CN117727183B - Automatic driving safety early warning method and system combining vehicle-road cooperation - Google Patents
Automatic driving safety early warning method and system combining vehicle-road cooperation Download PDFInfo
- Publication number
- CN117727183B CN117727183B CN202410179105.1A CN202410179105A CN117727183B CN 117727183 B CN117727183 B CN 117727183B CN 202410179105 A CN202410179105 A CN 202410179105A CN 117727183 B CN117727183 B CN 117727183B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- target
- safety
- driving
- static
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000001514 detection method Methods 0.000 claims abstract description 241
- 230000003068 static effect Effects 0.000 claims abstract description 225
- 230000000007 visual effect Effects 0.000 claims abstract description 74
- 238000004458 analytical method Methods 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 20
- 230000005284 excitation Effects 0.000 claims description 16
- 230000001133 acceleration Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 9
- 238000009877 rendering Methods 0.000 claims description 7
- 230000002452 interceptive effect Effects 0.000 claims description 6
- 238000012098 association analyses Methods 0.000 claims description 4
- 238000005065 mining Methods 0.000 claims description 3
- 230000037361 pathway Effects 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 7
- 230000009471 action Effects 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 16
- 238000005516 engineering process Methods 0.000 description 9
- 230000006872 improvement Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The application provides an automatic driving safety pre-warning method and system combining vehicle-road cooperation, and relates to the technical field of data processing, wherein the method comprises the following steps: and reading target real-time driving data, then reading a driving association state data set, obtaining a target driving visual model, then carrying out static vehicle-road cooperative safety detection, obtaining a target static cooperative safety detection result, then carrying out dynamic vehicle-road cooperative safety detection, obtaining a dynamic cooperative safety detection result, generating a safety analysis report, and sending the safety analysis report to a safety precaution device for safety precaution. The method mainly solves the problem that the existing method excessively depends on historical data, which increases the difficulty of real-time early warning, possibly reduces early warning accuracy, and cannot carry out self-adaptive adjustment according to scene changes, thereby limiting the real-time performance of early warning effect. And judging whether the vehicle has safety risk or illegal action in real time according to the dynamic cooperative safety detection result, and carrying out early warning, thereby improving the real-time performance and accuracy of the data.
Description
Technical Field
The application relates to the technical field of data processing, in particular to an automatic driving safety early warning method and system combining vehicle-road cooperation.
Background
With the continuous development of technology, the automatic driving technology gradually becomes a research hotspot in the automobile industry. However, safety issues with autopilot technology have been a focus of attention. Traffic accidents are frequent, and traffic jams and delays are common problems faced by modern urban traffic. At present, people pay attention to environmental protection, and reduction of automobile emission and environmental pollution is a problem to be solved urgently. In order to improve the safety of the automatic driving automobile, an automatic driving safety early warning method for the cooperation of the automobile and the road is generated. The automatic driving safety early warning method for vehicle-road cooperation is mainly based on a wireless communication technology, and information sharing and cooperative sensing between vehicles and road infrastructure and other vehicles are realized. In this way, the vehicle may obtain information about the surrounding environment, traffic conditions, obstacles, etc., thereby better predicting and avoiding potential hazards. Meanwhile, the road cooperative technology can also monitor the road condition in real time, discover potential safety hazards and timely send early warning information to the vehicle.
However, in the process of implementing the technical scheme of the embodiment of the application, the above technology is found to have at least the following technical problems:
the existing method excessively depends on historical data, so that the difficulty of real-time early warning is increased, the early warning accuracy is possibly reduced, and self-adaptive adjustment cannot be performed according to scene changes, so that the real-time performance of the early warning effect is limited.
Disclosure of Invention
The method mainly solves the problem that the existing method excessively depends on historical data, which increases the difficulty of real-time early warning, possibly reduces early warning accuracy, and cannot carry out self-adaptive adjustment according to scene changes, thereby limiting the real-time performance of early warning effect.
In view of the above problems, the present application provides an automatic driving safety precaution method and system in combination with vehicle-road cooperation, and in a first aspect, the present application provides an automatic driving safety precaution method in combination with vehicle-road cooperation, where the method includes: the automatic driving module is connected with the target vehicle and reads the real-time driving data of the target; based on the target real-time driving data, an interactive vehicle road cooperative system reads a driving association state data set of the target vehicle; modeling based on the driving association state data set and the target real-time driving data to obtain a target driving visual model; carrying out static vehicle-road cooperative safety detection on the target driving visual model according to a static vehicle-road cooperative safety detection channel to obtain a target static cooperative safety detection result; according to the dynamic vehicle-road cooperative safety detection channel, carrying out dynamic vehicle-road cooperative safety detection on the target driving visual model to obtain a target dynamic cooperative safety detection result; generating a target driving safety analysis report based on the target static cooperative safety detection result and the target dynamic cooperative safety detection result; and sending the target driving safety analysis report to a driving safety precaution device, and carrying out safety precaution on the target vehicle according to the driving safety precaution device, wherein the driving safety precaution device comprises static collaborative safety precaution constraint and dynamic collaborative safety precaution constraint.
In a second aspect, the present application provides an autopilot safety warning system in combination with roadway collaboration, the system comprising: the real-time driving data reading module is used for connecting with an automatic driving module of a target vehicle and reading target real-time driving data; the association state data set reading module is used for reading a driving association state data set of the target vehicle based on the target real-time driving data and an interactive vehicle path cooperative system; the target driving visual model acquisition module is used for modeling based on the driving association state data set and the target real-time driving data to acquire a target driving visual model; the static detection result acquisition module is used for carrying out static vehicle-road collaborative safety detection on the target driving visual model according to the static vehicle-road collaborative safety detection channel to obtain a target static collaborative safety detection result; the dynamic detection result acquisition module is used for carrying out dynamic vehicle-road collaborative safety detection on the target driving visual model according to the dynamic vehicle-road collaborative safety detection channel to obtain a target dynamic collaborative safety detection result; the safety analysis report generation module is used for generating a target driving safety analysis report based on the target static cooperative safety detection result and the target dynamic cooperative safety detection result; the safety early warning module is used for sending the target driving safety analysis report to a driving safety early warning device and carrying out safety early warning on the target vehicle according to the driving safety early warning device, wherein the driving safety early warning device comprises static cooperative safety early warning constraint and dynamic cooperative safety early warning constraint.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
the application provides an automatic driving safety pre-warning method and system combining vehicle-road cooperation, and relates to the technical field of data processing, wherein the method comprises the following steps: and reading target real-time driving data, then reading a driving association state data set, obtaining a target driving visual model, then carrying out static vehicle-road cooperative safety detection, obtaining a target static cooperative safety detection result, then carrying out dynamic vehicle-road cooperative safety detection, obtaining a dynamic cooperative safety detection result, generating a safety analysis report, and sending the safety analysis report to a safety precaution device for safety precaution.
The method mainly solves the problem that the existing method excessively depends on historical data, which increases the difficulty of real-time early warning, possibly reduces early warning accuracy, and cannot carry out self-adaptive adjustment according to scene changes, thereby limiting the real-time performance of early warning effect. And judging whether the vehicle has safety risk or illegal action in real time according to the dynamic cooperative safety detection result, and carrying out early warning, thereby improving the real-time performance and accuracy of the data.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
In order to more clearly illustrate the application or the technical solutions of the prior art, the following brief description will be given of the drawings used in the description of the embodiments or the prior art, it being obvious that the drawings in the description below are only exemplary and that other drawings can be obtained from the drawings provided without the inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an automatic driving safety early warning method combined with vehicle-road cooperation according to an embodiment of the application.
Fig. 2 is a schematic flow chart of a method for generating a visual model of target driving in an automatic driving safety pre-warning method combined with vehicle-road cooperation according to an embodiment of the application.
Fig. 3 is a schematic flow chart of a method for obtaining multiple dynamic cooperative safety coefficients in an automatic driving safety pre-warning method combined with vehicle-road cooperation according to an embodiment of the present application.
