CN105584479B - A kind of model predictive control method towards brain control vehicle and the brain control vehicle using this method - Google Patents
A kind of model predictive control method towards brain control vehicle and the brain control vehicle using this method Download PDFInfo
- Publication number
- CN105584479B CN105584479B CN201610030979.6A CN201610030979A CN105584479B CN 105584479 B CN105584479 B CN 105584479B CN 201610030979 A CN201610030979 A CN 201610030979A CN 105584479 B CN105584479 B CN 105584479B
- Authority
- CN
- China
- Prior art keywords
- control
- brain
- vehicle
- brain control
- model
- 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
Classifications
-
- 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
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/02—Control of vehicle driving stability
-
- 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
- B60W40/02—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 ambient conditions
-
- 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
-
- 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
- B60W40/10—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 vehicle motion
Abstract
The present invention provides a kind of model predictive control method towards brain control vehicle and the brain control vehicle using this method.The method of the present invention makes the actual steering wheel corner tracking brain control driver that controller exports pass through the desired orientation disk corner of brain-computer interface and interface model output, and keep the manipulation stationarity during entire control under the premise of ensureing brain control vehicle safety.It can ensure brain control drive safety using the brain control vehicle of this method, implement auxiliary control focusing on people, ensure the manipulation stationarity that brain control drives.
Description
Technical field
The present invention relates to a kind of model predictive control method towards brain control vehicle and with the brain of the ancillary control function
Control vehicle.Specifically, the method for the present invention under the premise of ensureing brain control vehicle safety, makes the actual steering wheel that controller exports
Corner tracks the desired orientation disk corner that brain control driver is exported by brain-computer interface and interface model, and keeps entire control
Manipulation stationarity in the process.On the one hand, the present invention is directed to improve the drive safety of brain control vehicle, manipulation stability;It is another
Aspect, the present invention is directed to develop auxiliary control method focusing on people.The method of the present invention belongs to field of human-computer interaction, vehicle work
The integrated application in journey field, information technology field and automation field.
Background technology
For the patient that limb motion is limited, the forfeiture of locomotivity becomes the puzzlement of these patients.Brain
The appearance of machine interface (BCI) is effectively increased the moving range and self-care ability of these patients.Brain-computer interface can be people's
A kind of direct information interchange channel is established between brain and external equipment (such as computer, intelligent wheel chair and intelligent vehicle),
The intention of people directly can be transmitted to external control unit outside by brain.Brain-computer interface technology has been widely used in brain
Control artificial limb, brain man-controlled mobile robot, brain control wheelchair, brain control browsing webpage and brain control vehicle etc. fields.
Brain control vehicle refers to the laterally and longitudinally movement that brain control driver directly controls vehicle with brain by brain-computer interface.
On the one hand, the appearance of manned mobile device of the vehicle as a high-speed cruising, brain control vehicle has greatly expanded limb motion
The activity space and self-care ability of limited users;On the other hand, the appearance of brain control vehicle provides a kind of different for normal users
In the novel drive manner that tradition drives.
Existing brain control Vehicular system is in initial development stage, the performance of drive safety and manipulation stability etc.
It is not good enough.Demand in view of brain control driver to safety and comfort, as manned mobile device, brain control vehicle is answered
This has higher drive safety and manipulation stability.In brain control Vehicular system, key technology be brain-computer interface technology and
Aided control technology.Therefore, on the one hand the performance of brain control Vehicular system can be improved by improving brain-computer interface technology;It is another
Aspect can improve the performance of brain control Vehicular system by increasing aided control technology.
Brain-computer interface technology is generally divided into five parts:Signal behavior, obtain signal, preprocessed signal, feature extraction and
Classification.In order to improve brain-computer interface technology, existing research has done prodigious effort at this five aspects.But on the one hand due to
The unstable essence of EEG signals, on the other hand since brain machine interface system can only export the discrete command of finite number, brain machine
The development of interfacing is still difficult to reach desirable level.In existing brain control Vehicular system, existing brain machine is relied on merely
Interfacing brain control driving can not obtain preferable drive safety and manipulation stability.Therefore, existing brain control is improved
The development of Vehicular system performance, another key technology (aided control technology) of brain control Vehicular system is most important.Model is pre-
The control technology aided control technology important as one is surveyed, the masty Multivariable Constrained of traditional PID control can be solved
Optimal Control Problem.In this context, the present invention proposes a kind of model predictive control method towards brain control vehicle.Meanwhile
The present invention proposes a kind of brain control vehicle using this method.
