CN207965887U - A kind of driving style device for identifying of novel differentiation operating mode - Google Patents
A kind of driving style device for identifying of novel differentiation operating mode Download PDFInfo
- Publication number
- CN207965887U CN207965887U CN201721303031.XU CN201721303031U CN207965887U CN 207965887 U CN207965887 U CN 207965887U CN 201721303031 U CN201721303031 U CN 201721303031U CN 207965887 U CN207965887 U CN 207965887U
- Authority
- CN
- China
- Prior art keywords
- steering wheel
- personal computer
- display
- industrial personal
- driving style
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The utility model discloses a kind of driving style device for identifying of novel differentiation operating mode, include frame body, steering wheel, display, pedal assembly, industrial personal computer and power supply, wherein steering wheel and display are arranged in one end of frame body, pedal assembly is located at the obliquely downward of steering wheel, rotary angle transmitter is equipped on steering wheel, accelerator pedal position sensor and brake pedal position sensor are equipped on pedal assembly, steering wheel, display, pedal assembly and industrial personal computer are connected with power supply respectively by conducting wire, and method is:Step 1: building a set of driver's driving data acquisition system using industrial personal computer;Step 2: training Random Forest model is used for the identification of typical condition.Advantageous effect:The utility model provides novel tool means for the research work of the following intelligent automobile, teaching, is realizing the identification precision that driving style is also improved while the simulation of Driving Scene appropriateness.
Description
Technical field
The utility model is related to a kind of driving style device for identifying, more particularly to a kind of driving wind of novel differentiation operating mode
Lattice device for identifying.
Background technology
In recent years, the control system of flourishing with intelligent automobile, automobile is also increasingly complicated, driver and automobile control
Contradiction between system processed is also increasingly prominent.Show that 60% or more traffic accident can be attributed to driving according to relevant information
The operation fault of the driver of stylistic differences causes.How the driving style of correct understanding driver, and then realize " vehicle adapt to
People " has become the hot spot of research.Existing driver's driving style identification system to the identification of driver's driving style often
It is based on the analysis to the driver's driver behavior data collected, by analyzing the logical relation inside driving data
Judge the driving style of driver.However the prior art is often analyzed not in the presence of to driving data comprehensively, to driver's driving wind
Lattice division methods not science the problems such as.
China Patent Publication No. CN106249619A, publication date are that the entitled one kind of 2016.12.21 is based on
Pass through in the identification of LabVIEW-Matlab driver styles and reponse system and method and analyzes vehicle status data such as vehicle
The standard deviation of manipulation signal, that is, pedal rate of change of average acceleration and driver and then the driving style for judging driver.
Obviously, such driving style analysis is incomplete, and the related data of steering wheel angle also contains a large amount of driver and drives
Style information is sailed, being should not be ignored.So when analyzing driver's driving style, the driver of consideration manipulates phase
The data of pass should include the related data of steering wheel angle and pedal travel.
Invention content
Purpose of the utility model is to solve existing the relevant technologies generally existing is not complete to driving data analysis
Face, to driver's driving style division methods not science the problems such as and the driving style of a kind of novel differentiation operating mode that provides distinguish
Identification device.
The driving style device for identifying of novel differentiation operating mode provided by the utility model includes frame body, steering wheel, shows
Show that device, pedal assembly, industrial personal computer and power supply, wherein steering wheel and display are arranged in one end of frame body, pedal assembly, which is located at, to be turned
To the obliquely downward of disk, it is equipped with rotary angle transmitter on steering wheel, accelerator pedal position sensor and system are equipped on pedal assembly
Dynamic pedal position sensor, steering wheel, display, pedal assembly and industrial personal computer are connected with power supply respectively by conducting wire, power supply
Electric energy, display, rotary angle transmitter, accelerator pedal position sensor are provided for steering wheel, display, pedal assembly and industrial personal computer
It is connected respectively with industrial personal computer with brake pedal position sensor.
It is additionally provided with seat on the chassis of frame body, sound equipment, the model of sound equipment are additionally provided on the frame body of display one side
R12U, there are two Edifier/ rambler's plastic box sound equipments of sound channel for tool.
The model SENSO Wheel of steering wheel, steering wheel servo motor nominal torque >=8Nm, electric machine control system
Moment responses≤60ms, moment follow-up stable state accuracy > 90%.
Display is curved display, and the resolution ratio of model 34UC79G is the Curved screen of 2560*1080, and the arc is aobvious
Show that device horizontal viewable angle is 178 degree, plumb visible angle is 178 degree, point is away from 0.311mm, curved display passes through HDMI wire
It is connected with industrial personal computer.
Pedal assembly is made of clutch pedal, electronic brake pedal and electronic accelerator pedal, clutch pedal, deceleration of electrons
Pedal and electronic accelerator pedal array from left to right on pedal assembly.
The angle data signal of steering wheel can be sent to industrial personal computer, rotation angular sensing by rotary angle transmitter by CAN message
Device measures steering wheel rotation angle, and the angular signal of steering wheel is converted to voltage signal and is transferred to industrial personal computer, accelerator pedal position
Acceleration data-signal can be obtained by setting sensor, and accelerator pedal position sensor measures electronic accelerator pedal position, by electronics plus
The position signal of speed pedal is converted to voltage signal, is transferred to industrial personal computer, and brake pedal position sensor can obtain braking number
It is believed that number, brake pedal position sensor measures electronic brake pedal position, and the position signal of electronic brake pedal is converted to
Voltage signal is transferred to industrial personal computer.
Driving style identification system is provided in industrial personal computer, driving style identification system is realized based on computer software
, and in particular to software have a PanoSim and MATLAB/Simulink, PanoSim is collection vehicle dynamic model, automobile three
It is automatic to tie up running environment model, running car traffic model, vehicle environment sensing model, MATLAB/Simulink simulation models
Core Generator can emulate what vehicle inputted driver, road surface and aerodynamics in the automobile virtual emulation platform of one
Response, Simulink is a kind of Visual Simulation Tools in MATLAB, is a kind of block diagram design environment based on MATLAB, is
Realize Modelling of Dynamic System, emulation and analysis a software package, Simulink provides a Modelling of Dynamic System, emulation and comprehensive
Close the integration environment of analysis.
Driving style discrimination method provided by the utility model based on data acquisition, method are as described below:
Step 1: building a set of driver's driving data acquisition system using industrial personal computer, it is based on driving data acquisition system,
The typical driving cycles of three kinds of setting, three kinds of driving cycles are respectively:Congestion operating mode, city situation and expressway operating mode, then into
Row drive simulating acquires the driving data of several tested drivers in real time;
Step 2: being used for based on the driving data under three kinds of typical conditions, training Random Forest model according in step 1
The driver under each operating mode is respectively trained based on neural network algorithm based on the operating mode that identification obtains in the identification of typical condition
Personal characteristics identification model.
Random forest in step 2 is a kind of algorithm based on classification tree, and specific algorithm is as follows:
Step 1:If there are several samples, then there are the several samples of the random selection put back to, randomly choose a sample every time,
It is then back to and continues to select, a decision tree is trained using several samples, as the sample at decision root vertex;
Step 2:When each sample has M attribute, when each node of decision tree needs division, at random from this M
M attribute is selected in attribute, meets condition m<Then M selects an attribute from this m attribute using corresponding method
Split Attribute as the node;
Step 3:Each node will be divided according to step 2 in decision tree forming process, until can not divide again
Until, without carrying out beta pruning in entire decision tree forming process;
Step 4 establishes a large amount of decision tree according to step 1 to 3, thus constitutes random forest, chooses average speed
Vmean, the max speed Vmax, average acceleration ameana, average retardation rate ameand, peak acceleration amax, minimum acceleration amin、
Velocity standard difference Vs, acceleration standard deviation asAmount to the characteristic parameter that eight parameters are recognized as driving cycles.
Neural network algorithm in step 2, algorithm are as follows:
Step 1:Calculate hidden layer number of nodes h:
Driver's driving style is divided into radical type, conservative, GENERAL TYPE, that is, exports three classification, corresponds to output section
Points are 3, and hidden layer number of nodes is determined with empirical equation:Wherein h indicates hidden layer number of nodes, o tables
Show that input layer number, p indicate that output layer number of nodes, q indicate the regulating constant between 1-10;
Step 2:It calculates hidden layer and exports H:
According to input vector, the connection weight W of input layer and hidden layerij, hidden layer and threshold value aj, calculate hidden layer output
H:
H indicates that hidden layer number of nodes, o indicate input layer number in formula, and f is activation primitive, chooses activation primitive:
F (x)=1/ (1+e-x)
Step 3:It calculates hidden layer and exports Ok:
H, connection weight W are exported according to hidden layerijWith threshold value bk, calculate output layer and export Ok:
M indicates output layer number of nodes in formula;
Step 4:Computation model error:
O is exported according to network identificationkWith desired output y, network identification error E is calculated:
Step 5:Right value update:
According to network identification error E, update network connection weights WijAnd Wjk:
For learning rate,
δjk=(yk-Ok)·Ok·(1-Ok)
Step 6:Threshold value updates:
According to network identification error E, the threshold value a of network node is updatedj、bk:
Step 7:It determines whether algorithm iteration terminates by judging whether network identification error meets the requirements, is unsatisfactory for tying
Beam condition then returns to step 2, in MATLAB working spaces, using function gensim (), can be given birth to a neural network
It is described at modularization, to be emulated to it in Simulink, inputs driver's characteristic parameter, i.e. steering wheel angle standard
After difference, gas pedal aperture average value and yaw rate standard deviation, BP neural network model, that is, exportable this is driven
People is sailed with P1Probability is radical type, with P2Probability is conservative, with P3Probability is GENERAL TYPE, if certain in three kinds of driving style types
A kind of probability PiIt is maximum and think that the driving style type is the driving style identification result of current driver more than 80%.
The beneficial effects of the utility model:
A kind of driving style device for identifying of novel differentiation operating mode provided by the utility model, involved hardware each group
Reliable at being connected between part, repair demolition is convenient.Used driver's driving style discrimination method adequately takes into account
The otherness of driver's driving style judgment criteria under different operating modes can realize that the driver in view of different operating modes drives wind
The identification of lattice.The utility model provides novel tool means for the research work of the following intelligent automobile, teaching, in reality
The identification precision of driving style is also improved while existing Driving Scene appropriateness simulation.
Description of the drawings
Fig. 1 is device overall structure diagram described in the utility model.
Fig. 2 is device circuit connection diagram described in the utility model.
Fig. 3 is invention the method implementation process schematic diagram.
1, frame body 2, steering wheel 3, display 4, pedal assembly 5, industrial personal computer 6, power supply 7, seat 8, sound equipment 9,
Clutch pedal 10, electronic brake pedal 11, electronic accelerator pedal.
Specific implementation mode
Shown in please referring to Fig.1 to Fig.3:
The driving style device for identifying of novel differentiation operating mode provided by the utility model include frame body 1, steering wheel 2,
Display 3, pedal assembly 4, industrial personal computer 5 and power supply 6, wherein steering wheel 2 and display 3 are arranged in one end of frame body 1, and pedal is total
The obliquely downward for being located at steering wheel 2 at 4 is equipped with rotary angle transmitter on steering wheel 2, accelerator pedal position is equipped on pedal assembly 4
Set sensor and brake pedal position sensor, steering wheel 2, display 3, pedal assembly 4 and industrial personal computer 5 by conducting wire respectively with
Power supply 6 is connected, and power supply 6 is that steering wheel 2, display 3, pedal assembly 4 and industrial personal computer 5 provide electric energy, and display 3, corner pass
Sensor, accelerator pedal position sensor and brake pedal position sensor are connected with industrial personal computer 5 respectively.
It is additionally provided with seat 7 on the chassis of frame body 1, sound equipment 8 is additionally provided on the frame body 1 of 3 one side of display, sound equipment 8
Model R12U, there are two Edifier/ rambler's plastic box sound equipments of sound channel for tool.
The model SENSO Wheel of steering wheel 2,2 servo motor nominal torque of steering wheel >=8Nm, motor control system
Moment responses≤60ms, the moment follow-up stable state accuracy > 90% of system.
Display 3 is curved display, and the resolution ratio of model 34UC79G is the Curved screen of 2560*1080, and the arc is aobvious
Show that device horizontal viewable angle is 178 degree, plumb visible angle is 178 degree, point is away from 0.311mm, curved display passes through HDMI wire
It is connected with industrial personal computer 5.
Pedal assembly 4 is made of clutch pedal 9, electronic brake pedal 10 and electronic accelerator pedal 11, clutch pedal 9,
Electronic brake pedal 10 and electronic accelerator pedal 11 array from left to right on pedal assembly 4.
The angle data signal of steering wheel 2 can be sent to industrial personal computer 5 by rotary angle transmitter by CAN message, and corner passes
Sensor measures steering wheel rotation angle, and the angular signal of steering wheel 2 is converted to voltage signal and is transferred to industrial personal computer 5, accelerates to step on
Board position sensor can obtain acceleration data-signal, and accelerator pedal position sensor measures 11 position of electronic accelerator pedal, will
The position signal of electronic accelerator pedal 11 is converted to voltage signal, is transferred to industrial personal computer 5, and brake pedal position sensor can obtain
Braking-distance figures signal is taken, brake pedal position sensor measures 10 position of electronic brake pedal, by the position of electronic brake pedal 10
Confidence number is converted to voltage signal and is transferred to industrial personal computer 5.
Driving style identification system is provided in industrial personal computer 5, driving style identification system is realized based on computer software
, and in particular to software have a PanoSim and MATLAB/Simulink, PanoSim is collection vehicle dynamic model, automobile three
It is automatic to tie up running environment model, running car traffic model, vehicle environment sensing model, MATLAB/Simulink simulation models
Core Generator can emulate what vehicle inputted driver, road surface and aerodynamics in the automobile virtual emulation platform of one
Response, Simulink is a kind of Visual Simulation Tools in MATLAB, is a kind of block diagram design environment based on MATLAB, is
Realize Modelling of Dynamic System, emulation and analysis a software package, Simulink provides a Modelling of Dynamic System, emulation and comprehensive
Close the integration environment of analysis.
Driving style discrimination method provided by the utility model based on data acquisition, method are as described below:
Step 1: a set of driver's driving data acquisition system is built using industrial personal computer 5, based on driving data acquisition system
System, sets three kinds of typical driving cycles, and three kinds of driving cycles are respectively:Congestion operating mode, city situation and expressway operating mode, then
Drive simulating is carried out, the driving data of several tested drivers is acquired in real time;
Step 2: being used for based on the driving data under three kinds of typical conditions, training Random Forest model according in step 1
The driver under each operating mode is respectively trained based on neural network algorithm based on the operating mode that identification obtains in the identification of typical condition
Personal characteristics identification model.
Random forest in step 2 is a kind of algorithm based on classification tree, and specific algorithm is as follows:
Step 1:If there are several samples, then there are the several samples of the random selection put back to, randomly choose a sample every time,
It is then back to and continues to select, a decision tree is trained using several samples, as the sample at decision root vertex;
Step 2:When each sample has M attribute, when each node of decision tree needs division, at random from this M
M attribute is selected in attribute, meets condition m<Then M selects an attribute from this m attribute using corresponding method
Split Attribute as the node;
Step 3:Each node will be divided according to step 2 in decision tree forming process, until can not divide again
Until, without carrying out beta pruning in entire decision tree forming process;
Step 4 establishes a large amount of decision tree according to step 1 to 3, thus constitutes random forest, chooses average speed
Vmean, the max speed Vmax, average acceleration ameana, average retardation rate ameand, peak acceleration amax, minimum acceleration amin, speed
Spend standard deviation Vs, acceleration standard deviation asAmount to the characteristic parameter that eight parameters are recognized as driving cycles.
What the realization of the utility model Random Forest model algorithm was realized at MATLAB, the specific following institute of LISP program LISP
Show:
clear all
clc
warning off
Load data.mat% store driving data information
A=randperm (30);
Train=data (a (1:25),:);
Test=data (a (26:end),:);
P_train=Train (:,3:end);
T_train=Train (:,2);
P_test=Test (:,3:end);
T_test=Test (:,2);
Model=classRF_train (P_train, T_train);
So far the Random Forest model training for then being used to recognize operating mode type is completed, and is by inputting new characteristic parameter group
It can judge which kind of in congestion operating mode, city situation or expressway operating mode be operating mode be by Random Forest model.
And then under three kinds of operating modes (congestion operating mode, city situation, expressway operating mode), total 30 driving are raised respectively
People carries out drive simulating (10 people are radical type, 10 people are conservative, 10 people are GENERAL TYPE), acquires the driving in driving procedure
People manipulates data and vehicle status data.
When classifying to driver's driving style, by steering wheel angle standard deviation, gas pedal aperture average value and
Input of the three driving characteristics parameters of yaw rate standard deviation as trained BP neural network model, in turn
Realize effective identification to its driving style.
It should be noted that steering wheel angle standard deviation, gas pedal aperture average value and yaw rate mark
Accurate poor three driving characteristics parameters are obtained by what principal component analytical method was analyzed.
Neural network algorithm in step 2, algorithm are as follows:
Step 1:Calculate hidden layer number of nodes h:
Driver's driving style is divided into radical type, conservative, GENERAL TYPE, that is, exports three classification, corresponds to output section
Points are 3, and hidden layer number of nodes is determined with empirical equation:Wherein h indicates hidden layer number of nodes, o tables
Show that input layer number, p indicate that output layer number of nodes, q indicate the regulating constant between 1-10;
Step 2:It calculates hidden layer and exports H:
According to input vector, the connection weight W of input layer and hidden layerij, hidden layer and threshold value aj, calculate hidden layer output
H:
H indicates that hidden layer number of nodes, o indicate input layer number in formula, and f is activation primitive, chooses activation primitive:
F (x)=1/ (1+e-x)
Step 3:It calculates hidden layer and exports Ok:
H, connection weight W are exported according to hidden layerijWith threshold value bk, calculate output layer and export Ok:
M indicates output layer number of nodes in formula;
Step 4:Computation model error:
O is exported according to network identificationkWith desired output y, network identification error E is calculated:
Step 5:Right value update:
According to network identification error E, update network connection weights WijAnd Wjk:
For learning rate,
δjk=(yk-Ok)·Ok·(1-Ok)
Step 6:Threshold value updates:
According to network identification error E, the threshold value a of network node is updatedj、bk:
Step 7:It determines whether algorithm iteration terminates by judging whether network identification error meets the requirements, is unsatisfactory for tying
Beam condition then returns to step 2, in MATLAB working spaces, using function gensim (), can be given birth to a neural network
It is described at modularization, to be emulated to it in Simulink, inputs driver's characteristic parameter, i.e. steering wheel angle standard
After difference, gas pedal aperture average value and yaw rate standard deviation, BP neural network model, that is, exportable this is driven
People is sailed with P1Probability is radical type, with P2Probability is conservative, with P3Probability is GENERAL TYPE, if certain in three kinds of driving style types
A kind of probability PiIt is maximum and think that the driving style type is the driving style identification result of current driver more than 80%.
Claims (6)
1. a kind of driving style device for identifying of novel differentiation operating mode, it is characterised in that:Include frame body, steering wheel, display
Device, pedal assembly, industrial personal computer and power supply, wherein steering wheel and display are arranged in one end of frame body, and pedal assembly is located at steering
The obliquely downward of disk is equipped with rotary angle transmitter on steering wheel, accelerator pedal position sensor and braking is equipped on pedal assembly
Pedal position sensor, steering wheel, display, pedal assembly and industrial personal computer are connected with power supply respectively by conducting wire, and power supply is
Steering wheel, display, pedal assembly and industrial personal computer provide electric energy, display, rotary angle transmitter, accelerator pedal position sensor and
Brake pedal position sensor is connected with industrial personal computer respectively.
2. a kind of driving style device for identifying of novel differentiation operating mode according to claim 1, it is characterised in that:It is described
Frame body chassis on be additionally provided with seat, be additionally provided with sound equipment on the frame body of display one side, the model R12U of sound equipment, tool
There are two Edifier/ rambler's plastic box sound equipments of sound channel.
3. a kind of driving style device for identifying of novel differentiation operating mode according to claim 1, it is characterised in that:It is described
Steering wheel model SENSO Wheel, steering wheel servo motor nominal torque >=8Nm, electric machine control system torque
Response≤60ms, moment follow-up stable state accuracy > 90%.
4. a kind of driving style device for identifying of novel differentiation operating mode according to claim 1, it is characterised in that:It is described
Display be curved display, the resolution ratio of model 34UC79G is the Curved screen of 2560*1080, the curved display water
Flat visible angle is 178 degree, plumb visible angle is 178 degree, point is away from 0.311mm, and curved display passes through HDMI wire and industry control
Machine is connected.
5. a kind of driving style device for identifying of novel differentiation operating mode according to claim 1, it is characterised in that:It is described
Pedal assembly be made of clutch pedal, electronic brake pedal and electronic accelerator pedal, clutch pedal, electronic brake pedal and
Electronic accelerator pedal arrays from left to right on pedal assembly.
6. a kind of driving style device for identifying of novel differentiation operating mode according to claim 1, it is characterised in that:It is described
Rotary angle transmitter the angle data signal of steering wheel can be sent to industrial personal computer by CAN message, rotary angle transmitter measures
The angular signal of steering wheel is converted to voltage signal and is transferred to industrial personal computer, accelerator pedal position sensing by steering wheel rotation angle
Device can obtain acceleration data-signal, and accelerator pedal position sensor measures electronic accelerator pedal position, by electronic accelerator pedal
Position signal be converted to voltage signal, be transferred to industrial personal computer, brake pedal position sensor can obtain braking-distance figures signal,
Brake pedal position sensor measures electronic brake pedal position, and the position signal of electronic brake pedal is converted to voltage signal
It is transferred to industrial personal computer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201721303031.XU CN207965887U (en) | 2017-10-11 | 2017-10-11 | A kind of driving style device for identifying of novel differentiation operating mode |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201721303031.XU CN207965887U (en) | 2017-10-11 | 2017-10-11 | A kind of driving style device for identifying of novel differentiation operating mode |
Publications (1)
Publication Number | Publication Date |
---|---|
CN207965887U true CN207965887U (en) | 2018-10-12 |
Family
ID=63723496
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201721303031.XU Active CN207965887U (en) | 2017-10-11 | 2017-10-11 | A kind of driving style device for identifying of novel differentiation operating mode |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN207965887U (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112129290A (en) * | 2019-06-24 | 2020-12-25 | 罗伯特·博世有限公司 | System and method for monitoring riding equipment |
CN113094930A (en) * | 2021-05-06 | 2021-07-09 | 吉林大学 | Driver behavior state data acquisition device and detection method |
-
2017
- 2017-10-11 CN CN201721303031.XU patent/CN207965887U/en active Active
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112129290A (en) * | 2019-06-24 | 2020-12-25 | 罗伯特·博世有限公司 | System and method for monitoring riding equipment |
CN113094930A (en) * | 2021-05-06 | 2021-07-09 | 吉林大学 | Driver behavior state data acquisition device and detection method |
CN113094930B (en) * | 2021-05-06 | 2022-05-20 | 吉林大学 | Driver behavior state data acquisition device and detection method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107526906A (en) | A kind of driving style device for identifying and method based on data acquisition | |
CN111795832B (en) | Intelligent driving vehicle testing method, device and equipment | |
CN109801534A (en) | Driving behavior hardware-in-the-loop test system based on automatic Pilot simulator | |
CN112613169B (en) | Expected function safety analysis method for misoperation of automatic driving vehicle | |
CN105825241B (en) | Operator brake based on fuzzy neural network is intended to discrimination method | |
CN107886798A (en) | A kind of driving efficiency device for identifying and method based on driving analog system | |
CN104462716B (en) | A kind of the brain-computer interface parameter and kinetic parameter design method of the brain control vehicle based on people's bus or train route model | |
CN103823929A (en) | Method for testing performance of steering system of vehicle on basis of driver model | |
CN104298122A (en) | Hardware-in-loop test system and test method for ACC system development | |
CN107871418A (en) | It is a kind of to be used to evaluate the man-machine experiment porch for driving reliability altogether | |
CN109131351A (en) | Intact stability evaluation method based on stochastic Time-Delay | |
CN207965887U (en) | A kind of driving style device for identifying of novel differentiation operating mode | |
US11354458B1 (en) | Automated vehicle safety simulation using safety quotient method | |
CN113311727A (en) | Simulation system for automatic driving test | |
CN101587658A (en) | Graphics rendering engine and physics engine-based three-dimension automobile driving simulation device | |
CN116134292A (en) | Tool for performance testing and/or training an autonomous vehicle planner | |
Cheng et al. | Quantitative evaluation methodology for chassis-domain dynamics performance of automated vehicles | |
CN110501167A (en) | System for executing the simulated crash scene of motor vehicles and non-motor vehicle road user | |
CN112435530A (en) | Mining truck simulation driving training system | |
CN112572606B (en) | Working condition fusion road sense simulation method based on SVM (support vector machine) and BP (back propagation) neural network | |
Polesel et al. | Hierarchical control of overactuated vehicles via sliding mode techniques | |
Luo et al. | UML-based design of intelligent vehicles virtual reality platform | |
CN207966228U (en) | A kind of novel driving efficiency device for identifying based on automobile driving simulator | |
JP2024507998A (en) | Method for testing vehicle driver assistance systems | |
CN115096305A (en) | Intelligent driving automobile path planning system and method based on generation of countermeasure network and simulation learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant |