CN105867112A - Intelligent vehicle based on control algorithm with automatically optimized parameter and control method thereof - Google Patents
Intelligent vehicle based on control algorithm with automatically optimized parameter and control method thereof Download PDFInfo
- Publication number
- CN105867112A CN105867112A CN201610235462.0A CN201610235462A CN105867112A CN 105867112 A CN105867112 A CN 105867112A CN 201610235462 A CN201610235462 A CN 201610235462A CN 105867112 A CN105867112 A CN 105867112A
- Authority
- CN
- China
- Prior art keywords
- fuzzy
- module
- intelligent vehicle
- value
- pid
- 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
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
- G05B13/0275—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using fuzzy logic only
Abstract
The invention discloses an intelligent vehicle based on a control algorithm with an automatically optimized parameter and a control method thereof. The intelligent vehicle comprises the components of an intelligent vehicle body, a single-chip microcomputer which is mounted in the intelligent vehicle body, a speed detecting module, a camera module, a Bluetooth module, a motor driving module, a steering engine driving module and an OLED display module, wherein the speed detecting module, the camera module, the Bluetooth module, the motor driving module, the steering engine driving module and the OLED display module are connected with the single-chip microcomputer. The speed detecting module is used for detecting the rotating speed of a tyre. The camera module is mounted on the intelligent vehicle body and is used for acquiring racing track information in front of the vehicle body. The motor driving module is connected with a motor on the intelligent vehicle body. The steering engine driving module is connected with a steering engine on the intelligent vehicle body. The single-chip microcomputer comprises a PID fuzzy control module and a genetic algorithm optimization module.
Description
Technical field
The present invention relates to Freescale intelligent vehicle contest special intelligent car field, particularly relate to a kind of the most excellent based on parameter
The intelligent vehicle of the control algolithm changed and control method thereof.
Background technology
Intelligent carriage, as modern new invention, is later developing direction, and he can exist according to pattern set in advance
Operating automatically in one environment, it is not necessary to artificial management, militarily, intelligent vehicle can substitute for the mankind and completes jeopardously
The assignments such as the band removal of mines, scouting；Industrially, intelligent vehicle can substitute for the mankind and completes Equipment Inspection, the task such as transport goods；In agriculture
Industry mechanically, intelligent vehicle can substitute for the mankind complete to spray insecticide, the work such as harvesting, middle weeding；In terms of scientific research, intelligence
The mankind can be can substitute for complete Equipment Inspection, the task such as transport goods by car.Intelligent vehicle can realize being taken by self
The sensor carried comes perception outside vehicle environmental information and oneself state information, it is possible to show time, speed, mileage in real time, tool
There is Automatic Track Finding, seek light, barrier avoiding function, program-controlled travel speed, be accurately positioned parking, the function such as remote transmission image.Existing
Intelligent vehicle typically concentrate used automatically control, multi-sensor information fusion, airmanship, wireless communication technology and people
The new and high technologies such as work intelligence, are the synthesis of high-quality precision and sophisticated technology.The control aspect of existing intelligent carriage, typically uses in Path Recognition
On the basis of, used pid algorithm control before this for speeds control and servos control.
Pid control algorithm: the design of intelligent vehicle control system essentially consists in the routing information detected according to sensor and comes
Being controlled dolly, namely turn to intelligent vehicle and be controlled, good control could improve the average speed of car,
Increase the stability of intelligent vehicle, therefore the travel direction of dolly is controlled algorithm research, at present on the road of intelligent carriage
Footpath is modal in controlling is exactly fuzzy PID algorithm.The adjuster being controlled in the ratio of deviation, integration and differential is referred to as
PID regulator, it is technology maturation in continuous system, a kind of adjuster being most widely used, and simple in construction is prone on algorithm
Realize.
Genetic algorithm: genetic algorithm is the global optimizing technology of a kind of randomness, it is to solve nonlinear optimal problem
Common method, owing to it is not rely on studied a question specific field, and robustness is preferable, with other optimized algorithm phases
Ratio, he has: intelligent, adaptability is high, the advantage of concurrency, robustness, astaticism, global optimization.We are to be studied
Intelligent vehicle learning algorithm is, during intelligent vehicle moves, records the related data of intelligent vehicle motion, and is calculated by intelligence
Method finds the prioritization scheme of relevant parameter.Dolly is made again to travel under same racing track environment, it is possible to run on the most more
Under stable state.And the Optimization Work of this parameter value has hand down, parameter combination optimal in the most all vehicles is permissible
Automatically being loaded on new car, can use for reference the content of genetic algorithm, intelligent carriage Fuzzy control system based on genetic algorithm has
There is Road Detection and follow function.
Summary of the invention
It is an object of the invention to overcome the deficiencies in the prior art, it is provided that a kind of control algolithm based on parameter automatic optimization
Intelligent vehicle and control method.
Technical scheme is as follows:
The intelligent vehicle of a kind of control algolithm based on parameter automatic optimization includes: intelligent vehicle body, be arranged on intelligent vehicle this
Internal single-chip microcomputer, and be connected with single-chip microcomputer velocity measuring module, camera module, bluetooth module, motor drive module,
Servo driving module and OLED display module；Described velocity measuring module is for detecting the rotating speed of tire, described camera
Module is arranged on intelligent vehicle body and for gathering the racecourse information in car body front；Described motor drive module and intelligent vehicle
Motor on body is connected, and described servo driving module is connected with the steering wheel on intelligent vehicle body, and single-chip microcomputer includes that PID obscures
Control module and genetic algorithm optimization module.
The invention also discloses the servos control method of described intelligent vehicle:
1) camera module gathers the racing track image in car body front and is sent to single-chip microcomputer, the image that thecamera head is returned
For line number be m, columns be the pixel set of n, for given row mk, scan columns n residing for two racing track boundary linesk1With
nk2, calculate the column position residing for racing track center lineAnd residing for the center line of the image arrived with camera collection
Columns n/2 compare, and calculate the centre deviation of current intelligent vehicle position
2) centre deviation E value is carried out Fuzzy processing, obtain fuzzy variable e, i.e. E value is carried out segmentation, the most adjacent 8
The corresponding fuzzy class of individual E numerical value, fuzzy class is as the output e of obfuscation；
3) a given fuzzy relation matrix, finds the fuzzy output corresponding to fuzzy variable e in fuzzy relation matrix
Amount u；
4) fuzzy output amount u is refined, i.e. utilize expression formula to calculate the value of tri-parameters of PID, as PID Fuzzy Control
Output quantity U of molding block, calculation expression is as follows:
P value:
ServoPIDP=(ServoPIDPMat [e] * (8-ServoPFuzzyDegree)+ServoPIDPMat [e+1] *
ServoPFuzzyDegree)/8 I values:
ServoPIDI=0
D value:
ServoPIDD=ServoPIDDMat [e]
Wherein, ServoPIDP represents the P value of the PID that fuzzy control model exports, and ServoPIDD represents Fuzzy Control molding
The D value of the PID of block output, ServoPIDPMat [] is the fuzzy relation matrix that P value is corresponding, and ServoPIDDMat [] is that D value is right
The fuzzy relation matrix answered；ServoPFuzzyDegree is E divided by the remainder after 8；
5) output as single-chip microcomputer after genetic algorithm optimization module optimization of output quantity U is used for controlling servo driving mould
Block.
The process of described genetic algorithm module optimization is:
1) fitness function is chosen:Wherein ω1ω2ω3For to dependent variable
Coefficient, and meet ω1+ω2+ω3=3, t are current time, and u (t) is the output valve of PID, tuRepresent rising time；e(t)
Fuzzy variable e for t；
2) select the ratio of adaptive value as the standard of selection, obtain the selected probability P of each individualityi(ai)；
For the population { a that given number of individuals is n1,a2,…an, individual fitness is y (ai), wherein i=1,
2 ... n, its selected probability tables is shown as:
During selecting, individuality is selected to enter population according to the size of select probability；
3) the optimization pid control parameter expression formula that PID based on genetic algorithm controls is:
KP=(1-α1)KP0+α1PIDKP
KI=(1-α2)KI0+α2PIDKI
KD=(1-α3)KD0+α3PIDKD
Wherein, KP, KI, KD are the pid control parameter after optimizing, KP0、KI0、KD0For given PID initial value, PIDKP,
PIDKI, PIDKD are the control parameter of PID fuzzy control model output, α1、α2、α3For scale factor；
4) initial population is produced: randomly generate about α1,α2,α3Initial population,
5) carry out selecting, intersect, make a variation step, obtains new group combination；
6) end condition: judge whether to meet end condition, if reaching condition, then exports optimal solution, otherwise turns to step
5), until exporting optimal solution.
The invention also discloses the motor control method of a kind of described intelligent vehicle:
1) camera module gathers the racing track image in car body front and is sent to single-chip microcomputer, the image that thecamera head is returned
Being m for line number, columns is the pixel set of n, for given row mk, columns n residing for two racing track boundary lines can be scannedk1With
nk2, calculate the column position residing for racing track center lineAnd residing for the center line of the image arrived with camera collection
Columns n/2 compare, and calculate the centre deviation of current intelligent vehicle position
2) centre deviation E value is carried out Fuzzy processing, obtain fuzzy variable e: i.e. E value is carried out segmentation, the most adjacent 8
The corresponding fuzzy class of individual E numerical value, fuzzy class is as the output e of obfuscation；
3) a given fuzzy relation matrix, finds the fuzzy output corresponding to fuzzy variable e in fuzzy relation matrix
Amount u；
4) fuzzy output amount u is refined, i.e. utilize expression formula to calculate the input value of the PWM ripple controlling motor, express
Formula is:
PWM=SpeedTargetMat [e]
Wherein, PWM represents that the input value of the PWM of motor, SpeedTargetMat [] are the fuzzy relation matrix of motor；
5) single-chip microcomputer controls motor according to the input value calculated by motor drive module.
The control system of intelligent vehicle is made up of heading control loop and speed control system, and speed control system is by electricity
The control that machine drives makes intelligent vehicle maintain constant speed to run, and heading control loop is for maintaining stability and the fortune of intelligent vehicle
Fluency in row, uses the strategy of fuzzy control based on genetic algorithm, output PWM waveform to control steering wheel.
The present invention compared with prior art provides the benefit that:
PID based on parameter automatic optimization controls, and the regulation process solving fuzzy is complicated, and required precision is high, consumption
The problem taking substantial amounts of manpower and time cost；Break manual regulation and obscured the situation of variable element, made intelligent vehicle control to enter
One new stage.
Accompanying drawing explanation
Fig. 1 is the structural representation of the intelligent vehicle of present invention control algolithm based on parameter automatic optimization；
Fig. 2 is the process schematic that genetic algorithm module optimizes；
Fig. 3 is servos control frame diagram:
Fig. 4 is motor control framework figure.
Detailed description of the invention
As Figure 1-4, the intelligent vehicle of a kind of control algolithm based on parameter automatic optimization includes: intelligent vehicle body, peace
Be contained in the intrinsic single-chip microcomputer of intelligent vehicle, and be connected with single-chip microcomputer velocity measuring module, camera module, bluetooth module,
Motor drive module, servo driving module and OLED display module；Described velocity measuring module is used for detecting the rotating speed of tire,
Described camera module is arranged on intelligent vehicle body and for gathering the racecourse information in car body front；Described motor drives
Module is connected with the motor on intelligent vehicle body, and described servo driving module is connected with the steering wheel on intelligent vehicle body, monolithic
Machine includes PID fuzzy control model and genetic algorithm optimization module.
Use the single-chip microcomputer MK60DN512ZVLQ10 of dragon Qiu as single-chip microcomputer, use single motor, the form of single steering engine, make
Use OV7620 camera, allow intelligent vehicle run on set racing track.During intelligent vehicle runs, pass through camera collection
In the image of racing track, and the signal incoming MK60 single-chip microcomputer that will collect, by fuzzy-adaptation PID control based on genetic algorithm,
Output PWM ripple controls steering wheel and motor, thus controls the movement velocity of intelligent vehicle and turn to.
The information of the camera collection racing track of intelligent vehicle, single-chip microcomputer is by comparing center line and the racing track of camera collection image
The difference of center line calculates site error, using site error as the input value of heading control loop.
In this example, the application of fuzzy algorithmic approach i.e. for optimizing the fuzzy relation matrix during speed steering wheel PID controls, reduces it
Dependence to the experience of professional.
The fuzzy control of motor:
1) camera module gathers the racing track image in car body front and is sent to single-chip microcomputer, the image that thecamera head is returned
Being m for line number, columns is the pixel set of n.For given row mk, columns n residing for two racing track boundary lines can be scannedk1With
nk2, calculate the column position residing for racing track center lineAnd residing for the center line of the image arrived with camera collection
Columns n/2 compare, and calculate the centre deviation of current intelligent vehicle position
2) centre deviation E value is carried out Fuzzy processing, obtain fuzzy variable e；I.e. E value is carried out segmentation, the most adjacent 8
The corresponding fuzzy class of individual E numerical value, fuzzy class is as the output e of obfuscation.Concrete segmentation is as follows:
E ∈ [0,8), e=0
E ∈ [8,16), e=1
E ∈ [16,24), e=2
……
E ∈ [64,72), e=8
E ∈ [72 ,+∞), e=9
3) a given fuzzy relation matrix, finds the fuzzy output corresponding to fuzzy variable e in fuzzy relation matrix
Amount u.The fuzzy matrix chosen in this example is:
SpeedTargetMat []=[1600,1600,1550,1500,1450,1400,1350,1300]
4) fuzzy output amount u is refined, i.e. utilize expression formula to calculate the input value of the PWM ripple controlling motor.Express
Formula is:
PWM=SpeedTargetMat [e]
Wherein, PWM represents that the input value of the PWM of motor, SpeedTargetMat [] are the fuzzy relation matrix of motor.
5) single-chip microcomputer controls motor according to the input value calculated by motor drive module.
The fuzzy-adaptation PID control of steering wheel:
1) camera module gathers the racing track image in car body front and is sent to single-chip microcomputer, the image that thecamera head is returned
Being m for line number, columns is the pixel set of n.For given row mk, columns n residing for two racing track boundary lines can be scannedk1With
nk2, calculate the column position residing for racing track center lineAnd residing for the center line of the image arrived with camera collection
Columns n/2 compare, and calculate the centre deviation of current intelligent vehicle position
2) centre deviation E value is carried out Fuzzy processing, obtain fuzzy variable e；I.e. E value is carried out segmentation, the most adjacent 8
The corresponding fuzzy class of individual E numerical value, fuzzy class is as the output e of obfuscation, and concrete segmentation is as follows:
E ∈ [0,8), e=0
E ∈ [8,16), e=1
E ∈ [16,24), e=2
……
E ∈ [64,72), e=8
E ∈ [72 ,+∞), e=9
3) a given fuzzy relation matrix, finds the fuzzy output corresponding to fuzzy variable e in fuzzy relation matrix
Amount u.In this example, fuzzy relation matrix is:
SeveroPIDPMat [10]=[35,37,40,41,45,49,52,56,54,51]
SeveroPIDIMat [10]=[0,0,0,0,0,0,0,0,0,0]
SeveroPIDPMat [10]=[20,20,21,22,24,25,25,24,25,20]
4) fuzzy output amount u is refined, i.e. utilize expression formula to calculate the value of tri-parameters of PID, as PID Fuzzy Control
Output quantity U of molding block.Calculation expression is as follows:
P value:
ServoPIDP=(ServoPIDPMat [e] * (8-ServoPFuzzyDegree)+ServoPIDPMat [e+1] *
ServoPFuzzyDegree)/8I value:
ServoPIDI=0
D value:
ServoPIDD=ServoPIDDMat [e]
Wherein, ServoPIDP represents the P value of the PID that fuzzy control model exports, and ServoPIDD represents Fuzzy Control molding
The D value of the PID of block output, ServoPIDPMat [] is the fuzzy relation matrix that P value is corresponding, and ServoPIDDMat [] is that D value is right
The fuzzy relation matrix answered；ServoPFuzzyDegree is E divided by the remainder after 8.
5) output as single-chip microcomputer after genetic algorithm optimization module optimization of output quantity U is used for controlling servo driving mould
Block.
Genetic algorithm optimization process:
1) as a example by the control of steering wheel, the present invention can choose fitness function:
Wherein ω1ω2ω3For the coefficient to dependent variable, and meet ω1+ω2+ω3=3, t are current time, and u (t) is PID controller
Output valve, tuRepresent rising time.
2) in the present invention, the ratio of optional adaptive value, as the standard of selection, obtains the selected probability of each individuality.
For the population { a that given number of individuals is n1,a2,...an, individual fitness is y (ai) (i=1,2 ... n), then it enters
Probability is selected to be expressed as:During selecting, according to the size of select probability
Select individual entrance population；Taking size n=50 of population, evolutionary generation is 100, crossover probability Pc=0.8, mutation probability Pm
=0.01, ω1=1.495, ω2=0.005, ω3=1.5
3) the optimization pid control parameter expression formula that PID based on genetic algorithm controls is:
KP=(1-α1)KP0+α1PIDKP
KI=(1-α2)KI0+α2PIDKI
KD=(1-α3)KD0+α3PIDKD
Wherein, KP, KI, KD are the pid control parameter after optimizing, KP0、KI0、KD0For given PID initial value, PIDKP,
PIDKI, PIDKD are the pid control parameter of fuzzy controller output, α1、α2、α3For scale factor.