Invention content
The purpose of control method is to make the reality of controller output under the premise of ensureing brain control vehicle safety in the present invention
Steering wheel angle tracks the desired orientation disk corner that brain control driver is exported by brain-computer interface and interface model, and keeps whole
Control stationarity during a control.
The cost function that the present invention solves belt restraining by rolling optimization finds the method for Optimal Control output to realize this
The purpose of invention.It specifically refers to, at every sampling moment, according to the metrical information currently acquired, online solution one carries
The finite time-domain open loop optimization problem of constraint, and by first control signal function of obtained control sequence in controlled device.
In next sampling instant, repeat the above process:Above-mentioned optimization problem is solved again with new metrical information, and will be new
First control signal function of control sequence is in controlled device.Wherein, metrical information is vehicle-state and environmental information;It is controlled
Object is the brain control vehicle of the present invention;It is steering wheel angle to control signal (exporting).Vehicle-state can through the invention in
The internal sensor of brain control vehicle obtains, and environmental information can be obtained by the environmental sensor of brain control vehicle.
In the present invention, optimization object function includes two:One is prediction output and brain control driver's desired output
Accumulated error, another is the accumulated value for predicting output increment.Correspondingly, one meaning is the reality for making controller export
Steering wheel angle tracks the desired orientation disk corner that brain control driver is exported by brain-computer interface and interface model, the meaning of another
Justice is the control stationarity during keeping entirely controlling.Each has corresponding weighted factor to optimization object function, passes through
Adjustment weighted factor can change corresponding entry and correspond to significance level of the meaning in optimization.In the present invention, the pact of optimization problem
Beam includes dynamics of vehicle constraint, output constraint and security constraint.In order to realize that accurate prediction, dynamics of vehicle constraint are wanted
Prediction model is asked to meet the kinetic characteristics of vehicle.Executing agency's electricity is inputed to since model predictive controller will control signal
Machine, therefore should consider that the size of output can be limited in defined by the input limitation of motor and frequency band limitation, output constraint
In threshold value.In order to ensure that the safety of brain control driving, security constraint require vehicle that cannot exceed defined road in the process of moving
Boundary.
A kind of another aspect of the present invention, it is proposed that brain control vehicle with the method for the present invention.Combining environmental sensor, vehicle
Internal sensor and model predictive control technique, brain control vehicle of the invention have the auxiliary control work(driven towards brain control
Energy.
Description of the drawings
Fig. 1 is the brain control vehicle supplementary controlled system block diagram of the present invention.
Fig. 2 is the model predictive control method implementation flow chart of the present invention.
Specific implementation mode
The model predictive control method towards brain control vehicle is described in detail with reference to the accompanying drawings, the present invention is carried out further
Explanation.
Fig. 1 is the brain control vehicle supplementary controlled system block diagram of the present invention.
As shown in Figure 1, when carrying out brain control driving, brain control driver carries out according to current road information and vehicle-state
Control decision, decision go out corresponding driving intention.The state of vehicle includes the yaw angle of vehicle, lateral coordinate, longitudinal coordinate, side
To speed, longitudinal velocity, side acceleration and longitudinal acceleration, road information includes the boundary information and road curvature of road.
Brain control driver stares at corresponding stimulation (or the corresponding Mental imagery carried out), generates corresponding according to the driving intention of oneself
EEG signals.Brain-computer interface obtains the driving intention of driver, exports corresponding identification control life by parsing EEG signals
It enables.Interface model by the BCI control commands of identification (turn left, non-control and right-hand rotation) conversion in order to control steering wheel angle increment (-
10 °, 0 ° and 10 °), it acts on the steering wheel angle of last moment, obtains current desired steering wheel angle and define
The maximum value of steering wheel angle is 100 °.It is shown below:
α (n)=min | α (n-1)+Δ α × l (n) |, αmax},
L (n) ∈ [- 1,0,1], Δ α=10 °, (1)
α (0)=0 °, αmax=100 °, n >=1
Wherein, l (n) is the discrete control command for being input to interface model, and -1,0 and 1 respectively represents left-hand rotation, non-control and the right side
The control command turned, α (n) and α (n-1) indicate the steering wheel angle at n moment and n-1 moment respectively, steering wheel angle it is initial
Value is 0 °, and Δ α is the controlling increment of steering wheel angle, αmaxIt is the maximum value of steering wheel angle.The steering wheel of interface model output
Corner, that is, brain control driver is expected that by the steering wheel angle of brain-computer interface output.Model predictive controller passes through environmental sensor
A certain range of road information and car status information are obtained with term vehicle internal sensors.According to road information, the vehicle detected
State and the desired orientation disk corner of input, model predictive controller combination prediction model (auto model) judge that vehicle exists
Within the scope of prediction level whether in security restriction condition.If vehicle is in a safe condition within the scope of prediction level,
The expectation of the output tracking brain control driver of model predictive controller inputs and ensures the manipulation stationarity of vehicle;If vehicle
In the hole within the scope of prediction level, correction of the model predictive controller to steering wheel angle ensures first after correcting
Actual steering wheel corner keep vehicle in a safe condition within the scope of prediction level, next makes actual steering wheel angle as possible
Desired direction corner is tracked, and ensures the manipulation stationarity of vehicle as possible.Specific realization process this specification of correcting will combine
Fig. 2 is introduced.
Interface model, model predictive controller combination microcontroller are dissolved into brain control vehicle by another aspect of the present invention.
That is, the control command that Fig. 1 midbrain control drivers are exported by BCI is directly defeated by brain control vehicle, connecing in brain control vehicle
Mouth mold type converts control command to corresponding desired orientation disk corner and is input in model predictive controller, Model Predictive Control
The vehicle-state that the environmental information and term vehicle internal sensors that device combining environmental sensor obtains obtain, turns desired steering wheel
Angle is handled, then carries out actual control to brain control vehicle.
Fig. 2 is the model predictive control method implementation flow chart of the present invention.
As shown in Fig. 2, the specific implementation of model predictive control method includes the following steps in the present invention.
In step 201, the work connection status of each component and sensor is first detected, then begins to use Model Predictive Control
Device carries out auxiliary control to brain control vehicle.Before beginning to use, need to be detected the working condition of vehicle part, simultaneously
Detect each sensor (for example, environmental sensor and term vehicle internal sensors for being installed on vehicle) whether normal work
Make.After inspection finishes, the model interface and involvement mould that are designed the interface of each sensor and the present invention by A/D conversion modules
The controller (for example, microcontroller) of type PREDICTIVE CONTROL function is connected, by controller with external driving motor (for example, turning to electricity
Machine, speed electric motor etc.) connection, to realize the final control to brain control vehicle.In the present invention, the output of each sensor is with mould
Input of the output of type interface as controller.
In step 202, clock, sensor and controller are initialized.Forbid interrupting in initialization procedure, when initialization
Clock so that starting for each sensor is synchronous with the holding of the enabling time of controller using the time.Remove each sensor and controller
The input/output port and register of controller is arranged in interior data.How to initialize these sensors and controller belongs to ability
The common knowledge in domain, so will omit herein to the specific descriptions how to initialize.
In step 203, the dynamic scan of turn on sensor allows to interrupt.Environmental sensor dynamic scan environmental information,
To obtain the environmental information within the scope of model predictive controller prediction level (i.e. road boundary information).Term vehicle internal sensors
Detect and record brain control vehicle state parameter (including yaw angle, lateral coordinate, longitudinal coordinate, side velocity, longitudinal velocity,
Side acceleration and longitudinal acceleration etc.).Allow scanning by other events (for example, sensor fault etc.) in scanning process
It is disconnected.Here, it is desirable that the sampling time of sensor dynamic scan is less than the sampling time of model predictive controller.
In step 204, environmental sensor and term vehicle internal sensors are communicated with model predictive controller.Pass through ring
Border sensor and term vehicle internal sensors obtain environmental information and car status information, then by environmental information and car status information
It is input in model predictive controller.In entire detection and communication process, it is provided in model predictive controller corresponding
Memory headroom storage unit, with the environmental information of storage model predictive controller prediction level range and current and history vehicle
Status information.
In step 205, constrained quadratic programming problem is solved.In the Model Predictive Control Algorithm that the present invention designs
Optimization problem is the quadratic programming problem of a belt restraining.The Model Predictive Control Algorithm that the present invention designs is specifically described below.
The mathematical form of model predictive control method is as follows:
Subject to x (k+1+i | k)=Adx(k+i|k)+Bdu(k+i)+B′dw(k+i) (2b)
Y (k+1+i | k)=Cdx(k+1+i|k) (2c)
umin≤u(k+i)≤umax, i=0 ... Np-1 (2d)
Δ u (k+i)=u (k+i)-u (k+i-1) (2e)
Δ u (k+i)=0, i=Nc…Np (2f)
emin≤ey≤emax (2g)
Wherein, (2a) formula represents the majorized function of model predictive control method of the present invention, and (2b)~(2g) formulas represent Ben Fa
The constraint of bright model predictive control method.
In (2a) formula, k indicates current time, NPIndicate the prediction level of model predictive controller, NCIndicate model prediction
The controlled level of controller, u (k) indicate that the steering wheel angle sequence of model predictive controller optimization output, u ' (k) indicate brain control
The desired orientation disk corner sequence that driver is exported by BCI, Δ u (k) indicate the increment of prediction output.First item in (2a) formula
Optimization aim be to minimize prediction output and the accumulated error of brain control driver's desired output, its significance lies in that making controller
The actual steering wheel of output tracks the desired orientation disk corner that brain control driver is exported by brain-computer interface and interface model as possible,
Embody auxiliary control thought focusing on people.The optimization aim of Section 2 is to minimize prediction output increment in (2a) formula
Accumulated value, its significance lies in that keeping the control stationarity during entire control as possible.a1And a2For weighted factor, pass through tune
The numerical value of whole weighted factor can change corresponding entry and correspond to significance level of the meaning in optimization.
The state-space expression of (2b) and (2c) formula represents the Dynamic Constraints of prediction model.The prediction that the present invention uses
Model is road vehicle model.In formula, k+i | k indicates prediction of the k moment to the k+1 moment;Meet " | " subsequent k and indicates current
Moment is k.The state variable x (k) of prediction model=[vy(k) ω(k) ey(k) eψ(k)]T, including the side velocity of vehicle,
The heading angle deviation relative to road curvature of lateral deviation and vehicle of yaw velocity, vehicle relative to road boundary, u (k)
For the sale at reduced prices corner of input prediction model, w (k) is the road curvature obtained according to environmental information and road boundary information, y (k)
For the output of prediction model.BdWith B 'dFor input matrix, AdFor state matrix, CdFor output matrix.
The output constraint of (2d), (2e) and (2f) formula representative model predictive controller.In practical applications, since model is pre-
It surveys controller and inputs to executing agency's (motor) by signal is controlled, therefore should consider input limitation and the frequency band limitation of motor.
(2d) formula limits the extreme value of outbound course disk corner.Output increment is defined as current output valve with before (2e) formula
The difference of the output valve at one moment.(2f) indicates that except the control time domain of model predictive controller, controlling increment remains unchanged.
(2g) formula indicates the security constraint of Model Predictive Control.In order to ensure the safety driven, examined according to environmental sensor
The road information measured, it is desirable that brain control vehicle cannot exceed the boundary of road in the process of moving.
In step 206, judge whether quadratic programming problem has solution.If quadratic programming problem has solution, then follow the steps
208, if without solution, then follow the steps 207.
In step 207, failed controller otherwise processed.This step, brain control vehicle are executed when quadratic programming problem is without solution
Pause receive brain control driver control command and stop motion, then so that vehicle is returned in road by autocontrol method
Between position, then re-start initialization, start the control command for receiving brain control driver, auxiliary control is carried out to brain control driving..
In a step 208, effective controlling increment is obtained.ΔU*(k) it is to be solved by quadratic programming problem at current time
Optimal control sequence.According to the rolling optimization principle of Model Predictive Control, first controlling increment of control sequence is obtained.
In step 209, the controlling increment that previous step obtains is acted on into brain control vehicle.Previous step has been taken out optimal
First control signal in control sequence, the control signal function that this step takes out previous step in controlled device, and
In next sampling instant, step 204~209 are repeated, with new metrical information and new brain control driver's control command to upper
It states optimization problem to be solved again, and by first control signal function of new control sequence in controlled device.
As described above, interface model and model predictive controller by merging the present invention, combining environmental sensor and vehicle
Internal sensor, brain control vehicle of the invention have the ancillary control function driven towards brain control.The ancillary control function body
Following three aspects now:1) ensure brain control drive safety, that is, ensure that brain control vehicle does not go out road boundary;2) implement taking human as
The auxiliary at center controls, i.e., follows the intention of people as far as possible during auxiliary control;3) ensure that the manipulation that brain control drives is steady
Property.
Claims (9)
1. a kind of model predictive control method towards brain control vehicle, which is characterized in that solve belt restraining by rolling optimization
Cost function finds the method for Optimal Control output to realize under the premise of ensureing brain control vehicle safety, and controller is made to export
Actual steering wheel corner tracks the desired orientation disk corner that brain control driver is exported by brain-computer interface and interface model, and protects
Hold the manipulation stationarity during entire control;Wherein optimization object function includes two:One is that prediction output is driven with brain control
The accumulated error of the person's of sailing desired output, another is the accumulated value for predicting output increment;The constraint of optimization problem is dynamic including vehicle
Mechanics constraint, output constraint and security constraint.
2. according to the method described in claim 1, wherein, ensureing brain control vehicle by the security constraint of Model Predictive Control Algorithm
Safety.
3. according to the method described in claim 1, wherein, in the majorized function of Model Predictive Control Algorithm, minimizing prediction
The accumulated error of output and brain control driver's desired output, the actual steering wheel corner tracking brain control driver for making controller export
The desired orientation disk corner exported by brain-computer interface and interface model.
4. according to the method described in claim 1, wherein, in the majorized function of Model Predictive Control Algorithm, minimizing prediction
The accumulated value of output increment keeps the manipulation stationarity during entire control.
5. according to the method described in claim 1, wherein, the prediction model of model predictive control method is road vehicle model,
Its state-space expression embodies in the Dynamic Constraints of Model Predictive Control Algorithm.
6. according to the method described in claim 1, wherein, the step of interface model obtains current desired steering wheel angle, wraps
It includes:
By the BCI control commands of identification (turn left, non-control and right-hand rotation) conversion in order to control steering wheel angle increment (- 10 °, 0 ° and
10 °), it acts on the steering wheel angle of last moment, and the maximum value for limiting steering wheel angle finally obtains current as 100 °
Desired steering wheel angle.
7. according to the method described in claim 1, wherein, when Model Predictive Control Algorithm is without solution, the step of otherwise processed, includes:
The pause of brain control vehicle receives control command and the stop motion of brain control driver, then makes vehicle by autocontrol method
Road centre position is returned to, then re-starts initialization, starts the control command for receiving brain control driver, brain control is driven and is carried out
Auxiliary control.
8. according to the method described in claim 5, wherein, passing through the road curvature and road boundary information of environmental sensor acquisition
It is input in road vehicle model.
9. a kind of brain control vehicle using any one of claim 1-8 methods, the brain control vehicle ensures brain control driving safety
Property, implement auxiliary control focusing on people, ensures the manipulation stationarity that brain control drives.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610030979.6A CN105584479B (en) | 2016-01-18 | 2016-01-18 | A kind of model predictive control method towards brain control vehicle and the brain control vehicle using this method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610030979.6A CN105584479B (en) | 2016-01-18 | 2016-01-18 | A kind of model predictive control method towards brain control vehicle and the brain control vehicle using this method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105584479A CN105584479A (en) | 2016-05-18 |
CN105584479B true CN105584479B (en) | 2018-10-19 |
Family
ID=55924475
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610030979.6A Active CN105584479B (en) | 2016-01-18 | 2016-01-18 | A kind of model predictive control method towards brain control vehicle and the brain control vehicle using this method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105584479B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101876051B1 (en) * | 2016-08-31 | 2018-08-02 | 현대자동차주식회사 | Machine learning system and method for learning user controlling pattern thereof |
US11814073B2 (en) * | 2020-03-18 | 2023-11-14 | Baidu Usa Llc | Learning based controller for autonomous driving |
CN111258323B (en) * | 2020-03-30 | 2021-10-26 | 华南理工大学 | Intelligent vehicle trajectory planning and tracking combined control method |
CN112051780B (en) * | 2020-09-16 | 2022-05-17 | 北京理工大学 | Brain-computer interface-based mobile robot formation control system and method |
CN114089628B (en) * | 2021-10-25 | 2022-11-04 | 西北工业大学 | Brain-driven mobile robot control system and method based on steady-state visual stimulation |
CN114103974B (en) * | 2021-11-01 | 2022-07-29 | 北京理工大学 | Brain-computer interface method for vehicle continuous control |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102076541A (en) * | 2008-06-20 | 2011-05-25 | 通用汽车环球科技运作公司 | Path generation algorithm for automated lane centering and lane changing control system |
CN102788704A (en) * | 2012-06-29 | 2012-11-21 | 北京理工大学 | Automobile operation stability testing system based on driver model and testing method |
CN103204162A (en) * | 2012-01-11 | 2013-07-17 | 通用汽车环球科技运作有限责任公司 | Lane Tracking System With Active Rear-steer |
CN104462716A (en) * | 2014-12-23 | 2015-03-25 | 北京理工大学 | Method for designing brain-computer interface parameters and kinetic parameters of brain controlled vehicle based on human-vehicle-road model |
US9227632B1 (en) * | 2014-08-29 | 2016-01-05 | GM Global Technology Operations LLC | Method of path planning for evasive steering maneuver |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9428187B2 (en) * | 2014-06-05 | 2016-08-30 | GM Global Technology Operations LLC | Lane change path planning algorithm for autonomous driving vehicle |
-
2016
- 2016-01-18 CN CN201610030979.6A patent/CN105584479B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102076541A (en) * | 2008-06-20 | 2011-05-25 | 通用汽车环球科技运作公司 | Path generation algorithm for automated lane centering and lane changing control system |
CN103204162A (en) * | 2012-01-11 | 2013-07-17 | 通用汽车环球科技运作有限责任公司 | Lane Tracking System With Active Rear-steer |
CN102788704A (en) * | 2012-06-29 | 2012-11-21 | 北京理工大学 | Automobile operation stability testing system based on driver model and testing method |
US9227632B1 (en) * | 2014-08-29 | 2016-01-05 | GM Global Technology Operations LLC | Method of path planning for evasive steering maneuver |
CN104462716A (en) * | 2014-12-23 | 2015-03-25 | 北京理工大学 | Method for designing brain-computer interface parameters and kinetic parameters of brain controlled vehicle based on human-vehicle-road model |
Also Published As
Publication number | Publication date |
---|---|
CN105584479A (en) | 2016-05-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105584479B (en) | A kind of model predictive control method towards brain control vehicle and the brain control vehicle using this method | |
CN105667574B (en) | Self-adapting steering control system and its control method based on driving style | |
CN105329238B (en) | A kind of autonomous driving vehicle lane-change control method based on monocular vision | |
CN105741494B (en) | A kind of driver fatigue monitoring method based on Data Matching under line | |
CN104756398B (en) | Controller for motor and motor drive | |
CN107200020A (en) | It is a kind of based on mix theory pilotless automobile self-steering control system and method | |
CN106741137A (en) | A kind of personalized electric boosting steering system and control method | |
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 | |
CN108491071B (en) | Brain-controlled vehicle sharing control method based on fuzzy control | |
CN104950887A (en) | Transportation device based on robot vision system and independent tracking system | |
CN110525436A (en) | Vehicle lane-changing control method, device, vehicle and storage medium | |
CN103926839A (en) | Movement subdivision control method of wheeled mobile robot | |
CN108682119A (en) | Method for detecting fatigue state of driver based on smart mobile phone and smartwatch | |
CN113581209B (en) | Driving assistance mode switching method, device, equipment and storage medium | |
CN107215329A (en) | A kind of distributed-driving electric automobile lateral stability control method based on ATSM | |
CN112000087A (en) | Intent priority fuzzy fusion control method for brain-controlled vehicle | |
US20220050524A1 (en) | Analog driving feature control brain machine interface | |
CN109367620A (en) | A kind of Induction Control method of semi-trailer train straight line car-backing | |
CN206475931U (en) | A kind of personalized electric boosting steering system | |
CN109334451A (en) | The throttle autocontrol method of the vehicle in highway driving based on bi-fuzzy control | |
CN112034828A (en) | Discrete integral sliding mode control device and method of brain-controlled mobile robot | |
CN101544227A (en) | ABS double-mode control method for automobile | |
CN114089628B (en) | Brain-driven mobile robot control system and method based on steady-state visual stimulation | |
CN114323698B (en) | Real vehicle experiment platform testing method for man-machine co-driving intelligent vehicle | |
CN108871786A (en) | A kind of automatic driving vehicle semi-hardware type simulation test system and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |