CN109658503A - A kind of driving behavior intention detection method merging EEG signals - Google Patents
A kind of driving behavior intention detection method merging EEG signals Download PDFInfo
- Publication number
- CN109658503A CN109658503A CN201811634944.9A CN201811634944A CN109658503A CN 109658503 A CN109658503 A CN 109658503A CN 201811634944 A CN201811634944 A CN 201811634944A CN 109658503 A CN109658503 A CN 109658503A
- Authority
- CN
- China
- Prior art keywords
- driver
- signal
- driving
- eeg signals
- behavior
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W40/09—Driving style or behaviour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Abstract
The present invention relates to a kind of driving behaviors for merging EEG signals to be intended to detection method, belongs to intelligent driving technical field, and solving the problems, such as detection device in the prior art, there are time delays by the interference and detection of external environment.Include: building virtual driving scene model, and acquisition is synchronized to the EEG signals of driver and behavior signal;The behavior signal of the driver of acquisition and EEG signals are subjected to convergence analysis, obtain convergence analysis result;Driver's EEG signals are obtained in real time, and according to above-mentioned convergence analysis as a result, the driving intention of prediction driver, carries out auxiliary control to vehicle control device.The present invention is predicted using the EEG signals of driver and the convergence analysis result of driving behavior signal the driving intention of driver and driving behavior control, both existing detection driving behavior time delay defect had been eliminated, the corresponding variation that can sufficiently reflect driver's EEG signals in driving procedure again, ensure that the accurate real-time control to vehicle.
Description
Technical field
The present invention relates to intelligent driving technical fields more particularly to a kind of driving behavior for merging EEG signals to be intended to inspection
Survey method.
Background technique
Currently, Road Traffic Injury has become one of important death cause of crowd, about 95% all kinds of motor vehicle accidents
It is and the traffic induced completely by the inappropriate driving behavior of driver as caused by driver's misoperation to a certain extent
Accident has accounted for 3/4ths of total number of accident.Therefore, it is very important to the analysis of driving behavior and driver status.
In order to improve driving safety, the existing research for being related to auxiliary driving is broadly divided into two classes: vehicle-mounted one is utilizing
Sensor (such as video camera, infra-red detection) obtains the obstacle information of vehicle front and judges whether there is potential danger
Factor, to take some control measure to avoid vehicle collision front obstacle;The deficiency of this kind of technology is that external equipment is easy
By the interference that weather, external environment change, detection effect is bad.Another kind is that (such as video camera carries out face using external equipment
Identification, infrared equipment induction etc.) driving behavior of driver or intention are predicted and analyzed, and based on the analysis results to driving
Strategy is sailed to be adjusted;But due to the retardance of driver's driving behavior, the signal detected, which is difficult to reflect in time, to be driven
The variation of the person's of sailing state can not reach preferable synchronization in addition, detection signal is separately analyzed with driving behavior signal
Detection effect.
In addition, there are also a kind of technical solution be it is unmanned, it is unmanned main using multiple sensors, processor and holding
Row device replaces control of the driver to vehicle.But current unmanned technology has not yet been reached and perfect can replace driver
Stage, the control of vehicle is not sufficiently stable, control precision it is not high enough, comfort and ride comfort cannot be guaranteed.
Summary of the invention
In view of above-mentioned analysis, the present invention is intended to provide a kind of driving behavior for merging EEG signals is intended to detection side
Method, to solve the problems, such as detection device in existing method, by the interference and detection of external environment, there are time delays.
The purpose of the present invention is mainly achieved through the following technical solutions:
Provide a kind of driving behavior intention detection method for merging EEG signals, comprising the following steps:
Step S1, virtual driving scene model is constructed, and the EEG signals of driver are synchronized with behavior signal and are adopted
Collection;
Step S2, the behavior signal of the driver of acquisition and EEG signals are subjected to convergence analysis, obtain fusion point
Analyse result;
Step S3, driver's EEG signals are obtained in real time, and according to above-mentioned convergence analysis as a result, the driving of prediction driver
It is intended to, auxiliary control is carried out to vehicle control device.
The present invention has the beneficial effect that: by analyze driver driving data, realize driver EEG signals and
The convergence analysis of driving behavior signal predicted using driving intention of the convergence analysis result to driver, and to later
Driving behavior controlled, not only eliminated time delay problem of the prior art when detecting driving behavior, but also can sufficiently reflect
The corresponding variation of driver's EEG signals in driving procedure;In addition, using EEG signals as important during intelligent driving
Reference signal and control input signal, so that driving procedure is more intelligent, real-time also can be ensured preferably, be realized pair
The accurate control of vehicle;The present invention can be used for the design of driving assistance system, facilitate the driving intention of prediction driver simultaneously
The driving behavior of auxiliary adjustment in time is of great significance to safeguarding traffic safety, evading road traffic accident.