Fig. 4 is a schematic structural diagram of an automatic driving safety early warning system combined with vehicle-road cooperation according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a real-time driving data reading module 10, a correlation state data set reading module 20, a target driving visual model obtaining module 30, a static detection result obtaining module 40, a dynamic detection result obtaining module 50, a safety analysis report generating module 60 and a safety pre-warning module 70.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The method mainly solves the problem that the existing method excessively depends on historical data, which increases the difficulty of real-time early warning, possibly reduces early warning accuracy, and cannot carry out self-adaptive adjustment according to scene changes, thereby limiting the real-time performance of early warning effect. And judging whether the vehicle has safety risk or illegal action in real time according to the dynamic cooperative safety detection result, and carrying out early warning, thereby improving the real-time performance and accuracy of the data.
For a better understanding of the foregoing technical solutions, the following detailed description will be given with reference to the accompanying drawings and specific embodiments of the present invention:
Example 1
The automatic driving safety pre-warning method combined with the vehicle-road cooperation as shown in fig. 1 comprises the following steps:
the automatic driving module is connected with the target vehicle and reads the real-time driving data of the target;
Specifically, an interface and protocol for communicating with an autopilot module of a target vehicle. Including determining the format, rate, encryption mode, etc. of the data transmission to ensure safe, accurate and reliable transmission of the data. And the automatic driving module of the target vehicle is physically connected with the vehicle-road cooperative system through proper hardware equipment such as a serial port converter, a CAN bus adapter and the like. This enables data exchange and communication between the two. And then reading driving data of the target vehicle, and verifying and checking the data read from the automatic driving module of the target vehicle. This may be achieved by way of data hashing, checksum, etc. to ensure reliability and validity of the data. And formatting and standardizing the read target real-time driving data. The method comprises the steps of properly converting, encoding and decoding the original data, adapting the original data to the data format and standard of the vehicle-road cooperative system, and transmitting and sharing the processed target real-time driving data through the vehicle-road cooperative system. This allows for data interaction with other related vehicles or infrastructure, enabling information sharing and collaborative decisions. The automatic driving module of the target vehicle can be better connected, and the real-time driving data of the target can be accurately read. The data provides important input and basis for the automatic driving safety early warning method of the vehicle-road cooperation, and is beneficial to improving the accuracy and the instantaneity of early warning.
Based on the target real-time driving data, an interactive vehicle road cooperative system reads a driving association state data set of the target vehicle;
specifically, by installing sensors and devices on the target vehicle, driving data of the vehicle, including vehicle position, speed, acceleration, steering wheel angle, brake and accelerator pedal position, etc., are collected in real time. The data are transmitted through the vehicle-road cooperative system, and the vehicle-road cooperative system processes and analyzes the data after receiving the driving data of the target vehicle. This includes data cleaning, denoising, format conversion, etc. operations to ensure accuracy and reliability of the data. Meanwhile, the characteristics and modes related to the safety precaution are extracted through mining and analyzing the data. Based on the processed target real-time driving data, the vehicle-road coordination system generates a driving association state data set. The data set includes parameters such as relative position, speed, acceleration, etc. between the vehicles, as well as communication data and sensor data between the vehicles and the road infrastructure. The data reflect the running state and the behavior mode of the vehicle, and are helpful for accurate judgment of the early warning system. The road collaboration system supports data interaction and sharing between different vehicles and facilities. Through the vehicle-road cooperative system, related vehicles can acquire driving association state data sets of other vehicles in real time so as to realize information sharing and cooperative decision. This contributes to an improvement in the overall running efficiency and safety of road traffic. The data sets provide important input and basis for the automatic driving safety early warning method of the vehicle-road cooperation, and are beneficial to improving the accuracy and the instantaneity of early warning.
Modeling based on the driving association state data set and the target real-time driving data to obtain a target driving visual model;
Specifically, the driving association state data set and the target real-time driving data are preprocessed, including operations such as data cleaning, denoising, normalization and the like, so that the quality and the reliability of the data are improved. Features associated with the safety precaution, such as vehicle speed, acceleration, steering angle, braking status, etc., are extracted from the data. These features can reflect the driving state and behavior pattern of the vehicle, select a suitable machine learning or deep learning model, such as a Support Vector Machine (SVM), random forest, neural network, etc., and train and learn the features. Through training, the model can learn the internal rules and modes of the data, and the model is optimized and adjusted according to the training result so as to improve the accuracy and instantaneity of early warning. Including parameter adjustment, feature selection, model fusion, etc. And deploying the trained model in a vehicle-road cooperative system, and receiving the driving association state data set and the real-time driving data of the target vehicle in real time. And obtaining a visual target driving model, quickly generating early warning information through model calculation, and timely transmitting the early warning information to related personnel or vehicles so as to reduce accident risks. The accuracy and the instantaneity of early warning can be improved.
Carrying out static vehicle-road cooperative safety detection on the target driving visual model according to a static vehicle-road cooperative safety detection channel to obtain a target static cooperative safety detection result;
specifically, a static vehicle-road cooperative safety detection channel is established. The channel should have the capability of safety detection of vehicles and road infrastructure, including detection of vehicle position, speed, acceleration, etc., as well as sensing and recognition of road geometry, obstacles, traffic signals, etc. And taking the obtained visual target driving model as input, and transmitting the visual target driving model into the static vehicle-road cooperative safety detection channel. The model contains the running state and behavior pattern of the vehicle, and the interactions with other vehicles and road infrastructure. And the static vehicle-road collaborative safety detection channel performs safety detection analysis and evaluation on the target driving visual model. Based on a preset safety detection algorithm and rules, the channel analyzes parameters such as the running track, speed change, relative position among vehicles and the like of the vehicles, and judges whether potential safety risks or illegal behaviors exist. And generating a target static cooperative security detection result by the static vehicle-road cooperative security detection channel according to the security detection analysis and evaluation result. The results may be presented in numerical, textual, or visual form, indicating a safety issue or hazard with the vehicle during travel, and providing corresponding improvement advice. The static vehicle-road cooperative safety detection can be carried out on the target driving visual model according to the static vehicle-road cooperative safety detection channel, and a target static cooperative safety detection result is obtained. The result provides important information about the running safety of the vehicle for drivers and related institutions, is helpful for timely finding and solving potential safety problems, and improves the safety and reliability of road traffic.
According to the dynamic vehicle-road cooperative safety detection channel, carrying out dynamic vehicle-road cooperative safety detection on the target driving visual model to obtain a target dynamic cooperative safety detection result;
Specifically, the dynamic vehicle-road cooperative security detection channel should have the capability of sensing and identifying the vehicle and road environment changes in real time, including real-time detection of parameters such as position, speed, acceleration, behavior pattern and the like of other vehicles, and real-time sensing of road conditions and traffic flow. And taking the obtained visual target driving model as input, and transmitting the visual target driving model into a dynamic vehicle-road cooperative safety detection channel. The model contains real-time driving states and behavior patterns of the vehicle and real-time interaction relations with other vehicles and road infrastructure. And the dynamic vehicle-road collaborative safety detection channel performs real-time safety detection analysis and evaluation on the visual target driving model. Based on a preset safety detection algorithm and rules, the channel analyzes parameters such as real-time running track, speed change, relative position among vehicles and the like of the vehicles, and judges whether potential safety risks or illegal behaviors exist. And generating a target dynamic cooperative security detection result by the dynamic vehicle-road cooperative security detection channel according to the real-time security detection analysis and evaluation result. The results may be presented in numerical, textual, or visual form, indicating real-time safety issues or hazards in the vehicle during travel, and providing corresponding improvement suggestions. The dynamic vehicle-road cooperative safety detection can be carried out on the target driving visual model according to the dynamic vehicle-road cooperative safety detection channel, and a target dynamic cooperative safety detection result is obtained. The result provides important information about real-time safety of vehicle running for drivers and related institutions, is helpful for timely finding and solving potential safety problems, and improves safety and reliability of road traffic.
