CN105584479A - Computer-controlled vehicle-oriented model prediction control method and computer-controlled vehicle utilizing method - Google Patents

Computer-controlled vehicle-oriented model prediction control method and computer-controlled vehicle utilizing method Download PDF

Info

Publication number
CN105584479A
CN105584479A CN201610030979.6A CN201610030979A CN105584479A CN 105584479 A CN105584479 A CN 105584479A CN 201610030979 A CN201610030979 A CN 201610030979A CN 105584479 A CN105584479 A CN 105584479A
Authority
CN
China
Prior art keywords
control
brain
vehicle
model
computer
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
Application number
CN201610030979.6A
Other languages
Chinese (zh)
Other versions
CN105584479B (en
Inventor
毕路拯
陆赟
滕腾
王明涛
和福建
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Technology BIT
Original Assignee
Beijing Institute of Technology BIT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Institute of Technology BIT filed Critical Beijing Institute of Technology BIT
Priority to CN201610030979.6A priority Critical patent/CN105584479B/en
Publication of CN105584479A publication Critical patent/CN105584479A/en
Application granted granted Critical
Publication of CN105584479B publication Critical patent/CN105584479B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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 invention provides a computer-controlled vehicle-oriented model prediction control method and a computer-controlled vehicle utilizing the method. According to the method provided by the invention, on the premise that the safety of the computer-controlled vehicle is ensured, an actual steering wheel angle output by a controller tracks an expected steering wheel angle output by a computer-controlled driver through a computer interface and an interface model, and the control stability in the whole control process is kept. The computer-controlled vehicle utilizing the method can ensure computer-controlled driving safety, implement human-centered auxiliary control as well as ensure computer-controlled driving control stability.

Description

A kind of model predictive control method towards brain control vehicle and the brain control vehicle that utilizes the method
Technical field
The present invention relates to a kind of model predictive control method towards brain control vehicle and the brain with this ancillary control functionControl vehicle. Specifically, the inventive method is ensureing, under the prerequisite of brain control vehicle safety, to make the actual steering wheel of controller outputCorner is followed the tracks of brain control driver by the desired orientation dish corner of brain-computer interface and interface model output, and keeps whole controlManipulation stationarity in process. On the one hand, the present invention is intended to improve drive safety, the manipulation stability of brain control vehicle; AnotherAspect, the present invention is intended to develop auxiliary control method focusing on people. The inventive method belongs to field of human-computer interaction, vehicle workThe integrated application of journey field, areas of information technology and automation field.
Background technology
For the limited patient of limb motion, the forfeiture of locomotivity becomes these patients' a puzzlement. BrainThe appearance of machine interface (BCI) has effectively increased these patients' moving range and self-care ability. Brain-computer interface can be people'sFor example, between brain and external equipment (computer, intelligent wheel chair and intelligent vehicle), set up a kind of directly information interchange passage,People's intention directly can be delivered to external control unit by brain. Brain-computer interface technology has been widely used in brainThe fields such as control artificial limb, brain man-controlled mobile robot, brain control wheelchair, brain control browsing page and brain control vehicle.
Brain control vehicle refer to brain control driver directly with brain by side direction and the lengthwise movement of brain-computer interface control vehicle.On the one hand, vehicle is as the manned mobile device of a high-speed cruising, the appearance of the brain control vehicle limb motion that increased greatlyThe activity space of limited users and self-care ability; On the other hand, the normal users that appears as of brain control vehicle provides a kind of differentThe novel drive manner of driving in tradition.
Existing brain control Vehicular system is in the initial development stage, the performance of the aspects such as drive safety and manipulation stabilityGood not enough. Consider the demand of brain control driver to security and comfortableness, as manned mobile device, brain control vehicle shouldThis possesses higher drive safety and manipulation stability. In brain control Vehicular system, key technology be brain-computer interface technology andAided control technology. Therefore, can improve by improving brain-computer interface technology on the one hand the performance of brain control Vehicular system; AnotherAspect can improve by increasing aided control technology the performance of brain control Vehicular system.
Brain-computer interface technology is generally divided into five parts: signal select, obtain signal, preprocessed signal, feature extraction andClassification. In order to improve brain-computer interface technology, existing research has been done very large effort aspect these five. But on the one hand due toThe unsettled essence of EEG signals, the discrete command that can only export on the other hand limited number due to brain machine interface system, brain machineThe development of interfacing is still difficult to reach desirable level. In existing brain control Vehicular system, rely on merely existing brain machineThe control of interfacing brain is driven and can not be obtained good drive safety and manipulation stability. Therefore, improve existing brain controlVehicular system performance, the development of another key technology (aided control technology) of brain control Vehicular system is most important. Model is pre-Survey control technology as an important aided control technology, can solve the masty Multivariable Constrained of traditional PID controlOptimal Control Problem. Under this background, 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 that utilizes the method.
Summary of the invention
In the present invention, the object of control method is to ensure, under the prerequisite of brain control vehicle safety, to make the reality of controller outputSteering wheel angle is followed the tracks of brain control driver by the desired orientation dish corner of brain-computer interface and interface model output, and keeps wholeControl stationarity in individual control procedure.
The method that the present invention solves the cost function searching Optimal Control output of belt restraining by rolling optimization realizes thisThe object of invention. Specifically refer to, in each sampling instant, according to the metrical information of current collection, online solve one withThe finite time-domain open loop optimization problem of constraint, and first control signal of the control sequence obtaining is acted on to controlled device.In next sampling instant, repeat said process: above-mentioned optimization problem is solved again by new metrical information, and will be newlyFirst control signal of control sequence acts on controlled device. Wherein, metrical information is vehicle-state and environmental information; ControlledObject is brain control vehicle of the present invention; Control signal (i.e. output) is steering wheel angle. Vehicle-state can be by the present inventionThe internal sensor of brain control vehicle obtains, and environmental information can obtain by the environmental sensor of brain control vehicle.
In the present invention, optimization aim function comprises two: one is to predict output and brain control driver desired outputAccumulated error, another is the accumulated value of prediction output increment. Accordingly, the meaning of is to make the reality of controller outputSteering wheel angle is followed the tracks of brain control driver by the desired orientation dish corner of brain-computer interface and interface model output, the meaning of anotherJustice is to keep the control stationarity in whole control procedure. Every of optimization aim function has corresponding weighted factor, passes throughAdjust weighted factor and can change the significance level of the corresponding meaning of corresponding entry in optimization. In the present invention, the pact of optimization problemBundle comprises dynamics of vehicle constraint, output constraint and security constraint. In order to realize prediction more accurately, dynamics of vehicle constraint is wantedAsk forecast model to meet the dynamics of vehicle. Because control signal is inputed to executing agency's electricity by model predictive controllerMachine, therefore should consider that import-restriction and the frequency band limits of motor, output constraint can be limited in the size of output regulationIn threshold value. For the safety that ensures that brain control is driven, security constraint requires vehicle can not exceed in the process of moving the road of regulationBorder.
Another aspect of the present invention, has proposed a kind of brain control vehicle with the inventive method. Combining environmental sensor, carInternal sensor and model predictive control technique, brain control vehicle of the present invention has the auxiliary control merit of driving towards brain controlEnergy.
Brief description of the drawings
Fig. 1 is brain control vehicle supplementary controlled system block diagram of the present invention.
Fig. 2 is model predictive control method realization flow figure of the present invention.
Detailed description of the invention
Describe in detail with reference to the accompanying drawings towards the model predictive control method of brain control vehicle, the present invention is carried out furtherExplanation.
Fig. 1 is brain control vehicle supplementary controlled system block diagram of the present invention.
As shown in Figure 1, in the time carrying out brain control driving, brain control driver carries out according to current road information and vehicle-stateControl decision, decision-making goes out corresponding driving intention. The state of vehicle comprises yaw angle, side direction coordinate, along slope coordinate, the side of vehicleTo speed, longitudinal velocity, side acceleration and longitudinal acceleration, road information comprises boundary information and the road curvature of road.Brain control driver, according to the driving intention of oneself, stares at corresponding stimulation (or the corresponding motion imagination of carrying out), produces correspondingEEG signals. Brain-computer interface, by resolving EEG signals, obtains driver's driving intention, and life is controlled in the corresponding identification of outputOrder. Interface model by the BCI control command (turn left, non-control and right-hand rotation) of identification be converted into control steering wheel angle increment (10 °, 0 ° and 10 °), act on the steering wheel angle in a moment, obtain the steering wheel angle of current expectation and defineThe maximum of steering wheel angle is 100 °. Be shown below:
α(n)＝min{｜α(n-1)+Δα×l(n)｜,αmax},
l(n)∈[-1,0,1],Δα＝10°,(1)
α(0)＝0°,αmax＝100°,n≥1
Wherein, l (n) is for being input to the discrete control command of interface model, and-1,0 and 1 represents respectively, non-control and the right sideThe control command turning, α (n) and α (n-1) represent respectively the steering wheel angle in n moment and n-1 moment, steering wheel angle initialValue is 0 °, and Δ α is the controlling increment of steering wheel angle, αmaxIt is the maximum of steering wheel angle. The steering wheel of interface model outputCorner is that brain control driver expects the steering wheel angle of exporting by brain-computer interface. Model predictive controller passes through environmental sensorRoad information and car status information with term vehicle internal sensors acquisition certain limit. According to the road information detecting, carThe desired orientation dish corner of state and input, model predictive controller judges that in conjunction with forecast model (auto model) vehicle existsWithin the scope of prediction level whether in security limitations condition. If vehicle is in a safe condition within the scope of prediction level,The output tracking brain control driver's of model predictive controller expectation input and the manipulation stationarity of guarantee vehicle; If vehicleIn the hole within the scope of prediction level, the correction of model predictive controller to steering wheel angle, after first ensureing to correctActual steering wheel corner make vehicle in a safe condition within the scope of prediction level, next makes actual steering wheel angle as far as possibleFollow the tracks of the direction corner of expecting, and ensure the manipulation stationarity of vehicle as far as possible. Concrete correct this description of implementation procedure in connection withFig. 2 is introduced.
Another aspect of the present invention, is dissolved into interface model, model predictive controller in brain control vehicle in conjunction with single-chip microcomputer.That is to say, the control command that Fig. 1 midbrain control driver exports by BCI is directly defeated by brain control vehicle, connecing in brain control vehicleMouth model is converted into corresponding desired orientation dish corner by control command and is input in model predictive controller, Model Predictive ControlThe vehicle-state that the environmental information that device combining environmental sensor obtains and term vehicle internal sensors obtain, turns the steering wheel of expectingProcess at angle, then brain control vehicle is carried out to actual control.
Fig. 2 is model predictive control method realization flow figure of the present invention.
As shown in Figure 2, in the present invention, the specific implementation of model predictive control method comprises the following steps.
In step 201, first detect the work connection status of each parts and sensor, then bring into use Model Predictive ControlDevice is assisted control to brain control vehicle. Before bringing into use, need to detect the duty of vehicle part, simultaneouslyDetect the whether normal work of each sensor (for example, being arranged on environmental sensor and the term vehicle internal sensors on vehicle)Do. Check complete after, by A/D modular converter by the model interface of the interface of each sensor and the present invention design with incorporate mouldThe controller (for example, single-chip microcomputer) of type PREDICTIVE CONTROL function is connected, and controller and outside drive motors (for example, are turned to electricityMachine, speed motor etc.) connect, thus realize the final control to brain control vehicle. In the present invention, the output of each sensor is with mouldThe output of type interface is as the input of controller.
In step 202, initialize clock, sensor and controller. Disable interrupts in initialization procedure, when initializationClock, makes the enabling time that starts employing time and controller of each sensor keep synchronous. Remove each sensor and controllerIn data, input/output port and the register of controller are set. How to initialize these sensors and controller and belong to abilityThe common practise in territory, so will omit the initialized specific descriptions to how at this.
In step 203, the dynamic scan of turn on sensor, allows to interrupt. Environmental sensor dynamic scan environmental information,To obtain the environmental information (being road boundary information) within the scope of model predictive controller prediction level. Term vehicle internal sensorsDetect and record brain control vehicle state parameter (comprise yaw angle, side direction coordinate, along slope coordinate, side velocity, longitudinal velocity,Side acceleration and longitudinal acceleration etc.). In scanning process, allow scanning for example, by other events (, sensor fault etc.)Disconnected. Here require the sampling time of sensor dynamic scan to be less than the sampling time of model predictive controller.
In step 204, environmental sensor and term vehicle internal sensors and model predictive controller carry out communication. By ringBorder sensor and term vehicle internal sensors obtain environmental information and car status information, then by environmental information and car status informationBe input in model predictive controller. In whole detection and communication process, in model predictive controller, be provided with correspondingMemory headroom memory cell, with the environmental information of memory model predictive controller prediction level scope and current and historical carStatus information.
In step 205, solve constrained quadratic programming problem. In the Model Predictive Control Algorithm of the present invention's designOptimization problem is the quadratic programming problem of a belt restraining. Illustrate the Model Predictive Control Algorithm of the present invention's design below.The mathematical form of model predictive control method is as follows:
min i m i z e Σ k = 1 N C ( a 1 ( u ( k ) - u ′ ( k ) ) 2 + a 2 Δ u ( k ) 2 ) - - - ( 2 a )
subjecttox(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)
Δu(k+i)＝u(k+i)-u(k+i-1)(2e)
Δu(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, (2b)～and (2g) formula represents Ben FaThe constraint of bright model predictive control method.
In (2a) formula, k represents current time, NPRepresent the prediction level of model predictive controller, NCRepresent model predictionThe level of control of controller, u (k) represents the steering wheel angle sequence of model predictive controller optimization output, u ' (k) represents brain controlThe desired orientation dish corner sequence that driver exports by BCI, Δ u (k) represents the increment of prediction output. (2a) Section 1 in formulaOptimization aim be to minimize the accumulated error of prediction output and brain control driver desired output, its meaning is to make controllerThe actual steering wheel of output is followed the tracks of brain control driver by the desired orientation dish corner of brain-computer interface and interface model output as far as possible,Embody auxiliary control thought focusing on people. (2a) in formula, the optimization aim of Section 2 is to minimize prediction output incrementAccumulated value, its meaning is to keep the control stationarity in whole control procedure as far as possible. a1And a2For weighted factor, by adjustingThe numerical value of whole weighted factor can change the significance level of the corresponding meaning of corresponding entry in optimization.
(2b) and (2c) state-space expression of formula represents the Dynamic Constraints of forecast model. The prediction that the present invention usesModel is road vehicle model. In formula, k+i|k represents the prediction of k moment to the k+1 moment; Meeting " | " k below represents currentMoment is k. State variable x (k)=[v of forecast modely(k)ω(k)ey(k)eψ(k)]T, comprise vehicle side velocity,Yaw velocity, vehicle be the course angle deviation with respect to road curvature with respect to the lateral deviation of road boundary and vehicle, u (k)For the sale at reduced prices corner of input prediction model, w (k) is road curvature and the road boundary information obtaining according to environmental information, y (k)For the output of forecast model. BdAnd B 'dFor input matrix, AdFor state matrix, CdFor output matrix.
(2d), (2e) and (2f) output constraint of formula representative model predictive controller. In actual applications, because model is pre-Survey controller control signal is inputed to executing agency's (motor), therefore should consider import-restriction and the frequency band limits of motor.(2d) formula has limited the extreme value of outbound course dish corner. (2e) formula is defined output increment into current output valve and frontThe output valve in a moment poor. (2f) be illustrated in outside the control time domain of model predictive controller, controlling increment remains unchanged.
(2g) formula represents the security constraint of Model Predictive Control. For the safety that ensures to drive, examine according to environmental sensorThe road information measuring, requires brain control vehicle can not exceed in the process of moving the border of road.
In step 206, judge whether quadratic programming problem has solution. If quadratic programming problem has solution, execution step208, if without solution, perform step 207.
In step 207, failed controller otherwise processed. When quadratic programming problem is carried out this step, brain car controlling when separatingTime-out is accepted brain control driver's control command stop motion, then by autocontrol method, vehicle is got back in roadBetween position, then re-start initialization, start to accept brain control driver's control command, brain control is driven and is assisted control. .
In step 208, obtain effective controlling increment. Δ U*(k) solve by quadratic programming problem for current timeOptimal control sequence. According to the rolling optimization principle of Model Predictive Control, obtain first controlling increment of control sequence.
In step 209, the controlling increment that previous step is obtained acts on brain control vehicle. Previous step has been taken out optimumFirst control signal in control sequence, the control signal that this step is taken out previous step acts in controlled device, andIn next sampling instant, repeating step 204～209, by new metrical information and new brain control driver control command to upperState optimization problem and again solve, and first control signal of new control sequence is acted on to controlled device.
As mentioned above, by merging interface model of the present invention and model predictive controller, combining environmental sensor and carInternal sensor, brain control vehicle of the present invention has the ancillary control function of driving towards brain control. This ancillary control function bodyNow following three aspects: 1) ensure brain control drive safety, ensure that brain control vehicle does not go out road boundary; 2) implement with artificiallyPeople's intention is followed as far as possible in the auxiliary control at center in auxiliary control procedure; 3) manipulation that the control of guarantee brain is driven is steadyProperty.

Claims (9)

1. towards a model predictive control method for brain control vehicle, it is characterized in that, the method is ensureing brain control vehicle safetyPrerequisite under, make the actual steering wheel corner of controller output follow the tracks of brain control driver by brain-computer interface and interface model outputDesired orientation dish corner, and keep the manipulation stationarity in whole control procedure.
2. method according to claim 1, wherein, ensures brain control vehicle by the security constraint of Model Predictive Control AlgorithmSafety.
3. method according to claim 1, wherein, in the majorized function of Model Predictive Control Algorithm, minimizes predictionThe accumulated error of output and brain control driver desired output, makes the actual steering wheel corner of controller output follow the tracks of brain control driverBy the desired orientation dish corner of brain-computer interface and interface model output.
4. method according to claim 1, wherein, in the majorized function of Model Predictive Control Algorithm, minimizes predictionThe accumulated value of output increment, keeps the manipulation stationarity in whole control procedure.
5. method according to claim 1, wherein, the forecast 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. method according to claim 1, wherein, interface model obtains the step bag of the steering wheel angle of current expectationDraw together:
By the BCI control command (turn left, non-control and right-hand rotation) of identification be converted into control steering wheel angle increment (10 °, 0 ° and10 °), act on the steering wheel angle in a moment, and the maximum that limits steering wheel angle is 100 °, finally obtain currentThe steering wheel angle of expecting.
7. method according to claim 1, wherein, Model Predictive Control Algorithm without separate time, the step of otherwise processed comprises:
Brain control vehicle suspends control command the stop motion of accepting brain control driver, then makes vehicle by autocontrol methodGet back to road centre position, then re-start initialization, start to accept brain control driver's control command, brain control is driven and carried outAuxiliary control.
8. method according to claim 5, wherein, the road curvature obtaining by environmental sensor and road boundary informationBe input in road vehicle model.
9. utilize a brain control vehicle for the method for claim 1-8, described brain control vehicle exploitation right profit requires the method for 1-8 canTo ensure brain control drive safety, implement auxiliary control focusing on people, ensure the manipulation stationarity that brain control is driven.
CN201610030979.6A 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 Active CN105584479B (en)

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 true CN105584479A (en) 2016-05-18
CN105584479B 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)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107783528A (en) * 2016-08-31 2018-03-09 现代自动车株式会社 Machine learning system and its method for learning user's control pattern
CN111258323A (en) * 2020-03-30 2020-06-09 华南理工大学 Intelligent vehicle trajectory planning and tracking combined control method
CN112051780A (en) * 2020-09-16 2020-12-08 北京理工大学 Brain-computer interface-based mobile robot formation control system and method
CN113495559A (en) * 2020-03-18 2021-10-12 百度（美国）有限责任公司 Learning-based controller for autonomous driving
CN114089628A (en) * 2021-10-25 2022-02-25 西北工业大学 Brain-driven mobile robot control system and method based on steady-state visual stimulation
CN114103974A (en) * 2021-11-01 2022-03-01 北京理工大学 Brain-computer interface method for vehicle continuous control

Citations (6)

* Cited by examiner, † Cited by third party
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
US20150353085A1 (en) * 2014-06-05 2015-12-10 GM Global Technology Operations LLC Lane change path planning algorithm for autonomous driving vehicle
US9227632B1 (en) * 2014-08-29 2016-01-05 GM Global Technology Operations LLC Method of path planning for evasive steering maneuver

Patent Citations (6)

* Cited by examiner, † Cited by third party
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
US20150353085A1 (en) * 2014-06-05 2015-12-10 GM Global Technology Operations LLC Lane change path planning algorithm for autonomous driving vehicle
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

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107783528A (en) * 2016-08-31 2018-03-09 现代自动车株式会社 Machine learning system and its method for learning user's control pattern
CN107783528B (en) * 2016-08-31 2021-09-17 现代自动车株式会社 Machine learning system and method for learning user control patterns
CN113495559A (en) * 2020-03-18 2021-10-12 百度（美国）有限责任公司 Learning-based controller for autonomous driving
CN111258323A (en) * 2020-03-30 2020-06-09 华南理工大学 Intelligent vehicle trajectory planning and tracking combined control method
CN112051780A (en) * 2020-09-16 2020-12-08 北京理工大学 Brain-computer interface-based mobile robot formation control system and method
CN114089628A (en) * 2021-10-25 2022-02-25 西北工业大学 Brain-driven mobile robot control system and method based on steady-state visual stimulation
CN114103974A (en) * 2021-11-01 2022-03-01 北京理工大学 Brain-computer interface method for vehicle continuous control

Also Published As

Publication number Publication date
CN105584479B (en) 2018-10-19

Similar Documents

Publication Publication Date Title
CN105584479A (en) Computer-controlled vehicle-oriented model prediction control method and computer-controlled vehicle utilizing method
Baturone et al. Automatic design of fuzzy controllers for car-like autonomous robots
CN101655708B (en) Intelligent vehicle carrier and control system and control method thereof
CN106741137A (en) A kind of personalized electric boosting steering system and control method
CN102788704B (en) Based on vehicle handling stability detection system and the detection method of pilot model
CN106184199A (en) The integrated control method of distributed AC servo system electric automobile stability
CN103926839A (en) Movement subdivision control method of wheeled mobile robot
CN107292048A (en) One kind is based on veDYNA tracks keeping method and 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
CN106275061A (en) A kind of man-machine drive type electric boosting steering system and control method altogether based on mix theory
CN110329347A (en) A kind of steering control system and its control method based on driver characteristics
CN113104010B (en) Vehicle brake control method, system, computer device and storage medium
CN107585207B (en) A kind of vehicle line traffic control four-wheel steering system and its control method
CN206954218U (en) A kind of intelligent vehicle line traffic control automatic cruise control system based on monocular vision
CN105015544A (en) Vehicle speed control system and method for full-automatic parking of electric car
CN113650609A (en) Flexible transfer method and system for man-machine co-driving control power based on fuzzy rule
CN206475931U (en) A kind of personalized electric boosting steering system
CN106019938A (en) ACC system dispersion second-order slip form control system based on data driving and method thereof
CN112034828B (en) Discrete integral sliding mode control device and method of brain-controlled mobile robot
CN102530078B (en) System for displaying automobile wheel steering angles
CN204821553U (en) Speed of a motor vehicle control system of full -automatic in -process of parking of electric automobile
CN108871786A (en) A kind of automatic driving vehicle semi-hardware type simulation test system and method
CN105241678A (en) Fast control prototype realization method of active rear wheel steering
CN206067874U (en) It is a kind of man-machine to drive type electric boosting steering system altogether based on mix theory

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