CN116434523A - Vehicle active safety control method and device based on constraint degree in information perception scene - Google Patents
Vehicle active safety control method and device based on constraint degree in information perception scene Download PDFInfo
- Publication number
- CN116434523A CN116434523A CN202211513038.XA CN202211513038A CN116434523A CN 116434523 A CN116434523 A CN 116434523A CN 202211513038 A CN202211513038 A CN 202211513038A CN 116434523 A CN116434523 A CN 116434523A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- road
- information
- constraint degree
- constraint
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000008447 perception Effects 0.000 title claims abstract description 8
- 238000012544 monitoring process Methods 0.000 claims abstract description 49
- 238000011217 control strategy Methods 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 15
- 230000033001 locomotion Effects 0.000 claims description 39
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 10
- 238000003066 decision tree Methods 0.000 claims description 6
- 230000006399 behavior Effects 0.000 description 20
- 206010039203 Road traffic accident Diseases 0.000 description 11
- 238000007726 management method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000013058 risk prediction model Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/164—Centralised systems, e.g. external to vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses a vehicle active safety control method and device based on constraint degree in an information perception scene, wherein the method comprises the following steps: s01, establishing a coordinate system for different types of road nodes, and carrying out regional subdivision, and establishing a road node database; s02, sensing and capturing road, vehicle and traffic flow information and storing the information; s03, calculating constraint degree and training to form a constraint degree prediction model; s04, triggering safety early warning and acquiring ID number information of a current vehicle when the vehicle is detected to enter a preset road node; s05, acquiring current real-time vehicle monitoring data and surrounding environment information; s06, calculating the constraint degree level of the current vehicle and predicting the vehicle risk state; s07, controlling to acquire corresponding active vehicle control strategy release according to the constraint degree level of the current prediction; s08, updating a database and a vehicle safety early warning model. The invention has the advantages of simple implementation method, high control precision, high efficiency, safety, reliability and the like.
Description
Technical Field
The invention relates to the technical field of vehicle safety control, in particular to a vehicle active safety control method and device based on constraint degree in an information perception scene.
Background
The complex road node is a road section easy to develop traffic accidents, and the accident frequent reason is mainly that the driving behavior is mixed due to the complex environment of the road, and the vehicle can frequently change the road and turn around at the complex road node. If the active safety control of the vehicle can be realized, the risk is predicted when the vehicle has accident risk, and the vehicle is actively controlled, so that the possibility of accident occurrence can be effectively reduced, and the running safety of the vehicle is improved. The key point is to realize the prediction of the accident risk of the vehicle. The vehicle accident risk can be predicted according to the driving behavior, and the method for realizing the vehicle accident risk prediction aiming at the driving behavior in the prior art is mainly realized by adopting the following modes:
1. and (5) extracting historical data by utilizing road nodes to establish an accident risk prediction model. The patent application CN112949999 discloses a high-speed traffic accident risk early warning method, which comprises the steps of extracting minute-level traffic flow and average speed from a high-speed fixed node to obtain a regional vehicle collision index; clustering by using a Gaussian Mixture Model (GMM), and dividing high-speed accident risk levels; and extracting features by using Bayesian deep learning, predicting the minute-level vehicle flow and the average speed of a future target node, calculating the regional vehicle collision index, and providing safety early warning according to the risk level. However, the method only can actually represent the historical state by using the historical data modeling, and certain errors exist when the historical state is used for representing the state of the future node, so that the method cannot accurately predict the real-time traffic accident risk of the vehicle, only considers the influencing factors such as the traffic flow, the average speed and the like, and is difficult to accurately predict the running risk of the single vehicle.
2. And establishing a real-time accident risk prediction model by utilizing the historical data aiming at the conventional road environment. As disclosed in patent application CN104732075, a real-time prediction method for urban road traffic accident risk is disclosed, which comprises the steps of extracting geometric line data of a research road section, historical traffic flow basic data n minutes before traffic accidents occur and historical weather condition data, establishing a real-time urban road traffic accident prediction model based on poisson distribution, performing model calibration by using the historical data, and calculating the grade and distribution probability of the real-time traffic flow characteristic and the weather condition data converted into classification variables to obtain a traffic accident analysis prediction result. The method is only suitable for risk prediction of conventional roads, is difficult to be suitable for traffic accident risk prediction of complex nodes, only considers traffic flow characteristics and weather factors, is difficult to accurately reflect potential risks of vehicles, and simultaneously needs to perform a large amount of preprocessing on real-time acquired data to obtain prediction results, and has high requirements on system computing capacity, so that the prediction efficiency is not high.
