CN112070419A - Risk degree quantification method for potential dangerous situations of automobile driving - Google Patents
Risk degree quantification method for potential dangerous situations of automobile driving Download PDFInfo
- Publication number
- CN112070419A CN112070419A CN202011007534.9A CN202011007534A CN112070419A CN 112070419 A CN112070419 A CN 112070419A CN 202011007534 A CN202011007534 A CN 202011007534A CN 112070419 A CN112070419 A CN 112070419A
- Authority
- CN
- China
- Prior art keywords
- risk
- degree
- elements
- potential
- driving
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000011002 quantification Methods 0.000 title claims description 6
- 238000011156 evaluation Methods 0.000 claims description 41
- 238000000605 extraction Methods 0.000 claims description 13
- 238000005286 illumination Methods 0.000 claims description 8
- 238000007619 statistical method Methods 0.000 claims description 8
- 238000013077 scoring method Methods 0.000 claims description 4
- 230000003068 static effect Effects 0.000 claims description 3
- 238000012502 risk assessment Methods 0.000 claims 1
- 238000013139 quantization Methods 0.000 abstract description 7
- 238000004458 analytical method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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 method for quantifying risk degree of a potential risk situation of automobile driving, which comprises the steps of extracting primary, intermediate and final risk elements in a grading manner according to components of the potential risk situation, then calculating the risk degree membership degree of the final risk element, calculating the weight values of the primary risk element and the intermediate risk element, and calculating the risk degree membership degree of the primary risk element; and finally, calculating the risk degree of the potential dangerous situation of the automobile driving according to the weight value and the risk degree membership degree of the primary risk element, the driving speed and the potential dangerous movement speed. By the method, the risk situation can be measured by using the quantitative index, and the method has the advantages of quantization, simplicity and high quantization precision.
Description
Technical Field
The invention belongs to the technical field of driver safety risk management, and particularly relates to a risk degree quantification method for a potential risk situation of automobile driving.
Background
The driver's danger identification is a special risk management behavior, which is a driving behavior that the driver identifies and evaluates the risk degree of the traffic environment, and adjusts the vehicle driving state according to the risk degree to ensure safe driving, and is closely related to the road traffic safety. Currently, scholars at home and abroad research various methods for evaluating the danger identification capability of drivers, but the accuracy and the effectiveness of evaluation results obtained by the evaluation methods are questioned. The risk degree of the potential dangerous situation of the automobile driving is one of the important factors influencing the credibility of the evaluation result. Different risk degrees exist in different dangerous driving situations of the automobile, and different identification difficulties are generated. If different drivers adopt the potential danger scenes with different risk degrees for evaluation and do not make a difference in the evaluation model, the credibility of the evaluation result is influenced. Therefore, quantification of risk degree of the potential danger situation of automobile driving is achieved, unified judgment standard of the risk degree is obtained, and the confidence and validity degree of the evaluation result of the potential danger identification capability of the driver can be further improved.
Disclosure of Invention
Therefore, the invention provides a method for quantifying the risk degree of the potential danger situation of the driving of the automobile, which is used for solving the problem of accuracy of identification capability evaluation of the potential danger of the driving of the automobile. The invention has the characteristics of simple quantization method and high quantization precision.
In order to achieve the purpose, the invention adopts the following technical scheme to realize the purpose:
a risk degree quantification method for a potential dangerous situation of automobile driving comprises the following steps:
s1: extracting elements which can influence the risk degree of the automobile driving potential danger scene as first-level risk elements according to the components of the automobile driving potential danger scene;
s2: extracting elements which can influence the risk degree of the primary risk elements as secondary risk elements according to the composition of the primary risk elements;
s3: extracting elements which can influence the risk degree of the secondary risk elements as tertiary risk elements according to the composition of the secondary risk elements;
defining: all elements participating in further extraction in the primary risk elements are called primary risk elements, all elements participating in further extraction in the secondary risk elements are called intermediate risk elements, and all elements not participating in further extraction and all tertiary risk elements in the secondary risk elements are called final risk elements;
s4: calculating the risk degree membership degree of the final level risk element by adopting a method of combining a level evaluation system and a fuzzy statistical method according to the influence degree of the final level risk element on the risk degree of the potential dangerous situation of the driving of the automobile;
s5: respectively calculating the weight values of the primary risk elements and the intermediate risk elements by adopting a method of combining a grading method and an analytic hierarchy process according to the influence degree of the primary risk elements and the intermediate risk elements on the risk degree of the potential dangerous situation of the automobile driving;
s6: calculating the risk degree membership degree of the corresponding primary risk element by adopting a fuzzy comprehensive evaluation method according to the weight value of the intermediate risk element and the risk degree membership degree of the corresponding final risk element;
s7: and calculating the risk degree of the potential dangerous situation of the automobile driving by adopting a fuzzy comprehensive evaluation method according to the weighted value and the risk degree membership degree of the primary risk element and the ratio of the driving speed to the potential dangerous movement speed of the automobile driving.
The primary risk elements include: 1) driving environment characteristics, 2) potential danger prompt information characteristics, 3) potential danger characteristics, 4) relevance degree of the potential danger prompt information and the potential danger, and 5) driving speed; wherein the travel speed does not participate in further extraction.
The secondary risk elements include: 1) traffic environment, road line type and traffic environment illumination under the driving environment characteristic; 2) the motion state, the position, the color and the size of the potential danger prompt message; 3) motion state, location, color and size under potentially dangerous characteristics; 4) the relevance between the potential danger prompt information and the potential danger relevance is strong or weak; and the intensity of the potential danger prompt information and the potential danger correlation degree does not participate in further extraction.
The three-level risk elements comprise: 1) urban roads, expressways, mountain roads, suburban roads in traffic environments; 2) straight roads, ramps, curves and intersections under the road line type; 3) under the illumination of the traffic environment, the vehicle is cloudy and cloudy in sunny days, rains are small, snow is small, fog is small, rains are large, snow is heavy and fog is strong, and the vehicle is used at night; 4) potential danger prompt information and static, slow-speed movement, medium-speed movement and high-speed movement of potential dangers in a motion state; 5) the front, the left front, the right front and the back under the positions of the potential danger prompt information and the potential danger; 6) the potential danger prompt information and the potential danger are bright, dark and close to the environment; 7) the potential danger prompt information and the magnitude of the potential danger are large, medium, small and tiny.
In step S4, a 5-level evaluation system including high, medium, and low is adopted; according to a 5-level evaluation system, firstly, evaluation experts evaluate final-level risk elements according to the influence degree of the risk elements on the risk degree of the potential risk situation of the driving of the automobile, then, statistical analysis is carried out on the evaluation results of all the evaluation experts by adopting a fuzzy statistical method, and the occupation ratio of the number of experts in each evaluation level is calculated, namely the risk degree membership degree of the risk elements in the evaluation level.
In step S5, a scoring system is adopted to respectively score each sub-element included in each type of primary risk element and each type of secondary risk element by pairwise comparison according to the degree of influence of the primary risk elements and the secondary risk elements on the risk degree of the potential risk situation of driving the automobile; the scale of scoring is:
the scoring method comprises the following steps: and (3) relative to the risk element B, selecting a corresponding value for the risk element A if the influence degree of the risk element A on the risk degree of the potential dangerous situation of the automobile driving is closer to which type in the scoring scale, and then calculating the weight values of the primary risk element and the intermediate risk element by adopting an analytic hierarchy process according to the scoring result of the expert.
In step S6, the weight values of the intermediate-level risk elements and the risk degree membership degrees of the corresponding final-level risk elements are multiplied to obtain the risk degree membership degrees of the corresponding primary-level risk elements.
In step S7, the maximum value of the product of the weighted values of all the primary risk elements and the risk degree membership is taken, and then multiplied by the ratio of the driving speed to the vehicle driving potential risk movement speed, so as to obtain the risk degree of the vehicle driving potential risk situation.
The invention has the beneficial effects that: by the method, the risk degree of the potential dangerous situation of automobile driving can be measured by using the quantization index, and the method has the advantages of quantization, simplicity and high quantization precision. Additional features and advantages of the invention will be set forth in the description which follows.
Drawings
Fig. 1 is a flowchart of a risk degree quantifying method for a potentially dangerous situation of driving an automobile according to the present invention.
Detailed Description
The present invention is described in detail below with reference to the drawings and examples, but it should be understood by those skilled in the art that the following examples are not intended to limit the technical solutions of the present invention, and any equivalent changes or modifications made within the spirit of the technical solutions of the present invention should be considered as falling within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a method for quantifying risk of a potentially dangerous situation in driving an automobile, comprising the following steps:
s1: and extracting the first-level risk elements of the potential dangerous situations of automobile driving. According to the components of the potential dangerous situation of automobile driving, the factors for analyzing the influence on the risk degree of the potential dangerous situation of automobile driving mainly comprise: (1) driving environment characteristics, (2) potential danger prompting information characteristics, (3) potential danger characteristics, (4) relevance degree of potential danger prompting information and potential danger, and (5) driving speed, therefore, the elements are extracted as first-level risk elements of the potential danger scene of automobile driving, namely, the expression is as follows:
R＝{R1,R2,R3,R4,R5and { driving environment characteristic, potential danger prompt information characteristic, potential danger prompt information and potential danger correlation degree, driving speed }.
S2: and extracting secondary risk elements of the potential dangerous situations of automobile driving. According to the composition of the first-level risk elements, further analysis comprises the following steps: (1) the following factors that affect the risk of driving environment characteristics are mainly: traffic environment, road linetype and traffic environment illuminance; (2) the main factors influencing the risk degree of the characteristics of the potentially dangerous prompt message are as follows: motion state, location, color and size; (3) the main factors that affect the risk of the potentially dangerous nature are: motion state, location, color and size; (4) the factor that influences the risk degree of the relevance degree of the potential danger prompt information and the potential danger is mainly the strength of the relevance degree of the two; (5) no risk element has influence on the risk degree of the driving speed, so that the driving speed does not need to subdivide secondary risk elements. Therefore, the above elements are extracted as secondary risk elements of the potential dangerous situation of automobile driving, namely expressed as follows:
R1＝{R11,R12,R13traffic environment, road line type, traffic environment illumination }
R2＝{R21,R22,R23,R24Motion state, position, color, size
R3＝{R31,R32,R33,R34Motion state, position, color, size
R4＝{R41,R42,R43,R44Is strong, medium, weak, uncorrelated
S3: and extracting three-level risk elements of the potential dangerous situations of automobile driving. According to the composition of the secondary risk elements, further analysis comprises the following steps: (1) the main factors that affect the risk of the traffic environment are: urban roads, expressways, mountain roads, suburban roads; (2) the main factors that affect the risk of road alignment are: straight roads, ramps, curves, intersections; (3) the main factors influencing the risk of the traffic environment illumination are: cloudy and cloudy in sunny days, light rain, small snow and small fog, heavy rain, large snow and thick fog at night; because the influence of sunny days, cloudy days and cloudy days on the risk degree belongs to the same level, the influence is commonly attributed to the same type of elements; similarly, the influence of light rain, small snow and small fog, heavy rain and large snow and heavy fog on the risk degree at night is also divided into the same type of elements; (4) the factors that influence the risk degree of the potentially dangerous prompt information and the potentially dangerous motion state mainly include: static, slow moving, medium-speed moving and high-speed moving; (5) the factors influencing the risk degree of the position where the potential danger is located and the potential danger prompt information mainly include: right front, left front, right front, rear; (6) the main factors influencing the risk degree of the potentially dangerous prompt message and the potentially dangerous color are: bright, bright and dark colors, close to the environment; (7) the main factors that affect the risk degree of the potential danger prompt information and the magnitude of the potential danger are: large, medium, small and tiny; (8) no risk element influences the strength of the relevance degree of the potential danger prompt information and the potential danger, so that the relevance degree of the potential danger prompt information and the potential danger does not need to be subdivided into three levels of risk elements. Therefore, the above elements are extracted as three-level risk elements of the potential dangerous situation of automobile driving, namely:
R11＝{R111,R112,R113,R114(urban road, highway, mountain road, suburban road) }
R12＝{R121,R122,R123,R124(a straight road, a ramp, a curve, an intersection) }
R13＝{R131,R132,R133,R134In sunny, cloudy and cloudy days, in rainy, snowy and foggy days, in rainy and snowy days, in heavy rainy and snowy days, at night
R21＝{R211,R212,R213,R214At rest, moving at slow speed, moving at medium speed, and moving at high speed
R22＝{R221,R222,R223,R224Front, left front, right front, rear
R23＝{R231,R232,R233,R234Bright, dark, close to the environment
R24＝{R241,R242,R243,R244Large, medium, small, tiny }
R31＝{R311,R312,R313,R314At rest, moving at slow speed, moving at medium speed, and moving at high speed
R32＝{R321,R322,R323,R324Front, left front, right front, rear
R33＝{R331,R332,R333,R334Bright, dark, close to the environment
R34＝{R341,R342,R343,R344Large, medium, small, tiny }
The driving speed in the first-level risk elements, the strength of the correlation between the potential danger prompt information and the potential danger in the second-level risk elements and all the third-level risk elements are the most intuitive feature expression of the potential danger scene of the automobile driving, so that the extraction cannot be continued. Therefore, all the elements participating in further extraction in the primary risk elements are called primary risk elements; all elements participating in further extraction in the secondary risk elements are called intermediate risk elements; elements of the secondary risk elements that cannot be further extracted and all tertiary risk elements are referred to as final risk elements. This definition is described below.
S4: and calculating the risk degree membership of the final risk elements of the potential dangerous situations of automobile driving. And evaluating the influence degree of the final-level risk elements on the risk degree of the potential dangerous situation of the driving of the automobile by adopting a 5-level evaluation system, wherein the evaluation level is expressed as follows:
M＝{m1,m2,m3,m4,m5hi, mid-high, mid-low, low
And calculating the risk degree membership of the ultimate risk elements according to an evaluation system, wherein the method comprises the following steps: firstly, the final-level risk elements are evaluated by the experts of the evaluation group according to the influence degree of the risk elements on the risk degree of the automobile driving potential risk situation, for example, if someone thinks that the influence degree of a certain risk element on the risk of the automobile driving potential risk situation is very large, the evaluation is high, and if someone thinks that the influence degree of the risk element is not large, the evaluation is medium.
And then, carrying out statistical analysis on the evaluation results of all the evaluation experts by adopting a fuzzy statistical method, and calculating the proportion of the number of experts in each evaluation level, namely the risk degree membership of the risk element in the evaluation level. For example, the degree of influence of the risk element "urban road" on the risk degree of the potential risk situation of driving a car is evaluated, and there are 10 evaluation experts in total, wherein 4 experts are considered as "high", 2 experts are considered as "medium high", 1 expert is considered as "medium", 2 experts are considered as "medium low", 1 expert is considered as "low", the risk degree membership degree of the risk element belonging to "high" is 4/10, the risk degree membership degree belonging to "medium high" is 2/10, the risk degree membership degree belonging to "medium" is 1/10, the risk degree membership degree belonging to "medium low" is 2/10, and the risk degree membership degree belonging to "low" is 1/10.
Counting according to the method, and recording:
(1) the risk degree membership of each three-level risk element in the traffic environment is as follows:
urban road: m111＝[m1111,m1112,m1113,m1114,m1115]
An expressway: m112＝[m1121,m1122,m1123,m1124,m1125]
Mountain road: m113＝[m1131,m1132,m1133,m1134,m1135]
Suburb highway: m114＝[m1141,m1142,m1143,m1144,m1145]
(2) The risk degree membership of each three-level risk element in the road line type is as follows:
straight path: m121＝[m1211,m1212,m1213,m1214,m1215]
Ramp: m122＝[m1221,m1222,m1223,m1224,m1225]
Bending: m123＝[m1231,m1232,m1233,m1234,m1235]
Intersection: m124＝[m1241,m1242,m1243,m1244,m1245]
(3) The risk degree membership of each three-level risk element in the traffic environment illumination is as follows:
cloudy and cloudy in sunny days: m131＝[m1311,m1312,m1313,m1314,m1315]
Rain, snow and fog: m132＝[m1321,m1322,m1323,m1324,m1325]
Heavy rain, snow and fog: m133＝[m1331,m1332,m1333,m1334,m1335]
At night: m134＝[m1341,m1342,m1343,m1344,m1335]
(4) The risk degree membership of each three-level risk element in the motion state of the potential danger prompt information is as follows:
and (3) standing: m211＝[m2111,m2112,m2113,m2114,m2115]
And (3) slow moving: m212＝[m2121,m2122,m2123,m2124,m2125]
Moving at a medium speed: m213＝[m2131,m2132,m2133,m2134,m2135]
Moving at a high speed: m214＝[m2141,m2142,m2143,m2144,m2145]
(5) The risk degree membership of each three-level risk element in the position of the potential danger prompt information is as follows:
right ahead: m221＝[m2211,m2212,m2213,m2214,m2215]
Left front: m222＝[m2221,m2222,m2223,m2224,m2225]
Right front: m223＝[m2231,m2232,m2233,m2234,m2235]
Rear: m224＝[m2241,m2242,m2243,m2244,m2245]
(6) The risk degree membership of each three-level risk element in the color of the potential danger prompt information is as follows:
bright: m231＝[m2311,m2312,m2313,m2314,m2315]
And (3) color cast: m232＝[m2321,m2322,m2323,m2324,m2325]
Partial dark color: m233＝[m2331,m2332,m2333,m2334,m2335]
Close to the environment: m234＝[m2341,m2342,m2343,m2344,m2345]
(7) The risk degree membership of each three-level risk element in the size of the potential danger prompt information is as follows:
large: m241＝[m2411,m2412,m2413,m2414,m2415]
The method comprises the following steps: m242＝[m2421,m2422,m2423,m2424,m2425]
Small: m243＝[m2431,m2432,m2433,m2434,m2435]
And (2) micro: m244＝[m2441,m2442,m2443,m2444,m2445]
(8) The risk degree membership of each three-level risk element in the potentially dangerous motion state is as follows:
and (3) standing: m311＝[m3111,m3112,m3113,m3114,m3115]
And (3) slow moving: m312＝[m3121,m3122,m3123,m3124,m3125]
Moving at a medium speed: m313＝[m3131,m3132,m3133,m3134,m3135]
Moving at a high speed: m314＝[m3141,m3142,m3143,m3144,m3145]
(9) The risk degree membership of each three-level risk element in the position of the potential risk is as follows:
right ahead: m321＝[m3211,m3212,m3213,m3214,m3215]
Left front: m322＝[m3221,m3222,m3223,m3224,m3225]
Right front: m323＝[m3231,m3232,m3233,m3234,m3235]
Rear: m324＝[m3241,m3242,m3243,m3244,m3245]
(10) The risk degree membership of each tertiary risk element in the potentially dangerous color is:
bright: m331＝[m3311,m3312,m3313,m3314,m3315]
And (3) color cast: m332＝[m3321,m3322,m3323,m3324,m3325]
Partial dark color: m333＝[m3331,m3332,m3333,m3334,m3335]
Close to the environment: m334＝[m3341,m3342,m3343,m3344,m3345]
(11) The risk degree membership of each three-level risk element in the potential risk size is as follows:
large: m341＝[m3411,m3412,m3413,m3414,m3415]
The method comprises the following steps: m342＝[m3421,m3422,m3423,m3424,m3425]
Small: m343＝[m3431,m3432,m3433,m3434,m3435]
And (2) micro: m344＝[m3441,m3442,m3443,m3444,m3445]
(12) The risk degree membership of each secondary risk element in the relevance between the potential risk prompt information and the potential risk is as follows:
strong: m41＝[m411,m412,m413,m414,m415]
The method comprises the following steps: m42＝[m421,m422,m423,m424,m425]
Weak: m43＝[m431,m432,m433,m434,m435]
No correlation is found: m44＝[m441,m442,m443,m444,m445]
S5: and calculating the weight values of the primary risk element and the intermediate risk element of the potential dangerous situation of the automobile driving. The method comprises the following steps:
and (4) adopting a scoring system, and respectively carrying out pairwise comparison and scoring on each sub-element contained in each type of primary risk element and each sub-element contained in each type of secondary risk element according to the influence degree of the sub-elements on the risk degree of the potential risk situation. The scale of scoring is:
the scoring method comprises the following steps: and (4) relative to the risk element B, selecting a corresponding value for A if the influence degree of the risk element A on the risk degree of the potential dangerous situation of the automobile driving is closer to which type in the scoring scale. For example, if the risk element a has a significantly greater influence on the risk degree of the potentially dangerous situation of driving an automobile than the risk element B, the risk element a is classified into 3 points; if the degree of influence is significantly less than B, score A is 1/3.
And also hiring a plurality of evaluation experts, respectively scoring according to scoring scale and scoring method, then calculating the weight values of the primary risk elements and the intermediate risk elements by adopting an analytic hierarchy process according to the scoring results of the experts, and marking as:
(1) the weight value of each sub-element in the primary risk element is as follows:
wR＝[w1,w2,w3,w4]
w1as a weight of driving environment characteristics, w2Weight of the characteristic of the potentially dangerous cue information, w3Weight of potentially dangerous characteristic, w4And the relevance degree weight of the potential danger prompt information and the potential danger.
(2) The weight values of the intermediate risk elements under the driving environment characteristic are as follows:
w11as a traffic environment weight, w12Is a road linear weight, w13And the traffic environment illumination weight is obtained.
(3) The weight values of the intermediate risk elements under the characteristic of the potential danger prompt information are as follows:
w21as a motion state weight, w22As location weight, w23Is a color weight, w24Is a magnitude weight.
(4) The weight values for the intermediate risk elements under the potential hazard characteristics are:
w31as a motion state weight, w32As location weight, w33Is a color weight, w34Is a magnitude weight.
S6: and calculating the risk degree membership of the primary risk elements of the potential dangerous situations of automobile driving. And calculating the risk degree membership of the primary risk element of the automobile driving potential risk situation by adopting a fuzzy comprehensive evaluation method according to the weight value of the intermediate risk element and the type and risk degree membership of the final risk element. Comprises the following steps:
(1) the risk degree membership degree of the driving environment characteristic is as follows:
(2) the risk degree membership of the potential danger prompt information characteristic is as follows:
(3) the risk degree membership of the potentially dangerous characteristic is:
(4) the risk degree membership of the relevance between the potential risk prompt information and the potential risk is as follows:
M4＝[m41,m42,m43,m44,m45]＝[m4n1，m4n2，m4n3，m4n4，m4n5]
and selecting i, j, k, m and n as one of values 1, 2, 3 or 4 respectively according to the type of the final risk elements of the potential dangerous situation of the automobile driving. For example, if a traffic environment where a certain car drives a potentially dangerous situation is an urban road, M is1I in (1) is selected as 1.
S7: and calculating the risk degree of the potential dangerous situation of the automobile driving. And calculating the risk degree of the potential dangerous situation of the automobile driving by adopting a fuzzy comprehensive evaluation method according to the weighted value and the risk degree membership degree of the primary risk element and the proportional relation between the driving speed and the potential dangerous movement speed of the automobile driving. Namely:
wherein v is the running speed of the automobile, v0Potentially dangerous speeds for the vehicle driving.
The above-described embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above-described embodiments, and any obvious improvements, substitutions or modifications that can be made by those skilled in the art without departing from the spirit of the present invention belong to the protection scope of the present invention.
Claims (8)
1. A risk degree quantification method for a potential dangerous situation of automobile driving is characterized by comprising the following steps:
s1: extracting elements which can influence the risk degree of the automobile driving potential danger scene as first-level risk elements according to the components of the automobile driving potential danger scene;
s2: extracting elements which can influence the risk degree of the primary risk elements as secondary risk elements according to the composition of the primary risk elements;
s3: extracting elements which can influence the risk degree of the secondary risk elements as tertiary risk elements according to the composition of the secondary risk elements;
defining: all elements participating in further extraction in the primary risk elements are called primary risk elements, all elements participating in further extraction in the secondary risk elements are called intermediate risk elements, and all elements not participating in further extraction and all tertiary risk elements in the secondary risk elements are called final risk elements;
s4: calculating the risk degree membership degree of the final level risk element by adopting a method of combining a level evaluation system and a fuzzy statistical method according to the influence degree of the final level risk element on the risk degree of the potential dangerous situation of the driving of the automobile;
s5: respectively calculating the weight values of the primary risk elements and the intermediate risk elements by adopting a method of combining a grading method and an analytic hierarchy process according to the influence degree of the primary risk elements and the intermediate risk elements on the risk degree of the potential dangerous situation of the automobile driving;
s6: calculating the risk degree membership degree of the corresponding primary risk element by adopting a fuzzy comprehensive evaluation method according to the weight value of the intermediate risk element and the risk degree membership degree of the corresponding final risk element;
s7: and calculating the risk degree of the potential dangerous situation of the automobile driving by adopting a fuzzy comprehensive evaluation method according to the weighted value and the risk degree membership degree of the primary risk element and the ratio of the driving speed to the potential dangerous movement speed of the automobile driving.
2. The method of claim 1, wherein the primary risk element comprises: 1) driving environment characteristics, 2) potential danger prompt information characteristics, 3) potential danger characteristics, 4) relevance degree of the potential danger prompt information and the potential danger, and 5) driving speed; wherein the travel speed does not participate in further extraction.
3. The method of claim 2, wherein the secondary risk elements comprise: 1) traffic environment, road line type and traffic environment illumination under the driving environment characteristic; 2) the motion state, the position, the color and the size of the potential danger prompt message; 3) motion state, location, color and size under potentially dangerous characteristics; 4) the relevance between the potential danger prompt information and the potential danger relevance is strong or weak; and the intensity of the potential danger prompt information and the potential danger correlation degree does not participate in further extraction.
4. The method of claim 3, wherein the three-level risk elements comprise: 1) urban roads, expressways, mountain roads, suburban roads in traffic environments; 2) straight roads, ramps, curves and intersections under the road line type; 3) under the illumination of the traffic environment, the vehicle is cloudy and cloudy in sunny days, rains are small, snow is small, fog is small, rains are large, snow is heavy and fog is strong, and the vehicle is used at night; 4) potential danger prompt information and static, slow-speed movement, medium-speed movement and high-speed movement of potential dangers in a motion state; 5) the front, the left front, the right front and the back under the positions of the potential danger prompt information and the potential danger; 6) the potential danger prompt information and the potential danger are bright, dark and close to the environment; 7) the potential danger prompt information and the magnitude of the potential danger are large, medium, small and tiny.
5. The risk assessment method for the potentially dangerous driving situation of claim 1, wherein in step S4, 5-level evaluation is adopted, including high, medium, and low; according to a 5-level evaluation system, firstly, evaluation experts evaluate final-level risk elements according to the influence degree of the risk elements on the risk degree of the potential risk situation of the driving of the automobile, then, statistical analysis is carried out on the evaluation results of all the evaluation experts by adopting a fuzzy statistical method, and the occupation ratio of the number of experts in each evaluation level is calculated, namely the risk degree membership degree of the risk elements in the evaluation level.
6. The method for quantifying risk degree of a potentially dangerous driving situation of a vehicle according to claim 1, wherein in step S5, a scoring system is used to score each type of the primary risk elements and each sub-element included in the intermediate risk elements according to their influence degree on the risk degree of the potentially dangerous driving situation of the vehicle;
the scale of scoring is:
the scoring method comprises the following steps: and (3) relative to the risk element B, selecting a corresponding value for the risk element A if the influence degree of the risk element A on the risk degree of the potential dangerous situation of the automobile driving is closer to which type in the scoring scale, and then calculating the weight values of the primary risk element and the intermediate risk element by adopting an analytic hierarchy process according to the scoring result of the expert.
7. The method for quantifying risk level of the risk scenario of potential danger of driving an automobile according to claim 1, wherein in step S6, the weight value of the intermediate level risk element is multiplied by the risk level membership level of the corresponding final level risk element, so as to obtain the risk level membership level of the corresponding primary level risk element.
8. The method for quantifying the risk degree of the driving potential risk situation of the automobile according to claim 1, wherein in step S7, the maximum value of the product of the weight values and the risk degree membership degrees of all the primary risk elements is taken and then multiplied by the ratio of the driving speed to the movement speed of the driving potential risk situation of the automobile, so as to obtain the risk degree of the driving potential risk situation of the automobile.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011007534.9A CN112070419B (en) | 2020-09-23 | 2020-09-23 | Method for quantifying risk of potential dangerous situation of automobile driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011007534.9A CN112070419B (en) | 2020-09-23 | 2020-09-23 | Method for quantifying risk of potential dangerous situation of automobile driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112070419A true CN112070419A (en) | 2020-12-11 |
| CN112070419B CN112070419B (en) | 2023-11-07 |
Family
ID=73680833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011007534.9A Active CN112070419B (en) | 2020-09-23 | 2020-09-23 | Method for quantifying risk of potential dangerous situation of automobile driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112070419B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114104007A (en) * | 2022-01-28 | 2022-03-01 | 交通运输部公路科学研究所 | Minimum risk control strategy for automatic driving vehicle |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006127491A (en) * | 2004-09-29 | 2006-05-18 | Yamaha Motor Co Ltd | Driving decision support device, driving decision support method and vehicle |
| CN104376400A (en) * | 2014-10-27 | 2015-02-25 | 广州市中南民航空管通信网络科技有限公司 | Risk assessment method based on fuzzy matrix and analytic hierarchy process |
| CN106920040A (en) * | 2017-03-01 | 2017-07-04 | 西南交通大学 | Freeway tunnel street accidents risks appraisal procedure based on Fuzzy Level Analytic Approach |
| CN106960613A (en) * | 2017-05-26 | 2017-07-18 | 交通运输部公路科学研究所 | Non-intrusion type driver's potential danger identification capability is assessed and training system and method |
| CN107153914A (en) * | 2017-04-18 | 2017-09-12 | 交通运输部公路科学研究所 | A kind of evaluation system and method for automobilism risk |
| KR20190063956A (en) * | 2017-11-30 | 2019-06-10 | 황준호 | System and method for driving evaluation for safe car sharing |
| 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 |
| WO2019213980A1 (en) * | 2018-05-08 | 2019-11-14 | 清华大学 | Intelligent vehicle safety decision-making method employing driving safety field |
| CN110866677A (en) * | 2019-10-25 | 2020-03-06 | 东南大学 | Driver relative risk evaluation method based on benchmark analysis |
| CN111144772A (en) * | 2019-12-30 | 2020-05-12 | 交通运输部公路科学研究所 | Road transportation safety risk real-time assessment method based on data mining |
| CN111489588A (en) * | 2020-03-30 | 2020-08-04 | 腾讯科技（深圳）有限公司 | Vehicle driving risk early warning method and device, equipment and storage medium |
-
2020
- 2020-09-23 CN CN202011007534.9A patent/CN112070419B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006127491A (en) * | 2004-09-29 | 2006-05-18 | Yamaha Motor Co Ltd | Driving decision support device, driving decision support method and vehicle |
| CN104376400A (en) * | 2014-10-27 | 2015-02-25 | 广州市中南民航空管通信网络科技有限公司 | Risk assessment method based on fuzzy matrix and analytic hierarchy process |
| CN106920040A (en) * | 2017-03-01 | 2017-07-04 | 西南交通大学 | Freeway tunnel street accidents risks appraisal procedure based on Fuzzy Level Analytic Approach |
| CN107153914A (en) * | 2017-04-18 | 2017-09-12 | 交通运输部公路科学研究所 | A kind of evaluation system and method for automobilism risk |
| CN106960613A (en) * | 2017-05-26 | 2017-07-18 | 交通运输部公路科学研究所 | Non-intrusion type driver's potential danger identification capability is assessed and training system and method |
| KR20190063956A (en) * | 2017-11-30 | 2019-06-10 | 황준호 | System and method for driving evaluation for safe car sharing |
| WO2019213980A1 (en) * | 2018-05-08 | 2019-11-14 | 清华大学 | Intelligent vehicle safety decision-making method employing driving safety field |
| 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 |
| CN110866677A (en) * | 2019-10-25 | 2020-03-06 | 东南大学 | Driver relative risk evaluation method based on benchmark analysis |
| CN111144772A (en) * | 2019-12-30 | 2020-05-12 | 交通运输部公路科学研究所 | Road transportation safety risk real-time assessment method based on data mining |
| CN111489588A (en) * | 2020-03-30 | 2020-08-04 | 腾讯科技（深圳）有限公司 | Vehicle driving risk early warning method and device, equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 景旭轩;李泾龙;谭宁军;程国锋: "基于驾驶安全性的道路交通环境风险评价模型与应用", 中国职业安全健康协会2015年学术年会 * |
| 王长君;李江平;金会庆;王笑京;蔡凤田;曾涛;高岩;邓毅萍;张树林;: "我国重特大道路交通事故防控体系构建", 人类工效学, no. 05 * |
| 缪明月;尚华燕;裴佳瑢: "非机动车驾驶人道路交通事故风险行为量化分级研究", 安全与环境学报, vol. 14, no. 4 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114104007A (en) * | 2022-01-28 | 2022-03-01 | 交通运输部公路科学研究所 | Minimum risk control strategy for automatic driving vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112070419B (en) | 2023-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109977812B (en) | Vehicle-mounted video target detection method based on deep learning | |
| Sun et al. | The estimation of vehicle speed and stopping distance by pedestrians crossing streets in a naturalistic traffic environment | |
| CN108550263B (en) | Expressway traffic accident cause analysis method based on fault tree model | |
| CN108364467B (en) | Road condition information prediction method based on improved decision tree algorithm | |
| CN110458244B (en) | Traffic accident severity prediction method applied to regional road network | |
| CN109523786A (en) | A kind of traffic accidents genetic analysis method | |
| CN109408557B (en) | Traffic accident cause analysis method based on multiple correspondences and K-means clustering | |
| CN108682149A (en) | The linear causation analysis method in highway accident stain section based on binary logistic regression | |
| Se et al. | The impact of weekday, weekend, and holiday crashes on motorcyclist injury severities: Accounting for temporal influence with unobserved effect and insights from out-of-sample prediction | |
| CN111651712A (en) | Method and system for evaluating complexity of test scene of intelligent automobile | |
| CN113313357A (en) | Traffic road safety evaluation method based on Gaussian process regression analysis | |
| CN112070419A (en) | Risk degree quantification method for potential dangerous situations of automobile driving | |
| Madushani et al. | Evaluating expressway traffic crash severity by using logistic regression and explainable & supervised machine learning classifiers | |
| CN114550445A (en) | Urban area traffic safety state evaluation method and device | |
| CN113095387B (en) | Road risk identification method based on networking vehicle-mounted ADAS | |
| CN116061953A (en) | Truck dangerous driving behavior discrimination evaluation method based on driving track data | |
| Hashemi et al. | Exploratory Analysis of Roadway Departure Crashes Contributing Factors Based on Classification and Regression Trees | |
| Ihs et al. | Road user effect models: the influence of rut depth on traffic safety | |
| Shamanian Esfahani et al. | Investigating the effect of marginal areas around the cities on rural road accidents in Iran using linear and logistic regression approaches | |
| Hashemi et al. | Potential Factors Affecting Roadway Departure Crashes in Oahu, Hawaii | |
| Li et al. | Scene Identification of Single-Motorcycle Death Accidents Based on Binary Logistic Regression and Association Rules | |
| CN115394073B (en) | Highway congestion propagation method based on CA-SIR model in foggy environment | |
| Cheng et al. | Overtaking safety evaluation and setting of auxiliary lane on two-lane highway in China | |
| Chen et al. | Analysis of freeway traffic accidents based on association rule mining | |
| Janoff | Visibility vs response distance: A comparison of two experiments and the implications of their results |
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 |