CN116453345B - Bus driving safety early warning method and system based on driving risk feedback - Google Patents
Bus driving safety early warning method and system based on driving risk feedback Download PDFInfo
- Publication number
- CN116453345B CN116453345B CN202310696828.4A CN202310696828A CN116453345B CN 116453345 B CN116453345 B CN 116453345B CN 202310696828 A CN202310696828 A CN 202310696828A CN 116453345 B CN116453345 B CN 116453345B
- Authority
- CN
- China
- Prior art keywords
- driving
- vehicle
- driver
- bus
- risk
- 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 117
- 230000008569 process Effects 0.000 claims abstract description 27
- 238000004364 calculation method Methods 0.000 claims description 47
- 230000001133 acceleration Effects 0.000 claims description 36
- 206010039203 Road traffic accident Diseases 0.000 claims description 34
- 238000011156 evaluation Methods 0.000 claims description 34
- 239000011159 matrix material Substances 0.000 claims description 33
- 238000012502 risk assessment Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 18
- 230000003993 interaction Effects 0.000 claims description 14
- 238000012937 correction Methods 0.000 claims description 12
- 230000006399 behavior Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 8
- 230000009471 action Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 4
- 238000005286 illumination Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 241000764238 Isis Species 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 206010063659 Aversion Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- 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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Human Resources & Organizations (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Analytical Chemistry (AREA)
- Algebra (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Atmospheric Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
Abstract
The invention belongs to the field of intelligent safety early warning of vehicles, and relates to a bus driving safety early warning method and system based on driving risk feedback. The method solves the problems that in the current driving safety early warning process, feedback of a driver is ignored for multiple unnecessary early warning, so that psychological stress of the driver is high, and the importance degree of an alarm signal is lowered.
Description
Technical Field
The invention belongs to the technical field of urban bus operation management, relates to intelligent safety early warning of a vehicle, and particularly relates to a bus driving safety early warning method and system based on driving risk feedback.
Background
In recent years, under the age background that people actively respond to low-carbon travel, urban buses become important travel routes of residents, so that the bus passenger traffic is increased greatly. The urban buses bear great safety responsibility, and serious casualties and property loss are often caused once accidents occur. Therefore, related departments strongly advance intelligent networking construction of buses, and scientific and advanced bus risk early warning technology is urgently needed to ensure operation safety of the buses.
At present, some researches on the aspect of bus driving safety pre-warning exist. For example: the Chinese patent CN110120153A discloses a public transportation driving accident risk assessment system and a method thereof on the day of the month of the 2019 and the day of the 08, and the running records of all drivers on the same line in a statistical period are collected and ranked by presetting accident risk assessment indexes in the system, so that the accident risk scores are calculated and the risk is predicted according to the ranking order, and the method focuses on post-hoc driving risk assessment and cannot realize real-time risk early warning. The Chinese patent CN111210163B discloses a multi-source data-based bus risk evaluation system and method in 2023, namely, the method calculates time and space risks in weather environments of buses by collecting multi-source data in a period of time so as to realize the risk visualization of an overall bus network, and the method focuses on describing the current bus driving risk from a macroscopic layer by using a statistical method, so that the microscopic kinematic risk of the vehicle is not considered sufficiently, and the sudden driving risk is difficult to identify. The Chinese patent CN 114550477A discloses a bus driving safety early warning system and method in 2022, wherein vehicle-mounted and road side sensors are used for collecting motion information of surrounding buses, track calculation is carried out, and early warning is carried out on a scene with collision conflict risks.
From the above, it can be seen that the researches on the driving safety pre-warning of the existing bus still have certain defects. Firstly, the conventional traffic safety early warning system is insufficient in consideration of the multi-element influence on the macro-micro level, and comprehensive assessment of real-time overlapping traffic risks under the interaction condition of 'people and vehicles road rings' is difficult. Secondly, the existing early warning system carries out early warning when the driving risk reaches a threshold value, and risk feedback behaviors of a driver are completely ignored. When a driver perceives potential driving risks in advance and takes feedback actions to carry out danger avoiding operation, sudden early warning stimulation often aggravates psychological pressure of the driver and interferes with the danger avoiding operation; the long-term unnecessary driving early warning can not only make the driver feel aversion to the driving environment, but also make the driver not sensitive to the early warning signal any more, and greatly reduce the driving safety early warning effect.
Therefore, under the support of the plan project of intelligent monitoring and early warning technology and demonstration of the suitable condition of operating vehicle and ship drivers (2021 YFC 3001500), the invention provides a bus driving safety early warning method and system based on driving risk feedback.
Disclosure of Invention
In view of the technical problems and defects, the invention aims to provide a bus driving safety early warning method based on driving risk feedback, which takes bus acceleration as risk feedback expression of a driver, calculates driving risk feedback degree of the current bus driver through a risk feedback model, carries out early warning reminding on the driver with the driving risk feedback degree lower than a safety level, and solves the problems that the psychological pressure of the driver is high and the importance degree of an alarm signal is reduced due to the fact that the driver feedback is neglected for multiple unnecessary early warning in the current driving safety early warning process.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a bus driving safety early warning method based on driving risk feedback comprises the following steps:
step 1, a bus o is provided with a vehicle-mounted terminal, an external motion information acquisition module, an internal working condition information acquisition module, a driver information extraction module and a road side terminal on the vehicle-mounted terminal acquire corresponding information respectively, and a vehicle running risk assessment module which is sent to the vehicle-mounted terminal is updated in real time so as to assess driving risk in real time;
wherein the external motion information acquisition module is used for acquiring the motion information of the vehicle and surroundingNCollecting driving parameters and position information of a vehicle; the internal working condition information acquisition module is used for acquiring the current driving state of the driver and the environmental information in the vehicle; the road side terminal is used for collecting road traffic environment information and natural environment information of a driving area of the bus o; the driver information extraction module is used for extracting driver information corresponding to the bus o from a bus driver database;
step 2, a vehicle running risk assessment module of the vehicle-mounted terminal calculates the current running risk amount of the bus o in real time according to the received data; current line When the vehicle risk is calculated, according to the predicted bus o and surrounding vehiclesiAccident severity of (a) and (b) bus o and surrounding vehicles under interaction condition of' people and vehicles road ringiCalculating the relative probability of the accident;
step 3, after a vehicle running risk assessment module of the vehicle-mounted terminal calculates the current running risk amount of the bus o, judging whether the current running risk amount reaches the critical accident risk amount or not; if the current driving risk is higher than the critical value, the risk information is sent to a driver feedback evaluation module of the vehicle-mounted terminal, and step 4 is executed; otherwise, the risk amount information does not need to be sent;
step 4, after the driver feedback evaluation module of the vehicle-mounted terminal receives the risk amount information sent by the vehicle running risk evaluation module, evaluating the risk feedback degree of the current driver, wherein the specific flow is as follows:
4.1 The driver feedback evaluation module invokes the historical driving record of the current driver in the driver information extraction module, establishes a safe driving track fitting model according to the safe driving track data of the driver, calculates the driving acceleration of safe driving conforming to the current risk state, and the safe driving track fitting model is as follows:
;
;
In the method, in the process of the invention,is a bus +.>At the current driving risk amount->The acceleration of safe driving can be maintained under the influence,is the risk transformation coefficient,/->Is the inertial running acceleration,/->Is the maximum acceleration of the vehicle, < > is->Is the desired speed of the vehicle and,is the current driving speed of the vehicle, < > is->Is the speed difference influence coefficient;
4.2 The driver feedback evaluation module invokes the bus from the external motion information acquisition moduleCurrent accelerationDriving risk feedback degree +_using current acceleration and driving acceleration for safe driving>The calculation formula is as follows:;
4.3 According to the feedback degree of driving riskJudging the size of the bus +.>At the current driving risk amount->Under the influence, whether the driving feedback state of the driver is normal or not; when (when)When the driving risk feedback degree is lower than the safety critical value, the driver feedback evaluation module sends an early warning signal to the vehicle early warning module, and the step 5 is executed; otherwise, no early warning signal is required to be sent;
and 5, after the vehicle early warning module of the vehicle-mounted terminal receives the early warning information sent by the driver feedback evaluation module, reminding the driver until the early warning information is sent.
As a preferred aspect of the invention, the driving parameters include in particular a bus And the speed of surrounding N vehicles +.>、Acceleration->、Quality->、The method comprises the steps of carrying out a first treatment on the surface of the The location information refers to bus +.>Position coordinates of centroid->And the position coordinates of the centroid of the surrounding N vehicles +.>，Refers to the surrounding->Any one of the vehicles; the current driving state information of the driver comprises a distraction state and a fatigue state of the driver; the in-vehicle environmental information includes a passenger load rate; the road traffic environment information comprises bus->Traffic flow density of the traveling area, traffic control conditions; the natural environment information comprises weather conditions and illumination conditions; the driver information includes the driver's age, sex, number of traffic accidents, number of bad driving behaviors, driving mileage on the day, operating route mileage, driving duration on the day, and historical driving record.
Preferably, in step 2, the bus is usedCurrent driving risk amount->The calculation formula of (2) is as follows:
;
in the method, in the process of the invention,bus calculated in real time +.>Current driving risk amount->Is a predictive vehicle->Is +.>Is to be treated as the accident severity->Is considered'Bus under man-car road ring' interaction condition ∈>Is>Is>Is a vehicle->Risk amount correction coefficient of (a).
As a further preference of the invention, the severity of the accidentThe calculation formula of (2) is as follows:
;
;
;
in the method, in the process of the invention,is a vehicle->Equivalent mass of->Consider the vehicle +>Is +.>Pseudo-spatial distance of relative positional relationship, +.>Is a critical threshold for the safe distance, +.>And->Respectively represent vehicle->The current position is at bus->Deviation angle in driving direction, bus +.>The current position being in the vehicleiDeviation angle in driving direction +.>、、For the pending correction factor, bus +.>Position coordinates of centroid->Quality->Speed->Vehicle->Position coordinates of centroid->Quality ofSpeed->Acceleration->。
As a further preferred aspect of the invention, a busIs>Collision probability term under the interaction condition of "people and vehicles road ring>The calculation formula of (2) is as follows:
；
in the method, in the process of the invention,is a kinematic collision coefficient, < >>Is the macroscopic collision coefficient, < >>、Is a correction coefficient.
As a further preferred aspect of the present invention, the kinetic collision coefficientThe calculation formula of (2) is as follows:
；
in the method, in the process of the invention,is the speed difference between the rear vehicle and the front vehicle, < >>Consider the vehicle +>Is +.>Pseudo-spatial distance of relative positional relationship;
macroscopic collision coefficientDuring calculation, firstly, a structural equation is established, and a structural equation calculation model is as follows:
；
；
；
In the method, in the process of the invention,is an endogenous latent variable matrix>Is an exogenous latent variable matrix,>is a matrix of interference terms in the equation, +.>Representing exogenous versus endogenous latent variablesCoefficient matrix, < >>Representing the effect matrix between endogenous latent variables, +.>Is->Is>Is->Is>Is->At->Load matrix on->Is->At->Load matrix on->Is->Error matrix of measurement, +.>Is->Is a measurement error matrix of (a);
wherein, the exogenous latent variable matrixComprises natural environment->In-car environment->Driver attribute->Risk drive record->Intensity of work->The method comprises the steps of carrying out a first treatment on the surface of the Endogenous latent variable matrix->Including traffic accident probability->Traffic environment->Driver state->The method comprises the steps of carrying out a first treatment on the surface of the Natural environment->The observed variables of (2) include the light conditions +.>Weather conditions->The method comprises the steps of carrying out a first treatment on the surface of the In-car Environment->The observed variables of (a) include passenger load rate +.>The method comprises the steps of carrying out a first treatment on the surface of the Driver attribute->The observed variables of (2) include age->Sex->The method comprises the steps of carrying out a first treatment on the surface of the Risk driving record->The observation variables of (1) include the number of traffic accidents per month +.>Number of bad driving behavior in month +.>The method comprises the steps of carrying out a first treatment on the surface of the Work intensity->The observed variables of (2) include mileage on the day +.>Mileage of operation route->Duration of driving on the same day->The method comprises the steps of carrying out a first treatment on the surface of the Probability of traffic accident >The observed variables of (2) include event outcome +.>The method comprises the steps of carrying out a first treatment on the surface of the Traffic environment->The observed variables of (2) include traffic flow density +.>Traffic control situation->The method comprises the steps of carrying out a first treatment on the surface of the Driver state->The observed variables of (2) include the distraction state +.>Fatigue state->；
The internal action relationship between the external latent variable and the internal latent variable is as follows: natural environmentProbability of traffic accident->Traffic environment->Driver state->All have influence; in-car Environment->Probability of traffic accident->Driver state->Has an influence; driver attribute->Probability of traffic accident->Driving methodPerson state->Has an influence; risk driving record->Probability of traffic accident->Has an influence; the intrinsic function relationship between the intrinsic latent variable and the intrinsic latent variable is as follows: traffic environment->Probability of traffic accident->Driver state->Has an influence; driver state->Probability of traffic accident->Has an influence;
according to the simultaneous calculation equation set of the internal action relations between the structural equation calculation model and the external and internal latent variables, and between the internal and internal latent variables, substituting the coded values of the apparent variables of each historical record into the simultaneous equation set, and fitting out the coefficient matrix to be determined in the structural equation、、、、、、The specific numerical value of the traffic accident probability is obtained by taking the current real-time driving data as a model input >At this time->Namely bus +.>Macroscopic crash coefficient of a vehicle->。
Another object of the invention is to provide a bus driving safety early warning system based on driving risk feedback, which comprises a road side terminal, a bus driver database and a vehicle-mounted terminal, wherein the road side terminal is communicated with the vehicle-mounted terminal, and the road side terminal under intelligent traffic conditions is used for collecting busesRoad traffic environment information and natural environment information of the driving area;
the bus driver database is communicated with the vehicle-mounted terminal and is used for storing bus driver information, vehicle information corresponding to the bus driver and historical driving records of the bus driver;
the vehicle-mounted terminal comprises an external motion information acquisition module, an internal working condition information acquisition module, a driver information extraction module, a vehicle driving risk assessment module, a driver feedback assessment module and a vehicle early warning module;
the external motion information acquisition module is used for acquiring driving parameters and position information of the vehicle and N vehicles nearest to the periphery;
the internal working condition information acquisition module is used for acquiring the current driving state of the driver and the in-vehicle environment information;
The driver information extraction module is used for extracting buses from a bus driver databaseExtracting corresponding driver information;
the vehicle driving risk assessment module is used for assessing driving risk in real time according to the received data and comprises an accident severity prediction module, a collision probability calculation module and a risk calculation module;
the accident severity prediction module is used for predicting vehiclesiWith public transport vehiclesAccident severity of (2);
the collision probability calculation module is used for integrating the kinematic collision coefficient and the macroscopic collision coefficient to calculate the busWith vehiclesiCollision probability under the interaction condition of 'people and vehicles road rings';
the risk amount calculation module is used for calculating the current running risk amount in real time according to the data of the accident severity prediction module and the collision probability calculation module, and if the current running risk amount is higher than a critical value, the risk amount information is sent to the driver feedback evaluation module of the vehicle-mounted terminal;
the driver feedback evaluation module is used for retrieving the history driving record of the current driver in the driver information extraction module, calculating the driving acceleration of the safe driving conforming to the current risk state and according to the bus Current acceleration->Calculating the driving risk feedback degree with the driving acceleration of the safe driving, and sending an early warning signal to the vehicle early warning module when the driving risk feedback degree is lower than a safety critical value; the calculation formula of the driving risk feedback degree is as follows:
；
；
；
in the method, in the process of the invention,is driving risk feedback degree, < >>Is a bus +.>At the current driving risk amount->Acceleration which can keep safe driving under influence, < +.>Is the risk transformation coefficient,/->Is the inertial running acceleration,/->Is the maximum acceleration of the vehicle, < > is->Is the desired speed of the vehicle,/->Is the current driving speed of the vehicle, < > is->Is the speed difference influence coefficient;
and the vehicle early warning module reminds the driver through audible and visual alarm after receiving the early warning information sent by the driver feedback evaluation module.
As the preferable mode of the invention, the external motion information acquisition module comprises a binocular camera and a vehicle-mounted laser radar; the internal working condition information acquisition module comprises a vehicle-mounted high-definition camera.
The present invention also provides an electronic device including: one or more processors, memory; the memory is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors realize the bus driving safety early warning method based on driving risk feedback.
The invention also provides a computer readable medium, on which a computer program is stored, which when executed by a processor, implements the bus driving safety pre-warning method based on driving risk feedback.
The invention has the advantages and beneficial effects that:
(1) According to the early warning method provided by the invention, after the driver feedback evaluation module receives the current driving risk amount information sent by the vehicle driving risk evaluation module, the bus acceleration is used as the risk feedback performance of the driver, the risk feedback degree of the current bus driver is calculated through the risk feedback model, the early warning reminding is carried out on the driver with the risk feedback degree lower than the safety level, and the problems that the psychological pressure of the driver is high and the importance degree of warning signals is reduced due to the fact that the feedback of the driver is neglected for multiple times in the current driving safety early warning process are solved.
(2) The early warning method can finely calculate the comprehensive driving risk quantity of the real-time bus under the interaction condition of the people and vehicles road rings, predicts the accident severity according to the parameters such as the pseudo-space distance, the relative position relation and the like of the relative position relation between the current vehicle and the surrounding vehicles when the driving risk assessment of the bus is carried out, and then calculates the risk quantity in real time based on the accident severity and the collision probability under the interaction condition of the people and vehicles road rings, thereby realizing the real-time risk early warning.
(3) When macroscopic collision probability calculation is carried out, a structural equation is established according to historical driving data of a driver, a pending coefficient matrix in the structural equation is calculated according to a structural equation path diagram by applying the historical driving data of the current bus driver, then the current real-time driving data is used as a model input to obtain a macroscopic collision coefficient of the bus in the current driving state, the comprehensive evaluation of real-time superposition driving risk under the interaction condition of a 'man-vehicle road ring' is realized, the actual driving risk under the complex driving environment is accurately evaluated, and the problem that the superposition driving risk is difficult to quantitatively evaluate when the bus is influenced by multi-risk factors on the macro-micro level is solved.
Drawings
Other objects and attainments together with a more complete understanding of the invention will become apparent and appreciated by referring to the following description taken in conjunction with the accompanying drawings. In the drawings:
FIG. 1 is a diagram of the position of a bus in relation to surrounding vehicles;
FIG. 2 is a structural equation path diagram for macroscopic collision coefficient calculation in the present invention;
FIG. 3 is a flow chart of the whole bus driving safety pre-warning method based on driving risk feedback;
FIG. 4 is a block diagram of a bus driving safety early warning system based on driving risk feedback of the invention;
FIG. 5 is a variable partition diagram of the structural equation model of the present application;
FIG. 6 is a graph of the code assignment of the present application display variables.
Detailed Description
The following detailed description of the application, taken in conjunction with the accompanying drawings, is not intended to limit the scope of the application, so that those skilled in the art may better understand the technical solutions of the application and their advantages.
Example 1
The application provides a bus driving safety pre-warning method based on driving risk feedback, which comprises the following steps:
step 1, busThe system comprises a vehicle-mounted terminal, wherein an external motion information acquisition module, an internal working condition information acquisition module, a driver information extraction module and a road side terminal on the vehicle-mounted terminal acquire corresponding information respectively, and a vehicle driving risk assessment module which is updated and sent to the vehicle-mounted terminal in real time is used for assessing real-time driving risk, and the specific acquired information is as follows:
external motion information acquisition module of vehicle-mounted terminal for the vehicle (bus)) And nearest->Collecting driving parameters and position information of a vehicle; as shown in figure 1, the bus is +.>Surrounding nearest->The vehicle is located in a bus>Front, rear, left side, front left, rear left, right side, front right, rear right vehicle,/- >Generally less than or equal to 8, specific number and buses in actual driving scene +.>Whether other vehicles in the nearest direction around exist or not; the driving parameters comprise bus ∈>Speed of surrounding vehicle +.>、Acceleration->、Quality->、The method comprises the steps of carrying out a first treatment on the surface of the The location information refers to bus +.>Position coordinates of centroid->And the position coordinates of the centroid of the surrounding vehicle +.>，Refers to the surrounding->Any one of the vehicles;
the internal working condition information acquisition module of the vehicle-mounted terminal acquires the current driving state of the driver and the environmental information in the vehicle; the current driving state information of the driver comprises a distraction state and a fatigue state of the driver, and the in-vehicle environment information refers to the load rate of passengers;
the driver information extraction module extracts bus from bus driver databaseExtracting corresponding driver information, wherein the driver information comprises the age, sex, number of traffic accidents, number of bad driving behaviors, driving mileage on the same day, operating route mileage, driving duration on the same day and historical driving records of a driver;
the historical driving record comprises two types of safety events and collision events; the collision event takes the moment that the current running risk reaches the critical accident risk as a recording starting point until the real-time vehicle collision is stopped; the safety event is stored by taking 5 minutes as a recording time length, and each event records driving parameters, position information, driving state information of a driver, in-vehicle environment information, road traffic environment information, natural environment information, driver information, a final event result and the like.
The road side terminal communicates with the vehicle-mounted terminal, and the road side terminal acquires the bus in real time under the intelligent traffic conditionRoad traffic environment information and natural environment information of the driving area; the road traffic environment information comprises bus->The traffic flow density and traffic control condition of the driving area, and the natural environment information comprises weather conditions and illumination conditions;
step 2, after the vehicle running risk assessment module of the vehicle-mounted terminal receives the real-time data sent by each information collecting unit, carrying out busCurrent driving risk amount->Is calculated, bus->Current driving risk amount->The calculation formula of (2) is as follows:
；
in the method, in the process of the invention,bus calculated in real time +.>Current driving risk amount->Is a predictive vehicle->Is +.>Is to be treated as the accident severity->Consider bus +.>Is>Is>Is a vehicle->Risk amount correction coefficient of (a).
In this embodiment, the predicted vehicleIs +.>Accident severity->The greater the mass and the speed of the vehicles, the smaller the distance between the vehicles, the greater the severity of the accident which is possibly caused, mainly affected by the motion state and the inherent attribute of the two vehicles; thus, accident severity- >The calculation formula of (2) is as follows:
；
；
；
in the method, in the process of the invention,is a vehicle->Equivalent mass of->Consider the vehicle +>Is +.>Pseudo-spatial distance of relative positional relationship, +.>Is a critical threshold for the safe distance, +.>And->Respectively represent vehicle->The current position is at bus->Deviation angle in driving direction, bus +.>The current position being in the vehicleiDeviation angle in driving direction (+)>And->Can be calculated from the coordinates of two vehicle positions),>、、the meaning of the remaining parameters for the pending correction coefficients remain the same as above.
In this embodiment, a busIs>Collision probability term->Described is a bus->Is>Relative probability of accident>Fully considers the comprehensive influence of the interaction condition of the 'man-vehicle road ring', and adopts the kinematic collision coefficient +.>And macroscopic crash coefficient->Constructing;
wherein the kinematic collision coefficientMainly receive bus->And vehicle->The influence of the speed difference and the distance, when the speed of the rear vehicle is greater than that of the front vehicle, the greater the speed difference, the higher the collision coefficient; when the speed of the rear vehicle is smaller than that of the front vehicle, the larger the speed difference is, the lower the collision coefficient is, and the distance between the two vehicles is always inversely proportional to the kinematic collision coefficient; thus, the kinetic collision coefficient The calculation formula of (2) is as follows:
；
in the method, in the process of the invention,is the speed difference between the rear vehicle and the front vehicle, < >>Consider the vehicle +>Is +.>Pseudo-spatial distance of relative positional relationship.
Macroscopic collision coefficientThe method mainly relates to the current environment and the characteristics of a bus driver, a structural equation is established according to the historical driving data of the bus driver, and the internal action relation between each influence factor of the current bus driver and the occurrence of traffic accidents is calculated; the structural equation calculation model is as follows:
；
；
；
in the method, in the process of the invention,is an endogenous latent variable matrix>Is an exogenous latent variable matrix,>is a matrix of interference terms in the equation, +.>Coefficient matrix representing exogenous versus endogenous latent variable,>representing the effect matrix between endogenous latent variables, +.>Is->Observation of (2) apparent changesQuantity matrix,/->Is->Is>Is->At->Load matrix on->Is->At->Load matrix on->Is->Error matrix of measurement, +.>Is->Is provided.
In this embodiment, the specific variable division is shown in fig. 5, and as can be seen from fig. 5, the exogenous latent variable matrixComprises natural environment->In-car environment->Driver attribute->Risk drive record->Intensity of work->The method comprises the steps of carrying out a first treatment on the surface of the Endogenous latent variable matrix- >Including traffic accident probability->Traffic environment->Driver state->The method comprises the steps of carrying out a first treatment on the surface of the Natural environment->The observed variables of (2) include the light conditions +.>Weather conditions->The method comprises the steps of carrying out a first treatment on the surface of the In-car Environment->The observed variables of (a) include passenger load rate +.>The method comprises the steps of carrying out a first treatment on the surface of the Driver attribute->The observed variables of (2) include age->Sex->The method comprises the steps of carrying out a first treatment on the surface of the Risk driving record->The observation variables of (1) include the number of traffic accidents per month +.>Number of bad driving behavior in month +.>The method comprises the steps of carrying out a first treatment on the surface of the Work intensity->The observed variables of (2) include mileage on the day +.>Mileage of operation routeDuration of driving on the same day->The method comprises the steps of carrying out a first treatment on the surface of the Probability of traffic accident>The observed variables of (2) include event outcome +.>The method comprises the steps of carrying out a first treatment on the surface of the Traffic environment->The observed variables of (2) include traffic flow density +.>Traffic control situation->The method comprises the steps of carrying out a first treatment on the surface of the Driver state->The observed variables of (2) include the distraction state +.>Fatigue state->。
The method comprises the steps of carrying out coding assignment on each of the display variables in the current public transportation driver history driving record, dividing the display variables into sequential display variables and classified display variables in fig. 5, carrying out normalized coding assignment on the sequential display variables according to the numerical values, carrying out classification processing on the classified display variables, and carrying out the nonlinear influence of the classified display variables on the latent variables in a structural equation model by a classification processing method, wherein the specific display variable coding assignment is shown in fig. 6.
In this embodiment, a structural equation path diagram is shown in fig. 2, and as can be seen from fig. 2, the intrinsic action relationship between the exogenous latent variable and the endogenous latent variable is: natural environmentProbability of traffic accident->Traffic environment->Driver state->All have influence; in-car Environment->Probability of traffic accident->Driver state->Has an influence; driver attribute->Probability of traffic accident->Driver state->Has an influence; risk driving record->Probability of traffic accident->Has an influence; the intrinsic function relationship between the intrinsic latent variable and the intrinsic latent variable is as follows: traffic environment->Probability of traffic accident->Driver state->Has an influence; driver state->Probability of traffic accident->Has an influence;
according to the simultaneous calculation equation set of the (6) - (8) and the structural equation path diagram, substituting the coded values of the apparent variables of each historical record into the simultaneous equation set, and fitting the matrix of the coefficient to be determined in the structural equation、、、、、、The specific numerical value of the traffic accident probability is obtained by taking the current real-time driving data as a model input>At this time->Namely bus +.>Macroscopic crash coefficient of a vehicle->。
Comprehensive kinematic collision coefficient and macroscopic collision coefficient, and calculating bus Is>Collision probability term under the interaction condition of "people and vehicles road ring>，The calculation formula is as follows:
；
in the method, in the process of the invention,is a kinematic collision coefficient, < >>Is the macroscopic collision coefficient, < >>、Is a correction coefficient.
Step 3, a vehicle running risk assessment module of the vehicle-mounted terminal calculates the current running risk quantity of the busAfter that, judging the current driving risk amount +.>Whether the critical accident risk is reached, if the current driving risk is + ->If the risk quantity information is higher than the critical value, the risk quantity information is sent to a driver feedback evaluation module of the vehicle-mounted terminal, and step 4 is executed; otherwise, the risk amount information does not need to be sent;
step 4, after the driver feedback evaluation module of the vehicle-mounted terminal receives the current running risk amount information sent by the vehicle running risk evaluation module, evaluating the risk feedback degree of the current driver, wherein the specific flow is as follows:
4.1 The driver feedback evaluation module invokes the historical driving record of the current driver in the driver information extraction module, establishes a safe driving track fitting model according to the safe driving track data of the driver, and calculates the driving acceleration of safe driving conforming to the current risk stateThe safe driving track fitting model is as follows:
；
；
In the method, in the process of the invention,is a bus +.>At the current driving risk amount->The acceleration of safe driving can be maintained under the influence,is the risk transformation coefficient,/->Is the inertial running acceleration,/->Is the maximum acceleration of the vehicle, < > is->Is the desired speed of the vehicle and,is the current driving speed of the vehicle, < > is->Is the speed difference influence coefficient.
4.2 The driver feedback evaluation module invokes the bus from the external motion information acquisition moduleCurrent accelerationDriving risk feedback degree +_using current acceleration and driving acceleration for safe driving>The calculation formula is as follows:
；
4.3 According to the feedback degree of driving riskJudging the size of the bus +.>At the current driving risk amount->Under the influence, whether the driving feedback state of the driver is normal or not;
when the driving risk feedback degree is lower than the safety critical value, indicating that the driver does not pay attention to the driving risk at present or the risk response is overdriven and the risk avoiding operation is improper, sending an early warning signal to a vehicle early warning module by a driver feedback evaluation module at the moment, and executing the step 5;
when the driving risk feedback degree is higher than the safety critical value, the driver is informed that the current driving risk is perceived in advance and safe risk avoiding operation is adopted, an early warning signal is not required to be sent to a vehicle early warning module, and unnecessary early warning is avoided.
And 5, after the vehicle early warning module of the vehicle-mounted terminal receives the early warning information sent by the driver feedback evaluation module, reminding the driver until the early warning information is sent.
Further, in this embodiment, the vehicle early warning module reminds the driver in an audible and visual alarm manner.
Example 2
As shown in fig. 4, the invention provides a bus driving safety early warning system based on driving risk feedback, which comprises a road side terminal 1, a bus driver database 2 and a vehicle-mounted terminal 3, wherein the road side terminal 1 is communicated with the vehicle-mounted terminal 3, and the road side terminal under intelligent traffic conditions is used for collecting busesRoad traffic environment information and natural environment information of a driving area, the road traffic environment information including bus +.>The traffic flow density and the traffic control condition of the driving area, and the natural environment information comprises weather conditions and illumination conditions;
the bus driver database 2 is communicated with the vehicle-mounted terminal 3 and is used for storing bus driver information, vehicle information corresponding to the bus driver and historical driving records of the bus driver;
the vehicle-mounted terminal 3 comprises an external motion information acquisition module 31, an internal working condition information acquisition module 32, a driver information extraction module 33, a vehicle running risk assessment module 34, a driver feedback assessment module 35 and a vehicle early warning module 36;
Wherein, the external motion information acquisition module 31 is used for acquiring information of the vehicle (bus) And nearest->Collecting driving parameters and position information of a vehicle; the driving parameters comprise bus ∈>Speed of surrounding vehicle +.>、Acceleration->、Quality->、The method comprises the steps of carrying out a first treatment on the surface of the The location information refers to bus +.>Position coordinates of centroid->And the position coordinates of the centroid of the surrounding vehicle +.>，Refers to the surrounding->Any one of the vehicles; the data can be obtained by a binocular camera and a vehicle-mounted laser radar;
the internal working condition information acquisition module 32 is configured to acquire a current driving state of a driver and in-vehicle environment information, where the current driving state information includes a distraction state and a fatigue state of the driver, and the in-vehicle environment information refers to a passenger load rate; the vehicle-mounted high-definition camera can be adopted to acquire the image data inside the bus, and then the acquired image is processed by the residual neural network and the support vector machine classification method, so that the characteristics of the driver and the environment inside the bus are identified, and the data are acquired.
The driver information extraction module 33 is configured to extract a bus from a bus driver databaseExtracting corresponding driver information, wherein the driver information comprises the age, sex, number of traffic accidents, number of bad driving behaviors, driving mileage on the same day, operating route mileage, driving duration on the same day and historical driving records of the driver;
The vehicle driving risk assessment module 34 is configured to assess driving risk in real time according to the received data, and includes an accident severity prediction module 341, a collision probability calculation module 342, and a risk amount calculation module 343;
the accident severity prediction module 341 is configured to predict a vehicleiWith public transport vehiclesThe accident severity of (2) is calculated as follows:
；
；
；
in the method, in the process of the invention,is the predicted severity of the accident, +.>Is a vehicle->Equivalent mass of->Consider the vehicle +>Is +.>Pseudo-spatial distance of relative positional relationship, +.>Is a critical threshold for the safe distance, +.>And->Respectively represent vehiclesiThe current position is at bus->Deviation angle in driving direction, bus +.>The current position is at the vehicle->Deviation angle in driving direction +.>、、For the undetermined correction coefficient, the meaning of the rest parameters is consistent with the above; />
The collision probability calculation module 342 is configured to calculate a bus by integrating a kinematic collision coefficient and a macroscopic collision coefficientIs>The collision probability under the interaction condition of the man-vehicle road ring is calculated as follows:
；
in the method, in the process of the invention,is a kinematic collision coefficient, < >>Is the macroscopic collision coefficient, < >>、Is a correction coefficient;
the risk amount calculation module 343 is configured to calculate a current running risk amount in real time according to the data of the accident severity prediction module and the collision probability calculation module, and send risk amount information to the driver feedback evaluation module of the vehicle-mounted terminal if the current running risk amount is higher than a critical value; bus The calculation formula of the current driving risk amount is as follows:
；
in the method, in the process of the invention,is a bus +.>Current driving risk amount->Is a predictive vehicle->Is +.>Is to be treated as the accident severity->Consider bus +.>Is>Is>Is a vehicle->Risk quantity correction coefficients of (a);
the driver feedback evaluation module 35 is configured to retrieve a history of driving records of a current driver in the driver information extraction module, calculate a driving acceleration of the safe driving according to the current risk state, and determine a driving acceleration of the safe driving according to the busCurrent accelerationCalculating the driving risk feedback degree with the driving acceleration of the safe driving, and sending an early warning signal to the vehicle early warning module when the driving risk feedback degree is lower than a safety critical value; the calculation formula of the driving risk feedback degree is as follows:
；
；
；
in the method, in the process of the invention,is driving risk feedback degree, < >>Is a bus +.>At the current driving risk amount->Driving acceleration keeping safe running under influence +.>Is the risk transformation coefficient,/->Is the inertial running acceleration,/->Is the maximum acceleration of the vehicle, < > is->Is the desired speed of the vehicle,/->Is the current driving speed of the vehicle, < > is->Is the speed difference influence coefficient;
The vehicle early warning module 36 reminds the driver through audible and visual alarm after receiving the early warning information sent by the driver feedback evaluation module.
In addition, the invention also provides electronic equipment, which comprises: one or more processors, memory; the memory is configured to store one or more programs, where when the one or more programs are executed by the one or more processors, the one or more processors implement the bus driving safety early warning method based on driving risk feedback according to embodiment 1.
The invention also provides a computer readable medium, on which a computer program is stored, which when executed by a processor implements the bus driving safety pre-warning method based on driving risk feedback described in embodiment 1.
Those skilled in the art will appreciate that all or part of the functions of the various methods/modules in the above embodiments may be implemented by hardware, or may be implemented by a computer program. When all or part of the functions in the above embodiments are implemented by means of a computer program, the program may be stored in a computer readable storage medium, and the storage medium may include: read-only memory, random access memory, magnetic disk, optical disk, hard disk, etc., and the program is executed by a computer to realize the above-mentioned functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the functions described above can be realized.
In addition, when all or part of the functions in the above embodiments are implemented by means of a computer program, the program may be stored in a storage medium such as a server, another computer, a magnetic disk, an optical disk, a flash disk, or a removable hard disk, and the program in the above embodiments may be implemented by downloading or copying the program into a memory of a local device or updating a version of a system of the local device, and when the program in the memory is executed by a processor.
The foregoing description of the invention has been presented for purposes of illustration and description, and is not intended to be limiting. Several simple deductions, modifications or substitutions may also be made by a person skilled in the art to which the invention pertains, based on the idea of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A bus driving safety early warning method based on driving risk feedback is characterized by comprising the following steps:
step 1, a bus o is provided with a vehicle-mounted terminal, an external motion information acquisition module, an internal working condition information acquisition module, a driver information extraction module and a road side terminal on the vehicle-mounted terminal acquire corresponding information respectively, and a vehicle running risk assessment module which is sent to the vehicle-mounted terminal is updated in real time so as to assess driving risk in real time;
The external motion information acquisition module is used for acquiring driving parameters and position information of the vehicle and N surrounding vehicles; the internal working condition information acquisition module is used for acquiring the current driving state of the driver and the environmental information in the vehicle; the road side terminal is used for collecting road traffic environment information and natural environment information of a driving area of the bus o; the driver information extraction module is used for extracting driver information corresponding to the bus o from a bus driver database;
step 2, a vehicle running risk assessment module of the vehicle-mounted terminal calculates the current running risk amount of the bus o in real time according to the received data; when the current driving risk is calculated, according to the predicted bus o and surrounding vehiclesiAccident severity of (a) and (b) bus o and surrounding vehicles under interaction condition of' people and vehicles road ringiCalculating the relative probability of the accident;
step 3, after a vehicle running risk assessment module of the vehicle-mounted terminal calculates the current running risk amount of the bus o, judging whether the current running risk amount reaches the critical accident risk amount or not; if the current driving risk is higher than the critical value, the risk information is sent to a driver feedback evaluation module of the vehicle-mounted terminal, and step 4 is executed; otherwise, the risk amount information does not need to be sent;
Step 4, after the driver feedback evaluation module of the vehicle-mounted terminal receives the risk amount information sent by the vehicle running risk evaluation module, evaluating the risk feedback degree of the current driver, wherein the specific flow is as follows:
4.1 The driver feedback evaluation module invokes the historical driving record of the current driver in the driver information extraction module, establishes a safe driving track fitting model according to the safe driving track data of the driver, calculates the driving acceleration of safe driving conforming to the current risk state, and the safe driving track fitting model is as follows:
；
；
in the method, in the process of the invention,is a bus +.>At the current driving risk amount->Acceleration for maintaining safe driving under influence, +.>Is the risk transformation coefficient,/->Is the inertial running acceleration,/->Is the maximum acceleration of the vehicle, < > is->Is the desired speed of the vehicle,/->Is the current driving speed of the vehicle, < > is->Is the speed difference influence coefficient;
4.2 The driver feedback evaluation module invokes the bus from the external motion information acquisition moduleCurrent acceleration->Driving risk feedback degree +_using current acceleration and driving acceleration for safe driving>The calculation formula is as follows:
；
4.3 According to the feedback degree of driving riskJudging the size of the bus +. >At the current driving risk amount->Under the influence, whether the driving feedback state of the driver is normal or not; when the driving risk feedback degree is lower than the safety critical value, the driver feedback evaluation module sends an early warning signal to the vehicle early warning module, and step 5 is executed; otherwise, no early warning signal is required to be sent;
and 5, after the vehicle early warning module of the vehicle-mounted terminal receives the early warning information sent by the driver feedback evaluation module, reminding the driver until the early warning information is sent.
2. The bus driving safety pre-warning method based on driving risk feedback according to claim 1, wherein the driving parameters specifically comprise a busAnd the speed of surrounding N vehicles +.>、Acceleration->、Quality->、The method comprises the steps of carrying out a first treatment on the surface of the The location information refers to bus +.>Position coordinates of centroid->And the position coordinates of the centroid of the surrounding N vehicles +.>，Refers to the surrounding->Any one of the vehicles; the current driving state information of the driver comprises a distraction state and a fatigue state of the driver; the in-vehicle environmental information includes a passenger load rate; the road traffic environment information comprises bus->Traffic flow density of the traveling area, traffic control conditions; the natural environment information comprises weather conditions and illumination conditions; the driver information includes the driver's age, sex, number of traffic accidents, number of bad driving behaviors, driving mileage on the day, operating route mileage, driving duration on the day, and historical driving record.
3. The bus driving safety pre-warning method based on driving risk feedback according to claim 1, wherein in step 2, the bus isCurrent driving risk amount->The calculation formula of (2) is as follows:
；
in the method, in the process of the invention,bus calculated in real time +.>Current driving risk amount->Is a predictive vehicle->Is +.>Is to be treated as the accident severity->Consider bus +.>Is>Is>Is a vehicle->Risk amount correction coefficient of (a).
4. A bus driving safety pre-warning method based on driving risk feedback according to claim 3, characterized in that the accident severity degreeThe calculation formula of (2) is as follows:
；
；
；
in the method, in the process of the invention,is a vehicle->Equivalent mass of->Consider the vehicle +>Is +.>Pseudo-spatial distances of the relative positional relationship,is a critical threshold for the safe distance, +.>And->Respectively represent vehicle->The current position is at bus->Deviation angle in driving direction, bus +.>The current position is at the vehicle->Deviation angle in driving direction +.>、、For the pending correction factor, bus +.>Position coordinates of centroid->Quality->Speed->Vehicle->Position coordinates of centroid- >Quality and quality of the productQuantity->Speed->Acceleration->。
5. A bus driving safety pre-warning method based on driving risk feedback according to claim 3, wherein the bus isIs>Collision probability term under the interaction condition of "people and vehicles road ring>The calculation formula of (2) is as follows:
；
in the method, in the process of the invention,is a kinematic collision coefficient, < >>Is the macroscopic collision coefficient, < >>、Is a correction coefficient.
6. Root of Chinese characterThe bus driving safety pre-warning method based on driving risk feedback as set forth in claim 5, wherein the motion collision coefficient isThe calculation formula of (2) is as follows:
；
in the method, in the process of the invention,is the speed difference between the rear vehicle and the front vehicle, < >>Consider the vehicle +>Is +.>Pseudo-spatial distance of relative positional relationship;
macroscopic collision coefficientDuring calculation, firstly, a structural equation is established, and a structural equation calculation model is as follows:
；
；
；
in the method, in the process of the invention,is an endogenous latent variable matrix>Is an exogenous latent variable matrix,>is a matrix of interference terms in the equation, +.>Coefficient matrix representing exogenous versus endogenous latent variable,>representing the effect matrix between endogenous latent variables, +.>Is->Is>Is->Is>Is->At->Load matrix on->Is->At->Load matrix on- >Is->Error matrix of measurement, +.>Is->Is a measurement error matrix of (a); wherein, exogenous latent variable matrix->Comprises natural environment->In-car environment->Driver attribute->Risk drive record->Intensity of work->The method comprises the steps of carrying out a first treatment on the surface of the Endogenous latent variable matrix->Including traffic accident probability->Traffic ringEnvironment->Driver state->The method comprises the steps of carrying out a first treatment on the surface of the Natural environment->The observed variables of (2) include the light conditions +.>Weather conditions->The method comprises the steps of carrying out a first treatment on the surface of the In-car Environment->The observed variables of (a) include passenger load rate +.>The method comprises the steps of carrying out a first treatment on the surface of the Driver attribute->The observed variables of (2) include age->Sex (sex)The method comprises the steps of carrying out a first treatment on the surface of the Risk driving record->The observation variables of (1) include the number of traffic accidents per month +.>Number of bad driving behavior in month +.>The method comprises the steps of carrying out a first treatment on the surface of the Work intensity->The observed variables of (2) include mileage on the day +.>Mileage of operation route->Duration of driving on the same dayThe method comprises the steps of carrying out a first treatment on the surface of the Probability of traffic accident>The observed variables of (2) include event outcome +.>The method comprises the steps of carrying out a first treatment on the surface of the Traffic environment->The observed variables of (2) include traffic flow density +.>Traffic control situation->The method comprises the steps of carrying out a first treatment on the surface of the Driver state->The observed variables of (2) include the distraction state +.>Fatigue state；
The internal action relationship between the external latent variable and the internal latent variable is as follows: natural environmentProbability of traffic accident->Traffic environment->Driver state- >All have influence; in-car Environment->Probability of traffic accident->Driver state->Has an influence; driver attribute->Probability of traffic accident->Driver state->Has an influence; risk driving record->Probability of traffic accident->Has an influence; the intrinsic function relationship between the intrinsic latent variable and the intrinsic latent variable is as follows: traffic environment->Probability of traffic accident->Driver state->Has an influence; driver state->Probability of traffic accident->Has an influence;
according to the simultaneous calculation equation set of the internal action relations between the structural equation calculation model and the external and internal latent variables, and between the internal and internal latent variables, substituting the coded values of the apparent variables of each historical record into the simultaneous equation set, and fitting out the coefficient matrix to be determined in the structural equation、、、、、、The specific numerical value of the traffic information is input by taking the current real-time driving data as a model to obtain traffic matters in the current driving stateTherefore, probability->At this time->Namely bus +.>Macroscopic collision coefficient of driving vehicle。
7. The bus driving safety early warning system based on driving risk feedback is characterized by comprising a road side terminal, a bus driver database and a vehicle-mounted terminal, wherein the road side terminal is communicated with the vehicle-mounted terminal, and the road side terminal under intelligent traffic conditions is used for collecting buses Road traffic environment information and natural environment information of the driving area; the bus driver database is communicated with the vehicle-mounted terminal and is used for storing bus driver information, vehicle information corresponding to the bus driver and historical driving records of the bus driver;
the vehicle-mounted terminal comprises an external motion information acquisition module, an internal working condition information acquisition module, a driver information extraction module, a vehicle driving risk assessment module, a driver feedback assessment module and a vehicle early warning module;
the external motion information acquisition module is used for acquiring driving parameters and position information of the vehicle and N surrounding vehicles;
the internal working condition information acquisition module is used for acquiring the current driving state of the driver and the in-vehicle environment information;
the driver information extraction module is used for extracting buses from a bus driver databaseExtracting corresponding driver information;
the vehicle driving risk assessment module is used for assessing driving risk in real time according to the received data and comprises an accident severity prediction module, a collision probability calculation module and a risk calculation module;
the accident severity prediction module is used for predicting vehicles iWith public transport vehiclesAccident severity of (2);
the collision probability calculation module is used for integrating the kinematic collision coefficient and the macroscopic collision coefficient to calculate the busWith vehiclesiCollision probability under the interaction condition of 'people and vehicles road rings';
the risk amount calculation module is used for calculating the current running risk amount in real time according to the data of the accident severity prediction module and the collision probability calculation module, and if the current running risk amount is higher than a critical value, the risk amount information is sent to the driver feedback evaluation module of the vehicle-mounted terminal;
the driver feedback evaluation module is used for retrieving the history driving record of the current driver in the driver information extraction module, calculating the driving acceleration of the safe driving conforming to the current risk state and according to the busCurrent acceleration->Calculating the driving risk feedback degree with the driving acceleration of the safe driving, and sending an early warning signal to the vehicle early warning module when the driving risk feedback degree is lower than a safety critical value; the calculation formula of the driving risk feedback degree is as follows:
;
;
;
in the method, in the process of the invention,is driving risk feedback degree, < >>Is a bus +.>At the current driving risk amount->Acceleration which can keep safe driving under influence, < +. >Is the risk transformation coefficient,/->Is the inertial running acceleration,/->Is the maximum acceleration of the vehicle, < > is->Is the desired speed of the vehicle,/->Is the current driving speed of the vehicle, < > is->Is the speed difference influence coefficient;
and the vehicle early warning module reminds the driver through audible and visual alarm after receiving the early warning information sent by the driver feedback evaluation module.
8. The bus driving safety early warning system based on driving risk feedback according to claim 7, wherein the external motion information acquisition module comprises a binocular camera and a vehicle-mounted laser radar; the internal working condition information acquisition module comprises a vehicle-mounted high-definition camera.
9. An electronic device, comprising: one or more processors, memory; the bus driving safety early warning method based on the driving risk feedback is characterized in that the memory is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors realize the bus driving safety early warning method based on the driving risk feedback.
10. A computer readable medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the bus driving safety precaution method based on driving risk feedback as claimed in any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310696828.4A CN116453345B (en) | 2023-06-13 | 2023-06-13 | Bus driving safety early warning method and system based on driving risk feedback |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310696828.4A CN116453345B (en) | 2023-06-13 | 2023-06-13 | Bus driving safety early warning method and system based on driving risk feedback |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116453345A CN116453345A (en) | 2023-07-18 |
| CN116453345B true CN116453345B (en) | 2023-08-18 |
Family
ID=87130520
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310696828.4A Active CN116453345B (en) | 2023-06-13 | 2023-06-13 | Bus driving safety early warning method and system based on driving risk feedback |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116453345B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117636591B (en) * | 2023-11-29 | 2024-09-24 | 武汉市公共交通集团有限责任公司信息中心 | Public transport driving safety early warning method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110120153A (en) * | 2019-05-24 | 2019-08-13 | 广州公交集团第三公共汽车有限公司 | A kind of public transport drives accident risk assessment system and its method |
| CN110414831A (en) * | 2019-07-24 | 2019-11-05 | 清华大学 | People's bus or train route coupling methods of risk assessment and device based on driver's Cognitive Perspective |
| CN111079834A (en) * | 2019-12-16 | 2020-04-28 | 清华大学 | Intelligent vehicle safety situation assessment method considering multi-vehicle interaction |
| CN112991685A (en) * | 2021-02-10 | 2021-06-18 | 武汉理工大学 | Traffic system risk assessment and early warning method considering fatigue state influence of driver |
| WO2021223458A1 (en) * | 2020-05-06 | 2021-11-11 | 重庆文理学院 | Driving risk unified quantification method based on comprehensive consideration of human, vehicle and road factors |
| WO2021251351A1 (en) * | 2020-06-09 | 2021-12-16 | 株式会社日立物流 | Operation support method, operation support system, and operation support server |
| CN115620530A (en) * | 2022-09-19 | 2023-01-17 | 哈尔滨工业大学 | Automatic driving takeover risk assessment model considering driving risk field and construction method thereof |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10356309A1 (en) * | 2003-11-28 | 2005-06-23 | Robert Bosch Gmbh | Method and device for warning the driver of a motor vehicle |
| US10417909B1 (en) * | 2018-02-26 | 2019-09-17 | Verizon Connect Ireland Ltd. | Identifying wrong-way travel events |
-
2023
- 2023-06-13 CN CN202310696828.4A patent/CN116453345B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110120153A (en) * | 2019-05-24 | 2019-08-13 | 广州公交集团第三公共汽车有限公司 | A kind of public transport drives accident risk assessment system and its method |
| CN110414831A (en) * | 2019-07-24 | 2019-11-05 | 清华大学 | People's bus or train route coupling methods of risk assessment and device based on driver's Cognitive Perspective |
| CN111079834A (en) * | 2019-12-16 | 2020-04-28 | 清华大学 | Intelligent vehicle safety situation assessment method considering multi-vehicle interaction |
| WO2021223458A1 (en) * | 2020-05-06 | 2021-11-11 | 重庆文理学院 | Driving risk unified quantification method based on comprehensive consideration of human, vehicle and road factors |
| WO2021251351A1 (en) * | 2020-06-09 | 2021-12-16 | 株式会社日立物流 | Operation support method, operation support system, and operation support server |
| CN112991685A (en) * | 2021-02-10 | 2021-06-18 | 武汉理工大学 | Traffic system risk assessment and early warning method considering fatigue state influence of driver |
| CN115620530A (en) * | 2022-09-19 | 2023-01-17 | 哈尔滨工业大学 | Automatic driving takeover risk assessment model considering driving risk field and construction method thereof |
Non-Patent Citations (1)
| Title |
|---|
| Huihua Gao ; Ting Qu ; Yunfeng Hu ; .Personalized Driver Car-Following Model — Considering Human's Limited Perception Ability and Risk Assessment Characteristics.《2022 6th CAA International Conference on Vehicular Control and Intelligence (CVCI)》.2022,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116453345A (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11688203B2 (en) | Systems and methods for providing visual allocation management | |
| US11878720B2 (en) | Method and system for risk modeling in autonomous vehicles | |
| US11769356B2 (en) | Collision evaluation | |
| WO2020169052A1 (en) | Systems and methods for driving condition identification | |
| KR101617349B1 (en) | Diagnostic system and method for the analysis of driving behavior | |
| US11928739B2 (en) | Method and system for vehicular collision reconstruction | |
| CN110782111B (en) | Risk assessment method and system | |
| CN106651602A (en) | ADAS intelligent vehicle-mounted terminal-based vehicle insurance management service system | |
| CN113256993B (en) | Method for training and analyzing vehicle driving risk by model | |
| CN111598368B (en) | Risk identification method, system and device based on stop abnormality after stroke end | |
| CN110807930A (en) | Dangerous vehicle early warning method and device | |
| CN116453345B (en) | Bus driving safety early warning method and system based on driving risk feedback | |
| TW202101344A (en) | Systems And Method For Calculating Liability Of A Driver Of A Vehicle | |
| Russell et al. | Naturalistic study of Level 2 driving automation functions | |
| CN113022557A (en) | Vehicle-mounted monitoring system and method based on active safety early warning | |
| CN114997756B (en) | Vehicle residual value evaluation system and method based on cockpit data | |
| CN116596307A (en) | Method for constructing driver security portrait model based on public transport operation security data | |
| CN115871682A (en) | Method and system for monitoring, evaluating and early warning safe driving behavior of driver | |
| CN110991782A (en) | Risk order studying and judging method and system | |
| CN111341106B (en) | Traffic early warning method, device and equipment | |
| CN113947326A (en) | Comprehensive vehicle risk classification and risk premium measurement and calculation method | |
| Jain et al. | A computational model for driver risk evaluation and crash prediction using contextual data from on-board telematics | |
| Loureiro et al. | Building a Dataset for Trip Style Assessment Based on Real Trip Data. | |
| Ghasemi et al. | Traffic Lane Change Detection using mobile phone sensors and geolocation | |
| Jacob | What can the road-based transport can learn from the aviation safety system: a case study of the black boxes and event data recorders |
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 |