4) initial population is produced: randomly generating in the initial population of n=50, such as population one group of individuality can be expressed as
{α1,α2,α3}={ 0.3,0.4,0.5}；
5) select: calculate its genetic probability according to the fitness of initial population, screen population of future generation according to probability；
6) intersect: intersecting is exactly to be reconfigured by the part between different individualities, obtains new population of future generation
Process.Example: individual 1:A1={ 0.3,0.4,0.5}, individual 2:A2={ 0.5,0.6,0.2}, after intersecting, its generation is new
Generation individuality may be: A1 (2)={ 0.3,0.6,0.2} and A2 (2)={ 0.5,0.4,0.5}；
7) variation: introduced the factor being not belonging to this population by small probability in population.Example A1={ 0.3,0.4,0.5} becomes
A can be produced after different1 (3)={ the offspring individual of 0.9,0.4,0.5}；
8) end condition: determining whether through 100 heredity, if having, then terminating, exports population, if nothing, then returns 5) enter
Row next round iteration.
Claims (4)
1. the intelligent vehicle of a control algolithm based on parameter automatic optimization, it is characterised in that including: intelligent vehicle body, be arranged on
The intrinsic single-chip microcomputer of intelligent vehicle, and be connected with single-chip microcomputer velocity measuring module, camera module, bluetooth module, motor
Drive module, servo driving module and OLED display module；Described velocity measuring module is for detecting the rotating speed of tire, described
Camera module be arranged on intelligent vehicle body and for gathering the racecourse information in car body front；Described motor drive module
Being connected with the motor on intelligent vehicle body, described servo driving module is connected with the steering wheel on intelligent vehicle body, single-chip microcomputer bag
Include PID fuzzy control model and genetic algorithm optimization module.
2. the servos control method of an intelligent vehicle as claimed in claim 1, it is characterised in that:
1) camera module gathers the racing track image in car body front and is sent to single-chip microcomputer, and the image that thecamera head is returned is row
The pixel set that number is m, columns is n, for given row mk, scan columns n residing for two racing track boundary linesk1And nk2, meter
Calculate the column position residing for racing track center lineAnd the columns residing for center line of the image arrived with camera collection
N/2 compares, and calculates the centre deviation of current intelligent vehicle position
2) centre deviation E value is carried out Fuzzy processing, obtain fuzzy variable e, i.e. E value is carried out segmentation, 8 the most adjacent E
The corresponding fuzzy class of numerical value, fuzzy class is as the output e of obfuscation；
3) a given fuzzy relation matrix, finds fuzzy output amount u corresponding to fuzzy variable e in fuzzy relation matrix；
4) fuzzy output amount u is refined, i.e. utilize expression formula to calculate the value of tri-parameters of PID, as PID Fuzzy Control molding
Output quantity U of block, calculation expression is as follows:
P value:
ServoPIDP=(ServoPIDPMat [e] * (8-ServoPFuzzyDegree)+ServoPIDPMat [e+1] *
ServoPFuzzyDegree)/8I value:
ServoPIDI=0
D value:
ServoPIDD=ServoPIDDMat [e]
Wherein, ServoPIDP represents the P value of the PID that fuzzy control model exports, and ServoPIDD represents that fuzzy control model is defeated
The D value of the PID gone out, ServoPIDPMat [] is the fuzzy relation matrix that P value is corresponding, and ServoPIDDMat [] is that D value is corresponding
Fuzzy relation matrix；ServoPFuzzyDegree is E divided by the remainder after 8；
5) output as single-chip microcomputer after genetic algorithm optimization module optimization of output quantity U is used for controlling servo driving module.
3. the servos control method of intelligent vehicle as claimed in claim 2, it is characterised in that described genetic algorithm module optimization
Process be:
1) fitness function is chosen:Wherein ω1ω2ω3For the coefficient to dependent variable,
And meet ω1+ω2+ω3=3, t are current time, and u (t) is the output valve of PID, tuRepresent rising time；When e (t) is t
Fuzzy variable e carved；
2) select the ratio of adaptive value as the standard of selection, obtain the selected probability P of each individualityi(ai)；
For the population { a that given number of individuals is n1,a2,...an, individual fitness is y (ai), wherein i=1,2 ... n,
Its selected probability tables is shown as:
During selecting, individuality is selected to enter population according to the size of select probability；
3) the optimization pid control parameter expression formula that PID based on genetic algorithm controls is:
KP=(1-α1)KP0+α1PIDKP
KI=(1-α2)KI0+α2PIDKI
KD=(1-α3)KD0+α3PIDKD
Wherein, KP, KI, KD are the pid control parameter after optimizing, KP0、KI0、KD0For given PID initial value, PIDKP,
PIDKI, PIDKD are the control parameter of PID fuzzy control model output, α1、α2、α3For scale factor；
4) initial population is produced: randomly generate about α1,α2,α3Initial population,
5) carry out selecting, intersect, make a variation step, obtains new group combination；
6) end condition: judge whether to meet end condition, if reaching condition, then exports optimal solution, otherwise turns to step 5), directly
To output optimal solution.
4. the motor control method of an intelligent vehicle as claimed in claim 1, it is characterised in that:
1) camera module gathers the racing track image in car body front and is sent to single-chip microcomputer, and the image that thecamera head is returned is row
Number is m, and columns is the pixel set of n, for given row mk, columns n residing for two racing track boundary lines can be scannedk1And nk2,
Calculate the column position residing for racing track center lineAnd the row residing for center line of the image arrived with camera collection
Number n/2 compares, and calculates the centre deviation of current intelligent vehicle position
2) centre deviation E value is carried out Fuzzy processing, obtain fuzzy variable e: i.e. E value is carried out segmentation, 8 the most adjacent E
The corresponding fuzzy class of numerical value, fuzzy class is as the output e of obfuscation；
3) a given fuzzy relation matrix, finds fuzzy output amount u corresponding to fuzzy variable e in fuzzy relation matrix；
4) fuzzy output amount u being refined, i.e. utilize expression formula to calculate the input value of the PWM ripple controlling motor, expression formula is:
PWM=SpeedTargetMat [e]
Wherein, PWM represents that the input value of the PWM of motor, SpeedTargetMat [] are the fuzzy relation matrix of motor；
5) single-chip microcomputer controls motor according to the input value calculated by motor drive module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610235462.0A CN105867112B (en) | 2016-04-15 | 2016-04-15 | A kind of intelligent vehicle and its control method of the control algolithm based on parameter automatic optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610235462.0A CN105867112B (en) | 2016-04-15 | 2016-04-15 | A kind of intelligent vehicle and its control method of the control algolithm based on parameter automatic optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105867112A true CN105867112A (en) | 2016-08-17 |
| CN105867112B CN105867112B (en) | 2019-02-12 |
Family
ID=56632190
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610235462.0A Expired - Fee Related CN105867112B (en) | 2016-04-15 | 2016-04-15 | A kind of intelligent vehicle and its control method of the control algolithm based on parameter automatic optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105867112B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992059A (en) * | 2018-01-08 | 2018-05-04 | 陕西理工大学 | The control method of electromagnetism intelligent vehicle |
| CN108803611A (en) * | 2018-06-14 | 2018-11-13 | 广东嘉腾机器人自动化有限公司 | A kind of trace follow control method, apparatus and walking mechanism |
| CN110609770A (en) * | 2019-08-16 | 2019-12-24 | 中国地质大学（武汉） | Flash off-line parameter adjusting system and method based on single chip microcomputer |
| CN113311454A (en) * | 2020-02-26 | 2021-08-27 | 中移物联网有限公司 | Method, device and equipment for evaluating discrete degree of GPS positioning point |
| CN115755589A (en) * | 2022-12-16 | 2023-03-07 | 上海第二工业大学 | Optimization method based on genetic algorithm in reaction kettle fuzzy control system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2264369A (en) * | 1992-02-12 | 1993-08-25 | Bosch Gmbh Robert | Method and device for positioning an adjusting mechanism in a motor vehicle |
| CN1952996A (en) * | 2005-10-18 | 2007-04-25 | 中国科学技术大学 | Inverted pendulum of remote car with two wheels and balance control method thereof |
| CN101221447A (en) * | 2008-01-18 | 2008-07-16 | 中国农业大学 | Mechanical automatic steering control method |
| CN204374769U (en) * | 2014-11-11 | 2015-06-03 | 浙江大学城市学院 | Based on the Intelligent tracking trolley of photoelectric sensor and photoelectric encoder |
-
2016
- 2016-04-15 CN CN201610235462.0A patent/CN105867112B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2264369A (en) * | 1992-02-12 | 1993-08-25 | Bosch Gmbh Robert | Method and device for positioning an adjusting mechanism in a motor vehicle |
| CN1952996A (en) * | 2005-10-18 | 2007-04-25 | 中国科学技术大学 | Inverted pendulum of remote car with two wheels and balance control method thereof |
| CN101221447A (en) * | 2008-01-18 | 2008-07-16 | 中国农业大学 | Mechanical automatic steering control method |
| CN204374769U (en) * | 2014-11-11 | 2015-06-03 | 浙江大学城市学院 | Based on the Intelligent tracking trolley of photoelectric sensor and photoelectric encoder |
Non-Patent Citations (1)
| Title |
|---|
| 杨栩: "基于视觉的智能车控制系统及其算法的应用研究", 《中国优秀硕士学位论文全文数据库（电子期刊） 工程科技II辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992059A (en) * | 2018-01-08 | 2018-05-04 | 陕西理工大学 | The control method of electromagnetism intelligent vehicle |
| CN108803611A (en) * | 2018-06-14 | 2018-11-13 | 广东嘉腾机器人自动化有限公司 | A kind of trace follow control method, apparatus and walking mechanism |
| CN108803611B (en) * | 2018-06-14 | 2021-10-19 | 广东嘉腾机器人自动化有限公司 | Tracing control method and device and walking mechanism |
| CN110609770A (en) * | 2019-08-16 | 2019-12-24 | 中国地质大学（武汉） | Flash off-line parameter adjusting system and method based on single chip microcomputer |
| CN113311454A (en) * | 2020-02-26 | 2021-08-27 | 中移物联网有限公司 | Method, device and equipment for evaluating discrete degree of GPS positioning point |
| CN115755589A (en) * | 2022-12-16 | 2023-03-07 | 上海第二工业大学 | Optimization method based on genetic algorithm in reaction kettle fuzzy control system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105867112B (en) | 2019-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105867112A (en) | Intelligent vehicle based on control algorithm with automatically optimized parameter and control method thereof | |
| Codevilla et al. | End-to-end driving via conditional imitation learning | |
| Müller et al. | Driving policy transfer via modularity and abstraction | |
| CN103940434B (en) | Real-time lane detection system based on monocular vision and inertial navigation unit | |
| CN109460029A (en) | Livestock and poultry cultivation place inspection mobile platform and its control method | |
| EP3588226B1 (en) | Method and arrangement for generating control commands for an autonomous road vehicle | |
| CN109426260A (en) | Servomechanism | |
| CN106080590A (en) | Control method for vehicle and device and the acquisition methods of decision model and device | |
| CN112130570B (en) | Blind guiding robot of optimal output feedback controller based on reinforcement learning | |
| CN110673602A (en) | Reinforced learning model, vehicle automatic driving decision method and vehicle-mounted equipment | |
| CN111061266A (en) | Night on-duty robot for real-time scene analysis and space obstacle avoidance | |
| CA3087361A1 (en) | Autonomous driving methods and systems | |
| CN109597412A (en) | A kind of Unmanned Systems and its control method | |
| CN108919810A (en) | The localization for Mobile Robot and navigation system of view-based access control model teaching | |
| CN116134292A (en) | Tool for performance testing and/or training an autonomous vehicle planner | |
| DE112021005708T5 (en) | Methods and systems for tracking a lane over time | |
| CN111257853B (en) | Automatic driving system laser radar online calibration method based on IMU pre-integration | |
| CN102745196A (en) | Intelligent control device and method for granular computing-based micro intelligent vehicle | |
| Fernandes et al. | Intelligent robotic car for autonomous navigation: Platform and system architecture | |
| CN116486356A (en) | Narrow scene track generation method based on self-adaptive learning technology | |
| CN115285143A (en) | Automatic driving vehicle navigation method based on scene classification | |
| Chen et al. | Cognitive map-based model: Toward a developmental framework for self-driving cars | |
| CN111310919B (en) | Driving control strategy training method based on scene segmentation and local path planning | |
| Sharma et al. | Self driving car using deep learning technique | |
| CN117382670A (en) | Vehicle control method, automatic driving prompting method and related devices |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190212 Termination date: 20190415 |