulation control system provided in this application embodiment;

[0026] Figure 2 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application;

[0027] Figure 3 This is an optional flowchart illustrating the vehicle simulation control method provided in this application embodiment;

[0028] Figure 4 This is a flowchart illustrating the method provided in this application for determining whether the distance between a target simulated vehicle and a simulated traffic light is less than or equal to a preset reaction line of sight.

[0029] Figure 5 This is a flowchart illustrating the simulation method provided in this application embodiment for a scenario where there are other vehicles between the target simulated vehicle and the simulated traffic light;

[0030] Figure 6 This is a schematic diagram of a countdown timer or second reader for a traffic light provided in an embodiment of this application;

[0031] Figure 7 This is a schematic diagram illustrating the relationship between the countdown reaction line distance of the traffic lights and the reaction line distance of each road entering the road, as provided in the embodiments of this application.

[0032] Figure 8 This is a flowchart illustrating the vehicle's response to the timer when approaching an intersection, as provided in an embodiment of this application.

[0033] Figure 9 This is a flowchart of a vehicle waiting at a red light at a stop line, as provided in an embodiment of this application. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0035] In the following description, references to "some embodiments" refer to a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same or different subsets of all possible embodiments and may be combined with each other without conflict. Unless otherwise defined, all technical and scientific terms used in the embodiments of this application have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiments of this application pertain. The terminology used in the embodiments of this application is for the purpose of describing the embodiments of this application only and is not intended to limit the application.

[0036] This application provides a vehicle simulation control method. This method introduces parameters such as the advance margin threshold and the lag margin threshold of traffic lights to describe the diversity of the simulated driver's perception and reaction when facing changes in the traffic light countdown. This ensures that the vehicle will make a corresponding response in the real world when approaching the traffic light countdown timer at the intersection, thereby making the simulation results more realistic.

[0037] The vehicle simulation control method provided in this application first displays a target simulated vehicle and a simulated traffic light with a countdown timer on a simulated lane of a simulated road network. Then, when the distance between the target simulated vehicle and the simulated traffic light is less than or equal to a preset reaction line of sight, the current color of the simulated traffic light and the current countdown value of the timer are obtained. Next, based on the current color and the current countdown value, the acceleration of the target simulated vehicle is determined. Finally, based on the acceleration, the target simulated vehicle is controlled to perform autonomous driving simulation on the simulated lane. Thus, since the traffic simulation process considers not only other simulated vehicles on the simulated lane of the simulated road network but also simulated traffic lights and countdown timers, determining the acceleration of the target simulated vehicle based on the current color of the simulated traffic light and the current countdown value of the timer can accurately model real-world scenarios. Furthermore, it can accurately simulate various decision-making processes of vehicles facing countdown timers in the real world, thereby improving the realism and accuracy of the simulation results.

[0038] The following describes an exemplary application of the vehicle simulation control device according to embodiments of this application. This vehicle simulation control device is an electronic device used to implement a vehicle simulation control method. The vehicle simulation control device provided in this application embodiment can be implemented as a terminal or as a server. In one implementation, the vehicle simulation control device provided in this application embodiment can be implemented as any terminal with vehicle simulation control function, such as a laptop, tablet, desktop computer, mobile device (e.g., mobile phone, portable music player, personal digital assistant, dedicated messaging device, portable gaming device), intelligent robot, smart home appliance, and intelligent vehicle device. In another implementation, the vehicle simulation control device provided in this application embodiment can also be implemented as a server. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. The terminal and the server can be directly or indirectly connected through wired or wireless communication, which is not limited in this application embodiment. The following will describe an exemplary application of the vehicle simulation control device as a server.

[0039] See Figure 1 , Figure 1 This is a schematic diagram of an optional architecture of the vehicle simulation control system provided in this application embodiment. This application embodiment uses the application of the vehicle simulation control method in simulation control applications as an example for illustration; for instance, it can be applied to microscopic simulation software. In simulation control applications, the method of this application embodiment can simulate driving conditions at a simulated traffic light intersection with a countdown timer.

[0040] In this embodiment, during vehicle simulation control, the terminal 100 can collect control parameters for the current vehicle simulation control. These control parameters include, but are not limited to: parameters of the simulated road network, parameters of the target simulated vehicle, parameters of the simulated driver of the target simulated vehicle, and parameters such as red light advance margin threshold, red light lag margin threshold, green light advance margin threshold, and green light lag margin threshold. The terminal 100 carries the control parameters in a simulation control request and sends the simulation control request to the server 300 via the network 200.

[0041] Server 300 constitutes the server for the simulation control application. After receiving a simulation control request, server 300 parses the request to obtain the control parameters for vehicle simulation control, and renders a road network image corresponding to the simulated road network based on the control parameters. The server 300 then sends the road network image to terminal 100, which displays the simulated lanes of the simulated road network, and displays the target simulated vehicle and simulated traffic lights with countdown timers on the simulated lanes. In some embodiments, server 300 may further include a display device, which can display the simulated lanes of the simulated road network, and display the target simulated vehicle and simulated traffic lights with countdown timers on the simulated lanes.

[0042] When displaying the target simulated vehicle and a simulated traffic light with a countdown timer, the server 300 performs real-time detection of the distances between the target simulated vehicle and other simulated vehicles, as well as between the target simulated vehicle and the simulated traffic light. When the distance between the target simulated vehicle and the simulated traffic light is detected to be less than or equal to a preset reaction line of sight, the server 300 obtains the current color of the simulated traffic light and the current countdown value of the timer; and based on the current color and the current countdown value, determines the acceleration of the target simulated vehicle; based on this acceleration, it controls the target simulated vehicle to perform autonomous driving simulation on the simulated lane. While controlling the target simulated vehicle to perform autonomous driving simulation, the server 300 can send the simulated driving image of the target simulated vehicle to the terminal 100 in real time, and the terminal 100 displays the continuous simulated driving image of the target simulated vehicle on the current interface.

[0043] In other embodiments, the vehicle simulation control method can also be implemented through a terminal, that is, the vehicle simulation control method of this application embodiment is implemented with the terminal as the execution subject. During implementation, the terminal collects the control parameters for this vehicle simulation control, renders and displays the road network image corresponding to the simulated road network based on the control parameters, and simultaneously displays the target simulated vehicle and simulated traffic lights with countdown timers on the simulated lanes of the simulated road network. While displaying the target simulated vehicle and the simulated traffic lights with countdown timers, the terminal can also perform real-time detection of the distance between the target simulated vehicle and other simulated vehicles, and between the target simulated vehicle and the simulated traffic lights. When the distance between the target simulated vehicle and the simulated traffic lights is detected to be less than or equal to a preset reaction line of sight, the terminal obtains the current color of the simulated traffic lights and the current countdown value of the countdown timer; and determines the acceleration of the target simulated vehicle based on the current color and the current countdown value; based on this acceleration, the terminal controls the target simulated vehicle to perform autonomous driving simulation on the simulated lane. While controlling the target simulated vehicle to perform autonomous driving simulation, continuous simulated driving images of the target simulated vehicle can be displayed in real time, i.e., simulated driving video can be displayed.

[0044] The vehicle simulation control method provided in this application embodiment can also be implemented based on a cloud platform and through cloud technology. For example, the server 300 mentioned above can be a cloud server. The cloud server controls the display of a target simulated vehicle and a simulated traffic light with a countdown timer on the simulated lane of the simulated road network. Alternatively, the cloud server determines whether there are other simulated vehicles between the target simulated vehicle and the simulated traffic light, and determines the relationship between the distance between the target simulated vehicle and the simulated traffic light and a preset reaction line of sight. Alternatively, the cloud server obtains the current color of the simulated traffic light and the current countdown value of the timer, and determines the acceleration of the target simulated vehicle based on the current color and the current countdown value. The cloud server controls the target simulated vehicle to perform autonomous driving simulation on the simulated lane.

[0045] In some embodiments, a cloud storage device may also be included, where control parameters for vehicle simulation control can be stored, or where simulated driving videos of autonomous driving simulation can be stored. Thus, when analyzing the vehicle simulation control process, the simulated driving videos can be retrieved from the cloud storage, and the simulation effect (e.g., the realism and accuracy of the simulation) of the vehicle simulation control process can be evaluated based on the simulated driving videos.

[0046] It's important to clarify that cloud technology refers to a hosting technology that unifies hardware, software, and network resources within a wide area network (WAN) or local area network (LAN) to achieve data computation, storage, processing, and sharing. Cloud technology is a collective term for network technologies, information technologies, integration technologies, management platform technologies, and application technologies applied in the cloud computing business model. It can form resource pools, providing flexible and convenient on-demand access. Cloud computing technology will become a crucial support. Backend services of technical network systems require substantial computing and storage resources, such as video websites, image websites, and many portal websites. With the rapid development and application of the internet industry, every item may have its own identification mark in the future, requiring transmission to backend systems for logical processing. Data at different levels will be processed separately, and various industry data will require robust system support, which can only be achieved through cloud computing.

[0047] Figure 2 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Figure 2The illustrated electronic device may be a vehicle simulation control device, which includes at least one processor 310, a memory 350, at least one network interface 320, and a user interface 330. The various components in the vehicle simulation control device are coupled together via a bus system 340. It is understood that the bus system 340 is used to implement communication between these components. In addition to a data bus, the bus system 340 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 2 The general labeled all buses as Bus System 340.

[0048] The processor 310 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0049] User interface 330 includes one or more output devices 331 that enable the presentation of media content, and one or more input devices 332.

[0050] Memory 350 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard disk drives, optical disk drives, etc. Memory 350 may optionally include one or more storage devices physically located remote from processor 310. Memory 350 may include volatile memory or non-volatile memory, or both. Non-volatile memory may be read-only memory (ROM), and volatile memory may be random access memory (RAM). The memory 350 described in this application embodiment is intended to include any suitable type of memory. In some embodiments, memory 350 is capable of storing data to support various operations, examples of which include programs, modules, and data structures, or subsets or supersets thereof, as illustrated below.

[0051] Operating system 351 includes system programs for handling various basic system services and performing hardware-related tasks, such as framework layer, core library layer, driver layer, etc., for implementing various basic business functions and handling hardware-based tasks; network communication module 352 is used to reach other computing devices via one or more (wired or wireless) network interfaces 320, exemplary network interfaces 320 include: Bluetooth, WiFi, and Universal Serial Bus (USB), etc.; input processing module 353 is used to detect and translate one or more user inputs or interactions from one or more input devices 332.

[0052] In some embodiments, the apparatus provided in this application may be implemented in software. Figure 2 A vehicle simulation control device 354 stored in memory 350 is shown. This vehicle simulation control device 354 can be a vehicle simulation control device in an electronic device, and can be software in the form of programs and plug-ins, including the following software modules: display module 3541, acquisition module 3542, determination module 3543, and simulation control module 3544. These modules are logically connected and can therefore be arbitrarily combined or further separated according to the functions they implement. The functions of each module will be described below.

[0053] In other embodiments, the apparatus provided in this application can be implemented in hardware. As an example, the apparatus provided in this application can be a processor in the form of a hardware decoding processor, which is programmed to execute the vehicle simulation control method provided in this application. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0054] The vehicle simulation control methods provided in the embodiments of this application can be executed by a vehicle simulation control device, which can be a terminal or a server. That is, the vehicle simulation control methods in the embodiments of this application can be executed by a terminal, or by a server, or by interaction between a terminal and a server.

[0055] See Figure 3 , Figure 3 This is an optional flowchart illustrating the vehicle simulation control method provided in this application embodiment. The following will be combined with... Figure 3 The steps shown will be explained. It should be noted that... Figure 3 The vehicle simulation control method in this example is illustrated by using a server as the execution entity.

[0056] Step S301: Display the target simulated vehicle and simulated traffic lights with countdown timers on the simulated lanes of the simulated road network.

[0057] In this embodiment, the simulated road network refers to a network of interconnected roads within a certain area, simulated using computer technology. It can also be called a simulated map and can be used for simulation testing. Within a virtual city, the network of roads is called the urban road network, which displays the roads of the virtual city used for simulation testing. It is understood that the simulated road network in this embodiment can be a planar map or a bird's-eye view, etc.

[0058] The target simulated vehicle can be the target control vehicle in an autonomous driving simulation. When a user needs to simulate the decision-making algorithm of the target simulated vehicle using a simulated road network in a simulated traffic environment, the user can call the simulation software (a simulation control application) running on the terminal to build the simulated traffic environment. When building the simulated traffic environment, the terminal can display the simulation interface on the monitor.

[0059] In some embodiments, a configuration interface can also be displayed on the current interface of the terminal (i.e., the simulation interface). This configuration interface displays configuration controls for inputting control parameters. Users can input the control parameters for setting the simulated traffic environment according to the actual needs of the vehicle simulation control, using the configuration controls displayed on the configuration interface. Then, based on the user-input control parameters, the simulated road network and the target simulated vehicle can be determined. These control parameters include, but are not limited to: parameters of the simulated road network, parameters of the target simulated vehicle, parameters of the simulated driver of the target simulated vehicle, and parameters such as red light advance margin threshold, red light lag margin threshold, green light advance margin threshold, and green light lag margin threshold. During vehicle simulation control, the terminal can include the control parameters in a simulation control request and send the request to the server. The simulation control request is used to request the server to implement the vehicle simulation control.

[0060] In this embodiment, after receiving a simulation control request, the server can parse the request to obtain control parameters. Based on these parameters, it determines the simulated road network, different simulated lanes, and target simulated vehicles. Furthermore, it simulates multiple other vehicles existing within the simulated road network at certain speeds and congestion densities. Based on this determined information, a macroscopic road network map is rendered. This macroscopic road network map describes the relationship between macroscopic traffic capacity, traffic density, and vehicle speed within the simulated network. When building different simulated traffic environments, users can select a suitable target macroscopic basic map from several macroscopic road network maps provided by the simulation system, based on actual simulation requirements.

[0061] In the macroscopic road network map corresponding to the simulated road network, simulated traffic lights with countdown timers are also simulated on the simulated lanes. The colors of the simulated traffic lights cycle according to the pattern of green->yellow->red->green, and the countdown timers count down for red and green lights for a certain duration. The target simulated vehicle travels in the current simulated lane, and the intersection of this simulated lane also includes simulated traffic lights with countdown timers. In this embodiment, the intersection of the simulated lane can be any intersection such as a crossroads, a three-way intersection, or a T-junction. Accordingly, the countdown durations for red and green lights of the simulated traffic lights are different for different intersections. In some embodiments, at different types of intersections, the simulated traffic lights can have left-turn indicator lights for left-turning vehicles, straight-ahead indicator lights for straight-ahead vehicles, and right-turn indicator lights for right-turning vehicles. The countdown durations of the indicator lights corresponding to different types of vehicles are also different. To make the vehicle simulation control process more realistic and better match the real road network, different types of simulated traffic lights can be set for different types of intersections, and different countdown durations can be set accordingly.

[0062] Step S302: When the distance between the target simulated vehicle and the simulated traffic light is less than or equal to the preset reaction line of sight, obtain the current color of the simulated traffic light and the current countdown value of the countdown timer.

[0063] It should be noted that, in the embodiments of this application, when driving in a simulated lane with simulated traffic lights having a countdown timer, the lane-changing behavior of the target simulated vehicle can be disregarded. That is, the target simulated vehicle drives in the current simulated lane until it passes through the intersection with simulated traffic lights in that simulated lane.

[0064] The preset reaction distance refers to the line-of-sight distance at which the simulated driver of the target vehicle can observe the simulated traffic lights and countdown timer. The preset reaction distance can include the traffic light reaction distance and the countdown reaction distance. The traffic light reaction distance is the distance at which the simulated driver can observe the color of the traffic light, and the countdown reaction distance is the distance at which the simulated driver can observe the countdown value on the countdown timer. Typically, the traffic light reaction distance is greater than or equal to the countdown reaction distance. That is, while the vehicle is in motion, the simulated driver can usually see the color of the traffic light first, and then see the countdown value on the countdown timer.

[0065] The preset reaction distance can be determined based on at least one of the following parameters: vehicle attribute parameters of the target simulated vehicle, driver attribute parameters of the simulated driver corresponding to the target simulated vehicle, and environmental parameters of the simulated road network. Vehicle attribute parameters include, but are not limited to: vehicle model and vehicle age; driver attribute parameters include, but are not limited to: driver age, gender, and driving experience; environmental parameters include, but are not limited to: city, region, current road conditions, road environment, intersection environment, weather conditions, and time (day or night).

[0066] The preset reaction sight distance varies under different parameters. In implementation, an inherent parameter can be provided for each simulated lane, and each simulated vehicle has a sensitivity coefficient, which can be determined based on the aforementioned vehicle attribute parameters, driver attribute parameters, and environmental parameters of the simulated road network. After obtaining the sensitivity coefficient of the target simulated vehicle, the product of the sensitivity coefficient and the inherent parameter of the simulated lane is determined as the preset reaction sight distance. In this embodiment, the sensitivity coefficient of the target simulated vehicle reflects its sensitivity to the countdown values ​​on the simulated traffic lights and countdown timers. The higher the sensitivity of the target simulated vehicle, the larger the sensitivity coefficient, and the larger the preset reaction sight distance; conversely, the lower the sensitivity of the target simulated vehicle, the smaller the sensitivity coefficient, and the smaller the preset reaction sight distance. In other words, the higher the sensitivity of the target simulated vehicle, the farther away the simulated driver can observe the countdown values ​​on the simulated traffic lights and countdown timers; the lower the sensitivity of the target simulated vehicle, the closer the simulated driver can observe the countdown values ​​on the simulated traffic lights and countdown timers.

[0067] In other embodiments, the current color of the simulated traffic light and the current countdown value of the countdown timer can be obtained when there are no other simulated vehicles between the target simulated vehicle and the simulated traffic light, and the distance between the target simulated vehicle and the simulated traffic light is less than or equal to a preset reaction line of sight.

[0068] Here, while the target simulated vehicle is traveling on the simulated lane, it can detect whether there are other simulated vehicles in front of it. In other words, it determines whether there are other simulated vehicles between the target simulated vehicle and the simulated traffic light. Simultaneously, it monitors the distance between the target simulated vehicle and the simulated traffic light in real time. When it detects that there are no other simulated vehicles between the target simulated vehicle and the simulated traffic light, and the distance between the target simulated vehicle and the simulated traffic light is less than or equal to a preset reaction line of sight, it acquires the current color of the simulated traffic light and the current countdown value of the countdown timer.

[0069] In this embodiment of the application, when there are no other simulated vehicles between the target simulated vehicle and the simulated traffic light, and the distance between the target simulated vehicle and the simulated traffic light is less than or equal to the preset reaction line of sight, it is necessary to simulate the reaction process of the target simulated vehicle to the simulated traffic light with a countdown timer. Therefore, the current color of the simulated traffic light and the current countdown value of the countdown timer are obtained, so as to realize the subsequent simulated driving process based on the current color of the simulated traffic light and the current countdown value of the countdown timer.

[0070] Step S303: Determine the acceleration of the target simulated vehicle based on the current color and the current countdown value.

[0071] Here, when the simulated driver of the target vehicle perceives the current color of the simulated traffic light and the current countdown value of the timer, they need to take certain driving measures based on the current color and countdown value to drive the target vehicle, that is, control the target vehicle to travel within the simulated road network. Therefore, it is necessary to determine the acceleration of the target vehicle, and then control the target vehicle's movement based on the determined acceleration.

[0072] In this embodiment, the acceleration of the target simulated vehicle includes negative, positive, and zero values. When the acceleration is negative, it indicates that the target simulated vehicle needs to decelerate; when the acceleration is positive, it indicates that the target simulated vehicle needs to accelerate; and when the acceleration is zero, it indicates that the target simulated vehicle needs to maintain its current constant speed.

[0073] In some embodiments, since the acceleration at each moment can be determined in real time, it is sufficient to determine only the acceleration at the current moment, thereby enabling autonomous driving simulation based on the acceleration at the current moment. At the next moment, the acceleration at the next moment can be determined, and the autonomous driving simulation can continue according to the acceleration at the next moment.

[0074] In other embodiments, along with determining the acceleration, a corresponding control duration can also be determined. This control duration characterizes the duration of acceleration at that acceleration. Thus, during autonomous driving simulation, the vehicle can continue driving according to the control duration and acceleration. When the control duration expires, the acceleration of the target simulated vehicle is determined again, thereby continuing the autonomous driving simulation control.

[0075] Step S304: Based on acceleration, control the target simulated vehicle to perform autonomous driving simulation on the simulated lane.

[0076] In this embodiment, after determining the acceleration, the target simulated vehicle is controlled to drive automatically based on the determined acceleration at the current speed. If the determined acceleration is negative, the target simulated vehicle is controlled to decelerate; if the determined acceleration is positive, the target simulated vehicle is controlled to accelerate; if the determined acceleration is zero, the target simulated vehicle is controlled to travel at a constant speed at the current speed.

[0077] During autonomous driving simulation, continuous simulated driving images can be acquired to form a simulated driving video, which is then displayed on the current interface of the terminal. When displaying the simulated driving video, either a first-person perspective or a third-person perspective can be provided. The first-person perspective refers to the viewpoint of the video image seen by the simulated driver driving the target simulated vehicle in the simulated lane. The third-person perspective refers to the viewpoint observed from outside the target simulated vehicle (e.g., from the top of the target simulated vehicle, at a first specific distance in front of the target simulated vehicle, or at a second specific distance behind the target simulated vehicle).

[0078] In some embodiments, after obtaining the simulated driving video, the video can be stored, and the simulation effect (e.g., the realism and accuracy of the simulated control process) of the vehicle simulation can be evaluated based on the video to obtain an evaluation result. After obtaining the evaluation result, the control parameters can be corrected to achieve a more realistic autonomous driving simulation of the target vehicle. During implementation, if the evaluation result indicates that the realism and accuracy of the current autonomous driving simulation is less than a preset threshold, the adjustment amount of the control parameters can be determined according to a method corresponding to the control parameter correction strategy. Then, based on the adjustment amount, the control parameters can be increased or decreased to obtain new control parameters, and the autonomous driving simulation can be repeated based on the new control parameters.

[0079] The vehicle simulation control method provided in this application displays a target simulated vehicle and a simulated traffic light with a countdown timer on a simulated lane in a simulated road network. It judges the simulation conditions at the current moment. If there are no other simulated vehicles between the target simulated vehicle and the simulated traffic light, and the distance between the target simulated vehicle and the simulated traffic light is less than or equal to a preset reaction line of sight, the acceleration of the target simulated vehicle is determined based on the current color of the simulated traffic light and the current countdown value of the timer. Autonomous driving simulation is then performed based on this acceleration. Thus, during traffic simulation, not only are other simulated vehicles on the simulated lane in the simulated road network considered, but also simulated traffic lights and countdown timers. The acceleration of the target simulated vehicle is determined based on the current color of the simulated traffic light and the current countdown value of the timer, thereby accurately modeling real-world scenarios and accurately simulating various decision-making processes of vehicles facing countdown timers in the real world, thus improving the realism and accuracy of the simulation results.

[0080] In some embodiments, a method is provided for determining whether the distance between a target simulated vehicle and a simulated traffic light is less than or equal to a preset reaction line of sight. Figure 4 This is a flowchart illustrating a method for determining whether the distance between a target simulated vehicle and a simulated traffic light is less than or equal to a preset reaction line of sight, as provided in an embodiment of this application. Figure 4 As shown, the method includes the following steps:

[0081] Step S401: The server obtains the preset reaction line of sight corresponding to the target simulation vehicle.

[0082] Here, the preset reaction line of sight refers to the line-of-sight distance at which the simulated driver of the target vehicle can observe the simulated traffic lights and countdown timer. The preset reaction line of sight can include the traffic light reaction line of sight and the countdown timer reaction line of sight. The traffic light reaction line of sight is the distance at which the simulated driver can observe the color of the traffic light, and the countdown timer reaction line of sight is the distance at which the simulated driver can observe the countdown value on the countdown timer. The traffic light reaction line of sight is greater than or equal to the countdown timer reaction line of sight.

[0083] The preset reaction line of sight can be determined based on at least one of the following parameters: vehicle attribute parameters of the target simulated vehicle, driver attribute parameters of the simulated driver corresponding to the target simulated vehicle, and environmental parameters of the simulated road network. The preset reaction line of sight varies depending on the parameters.

[0084] In some embodiments, the scheme for obtaining the preset reaction line of sight in step S401 can also be achieved through the following steps S4011 to S4014 (not shown in the figure):

[0085] Step S4011: Obtain the vehicle attribute parameters of the target simulation vehicle, the driver attribute parameters of the simulation driver corresponding to the target simulation vehicle, and the environmental parameters of the simulation road network.

[0086] Here, vehicle attribute parameters include, but are not limited to: vehicle model and vehicle age; driver attribute parameters include, but are not limited to: driver age, gender and driving experience; environmental parameters include, but are not limited to: city, region, current road conditions, road environment, intersection environment, weather conditions and time (day or night), etc.

[0087] Step S4012: Determine the sensitivity coefficient of the target simulation vehicle based on vehicle attribute parameters, driver attribute parameters, and environmental parameters.

[0088] Here, each simulated vehicle has a sensitivity coefficient, which is determined based on the aforementioned vehicle attribute parameters, driver attribute parameters, and environmental parameters of the simulated road network. The sensitivity coefficient of the target simulated vehicle reflects its responsiveness to the simulated traffic lights and countdown timers. The higher the responsiveness of the target simulated vehicle, the larger the sensitivity coefficient, and the greater the preset reaction distance; conversely, the lower the responsiveness of the target simulated vehicle, the smaller the sensitivity coefficient, and the smaller the preset reaction distance. In other words, the higher the responsiveness of the target simulated vehicle, the farther away the simulated driver can observe the simulated traffic lights and countdown timers; the lower the responsiveness of the target simulated vehicle, the closer the simulated driver needs to be to observe the simulated traffic lights and countdown timers.

[0089] Step S4013: Obtain the inherent road parameters corresponding to the simulated lane.

[0090] Here, each simulated lane has a fixed road parameter, which is determined at the start of the vehicle simulation control. Therefore, the inherent road parameters of each simulated lane remain unchanged during the vehicle simulation control process. The fixed road parameters can be determined based on the environmental parameters of the simulated road network; different simulated lanes have different fixed road parameters.

[0091] Step S4014: Determine the preset reaction sight distance based on the road's inherent parameters and the sensitivity coefficient.

[0092] Here, the product between the sensitivity coefficient of the target simulated vehicle and the inherent road parameters of the simulated lane can be calculated, and this product can be determined as the preset reaction sight distance.

[0093] In this embodiment, since the preset reaction sight distance can include the traffic light reaction sight distance and the countdown reaction sight distance, the inherent road parameters of the traffic lights and the inherent road parameters of the countdown for each simulated lane can be provided. That is, the fixed road parameters of each simulated lane include the inherent road parameters of the traffic lights and the inherent road parameters of the countdown. The values ​​of the inherent road parameters of the traffic lights and the inherent road parameters of the countdown can be the same or different. When the values ​​of the inherent road parameters of the traffic lights and the inherent road parameters of the countdown are different, the inherent road parameters of the traffic lights are greater than the inherent road parameters of the countdown. A first product between the inherent road parameters of the traffic lights and the sensitivity coefficient can be calculated, and this first product is determined as the traffic light reaction sight distance. A second product between the inherent road parameters of the countdown and the sensitivity coefficient can also be calculated, and this second product is determined as the countdown reaction sight distance.

[0094] In step S402, the server determines whether the distance between the target simulated vehicle and the simulated traffic light is less than or equal to the traffic light's reaction line of sight.

[0095] If the judgment result is yes, then step S403 is executed; if it is no, then the target simulated vehicle is controlled to drive autonomously according to the car-following algorithm.

[0096] In step S403, the server continuously detects the distance between the target simulated vehicle and the simulated traffic lights.

[0097] Here, continuous detection means that after detecting the distance between the simulated vehicle and the simulated traffic light at the current moment, the distance between the simulated vehicle and the simulated traffic light is detected again at the next moment. The time interval between two detections is less than a time threshold. This ensures accurate detection of the distance between the simulated vehicle and the simulated traffic light, and because the simulated vehicle is constantly moving, its position can be monitored in real time.

[0098] In step S404, the server determines whether the distance between the target simulated vehicle and the simulated traffic light is less than or equal to the countdown reaction line of sight.

[0099] If the judgment result is yes, then the distance between the target simulated vehicle and the simulated traffic light is determined to be less than or equal to the preset reaction line of sight. If the judgment result is no, then return to step S403 to continue distance detection.

[0100] In this embodiment, the distance between the target simulated vehicle and the simulated traffic light is determined to be less than or equal to the traffic light's reaction line of sight, and also less than or equal to the countdown reaction line of sight. In other words, the distance between the target simulated vehicle and the simulated traffic light must be simultaneously less than or equal to both the traffic light's reaction line of sight and the countdown reaction line of sight.

[0101] Since the countdown reaction line of sight is usually less than or equal to the traffic light reaction line of sight, in some embodiments, it is also possible to determine only whether the distance between the target simulated vehicle and the simulated traffic light is less than or equal to the countdown reaction line of sight. If the determination result is yes, it is directly determined that the distance between the target simulated vehicle and the simulated traffic light is less than or equal to the preset reaction line of sight. In this way, one judgment process is reduced, which can improve the efficiency of detection.

[0102] In some embodiments, the step S303 above, which determines the acceleration of the target simulated vehicle based on the current color and the current countdown value, may include at least one of the following simulation types:

[0103] Simulation Type 1: When the target simulated vehicle approaches an intersection near the simulated lane, the simulated traffic light is red, and the current countdown timer value is less than the time it would take for the target simulated vehicle to reach the stop line of the simulated lane at its current speed. In this case, acceleration simulation can be performed by following steps S11 to S14 (not shown in the figure) to determine the acceleration of the target simulated vehicle.

[0104] In the implementation process, simulation type one includes two cases. The first case is: the current countdown value of the countdown timer is relatively small, that is, the difference between the time it takes for the target simulated vehicle to travel to the stop line position of the simulated lane at the current speed and the current countdown value of the countdown timer is relatively large. In this case, acceleration simulation can be performed through the following steps S11 to S13.

[0105] Step S11: Determine the first travel time corresponding to the target simulation vehicle. The first travel time is the time it takes for the target simulation vehicle to travel from the current position to the stop line position of the simulation lane at the current speed.

[0106] Here, the distance between the current position and the stop line of the simulated lane can be calculated, and then the calculated distance can be divided by the current speed to obtain the first travel time.

[0107] Step S12: When the current color is red and the current countdown value is the first countdown value, if the first travel time is greater than the first countdown value, determine the first difference between the first travel time and the first countdown value.

[0108] Here, if the first driving time is greater than the first countdown value, it means that if the simulated driver drives at a constant speed to the stop line position of the simulated lane (i.e., the intersection), the red light countdown has ended and the simulated traffic light has turned green.

[0109] Step S13: When the first difference is greater than the preset red light advance margin threshold, select the acceleration of the target simulated vehicle as the first acceleration according to the first aggressive probability, or select the acceleration of the target simulated vehicle as zero according to the first conservative probability.

[0110] Here, when the first difference is greater than the preset red light advance margin threshold, it indicates that if the simulated driver travels at a constant speed to the stop line of the simulated lane, the time it takes for the red light to turn green is relatively long, exceeding the red light advance margin threshold. In other words, if the simulated driver travels at a constant speed to the stop line of the simulated lane, the initial travel time is significantly longer than the first countdown time of the red light, exceeding the red light advance margin threshold. In this case, the behavior of some drivers who attempt to run a red light—that is, high-speed driving—can be simulated to try and pass through the intersection just as the red light turns green.

[0111] The sum of the first aggressive probability and the first conservative probability is 1. The first aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle. The larger the aggressiveness parameter of the simulated driver, the more aggressive the simulated driver is, and the larger the first aggressive probability is. In this embodiment, the first acceleration is greater than zero.

[0112] In this embodiment of the application, before performing vehicle simulation control, the electronic device can generate a random floating-point number K greater than or equal to 0 and less than or equal to 1 for each virtual vehicle in the simulated road network. i (i.e., the degree of radicalism parameter), K i A value of 0 indicates that the simulated driver for the corresponding simulated vehicle i is the most conservative. i A value of 1 indicates that the simulated driver of the corresponding simulated vehicle i is the most aggressive.

[0113] In this embodiment, the first acceleration is positively correlated with the aggression parameter of the simulated driver; the greater the aggression parameter of the simulated driver, the greater the first acceleration. However, the first acceleration is less than or equal to the maximum acceleration of the target simulated vehicle, and the first acceleration is less than the target uniform acceleration of the target simulated vehicle.

[0114] Here, maximum acceleration refers to the maximum acceleration that the target simulated vehicle can achieve, and the maximum acceleration is related to the vehicle model of the target simulated vehicle. Target uniform acceleration refers to the uniform acceleration used by the target simulated vehicle when it travels from its current position to the stop line position, with the current speed as the initial speed, the first countdown value as the travel time.

[0115] The second case of simulation type one is: if the difference between the time it takes for the target simulated vehicle to travel to the stop line of the simulated lane at the current speed and the current countdown value of the countdown timer is small, then acceleration simulation can be performed through the following step S14.

[0116] Step S14: When the first difference is less than or equal to the red light advance margin threshold, the acceleration of the target simulated vehicle is selected as zero according to the second aggressive probability, or the acceleration of the target simulated vehicle is selected as the second acceleration according to the second conservative probability.

[0117] Here, when the first difference is less than or equal to the red light advance margin threshold, it indicates that if the simulated driver drives at a constant speed to the stop line of the simulated lane, the red light will turn green in a short time. If the driver accelerates, he will need to stop at the intersection and wait for the red light, which is obviously a driving method that many real drivers are unwilling to adopt. Therefore, the driver can drive at a constant speed or decelerate.

[0118] In this embodiment, the sum of the second aggressive probability and the second conservative probability is 1. The second aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle. The larger the aggressiveness parameter of the simulated driver, the more aggressive the simulated driver is, and the larger the second aggressive probability is. The second acceleration can be less than zero, that is, under the second conservative probability, the simulated driver chooses to decelerate.

[0119] Simulation Type 2: When the target simulated vehicle is approaching the intersection of the simulated lane, the simulated traffic light is red, and the current countdown value of the countdown timer is greater than or equal to the time it takes for the target simulated vehicle to travel to the stop line of the simulated lane at the current speed. In this case, when determining the acceleration of the target simulated vehicle, acceleration simulation can be performed through the following steps S21 to S24 (not shown in the figure).

[0120] In the implementation process, simulation type two includes two cases. The first case is: if the difference between the current countdown value of the countdown timer and the time it takes for the target simulated vehicle to travel to the stop line position of the simulated lane at the current speed is relatively small, then acceleration simulation can be performed through the following steps S21 to S23.

[0121] Step S21: Determine the first travel time corresponding to the target simulation vehicle. The first travel time is the time it takes for the target simulation vehicle to travel from the current position to the stop line position of the simulation lane at the current speed.

[0122] Here, the distance between the current position and the stop line of the simulated lane can be calculated, and then the calculated distance can be divided by the current speed to obtain the first travel time.

[0123] Step S22: When the current color is red and the current countdown value is the first countdown value, if the first travel time is less than or equal to the first countdown value, determine the second difference between the first countdown value and the first travel time.

[0124] Here, if the first driving time is less than or equal to the first countdown value, it means that if the simulated driver drives at a constant speed to the stop line position of the simulated lane (i.e., the intersection), the red light countdown has not yet ended, and the simulated traffic light is still red.

[0125] Step S23: When the second difference is less than or equal to the preset red light lag margin threshold, the acceleration of the target simulated vehicle is selected as the third acceleration according to the third aggressive probability, or the acceleration of the target simulated vehicle is selected as the fourth acceleration according to the third conservative probability.

[0126] Here, when the second difference is less than or equal to the preset red light lag margin threshold, it indicates that if the simulated driver travels at a constant speed to the stop line of the simulated lane, the remaining red light time is relatively short, and the remaining red light time is less than or equal to the red light lag margin threshold. In other words, if the simulated driver travels at a constant speed to the stop line of the simulated lane, the difference between the red light countdown timer and the initial travel time is less than or equal to the red light lag margin threshold. In this case, it is necessary to slow down.

[0127] The sum of the third aggressive probability and the third conservative probability is 1. The third aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle. The larger the aggressiveness parameter of the simulated driver, the more aggressive the simulated driver is, and the larger the third aggressive probability is. In the embodiments of this application, both the third acceleration and the fourth acceleration are less than zero; the absolute value of the third acceleration is less than the absolute value of the fourth acceleration; that is, when the simulated driver uses the third acceleration to decelerate, the degree of deceleration is higher than the degree of deceleration when the simulated driver uses the fourth acceleration.

[0128] In this embodiment, when the target simulated vehicle is traveling at a third acceleration, its speed exceeds a preset comfort speed threshold when it reaches the stop line of the simulated lane. The comfort speed threshold refers to the speed at which driving below this threshold negatively impacts driving comfort, similar to parking. The comfort speed threshold is related to the attribute parameters of the simulated driver.

[0129] In some embodiments, the third acceleration is positively correlated with the aggressiveness parameter of the simulated driver; the absolute value of the third acceleration is less than or equal to the absolute value of the maximum deceleration of the target simulated vehicle, and the absolute value of the third acceleration is less than or equal to the absolute value of the target uniform deceleration of the target simulated vehicle, the target uniform deceleration being the uniform deceleration adopted by the target simulated vehicle when it travels from the current position to the stop line position with the current speed as the initial speed, the first countdown value as the travel time.

[0130] The second case of simulation type two is: if the difference between the current countdown value of the countdown timer and the time it takes for the target simulated vehicle to travel to the stop line of the simulated lane at the current speed is relatively large, then acceleration simulation can be performed through the following step S24.

[0131] Step S24: When the second difference is greater than the red light lag margin threshold, the acceleration of the target simulated vehicle is determined as the first vehicle deceleration based on the distance between the current position and the stop line position; wherein, when the target simulated vehicle travels according to the first vehicle deceleration, the speed of the target simulated vehicle when it reaches the stop line position is zero.

[0132] Simulation Type 3: When the target simulated vehicle approaches an intersection near the simulated lane, the simulated traffic light is green, and the current countdown timer value is less than the time it would take for the target simulated vehicle to reach the stop line of the simulated lane at its current speed. In this case, acceleration simulation can be performed by following steps S31 to S34 (not shown in the figure) to determine the acceleration of the target simulated vehicle.

[0133] In the implementation process, simulation type three includes two cases. The first case is: the difference between the time it takes for the target simulation vehicle to travel to the stop line position of the simulation lane at the current speed and the current countdown value of the countdown timer is relatively small. Then, acceleration simulation can be performed through the following steps S31 to S33.

[0134] Step S31: Determine the first travel time corresponding to the target simulation vehicle. The first travel time is the time it takes for the target simulation vehicle to travel from the current position to the stop line position of the simulation lane at the current speed.

[0135] Here, the distance between the current position and the stop line of the simulated lane can be calculated, and then the calculated distance can be divided by the current speed to obtain the first travel time.

[0136] Step S32: When the current color is green and the current countdown value is the second countdown value, if the first travel time is greater than the second countdown value, determine the third difference between the first travel time and the second countdown value.

[0137] Here, if the first driving time is greater than the second countdown value, it means that if the simulated driver drives at the current speed to the stop line position of the simulated lane (i.e., the intersection), the green light countdown has ended, and the simulated traffic light has turned into a yellow or red light.

[0138] Step S33: When the third difference is less than or equal to the preset green light advance margin threshold, the acceleration of the target simulated vehicle is selected as the fifth acceleration according to the fourth aggressive probability, or the acceleration of the target simulated vehicle is selected as the sixth acceleration according to the fourth conservative probability.

[0139] Here, when the third difference is less than or equal to the preset green light advance margin threshold, it indicates that if the simulated driver travels at a constant speed to the stop line of the simulated lane, the green light change time is relatively short, less than the green light advance margin threshold. In other words, if the simulated driver travels at a constant speed to the stop line of the simulated lane, the first travel time is less than the second countdown time of the green light, and this extra time is less than or equal to the green light advance margin threshold. At this point, the behavior of some drivers rushing to cross the intersection before the green light changes or turns yellow can be simulated.

[0140] The sum of the fourth aggressive probability and the fourth conservative probability is 1. The fourth aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle. The larger the aggressiveness parameter of the simulated driver, the more aggressive the simulated driver, and the higher the fourth aggressive probability. In this embodiment, the fifth acceleration is greater than zero, and the sixth acceleration is less than zero. That is, if the simulated driver is more aggressive, they will accelerate to run a green light; if the simulated driver is more conservative, they will stop and wait. The fifth acceleration is positively correlated with the aggressiveness parameter of the simulated driver; however, the fifth acceleration is less than or equal to the maximum acceleration of the target simulated vehicle.

[0141] The second case of simulation type three is: if the difference between the time taken for the target simulated vehicle to travel to the stop line of the simulated lane at the current speed and the current countdown value of the countdown timer is relatively large, then acceleration simulation can be performed through the following step S34.

[0142] Step S34: When the third difference is greater than the green light advance margin threshold, the acceleration of the target simulated vehicle is determined to be the deceleration of the second vehicle based on the distance between the current position and the stop line position.

[0143] Here, when the third difference is greater than the green light advance margin threshold, it indicates that if the simulated driver drives at the current constant speed to the stop line position of the simulated lane, the green light change time is relatively long. If the driver accelerates, he will need to stop at the intersection and wait for the red light. He will not be able to accelerate to pass through the intersection before the green light changes. Therefore, he will need to slow down and wait at the intersection for the red light to end before passing through the intersection.

[0144] Simulation Type 4: When the target simulated vehicle approaches an intersection near the simulated lane, the simulated traffic light is green, and the current countdown timer value is greater than or equal to the time it would take for the target simulated vehicle to reach the stop line of the simulated lane at its current speed. In this case, acceleration simulation can be performed by following steps S41 to S44 (not shown in the figure) to determine the acceleration of the target simulated vehicle.

[0145] In the implementation process, simulation type four includes two cases. The first case is: if the difference between the current countdown value of the countdown timer and the time it takes for the target simulated vehicle to travel to the stop line position of the simulated lane at the current speed is relatively small, then acceleration simulation can be performed through the following steps S41 to S43.

[0146] Step S41: Determine the first travel time corresponding to the target simulation vehicle. The first travel time is the time it takes for the target simulation vehicle to travel from the current position to the stop line position of the simulation lane at the current speed.

[0147] Here, the distance between the current position and the stop line of the simulated lane can be calculated, and then the calculated distance can be divided by the current speed to obtain the first travel time.

[0148] Step S42: When the current color is green and the current countdown value is the second countdown value, if the first travel time is less than or equal to the second countdown value, determine the fourth difference between the second countdown value and the first travel time.

[0149] Here, if the first driving time is less than or equal to the second countdown value, it means that if the simulated driver drives at a constant speed to the stop line of the simulated lane, the green light countdown has not yet ended, and the simulated traffic light is still green.

[0150] Step S43: When the fourth difference is less than or equal to the preset green light lag margin threshold, the acceleration of the target simulated vehicle is selected as the seventh acceleration according to the fifth aggressive probability, or the acceleration of the target simulated vehicle is selected as zero according to the fifth conservative probability.

[0151] Here, when the fourth difference is less than or equal to the preset green light lag margin threshold, it indicates that if the simulated driver travels at a constant speed to the stop line of the simulated lane, the remaining green light time is relatively short, and the remaining green light time is less than or equal to the green light lag margin threshold. In other words, if the simulated driver travels at a constant speed to the stop line of the simulated lane, the difference between the green light countdown and the initial travel time is less than or equal to the green light lag margin threshold. At this point, the driver can either accelerate or maintain a constant speed.

[0152] The sum of the fifth aggressive probability and the fifth conservative probability is 1. The fifth aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle. The larger the aggressiveness parameter of the simulated driver, the more aggressive the simulated driver, and the higher the fifth aggressive probability. In this embodiment, the seventh acceleration is greater than zero, meaning that the simulated driver can accelerate through the intersection, making the remaining green light time longer. The seventh acceleration is positively correlated with the aggressiveness parameter of the simulated driver; however, the seventh acceleration is less than or equal to the maximum acceleration of the target simulated vehicle.

[0153] The second case of simulation type four is: if the difference between the current countdown value of the countdown timer and the time it takes for the target simulated vehicle to travel to the stop line of the simulated lane at the current speed is relatively large, then acceleration simulation can be performed through the following step S44.

[0154] Step S44: When the fourth difference is greater than the green light lag margin threshold, the acceleration of the target simulated vehicle is determined to be zero.

[0155] When the fourth difference is greater than the green light lag margin threshold, the simulated driver believes that the remaining time of the green light is long enough, and there is no need to accelerate; a constant speed is sufficient to pass safely.

[0156] Simulation Type 5: The starting situation occurs when the target simulated vehicle stops at the stop line of the simulated lane and waits for the red light to turn green, and the simulated traffic light changes color from red to green. In this starting situation, the acceleration of the target simulated vehicle can be simulated using the following steps S51 to S53 (not shown in the figure).

[0157] Step S51: When the target simulated vehicle stops at the stop line position of the simulated lane, obtain the historical color of the simulated traffic light one second before the current moment.

[0158] Step S52: If the historical color is red and the current color is green, select the start-up reaction time of the simulated driver corresponding to the target simulated vehicle according to the first sensitivity probability; the start-up reaction time is negatively correlated with the sensitivity parameter of the simulated driver; the larger the sensitivity parameter, the smaller the start-up reaction time. The first sensitivity probability is a function value that conforms to a normal distribution.

[0159] Here, the first sharpness probability is also related to the sharpness parameter of the simulated driver. The larger the sharpness parameter of the simulated driver, the more sharp the simulated driver is. In this case, the first sharpness probability for a start reaction time greater than the start reaction time threshold will be less than the sharpness probability threshold, and the first sharpness probability for a start reaction time less than or equal to the start reaction time threshold will be greater than or equal to the sharpness probability threshold.

[0160] Step S53: Determine that the acceleration of the target simulated vehicle is zero during the start-up reaction time starting from the current moment, and that the acceleration is greater than zero after the start-up reaction time.

[0161] Here, during the initial reaction time, the simulated driver did not react to the color change of the traffic light and therefore did not start the vehicle. Only after the initial reaction time did the simulated driver start the vehicle and begin driving.

[0162] In other embodiments, if there are other vehicles between the target simulated vehicle and the simulated traffic light, that is, if the target simulated vehicle is not the first vehicle on the simulated road approaching the simulated traffic light (i.e., there are other vehicles between the target simulated vehicle and the stop line of the simulated traffic light), then the vehicle in front of the target simulated vehicle can be used as the preceding vehicle in the car-following algorithm for car-following operation. Figure 5 This is a flowchart illustrating the simulation method provided in this application embodiment for simulating a target vehicle and a simulated traffic light when other vehicles are present. Figure 5 As shown, the implementation process can be achieved through the following steps:

[0163] Step S501: When there is at least one other simulated vehicle between the target simulated vehicle and the simulated traffic light, the other simulated vehicles that are located in the same simulated lane as the target simulated vehicle, adjacent to the target simulated vehicle, and in front of the target simulated vehicle are identified as following vehicles.

[0164] Step S502: Determine the speed and acceleration of the following vehicle.

[0165] Step S503: Based on the driving speed and driving acceleration, determine the following acceleration of the target simulated vehicle.

[0166] Step S504: Based on the following acceleration, control the target simulation vehicle to perform autonomous driving simulation on the simulation lane.

[0167] In this embodiment, when there is at least one other simulated vehicle between the target simulated vehicle and the simulated traffic light, since the movement of the other simulated vehicles will affect the movement of the target simulated vehicle, a following strategy is adopted to follow the other simulated vehicle in front of the target simulated vehicle until there are no other simulated vehicles between the target simulated vehicle and the simulated traffic light. Then, the method proposed in the above embodiment is used to judge the color of the simulated traffic light and the countdown value of the countdown timer, thereby realizing autonomous driving simulation.

[0168] In other embodiments, when there is at least one other simulated vehicle between the target simulated vehicle and the simulated traffic light, lane changing can also be performed based on a lane changing strategy (if lane changing conditions are met). If, after lane changing, there are no other simulated vehicles between the target simulated vehicle and the simulated traffic light in the new simulated lane, the method proposed in the above embodiments can be used to determine the color of the simulated traffic light and the countdown value of the countdown timer, thereby realizing autonomous driving simulation.

[0169] The following will describe an exemplary application of the embodiments of this application in a real-world application scenario.

[0170] In traffic simulation, when a simulated vehicle arrives at an intersection controlled by a traffic light equipped with a countdown timer, it needs to react to the changes in the countdown timer. How to make the simulated vehicle react in a way that most closely resembles the real world when faced with changes in the countdown timer has become the key to successfully conducting traffic simulations on large-scale road network maps.

[0171] This application proposes a vehicle simulation control method. This method introduces parameters such as the advance margin threshold and the lag margin threshold of traffic lights to describe the diversity of the driver's perception and reaction when facing changes in the countdown of traffic lights. This ensures that the vehicle will make a corresponding response in the real world when approaching the traffic light countdown timer at the intersection, thereby making the simulation results more realistic.

[0172] The algorithm proposed in this application embodiment can be embedded in microscopic simulation software (e.g., the autonomous driving virtual simulation system TAD Sim) to set how a vehicle reacts when it approaches or stops at an intersection with a traffic light countdown timer, especially in virtual city simulations of large-scale urban road networks.

[0173] It should be noted that the countdown timer or countdown timer of the traffic light, such as... Figure 6The device shown is an auxiliary device, not a necessary device as stipulated in national regulations. The purpose of the countdown timer on a traffic light is to remind drivers to pay attention to the transition between traffic lights, allowing them to prepare in advance to start on a green light or stop on a red light. From the driver's perspective, the countdown timer effectively indicates the remaining time to proceed or wait, allowing them to know in advance that the signal is about to change, facilitating correct traffic behavior choices, and reducing anxiety caused by waiting at red lights, thus improving traffic efficiency and reducing start-up delays. However, in reality, when drivers see that the countdown timer is running low, they often seize the last few seconds to accelerate through the intersection, which can easily lead to traffic accidents. If the countdown timer still indicates a lot of time left, drivers may look down at their phones and fail to notice the traffic light transition, resulting in them waiting too long at the stop line after the light turns green. All of these situations affect the efficiency and safety of the intersection.

[0174] In this embodiment, the target simulated vehicle is the first vehicle in front of the simulated traffic light. If it is not the first vehicle (i.e., there are other vehicles between the vehicle and the stop line of the simulated traffic light), the target simulated vehicle will treat the vehicle in front as the preceding vehicle in the car-following algorithm and follow it. That is, the acceleration can be updated according to the scheme and the car-following algorithm of this embodiment, and the smaller of the two can be selected as the actual acceleration used by the target simulated vehicle.

[0175] Using the algorithm in this application embodiment, the target simulated vehicle can update its longitudinal acceleration based on its position (distance from the stop line) and speed. The vehicle's lateral behavior is not considered here, meaning that the vehicle is not considered to be changing lanes at this stage.

[0176] It should be noted that in microscopic simulations, the longitudinal driving behavior of vehicles is determined by car-following algorithms, which generally include a maximum speed and a minimum safe following distance. These represent the maximum speed a vehicle cannot exceed during driving (such as a road speed limit) and the minimum following distance that must be maintained throughout the journey, respectively. In each simulation step of a typical car-following algorithm, the vehicle updates its acceleration based on the position and speed of the vehicle in front. The lateral driving behavior of vehicles in microscopic simulations is described by rule-based lane-changing algorithms. Provided the vehicle intends to change lanes, the distance between the vehicle and both the vehicle in front and the vehicle behind in the target lane should be greater than a certain preset safe distance. A lane-changing operation will only be executed when these safety conditions are met.

[0177] Since there is generally no countdown timer for yellow lights, this application embodiment mainly considers the vehicle's reaction algorithm when the green light countdown is on and the red light countdown is on. First, it considers the vehicle's reaction to the countdown timer when it approaches the intersection controlled by the traffic lights, and then it considers the vehicle's reaction to the countdown timer when it is waiting for the red light at the stop line. These will be explained separately below.

[0178] Regarding the response of the vehicle (i.e., the target simulated vehicle) to the timer as it approaches the intersection:

[0179] First, the countdown timer of the traffic light must be within the driver's reaction sight distance for the driver to react to the countdown. Sight distance generally refers to the maximum distance at which a driver can clearly identify an object, and is generally considered to be related to the driver's age, road alignment, roadside conditions, weather conditions, and the situation in front of the vehicle. Reaction sight distance, on the other hand, is the distance within the driver's sight distance that the driver will react to. For each traffic light's countdown timer at an intersection, since the alignment and roadside conditions of the corresponding entering road vary, a reaction sight distance D can be defined for each entering road. n (i.e., the inherent parameters of the road mentioned above), for each vehicle i traveling on this road, the driver's reaction sight distance D to the countdown of the traffic light ahead is... ni (That is, the countdown reaction distance mentioned above) is the distance from the stop line when the driver can clearly see the countdown timer, such as Figure 7 As shown. Where, D ni With D n The following relationship exists between them (1):

[0180] D ni =D n ·A ci (1).

[0181] In other words, in the inherent parameter D of each road n Based on this, the sensitivity coefficient A for each vehicle is determined. ci There are some adjustments. Each vehicle i can only enter the countdown timer D of the corresponding traffic light. ni Only after the distance range is reached will the driver perceive the numbers on the countdown timer and react accordingly to their changes. Here, the traffic light reflects the line-of-sight distance D. ri (i.e., the above-mentioned traffic light reaction distance) refers to the distance from the stop line when the color of the traffic light can be clearly seen, that is, the reaction distance at which the color of the traffic light can be perceived. Since the distance at which the driver can perceive (clearly see) the numbers on the countdown is definitely not much farther than the distance at which the color of the traffic light can be perceived, it is believed that the following relationship (2) must exist:

[0182] D ni ≤D ri (2).

[0183] It should be noted here that the sensitivity coefficient A c A is a floating-point number between (0, 1). ci This refers to the sensitivity coefficient of vehicle i. (Through A) cThis value represents the driver's level of alertness, with 0 representing the slowest response and 1 representing the most alert response. Drivers will react differently to varying levels of alertness to the diversity of traffic flow. This value is assigned to the vehicle before the simulation begins and does not change as the simulation progresses.

[0184] When the vehicle enters this reaction line of sight D ni Then, it begins to continuously sense and judge the countdown timer of the traffic lights. Here, the sequence of traffic light state changes is assumed to be green -> yellow -> red -> green. That is, vehicle i enters D... ni Then, observe the color status of the traffic lights and the countdown timer, and react accordingly. If there is a change, trigger the corresponding judgment process in this scheme; if the light color does not change, maintain the previous decision. See Scenarios 1 to 3 below for details. Figure 8 .

[0185] Scenario 1: If vehicle i travels at V i Speed ​​in D ri When the traffic light is red, vehicle i slows down and stops, aiming at the stop line. However, during the journey, if it proceeds to point D... ni When the distance was measured, the countdown timer showed a red light and a T. R- When the countdown timer (i.e., the first countdown value mentioned above) ends, vehicle i is at a distance from the stop line D. i At that time, vehicle i with V i The time T before reaching the stop line when traveling at a constant speed i =D i / V i T here i That is, the first travel time mentioned above.

[0186] In one implementation, if T i >T R- This means that the red light had already ended (i.e., turned green) when the vehicle reached the stop line while traveling at a constant speed. That is, there is still (T) after the red light turns green. i -T R- (i.e., the first difference) seconds later, vehicle i reaches the stop line at a constant speed. Theoretically, vehicle i has a certain time leeway to reach the stop line earlier, while ensuring the red light has turned green upon arrival. At this point, a red light advance leeway threshold T1 is introduced, used to compare with T... i With T R- The driver's behavior is described by comparing the difference (time margin). The choice of T1 is not restricted here and can be regarded as a function of the driver's aggressiveness; the more aggressive the driver, the smaller this threshold.

[0187] It should be noted that the driver's aggression level (also known as the aggression parameter) is a floating-point number between (0 and 1), denoted by A. 0 represents the most conservative approach, and 1 represents the most aggressive approach. The vehicle will adopt different driving behaviors based on the varying levels of aggression to reflect the vehicle's versatility. This value is assigned to the vehicle before the simulation begins and does not change as the simulation progresses.

[0188] In some embodiments, for vehicle i, if T exists i -T R- >T 1i (T 1i If the red light advance margin threshold for vehicle i is given, then the driver chooses to accelerate with probability P1 (i.e., the first aggressive probability mentioned above) at a1 (i.e., the first acceleration mentioned above), hoping to further shorten the time T to reach the stop line. i The goal is to cross the stop line as quickly as possible after the red light turns green, and upon reaching the stop line, the light will have turned green again. The driver will then choose to drive at a constant speed to the stop line with a probability of (1-P1) (i.e., the first conservative probability mentioned above). The calculation of P1 is not limited here; it can be set to be related to the driver's aggressiveness, i.e., the more aggressive the driver, the larger P1, and the more likely they are to accelerate through. The calculation of a1 is also not limited here; it can be set to be related to the driver's aggressiveness, i.e., the more aggressive the driver, the greater the acceleration, but a1 ≤ a max+ (a max+ Let a1 be the maximum acceleration that vehicle i can reach. Its calculation is not limited and can be set to be related to the level of aggression and vehicle type; the more aggressive the aggression, the greater the maximum acceleration that can be achieved. x , where a x (i.e., the aforementioned uniform acceleration) is V i Let T be the initial velocity. R- After a while, it drove past D i Distance, the uniform acceleration used to reach the stop line, a x It can be calculated using the following formula (3):

[0189] a x =2*(D i -V i ·T R- ) / T R- 2 (3).

[0190] In some embodiments, for vehicle i, if T i -T R- ≤T 1i ​If the driver perceives the time margin as small enough to warrant acceleration, they can choose to maintain a constant speed with probability P2 (the second aggressive probability mentioned above) and decelerate to the stop line with probability (1-P2) (the second conservative probability mentioned above), thus adopting a more conservative strategy. The calculation of P2 is not limited here; it can be set to be related to the driver's aggressiveness. The more aggressive the driver, the larger P2, and the more likely they are to choose to pass through at a constant speed without decelerating. In other words, when the driver needs to make a judgment here, a P is first calculated, and then the system generates a floating-point random number p′ between (0, 1) and compares it with P. If p′ ≤ P, the condition of "choosing with probability P" is met, and the system enters the corresponding decision branch; otherwise, it enters the (1-P) decision branch.

[0191] In another implementation, if T i ≤T R- If the vehicle reaches the stop line at a constant speed when the light is still red, the driver needs to determine how much time (T) it would take to reach the stop line if they appropriately slow down. i Is it possible to avoid coming to a complete stop at the stop line (V=0 at the stop line), or is it possible to simply slow down slightly and pass through the stop line without stopping when the light turns green? For some drivers, slowing down to a stop at the stop line and then accelerating again from zero when the light turns green can be uncomfortable. Therefore, some drivers choose to slow down appropriately so that when they reach the stop line, the light has turned green, and they can still maintain a comfortable speed to pass through. In this case, a red light lag margin threshold T2 is introduced to compare with T... i With T R- The driver's behavior is described by comparing the difference (time margin). The choice of T2 is not limited here; it can be considered a function of the driver's aggressiveness. The more aggressive the driver, the larger this threshold.

[0192] In some embodiments, for vehicle i, if T exists R- -T i ≤T 2i (T 2i This represents the red light lag threshold for vehicle i. From the driver's perspective, the difference between the time it takes to reach the stop line at a constant speed and the remaining time at the red light is small, but a driver must wait at least T before the stop line (because the time to decelerate and stop before the stop line exceeds the time to reach the stop line at a constant speed). R- -T iIt will take 1 second (i.e., the second difference mentioned above) for the color to turn green. The driver will choose not to stop with probability P3 (i.e., the third aggressive probability mentioned above), and will slightly decelerate with deceleration a2 (i.e., the third acceleration mentioned above), hoping that the speed will still not be lower than the minimum comfort speed V when reaching the stop line. cmin (That is, the aforementioned comfort speed threshold; for vehicle i, a speed below this minimum comfort speed V) cmin (Similar to stopping, this negatively impacts driving comfort.) The entire journey can pass the stop line without stopping. Choosing to decelerate and stop at the stop line with a probability of (1-P3) (i.e., the third conservative probability mentioned above) is a relatively conservative strategy. The calculation of P3 is not limited here; it can be set to be related to the driver's aggressiveness. That is, the more aggressive the driver, the larger P3, and the more likely they are to choose to decelerate but not stop to pass the stop line. The calculation of a2 is not limited here; it can be set to be related to the driver's aggressiveness. That is, the more aggressive the driver, the larger the deceleration (absolute value), but |a2|≤|a2|. max- |(The maximum deceleration that vehicle i can withstand, the calculation of which is not limited, can be set to be related to the level of aggression and vehicle type; the more aggressive the aggression, the greater the maximum deceleration that can be withstood.) And |a2|≤|a y |, where a y (i.e., the aforementioned target uniform deceleration) is V i Let T be the initial velocity. R- After a while, it drove past D i The uniform deceleration a used to reach the stop line y It can be calculated using the following formula (4):

[0193] a y =2*(D i -V i ·T R- ) / T R- 2 (4).

[0194] Furthermore, the speed V when reaching the stop line c ≥V cmin That is, not lower than the minimum comfortable speed.

[0195] In some embodiments, for vehicle i, if T R- -T i >T 2i This indicates that the driver has sufficient time to slow down and stop at the stop line. Since the driver should perceive the red light no later than the red light countdown time, the vehicle should already be slowing down and stopping, and can continue to slow down and stop at the stop line.

[0196] In this embodiment of the application, due to the different levels of driver aggression, a more aggressive driver finds that if in D... ri If the light changes from yellow to red while driving towards the inner stop line, the driver should react as if the light were yellow and not react separately when the light changes from yellow to red.

[0197] Scenario 2: If vehicle i is in D ri If the traffic light is green when the distance is detected, normal driving will be selected. If in D ri If the traffic light changes from red to green while the vehicle is traveling towards the inside stop line, the vehicle will use a car-following algorithm to calculate acceleration (re-accelerate). The vehicle continues driving into lane D. ni Distance (D) ni ≤D ri ), and I noticed that the countdown timer showed a green light and a T. G- The countdown ends in seconds (i.e., the second countdown value mentioned above), at which point vehicle i is a distance from the stop line D. i At that time, vehicle i with V i The time T before reaching the stop line when traveling at a constant speed i =D i / V i .

[0198] In one implementation, if T i >T G- This means that the green light had already ended (i.e., turned yellow or red) when the vehicle reached the stop line while traveling at a constant speed. In other words, there is still a (T) period after the green light turns yellow. i -T G- It takes vehicle i 1 second (i.e., the third difference mentioned above) to reach the stop line at a constant speed. Theoretically, vehicle i has a certain time leeway to reach the stop line earlier while still ensuring the light is green upon arrival. At this point, a green light advance leeway threshold T3 is introduced to compare with T... i With T G- The driver's behavior is described by comparing the difference (time margin). The choice of T3 is not limited here; it can be considered a function of the driver's aggressiveness. The more aggressive the driver, the smaller this threshold.

[0199] In some embodiments, for vehicle i, if T exists i -T G- ≤T 3i (T 3i If the driver considers the difference between the time it takes to reach the stop line at a constant speed and the green light countdown time to be small, then the driver can accelerate appropriately to cross the stop line before the green light turns yellow. The driver will choose to accelerate with a3 (the fifth acceleration mentioned above) at probability P4 (the fourth aggressive probability) while releasing the maximum speed V. maxThe restriction allows vehicles to attempt to pass the stop line at a green light even with a slight speeding. Here, the calculation of a3 is not limited; a3 can be set to be related to the driver's aggressiveness—that is, the more aggressive the driver, the greater the acceleration—but a3 ≤ a max+ The strategy is to choose to decelerate and stop at the stop line with a probability of (1-P4) (i.e., the fourth conservative probability mentioned above), which is a conservative strategy. However, even if the maximum deceleration a is used... max- If the driver is still unable to stop before the stop line when the green light turns yellow, they will continue to cross the stop line. The calculation of P4 here is not limited; it can be set to be related to the driver's aggressiveness—the more aggressive the driver, the higher the P4, and the more likely they are to accelerate through.

[0200] In some embodiments, for vehicle i, if T i -T G- >T 3i If the time difference between reaching the stop line at a constant speed and the green light countdown is too large to accelerate and cross the stop line before the green light turns yellow, the driver will choose to slow down and stop at the stop line, i.e., adopt a conservative strategy. However, even if the maximum deceleration 'a' is used... max- If you are still unable to stop before the stop line when the green light turns yellow, you will continue to drive past the stop line.

[0201] In another implementation, if T i ≤T G- If the light is still green when the vehicle reaches the stop line while traveling at a constant speed, it can proceed normally. However, some drivers do not want to wait until the green light countdown reaches 0 before crossing the stop line at a constant speed. Therefore, a green light lag margin threshold T4 is introduced to compare with T. i With T G- The driver's behavior is described by comparing the difference (time margin). The choice of T4 is not limited here; it can be considered a function of the driver's aggressiveness. The more aggressive the driver, the larger this threshold.

[0202] In some embodiments, for vehicle i, if T exists G- -T i ≤T 4i (T G- -T i That is, the fourth difference mentioned above; T 4i Let represent the green light lag margin threshold for vehicle i. The driver believes the time to reach the stop line at a constant speed is too short compared to the remaining countdown time of the green light, necessitating appropriate acceleration. Therefore, with probability P5 (i.e., the fifth aggressive probability mentioned above), the driver chooses to accelerate with a4 (i.e., the seventh acceleration mentioned above), aiming to further shorten the time T to reach the stop line. iThe goal is to cross the stop line as quickly as possible while the light is still green, rather than waiting until the countdown is very low. The driver chooses to drive at a constant speed to the stop line with a probability of (1-P5) (i.e., the fifth conservative probability mentioned above). The calculation of P5 is not limited here; it can be set to be related to the driver's aggressiveness—the more aggressive the driver, the larger P5, and the more likely they are to accelerate through. The calculation of a4 is also not limited here; it can be set to be related to the driver's aggressiveness—the more aggressive the driver, the greater the acceleration—but a4 ≤ a max+ And the speed after acceleration does not exceed the speed limit.

[0203] In some embodiments, for vehicle i, if T G- -T i >T 4i The driver believed that the remaining time on the green light countdown was long enough, and that there was no need to accelerate; a steady speed would suffice for a safe passage.

[0204] Scenario 3: If vehicle i is in D ri When the distance is measured, the traffic light is yellow, or at point D. ri As the vehicle moves toward the stop line, the traffic light changes from green to yellow. Since yellow lights generally do not have a countdown timer, the driver's reaction upon seeing the yellow light illuminate can be simulated using any microscopic simulation method that simulates a vehicle's response to changes in traffic light status.

[0205] Regarding the response of a vehicle to a stopwatch while waiting at a red light:

[0206] This consideration focuses on the reaction of the first vehicle waiting at the stop line at a red light during the countdown. Without a countdown timer, when the light turns green, the driver needs a certain amount of time to perceive and initiate acceleration after seeing the green light illuminate. This time is defined as the time from perceiving the signal to deciding to start (which may include shifting gears to D) to pressing the accelerator pedal. The duration of this time is closely related to the driver's physiological and environmental factors, such as experience, age, physical condition (whether the driver has been drinking or is fatigued), and mood. This time is defined here as the reaction time T. R In the simulation, this manifests as follows: after the green light turns on, vehicle i waiting at the stop line needs to wait for vehicle T. Ri (T Ri This indicates the start-up reaction time of vehicle i, after which the longitudinal speed is updated according to the car-following algorithm (i.e., the start of the vehicle begins). Here, for T... R The calculation is not limited and can be set to be related to the driver's alertness; that is, the less alert the driver, the higher T. R The larger the value, the longer the waiting time at the stop line after the green light turns on.

[0207] Before a stop line at a traffic light equipped with a timer, assuming that for a vehicle waiting at a red light, the time to start moving after the light turns green is T. RA The starting time of a vehicle at a traffic light equipped with a countdown timer is T. RB , here for T R The calculation is not limited; for example, two Ts can be used. R Set to conform to two normal distributions N(u) respectively A v A ) and N(u B v B The function value of ), where u A >u B Moreover, it is related to the driver's level of alertness; the more alert the driver, the better. R The smaller.

[0208] Figure 9 This is a flowchart of a vehicle waiting at a red light at the stop line, as provided in an embodiment of this application. Figure 9 As shown, when equipped with a red light countdown timer, the vehicle's start-up reaction time can be shortened, but there is also a certain probability P6 (i.e., the aforementioned first acute probability) that this start-up reaction time will become longer (T). RC This is used to simulate a situation where, when a red light countdown timer is active, some drivers may look down at their phones and fail to notice the traffic light change, resulting in a longer "dazed" period. The calculation of P6 here is not limited; it can be set to be related to the driver's alertness. That is, the less alert the driver, the higher the P6, and the more likely they are to choose to wait a longer time before starting. Here, T... RC The calculation is not limited; for example, it can be set to conform to a normal distribution N(u) respectively. C v C The function value of ), where u C >u B Moreover, it is related to the driver's level of alertness; the less alert the driver, the more likely they are to experience problems. RC The larger.

[0209] In this embodiment, by setting certain parameter values, the diversity of a vehicle's perception and reaction to changes in the state of a traffic light equipped with a countdown timer when approaching an intersection can be simulated. This ensures that the corresponding reactions are as consistent as possible with the real world. Simultaneously, it simulates the reaction of rushing to a green light and the phenomenon of prolonged waiting time due to inattention at a red light, thereby making the simulation results more realistic. The solution in this embodiment can be used in all traffic simulations involving signalized intersections, such as meso- and micro-level traffic simulations, as well as in autonomous driving simulations and virtual city simulations.

[0210] It is understood that in the embodiments of this application, if the content involves user information, such as control parameters of vehicle simulation control, simulation driving videos, etc., and if it involves data related to user information or enterprise information, when the embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0211] The following continues to describe the exemplary structure of the vehicle simulation control device 354 provided in the embodiments of this application as a software module. In some embodiments, such as Figure 2 As shown, the vehicle simulation control device 354 includes:

[0212] Display module 3541 is used to display a target simulated vehicle and a simulated traffic light with a countdown timer on a simulated lane of a simulated road network; acquisition module 3542 is used to acquire the current color of the simulated traffic light and the current countdown value of the countdown timer when the distance between the target simulated vehicle and the simulated traffic light is less than or equal to a preset reaction line of sight; determination module 3543 is used to determine the acceleration of the target simulated vehicle based on the current color and the current countdown value; simulation control module 3544 is used to control the target simulated vehicle to perform autonomous driving simulation on the simulated lane based on the acceleration.

[0213] In some embodiments, the apparatus further includes: a reaction distance acquisition module, configured to acquire a preset reaction distance corresponding to the target simulated vehicle; the preset reaction distance includes a traffic light reaction distance and a countdown reaction distance; the traffic light reaction distance is greater than or equal to the countdown reaction distance; a detection module, configured to continuously detect the distance between the target simulated vehicle and the simulated traffic light when the distance between the target simulated vehicle and the simulated traffic light is detected to be less than or equal to the traffic light reaction distance; and a condition determination module, configured to determine that the distance between the target simulated vehicle and the simulated traffic light is less than or equal to the preset reaction distance when the distance between the target simulated vehicle and the simulated traffic light is detected to be less than or equal to the countdown reaction distance.

[0214] In some embodiments, the reaction distance acquisition module is further configured to: acquire vehicle attribute parameters of the target simulated vehicle, driver attribute parameters of the simulated driver corresponding to the target simulated vehicle, and environmental parameters of the simulated road network; determine the acuity coefficient of the target simulated vehicle based on the vehicle attribute parameters, the driver attribute parameters, and the environmental parameters; acquire the road inherent parameters corresponding to the simulated lane; and determine the preset reaction distance based on the road inherent parameters and the acuity coefficient.

[0215] In some embodiments, the determining module is further configured to: determine a first travel time corresponding to the target simulated vehicle, wherein the first travel time is the time it takes for the target simulated vehicle to travel from its current position to the stop line position of the simulated lane at its current speed; when the current color is red and the current countdown value is a first countdown value, if the first travel time is greater than the first countdown value, determine a first difference between the first travel time and the first countdown value; when the first difference is greater than a preset red light advance margin threshold, select the acceleration of the target simulated vehicle as a first acceleration according to a first aggressive probability, or select the acceleration of the target simulated vehicle as zero according to a first conservative probability; wherein the sum of the first aggressive probability and the first conservative probability is 1, the first aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle, and the first acceleration is greater than zero.

[0216] In some embodiments, the first acceleration is positively correlated with the aggressiveness parameter of the simulated driver; the first acceleration is less than or equal to the maximum acceleration of the target simulated vehicle, and the first acceleration is less than the target uniform acceleration of the target simulated vehicle, wherein the target uniform acceleration refers to the uniform acceleration adopted by the target simulated vehicle when it travels from the current position to the stop line position with the current speed as the initial speed, the first countdown value as the travel time.

[0217] In some embodiments, the determining module is further configured to: when the first difference is less than or equal to the red light advance margin threshold, select the acceleration of the target simulated vehicle as zero according to a second aggressive probability, or select the acceleration of the target simulated vehicle as a second acceleration according to a second conservative probability; wherein the sum of the second aggressive probability and the second conservative probability is 1, the second aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle, and the second acceleration is less than zero.

[0218] In some embodiments, the determining module is further configured to: determine a first travel time corresponding to the target simulated vehicle, wherein the first travel time is the time it takes for the target simulated vehicle to travel from its current position to the stop line position of the simulated lane at its current speed; when the current color is red and the current countdown value is a first countdown value, if the first travel time is less than or equal to the first countdown value, determine a second difference between the first countdown value and the first travel time; when the second difference is less than or equal to a preset red light lag margin threshold, select the acceleration of the target simulated vehicle according to a third aggressive probability. The third acceleration, or the acceleration of the target simulated vehicle selected according to the third conservative probability, is the fourth acceleration; wherein the sum of the third aggressive probability and the third conservative probability is 1, and the third aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle; both the third acceleration and the fourth acceleration are less than zero; the absolute value of the third acceleration is less than the absolute value of the fourth acceleration; when the target simulated vehicle is traveling with the third acceleration, when the target simulated vehicle reaches the stop line position of the simulated lane, the speed of the target simulated vehicle is greater than a preset comfort speed threshold.

[0219] In some embodiments, the third acceleration is positively correlated with the aggressiveness parameter of the simulated driver; the absolute value of the third acceleration is less than or equal to the absolute value of the maximum deceleration of the target simulated vehicle, and the absolute value of the third acceleration is less than or equal to the absolute value of the target uniform deceleration of the target simulated vehicle, wherein the target uniform deceleration refers to the uniform deceleration adopted by the target simulated vehicle when it travels from the current position to the stop line position with the current speed as the initial speed, the first countdown value as the travel time.

[0220] In some embodiments, the determining module is further configured to: when the second difference is greater than the red light lag margin threshold, determine the acceleration of the target simulated vehicle as a first vehicle deceleration based on the distance between the current position and the stop line position; wherein, when the target simulated vehicle travels at the first vehicle deceleration, the speed of the target simulated vehicle is zero when it reaches the stop line position.

[0221] In some embodiments, the determining module is further configured to: determine a first travel time corresponding to the target simulated vehicle, wherein the first travel time is the time it takes for the target simulated vehicle to travel from its current position to the stop line position of the simulated lane at its current speed; when the current color is green and the current countdown value is a second countdown value, if the first travel time is greater than the second countdown value, determine a third difference between the first travel time and the second countdown value; when the third difference is less than or equal to a preset green light advance margin threshold, select the acceleration of the target simulated vehicle as a fifth acceleration according to a fourth aggressive probability, or according to a fourth conservative probability. The acceleration of the target simulated vehicle is selected as the sixth acceleration based on probability; wherein the sum of the fourth aggressive probability and the fourth conservative probability is 1, and the fourth aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle; the fifth acceleration is greater than zero, and the sixth acceleration is less than zero; the fifth acceleration is positively correlated with the aggressiveness parameter of the simulated driver; the fifth acceleration is less than or equal to the maximum acceleration of the target simulated vehicle; when the third difference is greater than the green light advance margin threshold, the acceleration of the target simulated vehicle is determined as the second vehicle deceleration based on the distance between the current position and the stop line position.

[0222] In some embodiments, the determining module is further configured to: determine a first travel time corresponding to the target simulated vehicle, wherein the first travel time is the time it takes for the target simulated vehicle to travel from its current position to the stop line position of the simulated lane at its current speed; when the current color is green and the current countdown value is a second countdown value, if the first travel time is less than or equal to the second countdown value, determine a fourth difference between the second countdown value and the first travel time; when the fourth difference is less than or equal to a preset green light lag margin threshold, select the target simulated vehicle according to a fifth aggressive probability. The acceleration of the real vehicle is the seventh acceleration, or the acceleration of the target simulated vehicle is selected as zero according to the fifth conservative probability; wherein, the sum of the fifth aggressive probability and the fifth conservative probability is 1, the fifth aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle; the seventh acceleration is greater than zero; the seventh acceleration is positively correlated with the aggressiveness parameter of the simulated driver; the seventh acceleration is less than or equal to the maximum acceleration of the target simulated vehicle; when the fourth difference is greater than the green light lag margin threshold, the acceleration of the target simulated vehicle is determined to be zero.

[0223] In some embodiments, the apparatus further includes: a historical color acquisition module, configured to acquire the historical color of the simulated traffic light one second before the current moment when the target simulated vehicle stops at the stop line position of the simulated lane; the determination module is further configured to: if the historical color is red and the current color is green, select the start reaction time of the simulated driver corresponding to the target simulated vehicle according to a first acuity probability; the start reaction time is negatively correlated with the acuity parameter of the simulated driver; the first acuity probability is a function value conforming to a normal distribution; and determine that the acceleration of the target simulated vehicle is zero within the start reaction time starting from the current moment, and the acceleration is greater than zero after the start reaction time.

[0224] In some embodiments, the apparatus further includes: a following vehicle determination module, configured to determine other simulated vehicles located in the same simulated lane as the target simulated vehicle, adjacent to the target simulated vehicle, and located in front of the target simulated vehicle as following vehicles when there is at least one other simulated vehicle between the target simulated vehicle and the simulated traffic light; a driving parameter determination module, configured to determine the driving speed and driving acceleration of the following vehicles; a following acceleration determination module, configured to determine the following acceleration of the target simulated vehicle based on the driving speed and the driving acceleration; and the simulation control module, further configured to control the target simulated vehicle to perform autonomous driving simulation on the simulated lane based on the following acceleration.

[0225] It should be noted that the description of the apparatus in this application embodiment is similar to the description of the method embodiment described above, and has similar beneficial effects as the method embodiment; therefore, it will not be repeated. For technical details not disclosed in this apparatus embodiment, please refer to the description of the method embodiment of this application for understanding.

[0226] This application provides a computer program product comprising a computer program or executable instructions, which are computer instructions; the computer program or executable instructions are stored in a computer-readable storage medium. When the processor of an electronic device reads the computer program or executable instructions from the computer-readable storage medium and executes the computer program or executable instructions, the electronic device performs the method described in this application embodiment.

[0227] This application provides a storage medium storing executable instructions. When these executable instructions are executed by a processor, they cause the processor to perform the method provided in this application, for example... Figure 3 The method shown.

[0228] In some embodiments, the storage medium may be a computer-readable storage medium, such as a ferromagnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEROM), flash memory, magnetic surface memory, optical disk, or a compact disk-read-only memory (CD-ROM); or it may be a device that includes one or any combination of the above-mentioned memories.

[0229] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0230] As an example, executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file containing other programs or data, for example, in one or more scripts within a Hypertext Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple collaborating files (e.g., files storing one or more modules, subroutines, or code sections). As an example, executable instructions may be deployed to execute on a single electronic device, or on multiple electronic devices located in one location, or on multiple electronic devices distributed across multiple locations and interconnected via a communication network.

[0231] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and scope of this application are included within the scope of protection of this application.

Claims

1. A vehicle simulation control method, characterized in that, The method includes: Display target simulated vehicles and simulated traffic lights with countdown timers on the simulated lanes of the simulated road network; When the distance between the target simulated vehicle and the simulated traffic light is less than or equal to a preset reaction line of sight, the current color of the simulated traffic light and the current countdown value of the countdown timer are obtained; Determine the first travel time corresponding to the target simulated vehicle, wherein the first travel time is the time it takes for the target simulated vehicle to travel from the current position to the stop line position of the simulated lane at the current speed; When the current color is red and the current countdown value is the first countdown value, if the first travel time is greater than the first countdown value, a first difference between the first travel time and the first countdown value is determined; When the first difference is greater than the preset red light advance margin threshold, the acceleration of the target simulated vehicle is selected as the first acceleration according to the first aggressive probability, or the acceleration of the target simulated vehicle is selected as zero according to the first conservative probability; wherein, the sum of the first aggressive probability and the first conservative probability is 1, the first aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle, and the first acceleration is greater than zero; Based on the acceleration, the target simulated vehicle is controlled to perform autonomous driving simulation on the simulated lane.

2. The method according to claim 1, characterized in that, The method further includes: Obtain a preset reaction line of sight corresponding to the target simulated vehicle; the preset reaction line of sight includes a traffic light reaction line of sight and a countdown reaction line of sight; the traffic light reaction line of sight is greater than or equal to the countdown reaction line of sight; When the distance between the target simulated vehicle and the simulated traffic light is detected to be less than or equal to the reaction line distance of the traffic light, the distance between the target simulated vehicle and the simulated traffic light is continuously detected; When the distance between the target simulated vehicle and the simulated traffic light is detected to be less than or equal to the countdown reaction line of sight, it is determined that the distance between the target simulated vehicle and the simulated traffic light is less than or equal to the preset reaction line of sight.

3. The method according to claim 2, characterized in that, The step of obtaining the preset reaction line of sight corresponding to the target simulation vehicle includes: Obtain the vehicle attribute parameters of the target simulated vehicle, the driver attribute parameters of the simulated driver corresponding to the target simulated vehicle, and the environmental parameters of the simulated road network; Based on the vehicle attribute parameters, the driver attribute parameters, and the environmental parameters, the sensitivity coefficient of the target simulated vehicle is determined. Obtain the inherent road parameters corresponding to the simulated lane; The preset reaction distance is determined based on the inherent road parameters and the sensitivity coefficient.

4. The method according to claim 1, characterized in that, The first acceleration is positively correlated with the aggression parameter of the simulated driver; The first acceleration is less than or equal to the maximum acceleration of the target simulated vehicle, and the first acceleration is less than the target uniform acceleration of the target simulated vehicle. The target uniform acceleration refers to the uniform acceleration used by the target simulated vehicle when it travels from the current position to the stop line position with the current speed as the initial speed, the first countdown value as the travel time.

5. The method according to claim 1, characterized in that, The method further includes: When the first difference is less than or equal to the red light advance margin threshold, the acceleration of the target simulated vehicle is selected as zero according to the second aggressive probability, or the acceleration of the target simulated vehicle is selected as the second acceleration according to the second conservative probability. Wherein, the sum of the second aggressive probability and the second conservative probability is 1, the second aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle, and the second acceleration is less than zero.

6. The method according to claim 1, characterized in that, The method further includes: When the current color is red and the current countdown value is the first countdown value, if the first travel time is less than or equal to the first countdown value, a second difference between the first countdown value and the first travel time is determined. When the second difference is less than or equal to the preset red light lag margin threshold, the acceleration of the target simulated vehicle is selected as the third acceleration according to the third aggressive probability, or the acceleration of the target simulated vehicle is selected as the fourth acceleration according to the third conservative probability. Wherein, the sum of the third aggressive probability and the third conservative probability is 1, the third aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle; the third acceleration and the fourth acceleration are both less than zero; the absolute value of the third acceleration is less than the absolute value of the fourth acceleration; When the target simulated vehicle is traveling at the third acceleration, when the target simulated vehicle reaches the stop line position of the simulated lane, the speed of the target simulated vehicle is greater than a preset comfort speed threshold.

7. The method according to claim 6, characterized in that, The third acceleration is positively correlated with the aggression parameter of the simulated driver; The absolute value of the third acceleration is less than or equal to the absolute value of the maximum deceleration of the target simulated vehicle, and the absolute value of the third acceleration is less than or equal to the absolute value of the target uniform deceleration of the target simulated vehicle. The target uniform deceleration refers to the uniform deceleration adopted by the target simulated vehicle when it travels from the current position to the stop line position with the current speed as the initial speed, the first countdown value as the travel time.

8. The method according to claim 6, characterized in that, The method further includes: When the second difference is greater than the red light lag margin threshold, the acceleration of the target simulated vehicle is determined as the first vehicle deceleration based on the distance between the current position and the stop line position; wherein, when the target simulated vehicle is traveling at the first vehicle deceleration, the speed of the target simulated vehicle is zero when it reaches the stop line position.

9. The method according to claim 1, characterized in that, The method further includes: When the current color is green and the current countdown value is the second countdown value, if the first travel time is greater than the second countdown value, a third difference between the first travel time and the second countdown value is determined; When the third difference is less than or equal to the preset green light advance margin threshold, the acceleration of the target simulated vehicle is selected as the fifth acceleration according to the fourth aggressive probability, or the acceleration of the target simulated vehicle is selected as the sixth acceleration according to the fourth conservative probability. Wherein, the sum of the fourth aggressive probability and the fourth conservative probability is 1, the fourth aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle; the fifth acceleration is greater than zero, the sixth acceleration is less than zero; the fifth acceleration is positively correlated with the aggressiveness parameter of the simulated driver; the fifth acceleration is less than or equal to the maximum acceleration of the target simulated vehicle; When the third difference is greater than the green light advance margin threshold, the acceleration of the target simulated vehicle is determined to be the second vehicle deceleration based on the distance between the current position and the stop line position.

10. The method according to claim 1, characterized in that, The method further includes: When the current color is green and the current countdown value is the second countdown value, if the first travel time is less than or equal to the second countdown value, a fourth difference between the second countdown value and the first travel time is determined; When the fourth difference is less than or equal to the preset green light lag margin threshold, the acceleration of the target simulated vehicle is selected as the seventh acceleration according to the fifth aggressive probability, or the acceleration of the target simulated vehicle is selected as zero according to the fifth conservative probability. Wherein, the sum of the fifth aggressive probability and the fifth conservative probability is 1, the fifth aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle; the seventh acceleration is greater than zero; The seventh acceleration is positively correlated with the aggression parameter of the simulated driver; the seventh acceleration is less than or equal to the maximum acceleration of the target simulated vehicle. When the fourth difference is greater than the green light lag margin threshold, the acceleration of the target simulated vehicle is determined to be zero.

11. The method according to any one of claims 1 to 10, characterized in that, The method further includes: when the target simulated vehicle stops at the stop line position of the simulated lane, obtaining the historical color of the simulated traffic light one second before the current moment; The method further includes: If the historical color is red and the current color is green, the start reaction time of the simulated driver corresponding to the target simulated vehicle is selected according to the first sensitivity probability; the start reaction time is negatively correlated with the sensitivity parameter of the simulated driver; the first sensitivity probability is a function value that conforms to a normal distribution. It is determined that the acceleration of the target simulated vehicle is zero during the start-up reaction time starting from the current moment, and the acceleration is greater than zero after the start-up reaction time.

12. A vehicle simulation control device, characterized in that, The device includes: The display module is used to display target simulated vehicles and simulated traffic lights with countdown timers on the simulated lanes of the simulated road network; The acquisition module is used to acquire the current color of the simulated traffic light and the current countdown value of the countdown timer when the distance between the target simulated vehicle and the simulated traffic light is less than or equal to a preset reaction line of sight. The determining module is used to determine the first travel time corresponding to the target simulated vehicle, where the first travel time is the time it takes for the target simulated vehicle to travel from its current position to the stop line position of the simulated lane at its current speed; when the current color is red and the current countdown value is the first countdown value, if the first travel time is greater than the first countdown value, a first difference between the first travel time and the first countdown value is determined; when the first difference is greater than a preset red light advance margin threshold, the acceleration of the target simulated vehicle is selected as the first acceleration according to a first aggressive probability, or the acceleration of the target simulated vehicle is selected as zero according to a first conservative probability; wherein, the sum of the first aggressive probability and the first conservative probability is 1, the first aggressive probability is positively correlated with the aggressiveness parameter of the simulated driver corresponding to the target simulated vehicle, and the first acceleration is greater than zero; The simulation control module is used to control the target simulation vehicle to perform autonomous driving simulation on the simulation lane based on the acceleration.

13. An electronic device, characterized in that, include: Memory, used to store executable instructions; A processor, when executing executable instructions stored in the memory, implements the vehicle simulation control method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, The device stores executable instructions that, when executed by a processor, implement the vehicle simulation control method according to any one of claims 1 to 11.

Images