In summary, in the prior art, the vehicle risk prediction mode is generally suitable for a conventional road environment, cannot be suitable for accident risk prediction at complex nodes, and generally considers conventional traffic flow characteristics, weather and other influencing factors, so that the vehicle risk prediction mode can only be suitable for accident risk prediction under simple terrain and general driving behaviors, the driving risk of a single vehicle cannot be accurately predicted, in addition, the mode of establishing a model by using historical data also has the problem of poor real-time performance, real-time prediction of the vehicle accident risk by using real-time vehicle cooperative data cannot be fully utilized, and therefore, the vehicle safety management and control is difficult to realize quickly and accurately.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the technical problems existing in the prior art, the invention provides a vehicle active safety control method, a vehicle active safety control method and a vehicle active safety control device based on constraint degree in an information perception scene, wherein the vehicle active safety control method, the vehicle active safety control method and the vehicle active safety control device are simple in implementation method, high in prediction precision and efficiency, and safe and reliable.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
a vehicle active safety control method based on constraint degree in an information perception scene comprises the following steps:
s01, establishing a coordinate system for different types of road nodes, and inserting a plurality of sub-nodes into a monitoring range corresponding to each road node to subdivide areas, so as to establish a road node database;
s02, sensing and capturing road, vehicle and traffic flow information based on road side information sensing equipment and storing the road, vehicle and traffic flow information;
s03, selecting historical sample data from a vehicle motion information database according to a preset time period, calculating the constraint degree of the vehicle on each road node according to the selected historical sample data, and training to form a constraint degree prediction model aiming at each road node;
s04, triggering safety early warning and acquiring ID number information of a current vehicle when the vehicle is detected to enter a specified range around a preset road node;
s05, acquiring the current vehicle and real-time monitoring information of traffic flow where the current vehicle is located according to the ID number information of the current vehicle, and acquiring real-time motion and surrounding environment information of each vehicle in a specified range around the current road node;
s06, calculating the constraint degree of the current vehicle according to the constraint degree prediction model and the information obtained in the step S05, predicting the vehicle risk state according to the calculated constraint degree, and issuing early warning information;
s07, controlling to acquire and issue a corresponding pre-configured active vehicle management and control strategy according to the constraint degree level obtained by current prediction;
s08, updating a vehicle motion information database and a vehicle safety early warning model according to a preset time period.
Further, the step S01 includes:
s101, establishing a coordinate system: establishing a coordinate system for each road node, wherein an origin is determined according to an end point along a driving direction in a boundary point of each node area, an x axis and a y axis are determined according to the driving direction, and a road plane coordinate system of each node is established;
s102, region subdivision: and determining a corresponding monitoring range according to the characteristics of each road node, and subdividing the area into a plurality of secondary monitoring areas in the monitoring range corresponding to the x axis of each node, wherein the monitoring range comprises a vehicle interweaving road section and a section of normal environment road section connected with the vehicle interweaving road section.
Further, the constraint degree is calculated according to the following formula:
wherein i represents a region, si is the degree of constraint of the vehicle in the ith secondary region compared with the 1 st secondary region, and the 1 st secondary region is a normal road section, alpha 1 Is the weight of the lane change index, alpha 2 The weight of the angle index; l (L) i C for the lane change frequency of the vehicle in the ith area i An average running angle of the vehicle in the i-th region, C 0 Is the minimum angle value of the vehicle in all areas.
Further, in the step S03, the constraint degree of the vehicle at each road node is calculated by extracting the characteristic parameter from the historical sample data, and model training is performed on the constraint degree calculated by each road node by using a decision tree model, wherein the calculated constraint degree is taken as a predicted value, and the constraint degree predicted model for each road node is constructed by taking the real-time motion information of the vehicle, the surrounding traffic flow state and the road environment information extracted from the historical sample data as independent variables.
Further, the characteristic parameters include any of a toll type of the vehicle, a real-time position of the vehicle, a real-time speed of the vehicle, a real-time lane change condition of the vehicle, a distance between a current position of the vehicle and a node destination, a current lane where the vehicle is located, a real-time traffic flow around the vehicle, a real-time traffic flow mixing degree around the vehicle, a road node type where the vehicle is located, a road width or a curvature radius where the vehicle is located, a road marking type, a lane change frequency of the vehicle in each secondary area, and an average running angle of the vehicle in each secondary area.
Further, the step S07 includes:
dividing the constraint degree into a plurality of grades in advance, and configuring corresponding vehicle management and control strategies for the constraint degrees of different grades;
controlling a vehicle according to a vehicle control strategy corresponding to the constraint degree level obtained by current prediction;
if the vehicle is within the specified range around the preset road node, returning to the step S05 to continuously monitor the position and the motion state of the current vehicle, and calculating the obtained constraint degree prediction vehicle risk state and controlling the vehicle according to the vehicle management and control strategy corresponding to the constraint degree level obtained by the current prediction until the vehicle leaves the current road node.
Further, the dividing the constraint into a plurality of levels includes:
determining the potential possibility of the vehicle driving risk according to the level of the constraint degree, wherein the constraint degree S of each road node i i ∈[a，b]，S i Minimum constraint degree, highest corresponding vehicle risk when=a, S i Maximum constraint and minimum corresponding vehicle risk when=b;
and determining constraint degree distribution value range intervals of the sample data and determining a plurality of constraint degree grading thresholds according to constraint degree calculation results of the historical sample data so as to divide the constraint degree of the vehicle in a secondary region into a plurality of grades, wherein the secondary region is a region obtained by conducting regional subdivision in a corresponding monitoring range determined by each road node.
A vehicle active safety control device based on constraint degree under an information sensing scene, comprising:
the database building module is used for building a coordinate system for different types of road nodes, and inserting a plurality of sub-nodes into the monitoring range corresponding to each road node to subdivide the area, so as to build a road node database;
the road side information sensing equipment is used for sensing and capturing road, vehicle and traffic flow information and storing the information;
the constraint degree calculation and model training module is used for selecting historical sample data from the vehicle motion information database according to a preset time period, calculating the constraint degree of the vehicle at each road node for the selected historical sample data, and training to form a constraint degree prediction model for each road node;
the early warning triggering module is used for triggering safety early warning and acquiring ID number information of the current vehicle when detecting that the vehicle enters a specified range around a preset road node;
the information acquisition module is used for acquiring the current vehicle and the real-time monitoring information of the traffic flow of the current vehicle according to the ID number information of the current vehicle, and acquiring the real-time movement and surrounding environment information of each vehicle in a specified range around the current road node;
the risk prediction module is used for calculating the constraint degree grade of the current vehicle according to the constraint degree prediction model and the information acquired by the information acquisition module, predicting the vehicle risk state according to the constraint degree grade and issuing early warning information;
the active safety control module is used for controlling the acquisition and release of the corresponding pre-configured active vehicle control strategy according to the constraint degree level obtained by current prediction;
and the updating module is used for updating the vehicle motion information database and the vehicle safety early warning model according to the preset time period.
A computer device comprising a processor and a memory for storing a computer program, the processor being adapted to execute the computer program to perform the vehicle risk prediction method described above, or to perform the management method described above.
A computer readable storage medium storing a computer program which when executed performs a method as described above.
Compared with the prior art, the invention has the advantages that:
1. the method introduces the concept of constraint degree in a mechanical principle aiming at a special environment of complex road nodes, establishes a road node database by dividing the road nodes, calculates the constraint degree of the vehicle at each road node by utilizing historical sample data of the vehicle, trains to form a constraint degree prediction model aiming at each road node, acquires real-time information of the vehicle and communication, surrounding environment information and the like when the vehicle enters the complex road node appointed in advance, predicts the constraint degree of the vehicle in real time by utilizing the real-time information and the constraint degree prediction model, predicts the potential risk of the vehicle, can solve the problem of insufficient constraint consideration of the environment of the complex node in the traditional risk prediction method, can be suitable for realizing effective prediction of the safety condition of the vehicle aiming at different nodes in the complex road environment, and realizes real-time and accurate prediction of the traffic accident risk of the vehicle at the complex node, thereby effectively ensuring the traffic safety of the vehicle and avoiding traffic accident at the complex node.
2. According to the method, the association relation between the driving behavior constraint degree and the vehicle safety of the complex road node is established, the driving behavior constraint degree is utilized to predict the vehicle driving accident risk, the constraint degree level of the vehicle is determined according to the prediction result, and the corresponding active safety decision is further obtained according to the predicted constraint degree level to feed back, so that the adaptive vehicle active safety control strategy can be flexibly obtained under different risks and the like, and the driving safety of the vehicle under various environments is effectively ensured.
Drawings
Fig. 1 is a schematic flow chart of an implementation of a constraint-based vehicle risk prediction method in an information-aware scenario according to the present embodiment.
Fig. 2 is a schematic diagram of the effect of establishing a coordinate system for complex road nodes in a specific application embodiment.
Fig. 3 is a schematic diagram showing the effect of the subdivision of the zones in a specific application embodiment of the present invention.
Fig. 4 is a schematic structural diagram of a vehicle control device according to an embodiment of the present invention.
Detailed Description
The invention is further described below in connection with the drawings and the specific preferred embodiments, but the scope of protection of the invention is not limited thereby.
In the complex road node, the complex environment of the road causes the driving behavior to be mixed, the vehicle can frequently change the road and turn around in the complex road node, and the characteristic represented by the constraint degree is the characteristic that the motion of the vehicle can reduce the constraint degree, namely the constraint degree of the driving behavior, so that the potential risk of the vehicle can be accurately reflected to a certain degree. The driving behavior constraint degree index can fundamentally represent the influence of a complex environment on a driver, so that the complex situation of the environment can be effectively reflected, and the constraint influence of a special road environment of a complex road node on the driving behavior of the driver is far different from that of a conventional road environment, so that the potential risk prediction of the vehicle at the complex road node can be effectively realized by using the driving behavior constraint degree.
According to the method, the characteristics are utilized, the concept of constraint degree in a mechanical principle is introduced for a special environment of complex road nodes, a road node database is established by dividing the road nodes, then the constraint degree (driving behavior constraint degree) of the vehicle at each road node is calculated by utilizing historical sample data of the vehicle, a constraint degree prediction model for each road node is formed through training, when the vehicle enters the pre-designated complex road node, real-time information of the vehicle and communication, surrounding environment information and the like are obtained, the constraint degree of the vehicle is predicted in real time by utilizing the real-time information and the constraint degree prediction model, and the potential risk of the vehicle can be predicted based on the constraint degree, so that the problem of insufficient constraint consideration for the complex node environment in the traditional risk prediction method can be solved, the method can be suitable for realizing effective prediction of the vehicle safety conditions for different nodes, realizing real-time and accurate prediction of the vehicle driving accident risk at the complex node, effectively ensuring the vehicle driving safety, and avoiding the occurrence of traffic accident at the complex node. Meanwhile, through establishing the association relation between the constraint degree of driving behaviors and the vehicle safety of the complex road nodes, the risk of the vehicle driving accident is predicted by utilizing the constraint degree of the driving behaviors, the constraint degree level of the vehicle is determined by utilizing the prediction result, and the corresponding active safety decision is further obtained according to the predicted constraint degree level to feed back, so that the adaptive active safety control strategy of the vehicle can be flexibly obtained under different risks and the like, and the driving safety of the vehicle under various environments is effectively ensured.
As shown in fig. 1, the specific steps of the vehicle risk prediction method based on the constraint degree in the information sensing scene of the embodiment include:
s01, establishing a coordinate system for different types of road nodes, and inserting a plurality of sub-nodes into a monitoring range corresponding to each road node to subdivide areas, so as to establish a road node database;
s02, sensing and capturing road, vehicle and traffic flow information based on road side information sensing equipment and storing the road, vehicle and traffic flow information;
s03, selecting historical sample data from a vehicle motion information database according to a preset time period, calculating the constraint degree of the vehicle on each road node according to the selected historical sample data, and training to form a constraint degree prediction model aiming at each road node;
s04, triggering safety early warning and acquiring ID number information of a current vehicle when the vehicle is detected to enter a specified range around a preset road node;
s05, acquiring the current vehicle and real-time monitoring information of traffic flow where the current vehicle is located according to the ID number information of the current vehicle, and acquiring real-time motion and surrounding environment information of each vehicle in a specified range around the current road node;
s06, calculating the constraint degree of the current vehicle according to the constraint degree prediction model and the information obtained in the step S05, predicting the vehicle risk state according to the calculated constraint degree and issuing early warning information;
s07, controlling to acquire and issue a corresponding pre-configured active vehicle management and control strategy according to the constraint degree level obtained by current prediction;
s08, updating a vehicle motion information database and a vehicle safety early warning model according to a preset time period.
In this embodiment, step S01 establishes a coordinate system for different types of complex road nodes, performs regional subdivision, and establishes a complete complex road node database, which specifically includes:
s101, establishing a coordinate system: establishing a coordinate system for each road node, wherein an origin is determined according to an end point along a driving direction in a boundary point of each node area, an x axis and a y axis are determined according to the driving direction, and a road plane coordinate system of each node is established;
s102, region subdivision: and determining a corresponding monitoring range according to the characteristics of each road node, and subdividing the area into a plurality of secondary monitoring area monitoring ranges in the monitoring range corresponding to the x axis of each node, wherein each secondary monitoring area monitoring range comprises a vehicle interweaving road section and a section of normal environment road section connected with the vehicle interweaving road section.
In the step S101, a complete road plane coordinate system on each road node is established by taking a south end point along the driving direction in the node area boundary point as an origin, taking the driving direction as an x axis and taking the driving direction cross section direction as a y axis. The specific construction mode of the coordinate system can be configured according to actual requirements.
In the step S102, the complete monitoring range of each road node may be specifically determined according to the characteristics of the complex road node, where the monitoring range includes two parts: 1. road segments (vehicle-interleaved segments) where vehicle interleaving is likely to occur; 2. a normal surrounding road section (a regular road section where vehicle interleaving is less likely to occur) connected to the 1 region (vehicle interleaving road section) in the upstream direction of the traveling. And uniformly inserting a plurality of sub-points into the complex road node area in the corresponding monitoring range on the x coordinate axis of each road node so as to subdivide the complete monitoring range of the node into a plurality of uniform-length secondary monitoring areas.
In a specific application embodiment, it is assumed that the built complex road node database is denoted as complex road node set n= { N 1 ,n 2 … … }, then node n therein 1 The specific steps of coordinate system establishment and region subdivision are as follows:
(1) Establishing a coordinate system: for complex road node n 1 Establishing coordinatesIs based on node n 1 The south end point (when the routine vehicle direction is the west direction, the southwest end point) along the driving direction in the boundary point of the area is taken as an origin, the driving direction is taken as an x axis, the section direction of the driving direction is taken as a y axis, and a node n is established 1 And (5) a complete road plane coordinate system. The effect of establishing a coordinate system for complex road nodes in a specific application embodiment is shown in fig. 2.
(2) Region subdivision: firstly, determining a node n according to the node characteristics of a complex road 1 Complete monitoring range, at node n 1 Uniformly inserting i-1 sub-points into the complex road node area in the corresponding monitoring range on the x coordinate axis of (1), and connecting the node n 1 The complete monitoring range is subdivided into i uniform length secondary monitoring regions. Numbering the secondary regions d in order of the x-coordinate from the largest to the smallest 1 、d 2 …d i The secondary region set is noted as d= { D 1 、d 2 …d i }, where d 1 For a regular main line road section corresponding to a vehicle interleaved section, a complex road node of length L is divided into i length
Is a secondary region of (c). Let O point be the origin of the coordinate system, its coordinates be (0, 0), then the left boundary of the nth region along the x-axis is +.>
Right border is +.>
In a specific application embodiment, fig. 3 is a schematic diagram of the initial lane and the toll gate of the toll gate diversion area divided in the above manner, and the numbers of the divided areas are shown in the figure.
In this embodiment, the constraint degree is specifically calculated according to the following formula:
where i represents the area, si is the degree of restriction to which the vehicle is subjected in the ith secondary area compared with the 1 st secondary area (i.e. normal environmental road section), α 1 Is the weight of the lane change index, alpha 2 The weight of the angle index; l (L) i C for the lane change frequency of the vehicle in the ith area i An average running angle of the vehicle in the i-th region, C 0 Is the minimum angle value of the vehicle in all areas.
After the road node coordinate system is established and the subdivision result of the area is obtained, the historical sample data is calculated based on the coordinate system and the result, and particularly, the vehicle microscopic track information can be extracted by adopting a computer video recognition technology to further extract effective characteristic parameters for constraint degree calculation. After the road node database is established, in step S02 of the present embodiment, information of the road, the vehicle and the traffic flow is perceived and captured based on the road side information perceiving device in real time and stored, so as to obtain a database of information of the road, the traffic flow and the vehicle movement. In step S03 of this embodiment, the constraint degree of the vehicle at each road node is calculated by extracting the feature parameter from the historical sample data, and model training is performed on the constraint degree calculated by each road node by using a decision tree model, where the calculated constraint degree is taken as a predicted value, and real-time motion information of the vehicle, the surrounding traffic flow state and the road environment information extracted from the historical sample data are taken as independent variables, so as to construct a constraint degree prediction model for each road node.
The characteristic parameters specifically include a charging type of the vehicle, a real-time position of the vehicle, a real-time speed of the vehicle, a real-time lane changing condition of the vehicle, a distance between a current position of the vehicle and a node destination, a current lane where the vehicle is located, a surrounding real-time traffic flow of the vehicle, a real-time traffic flow mixing degree of the surrounding of the vehicle, a road node type where the vehicle is located, a road width or a curvature radius where the vehicle is located, a road marking type, lane changing frequency of the vehicle in each secondary area, an average running angle of the vehicle in each secondary area and the like, and the characteristic parameters can be specifically selected according to actual requirements.
In a specific application embodiment, after relevant parameters of a historical sample are extracted according to a certain time period, a decision tree model is adopted, constraint degree calculated in the formula (1) is taken as a predicted value (namely a dependent variable), parameters such as real-time motion information of a vehicle, surrounding traffic flow state and road environment information extracted from the historical sample are taken as independent variables, model training and model verification results are carried out, and finally a constraint degree level prediction model aiming at each complex road node is constructed.
In a specific application embodiment, the historical sample data may be extracted in a cycle of the monitoring period T, for example, one week is taken as a monitoring period t=7 days, and the historical sample data is 5 small pieces of data extracted in a day before the monitoring period, which are respectively a peak in the morning and evening, a peak in the afternoon and the afternoon, and a period of each night, and the time length of each small piece of data is not less than 30 minutes. In a specific application embodiment, the selected historical sample data is: the instantaneous speed of the vehicle entering the toll station diversion area is 50.78km/h; the overall average speed of the vehicle in zone 1 is 42.50km/h, the speed of the vehicle when the vehicle is about to drive into the toll road is 23.57km/h, and the overall average speed in zone 8 is 22.28km/h; the average speed of the vehicle is 33.79km/h; the average travel time of the vehicle through the complex node was 20.23s. The driving angle characteristics of the vehicle extracted in the specific application example are shown in table 1, and the lane change behavior characteristics of the vehicle are shown in table 2.
TABLE 1 Driving Angle characterization
TABLE 2 vehicle lane change behavior characteristics
In a specific application embodiment, a decision tree model can be built by a MATLAB box, and a cross-validation method is selected to validate the model. The fitting precision of the decision tree model is 84.9%, the auc=0.90 of the model, and the true instance rate (i.e. sensitivity) is 90%, i.e. the authenticity of the model is high.
In the step S04, when the real-time monitoring of the safety state of the complex road node is started, the real-time ID of the vehicle is established in the form of a number for the vehicle entering the monitored area, and the ID of the vehicle located at the same node in the same period of time is configured to be unrepeatable.
In the step S05, the real-time monitoring data of the vehicle and the traffic flow are obtained through the road monitoring device, wherein the real-time monitoring data specifically comprises speed data collected through a radar velocimeter, vehicle track data collected through a high-definition camera, position data obtained through a high-precision positioning device, vehicle type data collected through a charging mode, and the like, and the real-time monitoring data can be specifically selected according to actual requirements. The real-time motion parameters and the surrounding environment parameters of the vehicle specifically include independent variables required by the constraint degree prediction model constructed in the step S03, and the calculation can be specifically completed by two stages of edge calculation and cloud calculation in order to ensure that the calculation speed meets the requirement of safety early warning, for example, the simple motion parameters of the vehicle are calculated by a Road Side Unit (Road Side Unit), and the complex motion parameters highway management platform performs cloud auxiliary calculation.
In a specific application embodiment, when the method disclosed by the invention is adopted to realize vehicle risk prediction, firstly, a coordinate system is established for different types of complex road nodes, region subdivision is carried out, and a complete complex road node database is established; then selecting sample data from a vehicle motion information database according to a certain time period to construct a constraint degree prediction model; when a vehicle enters a complex road node, the road detection equipment monitors the vehicle and then triggers the complex road node safety early warning function, and the vehicle obtains a unique vehicle ID; then, acquiring real-time vehicle motion information and environment information, acquiring real-time vehicle and traffic flow monitoring data through road monitoring equipment, and calculating and acquiring real-time motion and surrounding environment information of each vehicle; according to the obtained related data and the established constraint degree prediction model, calculating the driving behavior constraint degree of the vehicle, and predicting the risk of the vehicle according to the constraint degree, namely, the corresponding risk of the vehicle, wherein the potential risk is higher when the constraint degree is smaller.
The specific steps for realizing active safety control of the vehicle by using the vehicle risk prediction result in step S07 of the present embodiment include:
dividing the constraint degree into a plurality of grades in advance, and configuring corresponding vehicle management and control strategies for the constraint degrees of different grades;
controlling a vehicle according to a vehicle control strategy corresponding to the constraint degree level obtained by current prediction;
if the vehicle is within the specified range around the preset road node, returning to the step S05 to continuously monitor the position and the motion state of the current vehicle, and predicting the vehicle risk state by the calculated constraint degree and controlling the vehicle according to the vehicle management strategy corresponding to the constraint degree level obtained by the current prediction until the vehicle leaves the current road node.
According to the vehicle risk prediction method, the vehicle risk prediction is carried out on the basis of the driving behavior constraint degree, the constraint degree level of the vehicle is determined according to the prediction result, and the corresponding control strategy output is called on the basis of the constraint degree level, so that the adaptive vehicle active safety control strategy can be flexibly obtained under different risks and the like, and the driving safety of the vehicle under various environments is effectively ensured.
The constraint degree can be divided into a plurality of constraint degree grades according to actual conditions, and an active safety control decision-making library is formulated based on the constraint degree grades, and the method specifically comprises the following steps:
(1) Determining a constraint degree level: the potential possibility of the running risk of the vehicle is measured by the constraint degree, and the lower the constraint degree is, the more the vehicle is limited by road marking, sign marks or peripheral traffic flows, the greater the possibility of changing the motion state of the vehicle is, and the higher the peripheral traffic flow mixing degree is, namely the higher the running risk is.
Set S i ∈[a，b]，S i The constraint degree is the smallest when the vehicle running risk is the highest, and S i The constraint is the largest when =b, and the vehicle running risk is the lowest. Based on a sample data vehicle constraint degree calculation result, a sample constraint degree distribution value range interval is determined, three constraint degree classification thresholds (namely classification judgment critical points) are determined according to a percentile method (25%, 50% and 75%) to divide the motion constraint degree of the vehicle in a secondary region into AFour ranks B, C, D, from a to D, represent a low rise in constraint, i.e., a high fall in vehicle risk potential.
(2) Making an active safety control decision base based on the constraint degree level: four-level control decision is made towards A, B, C, D four-level constraint degree, and complex road node n 1 The hierarchical active security management decision content of (2) is shown in table 4.
TABLE 3 Complex road node n 1 Hierarchical active security management decisions for (1)
In a specific application embodiment, the constraint degree level of the vehicle is calculated once every 3-5 seconds, the decision is updated along with time change and is issued to a road side electronic display screen or an intelligent vehicle-mounted terminal, and further active safety control decision information can be issued to the road side electronic display screen and the intelligent vehicle-mounted terminal, so that a user can acquire the active safety control decision information in real time.
In a specific application embodiment, when the method is adopted to carry out vehicle safety control, the constraint degree is divided into a plurality of constraint degree grades in advance according to actual conditions, and an active safety control decision base is formulated based on the constraint degree grades; after predicting the motion constraint degree level of the vehicle, acquiring an active safety decision corresponding to the current constraint degree level based on an active safety control decision library, and issuing early warning information and the active safety decision to a road side information display screen and an intelligent vehicle-mounted terminal; and after the driver acquires the information, taking corresponding measures, monitoring the position and the motion state of the vehicle by the road monitoring equipment, updating the position and the motion information of the corresponding vehicle in a database, and circularly executing the risk prediction of the vehicle until the vehicle leaves the complex node. It can be understood that after the current active safety control strategy of the vehicle is obtained, the vehicle can be configured to control the vehicle according to the obtained active safety decision according to actual requirements so as to realize automatic control.
The vehicle active safety control device based on the constraint degree in the information sensing scene of the embodiment comprises:
the database building module is used for building a coordinate system for different types of road nodes, and inserting a plurality of sub-nodes into the monitoring range corresponding to each road node to subdivide the area, so as to build a road node database;
the road side information sensing equipment is used for sensing and capturing road, vehicle and traffic flow information and storing the information;
the constraint degree calculation and model training module is used for selecting historical sample data from the vehicle motion information database according to a preset time period, calculating the constraint degree of the vehicle at each road node for the selected historical sample data, and training to form a constraint degree prediction model for each road node;
the early warning triggering module is used for triggering safety early warning and acquiring ID number information of the current vehicle when detecting that the vehicle enters a specified range around a preset road node;
the information acquisition module is used for acquiring the current vehicle and real-time monitoring data of traffic flow where the current vehicle is located according to the ID number information of the current vehicle, and acquiring real-time movement and surrounding environment information of each vehicle in a specified range around the current road node;
the risk prediction module is used for calculating the constraint degree grade of the current vehicle according to the constraint degree prediction model and the data acquired by the information acquisition module, predicting the risk state of the vehicle according to the constraint degree grade and issuing early warning information;
the active safety control module is used for controlling the acquisition and release of the corresponding pre-configured active vehicle control strategy according to the constraint degree level obtained by current prediction;
and the updating module is used for updating the vehicle motion information database and the vehicle safety early warning model according to the preset time period.
The modules can be realized in a mode of independent respectively or in a mode of integrating the modules, and the functions of the modules can be realized by different independent modules. For example, in a specific application embodiment, as shown in fig. 4, the active safety control device for a vehicle of this embodiment specifically includes:
the vehicle ID building module is used for building ID numbers for all vehicles in the node in real time;
the information storage module is used for storing real-time dynamic data acquired by the monitoring device, static data such as complex road node basic data and vehicle basic data;
the real-time traffic information acquisition module is used for acquiring vehicle driving data in real time, wherein the vehicle driving data comprises information such as charging type of a vehicle, real-time position of the vehicle, real-time speed of the vehicle, real-time lane changing condition of the vehicle, distance between the current position of the vehicle and a node destination, current lane where the vehicle is located, real-time traffic flow around the vehicle, the mixing degree of the traffic flow around the vehicle, the node type of the road where the vehicle is located, the width or curvature radius of the road where the vehicle is located, the road marking type and the like;
the restraint degree level calculation and active safety decision making module is used for calculating restraint degree levels of the vehicle at different positions in real time according to related algorithms and data, and making an active safety decision according to the restraint degree levels;
and the information release module is used for releasing the initiative safety decision information on the road side electronic display screen and transmitting the initiative safety decision information to the vehicle-mounted information transmission device.
Further, the system also comprises an information dynamic updating module which is used for uploading the acquired updated vehicle driving data to the information system.
The traffic information acquisition module specifically comprises vehicle motion information sensing equipment and/or a GPS positioning system at a complex road node; the information dynamic updating module comprises an internet-connected information system and/or a vehicle information sharing platform.
In this embodiment, the vehicle risk prediction device based on the driving behavior constraint degree corresponds to the vehicle risk prediction method based on the driving behavior constraint degree in a one-to-one manner, and the control device corresponds to the control method in a one-to-one manner, which is not described in detail herein.
The computer apparatus of this embodiment includes a processor and a memory, where the memory is configured to store a computer program, and the processor is configured to execute the computer program to perform the method or perform the method.
The present embodiment also provides a computer-readable storage medium storing a computer program which, when executed, implements a method as described above.
The foregoing is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. While the invention has been described with reference to preferred embodiments, it is not intended to be limiting. Therefore, any simple modification, equivalent variation and modification of the above embodiments according to the technical substance of the present invention shall fall within the scope of the technical solution of the present invention.
Claims (10)
1. The vehicle active safety control method based on the constraint degree in the information perception scene is characterized by comprising the following steps:
s01, establishing a coordinate system for different types of road nodes, and inserting a plurality of sub-nodes into a monitoring range corresponding to each road node to subdivide areas, so as to establish a road node database;
s02, sensing and capturing road, vehicle and traffic flow information based on road side information sensing equipment and storing the road, vehicle and traffic flow information;
s03, selecting historical sample data from a vehicle motion information database according to a preset time period, calculating the constraint degree of the vehicle on each road node according to the selected historical sample data, and training to form a constraint degree prediction model aiming at each road node;
s04, triggering safety early warning and acquiring ID number information of a current vehicle when the vehicle is detected to enter a specified range around a preset road node;
s05, acquiring the current vehicle and real-time monitoring information of traffic flow where the current vehicle is located according to the ID number information of the current vehicle, and acquiring real-time motion and surrounding environment information of each vehicle in a specified range around the current road node;
s06, calculating the constraint degree of the current vehicle according to the constraint degree prediction model and the information obtained in the step S05, predicting the vehicle risk state according to the calculated constraint degree, and issuing early warning information;
s07, controlling to acquire and issue a corresponding pre-configured active vehicle management and control strategy according to the constraint degree level obtained by current prediction;
s08, updating a vehicle motion information database and a vehicle safety early warning model according to a preset time period.
2. The method for actively controlling safety of a vehicle based on constraint degree in an information-aware scenario according to claim 1, wherein the step S01 comprises:
s101, establishing a coordinate system: establishing a coordinate system for each road node, wherein an origin is determined according to an end point along a driving direction in a boundary point of each node area, an x axis and a y axis are determined according to the driving direction, and a road plane coordinate system of each node is established;
s102, region subdivision: and determining a corresponding monitoring range according to the characteristics of each road node, and subdividing the area into a plurality of secondary monitoring areas in the monitoring range corresponding to the x axis of each node, wherein the monitoring range comprises a vehicle interweaving road section and a section of normal environment road section connected with the vehicle interweaving road section.
3. The method for actively controlling safety of a vehicle based on a constraint degree in an information-aware scene according to claim 1, wherein the constraint degree is calculated according to the following formula:
wherein i represents a region, si is the degree of constraint of the vehicle in the ith secondary region compared with the 1 st secondary region, and the 1 st secondary region is a normal road section, alpha 1 Is the weight of the lane change index, alpha 2 The weight of the angle index; l (L) i C for the lane change frequency of the vehicle in the ith area i An average running angle of the vehicle in the i-th region, C 0 Is the minimum angle value of the vehicle in all areas.
4. The method according to claim 1, wherein in the step S03, the constraint degree of the vehicle at each road node is calculated by extracting feature parameters from historical sample data, and model training is performed on the constraint degree calculated by each road node by using a decision tree model, wherein the calculated constraint degree is used as a predicted value, and real-time motion information of the vehicle, surrounding traffic flow states and road environment information extracted from the historical sample data are used as independent variables, so as to construct the constraint degree prediction model for each road node.
5. The method for actively controlling safety of a vehicle based on constraint degree in an information-aware scene according to claim 4, wherein the characteristic parameters include any of a toll type of the vehicle, a real-time position of the vehicle, a real-time speed of the vehicle, a real-time lane change condition of the vehicle, a distance between a current position of the vehicle and a node destination, a current lane of the vehicle, a real-time traffic flow around the vehicle, a real-time traffic flow mixing degree around the vehicle, a road node type on which the vehicle is located, a road width or a radius of curvature on which the vehicle is located, a road marking type, a lane change frequency of the vehicle in each secondary area, and an average driving angle of the vehicle in each secondary area.
6. The method for actively controlling safety of a vehicle based on constraint degrees in an information-aware scenario according to claim 5, wherein the step of step S07 comprises:
dividing the constraint degree into a plurality of grades in advance, and configuring corresponding vehicle management and control strategies for the constraint degrees of different grades;
controlling a vehicle according to a vehicle control strategy corresponding to the constraint degree level obtained by current prediction;
if the vehicle is within the specified range around the preset road node, returning to the step S05 to continuously monitor the position and the motion state of the current vehicle, and calculating the obtained constraint degree prediction vehicle risk state and controlling the vehicle according to the vehicle management and control strategy corresponding to the constraint degree level obtained by the current prediction until the vehicle leaves the current road node.
7. The method for actively controlling safety of a vehicle based on a constraint degree in an information-aware scene of claim 6, wherein said classifying the constraint degree into a plurality of levels comprises:
determining the potential possibility of the vehicle driving risk according to the level of the constraint degree, wherein the constraint degree S of each road node i i ∈[a，b]，S i Minimum constraint degree, highest corresponding vehicle risk when=a, S i Maximum constraint and minimum corresponding vehicle risk when=b;
and determining constraint degree distribution value range intervals of the sample data and determining a plurality of constraint degree grading thresholds according to constraint degree calculation results of the historical sample data so as to divide the constraint degree of the vehicle in a secondary region into a plurality of grades, wherein the secondary region is a region obtained by conducting regional subdivision in a corresponding monitoring range determined by each road node.
8. The utility model provides a vehicle initiative safety control device based on restraint under information perception scene which characterized in that includes:
the database building module is used for building a coordinate system for different types of road nodes, and inserting a plurality of sub-nodes into the monitoring range corresponding to each road node to subdivide the area, so as to build a road node database;
the road side information sensing equipment is used for sensing and capturing road, vehicle and traffic flow information and storing the information;
the constraint degree calculation and model training module is used for selecting historical sample data from the vehicle motion information database according to a preset time period, calculating the constraint degree of the vehicle at each road node for the selected historical sample data, and training to form a constraint degree prediction model for each road node;
the early warning triggering module is used for triggering safety early warning and acquiring ID number information of the current vehicle when detecting that the vehicle enters a specified range around a preset road node;
the information acquisition module is used for acquiring the current vehicle and the real-time monitoring information of the traffic flow of the current vehicle according to the ID number information of the current vehicle, and acquiring the real-time movement and surrounding environment information of each vehicle in a specified range around the current road node;
the risk prediction module is used for calculating the constraint degree grade of the current vehicle according to the constraint degree prediction model and the information acquired by the information acquisition module, predicting the vehicle risk state according to the constraint degree grade and issuing early warning information;
the active safety control module is used for controlling the acquisition and release of the corresponding pre-configured active vehicle control strategy according to the constraint degree level obtained by current prediction;
and the updating module is used for updating the vehicle motion information database and the vehicle safety early warning model according to the preset time period.
9. A computer device comprising a processor and a memory for storing a computer program, characterized in that the processor is adapted to execute the computer program to perform the method according to any of claims 1-7.
10. A computer readable storage medium storing a computer program, characterized in that the computer program, when executed, implements the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211513038.XA CN116434523A (en) | 2022-11-28 | 2022-11-28 | Vehicle active safety control method and device based on constraint degree in information perception scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211513038.XA CN116434523A (en) | 2022-11-28 | 2022-11-28 | Vehicle active safety control method and device based on constraint degree in information perception scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116434523A true CN116434523A (en) | 2023-07-14 |
Family
ID=87086030
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211513038.XA Pending CN116434523A (en) | 2022-11-28 | 2022-11-28 | Vehicle active safety control method and device based on constraint degree in information perception scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116434523A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117475628A (en) * | 2023-11-01 | 2024-01-30 | 中交资产管理有限公司 | Expressway operation method and information system based on risk theory |
| CN117710909A (en) * | 2024-02-02 | 2024-03-15 | 多彩贵州数字科技股份有限公司 | Rural road intelligent monitoring system based on target detection and instance segmentation |
-
2022
- 2022-11-28 CN CN202211513038.XA patent/CN116434523A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117475628A (en) * | 2023-11-01 | 2024-01-30 | 中交资产管理有限公司 | Expressway operation method and information system based on risk theory |
| CN117475628B (en) * | 2023-11-01 | 2024-05-03 | 中交资产管理有限公司 | Expressway operation method and information system based on risk theory |
| CN117710909A (en) * | 2024-02-02 | 2024-03-15 | 多彩贵州数字科技股份有限公司 | Rural road intelligent monitoring system based on target detection and instance segmentation |
| CN117710909B (en) * | 2024-02-02 | 2024-04-12 | 多彩贵州数字科技股份有限公司 | Rural road intelligent monitoring system based on target detection and instance segmentation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3533681B1 (en) | Method for detecting safety of driving behavior, apparatus and storage medium | |
| CN110823235B (en) | Intelligent vehicle navigation system, method and control logic for deriving road segment speed limits | |
| CN102208013B (en) | Landscape coupling reference data generation system and position measuring system | |
| CN107272687A (en) | A kind of driving behavior decision system of automatic Pilot public transit vehicle | |
| CN116434523A (en) | Vehicle active safety control method and device based on constraint degree in information perception scene | |
| CN110843789B (en) | Vehicle lane change intention prediction method based on time sequence convolution network | |
| DE102015202367A1 (en) | AUTONOMIC CONTROL IN A SEALED VEHICLE ENVIRONMENT | |
| DE102012212740A1 (en) | System and method for updating a digital map of a driver assistance system | |
| Saiprasert et al. | Driver behaviour profiling using smartphone sensory data in a V2I environment | |
| CN114385661A (en) | High-precision map updating system based on V2X technology | |
| CN107316457B (en) | Method for judging whether road traffic condition accords with automatic driving of automobile | |
| CN113936463B (en) | Tunnel traffic control method and system based on radar and video data fusion | |
| CN112912883B (en) | Simulation method and related equipment | |
| CN114454878B (en) | Method and device for determining vehicle speed control model training sample | |
| DE102021132722A1 (en) | SELECTING TEST SCENARIOS TO EVALUATE AUTONOMOUS VEHICLE PERFORMANCE | |
| CN112258850A (en) | Edge side multi-sensor data fusion system of vehicle-road cooperative system | |
| DE102019114595B4 (en) | Method for controlling the operation of a motor vehicle and for deriving road segment speed limits | |
| US10953871B2 (en) | Transportation infrastructure communication and control | |
| CN116013101B (en) | System and method for suggesting speed of signal-free intersection based on network environment | |
| CN116596380A (en) | Optimization determination method, platform, equipment and medium for expressway construction organization scheme and management and control scheme | |
| Shan et al. | Vehicle collision risk estimation based on RGB-D camera for urban road | |
| CN113128847A (en) | Entrance ramp real-time risk early warning system and method based on laser radar | |
| Wang et al. | Wide-area vehicle trajectory data based on advanced tracking and trajectory splicing technologies: Potentials in transportation research | |
| Zhao et al. | Is the cut-in behavior in china dangerous? Research and analysis based on Chinese driving behavior characteristics in highway | |
| Whitley | Applications in Traffic Analysis from Automatically Extracted Road User Interactions with Roadside LiDAR Trajectories |
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 |