On the basis of above scheme, the present invention has also done following improvement:
Further, the building virtual driving scene model includes:
It constructs driving vision scene: scene construction being carried out by 3D modeling software and 3D is rendered, utilizes virtual reality software
It generates three dimensional virtual models and carries out three-dimensional presentation;
Manipulation device needed for building driving, and signal acquisition sensor is installed on the manipulation device;
Above-mentioned driving control device and the driving vision scene of building are interconnected, virtual driving scene model is obtained.
Further, the EEG signals to driver and behavior signal synchronize acquisition, comprising: driver head wears
Electrode cap is worn, and carries out driver behavior in the virtual driving scene model of the building by controlling manipulation device;It is driving
In the process, electrode potential variation acquisition driver's EEG signals at driver head's difference channel are obtained by electrode cap;Together
When, pass through the sensing data variation acquisition driving behavior signal on each manipulation device.
Further, behavior signal with EEG signals the progress convergence analysis of the driver by above-mentioned acquisition includes:
The collected behavior signal of sensor on manipulation device is carried out to the conversion of analog to digital signal;
Convergence analysis is carried out to the EEG signals of driving behavior digital signal obtained above and acquisition;
Signal obtained above is subjected to latency values extraction, the behavior signal for obtaining driver is merged with EEG signals
As a result.
Further, the EEG signals to digital signal obtained above and acquisition carry out convergence analysis, comprising:
With reference to conversion, driver's EEG signals and driving behavior digital signal are placed in it is same with reference to initial point, and will
The reference point of EEG signals is placed at regulation electrode reference position;
Baseline correction determines the baseline position of signal according to above-mentioned reference conversion result, so that the wave of all channel signals
Shape and label correspond to baseline position coincidence;
Data filtering is filtered the multi channel signals after baseline correction using low-pass filter, filters out in signal
Distorted portion;
For the segmentation of brain electricity with averagely, data and driver when driver is generated braking event do not generate data when braking
It is overlapped averagely, obtains the ERP signal induced by driver's driving behavior.
Further, the EEG signals to digital signal obtained above and acquisition carry out convergence analysis, further includes:
Eye electricity is removed, the segment interfered in removal EEG signals by electro-ocular signal is decomposed using covariance analysis method;
Removal drift, by limiting the amplitude range of fusion signal, removal is led due to the unrelated significantly behavior of driver
The amplitude signal in band of cause.
Further, on the manipulation device install signal acquisition sensor include: brake pedal, gas pedal and from
Pressure sensor is respectively mounted in clutch;Setting angle sensor on the steering wheel.
Further, the collected analog signal of sensor by manipulation device is converted into digital signal, comprising: when
When driver controls manipulation device movement, corresponding driving behavior is generated, the signal value at the moment is greater than 0, and numerical value is set to 1;When
When driver does not control manipulation device movement, driving behavior is not generated, and the signal value at the moment is 0, and numerical value is set to 0.
Further, the collected analog signal of sensor by manipulation device is converted into digital signal, comprising: adopts
With fuzzy control, different discrete signal values is set according to the size of signal value on manipulation device, obtains discrete signal value and behaviour
The corresponding relationship of the displacement variable of vertical device.
Further, real-time acquisition driver's EEG signals, and according to above-mentioned convergence analysis as a result, predicting driver's
Driving intention carries out auxiliary control to vehicle control device, comprising: according to convergence analysis obtained above as a result, will collect
The EEG signals of driver translated by incubation period, obtain the response signal of corresponding vehicle control device, and pass through vehicle
The controlling extent of the response time of manipulation device response signal and the adjustment of signal value size to vehicle control device.
It in the present invention, can also be combined with each other between above-mentioned each technical solution, to realize more preferred assembled schemes.This
Other feature and advantage of invention will illustrate in the following description, also, certain advantages can become from specification it is aobvious and
It is clear to, or understand through the implementation of the invention.The objectives and other advantages of the invention can by specification, claims with
And it is achieved and obtained in specifically noted content in attached drawing.
Detailed description of the invention
Attached drawing is only used for showing the purpose of specific embodiment, and is not to be construed as limiting the invention, in entire attached drawing
In, identical reference symbol indicates identical component.
Fig. 1 is the driving behavior intention detection method flow chart that EEG signals are merged in the embodiment of the present invention;
Fig. 2 is foundation and the presentation flow chart of virtual driving scene model in the embodiment of the present invention;
Fig. 3 is driver's EEG signals and behavior signal synchronous collection flow chart in the embodiment of the present invention;
Fig. 4 is to carry out convergence analysis flow chart to the behavior signal of driver and EEG signals in the embodiment of the present invention.
Specific embodiment
Specifically describing the preferred embodiment of the present invention with reference to the accompanying drawing, wherein attached drawing constitutes the application a part, and
Together with embodiments of the present invention for illustrating the principle of the present invention, it is not intended to limit the scope of the present invention.
A specific embodiment of the invention discloses a kind of driving behavior intention detection side for merging EEG signals
Method.As shown in Figure 1, comprising the following steps:
Step S1, virtual driving scene model is constructed, and the EEG signals of driver are synchronized with behavior signal and are adopted
Collection;
Step S2, the behavior signal of the driver of acquisition and EEG signals are subjected to convergence analysis, obtain fusion point
Analyse result;
Step S3, driver's EEG signals are obtained in real time, and according to above-mentioned convergence analysis as a result, the driving of prediction driver
It is intended to, auxiliary control is carried out to vehicle control device.
Compared with prior art, the driving behavior of fusion EEG signals provided in this embodiment is intended to detection method, leads to
The driving data for crossing analysis driver, realizes the EEG signals of driver and the convergence analysis of driving behavior signal, utilizes
Convergence analysis result predicts the driving intention of driver, and controls driving behavior later, has both eliminated existing
There is time delay problem of the technology when detecting driving behavior, and can sufficiently reflect pair of driver's EEG signals in driving procedure
It should change;In addition, using EEG signals as the important references signal and control input signal during intelligent driving, so that driving
Process is more intelligent, and real-time also can be ensured preferably, realizes the accurate control to vehicle;The present invention can be used for driving
The design for sailing auxiliary system facilitates the driving intention for predicting driver and the driving behavior of auxiliary adjustment in time, to maintenance road
Traffic safety evades road traffic accident and is of great significance.
It should be noted that the present invention can be used for detecting the behaviors such as acceleration, braking, steering, the shift of driver intention,
Braking action in following procedure mainly using driver is illustrated as specific embodiment, the detection method of other driving behaviors
Process be it is same or similar, the correspondence behavior in embodiment can be replaced with directly and need to be implemented and examine by those skilled in the art
The driving behavior of survey.
Specifically, in step sl, by constructing virtual driving scene model, drive simulating environment, driver is at this
Driving simulation driver behavior is carried out in environment, meanwhile, to the EEG signals of driver and behavior signal during driver behavior
Synchronize acquisition;Specifically,
Step S101 constructs virtual driving scene model, carries out scene by 3D modeling software (preferred, 3ds MAX)
It builds and 3D rendering, generates three dimensional virtual models using virtual reality software (preferred, Vizard software) and carry out solid and be in
It is existing;As shown in Fig. 2, specifically,
Step S10101 constructs driving vision scene, firstly, establishing threedimensional model;The void detected according to driving behavior
Quasi- Driving Scene demand, the corresponding model of building in 3D modeling software (such as 3ds MAX), illustratively, elementary path scene
Component part may include road, street lamp, vehicle, traffic lights etc.;Can drive simulating according to demand different scenes
It needs voluntarily component part to be selected to be built.
Secondly, carrying out 3D rendering to above-mentioned model;Illustratively, 3D wash with watercolours is carried out using 3D modeling software (such as 3ds MAX)
Dye, so that the threedimensional model of above-mentioned foundation is more three-dimensional;The model for completing rendering exports as * .py file format, walks for after
Suddenly.
Finally, carrying out virtual reality model generation and three-dimensional presentation;Above-mentioned derived * .py file is directed into virtual existing
In virtual reality software (such as Vizard) in real platform, realizes the generation of three dimensional virtual models and stereoscopic model is in
It is existing.
