CN109685273A - Brake failure method for early warning, device, electronic equipment, the storage medium of vehicle - Google Patents
Brake failure method for early warning, device, electronic equipment, the storage medium of vehicle Download PDFInfo
- Publication number
- CN109685273A CN109685273A CN201811598302.8A CN201811598302A CN109685273A CN 109685273 A CN109685273 A CN 109685273A CN 201811598302 A CN201811598302 A CN 201811598302A CN 109685273 A CN109685273 A CN 109685273A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- state
- load
- hidden
- carrying vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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—Systems or methods specially adapted for 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/22—Character recognition characterised by the type of writing
- G06V30/226—Character recognition characterised by the type of writing of cursive writing
- G06V30/2268—Character recognition characterised by the type of writing of cursive writing using stroke segmentation
- G06V30/2276—Character recognition characterised by the type of writing of cursive writing using stroke segmentation with probabilistic networks, e.g. hidden Markov models
Abstract
The present invention provides brake failure method for early warning, device, electronic equipment, the storage medium of a kind of load-carrying vehicle, and method includes: the vehicle-periphery and road environment data and from vehicle vehicle-state and driver behavior data for obtaining each load-carrying vehicle;Multiclass feature information is extracted according to vehicle-periphery and road environment data and from vehicle vehicle-state and driver behavior data;It is established according to extracted multiclass feature information and trains the hidden Markov model for predicting braking state;Using the real-time vehicle ambient enviroment of load-carrying vehicle to be predicted and road environment data and in real time from vehicle vehicle-state and driver behavior data as the input of hidden Markov model;The braking state of load-carrying vehicle to be predicted is determined according to hidden Markov model;If failure state, generates warning information subject to the braking state of load-carrying vehicle to be predicted;If the braking state of load-carrying vehicle to be predicted is failure state, secure path is planned.Method and device provided by the invention realizes brake failure early warning.
Description
Technical field
The present invention relates to brake failure method for early warning, device, the electronics of vehicle early warning field more particularly to a kind of vehicle to set
Standby, storage medium.
Background technique
In recent years, with the development of logistics, Chinese Highway leads and bounds ahead of other means of transportation in the rotation volume of goods transport
Summation.Data show that 2016 end of the year whole nations possess cargo vehicle more than 1,003,000,000.Currently, the every year traffic fortune in China
Defeated accident total amount still occupies a high position, and cargo vehicle causes toll on traffic to account for about one third.According to studies have shown that in crowd
In more traffic accidents, rear-end impact event accounts for 70% or more of accident toatl proportion, and that especially causes on a highway chases after
Tail accident is more, and severe and great casualty takes place frequently, and causes the loss of personnel and property also more serious.When running at high speed, when
Driver lacks conventional maintenance to brake system, gas circuit, valve aging, it is poorly sealed situations such as cause braking pressure insufficient
When, or frequently braked in long downhill path rapid lapse of time, the huge heat for the generation that rubs causes brake thermal decay occur, or
The phenomenon that person's truck load is heavier, and vehicle is caused to be increased by weight inertia, be all easy to cause brake failure.Compared to common vapour
Vehicle, due to truck there is vehicle body length and the vehicle properties such as again, it is easier to brake failure occur, therefore needing will in brake
It issues and alerts to driver when reaching failure warning line.Also, after brake failure occurs for truck, driver is due to alarmed
Often correct reaction immediately can not be made, lose the best time saved oneself and cried for help, in some instances it may even be possible to lead to vehicle pileup phase
The major traffic accidents hit.
For the validity for improving trunk brake, Some Enterprises have developed various auxiliary braking devices.Utilize setting
Friction member and ground touch, to increase the frictional force of automobile and ground.But it does not consider how that eliminating or reduce brake loses
Spirit is lost to caused by vehicle.Some prior arts cause for the linkage deficiency between existing active safety technologies and driver
Active safety technologies can not correct understanding driver intention the problem of, disclose a kind of driver and vehicle active safety technologies join
Dynamic control method and control system, realizes the linkage between active safety technologies and driver, improve vehicle safety and
Reliability.Other prior arts are to overcome existing auxiliary braking system because not having intelligent control function, are existed to driving
Security risk, propose a kind of vehicle auxiliary braking system based on artificial intelligence, can be in emergency braking shape using the system
Under state, by the intellectual analysis to driving states, the braking strategy for meeting current driving security requirement is generated.
It is touched, is increased using the friction member and ground of setting it can be seen that having various auxiliary braking devices at present
The frictional force of automobile and ground, validity and some technologies based on artificial intelligence for improving automobile brake assist vehicle
Braking.But for load-carrying vehicle brake, there is a situation where failures but without related art method.
Summary of the invention
The present invention provides a kind of pre- police of brake failure of load-carrying vehicle to overcome defect existing for above-mentioned the relevant technologies
Method, device, electronic equipment, storage medium, so overcome limitation and defect due to the relevant technologies at least to a certain extent and
One or more caused problem.
According to an aspect of the present invention, a kind of brake failure method for early warning of load-carrying vehicle is provided, comprising:
Obtain the vehicle-periphery and road environment data and from vehicle vehicle-state and driver behavior number of each load-carrying vehicle
According to;
It is special that multiclass is extracted according to vehicle-periphery and road environment data and from vehicle vehicle-state and driver behavior data
Reference breath;
It is established according to extracted multiclass feature information and trains the hidden Markov model for predicting braking state;
By the real-time vehicle ambient enviroment of load-carrying vehicle to be predicted and road environment data and in real time from vehicle vehicle-state and
Input of the driver behavior data as the hidden Markov model;
The braking state of the load-carrying vehicle to be predicted is determined according to the hidden Markov model;
If failure state subject to the braking state of the load-carrying vehicle to be predicted, generates warning information;
If the braking state of the load-carrying vehicle to be predicted is failure state, secure path is planned.
Optionally, described according to vehicle-periphery and road environment data and from vehicle vehicle-state and driver behavior data
Extracting multiclass feature information includes:
The processing of centralization dimension is carried out to all kinds of characteristic informations.
Optionally, described to be established according to extracted multiclass feature information and train the hidden Ma Er for predicting braking state
Can husband's model include:
To the hidden state of each hidden Markov model, corresponding judgment matrix is generated, the i-th of the judgment matrix
The item that judge of row jth column indicates the importance fiducial value between the i-th category feature information and jth category feature information, i, j for greater than etc.
In 1 integer;
Calculate the observation probability matrix for obtaining the hidden Markov model, the row k of the observation probability matrix
The observation probability item of l column indicates that the probability for occurring k-th of characteristic information under first of hidden state, k, l are more than or equal to 1
Integer;
Determine the initial probability distribution matrix of the hidden state of the hidden Markov model, the initial probability distribution matrix
Line number be 1, the probability item of the 1st row l of initial probability distribution matrix column is the initial distribution of first of hidden state
Probability;
The braking state training hidden Markov of vehicle when according to extracted characteristic information, extraction characteristic information
Model, obtains the hidden state-transition matrix of the hidden Markov model, and the hidden state-transition matrix m row n-th arranges hidden
State transfer item is that m-th of hidden state is transferred to n-th of hidden shape probability of state,
Wherein, the hidden state of the hidden Markov model includes failure state, quasi- failure state and normal condition.
Optionally, using the Forward-backward algorithm training hidden Markov model.
Optionally, the planning secure path includes:
Determine the destination of safety;
It is planned automatically using solution space genetic algorithm to the secure path of the destination.
Optionally, described to plan that the secure path to the destination includes: automatically using solution space genetic algorithm
Iteration updates initial population as follows, until meeting predetermined termination condition:
Map coordinates system is established using Grid Method, and generates the path of predetermined quantity at random, by the path of the predetermined quantity
Form initial population;
Advanced group species are formed from selected part path in the initial population using roulette method;
Path in the Advanced group species is intersected, variation processing;
It will be intersected, the Advanced group species for the processing that makes a variation are by corresponding fitness function value update initial population.
It is optionally, described to use roulette method from after composition Advanced group species in selected part path in the initial population,
The path in the Advanced group species is intersected, before the processing that makes a variation further include:
Retain in the Advanced group species that the highest path of fitness function value is as elite path, the elite path is without friendship
Fork, variation processing.
Optionally, the fitness function value is the inverse of the path length.
According to another aspect of the invention, a kind of brake failure prior-warning device of load-carrying vehicle is also provided, comprising:
First obtains module, for obtaining the vehicle-periphery and road environment data and from vehicle vehicle of each load-carrying vehicle
State and driver behavior data;
Extraction module, for according to vehicle-periphery and road environment data and from vehicle vehicle-state and driver behavior number
According to extraction multiclass feature information;
Model building module, for being established and being trained for predicting braking state according to extracted multiclass feature information
Hidden Markov model;
Input module, for by the real-time vehicle ambient enviroment of load-carrying vehicle to be predicted and road environment data and in real time from
The input of vehicle vehicle-state and driver behavior data as the hidden Markov model;
Prediction module, for determining the braking state of the load-carrying vehicle to be predicted according to the hidden Markov model;
Warning information generation module, for when failure state, being given birth to subject to the braking state of the load-carrying vehicle to be predicted
At warning information;
Planning module, for planning secure path when the braking state of the load-carrying vehicle to be predicted is failure state.
According to another aspect of the invention, a kind of electronic equipment is also provided, the electronic equipment includes: processor;Storage
Medium, is stored thereon with computer program, and the computer program executes step as described above when being run by the processor.
According to another aspect of the invention, a kind of storage medium is also provided, computer journey is stored on the storage medium
Sequence, the computer program execute step as described above when being run by processor.
Compared with prior art, present invention has an advantage that
The present invention is by the vehicle-periphery and road environment data of each load-carrying vehicle and from vehicle vehicle-state and drives
Action data is sailed, to establish and train the hidden Markov model for predicting braking state, and passes through bogie to be predicted
It real-time vehicle ambient enviroment and road environment data and from vehicle vehicle-state and driver behavior data and is trained hidden in real time
Markov model determines the braking state of vehicle, when recognizing heavy-duty truck brake and being in fast failure (quasi- failure state),
Vehicle issues alarm prompt, reminds driver that need to stop in time in order to avoid brake failure.It has been lost when recognizing heavy-duty truck brake
When clever (failure state), automatic path planning guides driver to enter the safety areas such as emergency lane or Expressway Service.
Detailed description of the invention
Its example embodiment is described in detail by referring to accompanying drawing, above and other feature of the invention and advantage will become
It is more obvious.
Fig. 1 shows the flow chart of the brake failure method for early warning of load-carrying vehicle according to an embodiment of the present invention.
Fig. 2 shows the flow charts of the path planning of load-carrying vehicle according to an embodiment of the present invention.
Fig. 3 shows the schematic diagram that Grid Method according to an embodiment of the present invention establishes coordinate system.
Fig. 4 shows the schematic diagram for generating the direction selection in path in initial population according to an embodiment of the present invention at random.
Fig. 5 shows the schematic diagram that the path according to an embodiment of the present invention in Advanced group species carries out cross processing.
Fig. 6 shows the schematic diagram that the path according to an embodiment of the present invention in Advanced group species carries out variation processing.
Fig. 7 shows the module map of the brake failure prior-warning device of load-carrying vehicle according to an embodiment of the present invention.
Fig. 8 shows the schematic diagram of the brake failure early warning system of the load-carrying vehicle of specific embodiment according to the present invention.
Fig. 9 schematically shows a kind of computer readable storage medium schematic diagram in exemplary embodiment of the present.
Figure 10 schematically shows a kind of electronic equipment schematic diagram in exemplary embodiment of the present.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein;On the contrary, thesing embodiments are provided so that the present invention will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.
In addition, attached drawing is only schematic illustrations of the invention, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are function
Energy entity, not necessarily must be corresponding with physically or logically independent entity.These function can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all steps.For example, the step of having
It can also decompose, and the step of having can merge or part merges, therefore, the sequence actually executed is possible to according to the actual situation
Change.
Fig. 1 shows the flow chart of the brake failure method for early warning of load-carrying vehicle according to an embodiment of the present invention.Bogie
Brake failure method for early warning include the following steps:
Step S110: the vehicle-periphery and road environment data and from vehicle vehicle-state and driving of each load-carrying vehicle are obtained
Sail action data;
Step S120: it is mentioned according to vehicle-periphery and road environment data and from vehicle vehicle-state and driver behavior data
Take multiclass feature information;
Step S130: establishing according to extracted multiclass feature information and trains the hidden Ma Erke for predicting braking state
Husband's model;
Step S140: by the real-time vehicle ambient enviroment of load-carrying vehicle to be predicted and road environment data and in real time from vehicle vehicle
The input of state and driver behavior data as the hidden Markov model;
Step S150: the braking state of the load-carrying vehicle to be predicted is determined according to the hidden Markov model;
Step S160: if failure state subject to the braking state of the load-carrying vehicle to be predicted, generates warning information;
Step S170: if the braking state of the load-carrying vehicle to be predicted is failure state, secure path is planned.
In the brake failure method for early warning of load-carrying vehicle provided by the invention, pass through the vehicle periphery of each load-carrying vehicle
Environment and road environment data and from vehicle vehicle-state and driver behavior data, to establish and train for predicting braking state
Hidden Markov model, and by load-carrying vehicle real-time vehicle ambient enviroment to be predicted and road environment data and in real time from vehicle
Vehicle-state and driver behavior data and the hidden Markov model trained determine the braking state of vehicle, when recognizing load-carrying
When braking automobile is in fast failure (quasi- failure state), vehicle issues alarm prompt, reminds driver that need to stop in time in order to avoid stopping
Vehicle failure.When recognizing heavy-duty truck brake failure (failure state), automatic path planning guides driver to enter and keeps away
The safety areas such as dangerous lane or Expressway Service.
Specifically, although personal driving habit and vehicle-state have otherness, from system of vehicle transmission mechanism and vehicle
The analysis of operation situation as a result, it has been found that, vehicle is by by the front in the state of a certain particular moment and the driving behavior of driver
Driver's operational motion is influenced in certain time length.If vehicle is before realizing turning, driver can implement to slow down, downshift, beat
Open the relevant operations such as turn signal.Observation information amount for prediction increases, the degree of association with driving behavior and vehicle-state
It increases with it.
In the present embodiment, the vehicle-periphery and road environment data and from vehicle vehicle-state and driver behavior number
According to may include: vehicle, history maintenance data, car speed, maximum speed, vehicle acceleration, direction, steering wheel grip, length
The 11 category feature information such as time brake, leading vehicle distance, lane line, road nature is as observation information.And all kinds of characteristic informations can
Polymerization classification is carried out with the abbreviation by such as table one.
The abbreviation of 1 vehicle of table acquisition data field
Wherein, vehicle data may include vehicle, history maintenance data, car speed, maximum speed, vehicle acceleration
Degree and direction.Vehicle can be classified as min-truck (WK), light truck (QK), Medium Truck (MK), heavy truck by table one
(ZK), superduty truck (CK).History maintenance data can be classified as maintenance lower than 5 times (DR), maintenance 5~10 times by table one
(MR), maintenance 10 times or more (GR).Car speed can be classified as low speed (L), middling speed (M) and high speed (L) by table one.Most high speed
Degree can be classified as maximum speed 80km/h or less (EV), maximum speed 80-100km/h (HV), maximum speed 100- by table one
120km/h (TV), maximum speed 120km/h or more (GV).Vehicle acceleration can be classified as by table one accelerate (A), slow down (B),
At the uniform velocity (C), wherein accelerate (A) that anxious acceleration (AA) and normal acceleration (NA) can be classified as by table one, deceleration (B) can be divided by table one
Class is anxious deceleration (AB) and normal deceleration (NB).Direction can be classified as straight trip (S) by table one and be turned (CN), wherein turning
(CN) radical turning (AC) and normal excessively curved (NC) can be classified as by table one.
Driver behavior data may include steering wheel grip and brake for a long time.Steering wheel grip can be classified as by table one
Steering wheel grip 20kg or less (TK), steering wheel grip 20-40kg (FK), steering wheel grip 40-60kg (SK), steering wheel grip
60kg or more (GK).Brake for a long time can be classified as brake lasting 10s or less (CB), the lasting 10-30s of brake by table one
(DB), it brakes lasting 30-60s (EB), brake lasting 60-120s (FB), braking continues 120s or more (GB).
Vehicle environmental data may include leading vehicle distance and lane line.Leading vehicle distance can be classified as no front truck by table one
(N) and with speed (F), wherein with speeding, (F) can be classified as normally with speeding (NF) and excessively closely with speed (AF) by table one.Lane line can
(LK) and lane-change (LC) are kept to be classified as lane by table one, wherein lane-change (LC) can be classified as anxious lane-change (AL) by table one
With normal lane-change (NL).
Road environment data may include road nature.Road nature can be classified as straight way (ZD), bend by table one
(WD), descending (XP), upward slope (SP).
Tree structure can be formed by above-mentioned classification accordingly, for 11 category feature information, in the leaf section of tree structure
Each driving mode and environmental information of point all have single feature and motivation, constitute basic driving mode and environment letter
Breath.Driver's driver behavior at any time and environment can regard answering for above-mentioned basic driving mode and environmental information as
It closes.In driving procedure, following driving condition and vehicle-state are unobservable, but can pass through current driving behavior and ring
Border shows a series of external visible observation sequences with time change, and hidden Markov model is one kind by external sight
Examine the good method that sequence recognizes inherent invisible mode.When the basic driving mode and environmental information for identifying any time, just
It can use the braking state that hidden Markov model identifies any a period of time.
Specifically, step S110 obtains the vehicle-periphery and road environment data and from vehicle vehicle of each load-carrying vehicle
When state and driver behavior data, the braking state at the vehicle current time is also obtained.It is special that multiclass is extracted in step S120 as a result,
When reference ceases, multiple sample S can be formedn={ v1,v2,v3,v4,v5,v6,v7,v8,v9,v10,v11, wherein n=1,2,3.Sn
Indicate brake failure state, the quasi- failure state of brake and brake normal condition.v1,v2,v3,v4,v5,v6,v7,v8,v9,v10,v11
Respectively indicate vehicle, history maintenance data, car speed, maximum speed, vehicle acceleration, direction, steering wheel grip, long-time
Brake, leading vehicle distance, lane line, road nature specific features information (such as leaf node of above-mentioned tree structure).In step
Data cleansing can be carried out to the data and passing magnanimity driving data got in rapid S110 and step S120, reject from
The pretreatment such as group's point and abnormal point.
In a specific embodiment, described in above-mentioned steps S120 according to vehicle-periphery and road environment data and from
It includes: to carry out at centralization dimension to all kinds of characteristic informations that vehicle vehicle-state and driver behavior data, which extract multiclass feature information,
Reason.
Specifically, the processing of centralization dimension can be carried out to all kinds of characteristic informations as follows:
Wherein, xijCentered on change jth category feature information v before dimension is handledjIn ith feature information, x 'ijCentered on change
Jth category feature information v after dimension processingjIn ith feature information,And vjRespectively jth category feature information vjIn each feature
The sample mean of information and sample index are poor.After the processing of centralization dimension, the mean value of all kinds of characteristic informations is 0, and side
Difference is 1.
Specifically, hidden Markov model include two groups of state sets and three groups of Making by Probability Sets, be expressed as λ=N, M,
A ', B, π }, it is abbreviated λ={ A ', B, π }.Wherein, N is the quantity (S={ s of hidden state in hidden state set1,s2,…,sN, S is
Hidden state set, s1,s2,…,sNFor hidden state).In the present embodiment, hidden state includes brake failure state, the quasi- failure of brake
State, brake normal condition, therefore, N 3.M is the observable state number of observable state set, in the present embodiment, M
The as class number of characteristic information, that is, 11 (V={ v1,v2,…,vM, V is observable state set, v1,v2,…,vMIt is each
Category feature information).It is denoted as q1 in the model state of t moment, the status switch of model experience is denoted as q={ q1, q2..., qt,
In, q1, q2..., qtAny state in respectively hidden state set.A ' is that the hidden state of the hidden Markov model shifts
Matrix, the hidden state transfer item that the hidden state-transition matrix m row n-th arranges are that m-th of hidden state is transferred to n-th of hidden state
Probability, wherein m, n be more than or equal to 1 be less than or equal to N integer.B is the observation probability square of the hidden Markov model
There is k-th of spy under first of hidden state in the observation probability item expression of battle array, the row k l column of the observation probability matrix
The probability of reference breath, k are the integer for being less than or equal to M more than or equal to 1, and l is integer of the integer more than or equal to 1 less than or equal to N.π
For the initial probability distribution matrix of the hidden state of the hidden Markov model, the line number of the initial probability distribution matrix is 1,
The probability item of the 1st row l column of the initial probability distribution matrix is the initial distribution probability of first of hidden state.L is big
It is less than or equal to the integer of N in the integer equal to 1.
In one embodiment of the invention, it can establish as follows and train the hidden horse for predicting braking state
Er Kefu model:
Firstly, generating corresponding judgment matrix A=[a to the hidden state of each hidden Markov modelij]M×M, institute
State the judgement item α of the i-th row jth column of judgment matrixijIndicate the importance between the i-th category feature information and jth category feature information
Fiducial value, i, j are the integer more than or equal to 1.The step is equivalent to using the analytic hierarchy process (AHP) in multiindicator analysis to each
Observation information carries out prediction weight analysis, matches two-by-two to observation information and carries out important ratio pair, will by multilevel iudge quantification
Qualitative analysis is converted into quantitative analysis, wherein αij=f (vi,vj) it is contrast function, contrast function value is as shown in table 2.
Table 2 is classified proportion quotiety reference table
By taking hidden state is brake failure state as an example, judgment matrix A is as follows:
Judgment matrix is used to calculate the weight of observation information (all kinds of characteristic informations) under each hidden state.Judgment matrix A is each
Row element connects multiplied Mi, (i=1,2 ..., M), to MiIt opens M power and obtains αi, by αiNormalizationI.e.
Obtain characteristic information viWeight coefficient wi.By taking hidden state is brake failure state as an example, according to solution procedure, to contrast judgement square
Battle array solves characteristic value and feature vector, obtain each observation information forecast and decision coefficient vector W=(0.029,0.037,
0.090,0.195,0.195,0.051,0.051,0.219,0.039,0.025,0.069).Similar method can determine remaining
The decision weights coefficient vector of two states.
Then, the observation probability matrix B=[b for obtaining the hidden Markov model is calculatedkl], the observation probability
The observation probability item b of the row k l column of matrixkl=p (Os=vk/qt=sl), there is kth under first of hidden state in expression
A characteristic information (OsIndicate observation information) probability, k be more than or equal to 1 be less than or equal to M integer, l be it is whole more than or equal to 1
Number is less than or equal to the integer of N.
Then, it is determined that initial probability distribution matrix π=[π of the hidden state of the hidden Markov modeli], it is described initial
The line number of probability distribution matrix π is 1, the probability item π of the 1st row l column of the initial probability distribution matrixi=p (qt=
sl) be first of hidden state initial distribution probability.∑ π need to be meti=1, in the present embodiment, π=[0.15,0.25,0.6].
The braking state training hidden horse of vehicle when then, according to extracted characteristic information, extraction characteristic information
Er Kefu model obtains hidden state-transition matrix A '=[α ' of the hidden Markov modelmn], the hidden state-transition matrix
The hidden state transfer item α ' that m row n-th arrangesmn=p (qt+1=sn/qt=sm) it is m-th of hidden state smIt is transferred to n-th of hidden state
snProbability.α‘mn> 0, andIt in the present embodiment, can be described hidden using Forward-backward algorithm training
Markov model.Sample format is as shown in table 3.
3 hidden Markov model pattern drill sample format of table
In table 3, input observation information sequence are as follows: vehicle, history maintenance data, car speed, maximum speed, vehicle add
Speed, direction, steering wheel grip, brake, leading vehicle distance, lane line, road nature for a long time.Numerical value is suitable in output probability vector
Sequence are as follows: brake failure state, the quasi- failure state of brake, brake normal condition.In the probability value maximum value of corresponding position then indicates
It is exactly the braking state that this position represents in state.In the present embodiment, the state-transition matrix A ' of acquisition is
Thus, it is possible to determine braking state by real-time observation information and housebroken hidden Markov model.
Further, planning secure path described in above-mentioned steps S170 comprises determining that safe destination;It is empty using solution
Between genetic algorithm planned automatically to the secure path of the destination.
It is described to be planned automatically into the secure path of the destination using solution space genetic algorithm by such as the step of Fig. 2
Iteration updates initial population, until meeting predetermined termination condition:
Step S210: establishing map coordinates system using Grid Method, and generates the path of predetermined quantity at random, by the predetermined number
The path of amount forms initial population.
Specifically, map two-dimensional surface is divided into the grid of Y*Y using Grid Method by step S210, it is original with the lower left corner
Point establishes cartesian coordinate system, as shown in Figure 3.The starting point of truck and destination are indicated with S and G respectively, therefore path
It is represented by { S, 11,23,33,45,55,65,76,77,88, G }.During generating path at random, each path is determined
After one grid, the next step route of the grid can choose a free grid as next from 8 adjacent cells of surrounding
A grid, but the path quality generated in this way is not high, and Yi Zengjia evolutionary generation influences convergence rate.Therefore from its adjacent 8 grid
It is middle to choose 5 alternately grids, the i.e. grid in { 1,2,3,4,8 } this 5 directions, as shown in Figure 4.Then at random in space
The path (such as 50,100,200, the present invention is not limited thereto) of predetermined quantity is generated, is formed initial population P (x).
Step S220: Advanced group species are formed from selected part path in the initial population using roulette method.
Specifically, step S220 can for example choose the number such as 1/2,1/3,1/4 of number of paths in initial population P (x)
The path of amount.Further, in the present embodiment, retain the highest path of fitness function value in the Advanced group species as essence
English path, the elite path are handled without the intersection of following step S230, variation.The fitness function value is the path length
Inverse.
Step S230: the path in the Advanced group species is intersected, variation processing.
Specifically, predetermined termination condition for example may is that 1) algorithm finds receptible excellent individual (optimal solution);2)
Algorithm has been evolved prior scheduled maximum algebra;3) in prior scheduled algebra fitst water individual fitness function without
It improves;4) ratio that fitst water individual accounts for group has reached defined ratio in advance.Termination condition can be above-mentioned one or
It is a plurality of.In a particular embodiment, in a specific embodiment, termination condition can be algorithm iteration number and reach 500 times;Or
In predetermined the number of iterations 500 times, the fitness function difference for obtaining optimal solution twice is less than a certain threshold value (such as 10-4) when terminate
Algorithm.
Specifically, for Advanced group species E (x), it is random to select single point crossing method.It chooses and is intersected at same sequence number point
(starting point S and terminal G except), to guarantee the continuity in path, as shown in Figure 5 (the 3rd serial number point in two paths is identical,
Then intersect at the 4th serial number point).If serial number point more than one having the same, optional one is intersected, if without phase
When with serial number point, two serial number points are randomly selected from two individuals and are intersected.If being discontinuous caused by after intersecting
Path, using any grid of upper half segment endpoint and lower semisection as starting point and target point, using generation initial population
Method is repaired into a continuous path.Variation mode is some serial number point of random selection individual, changes it at random
Unit numbers, (changing into 45 for the 44 of the 6th serial number point in path) as shown in Figure 6.
Step S240: will be intersected, the Advanced group species for the processing that makes a variation are by corresponding fitness function value update initial population.
Above is only schematically to describe specific implementation of the invention, and above steps can be individually performed or group
It closes and executes, under the premise of without prejudice to present inventive concept, all within protection scope of the present invention.
Fig. 7 shows the schematic diagram of the brake failure prior-warning device of load-carrying vehicle according to an embodiment of the present invention.Fig. 7 is shown
The module map of the brake failure prior-warning device of load-carrying vehicle according to an embodiment of the present invention.The brake failure early warning of load-carrying vehicle
Device 300 includes the first acquisition module 310, extraction module 320, model building module 330, input module 340, prediction module
350, warning information generation module 360.
First acquisition module 310 is used to obtain the vehicle-periphery and road environment data and from vehicle vehicle of each load-carrying vehicle
State and driver behavior data;
Extraction module 320 is used for according to vehicle-periphery and road environment data and from vehicle vehicle-state and driver behavior
Data extract multiclass feature information;
Model building module 330 according to extracted multiclass feature information for establishing and training for predicting braking state
Hidden Markov model;
Input module 340 is for by the real-time vehicle ambient enviroment of load-carrying vehicle to be predicted and road environment data and in real time
Input from vehicle vehicle-state and driver behavior data as the hidden Markov model;
Prediction module 350 is used to determine the brake shape of the load-carrying vehicle to be predicted according to the hidden Markov model
State;
Warning information generation module 360 is used for subject to the braking state of the load-carrying vehicle to be predicted when failure state,
Generate warning information;
Planning module 370 is used to plan safe road when the braking state of the load-carrying vehicle to be predicted is failure state
Diameter.
In the brake failure prior-warning device of the load-carrying vehicle of exemplary embodiments of the present invention, pass through each bogie
Vehicle-periphery and road environment data and from vehicle vehicle-state and driver behavior data, be used for establish and train
It predicts the hidden Markov model of braking state, and passes through load-carrying vehicle real-time vehicle ambient enviroment to be predicted and road environment number
According to and in real time determine the braking state of vehicle from vehicle vehicle-state and driver behavior data and the hidden Markov model trained,
When recognizing heavy-duty truck brake and being in fast failure (quasi- failure state), vehicle issues alarm prompt, remind driver need and
When parking in order to avoid brake failure.When recognizing heavy-duty truck brake failure (failure state), automatic path planning is guided
Driver enters the safety areas such as emergency lane or Expressway Service.
Fig. 7 is only the brake failure prior-warning device 300 for showing schematically load-carrying vehicle provided by the invention, is not being disobeyed
Under the premise of carrying on the back present inventive concept, the fractionation of module, increases all within protection scope of the present invention merging.
Fig. 8 shows the schematic diagram of the brake failure early warning system of the load-carrying vehicle of specific embodiment according to the present invention.It carries
The brake failure early warning system of loaded vehicle includes information acquisition module 405, CAN bus 407, car-mounted terminal 409, cloud platform
415 and control module 423.
Information acquisition module 405 includes surrounding vehicles and environment sensing unit 401 and vehicle-state and driver behavior perception
Unit 403.Surrounding vehicles and environment sensing unit 401 include camera unit, radar sensor, laser sensor, positioning system,
Ultrasonic sensor, distance measuring sensor, surrounding vehicles and environmental data processing unit and data outputting unit.It vehicle-state and drives
Sail movement sension unit 403 include steering wheel grip detection unit, vehicle essential information reading unit, accelerator pedal sensor,
Brake pedal sensor, velocity sensor, pressure sensor, braking force sensor, angular acceleration transducer, angular transducer,
Light-sensing signal sensor, vehicle-state and driver behavior data processing unit and data outputting unit.Various kinds of sensors by with
CAN bus 407 connects and the information of acquisition is sent to the car-mounted terminal 409 by CAN bus 047.
In surrounding vehicles and environment sensing unit 401, camera unit includes the panoramic high-definition camera shooting for being set to roof
Machine and it is set to wide-angle high-definition camera before interior driver's cabin.Radar sensor, laser sensor, ultrasonic sensor, ranging
Sensor for perceiving and obtain surrounding vehicles environment and road environment, including from vehicle and front truck relative distance and vehicle be in
Lane line state.Positioning system is used to acquire the latitude and longitude information of cargo vehicle, the road nature that acquisition vehicle is in.Around
Vehicle and environmental data processing unit are for handling surrounding vehicles environment and road environment data;Surrounding vehicles and environmental data are defeated
Unit is used to export surrounding vehicles environment and road after surrounding vehicles and environmental data processing unit processes to car-mounted terminal out
Road environmental data.
In vehicle-state and driver behavior sension unit 403: steering wheel grip detection unit is for detecting driver's palm
To the pressure of holding with a firm grip of steering wheel.The essential information that vehicle essential information reading unit is used to read vehicle includes vehicle, history dimension
Protect data etc..Brake pedal sensor, pressure sensor, braking force sensor are for acquiring the work that driver tramples braking conditions
Make data.Velocity sensor, angular acceleration transducer are used to acquire the travel speed of truck, maximum speed, accelerate from vehicle
Degree, from vehicle deceleration etc..Angular transducer is for acquiring the data such as steering wheel angle;Vehicle-state and driver behavior data processing
Unit is for handling vehicle from car state and driver behavior data;Vehicle-state and driver behavior data outputting unit are used for vehicle
Mounted terminal output is through vehicle-state and driver behavior data processing unit treated vehicle from car state and driver behavior data.
Car-mounted terminal 409 includes microcomputer and vehicular map.Microcomputer is connect with vehicular map, and microcomputer includes
Image identification unit and data processing unit, image processing unit camera unit acquired image information for identification, including
Road markings information outside vehicle, road congestion information etc..Data processing unit is used for finishing analysis vehicle-state and driver behavior
Sension unit information collected.Vehicular map is used to show the planning route of vehicle.
Cloud platform 415 includes data storage 417, intelligent algorithm recognition unit 419, path planning unit 421.Data
Memory 417 is connect with microcomputer, and the data of microcomputer discriminance analysis are stored in data storage.Intelligent algorithm identification
Unit 419 is modeled and is analyzed according to the data in data storage, and obtained information is sent by cloud platform 415
To control module.Path planning unit 421 for planning the safety traffic route of truck automatically.
Control module 423 includes Alarm control unit 425 and signaling control unit 427.When intelligent algorithm recognition unit 419
When determining vehicle in the quasi- failure state of brake, the capable of emitting alarm of Alarm control unit 425.Signaling control unit 427 is used for
Control the signal of vehicle domestic demand transmission and control.
It is above only to schematically show a specific implementation of the invention, the present invention is not to be limited.
In an exemplary embodiment of the present invention, a kind of computer readable storage medium is additionally provided, meter is stored thereon with
Calculation machine program, the program may be implemented electronic prescription described in any one above-mentioned embodiment and circulate when being executed by such as processor
The step of processing method.In some possible embodiments, various aspects of the invention are also implemented as a kind of program production
The form of product comprising program code, when described program product is run on the terminal device, said program code is for making institute
State terminal device execute described in the brake failure method for early warning part of the above-mentioned load-carrying vehicle of this specification it is each according to the present invention
The step of kind illustrative embodiments.
Refering to what is shown in Fig. 9, describing the program product for realizing the above method of embodiment according to the present invention
700, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The computer readable storage medium may include in a base band or the data as the propagation of carrier wave a part are believed
Number, wherein carrying readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetism
Signal, optical signal or above-mentioned any appropriate combination.Readable storage medium storing program for executing can also be any other than readable storage medium storing program for executing
Readable medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or
Person's program in connection.The program code for including on readable storage medium storing program for executing can transmit with any suitable medium, packet
Include but be not limited to wireless, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in tenant
It calculates and executes in equipment, partly executed in tenant's equipment, being executed as an independent software package, partially in tenant's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to tenant and calculates equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In an exemplary embodiment of the present invention, a kind of electronic equipment is also provided, which may include processor,
And the memory of the executable instruction for storing the processor.Wherein, the processor is configured to via described in execution
Executable instruction is come the step of executing the circulation processing method of electronic prescription described in any one above-mentioned embodiment.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 500 of this embodiment according to the present invention is described referring to Figure 10.The electricity that Figure 10 is shown
Sub- equipment 500 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in Figure 10, electronic equipment 500 is showed in the form of universal computing device.The component of electronic equipment 500 can be with
Including but not limited to: at least one processing unit 510, at least one storage unit 520, the different system components of connection (including are deposited
Storage unit 520 and processing unit 510) bus 530, display unit 540 etc..
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 510
Row, so that the processing unit 510 executes described in the brake failure method for early warning part of the above-mentioned load-carrying vehicle of this specification
The step of various illustrative embodiments according to the present invention.For example, the processing unit 510 can execute as shown in the figures 1 and 2
Step.
The storage unit 520 may include the readable medium of volatile memory cell form, such as random access memory
Unit (RAM) 5201 and/or cache memory unit 5202 can further include read-only memory unit (ROM) 5203.
The storage unit 520 can also include program/practical work with one group of (at least one) program module 5205
Tool 5204, such program module 5205 includes but is not limited to: operating system, one or more application program, other programs
It may include the realization of network environment in module and program data, each of these examples or certain combination.
Bus 530 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 500 can also be with one or more external equipments 600 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, the equipment that also tenant can be enabled interact with the electronic equipment 500 with one or more communicates, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 500 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 550.Also, electronic equipment 500 can be with
By network adapter 560 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.Network adapter 560 can be communicated by bus 530 with other modules of electronic equipment 500.It should
Understand, although not shown in the drawings, other hardware and/or software module can be used in conjunction with electronic equipment 500, including but unlimited
In: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and number
According to backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the present invention
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server or network equipment etc.) executes the above-mentioned electronics of embodiment according to the present invention
Prescription circulation processing method.
Compared with prior art, present invention has an advantage that
The present invention is by the vehicle-periphery and road environment data of each load-carrying vehicle and from vehicle vehicle-state and drives
Action data is sailed, to establish and train the hidden Markov model for predicting braking state, and passes through bogie to be predicted
It real-time vehicle ambient enviroment and road environment data and from vehicle vehicle-state and driver behavior data and is trained hidden in real time
Markov model determines the braking state of vehicle, when recognizing heavy-duty truck brake and being in fast failure (quasi- failure state),
Vehicle issues alarm prompt, reminds driver that need to stop in time in order to avoid brake failure.It has been lost when recognizing heavy-duty truck brake
When clever (failure state), automatic path planning guides driver to enter the safety areas such as emergency lane or Expressway Service.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to of the invention its
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the invention, these modifications, purposes or
Person's adaptive change follows general principle of the invention and including the undocumented common knowledge in the art of the present invention
Or conventional techniques.The description and examples are only to be considered as illustrative, and true scope and spirit of the invention are by appended
Claim is pointed out.
Claims (11)
1. a kind of brake failure method for early warning of load-carrying vehicle characterized by comprising
Obtain the vehicle-periphery and road environment data and from vehicle vehicle-state and driver behavior data of each load-carrying vehicle;
Multiclass feature letter is extracted according to vehicle-periphery and road environment data and from vehicle vehicle-state and driver behavior data
Breath;
It is established according to extracted multiclass feature information and trains the hidden Markov model for predicting braking state;
By the real-time vehicle ambient enviroment of load-carrying vehicle to be predicted and road environment data and in real time from vehicle vehicle-state and driving
Input of the action data as the hidden Markov model;
The braking state of the load-carrying vehicle to be predicted is determined according to the hidden Markov model;
If failure state subject to the braking state of the load-carrying vehicle to be predicted, generates warning information;
If the braking state of the load-carrying vehicle to be predicted is failure state, secure path is planned.
2. the brake failure method for early warning of load-carrying vehicle as described in claim 1, which is characterized in that described according to vehicle periphery
Environment and road environment data and multiclass feature information is extracted from vehicle vehicle-state and driver behavior data include:
The processing of centralization dimension is carried out to all kinds of characteristic informations.
3. the brake failure method for early warning of load-carrying vehicle as described in claim 1, which is characterized in that described according to extracted
Multiclass feature information is established and trains the hidden Markov model for predicting braking state to include:
To the hidden state of each hidden Markov model, corresponding judgment matrix, the i-th row of the judgment matrix are generated
J column judge that item indicates that the importance fiducial value between the i-th category feature information and jth category feature information, i, j are more than or equal to 1
Integer;
Calculate the observation probability matrix for obtaining the hidden Markov model, the row k l column of the observation probability matrix
Observation probability item indicate occur the probability of k-th of characteristic information under first of hidden state, k, l are whole more than or equal to 1
Number;
Determine the initial probability distribution matrix of the hidden state of the hidden Markov model, the row of the initial probability distribution matrix
Number is 1, and the probability item of the 1st row l column of the initial probability distribution matrix is that the initial distribution of first of hidden state is general
Rate;
The braking state training hidden Markov mould of vehicle when according to extracted characteristic information, extraction characteristic information
Type obtains the hidden state-transition matrix of the hidden Markov model, the hidden shape that the hidden state-transition matrix m row n-th arranges
State transfer item is that m-th of hidden state is transferred to n-th of hidden shape probability of state,
Wherein, the hidden state of the hidden Markov model includes failure state, quasi- failure state and normal condition.
4. the brake failure method for early warning of load-carrying vehicle as claimed in claim 3, which is characterized in that using preceding to-calculation backward
The method training hidden Markov model.
5. the brake failure method for early warning of load-carrying vehicle as described in claim 1, which is characterized in that the planning secure path
Include:
Determine the destination of safety;
It is planned automatically using solution space genetic algorithm to the secure path of the destination.
6. the brake failure method for early warning of load-carrying vehicle as claimed in claim 5, which is characterized in that described to be lost using solution space
Propagation algorithm plans that the secure path to the destination includes: automatically
Iteration updates initial population as follows, until meeting predetermined termination condition:
Map coordinates system is established using Grid Method, and generates the path of predetermined quantity at random, the path of the predetermined quantity is formed
Initial population;
Advanced group species are formed from selected part path in the initial population using roulette method;
Path in the Advanced group species is intersected, variation processing;
It will be intersected, the Advanced group species for the processing that makes a variation are by corresponding fitness function value update initial population.
7. the brake failure method for early warning of load-carrying vehicle as claimed in claim 6, which is characterized in that described to use roulette method
From after composition Advanced group species in selected part path in the initial population, the path in the Advanced group species is handed over
Before fork, variation processing further include:
Retain in the Advanced group species the highest path of fitness function value as elite path, the elite path without intersect,
Variation processing.
8. the brake failure method for early warning of load-carrying vehicle as claimed in claims 6 or 7, which is characterized in that the fitness letter
Numerical value is the inverse of the path length.
9. a kind of brake failure prior-warning device of load-carrying vehicle characterized by comprising
First obtains module, for obtaining the vehicle-periphery and road environment data and from vehicle vehicle-state of each load-carrying vehicle
With driver behavior data;
Extraction module, for being mentioned according to vehicle-periphery and road environment data and from vehicle vehicle-state and driver behavior data
Take multiclass feature information;
Model building module, for being established according to extracted multiclass feature information and training the hidden horse for predicting braking state
Er Kefu model;
Input module, for by the real-time vehicle ambient enviroment of load-carrying vehicle to be predicted and road environment data and in real time from vehicle vehicle
The input of state and driver behavior data as the hidden Markov model;
Prediction module, for determining the braking state of the load-carrying vehicle to be predicted according to the hidden Markov model;
Warning information generation module, for when failure state, generating and accusing subject to the braking state of the load-carrying vehicle to be predicted
Alert information;
Planning module, for planning secure path when the braking state of the load-carrying vehicle to be predicted is failure state.
10. a kind of electronic equipment, which is characterized in that the electronic equipment includes:
Processor;
Memory is stored thereon with computer program, is executed when the computer program is run by the processor as right is wanted
Seek 1 to 8 described in any item steps.
11. a kind of storage medium, which is characterized in that be stored with computer program, the computer program on the storage medium
Step as claimed in any one of claims 1 to 8 is executed when being run by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811598302.8A CN109685273A (en) | 2018-12-25 | 2018-12-25 | Brake failure method for early warning, device, electronic equipment, the storage medium of vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811598302.8A CN109685273A (en) | 2018-12-25 | 2018-12-25 | Brake failure method for early warning, device, electronic equipment, the storage medium of vehicle |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109685273A true CN109685273A (en) | 2019-04-26 |
Family
ID=66189624
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811598302.8A Pending CN109685273A (en) | 2018-12-25 | 2018-12-25 | Brake failure method for early warning, device, electronic equipment, the storage medium of vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109685273A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110288096A (en) * | 2019-06-28 | 2019-09-27 | 江苏满运软件科技有限公司 | Prediction model training and prediction technique, device, electronic equipment, storage medium |
CN111767933A (en) * | 2019-05-17 | 2020-10-13 | 北京京东尚科信息技术有限公司 | Method and device for identifying vehicle driving state |
CN112555084A (en) * | 2020-12-04 | 2021-03-26 | 湖南五凌电力科技有限公司 | Real-time state early warning method and device, electronic equipment and storage medium |
CN113888775A (en) * | 2020-06-19 | 2022-01-04 | 比亚迪股份有限公司 | Vehicle early warning method, server, storage medium, vehicle early warning system and vehicle |
CN114228719A (en) * | 2022-02-11 | 2022-03-25 | 同济大学 | Vehicle auxiliary braking method, electronic device and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105151044A (en) * | 2015-08-24 | 2015-12-16 | 奇瑞汽车股份有限公司 | Method and device for aided driving of vehicle |
US20170074964A1 (en) * | 2015-09-16 | 2017-03-16 | Here Global B.V. | Method And System Of Location Estimation And Navigation Of Autonomous Vehicles |
CN107958269A (en) * | 2017-11-28 | 2018-04-24 | 江苏大学 | A kind of driving risk factor Forecasting Methodology based on hidden Markov model |
CN108595844A (en) * | 2018-04-26 | 2018-09-28 | 成都博士信智能科技发展有限公司 | Automatic Pilot control method and device |
-
2018
- 2018-12-25 CN CN201811598302.8A patent/CN109685273A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105151044A (en) * | 2015-08-24 | 2015-12-16 | 奇瑞汽车股份有限公司 | Method and device for aided driving of vehicle |
US20170074964A1 (en) * | 2015-09-16 | 2017-03-16 | Here Global B.V. | Method And System Of Location Estimation And Navigation Of Autonomous Vehicles |
CN107958269A (en) * | 2017-11-28 | 2018-04-24 | 江苏大学 | A kind of driving risk factor Forecasting Methodology based on hidden Markov model |
CN108595844A (en) * | 2018-04-26 | 2018-09-28 | 成都博士信智能科技发展有限公司 | Automatic Pilot control method and device |
Non-Patent Citations (4)
Title |
---|
刘传领: "基于势场法和遗传算法的机器人路径规划技术研究", 《中国优秀博士学位论文全文数据库 信息科技辑》 * |
王家臣 等: "《煤矿岩层控制理论与技术进展 33届国际采矿岩层控制会议(中国)论文集》", 31 October 2014, 冶金工业出版社 * |
王曼丽: "《我国地质资料信息服务产业化模式研究》", 31 August 2016, 北京地质出版社 * |
邹权 等: "《系统生物学的网络分析方法》", 30 April 2015, 西安电子科技大学出版社 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111767933A (en) * | 2019-05-17 | 2020-10-13 | 北京京东尚科信息技术有限公司 | Method and device for identifying vehicle driving state |
CN110288096A (en) * | 2019-06-28 | 2019-09-27 | 江苏满运软件科技有限公司 | Prediction model training and prediction technique, device, electronic equipment, storage medium |
CN110288096B (en) * | 2019-06-28 | 2021-06-08 | 满帮信息咨询有限公司 | Prediction model training method, prediction model training device, prediction model prediction method, prediction model prediction device, electronic equipment and storage medium |
CN113888775A (en) * | 2020-06-19 | 2022-01-04 | 比亚迪股份有限公司 | Vehicle early warning method, server, storage medium, vehicle early warning system and vehicle |
CN112555084A (en) * | 2020-12-04 | 2021-03-26 | 湖南五凌电力科技有限公司 | Real-time state early warning method and device, electronic equipment and storage medium |
CN114228719A (en) * | 2022-02-11 | 2022-03-25 | 同济大学 | Vehicle auxiliary braking method, electronic device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109685273A (en) | Brake failure method for early warning, device, electronic equipment, the storage medium of vehicle | |
US11815892B2 (en) | Agent prioritization for autonomous vehicles | |
US20190155291A1 (en) | Methods and systems for automated driving system simulation, validation, and implementation | |
CN110362077A (en) | Automatic driving vehicle urgent danger prevention decision system, method and medium | |
CN110488802B (en) | Decision-making method for dynamic behaviors of automatic driving vehicle in internet environment | |
US10372136B2 (en) | Local trajectory planning method and apparatus for smart vehicles | |
CN106740864B (en) | A kind of driving behavior is intended to judgement and prediction technique | |
CN103158705B (en) | Method and system for controlling a host vehicle | |
US11673550B2 (en) | Agent prioritization for autonomous vehicles | |
CN108447308A (en) | A kind of intersection vehicles risk of collision prediction technique and system based on bus or train route collaboration | |
US8947218B2 (en) | Driving support device | |
CN106133805B (en) | Driving assistance method and system for collision elimination | |
CN109242251A (en) | Vehicular behavior safety detecting method, device, equipment and storage medium | |
CN110794851B (en) | Vehicle remote control safety protection method and device and unmanned vehicle | |
US11687077B2 (en) | Ranking agents near autonomous vehicles by mutual importance | |
CN109727469A (en) | Automatic driving vehicle COMPREHENSIVE RISK DEGREE appraisal procedure under a kind of multilane | |
CN108806018A (en) | A kind of data processing method, data processing equipment and intelligent automobile | |
CN110379203A (en) | A kind of driving steering anti-collision warning method | |
Yoon et al. | Predictive cruise control using radial basis function network-based vehicle motion prediction and chance constrained model predictive control | |
CN106291506A (en) | Vehicle target recognition methods based on single line cloud data machine learning and device | |
CN109515433A (en) | Vehicle control system | |
CN110068302A (en) | A kind of vehicle odometry method based on deep neural network | |
CN105151044B (en) | Vehicle assistant drive method and device | |
CN116872921A (en) | Method and system for avoiding risks of vehicle, vehicle and storage medium | |
Rafiei et al. | Pedestrian collision avoidance using deep reinforcement learning |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190426 |