A vehicle-road cooperation information interaction management system

Abstract

The application discloses a kind of vehicle-road cooperation information interaction management systems, it is related to vehicle-road cooperation information interaction management technical field, including, data acquisition module: collection vehicle sensor data, infrastructure data and telematics data;Preprocessing module: the data collected is preprocessed;Data fusion module: data is fused;Environment perception module: the data after fusion is environment perception, generates global environment perception graph;Behavior prediction module: behavior prediction is carried out based on global environment perception graph;Risk assessment module: risk assessment is carried out according to behavior prediction result;Early warning module: early warning signal is generated based on risk assessment result;The application has beneficial effects: the efficient fusion of multi-source heterogeneous data is realized, accurate global environment perception graph is generated, the perception ability to dynamic change in complex traffic environment is improved, and the reliability of behavior prediction and risk assessment is significantly enhanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle-road cooperative information interaction management, and particularly relates to a vehicle-road cooperative information interaction management system. BACKGROUND

[0002] The vehicle-road cooperative system realizes information interaction between vehicles, road infrastructure, other vehicles and pedestrians through integration of vehicle-mounted sensors, roadside infrastructure and vehicle networking technology, thereby improving traffic efficiency and driving safety. The existing vehicle-road cooperative system still faces many challenges in data fusion, environment perception, behavior prediction and risk assessment, especially in the effective integration of multi-source heterogeneous data and real-time requirements. The existing technology has not fully met the high-standard requirements of the development of autonomous driving and intelligent transportation.

[0003] The existing behavior prediction model is often based on a single or small number of input variables, and does not fully consider the interaction of multi-dimensional information, resulting in low reliability of the prediction results, especially in dealing with unexpected situations. The existing risk assessment and early warning mechanism usually cannot respond in time when facing high real-time and high dynamic traffic environment, and there is a delay in the transmission and feedback of the early warning signal, which greatly affects the overall effectiveness and safety of the system. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides a vehicle-road cooperative information interaction management system to solve the problems of multi-source heterogeneous data fusion difficulty and real-time and accuracy insufficiency in the vehicle-road cooperative system.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application embodiment provides a vehicle-road cooperative information interaction management system, which comprises,

[0008] The data acquisition module acquires vehicle sensor data, infrastructure data and vehicle networking data.

[0009] The preprocessing module preprocesses the collected data.

[0010] The data fusion module fuses the data.

[0011] The environment perception module performs environment perception on the fused data to generate a global environment perception map.

[0012] The behavior prediction module performs behavior prediction based on the global environment perception map.

[0013] The risk assessment module performs risk assessment according to the behavior prediction result.

[0014] The early warning module generates an early warning signal based on the risk assessment result;

[0015] The information interaction module sends the early warning signal to the vehicle and the driver based on information interaction;

[0016] The feedback module feeds back the execution operation of the vehicle and the driver to the central processing module;

[0017] The central processing module processes the feedback execution operation of the vehicle and the driver.

[0018] As a preferred scheme of the vehicle-road cooperative information interaction management system, wherein:

[0019] The vehicle sensor data includes GPS data, radar and laser radar data, and camera data, the infrastructure data includes signal lamp state data, weather condition data and road condition data, and the Internet of Vehicles data includes inter-vehicle communication data and vehicle-road communication data.

[0020] The collected data is preprocessed, and the preprocessed data is input to the multi-source data fusion module.

[0021] As a preferred scheme of the vehicle-road cooperative information interaction management system, wherein:

[0022] The data is fused, and the fused data is environmentally perceived to generate a global environmental perception map, including,

[0023] The data from different sensors is fused into a unified probability distribution by using a Bayesian inference method;

[0024] The global environmental perception map is constructed based on the fused data, the nodes represent the traffic participants and the environmental elements, the edges represent the spatial relationship and the interaction relationship between the nodes, and the global environmental perception map is defined as G=(V,E), wherein V is the node set, and E is the edge set.

[0025] As a preferred scheme of the vehicle-road cooperative information interaction management system, wherein:

[0026] The behavior of the traffic participant is predicted based on the global environmental perception map, including,

[0027] The traffic participant and the surrounding environmental information thereof are obtained according to the environmental perception map;

[0028] The position information of the traffic participant is extracted based on the GPS data speed and direction

[0029] Obstacle detection data relative to traffic participants extracted based on radar and lidar data as well as relative speed

[0030] Object detection information in front of the vehicle extracted by visual processing algorithms based on camera data

[0031] Current traffic light state extracted based on traffic light state

[0032] Traffic density of the current road extracted based on road condition data as well as weather information

[0033] Communication data with surrounding vehicles, including relative position and relative speed

[0034] Road information obtained from the traffic management center based on vehicle-to-road communication data

[0035] Normalize the extracted information to form a unified feature vector is represented as:

[0036]

[0037] According to the feature vector Using linear transformation and nonlinear activation function, calculate the intermediate feature, represented as:

[0038]

[0039] where F (t) is the intermediate feature, W1 is the weight matrix, b1 is the bias vector, and tanh(·) is the hyperbolic tangent activation function.

[0040] Extract time series features based on multiple time steps to generate a new feature vector H(t), represented as:

[0041]

[0042] where H (t) is the newly generated feature vector, λ k is the decay factor, and K is the number of historical time steps.

[0043] Map the time series feature vector to the prediction output Y^(t) of the future trajectory using linear transformation, represented as:

[0044]

[0045] wherein, is the behavior trajectory prediction result at time t, W1 is the weight matrix of the input layer, b1 is the bias vector of the input layer, W2 is the weight matrix of the prediction layer, b2 is the bias vector of the prediction layer, is the input data sequence at time t, K is the historical time step number.

[0046] As a preferred scheme of the vehicle-road cooperative information interaction management system, wherein:

[0047] The behavior prediction, according to the behavior prediction result, carries out risk assessment and generates a warning signal, comprising,

[0048] Based on the predicted trajectory of the ego vehicle and the predicted trajectory of the surrounding traffic participants, a time step Δt per second is selected, and for each time step Δt, the Euclidean distance between the ego vehicle and other traffic participants is calculated, expressed as:

[0049]

[0050] wherein, is the Euclidean distance between the ego vehicle and the traffic participant j at time point t+τ; and are the predicted position coordinates of the ego vehicle at time t+τ, i.e., the x and y directions; and are the predicted position coordinates of the other participants at time t+τ, i.e., the x and y directions.

[0051] Based on the Euclidean distance between the ego vehicle and other traffic participants, the collision risk is detected, expressed as:

[0052]

[0053] A safety distance threshold δ is set safe If the Euclidean distance between the ego vehicle and other traffic participants is less than the threshold, there is a collision risk;

[0054] The risk factor is calculated in combination with the speed difference, the acceleration difference, and the road condition;

[0055] The speed difference between the ego vehicle and other traffic participants is defined, expressed as:

[0056]

[0057] wherein, is the speed difference between the ego vehicle and the traffic participant j at time point t+τ; is the speed vector of the ego vehicle at time point t+τ; is the speed vector of the traffic participant j at time point t+τ;

[0058] The acceleration difference between the ego vehicle and other traffic participants is defined as:

[0059]

[0060] where: is the acceleration difference between the ego vehicle and traffic participant j at time point t+τ; is the acceleration vector of the ego vehicle at time point t+τ; is the acceleration vector of traffic participant j at time point t+τ;

[0061] The impact of road conditions on risk is calculated based on road infrastructure data, represented as:

[0062]

[0063] where: is the road condition impact factor at time point t+τ; is the road condition coefficient at time point t+τ, is the weather condition at time point t+τ; T max is the maximum allowed temperature or humidity value;

[0064] Based on the risk factor calculation formula, an analysis and evaluation model is constructed, represented as:

[0065]

[0066] where: is the comprehensive risk value at time point t+τ; ∈ is a small positive number to prevent division by zero errors; v max is the maximum speed of the ego vehicle; a max is the maximum acceleration of the ego vehicle; N is the total number of surrounding traffic participants; is the collision detection indicator function at time point t+τ.

[0067] Set the risk threshold T, if exceeds the threshold, there is a potential risk event, which needs to trigger the warning mechanism immediately;

[0068] Based on the value range of the risk assessment function , the warning information is divided into three categories: low-level warning, medium-level warning, and high-level warning. Define the low-level warning risk threshold T low and the high-level warning risk threshold T high , when is less than T low , it is a low-level warning, when is greater than T low and less than T high , it is a medium-level warning, and when Rrisk(t) is greater than T highThe high-level warning is a high-level warning.

[0069] Based on the warning level, the driver is issued a warning message in different ways:

[0070] The low-level warning is issued through visual prompts such as HUD display and instrument panel display.

[0071] The medium-level warning is issued through audio prompts such as alarm sound.

[0072] The high-level warning is not only through visual prompts and audio prompts, but also through steering wheel or seat vibration feedback.

[0073] As a preferred scheme of the vehicle-road cooperative information interaction management system of the present application, wherein:

[0074] The information interaction based on the information interaction sends the warning signal to the vehicle and the driver, comprising,

[0075] The information interaction includes information communication between vehicles, infrastructure, and cloud, and each vehicle continuously broadcasts its current position and speed information through vehicle-to-vehicle communication protocol.

[0076] When the risk event is detected, an emergency notification is sent through vehicle-to-vehicle communication;

[0077] Through vehicle-to-infrastructure communication, the current traffic signal state and road closure information are obtained from traffic lights and dynamic road sign infrastructure, and the vehicle and the driver adjust the driving strategy according to the received information;

[0078] Through vehicle-to-cloud communication, it is connected to the cloud platform to obtain the traffic flow distribution and weather condition global traffic information in the city, and the information is used for long-term path planning and strategy adjustment, and the driving data is uploaded to the cloud for subsequent data analysis and system optimization.

[0079] As a preferred scheme of the vehicle-road cooperative information interaction management system of the present application, wherein:

[0080] The feedback of the execution operation of the vehicle and the driver to the central processing module comprises,

[0081] Real-time monitoring of the driver's operation, the operation including steering wheel rotation, brake force, throttle operation, and determining whether the driver responds to the warning signal;

[0082] The feedback data after each decision execution, including driver operation and environmental change, are returned to the central processing module for analysis.

[0083] In a second aspect, an embodiment of the present application provides a computer device comprising a memory and a processor, and the memory stores a computer program, wherein the computer program, when executed by the processor, implements any step of the vehicle-road cooperative information interaction management system according to the first aspect of the present application.

[0084] In a third aspect, an embodiment of the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any step of the vehicle-road cooperative information interaction management system according to the first aspect of the present application.

[0085] The present application has the following beneficial effects: 1. Efficient fusion of multi-source heterogeneous data is achieved, accurate global environment perception map is generated, the perception ability of dynamic changes in complex traffic environment is improved, and the reliability of behavior prediction and risk assessment is significantly enhanced;

[0086] 2. By comprehensively considering the feature extraction information of multiple time steps, high-precision behavior prediction can be achieved, thereby effectively predicting possible dangerous situations and providing a reliable basis for subsequent risk assessment and early warning mechanism;

[0087] 3. Through real-time risk monitoring, the early warning mode can be flexibly adjusted according to different risk levels, so as to maximize the driving safety and prevent accidents. BRIEF DESCRIPTION OF DRAWINGS

[0088] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0089] Figure 1 Flowchart of the vehicle-road cooperative information interaction management system in embodiment 1. DETAILED DESCRIPTION

[0090] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0091] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the scope of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0092] Second, the "one embodiment" or "an embodiment" referred to herein means a particular feature, structure, or characteristic including an implementation that can be included in at least one implementation of the application. The appearances of "in one embodiment" or "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily all referring to a single, alternative embodiment, or a single, alternative implementation.

[0093] Embodiment 1, Reference Figure 1 For the first embodiment of the application, the embodiment provides a vehicle-road cooperative information interaction management system, comprising the following steps: a data acquisition module: acquiring vehicle sensor data, infrastructure data and Internet of Vehicles data;

[0094] a preprocessing module: preprocessing the collected data;

[0095] a data fusion module: fusing the data;

[0096] an environment perception module: performing environment perception on the fused data to generate a global environment perception map;

[0097] a behavior prediction module: performing behavior prediction based on the global environment perception map;

[0098] a risk assessment module: performing risk assessment according to the behavior prediction result;

[0099] a warning module: generating a warning signal based on the risk assessment result;

[0100] an information interaction module: sending the warning signal to the vehicle and the driver based on information interaction;

[0101] a feedback module: feeding back the execution operation of the vehicle and the driver to the central processing module;

[0102] a central processing module: processing the feedback execution operation of the vehicle and the driver.

[0103] The vehicle sensor data includes GPS data, radar and laser radar data, and camera data, the infrastructure data includes signal lamp state data, weather condition data and road condition data, and the Internet of Vehicles data includes inter-vehicle communication data and vehicle-road communication data.

[0104] The collected data is preprocessed, and the preprocessed data is input to the multi-source data fusion module. The input data includes vehicle state information, environment perception information and infrastructure information with unified time stamp.

[0105] The data is fused, and the fused data is subjected to environment perception to generate a global environment perception map, including,

[0106] The data from different sensors are fused into a unified probability distribution using Bayesian inference method;

[0107] Define multiple observations z1, z2, …, z n , the fused estimate , the expression is:

[0108]

[0109] where w i is the weight of each sensor data, the weight is determined by the signal-to-noise ratio of the data, historical accuracy, etc. is the independent estimate of each sensor, and the calculation formula of the weight is:

[0110]

[0111] where, is the observation error variance of sensor i.

[0112] Based on the fused data, a global environment perception graph is constructed, the nodes represent the traffic participants and environmental elements, and the edges represent the spatial relationship and interaction relationship between the nodes, define the global environment perception graph as G = (V, E), where V is the node set, and E is the edge set.

[0113] In the topological graph, each node and edge is labeled with corresponding information, such as position, speed, acceleration, etc. Dynamic information, as well as signal light state, road condition, etc. Static information.

[0114] The behavior prediction of the traffic participants based on the global environment perception graph includes,

[0115] According to the environment perception graph, the traffic participants and their surrounding environment information are obtained;

[0116] Based on GPS data, the position information of the traffic participants is extracted speed and direction

[0117] Based on radar and lidar data, obstacle detection data relative to the traffic participants is extracted and relative speed

[0118] Based on camera data, object detection information in front of the vehicle is extracted through visual processing algorithm

[0119] Based on the signal light state, the current signal light state is extracted

[0120] Extracting traffic density of current road based on road condition data and weather information

[0121] Extracting communication data with surrounding vehicles based on vehicle-to-vehicle communication data, including relative position and relative speed

[0122] Extracting road information obtained from traffic management center based on vehicle-to-road communication data

[0123] Normalizing the extracted information to form a unified feature vector represented as:

[0124]

[0125] According to the feature vector Using linear transformation and nonlinear activation function, calculate the intermediate feature, represented as:

[0126]

[0127] where F (t) is the intermediate feature, W1 is the weight matrix, b1 is the bias vector, and tanh(·) is the hyperbolic tangent activation function.

[0128] In the process of behavior prediction, the input environmental perception data and vehicle state data have high dimensionality and heterogeneity, different types of data have different feature spaces and different measurement standards, the speed and acceleration of the vehicle belong to physical quantities, while the road condition and signal light state are categorical data or discrete data, therefore, directly using these data for trajectory prediction may not be able to fully exploit their potential correlation and complex time dependence.

[0129] In order to effectively process heterogeneous data and extract useful information for trajectory prediction from them, through an intermediate feature representation step, the original data is reduced, normalized and feature extracted, so that the subsequent deep learning model can better capture the mutual relationship and time series characteristics between the data.

[0130] The position, direction, speed and acceleration of the ego vehicle: directly affect the motion state of the vehicle, and are the core variables of trajectory prediction, through intermediate feature extraction, the relationship between these variables and future trajectory can be understood.

[0131] The position, speed and acceleration of other traffic participants: used to predict possible interaction behavior, possible collision risk or avoidance behavior, intermediate feature extraction can help the model understand the complexity of these interactions.

[0132] Infrastructure data, including signal light status, road condition, weather information: usually categorical or discrete data, which can be converted into continuous feature vectors through feature extraction, facilitating fusion with other physical quantity data.

[0133] Vehicular network data: reflects the traffic dynamics in a larger range, which can help the model capture the relationship between local and global traffic states through feature extraction.

[0134] Feature extraction of time series based on multiple time steps, generate new feature vector H(t), expressed as:

[0135]

[0136] Among them, H (t) Newly generated feature vector, λ k Decay factor, K is the number of historical time steps;

[0137] Linear transformation is used to map the time series feature vector to the prediction output Y^(t) of the future trajectory, expressed as:

[0138]

[0139] Among them, Behavior trajectory prediction result at time t, W1 is the weight matrix of the input layer, b1 is the bias vector of the input layer, W2 is the weight matrix of the prediction layer, b2 is the bias vector of the prediction layer, Input data sequence at time t, K is the number of historical time steps.

[0140] The behavior prediction, according to the behavior prediction result, carries out risk assessment and generates early warning signal, including,

[0141] Based on the predicted trajectory of the ego vehicle and the predicted trajectory of the surrounding traffic participants, select each second as the time step Δt, for each time step Δt, calculate the Euclidean distance between the ego vehicle and other traffic participants, expressed as:

[0142]

[0143] Among them: Euclidean distance between ego vehicle and traffic participant j at time point t+τ; And The predicted position coordinates of the ego vehicle at time t+τ, i.e., x and y directions; And The predicted position coordinates of other participants at time t+τ, i.e., x and y directions.

[0144] Based on the Euclidean distance between the ego vehicle and other traffic participants, the collision risk is detected, expressed as:

[0145]

[0146] Setting a safety distance threshold δ safe If the Euclidean distance between the ego vehicle and other traffic participants is less than the threshold, there is a risk of collision;

[0147] Calculate the risk factor in combination with the speed difference, acceleration difference and road conditions;

[0148] Define the speed difference between the ego vehicle and other traffic participants, denoted as:

[0149]

[0150] Where: The speed difference between the ego vehicle and traffic participant j at time point t+τ; The speed vector of the ego vehicle at time point t+τ; The speed vector of traffic participant j at time point t+τ;

[0151] Define the acceleration difference between the ego vehicle and other traffic participants, denoted as:

[0152]

[0153] Where: The acceleration difference between the ego vehicle and traffic participant j at time point t+τ; The acceleration vector of the ego vehicle at time point t+τ; The acceleration vector of traffic participant j at time point t+τ;

[0154] Calculate the impact of road conditions on risk based on road infrastructure data, denoted as:

[0155]

[0156] Where: The road condition impact factor at time point t+τ; The road condition coefficient at time point t+τ, The weather conditions at time point t+τ; T max The maximum allowed temperature or humidity value;

[0157] Based on the risk factor calculation formula, build an analysis and evaluation model, denoted as:

[0158]

[0159] Where: The comprehensive risk value at time point t+τ; ∈ is a small positive number to prevent division by zero error; v maxVmax is the maximum speed of the ego vehicle; a max Vmax is the maximum acceleration of the ego vehicle; N is the total number of surrounding traffic participants; is the collision detection indicator function at time point t+τ.

[0160] Set a risk threshold T, if the threshold is exceeded, there is a potential risk event, which needs to trigger the warning mechanism immediately;

[0161] Based on the value range of the risk assessment function , the warning information is divided into three categories: low-level warning, medium-level warning and high-level warning, and the low-level warning risk threshold T low and the high-level warning risk threshold T high are defined, when is less than T low , it is a low-level warning, when is greater than T low is less than T high , it is a medium-level warning, and when Rrisk(t) is greater than T high , it is a high-level warning;

[0162] Based on the warning level, the driver is issued warning information in different ways:

[0163] Low-level warning is issued through visual prompts such as HUD display and instrument panel display;

[0164] Medium-level warning is issued through audio prompts such as alarm sound;

[0165] High-level warning is not only through visual prompts and audio prompts, but also through steering wheel or seat vibration feedback.

[0166] The information interaction includes,

[0167] The information interaction includes information communication between vehicles, between vehicles and infrastructure, and between vehicles and the cloud, and each vehicle continuously broadcasts its current position and speed information through the vehicle-to-vehicle communication protocol;

[0168] When the risk event is detected, an emergency notification is sent through vehicle-to-vehicle communication, including event type, location and timestamp;

[0169] Through vehicle-to-infrastructure communication, the current traffic signal state and road closure information are obtained from traffic signal lights and dynamic road sign infrastructure, and the vehicle and the driver adjust the driving strategy according to the received information;

[0170] The vehicle is connected to the cloud platform through communication with the cloud, obtains the traffic flow distribution, weather condition and global traffic information in the city, uses the information for long-term path planning and strategy adjustment, and uploads the driving data to the cloud for subsequent data analysis and system optimization.

[0171] The feedback of the execution operation of the vehicle and the driver to the central processing module includes,

[0172] The operation of the driver is monitored in real time, and the operation includes steering wheel rotation, brake force, throttle operation, and whether the driver responds to the warning signal is judged.

[0173] The feedback data after each decision execution, including driver operation and environmental change, are returned to the central processing module for analysis.

[0174] The embodiment also provides a computer device suitable for the case of the vehicle-road cooperation information interaction management system, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to realize the vehicle-road cooperation information interaction management system proposed in the above embodiment.

[0175] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device. In addition, the input device can be an external keyboard, touchpad or mouse, etc.

[0176] The embodiment also provides a storage medium on which a computer program is stored, the program being executed by a processor to implement the vehicle-road cooperative information interaction management system proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disk.

[0177] To sum up, the present application is through:

[0178] Embodiment 2, referring to Table 1, is a second embodiment of the present application, and experimental simulation data of the vehicle-road cooperative information interaction management system are given to further verify the technical solution of the present application.

[0179] In order to verify the performance of the vehicle-road cooperative information interaction management system, the test is set in a simulated urban traffic environment, and the experimental scene covers a variety of complex traffic conditions, including high-density traffic flow, unpredictable weather conditions, signal failure and other sudden situations, the test objects include the intelligent vehicle system 1 equipped with the system of the present application and the traditional vehicle system 2 not equipped with the system, and the experimental data collection includes data from GPS, radar, lidar, camera and other sensors, as well as signal light state data, weather condition data, road condition data, inter-vehicle communication data and vehicle-road communication data.

[0180] In the specific implementation process, first, the vehicle sensor data, infrastructure data and Internet of Vehicles data in the experiment are collected in real time by the data acquisition module, then the preprocessing module filters, denoises and time synchronizes these data to ensure the accuracy and timeliness of the data, after that, the data fusion module adopts the Bayesian inference method to fuse the multi-source data into a unified probability distribution, and generates a global environment perception map based on this, the perception map comprehensively displays the traffic participants, environmental elements and their spatial relationships and interaction relationships.

[0181] In the behavior prediction module, based on the environment perception map and multi-dimensional sensor data, the position information, speed, direction and other features of the traffic participants are extracted, and the future behavior trajectory is predicted through the time series model. The risk assessment module analyzes these prediction results, calculates the Euclidean distance, speed difference and acceleration difference between the ego vehicle and other traffic participants, and quantitatively evaluates the collision risk in combination with the road condition data. Once potential risks are detected, the warning module generates corresponding warning signals according to the risk level, and sends these signals to the vehicle driver through the information interaction module, reminding the driver to take necessary operations in time.

[0182] During the test, the vehicle driver of system 1 responds to the warning signal, such as steering wheel rotation, brake force, throttle operation and other operations, which are monitored in real time and fed back to the central processing module for analysis. The central processing module further optimizes the decision logic of the system and applies new strategies in the next test through this closed-loop system, so that the vehicle can maintain higher safety and response speed in complex traffic environments.

[0183] Specifically, as shown in the following table 1:

[0184] Table 1: System 1 and system 2 parameter comparison table

[0185]

[0186] Based on data analysis, it can be seen that the performance of the system in different environments. In terms of average response time, the response time of system 1 in rainy and sunny days is 0.8 seconds and 0.7 seconds respectively, while the response time of system 2 is 1.2 seconds and 1.0 seconds respectively, which shows that system 1 has significant advantages in data fusion and real-time risk assessment, and can analyze and process complex traffic information faster, so as to send warning signals to the driver in time, which is particularly important in high-risk environments, greatly reducing the probability of accidents.

[0187] In terms of collision risk assessment value, the assessment value of system 1 in rainy and sunny days is 0.3 and 0.2 respectively, which is significantly lower than 0.6 and 0.4 of system 2, which shows that system 1 can more accurately judge the potential collision risk by considering multi-dimensional data, and take corresponding warning measures, while system 2 lacks efficient data fusion and environment perception ability, resulting in higher risk assessment value, which is difficult to provide reliable safety protection in complex environments.

[0188] The data of the driver operation error rate also shows that the operation error rates of system 1 in rainy days and sunny days are 2.5% and 1.8% respectively, which are significantly lower than 4.6% and 3.2% of system 2, indicating that through real-time warning and information interaction, system 1 can effectively assist the driver to make correct decisions and reduce the operation errors caused by information lag or deficiency. Since the warning information of system 2 is not timely or accurate enough, the driver may make wrong judgments at critical moments, thereby increasing the risk of operation errors.

[0189] From the total number of warnings and the number of successful risk avoidance events, system 1 issued 10 and 8 warnings in rainy days and sunny days respectively, and the number of successful risk avoidance events was 9 and 7 respectively, while the number of warnings of system 2 was 15 and 12, and the number of successful risk avoidance events was only 10 and 8, indicating that the warning mechanism of system 1 is better, which can issue warnings when necessary and accurately guide the driver to avoid risks, avoiding unnecessary alarm interference with the driver's attention.

[0190] In summary, the vehicle-road cooperative information interaction management system of the present application significantly improves the safety and response ability of vehicles in complex traffic environment through advanced multi-source data fusion, accurate environmental perception and real-time behavior prediction. Compared with the prior art, the system has significant advantages in response speed, risk assessment accuracy and driver assistance, not only reducing the potential risk of traffic accidents, but also improving the operation accuracy and safety of the driver.

[0191] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit it. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the present application, which should be covered in the scope of the claims of the present application.

Claims

1.A vehicle infrastructure integration information interaction management system, characterized in that: Comprising, Data acquisition module: collect vehicle sensor data, infrastructure data and vehicle networking data; Preprocessing module: preprocess the collected data; Data fusion module: fuse the data; Environment perception module: perform environment perception on the fused data to generate a global environment perception graph; Behavior prediction module: perform behavior prediction based on the global environment perception graph, the steps are as follows: On extracted road information Normalization processing is performed to form a unified feature vector According to the feature vector An intermediate feature is calculated using a linear transformation and a nonlinear activation function, a time series feature is extracted based on multiple time steps, a new feature vector H(t) is generated, and a linear transformation is used to map the time series feature vector to a predicted output Y^(t) of the future trajectory. Risk assessment module: perform risk assessment based on the behavior prediction results; Early warning module: generate early warning signals based on the risk assessment results, the steps are as follows: A risk threshold T is set, if The threshold is exceeded, a potential risk event exists, the early warning mechanism needs to be triggered immediately, based on the value range of the risk assessment function The early warning information is divided into three categories: low-level early warning, medium-level early warning and high-level early warning, the low-level early warning risk threshold T low and the high-level early warning risk threshold T high are defined, when is less than T low , it is low-level early warning, when is greater than T low is less than T high , it is medium-level early warning, when Rrisk(t) is greater than T high , it is high-level early warning, based on the early warning level, the early warning information is issued to the driver in different ways: the low-level early warning is issued through visual prompts of HUD display and instrument panel display, the medium-level early warning is issued through audio prompts of alarm sound, the high-level early warning is not only issued through visual prompts and audio prompts, but also through steering wheel or seat vibration feedback; Information interaction module: send early warning signals to vehicles and drivers based on information interaction; Feedback module: feedback the execution operation of vehicles and drivers to the central processing module; Central processing module: process the feedback execution operation of vehicles and drivers. 2.The vehicle infrastructure integration information interaction management system of claim 1, wherein: The vehicle sensor data includes GPS data, radar and laser radar data, and camera data, the infrastructure data includes signal light state data, weather condition data and road condition data, the vehicle networking data includes inter-vehicle communication data and vehicle-road communication data; The collected data is preprocessed, and the preprocessed data is input to the multi-source data fusion module. 3.The vehicle infrastructure integration information interaction management system of claim 2, wherein: The data fusion and environment perception on the fused data to generate a global environment perception graph, including, Using Bayesian inference method, fuse data from different sensors into a unified probability distribution; Based on the fused data, construct a global environment perception graph, nodes represent traffic participants and environmental elements, edges represent spatial and interaction relationships between nodes, define the global environment perception graph as G=(V,E), where V is the node set and E is the edge set. 4.The vehicle infrastructure integration information interaction management system of claim 3, wherein: The behavior prediction of traffic participants based on the global environment perception graph, including, According to the environment perception graph, obtain the traffic participants and their surrounding environment information; Extracting traffic actor position information based on GPS data speed and direction Obstacle detection data relative to a traffic participant extracted based on radar and lidar data and relative speed Extracting object detection information in front of a vehicle based on camera data through a vision processing algorithm Extracting current signal light state based on signal light state Extracting traffic density of a current road based on road condition data and weather information Based on the inter-vehicle communication data extraction and the communication data of the surrounding vehicles, including relative position and relative speed Extracting road information obtained from a traffic management center based on car-to-road communication data 5.The vehicle infrastructure cooperation information interaction management system of claim 1, wherein: The behavior prediction, according to the behavior prediction results, performs risk assessment and generates early warning signals, Including, Based on the predicted trajectory of the ego vehicle and the predicted trajectory of the surrounding traffic participants, select a time step Δt per second, for each time step Δt, calculate the Euclidean distance between the ego vehicle and other traffic participants; Based on the Euclidean distance between the ego vehicle and other traffic participants, detect the collision risk; Setting a safety distance threshold δ safe If the Euclidean distance between the ego vehicle and other traffic participants is less than this threshold, there is a collision risk. 6.The vehicle infrastructure integration information interaction management system of claim 1, wherein: Combine the speed difference, acceleration difference and road conditions to calculate the risk factor; Define the speed difference between the ego vehicle and other traffic participants; Define the acceleration difference between the ego vehicle and other traffic participants; Based on the road infrastructure data, calculate the impact of road conditions on risk; Based on the risk factor calculation formula, construct an analysis and evaluation model. 7.The vehicle infrastructure integration information interaction management system of claim 1, wherein: The early warning signal is sent to the vehicle and the driver based on the information interaction, including, The information interaction includes information communication between vehicles, vehicles and infrastructure, and vehicles and cloud, each vehicle continuously broadcasts its current position and speed information through the vehicle-to-vehicle communication protocol; When the risk event is detected, send an emergency notification through vehicle-to-vehicle communication; Through vehicle and infrastructure communication, the current traffic signal state, road closure information is obtained from traffic lights, dynamic road sign infrastructure, and the vehicle and driver adjust the driving strategy according to the received information; Through vehicle and cloud communication, connect to the cloud platform, obtain the traffic flow distribution in the city, the weather situation global traffic information, use the information for long-term path planning and strategy adjustment, and upload the driving data to the cloud for subsequent data analysis and system optimization. 8.The vehicle infrastructure integration information interaction management system of claim 1, wherein: The feedback of the execution operation of the vehicle and the driver to the central processing module comprises, Real-time monitoring of the driver's operation, including steering wheel rotation, brake force, throttle operation, and determining whether the driver responds to the warning signal; The feedback data after each decision execution, including driver operation and environmental change, are returned to the central processing module for analysis.

Images