Generating a target driving safety analysis report based on the target static cooperative safety detection result and the target dynamic cooperative safety detection result;
Specifically, the target static cooperative security detection result and the target dynamic cooperative security detection result are integrated and compared. And analyzing potential safety problems and hidden dangers existing in the static detection result, and real-time safety risks and illegal behaviors in the dynamic detection result, so as to know the safety condition of the vehicle in the running process. Based on the integrated results, an in-depth security analysis was performed. The root causes that lead to safety problems, such as driver behavior, vehicle performance, road conditions, etc., are identified and analyzed. At the same time, the size and possible impact range of the security risk is assessed. And designing a framework of a target driving safety analysis report. The report should include portions such as headlines, summaries, description of the problem, analysis of the cause, suggested measures, etc., to facilitate understanding and taking of the corresponding improvements. And according to the result of the safety analysis, writing the specific content of the target driving safety analysis report. The report is ensured to objectively, accurately and completely reflect the safety condition of the vehicle in the running process, and specific improvement suggestions and measures are provided for the existing safety problems. And auditing and approving the written target driving safety analysis report. The report content is ensured to be accurate and meet the preset safety standard and requirement. And issuing the approved target driving safety analysis report to related personnel or institutions. The safety condition of the vehicle can be timely acquired and known by related personnel, so that corresponding measures can be adopted for improvement and optimization. And archiving the target driving safety analysis report, and establishing a corresponding updating mechanism. For subsequent security detection and analysis results, periodic updates and supplements can be made to ensure real-time and accuracy of the report. The target driving safety analysis report may be generated based on the target static cooperative safety detection result and the target dynamic cooperative safety detection result.
And sending the target driving safety analysis report to a driving safety precaution device, and carrying out safety precaution on the target vehicle according to the driving safety precaution device, wherein the driving safety precaution device comprises static collaborative safety precaution constraint and dynamic collaborative safety precaution constraint.
Specifically, the generated target driving safety analysis report is sent to a driving safety precaution device. The report contains the safety analysis results of the vehicle, including the static and dynamic cooperative safety detection results. And after the driving safety precaution device receives the report, carrying out safety precaution on the target vehicle according to the static cooperative safety precaution constraint. The static collaborative safety precaution constraint is set based on the static parameters of the vehicle and the safety threshold of the road infrastructure. And judging whether the vehicle has potential safety problems or illegal behaviors according to the static collaborative safety detection result in the target driving safety analysis report, and carrying out early warning according to the constraint conditions. Meanwhile, the driving safety precaution device carries out real-time safety precaution on the target vehicle according to dynamic cooperative safety precaution constraint. The dynamic collaborative safety precaution constraint is set based on real-time dynamic parameters of the vehicle and safety thresholds of the behavior mode. And judging whether the vehicle has safety risks or illegal behaviors in real time according to the dynamic collaborative safety detection result in the target driving safety analysis report, and carrying out early warning according to constraint conditions. And the driving safety precaution device generates corresponding safety precaution information according to the processing result of the static and dynamic cooperative safety precaution constraint. The early warning information can be output in the modes of sound, light, vibration and the like, so that a driver is reminded of the safety problem, and corresponding measures are taken for improvement and adjustment. After receiving the safety precaution information, the driver should take corresponding measures to respond and feed back. This includes adjusting the running state, avoiding dangerous behavior, selecting a safe running route, etc. to ensure safety during running. And evaluating the early warning effect of the driving safety precaution device according to the response and the feedback of the driver. The accuracy and timeliness of early warning and the influence of the response behavior of the driver on the safety are analyzed. Based on the evaluation result, the static and dynamic cooperative safety early warning constraint of the driving safety early warning device is optimized and adjusted, so that the accuracy and effectiveness of early warning are improved. The target driving safety analysis report can be sent to the driving safety precaution device, and safety precaution is carried out on the target vehicle according to the driving safety precaution device. The safety and the reliability of road traffic are improved.
Further, the method of the present application, based on the target real-time driving data, interacts with a vehicle road collaboration system to read a driving association status data set of the target vehicle, and includes:
extracting target driving position characteristic data according to the target real-time driving data;
The vehicle-road coordination system is connected, and a plurality of real-time vehicle-road coordination state data are read;
based on the target driving position feature data, respectively carrying out position association analysis on the plurality of real-time vehicle-road cooperative state data to obtain a plurality of position association degrees;
And screening the plurality of real-time vehicle-road collaborative state data according to the plurality of position relevancy based on a preset position relevancy constraint to obtain the driving relevancy state data set meeting the preset position relevancy constraint.
Specifically, target driving position feature data are extracted according to target real-time driving data, and position association analysis is carried out on a plurality of real-time vehicle-road cooperative state data based on the feature data so as to screen a driving association state data set meeting preset position association degree constraint. Extracting target driving position feature data: and processing and analyzing the real-time driving data of the target vehicle, and extracting the characteristic data related to the vehicle position. These characteristics may include latitude and longitude, direction of travel, speed, etc. Connecting the vehicle-road cooperation system and reading real-time vehicle-road cooperation state data: the system is connected with the vehicle-road cooperative system through a proper communication interface and a proper protocol. A plurality of real-time status data are read from the vehicle-road coordination system, which may include the position, speed, acceleration, traffic signal status, etc. of other vehicles. Position correlation analysis: and carrying out position correlation analysis on the real-time state data read from the vehicle-road cooperative system based on the position characteristic data of the target vehicle. The spatial and temporal relationships between the location of the target vehicle and each data point in the vehicle-road co-state data are analyzed. A degree of similarity or association between each data point and the location of the target vehicle is calculated. Screening data meeting preset position association degree constraint: and screening out vehicle-road coordination state data highly related to the position characteristics of the target vehicle according to a preset position association degree constraint condition. These data will constitute a driving association status data set satisfying a preset position association constraint. Obtaining a driving association state data set: according to the steps, a driving association state data set aiming at the target vehicle is finally obtained. The data set contains state information of other vehicles, traffic signals and the like closely related to the position of the target vehicle, and can be used for further driving behavior analysis and safety early warning. The position and the related state of the target vehicle in the road network can be more accurately identified and understood, and the key vehicle-road coordination state data highly related to the position of the target vehicle can be screened out.
Further, as shown in fig. 2, the method of the present application models based on the driving association status data set and the target real-time driving data to obtain a target driving visual model, and includes:
Reading vehicle entity data of the target vehicle;
invoking a related entity data set corresponding to the driving related state data set;
modeling based on the vehicle entity data and the associated entity data set to obtain a target driving scene model;
And rendering the driving association state data set and the target real-time driving data to the target driving scene model to generate the target driving visual model.
Specifically, vehicle entity data of the target vehicle is read: vehicle entity data is read from sensors or other data sources of the target vehicle. Such data may include physical properties of the vehicle (e.g., size, weight, maximum speed, etc.), the current state of the vehicle (e.g., position, speed, acceleration, etc.), and other vehicle-related information. Calling a related entity data set corresponding to the driving related state data set: based on the driving association state data sets obtained by screening, the association entity data sets related to the state data are further called from a vehicle-road coordination system or other data sources. The associated entity data set may include data of other related vehicles, traffic signals, road infrastructure, etc., which are closely related to the location and status of the target vehicle. Modeling is carried out based on vehicle entity data and associated entity data sets, and a target driving scene model is obtained: and combining the read vehicle entity data with the retrieved associated entity data set to perform modeling processing. Based on the data, a scene model is constructed that reflects the travel of the target vehicle in the road network, including the structure of the road network, traffic conditions, obstacle distribution, etc. Rendering the driving association state data set and the target real-time driving data to a target driving scene model to generate a target driving visual model: and rendering the driving association state data set and the target real-time driving data obtained by previous screening into a target driving scene model. By means of rendering technology, the data are combined with the scene model to generate a visual model, namely a visual model of target driving. The visual model is capable of graphically presenting the real-time location of the target vehicle in the road network, the relative relationship with other vehicles and traffic signals, and other relevant status information. Based on the generated target driving visual model, the processing of safety detection, behavior analysis, path planning and the like can be further performed. The visual model can also be used for a man-machine interaction interface to provide a driver or an automatic driving system with visual knowledge of the current road conditions and vehicle conditions. Through the steps, a scene model reflecting the running of the target vehicle in the road network can be constructed, real-time data are rendered into the model, and a visual target driving visual model is generated.
Furthermore, the method of the application carries out the static vehicle-road cooperative safety detection on the visual target driving model according to the static vehicle-road cooperative safety detection channel to obtain the target static cooperative safety detection result, and comprises the following steps:
Performing static vehicle-road collaborative scene recognition on the target driving visual model based on the target vehicle to obtain a plurality of target static collaborative scene models;
inputting the multiple target static collaborative scene models into the static vehicle-road collaborative safety detection channel to obtain multiple static collaborative safety coefficients;
And adding the plurality of static cooperative security coefficients to the target static cooperative security detection result.
Specifically, static vehicle-road collaborative scene recognition is performed on the target driving visual model based on the target vehicle: and carrying out static vehicle-road collaborative scene recognition on the target driving visual model by utilizing the vehicle entity data and the associated entity data set of the target vehicle. Static scene recognition is primarily the recognition and understanding of the location of vehicles in a road network, the status of traffic signals, the static layout and relative relationships of road infrastructure, and other related objects. Through static scene recognition, a plurality of target static collaborative scene models can be extracted from the visual model. Inputting a plurality of target static collaborative scene models into a static vehicle-road collaborative security detection channel: and inputting the extracted multiple target static collaborative scene models into a static vehicle-road collaborative security detection channel. The static vehicle-road cooperative safety detection channel has the capability of analyzing and evaluating the safety of a static scene. Based on a preset safety detection algorithm and rules, the channel can carry out safety detection on each target static collaborative scene model and calculate corresponding static collaborative safety coefficients. Obtaining a plurality of static cooperative safety coefficients: and after the analysis of the static vehicle-road cooperative safety detection channel, generating a static cooperative safety coefficient for each target static cooperative scene model. These static co-security coefficients reflect potential security problems and risks present in the scene model and can be used to evaluate the security of the vehicle in the static scene. Adding a plurality of static cooperative security coefficients to the target static cooperative security detection result: and adding the calculated multiple static cooperative security coefficients into a target static cooperative security detection result. The static scene of the target vehicle in the road network can be safely detected, and a corresponding static cooperative safety coefficient is generated. These results are of great significance for assessing road traffic safety and preventing potential risks and provide powerful support for further development and application of autopilot technology.
Furthermore, the method of the present application inputs the plurality of target static collaborative scene models into the static vehicle-road collaborative security detection channel to obtain a plurality of static collaborative security coefficients, and the method comprises:
based on a static vehicle-road cooperative safety detection record set, training a plurality of static vehicle-road cooperative safety detectors meeting preset convergence constraint, and embedding the plurality of static vehicle-road cooperative safety detectors into the static vehicle-road cooperative safety detection channel;
Obtaining a plurality of static safety detection precision corresponding to the plurality of static vehicle-road cooperative safety detectors;
Performing duty ratio calculation on the plurality of static safety detection precision to obtain static detection output excitation constraint, and embedding the static detection output excitation constraint into the static vehicle-road cooperative safety detection channel;
Extracting a first target static collaborative scene model based on the plurality of target static collaborative scene models;
inputting the first target static collaborative scene model into the plurality of static vehicle-road collaborative safety detectors to obtain a plurality of first static safety detection coefficients;
And carrying out weighted calculation on the plurality of first static safety detection coefficients according to the static detection output excitation constraint to obtain a first static cooperative safety coefficient, and adding the first static cooperative safety coefficient to the plurality of static cooperative safety coefficients.
Specifically, the static vehicle-road cooperative safety detector is trained based on the static vehicle-road cooperative safety detection record set: and training a plurality of static vehicle-road cooperative safety detectors meeting preset convergence constraints by using the static vehicle-road cooperative safety detection record set as training data. Through machine learning or deep learning algorithm, the static vehicle-road cooperative safety detector has the capability of automatically detecting and identifying the safety of a static scene. Embedding a plurality of static vehicle-road cooperative safety detectors into a static vehicle-road cooperative safety detection channel: and embedding the plurality of the static vehicle-road cooperative safety detectors obtained through training into the static vehicle-road cooperative safety detection channel. In this way, the channel has the ability to automatically analyze and detect the security of static scenes. Acquiring static safety detection precision: the embedded static road cooperative safety detector is tested to evaluate the safety detection precision of the static road cooperative safety detector in a static scene. And comparing the test result with the actual safety condition, and calculating to obtain the static safety detection precision of each static vehicle-road cooperative safety detector. And (3) duty ratio calculation is carried out on the static safety detection precision: and calculating the duty ratio according to the static safety detection precision of each static vehicle-road cooperative safety detector. This helps to understand the contribution and importance of each detector in the overall security detection. Obtaining a static detection output excitation constraint: and setting corresponding static detection output excitation constraints for each static vehicle-road cooperative safety detector according to the result of the duty ratio calculation. These constraints are used to guide the output weights of the detectors in the subsequent security detection process. Embedding the static detection output excitation constraint into a static vehicle-road cooperative safety detection channel: and embedding the obtained static detection output excitation constraint into a static vehicle-road cooperative safety detection channel. Thus, when the channel is used for safety detection, weight adjustment can be carried out according to the precision and excitation constraint of each detector, and the overall safety detection precision is improved. Extracting a first target static collaborative scene model: and extracting the first target static collaborative scene model from the target driving visual model based on a certain criterion or priority. This may refer to the scene model with the highest priority or most attention needed. Inputting the first target static collaborative scene model into a static vehicle-road collaborative safety detector: and inputting the extracted first target static collaborative scene model into a previously embedded static vehicle-road collaborative safety detector for safety detection. Obtaining a plurality of first static security detection coefficients: and calculating a plurality of first static safety detection coefficients related to the first target static cooperative scene model according to the output of the static vehicle-road cooperative safety detector. Weighting and calculating a first static safety detection coefficient according to the static detection output excitation constraint: and weighting the first static safety detection coefficient according to the static detection output excitation constraint determined previously. By means of the weighting calculation, a more representative first static collaborative security coefficient can be obtained. Adding the first static co-security factor to a plurality of static co-security factors: and adding the calculated first static cooperative security coefficient into a plurality of static cooperative security coefficients obtained before.
Further, as shown in fig. 3, the method of the present application performs dynamic vehicle-road cooperative security detection on the visual target driving model according to the dynamic vehicle-road cooperative security detection channel to obtain a target dynamic cooperative security detection result, and includes:
performing dynamic vehicle-road collaborative scene recognition on the target driving visual model based on the target vehicle to obtain a plurality of target dynamic collaborative scene models;
Inputting the multiple target dynamic cooperative scene models into the dynamic vehicle-road cooperative safety detection channel to obtain multiple dynamic cooperative safety coefficients;
And adding the dynamic collaborative security coefficients to the target dynamic collaborative security detection result.
Specifically, dynamic vehicle-road collaborative scene recognition is performed on the target driving visual model based on the target vehicle: and carrying out dynamic vehicle-road collaborative scene recognition on the scene model by utilizing the real-time data of the target vehicle and the target driving visual model. Dynamic scene recognition mainly focuses on dynamic changes of vehicles in road networks, traffic flow conditions, motion trajectories of other vehicles, and the like. Through dynamic scene recognition, multiple target dynamic collaborative scene models can be extracted from the visual model. Inputting a plurality of target dynamic collaborative scene models into a dynamic vehicle-road collaborative security detection channel: and inputting the plurality of target dynamic collaborative scene models extracted in the previous step into a dynamic vehicle-road collaborative security detection channel. The dynamic vehicle-road cooperative safety detection channel has the capability of analyzing and evaluating the safety of dynamic scenes. Based on a preset safety detection algorithm and rules, the channel can carry out safety detection on each target dynamic cooperative scene model and calculate corresponding dynamic cooperative safety coefficients. Obtaining a plurality of dynamic cooperative security coefficients: and after analysis of the dynamic vehicle-road cooperative safety detection channel, a dynamic cooperative safety coefficient is generated for each target dynamic cooperative scene model. The dynamic collaborative security coefficient reflects potential security problems and risks existing in the scene model and can be used for evaluating the security of the vehicle in the dynamic scene. And adding the calculated multiple dynamic cooperative security coefficients into a target dynamic cooperative security detection result. Through the steps, the safety detection can be carried out on the dynamic scene of the target vehicle in the road network, and corresponding dynamic cooperative safety coefficients are generated. These results are of great significance for assessing road traffic safety and preventing potential risks and provide powerful support for further development and application of autopilot technology.
Further, the method of the application comprises the steps of:
Calling a dynamic vehicle-road cooperative security detection set;
performing supervised training according to the dynamic vehicle-road cooperative safety detection set, and acquiring a dynamic detection loss operator when training is performed for preset times;
and if the dynamic detection loss operator is smaller than a preset loss operator, generating the dynamic vehicle-road cooperative safety detection channel.
Specifically, a dynamic vehicle-road cooperative security detection set is invoked: and the dynamic vehicle-road cooperative security detection set is invoked from a vehicle-road cooperative system or other data sources. This is a collection of dynamic scene samples that is used to train and optimize a dynamic roadway collaborative security detection pathway. Performing supervised training according to the dynamic vehicle-road cooperative safety detection set: and using the dynamic vehicle-road cooperative safety detection set as training data to perform supervised training on the dynamic vehicle-road cooperative safety detection channel. And calculating a dynamic detection loss operator by using a preset loss function through comparing the actual safety condition with the model prediction result. Each time training is performed for a preset number of times, a dynamic detection loss operator is obtained: in each training iteration, a dynamic detection loss operator is recorded or calculated. And calculating a dynamic detection loss operator by using a preset loss function through comparing the actual safety condition with the model prediction result. The dynamic detection loss operator is smaller than the preset loss operator: it is checked whether the current dynamic detection penalty operator is less than a predetermined penalty miscalculate sub-value. To determine if the performance of the model has improved. Generating a dynamic vehicle-road cooperative safety detection channel: if the dynamic detection loss operator is smaller than the preset loss operator, the safety detection capability of the model in the dynamic scene can be considered to be improved. Based on the current training state, a dynamic vehicle-road cooperative safety detection channel with better performance is generated. Through the steps, the performance of the dynamic vehicle-road cooperative safety detection channel can be continuously optimized and improved, and the safety detection precision of the dynamic vehicle-road cooperative safety detection channel in a dynamic scene is improved. This helps to improve the safety of road traffic and the reliability of the autopilot system.
Example two
Based on the same inventive concept as the automatic driving safety early warning method combined with the vehicle-road cooperation in the previous embodiment, as shown in fig. 4, the application provides an automatic driving safety early warning system combined with the vehicle-road cooperation, which comprises:
The real-time driving data reading module 10 is used for connecting an automatic driving module of a target vehicle and reading target real-time driving data;
The association state data set reading module 20 is used for reading a driving association state data set of the target vehicle based on the target real-time driving data by an interactive vehicle path cooperative system;
The target driving visual model obtaining module 30 is used for obtaining a target driving visual model by modeling based on the driving association state data set and the target real-time driving data by the target driving visual model obtaining module 30;
The static detection result obtaining module 40 is configured to perform static vehicle-road collaborative safety detection on the target driving visual model according to a static vehicle-road collaborative safety detection channel, so as to obtain a target static collaborative safety detection result;
The dynamic detection result acquisition module 50 is used for carrying out dynamic vehicle-road collaborative safety detection on the target driving visual model according to a dynamic vehicle-road collaborative safety detection channel to obtain a target dynamic collaborative safety detection result;
A safety analysis report generation module 60, wherein the safety analysis report generation module 60 generates a target driving safety analysis report based on the target static cooperative safety detection result and the target dynamic cooperative safety detection result;
The safety pre-warning module 70 is configured to send the target driving safety analysis report to a driving safety pre-warning device, and perform safety pre-warning on the target vehicle according to the driving safety pre-warning device, where the driving safety pre-warning device includes a static collaborative safety pre-warning constraint and a dynamic collaborative safety pre-warning constraint.
Further, the system further comprises:
The plurality of position association degree acquisition modules are used for extracting target driving position characteristic data according to the target real-time driving data; the vehicle-road coordination system is connected, and a plurality of real-time vehicle-road coordination state data are read; based on the target driving position feature data, respectively carrying out position association analysis on the plurality of real-time vehicle-road cooperative state data to obtain a plurality of position association degrees; and screening the plurality of real-time vehicle-road collaborative state data according to the plurality of position relevancy based on a preset position relevancy constraint to obtain the driving relevancy state data set meeting the preset position relevancy constraint.
Further, the system further comprises:
The target driving visual model generation module is used for reading vehicle entity data of the target vehicle; invoking a related entity data set corresponding to the driving related state data set; modeling based on the vehicle entity data and the associated entity data set to obtain a target driving scene model; and rendering the driving association state data set and the target real-time driving data to the target driving scene model to generate the target driving visual model.
Further, the system further comprises:
The static collaborative safety coefficient acquisition module is used for carrying out static vehicle-road collaborative scene recognition on the target driving visual model based on the target vehicle to acquire a plurality of target static collaborative scene models; inputting the multiple target static collaborative scene models into the static vehicle-road collaborative safety detection channel to obtain multiple static collaborative safety coefficients; and adding the plurality of static cooperative security coefficients to the target static cooperative security detection result.
Further, the system further comprises:
The static collaborative scene model extraction module is used for training a plurality of static vehicle-road collaborative safety detectors meeting preset convergence constraint based on a static vehicle-road collaborative safety detection record set, and embedding the plurality of static vehicle-road collaborative safety detectors into the static vehicle-road collaborative safety detection channel; obtaining a plurality of static safety detection precision corresponding to the plurality of static vehicle-road cooperative safety detectors; performing duty ratio calculation on the plurality of static safety detection precision to obtain static detection output excitation constraint, and embedding the static detection output excitation constraint into the static vehicle-road cooperative safety detection channel; extracting a first target static collaborative scene model based on the plurality of target static collaborative scene models; inputting the first target static collaborative scene model into the plurality of static vehicle-road collaborative safety detectors to obtain a plurality of first static safety detection coefficients; and carrying out weighted calculation on the plurality of first static safety detection coefficients according to the static detection output excitation constraint to obtain a first static cooperative safety coefficient, and adding the first static cooperative safety coefficient to the plurality of static cooperative safety coefficients.
Further, the system further comprises:
The dynamic cooperative safety coefficient acquisition module is used for carrying out dynamic vehicle-road cooperative scene recognition on the target driving visual model based on the target vehicle to acquire a plurality of target dynamic cooperative scene models; inputting the multiple target dynamic cooperative scene models into the dynamic vehicle-road cooperative safety detection channel to obtain multiple dynamic cooperative safety coefficients; and adding the dynamic collaborative security coefficients to the target dynamic collaborative security detection result.
Further, the system further comprises:
the safety detection channel generation module is used for calling a dynamic vehicle-road cooperative safety detection set; performing supervised training according to the dynamic vehicle-road cooperative safety detection set, and acquiring a dynamic detection loss operator when training is performed for preset times; and if the dynamic detection loss operator is smaller than a preset loss operator, generating the dynamic vehicle-road cooperative safety detection channel.
Through the foregoing detailed description of the automatic driving safety early warning method combined with the vehicle-road cooperation, those skilled in the art can clearly know that the automatic driving safety early warning system combined with the vehicle-road cooperation in this embodiment, and for the system disclosed in the embodiment, the description is simpler because it corresponds to the embodiment disclosure method, and relevant places refer to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. The automatic driving safety early warning method combined with the vehicle-road cooperation is characterized by comprising the following steps of:
the automatic driving module is connected with the target vehicle and reads the real-time driving data of the target;
Based on the target real-time driving data, the interactive vehicle road cooperative system reads a driving association state data set of the target vehicle, wherein the real-time driving data comprises a target vehicle position, a speed, an acceleration, a steering wheel angle, a brake and an accelerator pedal position, the real-time driving data is transmitted through the vehicle road cooperative system, after the driving data of the target vehicle is received, the vehicle road cooperative system performs data processing and analysis, and performs mining and analysis on the data, extracts characteristics and modes related to safety pre-warning, and generates the driving association state data set based on the processed target real-time driving data;
modeling based on the driving association state data set and the target real-time driving data to obtain a target driving visual model;
carrying out static vehicle-road cooperative safety detection on the target driving visual model according to a static vehicle-road cooperative safety detection channel to obtain a target static cooperative safety detection result, wherein the static vehicle-road cooperative safety detection channel has the capability of carrying out safety detection on vehicles and road infrastructures;
Carrying out dynamic vehicle-road cooperative safety detection on the target driving visual model according to a dynamic vehicle-road cooperative safety detection channel to obtain a target dynamic cooperative safety detection result, wherein the dynamic vehicle-road cooperative safety detection channel has the capability of sensing and identifying vehicle and road environment changes in real time;
generating a target driving safety analysis report based on the target static cooperative safety detection result and the target dynamic cooperative safety detection result;
The target driving safety analysis report is sent to a driving safety precaution device, and safety precaution is carried out on the target vehicle according to the driving safety precaution device, wherein the driving safety precaution device comprises static collaborative safety precaution constraint and dynamic collaborative safety precaution constraint;
modeling is performed based on the driving association state data set and the target real-time driving data, and a target driving visual model is obtained, and the method comprises the following steps:
Reading vehicle entity data of the target vehicle, wherein the vehicle entity data refers to reading the vehicle entity data from a sensor or other data source of the target vehicle, and comprises physical attributes of the vehicle, the current state of the vehicle and other information related to the vehicle;
Invoking the associated entity data set corresponding to the driving associated state data set, and further invoking the associated entity data set related to the state data from a vehicle-road cooperative system or other data sources based on the driving associated state data set obtained by screening, wherein the associated entity data set comprises other related vehicles, traffic signals and road infrastructure;
modeling based on the vehicle entity data and the associated entity data set to obtain a target driving scene model;
And rendering the driving association state data set and the target real-time driving data to the target driving scene model to generate the target driving visual model.
2. The method of claim 1, wherein based on the target real-time driving data, the interactive vehicle path coordination system reads a driving association status data set of the target vehicle, comprising:
extracting target driving position characteristic data according to the target real-time driving data;
The vehicle-road coordination system is connected, and a plurality of real-time vehicle-road coordination state data are read;
based on the target driving position feature data, respectively carrying out position association analysis on the plurality of real-time vehicle-road cooperative state data to obtain a plurality of position association degrees;
And screening the plurality of real-time vehicle-road collaborative state data according to the plurality of position relevancy based on a preset position relevancy constraint to obtain the driving relevancy state data set meeting the preset position relevancy constraint.
3. The method of claim 1, wherein performing static vehicle-road cooperative security detection on the target driving visual model according to a static vehicle-road cooperative security detection channel to obtain a target static cooperative security detection result, comprises:
Performing static vehicle-road collaborative scene recognition on the target driving visual model based on the target vehicle to obtain a plurality of target static collaborative scene models;
inputting the multiple target static collaborative scene models into the static vehicle-road collaborative safety detection channel to obtain multiple static collaborative safety coefficients;
And adding the plurality of static cooperative security coefficients to the target static cooperative security detection result.
4. The method of claim 3, wherein inputting the plurality of target static collaborative scene models into the static roadway collaborative safety detection pathway to obtain a plurality of static collaborative safety coefficients comprises:
based on a static vehicle-road cooperative safety detection record set, training a plurality of static vehicle-road cooperative safety detectors meeting preset convergence constraint, and embedding the plurality of static vehicle-road cooperative safety detectors into the static vehicle-road cooperative safety detection channel;
Obtaining a plurality of static safety detection precision corresponding to the plurality of static vehicle-road cooperative safety detectors;
Performing duty ratio calculation on the plurality of static safety detection precision to obtain static detection output excitation constraint, and embedding the static detection output excitation constraint into the static vehicle-road cooperative safety detection channel;
Extracting a first target static collaborative scene model based on the plurality of target static collaborative scene models;
inputting the first target static collaborative scene model into the plurality of static vehicle-road collaborative safety detectors to obtain a plurality of first static safety detection coefficients;
And carrying out weighted calculation on the plurality of first static safety detection coefficients according to the static detection output excitation constraint to obtain a first static cooperative safety coefficient, and adding the first static cooperative safety coefficient to the plurality of static cooperative safety coefficients.
5. The method of claim 1, wherein performing dynamic vehicle-road cooperative security detection on the target driving visual model according to a dynamic vehicle-road cooperative security detection channel to obtain a target dynamic cooperative security detection result, comprising:
performing dynamic vehicle-road collaborative scene recognition on the target driving visual model based on the target vehicle to obtain a plurality of target dynamic collaborative scene models;
Inputting the multiple target dynamic cooperative scene models into the dynamic vehicle-road cooperative safety detection channel to obtain multiple dynamic cooperative safety coefficients;
And adding the dynamic collaborative security coefficients to the target dynamic collaborative security detection result.
6. The method of claim 5, wherein the method comprises:
Calling a dynamic vehicle-road cooperative security detection set;
performing supervised training according to the dynamic vehicle-road cooperative safety detection set, and acquiring a dynamic detection loss operator when training is performed for preset times;
and if the dynamic detection loss operator is smaller than a preset loss operator, generating the dynamic vehicle-road cooperative safety detection channel.
7. An automatic driving safety pre-warning system combined with vehicle-road cooperation, characterized in that the system comprises:
the real-time driving data reading module is used for connecting with an automatic driving module of a target vehicle and reading target real-time driving data;
The system comprises a correlation state data set reading module, a vehicle-road coordination system and a vehicle-road coordination system, wherein the correlation state data set reading module is used for reading a driving correlation state data set of a target vehicle based on the target real-time driving data, the real-time driving data comprises a target vehicle position, a speed, an acceleration, a steering wheel angle, a brake and an accelerator pedal position, the real-time driving data is transmitted through the vehicle-road coordination system, the vehicle-road coordination system is used for carrying out data processing and analysis after receiving the driving data of the target vehicle, mining and analyzing the data, extracting characteristics and modes related to safety pre-warning, and generating the driving correlation state data set based on the processed target real-time driving data;
the target driving visual model acquisition module is used for modeling based on the driving association state data set and the target real-time driving data to acquire a target driving visual model;
the static detection result acquisition module is used for carrying out static vehicle-road collaborative safety detection on the target driving visual model according to a static vehicle-road collaborative safety detection channel to obtain a target static collaborative safety detection result, and the static vehicle-road collaborative safety detection channel has the capability of carrying out safety detection on vehicles and road infrastructures;
The dynamic detection result acquisition module is used for carrying out dynamic vehicle-road collaborative safety detection on the target driving visual model according to a dynamic vehicle-road collaborative safety detection channel to obtain a target dynamic collaborative safety detection result, and the dynamic vehicle-road collaborative safety detection channel has the capability of sensing and identifying the changes of the vehicle and road environment in real time;
The safety analysis report generation module is used for generating a target driving safety analysis report based on the target static cooperative safety detection result and the target dynamic cooperative safety detection result;
the safety early warning module is used for sending the target driving safety analysis report to a driving safety early warning device and carrying out safety early warning on the target vehicle according to the driving safety early warning device, wherein the driving safety early warning device comprises static cooperative safety early warning constraint and dynamic cooperative safety early warning constraint;
the system further comprises:
The system comprises a target driving visual model generation module, a target driving visual model generation module and a target driving visual model generation module, wherein the target driving visual model generation module is used for reading vehicle entity data of a target vehicle, and the vehicle entity data refer to reading vehicle entity data from a sensor or other data source of the target vehicle, wherein the vehicle entity data comprises physical attributes of the vehicle, the current state of the vehicle and other information related to the vehicle; invoking the associated entity data set corresponding to the driving associated state data set, and further invoking the associated entity data set related to the state data from a vehicle-road cooperative system or other data sources based on the driving associated state data set obtained by screening, wherein the associated entity data set comprises other related vehicles, traffic signals and road infrastructure; modeling based on the vehicle entity data and the associated entity data set to obtain a target driving scene model; and rendering the driving association state data set and the target real-time driving data to the target driving scene model to generate the target driving visual model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410179105.1A CN117727183B (en) | 2024-02-18 | 2024-02-18 | Automatic driving safety early warning method and system combining vehicle-road cooperation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410179105.1A CN117727183B (en) | 2024-02-18 | 2024-02-18 | Automatic driving safety early warning method and system combining vehicle-road cooperation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117727183A CN117727183A (en) | 2024-03-19 |
| CN117727183B true CN117727183B (en) | 2024-05-17 |
Family
ID=90211071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410179105.1A Active CN117727183B (en) | 2024-02-18 | 2024-02-18 | Automatic driving safety early warning method and system combining vehicle-road cooperation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117727183B (en) |
Citations (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109559532A (en) * | 2018-12-10 | 2019-04-02 | 北京工业大学 | Expressway exit shunting zone bus or train route Cooperative Security pre-warning and control method |
| CN110264783A (en) * | 2019-06-19 | 2019-09-20 | 中设设计集团股份有限公司 | Vehicle collision avoidance early warning system and method based on bus or train route collaboration |
| CN110364009A (en) * | 2019-07-16 | 2019-10-22 | 华人运通(上海)自动驾驶科技有限公司 | Traveling planing method, device, roadside device and storage medium based on roadside device |
| CN110779730A (en) * | 2019-08-29 | 2020-02-11 | 浙江零跑科技有限公司 | L3-level automatic driving system testing method based on virtual driving scene vehicle on-ring |
| CN111540237A (en) * | 2020-05-19 | 2020-08-14 | 河北德冠隆电子科技有限公司 | Method for automatically generating vehicle safety driving guarantee scheme based on multi-data fusion |
| CN111915915A (en) * | 2020-07-16 | 2020-11-10 | 华人运通(上海)自动驾驶科技有限公司 | Driving scene reconstruction method, device, system, vehicle, equipment and storage medium |
| CN112216146A (en) * | 2020-09-16 | 2021-01-12 | 浙江吉利控股集团有限公司 | Vehicle risk early warning method, device and equipment and vehicle |
| CN112532698A (en) * | 2020-11-17 | 2021-03-19 | 招商新智科技有限公司 | Method and system for linkage release of highway dangerous driving early warning and guidance screen |
| CN113485319A (en) * | 2021-06-08 | 2021-10-08 | 中兴智能汽车有限公司 | Automatic driving system based on 5G vehicle-road cooperation |
| CN113724531A (en) * | 2021-08-05 | 2021-11-30 | 武汉理工大学 | Intersection human-vehicle road cooperation early warning system and method under Internet of vehicles environment |
| CN113763703A (en) * | 2021-08-06 | 2021-12-07 | 腾讯科技（深圳）有限公司 | Driving risk early warning method and device, computer readable medium and electronic equipment |
| CN114118795A (en) * | 2021-11-26 | 2022-03-01 | 同济大学 | Safety risk degree evaluation grading and dynamic early warning method for intelligent heavy-load expressway |
| CN114141007A (en) * | 2021-10-15 | 2022-03-04 | 广东轻工职业技术学院 | Vehicle-road cooperative information interaction method and system based on intelligent traffic |
| CN114200849A (en) * | 2021-12-06 | 2022-03-18 | 苏州挚途科技有限公司 | Virtual simulation test system and method for automatic driving |
| CN114241750A (en) * | 2021-11-29 | 2022-03-25 | 重庆文理学院 | Vehicle-road cooperative information interaction system and method based on intelligent road traffic risk early warning method |
| WO2022063331A1 (en) * | 2020-09-25 | 2022-03-31 | 金龙联合汽车工业（苏州）有限公司 | V2x-based formation driving networked intelligent passenger vehicle |
| WO2022156520A1 (en) * | 2021-01-25 | 2022-07-28 | 国汽智控(北京)科技有限公司 | Cloud-road collaborative automatic driving model training method and system, and cloud-road collaborative automatic driving model calling method and system |
| CN115116216A (en) * | 2022-05-24 | 2022-09-27 | 清华大学 | Global cooperative sensing and decision-making method and device based on vehicle-road cloud interface |
| CN115257784A (en) * | 2022-06-15 | 2022-11-01 | 西安电子科技大学 | Vehicle-road cooperative system based on 4D millimeter wave radar |
| CN115290349A (en) * | 2022-07-29 | 2022-11-04 | 中汽创智科技有限公司 | Automatic driving test system |
| CN115512511A (en) * | 2021-06-07 | 2022-12-23 | 中移物联网有限公司 | Early warning method, early warning device, mobile terminal and readable storage medium |
| CN115649198A (en) * | 2022-11-03 | 2023-01-31 | 中科天极(新疆)空天信息有限公司 | Automatic vehicle driving method and system |
| WO2023088679A1 (en) * | 2021-11-22 | 2023-05-25 | Five AI Limited | Generating simulation environments for testing autonomous vehicle behaviour |
| WO2023103459A1 (en) * | 2021-12-07 | 2023-06-15 | 中兴通讯股份有限公司 | Vehicle control method, decision server, and storage medium |
| CN116384755A (en) * | 2023-06-02 | 2023-07-04 | 国汽(北京)智能网联汽车研究院有限公司 | Method and device for determining cooperative driving safety of vehicle Lu Yun, vehicle and storage medium |
| CN116767281A (en) * | 2023-07-21 | 2023-09-19 | 中国第一汽车股份有限公司 | Auxiliary driving method, device, equipment, vehicle and medium |
| CN117184109A (en) * | 2022-05-31 | 2023-12-08 | 武汉路特斯汽车有限公司 | Vehicle control method and system based on Internet of vehicles |
| CN117275235A (en) * | 2023-10-09 | 2023-12-22 | 广州吉码电子科技股份有限公司 | Vehicle monitoring method and system |
| CN117369427A (en) * | 2023-11-02 | 2024-01-09 | 中国第一汽车股份有限公司 | Automatic driving visualization method, device, system and storage medium |
| CN117452946A (en) * | 2023-11-16 | 2024-01-26 | 河南科技大学 | Intelligent automobile remote driving method and system based on digital twin |
| CN117519951A (en) * | 2024-01-04 | 2024-02-06 | 深圳博瑞天下科技有限公司 | Real-time data processing method and system based on message center |
| KR20240015762A (en) * | 2022-07-27 | 2024-02-06 | 주식회사 엘지유플러스 | Method for transmitting vehicle data for cooperative-intelligent transport systems and connected autonomous driving, and device and system therefor |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200262423A1 (en) * | 2020-05-08 | 2020-08-20 | Intel Corporation | Systems, devices, and methods for risk-aware driving |
| US20230282112A1 (en) * | 2022-01-31 | 2023-09-07 | Nissan North America, Inc. | System and Method for Intersection Collision Avoidance |
-
2024
- 2024-02-18 CN CN202410179105.1A patent/CN117727183B/en active Active
Patent Citations (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109559532A (en) * | 2018-12-10 | 2019-04-02 | 北京工业大学 | Expressway exit shunting zone bus or train route Cooperative Security pre-warning and control method |
| CN110264783A (en) * | 2019-06-19 | 2019-09-20 | 中设设计集团股份有限公司 | Vehicle collision avoidance early warning system and method based on bus or train route collaboration |
| CN110364009A (en) * | 2019-07-16 | 2019-10-22 | 华人运通(上海)自动驾驶科技有限公司 | Traveling planing method, device, roadside device and storage medium based on roadside device |
| CN110779730A (en) * | 2019-08-29 | 2020-02-11 | 浙江零跑科技有限公司 | L3-level automatic driving system testing method based on virtual driving scene vehicle on-ring |
| CN111540237A (en) * | 2020-05-19 | 2020-08-14 | 河北德冠隆电子科技有限公司 | Method for automatically generating vehicle safety driving guarantee scheme based on multi-data fusion |
| CN111915915A (en) * | 2020-07-16 | 2020-11-10 | 华人运通(上海)自动驾驶科技有限公司 | Driving scene reconstruction method, device, system, vehicle, equipment and storage medium |
| CN112216146A (en) * | 2020-09-16 | 2021-01-12 | 浙江吉利控股集团有限公司 | Vehicle risk early warning method, device and equipment and vehicle |
| WO2022063331A1 (en) * | 2020-09-25 | 2022-03-31 | 金龙联合汽车工业（苏州）有限公司 | V2x-based formation driving networked intelligent passenger vehicle |
| CN112532698A (en) * | 2020-11-17 | 2021-03-19 | 招商新智科技有限公司 | Method and system for linkage release of highway dangerous driving early warning and guidance screen |
| WO2022156520A1 (en) * | 2021-01-25 | 2022-07-28 | 国汽智控(北京)科技有限公司 | Cloud-road collaborative automatic driving model training method and system, and cloud-road collaborative automatic driving model calling method and system |
| CN115512511A (en) * | 2021-06-07 | 2022-12-23 | 中移物联网有限公司 | Early warning method, early warning device, mobile terminal and readable storage medium |
| CN113485319A (en) * | 2021-06-08 | 2021-10-08 | 中兴智能汽车有限公司 | Automatic driving system based on 5G vehicle-road cooperation |
| CN113724531A (en) * | 2021-08-05 | 2021-11-30 | 武汉理工大学 | Intersection human-vehicle road cooperation early warning system and method under Internet of vehicles environment |
| CN113763703A (en) * | 2021-08-06 | 2021-12-07 | 腾讯科技（深圳）有限公司 | Driving risk early warning method and device, computer readable medium and electronic equipment |
| CN114141007A (en) * | 2021-10-15 | 2022-03-04 | 广东轻工职业技术学院 | Vehicle-road cooperative information interaction method and system based on intelligent traffic |
| WO2023088679A1 (en) * | 2021-11-22 | 2023-05-25 | Five AI Limited | Generating simulation environments for testing autonomous vehicle behaviour |
| CN114118795A (en) * | 2021-11-26 | 2022-03-01 | 同济大学 | Safety risk degree evaluation grading and dynamic early warning method for intelligent heavy-load expressway |
| CN114241750A (en) * | 2021-11-29 | 2022-03-25 | 重庆文理学院 | Vehicle-road cooperative information interaction system and method based on intelligent road traffic risk early warning method |
| CN114200849A (en) * | 2021-12-06 | 2022-03-18 | 苏州挚途科技有限公司 | Virtual simulation test system and method for automatic driving |
| WO2023103459A1 (en) * | 2021-12-07 | 2023-06-15 | 中兴通讯股份有限公司 | Vehicle control method, decision server, and storage medium |
| CN115116216A (en) * | 2022-05-24 | 2022-09-27 | 清华大学 | Global cooperative sensing and decision-making method and device based on vehicle-road cloud interface |
| CN117184109A (en) * | 2022-05-31 | 2023-12-08 | 武汉路特斯汽车有限公司 | Vehicle control method and system based on Internet of vehicles |
| CN115257784A (en) * | 2022-06-15 | 2022-11-01 | 西安电子科技大学 | Vehicle-road cooperative system based on 4D millimeter wave radar |
| KR20240015762A (en) * | 2022-07-27 | 2024-02-06 | 주식회사 엘지유플러스 | Method for transmitting vehicle data for cooperative-intelligent transport systems and connected autonomous driving, and device and system therefor |
| CN115290349A (en) * | 2022-07-29 | 2022-11-04 | 中汽创智科技有限公司 | Automatic driving test system |
| CN115649198A (en) * | 2022-11-03 | 2023-01-31 | 中科天极(新疆)空天信息有限公司 | Automatic vehicle driving method and system |
| CN116384755A (en) * | 2023-06-02 | 2023-07-04 | 国汽(北京)智能网联汽车研究院有限公司 | Method and device for determining cooperative driving safety of vehicle Lu Yun, vehicle and storage medium |
| CN116767281A (en) * | 2023-07-21 | 2023-09-19 | 中国第一汽车股份有限公司 | Auxiliary driving method, device, equipment, vehicle and medium |
| CN117275235A (en) * | 2023-10-09 | 2023-12-22 | 广州吉码电子科技股份有限公司 | Vehicle monitoring method and system |
| CN117369427A (en) * | 2023-11-02 | 2024-01-09 | 中国第一汽车股份有限公司 | Automatic driving visualization method, device, system and storage medium |
| CN117452946A (en) * | 2023-11-16 | 2024-01-26 | 河南科技大学 | Intelligent automobile remote driving method and system based on digital twin |
| CN117519951A (en) * | 2024-01-04 | 2024-02-06 | 深圳博瑞天下科技有限公司 | Real-time data processing method and system based on message center |
Non-Patent Citations (4)
| Title |
|---|
| Experimental validation of intent sharing in cooperative maneuvering;Wang 等;2020 IEEE Intelligent vehicles Symposium;20230810;1-6 * |
| Safety analysis based on critical scenarios and collision avoidance of highly automated vehicle;Li 等;2020 IEEE 5th international conference on intelligent transportion engineering;20210422;355-360 * |
| 基于自动驾驶的车辆安全技术应用探讨;刘秀红 等;时代汽车;20230630(第06期);175-177 * |
| 面向智能网联的驾驶行为识别与预测预警方法研究;贾硕;中国博士学位论文全文数据库 工程科技Ⅱ辑;20230515(第2023年第05期期);C034-32 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117727183A (en) | 2024-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3533681B1 (en) | Method for detecting safety of driving behavior, apparatus and storage medium | |
| CN111052202A (en) | System and method for safe autonomous driving based on relative positioning | |
| JP2015501459A (en) | Computing platform for the development and deployment of sensor-driven vehicle telemetry applications and services | |
| Lv et al. | Automatic vehicle-pedestrian conflict identification with trajectories of road users extracted from roadside LiDAR sensors using a rule-based method | |
| Hong et al. | A driver behavior assessment and recommendation system for connected vehicles to produce safer driving environments through a “follow the leader” approach | |
| Eboli et al. | Measuring the driver's perception error in the traffic accident risk evaluation | |
| US11553363B1 (en) | Systems and methods for assessing vehicle data transmission capabilities | |
| Lu et al. | Performance evaluation of surrogate measures of safety with naturalistic driving data | |
| CN115273480B (en) | Traffic early warning system and method based on big data analysis | |
| CN112835790A (en) | Test method, device, equipment and medium for automatic driving software | |
| CN117727183B (en) | Automatic driving safety early warning method and system combining vehicle-road cooperation | |
| Peng et al. | Evaluation of emergency driving behaviour and vehicle collision risk in connected vehicle environment: A deep learning approach | |
| He et al. | [Retracted] An Individual Driving Behavior Portrait Approach for Professional Driver of HDVs with Naturalistic Driving Data | |
| US20230054889A1 (en) | Automatically tracking a trajectory of a vehicle | |
| CN116151045A (en) | Vehicle simulation test data accuracy analysis method, device, equipment and medium | |
| CN112346969B (en) | AEB development verification system and method based on data acquisition platform | |
| Fazio et al. | A new application for analyzing driving behavior and environment characterization in transportation systems based on a fuzzy logic approach | |
| Xu et al. | Novel fast safety assessment method for the buffer section of maintenance work zone | |
| Srinivasan et al. | Advanced Driver Assistance System (ADAS) in Autonomous Vehicles: A Complete Analysis | |
| Porwik et al. | A stable method for detecting driver maneuvers using a rule classifier | |
| Ma et al. | Exploring the Behavior‐Driven Crash Risk Prediction Model: The Role of Onboard Navigation Data in Road Safety | |
| CN117104255B (en) | Intelligent perception human-vehicle interaction system and method for intelligent driving vehicle | |
| KR102377233B1 (en) | System for acquiring mobility data under real driving circumstance and for simulating them | |
| CN118094424A (en) | Vehicle behavior analysis method and system based on Fourier transform | |
| CN117922595A (en) | Obstacle monitoring and early warning method and system based on automatic driving |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |