CN107697045A - A kind of pilotless automobile automatic brake controller and method - Google Patents
A kind of pilotless automobile automatic brake controller and method Download PDFInfo
- Publication number
- CN107697045A CN107697045A CN201710802092.9A CN201710802092A CN107697045A CN 107697045 A CN107697045 A CN 107697045A CN 201710802092 A CN201710802092 A CN 201710802092A CN 107697045 A CN107697045 A CN 107697045A
- Authority
- CN
- China
- Prior art keywords
- brake
- self
- barrier
- actuating brake
- information
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60T—VEHICLE BRAKE CONTROL SYSTEMS OR PARTS THEREOF; BRAKE CONTROL SYSTEMS OR PARTS THEREOF, IN GENERAL; ARRANGEMENT OF BRAKING ELEMENTS ON VEHICLES IN GENERAL; PORTABLE DEVICES FOR PREVENTING UNWANTED MOVEMENT OF VEHICLES; VEHICLE MODIFICATIONS TO FACILITATE COOLING OF BRAKES
- B60T7/00—Brake-action initiating means
- B60T7/12—Brake-action initiating means for automatic initiation; for initiation not subject to will of driver or passenger
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60T—VEHICLE BRAKE CONTROL SYSTEMS OR PARTS THEREOF; BRAKE CONTROL SYSTEMS OR PARTS THEREOF, IN GENERAL; ARRANGEMENT OF BRAKING ELEMENTS ON VEHICLES IN GENERAL; PORTABLE DEVICES FOR PREVENTING UNWANTED MOVEMENT OF VEHICLES; VEHICLE MODIFICATIONS TO FACILITATE COOLING OF BRAKES
- B60T7/00—Brake-action initiating means
- B60T7/12—Brake-action initiating means for automatic initiation; for initiation not subject to will of driver or passenger
- B60T7/22—Brake-action initiating means for automatic initiation; for initiation not subject to will of driver or passenger initiated by contact of vehicle, e.g. bumper, with an external object, e.g. another vehicle, or by means of contactless obstacle detectors mounted on the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Regulating Braking Force (AREA)
Abstract
A kind of pilotless automobile automatic brake controller and method, are related to intelligent automobile.Pilotless automobile automatic brake controller includes information acquisition module, data processing module, self-actuating brake control system and self-actuating brake braking execution module.Information acquisition module is loaded in the millimetre-wave radar of front side, in real time to environmental monitoring in front of automatic driving vehicle, by millimetre-wave radar obtain information current vehicle speed and with the distance between barrier information;The current vehicle speed that data processing module is obtained by information acquisition module and the distance with barrier, incoming data processing center, the relative distance between Current vehicle and barrier and relative velocity is calculated, and this information is passed in brake Predictive Control System;Self-actuating brake control system includes inverse dynamics model System Discrimination and self-actuating brake PREDICTIVE CONTROL;Executable instruction is processed into by braking execution module in the brake pressure value of self-actuating brake control system output, each brake-cylinder pressure is controlled.
Description
Technical field
The present invention relates to intelligent automobile, particularly with regard to a kind of pilotless automobile automatic brake controller and side
Method.
Background technology
Vehicle safety is the important indicator of unmanned technology, and unmanned self-actuating brake technology is active safety skill again
One of most important technology of art link.Peripheral information is generally detected by sensing technology in unmanned autobrake system,
And judge the current relative distance of front truck and relative speed using processing module, the speed and acceleration of Current vehicle are controlled accordingly,
The generation of collision free.Therefore it is even more important running into emergency circumstances self-actuating brake.
The autobrake system of automatic driving vehicle needs accurate detection front vehicles azimuth information, velocity information and acceleration
Information is spent, makes the control of reply with reference to this body structure of vehicle and dynamics accordingly, in the literature ([1] stable weighing apparatus, Meng Bo
Deep pool, a kind of research of automobile automatic brake system [J] agricultural equipments of poplar generation text and Vehicle Engineering, 2009 (4):42-43.) institute
The autobrake system stated realizes self-actuating brake by the threshold value of setting speed and distance, and does not set up dynamics of vehicle mould
Type, therefore control result can not reach ideal effect.Self-actuating brake control system needs to establish the inverse of longitudinal dynamics
Model, relative speed and relative distance are inputted, a corresponding brake pressure is obtained, establishes the dynamics to vehicle accurate description
System is particularly important, and accurate dynamic system is to realize the premise being precisely controlled, to vehicle brake power at present to use more
Be physical model modeling, and corresponding simplification such as document has been made to it ([2] Zheng Jie vehicle automatic emergency brake systems is built
Mould and simulation study [D] Wuhan University of Technologys, 2015), but physics mode modeling is excessively relied on vehicle structure parameter, and
And under operating mode complicated and changeable, vehicle structure parameter easily changes, the mode of physical modeling is not a kind of wide mathematics of practicality
Modeling method.
The content of the invention
It is an object of the invention to provide a kind of pilotless automobile automatic brake controller and method.
The pilotless automobile automatic brake controller includes information acquisition module, data processing module, automatic brake
Vehicle control and self-actuating brake braking execution module;Described information acquisition module gathers current vehicle speed and between barrier
Distance, the data processing module calculate current vehicle using the current vehicle speed of signal acquisition module and the distance between barrier
Relative velocity and relative distance between barrier, the phase that the self-actuating brake control system is obtained by data processing module
Adjust the distance with relative velocity and to recognize to obtain longitudinal inverse dynamics model using ant group optimization nerve network system, and it is inverse according to this
Forecast model of the kinetic model as PREDICTIVE CONTROL, made a prediction judgement according to current information using predictive control strategy, no
Only current vehicle condition is controlled, but also the state in some cycles is predicted and is based on this current input is repaiied
Just;The wheel cylinder brake pressure of the self-actuating brake control system output will be sent in self-actuating brake braking execution module, automatically
Brake pressure information can be changed into executable instruction in skidding execution module and pass to wheel cylinder controller, it is big to change pressure of wheel braking cylinder
It is small, realize the braking of vehicle.
The pilotless automobile self-actuating brake control method comprises the following steps:
1) information acquisition module is loaded in the millimetre-wave radar of front side, in real time to environment in front of automatic driving vehicle
Monitoring, by millimetre-wave radar obtain information current vehicle speed and with the distance between barrier information;
2) current vehicle speed that data processing module is obtained by information acquisition module and the distance with barrier, at incoming data
Reason center, the relative distance between Current vehicle and barrier and relative velocity is calculated, and this information is passed to brake
In Predictive Control System;
3) self-actuating brake control system includes inverse dynamics model System Discrimination and self-actuating brake PREDICTIVE CONTROL;
In step 3), the method for the inverse dynamics model System Discrimination can be:
(1) data-driven identification technique is utilized:Using ant group optimization neutral net seek optimal neural network structure and
Weights and threshold value, and longitudinal direction of car inversion model is established in nerve network system identification according to this, with current relative speed and relative distance
For input, wheel cylinder brake pressure is output;By millimetre-wave radar measure relative speed that information obtains through data processing module and
Relative distance, installation pressure sensor can obtain brake force at brake control valves, obtains input and output, it is non-thread to establish longitudinal model
Sexual system is described below:
Y (t)=F [y (t-1) ... y (t-n), u (t-d) ... .u (t-d-m)]
Dual input list output nonlinear dynamical system is represented, m and n are represented to input u respectively and exported y order, and d is non-thread
The time lag of sexual system, F () represent a unknown Continuous Nonlinear function to be identified;
(2) determine that input and output carry out identification experiment:Choose the starting of unmanned vehicle level land to accelerate, subtract with respect to barrier braking
Speed, tested, obtain a large amount of inputoutput datas;
(3) pretreatment of data:For the uncertain and factors of instability present in vehicle operation, in gatherer process
Containing much noise, the data of collection are filtered using wavelet analysis method;
(4) neutral net is trained using pretreated data.It is dynamic (dynamical) inverse to obtain accurate longitudinal direction of car
Model.
The method of the self-actuating brake PREDICTIVE CONTROL can be:
(1) be based on predictive control algorithm, longitudinal inverse dynamics model that System Discrimination is obtained as forecast model, and from
Dispersion establishes system discrete model;
(2) according to performance requirement when vehicle brake, controller performance index is designed, carries out rolling optimization;
(3) feedback correction is carried out according to prediction output quantity and current output quantity.
4) self-actuating brake braking execution module, performed in the brake pressure value of self-actuating brake control system output by braking
Resume module is controlled into executable instruction to each brake-cylinder pressure.
The advantage of the invention is that obtaining more that accurately inverse dynamics model being capable of accurate table by neural network identification
Up to the dynamic inverse of unmanned vehicle, numerous and diverse physical modeling process is saved, is controlled based on predictive control algorithm so that nobody drives
Sail vehicle corresponding speed and acceleration are obtained according to external information in real time and give unmanned vehicle brake pressure, realize unmanned mould
Formula and collision free generation.
Brief description of the drawings
Fig. 1 is self-actuating brake control system architecture figure.
Fig. 2 is that self-actuating brake inverse dynamics model recognizes flow chart.
Embodiment
Automatic driving vehicle dead-man's device of the present invention and method are described in further detail below in conjunction with accompanying drawing.
The present invention is provided at a kind of self-stopping control system of unmanned vehicle and method, including information acquisition module, data
Module, self-actuating brake control system and self-actuating brake braking execution module are managed, whole device structure is as shown in figure 1, information gathering
The distance between using millimetre-wave radar collection current vehicle speed and with barrier, data processing module is to utilize signal for module collection
The current vehicle speed of acquisition module and the distance between barrier calculate the relative velocity and phase between Current vehicle and barrier
Adjust the distance.The relative distance and relative velocity that self-actuating brake control module is obtained by data processing module utilize ant group optimization nerve
Network system recognizes to obtain longitudinal dynamics inversion model, and forecast model of the inverse dynamics model as PREDICTIVE CONTROL according to this, adopts
Made a prediction judgement according to current information with predictive control strategy, not only current vehicle condition be controlled, if but also pair
State in the dry cycle is predicted and is based on this to current Introduced Malaria;The wheel cylinder braking pressure of self-actuating brake control module output
Force signal will be sent in self-actuating brake braking execution module, can be become brake pressure information in self-actuating brake braking execution module
Wheel cylinder controller is passed to for executable instruction, the module includes brake signal importation, high-voltage power supply and pressure of wheel braking cylinder adjustment portion
Point, high-voltage power supply is made up of hydraulic pump, motor, accumulator and pressure sensor, and motor driven hydraulic pump forms height in accumulator
Pressure, can measure pressure value by pressure sensor, and pressure of wheel braking cylinder adjuster changes pressure of wheel braking cylinder size, realizes the braking of vehicle.
Implementation comprises the following steps that:
A. information acquisition module
The millimetre-wave radar of front side is loaded in, in real time to environmental monitoring in front of automatic driving vehicle, passes through millimeter wave
Radar obtains information current vehicle speed and the distance between with barrier.
B. data processing module
The current vehicle speed obtained by information acquisition module and the distance with barrier, incoming data processing center, are calculated
The relative distance and relative velocity gone out between Current vehicle and barrier, and this information is passed to brake Predictive Control System
In.
C. self-actuating brake control system includes two large divisions, inverse dynamics model System Discrimination part and self-actuating brake prediction
Control section:
C1. inverse dynamics model System Discrimination
Using data-driven identification technique, the modeling method recognized using nerve network system, unmanned vehicle is established offline and is indulged
To dynamic (dynamical) inversion model, using current relative speed and relative distance as input, brake pressure is output.Utilize millimetre-wave radar
The speed of real-time testing front truck and the distance between with barrier, and current time automatic driving car is obtained by data processing module
Relative distance and speed between barrier, pressure sensor is installed at brake control valves, can obtain brake control valves
Brake pressure.Utilize ant group optimization neural metwork training weights and threshold value.Automatic driving vehicle is established by System Discrimination
Longitudinal dynamics inversion model, inverse dynamics model are described such as formula (1):
Y (t)=F [y (t-1) ... y (t-n), u (t-d) ... .u (t-d-m)] (1)
Wherein, m and n is represented to input u respectively and is exported y order, and d is the time lag of nonlinear system, and F () represents one
Unknown Continuous Nonlinear function to be identified.
The identification of ant group optimization nerve network system specifically includes following steps:
The first step, data prediction, level land starting acceleration is carried out to real vehicle and high speed braking deceleration is tested, and utilizes sensing
566 groups of device collecting sample data, gone out using max min amplitude limit method and remove the number that its scope is not met in initial data
According to, and 3 σ criterion rejecting abnormalities data are used, and if primary data sample is y1, y2, y3 ... yn, average value areDeviationStandard deviation is calculated according to formula (2):
If deviation ei corresponding to a certain data sample yi, meet | ei| the σ of > 3, then it is assumed that this data is undesirable, deletes
This data.
Variation amplitude and unit are different in sample data, need to do normalized before network training, be network inputs and
Each numerical value is exported all between [- 1,1], normalized such as formula (3):
Wherein, y ' (n) be in sample data P n-th normalization after value, y (n) be normalization before initial data, max
(P) and min (P) is maximum and minimum value in P respectively.
After above-mentioned pretreatment, 424 groups of data are can obtain.Wherein made using 400 groups of carry out networking training, 24 groups of data
For network test.
Second step, utilize the hidden layer and each link weighting parameter for improving ant group algorithm optimization network, node in hidden layer
The set Q formed with network weight (being arranged according to the order of input layer, hidden layer and output layer) row vector, hidden node are independent
N number of integer is generated, weight vector is made up of N number of random value respectively.Specific steps process is as follows:
1) initialize:It is H to set ant number, time t=0, cycle-index Nc=0, sets maximum cycle
Ncmax, network parameter Q is randomly generated, makes approach (i, j) pheromones τ j (Q)=C (constant), and initial time Δ τ j (Q)=0,
H ant is placed on certain H element in m set at random.
2) all ants are started, every ant is pressed according to this throughout all set from N number of element in each set
Lower rule chooses one, and final m selected element forms a set of network parameters, and rule is as follows:For set Q, ant k (k
=1,2,3......H) probability calculated according to formula (4) randomly chooses j-th of element, and ant is moved to maximum shape
The element of state transition probability, and be recorded in element position is changed in taboo list.
3) repeat step 2), until all ants all reach selection H networkings in all foodstuffs source, that is, whole set
Road parameter.
4) t=t+m, Nc=Nc+1 are made, using the weights of each ant, sample data is brought into network and exported, calculates net
Network output valve and error, optimal solution is recorded, by m chronomere ant from ant nest arrival food source, the information on each path
Element is updated according to formula (5)~(7).
τj(Q) (t+m)=(1- ρ) τj(Q)(t)+Δτj(Q) (5)
Wherein, ρ is pheromones volatility coefficient,Be represent to have added reward with j-th yuan in set Q after punitive measures
The information content increment of element,Kth ant selected network parameter in the Nc-1 times and the Nc times iteration is represented respectively
The target value of map network, ifThen pheromones increase (reward);IfThen pheromones reduce and (punished
Penalize).
5) if ant is all converged on a paths or this cycle-index Nc>Ncmax, then export optimal solution, algorithm knot
Beam, otherwise empty taboo list and go to step 2) execution.
3rd step, network training, nerve network system is obtained by second step, nerve network system input is current relative
Distance and relative speed, nerve network system output is brake pressure, and using this network as dynamics of vehicle inversion model.
C2. self-actuating brake PREDICTIVE CONTROL
The first step, described automatic driving vehicle longitudinal dynamics inversion model is obtained as prediction mould by neural network identification
Type.The inversion model that neural network identification comes out, it is contemplated that many uncertain factors of vehicle in the process of running, work as vehicle detection
When needing to slow down to front obstacle, control program can calculate expectation deceleration automatically, and vehicle is under control system effect with one
Determine deceleration traveling, finally give desired speed.By the discrete nonlinear model being converted into shown in formula (8) of nonlinear dynamic system
Type is predicted
Second step, according to the performance index function formula (9) of system, continuous iteration obtains control law, carries out rolling optimization:
J=(y (t+1)-yr(t+1))2+λ(Δu(t+1))2 (9)
Wherein, λ is the weight coefficient of control.yr(t+1) it is prediction desired value, is minimized by performance index function, no
But error between reference model and controlled device output can be made minimum, and it is defeated to suppress controlled device by weight coefficient
Enter acute variation and reduce control dynamics.
3rd step, feedback compensation, each PREDICTIVE CONTROL controlled quentity controlled variable are Δ u (k), and prediction output can calculate according to formula (10)
Obtain:
Wherein,Represent to predict output at the time of t=kT, due to model be present
Error and interference, the output predicted value of system can not possibly be completely the same with forecast model, it is therefore desirable to by prediction output and reality
Deviation is done in output, and carries out feedback modifiers and compensation:
Y (k+1)=A Δs u (k)+he(k) (11)
Wherein, he is feedback error coefficient.
By rolling optimization and feedback compensation, obtain forecast model constantly close to actual control object model, and according to work as
Preceding information, following output can be predicted, preferably exported.
D. self-actuating brake braking execution module
In this step, the GES exported by brake Predictive Control System is sent into skidding execution module and handled
Into signal instruction, each brake disc is dealt into, as shown in fig. 1, skidding execution module includes brake signal importation, high pressure
Source, pressure of wheel braking cylinder adjusting means, motor driven hydraulic pump establish high pressure in accumulator, and thus control the pressure of each wheel cylinder
Value.
Fig. 2 provides self-actuating brake inverse dynamics model identification flow chart.
Claims (4)
1. a kind of pilotless automobile automatic brake controller, it is characterised in that including information acquisition module, data processing mould
Block, self-actuating brake control system and self-actuating brake braking execution module;Described information acquisition module gather current vehicle speed and with barrier
Hinder the distance between thing, current vehicle speed of the data processing module using signal acquisition module and the distance meter between barrier
The relative velocity and relative distance between Current vehicle and barrier are calculated, the self-actuating brake control system is by data processing mould
The relative distance and relative velocity that block obtains recognize to obtain longitudinal inverse dynamics mould using ant group optimization nerve network system
Type, and forecast model of the inverse dynamics model as PREDICTIVE CONTROL according to this, are made using predictive control strategy according to current information
Prediction judges, not only current vehicle condition is controlled, but also the state in some cycles is predicted and is based on this
To current Introduced Malaria;The wheel cylinder brake pressure of the self-actuating brake control system output will be sent to self-actuating brake braking and perform
Brake pressure information can be changed into executable instruction in module, in self-actuating brake braking execution module and pass to wheel cylinder controller, changed
Become pressure of wheel braking cylinder size, realize the braking of vehicle.
2. pilotless automobile self-actuating brake control method, it is characterised in that using a kind of unmanned as claimed in claim 1
Automobile automatic brake control device, the described method comprises the following steps:
1) information acquisition module is loaded in the millimetre-wave radar of front side, environment in front of automatic driving vehicle supervised in real time
Survey, by millimetre-wave radar obtain information current vehicle speed and with the distance between barrier information;
2) current vehicle speed that data processing module is obtained by information acquisition module and the distance with barrier, in incoming data processing
The heart, the relative distance between Current vehicle and barrier and relative velocity is calculated, and this information is passed to brake prediction
In control system;
3) self-actuating brake control system includes inverse dynamics model System Discrimination and self-actuating brake PREDICTIVE CONTROL;
4) self-actuating brake braking execution module, braking execution module is passed through in the brake pressure value of self-actuating brake control system output
Executable instruction is processed into, each brake-cylinder pressure is controlled.
3. pilotless automobile self-actuating brake control method as claimed in claim 2, it is characterised in that described inverse in step 3)
The method of kinetic model System Discrimination is:
(1) data-driven identification technique is utilized:Seek optimal neural network structure and weights using ant group optimization neutral net
And threshold value, and longitudinal direction of car inversion model is established in nerve network system identification according to this, using current relative speed and relative distance to be defeated
Enter, wheel cylinder brake pressure is output;Relative speed that information obtains through data processing module and relative is measured by millimetre-wave radar
Distance, installation pressure sensor obtains brake force at brake control valves, obtains input and output, establishes longitudinal model nonlinear system
It is described below:
Y (t)=F [y (t-1) ... y (t-n), u (t-d) ... .u (t-d-m)]
Dual input list output nonlinear dynamical system is represented, m and n are represented to input u respectively and exported y order, and d is nonlinear system
The time lag of system, F () represent a unknown Continuous Nonlinear function to be identified;
(2) determine that input and output carry out identification experiment:Choose the starting of unmanned vehicle level land to accelerate, with respect to barrier braking deceleration, enter
Row experiment, obtains a large amount of inputoutput datas;
(3) pretreatment of data:For the uncertain and factors of instability present in vehicle operation, contain in gatherer process
Much noise, the data of collection are filtered using wavelet analysis method;
(4) neutral net is trained using pretreated data, obtains the dynamic (dynamical) inversion model of accurate longitudinal direction of car.
4. pilotless automobile self-actuating brake control method as claimed in claim 2, it is characterised in that in step 3), it is described from
The method of dynamic brake PREDICTIVE CONTROL is:
(1) predictive control algorithm is based on, using longitudinal inverse dynamics model that System Discrimination obtains as forecast model, and discretization
Establish system discrete model;
(2) according to performance requirement when vehicle brake, controller performance index is designed, carries out rolling optimization;
(3) feedback correction is carried out according to prediction output quantity and current output quantity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710802092.9A CN107697045A (en) | 2017-09-07 | 2017-09-07 | A kind of pilotless automobile automatic brake controller and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710802092.9A CN107697045A (en) | 2017-09-07 | 2017-09-07 | A kind of pilotless automobile automatic brake controller and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107697045A true CN107697045A (en) | 2018-02-16 |
Family
ID=61172253
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710802092.9A Pending CN107697045A (en) | 2017-09-07 | 2017-09-07 | A kind of pilotless automobile automatic brake controller and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107697045A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108944882A (en) * | 2018-06-15 | 2018-12-07 | 湖北三环智能科技有限公司 | A kind of automatic driving vehicle electric control hydraulic braking system and its control method |
CN109263680A (en) * | 2018-09-11 | 2019-01-25 | 河南机电职业学院 | A kind of municipal rail train braking control system based on Fuzzy Predictive Control |
CN109407661A (en) * | 2018-08-30 | 2019-03-01 | 百度在线网络技术(北京)有限公司 | Collision prevention device and method based on unmanned vehicle |
CN109624945A (en) * | 2019-01-28 | 2019-04-16 | 银隆新能源股份有限公司 | A kind of active brake control system, method and automobile |
CN109724614A (en) * | 2019-02-22 | 2019-05-07 | 百度在线网络技术(北京)有限公司 | The speed planning method, apparatus and storage medium of automatic driving vehicle |
CN110329249A (en) * | 2019-07-02 | 2019-10-15 | 武汉理工大学 | To anti-collision warning control system and method before a kind of automobile of Recognition with Recurrent Neural Network |
CN110539739A (en) * | 2019-09-27 | 2019-12-06 | 成都坦途智行科技有限公司 | Unmanned vehicle line control braking system and braking method |
CN110920797A (en) * | 2018-09-03 | 2020-03-27 | 昆山君磊电器有限公司 | Automatic brake auxiliary device of electric bicycle |
CN110962828A (en) * | 2019-12-23 | 2020-04-07 | 奇瑞汽车股份有限公司 | Method and equipment for predicting brake pressure of electric automobile |
CN111257893A (en) * | 2020-01-20 | 2020-06-09 | 珠海上富电技股份有限公司 | Parking space detection method and automatic parking method |
CN112249309A (en) * | 2020-09-28 | 2021-01-22 | 西安航空学院 | Airplane fault safety brake control system |
CN112319441A (en) * | 2020-10-23 | 2021-02-05 | 上善智城(苏州)信息科技有限公司 | Electronic braking auxiliary braking system and method based on intelligent automobile networking |
CN114312768A (en) * | 2022-01-12 | 2022-04-12 | 廊坊市爱拼单网络技术有限公司 | Unmanned vehicle automatic braking system based on linear dynamic prediction model |
CN114407891A (en) * | 2022-01-06 | 2022-04-29 | 唐义诚 | Intelligent brake control system with multi-level identification and multifunctional detection |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101630144A (en) * | 2009-08-18 | 2010-01-20 | 湖南大学 | Self-learning inverse model control method of electronic throttle |
CN102109821A (en) * | 2010-12-30 | 2011-06-29 | 中国科学院自动化研究所 | System and method for controlling adaptive cruise of vehicles |
CN105094053A (en) * | 2014-05-22 | 2015-11-25 | 山东理工大学 | Machine tool thermal error modeling method based on ant colony neural network |
CN106671982A (en) * | 2017-01-09 | 2017-05-17 | 厦门大学 | Multi-intelligent agent based unmanned electric car automatic overtaking system and method |
-
2017
- 2017-09-07 CN CN201710802092.9A patent/CN107697045A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101630144A (en) * | 2009-08-18 | 2010-01-20 | 湖南大学 | Self-learning inverse model control method of electronic throttle |
CN102109821A (en) * | 2010-12-30 | 2011-06-29 | 中国科学院自动化研究所 | System and method for controlling adaptive cruise of vehicles |
CN105094053A (en) * | 2014-05-22 | 2015-11-25 | 山东理工大学 | Machine tool thermal error modeling method based on ant colony neural network |
CN106671982A (en) * | 2017-01-09 | 2017-05-17 | 厦门大学 | Multi-intelligent agent based unmanned electric car automatic overtaking system and method |
Non-Patent Citations (1)
Title |
---|
熊和金: "《智能信息处理》", 31 August 2012, 国防工业出版社 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108944882A (en) * | 2018-06-15 | 2018-12-07 | 湖北三环智能科技有限公司 | A kind of automatic driving vehicle electric control hydraulic braking system and its control method |
CN109407661A (en) * | 2018-08-30 | 2019-03-01 | 百度在线网络技术(北京)有限公司 | Collision prevention device and method based on unmanned vehicle |
CN110920797A (en) * | 2018-09-03 | 2020-03-27 | 昆山君磊电器有限公司 | Automatic brake auxiliary device of electric bicycle |
CN109263680A (en) * | 2018-09-11 | 2019-01-25 | 河南机电职业学院 | A kind of municipal rail train braking control system based on Fuzzy Predictive Control |
CN109624945A (en) * | 2019-01-28 | 2019-04-16 | 银隆新能源股份有限公司 | A kind of active brake control system, method and automobile |
CN109724614B (en) * | 2019-02-22 | 2021-06-04 | 百度在线网络技术(北京)有限公司 | Method, apparatus and storage medium for speed planning of autonomous vehicles |
CN109724614A (en) * | 2019-02-22 | 2019-05-07 | 百度在线网络技术(北京)有限公司 | The speed planning method, apparatus and storage medium of automatic driving vehicle |
CN110329249A (en) * | 2019-07-02 | 2019-10-15 | 武汉理工大学 | To anti-collision warning control system and method before a kind of automobile of Recognition with Recurrent Neural Network |
CN110539739A (en) * | 2019-09-27 | 2019-12-06 | 成都坦途智行科技有限公司 | Unmanned vehicle line control braking system and braking method |
CN110962828A (en) * | 2019-12-23 | 2020-04-07 | 奇瑞汽车股份有限公司 | Method and equipment for predicting brake pressure of electric automobile |
CN111257893A (en) * | 2020-01-20 | 2020-06-09 | 珠海上富电技股份有限公司 | Parking space detection method and automatic parking method |
CN112249309A (en) * | 2020-09-28 | 2021-01-22 | 西安航空学院 | Airplane fault safety brake control system |
CN112319441A (en) * | 2020-10-23 | 2021-02-05 | 上善智城(苏州)信息科技有限公司 | Electronic braking auxiliary braking system and method based on intelligent automobile networking |
CN114407891A (en) * | 2022-01-06 | 2022-04-29 | 唐义诚 | Intelligent brake control system with multi-level identification and multifunctional detection |
CN114312768A (en) * | 2022-01-12 | 2022-04-12 | 廊坊市爱拼单网络技术有限公司 | Unmanned vehicle automatic braking system based on linear dynamic prediction model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107697045A (en) | A kind of pilotless automobile automatic brake controller and method | |
CN108960426A (en) | Road grade Synthesize estimation system based on BP neural network | |
CN105136469A (en) | Unmanned vehicle speed control method based on PSO and RBF neutral network | |
CN105946861A (en) | NAR neural network vehicle speed prediction method based on driving intention recognition | |
CN107092256B (en) | Steering control method for unmanned vehicle | |
CN106707764A (en) | Multi-stage switching-based RBF (Radial Basis Function) model reference adaptive control method for bullet train braking process | |
CN101799888A (en) | Industrial soft measurement method based on bionic intelligent ant colony algorithm | |
CN105835854B (en) | A kind of emergency braking control system and its control method | |
Amer et al. | Hardware-in-the-loop simulation of trajectory following control for a light armoured vehicle optimised with particle swarm optimisation | |
Korayem et al. | Trailer mass estimation using system model-based and machine learning approaches | |
CN111415026A (en) | Unmanned equipment scheduling device, system and method | |
Heidari et al. | Design a PID controller for suspension system by back propagation neural network | |
Bian et al. | System identification method for small unmanned helicopter based on improved particle swarm optimization | |
Chen et al. | ES-DQN: A learning method for vehicle intelligent speed control strategy under uncertain cut-in scenario | |
Guidolini et al. | Neural-based model predictive control for tackling steering delays of autonomous cars | |
CN114253274B (en) | Data-driven-based networked hybrid vehicle formation rolling optimization control method | |
Wang et al. | Design and implementation of an adaptive cruise control system based on supervised actor-critic learning | |
Yang et al. | A study on a vehicle semi-active suspension control system based on road elevation identification | |
Kojis et al. | Deep neural network based data-driven virtual sensor in vehicle semi-active suspension real-time control | |
CN110816531B (en) | Control system and control method for safe distance between unmanned automobile vehicles | |
Namaghi et al. | An adaptive modified fuzzy-sliding mode longitudinal control design and simulation for vehicles equipped with ABS system | |
US20230001940A1 (en) | Method and Device for Optimum Parameterization of a Driving Dynamics Control System for Vehicles | |
CN113791598B (en) | Four-wheel moment distribution ring testing device under extreme working condition and torque optimizing method | |
Lu et al. | Road adhesion coefficient identification method based on vehicle dynamics model and multi-algorithm fusion | |
CN114861432A (en) | Vehicle brake joint simulation method and device, terminal equipment and storage medium |
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 |
Application publication date: 20180216 |
|
RJ01 | Rejection of invention patent application after publication |