Step S10102, manipulation device needed for building driving, and signal acquisition sensor is installed on manipulation device;
In order to preferably obtain driving behavior signal, signal is assembled on each manipulation device in the present embodiment and is adopted
Collect sensor, wherein manipulation device includes: brake pedal, gas pedal, clutch, steering wheel;Specifically, brake pedal,
Gas pedal and clutch are respectively mounted pressure sensor;In steering wheel setting angle sensor;Each sensor is connected with processor,
The data of each sensor can be obtained in real time.Data reflect the change of various types of signal in driver's driving procedure in each sensor
Change, driving behavior, such as pressure sensing of the driver in braking process, on brake pedal are reacted in the variation of these signals
The braking action of the corresponding driver of the variation for the brake signal that device is recorded.
Above-mentioned driving control device and the driving vision scene of building are interconnected, obtain virtual driving field by step S10103
Scape model controls virtual vehicle in driving vision scene by driving control device in this model and moves, and driver can be in void
Various emulation driving behaviors are executed in near-ring border.
Step S102, driver is used as " sensor ", carries out driving behaviour in the virtual driving scene model of above-mentioned building
Make, and export EEG signals and braking action signal, by synchronizing acquisition to EEG signals and braking action signal, is used for
Further convergence analysis, as shown in Figure 3, comprising:
Driver's eeg signal acquisition;Driver head wears electrode cap, carries out in above-mentioned virtual driving scene model
Driver behavior, during driving in virtual environment, electrode cap acquires the variation of the EEG signals of driver in real time.Electrode cap
On can collect electrode potential variation at driver head's difference channel, and Electroencephalo signal amplifier is transmitted to, by amplifier
EEG signals after exporting enhanced processing, the EEG signals are real-time transmitted to processor, are used for further convergence analysis;Together
When, electrode cap is convenient to wear, safe and reliable, can be real under the premise of ensureing that harmless to driver health, driving is glitch-free
The acquisition of existing High resolution electroencephalogram signal.
Driving behavior signal acquisition;During driver drives in virtual environment, operating method is identical as real vehicle,
Steering wheel controls the steering of virtual vehicle, and brake pedal controls virtual vehicle and slows down, and gas pedal controls vehicle and accelerates, clutch
Control virtual vehicle smoothly starts to walk and shifts gears.Sensing data on each manipulation device can reflect each in driver's driving procedure
Driving behavior is reacted in the variation of the variation of class signal, these signals;Behavior signal is real-time transmitted to processor, for into
The convergence analysis of one step.
Step S2, the behavior signal of the driver of above-mentioned acquisition and EEG signals are subjected to convergence analysis, obtain fusion point
Analyse result;As shown in Figure 4, comprising the following steps:
Step S201, data prediction is carried out to driving behavior signal;Specifically, the sensor on manipulation device is adopted
The behavior signal collected carries out the conversion of analog signal to digital signal.Still to merge the operator brake behaviors of EEG signals
For detection, operator brake behavior signal is pre-processed, by the collected analog signal of sensor on brake pedal
It is converted into digital signal.Specifically, when driver's brake pedal, braking action is generated, the signal value at the moment is greater than
0, numerical value is set to 1;When driver does not have brake pedal, braking action is not generated, and the signal value at the moment is 0, numerical value
It is set to 0.Further, in order to embody the degree size that driver steps on brake pedal, brake pedal braking effect is carried out accurate
Control can also use fuzzy control, different discrete signal values be arranged according to the size of braking signal value, by discrete signal value
It is corresponding with the change in displacement of brake pedal, that is, obtain the corresponding relationship of different discrete signal value and different braking effect.
Step S202, digital signal obtained above (the braking action signal of driver) is merged with EEG signals
Analysis;(re-referencing), baseline correction (baseline correct), data filtering are converted including reference
(filtering), removal eye electric (ocular artifact reduction), removal drift (bad block
Reduction), the segmentation of brain electricity and average (event related averaging) six steps, specifically:
With reference to conversion, EEG signals and operator brake behavior signal are placed in it is same with reference to initial point, and by brain telecommunications
Number reference point be placed at regulation electrode reference position;Be conducive to baseline correction link with reference to conversion and obtain most true baseline
The signal of (being similar to 0).Illustratively, reference electrode is averagely used as using bilateral mastoid process in the present embodiment.
Baseline correction determines the baseline position of signal;Baseline correction can allow the waveform and label pair of all channel signals
It answers baseline position (" X-axis ") to be overlapped, allows multi channel signals to fluctuate in same range, so that data are further processed.
Data filtering filters out the distorted portion in EEG signals and operator brake behavior signal;Using low-pass filter
Multi channel signals after baseline correction are filtered, are gone unless the amplitude human body signal of EEG signals makees the interference of data
With.
Eye electricity is removed, the segment interfered in EEG signals by electro-ocular signal, while the corresponding piece for formulating signal are removed
Section can be also removed;Illustratively, the influence that eye electricity artefact is decomposed and eliminated using covariance analysis method, avoids driver in reality
The eye movement information in example is applied to the interference effect of EEG signals.Signal after removal only includes single EEG signals and drives row
For the fusion signal of signal.
Removal drift, for removing the bad block wave band caused by driver significantly acts, to reduce to data point
Nonsensical part signal is analysed, Data Analysis Services efficiency is improved;Specifically, by limiting the amplitude range of fusion signal,
The amplitude signal in band as caused by driver's unrelated significantly behavior is removed, this wave band can be by the brain telecommunications of low amplitude value
It number is completely covered, leads to not analyze.Fusion signal after removal drift can be used to further brain electricity segmentation and average.
For the segmentation of brain electricity with averagely, data and driver when driver is generated braking event do not generate number when braking
It is average according to being overlapped, ERP (event related potential) letter induced by operator brake behavior after available removal interference
Number fluctuation situation.
Step S203, output EEG signals and operator brake behavior signal fused analyze result;
Specifically, incubation period (latency) numerical value is carried out to ERP signal obtained above using signal processing software to mention
It takes, output EEG signals and operator brake behavior signal fused analyze result.Preclinical numerical value reflects driver's brain electricity
Time and driver that the peak value of signal occurs generate the difference of the time of braking action, can reflect prediction operator brake
The effect of behavior.It should be noted that the incubation period of different driving behaviors is also different, the convergence analysis distinguished, really
Fixed specific latency values.Incubation period can be used as output signal, make the response time of vehicle control device flat by incubation period
It moves, reaches corresponding with EEG signals, to realize the purpose for eliminating control time delay.
Step S3, driver's EEG signals are obtained in real time, and according to above-mentioned convergence analysis as a result, the driving of prediction driver
It is intended to, auxiliary control is carried out to vehicle control device.
In actually driving, the EEG signals of driver are acquired in real time, and pre-processed (such as: denoising, whole to signal
Shape, filtering, signal enhanced processing etc.), and convergence analysis is obtained as a result, by collected EEG signals by obtaining according to above-mentioned
Incubation period is translated, and the response signal of corresponding vehicle control device is obtained, and reaches the real-time of EEG signals and response signal
It is corresponding, and vehicle is controlled by the response time of vehicle control device response signal and corresponding controlling extent (signal value size)
Stable motion in the road.At the same time it can also the sensor on continuous collecting steering wheel, brake pedal, gas pedal, clutch
Data, and cooperate with above-mentioned controlling extent, realize the accurate control to vehicle.Specifically, after detecting incubation period, driver
Relevant operation intention can be detected, according to convergence analysis obtained above as a result, controlling the signal of corresponding manipulation device
Enhancing weakens, and meets the driving intention of driver, reaches driving purpose.Illustratively, when driver has braking to anticipate
When figure, EEG signals and brake signal can all have certain variation, by the corresponding relationship both in above-mentioned fusion results can,
Prediction driving behavior be intended to (such as think completely brake still slightly slow down), thus to vehicle operation device (such as brake pedal) into
Row control, (pressure value such as obtained according to analysis EEG signals is big for the practical control cooperation with driver to vehicle operation device
It is small control brake pedal displacement), completion vehicle is accurately controlled, avoid driver's operating process overexert or
Person exerts oneself problem not in place.
It is emphasized that the embodiment of the present invention passes through EEG signals and driving behavior signal synchronous collection, convergence analysis,
Each sensor, processor effectively cooperate between actuator, and the Data Management Analysis link in perfect driving procedure enhances
The effect that driver plays in driving procedure is examined by detection time far faster than the EEG signals in the way of other external detections
It surveys, can effectively solve the problems, such as retardance, enable a driver to accomplish the real-time control to vehicle;Meanwhile proposition with
Driver carries out the novel method of signal transmitting as " sensor ", highlights driver in ring (DIL, driver-in-the-
Loop) control action can test different drivers and take different driving strategies, be different from common unmanned technology
With class people's driving technology, it can be directed to different driver's individual design personalized driving schemes, to improve the comfort driven
With enjoyment.
It will be understood by those skilled in the art that realizing all or part of the process of above-described embodiment method, meter can be passed through
Calculation machine program instruction relevant hardware is completed, and the program can be stored in computer readable storage medium.Wherein, described
Computer readable storage medium is disk, CD, read-only memory or random access memory etc..
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by anyone skilled in the art,
It should be covered by the protection scope of the present invention.
Claims (10)
1. a kind of driving behavior for merging EEG signals is intended to detection method, which comprises the following steps:
Virtual driving scene model is constructed, and acquisition is synchronized to the EEG signals of driver and behavior signal;
The behavior signal of the driver of acquisition and EEG signals are subjected to convergence analysis, obtain convergence analysis result;
Driver's EEG signals are obtained in real time, and according to above-mentioned convergence analysis as a result, the driving intention of driver is predicted, to vehicle
Manipulation device carries out auxiliary control.
2. the method according to claim 1, wherein the building virtual driving scene model includes:
It constructs driving vision scene: scene construction being carried out by 3D modeling software and 3D is rendered, utilizes virtual reality Software Create
Three dimensional virtual models simultaneously carry out three-dimensional presentation;
Manipulation device needed for building driving, and signal acquisition sensor is installed on the manipulation device;
Above-mentioned driving control device and the driving vision scene of building are interconnected, virtual driving scene model is obtained.
3. according to the method described in claim 2, it is characterized in that, the EEG signals to driver and behavior signal carry out
Synchronous acquisition, comprising: driver head wears electrode cap, and by controlling manipulation device in the virtual driving scene of building
Driver behavior is carried out in model;In driving procedure, the electrode potential at driver head's difference channel is obtained by electrode cap
Variation acquisition driver's EEG signals;Meanwhile passing through the sensing data variation acquisition driving behavior letter on each manipulation device
Number.
4. according to the method described in claim 3, it is characterized in that, the behavior signal and brain of the driver by above-mentioned acquisition
Electric signal carries out convergence analysis
The collected behavior signal of sensor on manipulation device is carried out to the conversion of analog to digital signal;
Convergence analysis is carried out to the EEG signals of driving behavior digital signal obtained above and acquisition;
Signal obtained above is subjected to latency values extraction, the behavior signal for obtaining driver merges knot with EEG signals
Fruit.
5. according to the method described in claim 4, it is characterized in that, the brain electricity to digital signal obtained above and acquisition
Signal carries out convergence analysis, comprising:
With reference to conversion, driver's EEG signals and driving behavior digital signal are placed in same with reference to initial point and brain is electric
The reference point of signal is placed at regulation electrode reference position;
Baseline correction determines the baseline position of signal according to above-mentioned reference conversion result so that the waveform of all channel signals and
Label corresponds to baseline position coincidence;
Data filtering is filtered the multi channel signals after baseline correction using low-pass filter, filters out the distortion in signal
Part;
With averagely, data when data and driver when driver is generated braking event do not generate braking carry out the segmentation of brain electricity
Superposed average obtains the ERP signal induced by driver's driving behavior.
6. according to the method described in claim 5, it is characterized in that, the brain electricity to digital signal obtained above and acquisition
Signal carries out convergence analysis, further includes:
Eye electricity is removed, the segment interfered in removal EEG signals by electro-ocular signal is decomposed using covariance analysis method;
Removal drift is removed as caused by the unrelated significantly behavior of driver by limiting the amplitude range of fusion signal
Amplitude signal in band.
7. according to the method described in claim 6, it is characterized in that, installing signal acquisition sensor packet on the manipulation device
It includes: being respectively mounted pressure sensor on brake pedal, gas pedal and clutch;Setting angle sensor on the steering wheel.
8. method described in one of -7 according to claim 1, which is characterized in that the sensor by manipulation device collects
Analog signal be converted into digital signal, comprising: when driver control manipulation device movement when, generate corresponding driving behavior,
The signal value at the moment is greater than 0, and numerical value is set to 1;When driver does not control manipulation device movement, driving behavior is not generated,
The signal value at the moment is 0, and numerical value is set to 0.
9. method described in one of -7 according to claim 1, which is characterized in that the sensor by manipulation device collects
Analog signal be converted into digital signal, comprising: use fuzzy control, be arranged according to the size of signal value on manipulation device different
Discrete signal value, obtain the corresponding relationship of the displacement variable of discrete signal value and manipulation device.
10. according to the method described in claim 9, it is characterized in that, real-time acquisition driver's EEG signals, and according to upper
Convergence analysis is stated as a result, predicting the driving intention of driver, auxiliary control is carried out to vehicle control device, comprising: according to above-mentioned
Obtained convergence analysis obtains corresponding vehicle as a result, the EEG signals of collected driver are translated by incubation period
The response signal of manipulation device, and adjusted by the response time of vehicle control device response signal and signal value size to vehicle
The controlling extent of manipulation device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811634944.9A CN109658503B (en) | 2018-12-29 | 2018-12-29 | Driver behavior intention detection method fused with electroencephalogram signals |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811634944.9A CN109658503B (en) | 2018-12-29 | 2018-12-29 | Driver behavior intention detection method fused with electroencephalogram signals |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109658503A true CN109658503A (en) | 2019-04-19 |
CN109658503B CN109658503B (en) | 2020-07-28 |
Family
ID=66117006
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811634944.9A Active CN109658503B (en) | 2018-12-29 | 2018-12-29 | Driver behavior intention detection method fused with electroencephalogram signals |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109658503B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112905001A (en) * | 2021-01-19 | 2021-06-04 | 武汉理工大学 | Driving sound mode switching method and system based on electroencephalogram signals |
CN113940688A (en) * | 2021-10-21 | 2022-01-18 | 北京理工大学 | Driving emergency steering intention detection method fusing friction nano generator and electroencephalogram |
CN114312819A (en) * | 2022-03-09 | 2022-04-12 | 武汉理工大学 | Brain heuristic type automatic driving assistance system and method based on capsule neural network |
CN117195082A (en) * | 2023-11-08 | 2023-12-08 | 清华大学 | Driving behavior prediction method and device |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101002686A (en) * | 2007-01-23 | 2007-07-25 | 武汉理工大学 | Analysis testing system for fatigue state of driver's fatigue based on driving simulator |
CN105468138A (en) * | 2015-07-15 | 2016-04-06 | 武汉理工大学 | Intelligent vehicle obstacle avoidance and navigation method based on brain-computer interface technology and lidar |
CN106937869A (en) * | 2017-04-06 | 2017-07-11 | 吴涛 | Driver's biology electroanalysis experimental system under brake hard operating mode based on Virtual Driving Platform |
JP2018016248A (en) * | 2016-07-29 | 2018-02-01 | 日産自動車株式会社 | Brake control method and brake control device |
CN108491071A (en) * | 2018-03-05 | 2018-09-04 | 东南大学 | A kind of brain control vehicle Compliance control method based on fuzzy control |
CN108693973A (en) * | 2018-04-17 | 2018-10-23 | 北京理工大学 | A kind of emergency detecting system of fusion EEG signals and environmental information |
CN108711204A (en) * | 2018-05-18 | 2018-10-26 | 长安大学 | A kind of the driving abnormality detection system and method for comprehensive people-Che-road multi-source information |
JP2018192909A (en) * | 2017-05-17 | 2018-12-06 | 日産自動車株式会社 | Behavior prediction method and behavior prediction device |
CN109035960A (en) * | 2018-06-15 | 2018-12-18 | 吉林大学 | Driver's driving mode analysis system and analysis method based on simulation driving platform |
-
2018
- 2018-12-29 CN CN201811634944.9A patent/CN109658503B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101002686A (en) * | 2007-01-23 | 2007-07-25 | 武汉理工大学 | Analysis testing system for fatigue state of driver's fatigue based on driving simulator |
CN105468138A (en) * | 2015-07-15 | 2016-04-06 | 武汉理工大学 | Intelligent vehicle obstacle avoidance and navigation method based on brain-computer interface technology and lidar |
JP2018016248A (en) * | 2016-07-29 | 2018-02-01 | 日産自動車株式会社 | Brake control method and brake control device |
CN106937869A (en) * | 2017-04-06 | 2017-07-11 | 吴涛 | Driver's biology electroanalysis experimental system under brake hard operating mode based on Virtual Driving Platform |
JP2018192909A (en) * | 2017-05-17 | 2018-12-06 | 日産自動車株式会社 | Behavior prediction method and behavior prediction device |
CN108491071A (en) * | 2018-03-05 | 2018-09-04 | 东南大学 | A kind of brain control vehicle Compliance control method based on fuzzy control |
CN108693973A (en) * | 2018-04-17 | 2018-10-23 | 北京理工大学 | A kind of emergency detecting system of fusion EEG signals and environmental information |
CN108711204A (en) * | 2018-05-18 | 2018-10-26 | 长安大学 | A kind of the driving abnormality detection system and method for comprehensive people-Che-road multi-source information |
CN109035960A (en) * | 2018-06-15 | 2018-12-18 | 吉林大学 | Driver's driving mode analysis system and analysis method based on simulation driving platform |
Non-Patent Citations (4)
Title |
---|
IL-HWA KIM等: "Detection of braking intention in diverse situations during simulated driving based on EEG feature combination", 《JOURNAL OF NEURAL ENGINEERING》 * |
LIU YANG等: "Exploring the relationship between electroencephalography(EEG) and ordinary driving behavior: A simulated driving study", 《TRANSPORTATION RESEARCH RECORD JOURNAL OF THE TRANSPORTATION RESEARCH BORAD》 * |
何莎: "驾驶员在无信号交叉口避撞过程中脑电行为特征研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
陈瑞雅: "模拟驾驶环境下驾驶员反应抑制能力及其脑电机制研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112905001A (en) * | 2021-01-19 | 2021-06-04 | 武汉理工大学 | Driving sound mode switching method and system based on electroencephalogram signals |
CN112905001B (en) * | 2021-01-19 | 2022-08-16 | 武汉理工大学 | Driving sound mode switching method and system based on electroencephalogram signals |
CN113940688A (en) * | 2021-10-21 | 2022-01-18 | 北京理工大学 | Driving emergency steering intention detection method fusing friction nano generator and electroencephalogram |
CN113940688B (en) * | 2021-10-21 | 2022-05-17 | 北京理工大学 | Driving emergency steering intention detection method fusing friction nano generator and electroencephalogram |
CN114312819A (en) * | 2022-03-09 | 2022-04-12 | 武汉理工大学 | Brain heuristic type automatic driving assistance system and method based on capsule neural network |
CN114312819B (en) * | 2022-03-09 | 2022-06-28 | 武汉理工大学 | Brain heuristic type automatic driving assistance system and method based on capsule neural network |
CN117195082A (en) * | 2023-11-08 | 2023-12-08 | 清华大学 | Driving behavior prediction method and device |
CN117195082B (en) * | 2023-11-08 | 2024-02-06 | 清华大学 | Driving behavior prediction method and device |
Also Published As
Publication number | Publication date |
---|---|
CN109658503B (en) | 2020-07-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109658503A (en) | A kind of driving behavior intention detection method merging EEG signals | |
CN101947152B (en) | Electroencephalogram-voice control system and working method of humanoid artificial limb | |
CN108615110B (en) | Driving risk assessment system based on visual characteristics | |
CN104083258B (en) | A kind of method for controlling intelligent wheelchair based on brain-computer interface and automatic Pilot technology | |
CN103679203B (en) | Robot system and method for detecting human face and recognizing emotion | |
CN108694367A (en) | A kind of method for building up of driving behavior model, device and system | |
CN108693973A (en) | A kind of emergency detecting system of fusion EEG signals and environmental information | |
CN102331782B (en) | Automatic vehicle controlling method with multi-mode brain-computer interface | |
CN109770923A (en) | A kind of driving fatigue detection method based on PGC demodulation value building brain function network | |
CN109636924A (en) | Vehicle multi-mode formula augmented reality system based on real traffic information three-dimensional modeling | |
CN109875583B (en) | Fatigue driving detection system and method based on AR technology | |
CN109035960A (en) | Driver's driving mode analysis system and analysis method based on simulation driving platform | |
CN103198616A (en) | Method and system for detecting fatigue driving based on head and neck movement feature recognition of driver | |
CN109658519A (en) | Vehicle multi-mode formula augmented reality system based on real traffic information image procossing | |
CN107480716A (en) | A kind of combination EOG and video pan signal recognition method and system | |
CN113743471A (en) | Driving evaluation method and system | |
CN110930811B (en) | System suitable for unmanned decision learning and training | |
CN113602287B (en) | Man-machine co-driving system for drivers with low driving ages | |
CN113128295A (en) | Method and device for identifying dangerous driving state of vehicle driver | |
CN113647956A (en) | Automatic driving automobile comfort level test evaluation method and system based on automatic driving robot | |
CN113064490B (en) | Eye movement track-based virtual enhancement equipment identification method | |
Zhang et al. | A brain-controlled vehicle system based on steady state visual evoked potentials | |
CN111818322A (en) | Immersive pedestrian traffic behavior experiment platform and method based on virtual reality technology | |
CN104181819B (en) | Human brain attention assessment system and car mould driving environment thereof under drive simulating environment | |
CN107168313A (en) | Control the method and device of vehicle drive |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |