CN109492599A - A kind of multiaxis electricity car self- steering method - Google Patents
A kind of multiaxis electricity car self- steering method Download PDFInfo
- Publication number
- CN109492599A CN109492599A CN201811382390.8A CN201811382390A CN109492599A CN 109492599 A CN109492599 A CN 109492599A CN 201811382390 A CN201811382390 A CN 201811382390A CN 109492599 A CN109492599 A CN 109492599A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- steering
- lane line
- satellite
- pid control
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000005611 electricity Effects 0.000 title claims abstract description 12
- 239000000284 extract Substances 0.000 claims abstract description 3
- 230000007246 mechanism Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 230000006835 compression Effects 0.000 claims description 5
- 238000007906 compression Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 abstract description 5
- 230000003287 optical effect Effects 0.000 description 12
- 238000001514 detection method Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 230000004888 barrier function Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000012937 correction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 239000013589 supplement Substances 0.000 description 3
- 210000004556 brain Anatomy 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000002567 autonomic effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000005211 surface analysis Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
- G05D1/027—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means comprising intertial navigation means, e.g. azimuth detector
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
- G06V20/38—Outdoor scenes
- G06V20/39—Urban scenes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- Automation & Control Theory (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
- Navigation (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention discloses a kind of multiaxis electricity car self- steering methods, comprising: the original image that vehicle front and rear sides camera captures is input to mobile unit and pre-processed to original image by step A., obtains pretreated image；Step B. is directed to pretreated image, carries out local enhancement to vehicle driving region；Step C. extracts lane line；Step D. determines vehicle location according to the position of camera and lane line；Step E. is run in the track of permission according to vehicle driving constraint condition with PID control method, fuzzy PID control method, forecast Control Algorithm, nonlinear control method control vehicle.The present invention can promote the accuracy and redundancy of vehicle self- steering system, and integrated use optics turning function synchronous with the lane holding function of satellite-inertial guidance navigation system realization vehicle and more wheels, electrically controlled steering device is passed to using electric signal and is also easy to control vehicle.
Description
Technical field
The invention belongs to field of urban traffic, in particular to a kind of multiaxis electricity car self- steering method.
Background technique
Because the size of population increases, the serious and traffic jam of aging of population is serious, more and more people go out
Row has selected passenger capacity big, does not need the large-scale public transport of oneself driving.Therefore, large-scale public transport increasingly becomes people
The selection of trip.In view of BRT passenger capacity is small, heavily loaded bus control is more difficult, and streetcar track is laid with higher cost, therefore solves
Certainly the current problems faced of these three vehicles by be future city traffic certainty developing direction.Since BRT passenger capacity is small, rail
Electric car is laid with the attribute that track is vehicle itself, it is more difficult to realize, therefore solve the problems, such as that heavily loaded bus control is more difficult to become
The most viable solution of next stage transportation industry.
Currently, multiaxis electricity car self- steering system is divided into contact and two kinds contactless, the guiding of contact has curb
The modes such as stone, guide rail, contactless guiding have optics and electromagnetism two ways.
There are Raul's system and Pang Badi guide track system, Tianjin Development Zone guide rail electric car 1 using the physics guidance system of guide rail
Raul's system that number line and Shanghai Zhangjiang tramcar are all made of.Optically guiding needs to utilize vehicle by image processing techniques
Front camera scans ground oriented identification line, by acquired image real-time data transmission to car-mounted computer, vehicle computing
The dynamic parameters such as these data and the speed of vehicle, deviation value, wheel angle are analyzed and processed by machine together, then to steering
System conveys instruction, to control the driving direction of vehicle, vehicle actual motion track is made to be consistent substantially with ground oriented identification line.
However, contact self- steering system is easily worn away, stability is poor, and needs to redesign road, cost compared with
It is high.In contactless method, then there is the problems such as vulnerable to electromagnetic interference influence in electromagnetic method, and optical means is main at this stage
Using Lane detection technology, i.e., the special rail diatom on road surface is identified by vehicle-mounted camera, and intelligently virtual track is carried out
Tracing control is guaranteeing so that operation information is sent to train " brain " (central control unit) according to the instruction of " brain "
While train realizes the regular events such as traction, braking, steering, train driving can be precisely controlled at set " virtual track "
On, realize intelligent operation.However the method is limited by the light intensity as brought by Changes in weather, light occlusion issue, light
Chemical contamination and ground lane line not enough completely etc. also directly influence optical means identification lane line, meanwhile, precision it is high and
The high optical means of stability requires camera filming frequency higher, high resolution, therefore also requires the amount of storage of controller sufficiently large,
The calculation processing power of main controller is sufficiently strong, and the data transmission capabilities of terrestrial transmission device are sufficiently stable, therefore in face at this stage
The problems such as facing danger or disaster with large-scale commercial and be more demanding to controller.
In addition, single optical means will be difficult in the case where the lane-change of reply burst and other deviation predetermined lanes
It returns former lane and completes Lane detection function, therefore, the stability and robustness of the method is not high.
Summary of the invention
It is an object of the present invention in view of the above shortcomings of the prior art, provide a kind of multiaxis electricity car self- steering method.
In order to solve the above technical problems, the technical scheme adopted by the invention is that:
A kind of multiaxis electricity car self- steering method, its main feature is that the following steps are included:
Step A. by the original image that vehicle front and rear sides camera captures be input to mobile unit and to original image into
Row pretreatment, obtains pretreated image；
Step B. is directed to pretreated image, carries out local enhancement to vehicle driving region；
Step C. extracts lane line；
Step D. determines vehicle location according to the position of camera and lane line；
Step E. is according to vehicle driving constraint condition, with PID control method, fuzzy PID control method, PREDICTIVE CONTROL side
Method, nonlinear control method control vehicle are run in the track of permission.
It further, further include utilizing global position system and/or the inertial navigation system for being mounted on intermediate vehicle in the step D
It unites and determines vehicle location.
The preprocessing process in the step A successively includes: compression of images, gray scale conversion, filter as a preferred method,
Wave processing, equilibrium treatment.
As a preferred method, in the step E, the control of steering mechanism's run-through channel is designed according to PID control method
System:Wherein KdDifferential divisor, K for PID control systempFor PID control system ratio because
Son, KiFor the integrating factor of PID control system.
It further, further include according to driving rule, comfort requirement, line length, noise limitation in the step E
And other conditions construct cost value function, find best vehicle running track.
Compared with prior art, the present invention can promote the accuracy and redundancy of vehicle self- steering system, and comprehensive fortune
Realize that the lane of vehicle keeps function and the synchronous turning function of more wheels with optics and satellite-inertial guidance navigation system, using electric signal
It passes to electrically controlled steering device and is also easy to control vehicle.
Detailed description of the invention
Fig. 1 is control principle drawing of the present invention.
Fig. 2 is video camera and satellite antenna layout drawing.
Fig. 3 is satellite system positioning schematic.
Fig. 4 is that vehicle location identifies schematic diagram.
Fig. 5 is the lane keeping method schematic diagram that straightway finely tunes corner.
Fig. 6 is that vehicle crosses bend schematic diagram.
Specific embodiment
As depicted in figs. 1 and 2, the present invention is applied to multiaxis heavy duty car, is respectively provided with camera in vehicle front and rear sides, uses
Picture before and after capturing vehicle simultaneously passes to central processing unit, in central processing unit by being inputted to image, the compression of image,
Gray scale conversion, image preprocessing, topography's enhancing, the methods of lane detection directly extracts lane line, thus according to vehicle
Diatom determines position of the vehicle on current route.
One, Lane detection and satellite-inertial guidance system
1. Lane detection
(1) image input and compression
Camera captured image is input in mobile unit and compression processing is carried out to image according to demand, simplifies meter
Calculation amount.
(2) gray scale conversion
It is that 2 value models are analyzed by rgb color model conversation, to be further simplified calculating.
(3) filtering processing and equilibrium treatment
Image is pre-processed using the methods of filtering methods or histogram equalization such as mean filters, to will likely deposit
Optical noise removal.
(4) Lane detection
The operator of lane line threshold value is set according to weather condition, and record meets the region of threshold value, to extract lane line.
After extracting lane line, lane line is locked, it is contemplated that there may be some noise signals or such as barrier, weather
Condition, the factors such as other vehicles cover lane line, therefore remove or pass through lane fitting side for noise signal by filter
Method supplements lane line complete.
It can choose area-of-interest for road conditions, i.e. the region of vehicle driving carries out local enhancement, for straight line
Lane line can use 5*5 matrix, it is contemplated that and lane line has special shape, therefore can compare with the method,
A kind of selectable feature is as shown in the table:
| 0 | 0 | 0 | 0 | 127 |
| 0 | 0 | 0 | 127 | 127 |
| 0 | 0 | 127 | 127 | 127 |
| 0 | 127 | 127 | 127 | 127 |
| 127 | 127 | 127 | 127 | 127 |
1 lane line eigenmatrix of table
(5) vehicle location identifies
In view of having lane line on the road of vehicle driving, it is generally divided into extraordinary lane line and common in-vehicle diatom, relatively
For be relatively easy to for the opposite identification of extraordinary lane line of the electric Bus & Coach Design of heavy duty, therefore the general lane of Main Analysis here
Line.
It, can be unique according to the position of camera in image and lane line in view of vehicle travels among lane line two sides
The position of vehicle is determined, to complete Lane detection.
Meanwhile in the car between vehicle simultaneously global position system and inertial navigation system are installed, pass through satellite system and inertial navigation system
It unites and determines vehicle location, guarantee that vehicle travels in the region that can identify lane line.In view of satellite can be received by antenna
Satellite-signal and the signal of base station, according to the system that several satellites and base station are constituted, according to satellite instantaneous position as
Know that measurement GPS signal reaches the time △ t of receiver, distance is then determined according to spread speed, then according to Vector triangle
Geometrical relationship is constructed, number of satellite is more, and determining position is also more acurrate.Illustrate that image is as shown in Figure 3.
Vehicle location explanatory diagram is as shown in figure 4, when vehicle is when different location, and the position of lane line is not yet
Together, therefore the position of lane line that can be identified according to camera uniquely determine the position of vehicle, thus in main controller, according to
Vehicle restraint condition and PID control, fuzzy-adaptation PID control, PREDICTIVE CONTROL, a variety of methods such as nonlinear Control guarantee that vehicle is allowing
Track in run.
Therefore, the method can reversely be inferred to the position of vehicle by comparing the information of lane line, and hold for main controller
Row control instruction provides foundation.
2. satellite system and inertial navigation system
Differential satellite signal system is the differential satellite standard station using known accurate three-dimensional coordinate, acquires pseudorange correction amount
Or position correction amount, then this correction amount is sent to user in real time or afterwards, the measurement data of user is modified, to mention
High satellite positioning precision.This system passes through the multi-satellite system for being mounted on a vehicle and intermediate vehicle, can completely capture vehicle
Location information, number of satellite is more, and its precision is higher, can reach a centimetre rank at present, worst also to can achieve sub-meter grade
Not, it is contemplated that optical video system must identify under conditions of having lane line, and identify that situation is also unstable, therefore, fortune
It can guarantee that vehicle is run in lane line with differential satellite signal system, while under conditions of optical system is unstable,
The positioning signal and cartographic information that can directly provide according to satellite directly provide foundation to turn to, and optical system will be only used as
One feedback system gives system one feedback signal, improves the robustness and stability of system.
Inertial navigation system (INS, hereinafter referred to as inertial navigation) is one kind independent of external information, also not to external radiation energy
The autonomic navigation system of amount.The basic functional principle of inertial navigation is based on Newton mechanics law, by measurement carrier used
The acceleration of property referential, it integrates the time, and it is transformed in navigational coordinate system, it will be able to obtain navigating
The information such as speed, yaw angle and position in coordinate system, are mounted on vehicle central axes, can be very good to make up vehicle satellite system
There is the problem of error in system, to guarantee vehicle location precision, and in view of intermediate vehicle installation camera needs to consider and stand
The interference problem of platform does not consider generally, so often considering to assist using inertial navigation system in intermediate vehicle, defending using camera
In the case that star system breaks down, the location information of vehicle is provided according to inertial navigation system, to complete the steering of executing agency
Function.
As shown in Figures 2 and 3, satellite heavy-duty vehicle in base station can interconnect, and the time of transmission is certain, according to speed
Out position can be calculated, then according to Vector triangle line, to uniquely determine specific location, it is contemplated that satellite is more,
Shape is more complicated, can use Polygon solution, to promote precision.
In view of aerial position it is known that the aerial position of each section vehicle can be uniquely determined by aerial position, such as
Fruit uses two antennas, when satellite precision reaches centimetre even millimeter rank, can also be determined according to the position of two antennas
The plane attitude angle surface analysis of line (two o'clock at), can determine that (at face for three-dimensional attitude angle at 3 points if using three antennas
Stereoscopic analysis), antenna is more, and its accuracy of identification is higher, and the map system carried further according to satellite system can be realized accurately
Positioning function.To determine the position of vehicle, attitude angle etc. according to vehicle position information and related system.
After antenna receives information, by interaction device, the information for receiving vehicle is fed back to main controller, master control by terminal and cable
After device integrated treatment information, vehicle location is uniquely determined, it is contemplated that have track of vehicle line map in vehicle control device, therefore can be with
It is analyzed according to the lane line that line condition and comprehensive camera identify, it is main by defending under conditions of bad weather
Star system realizes positioning, and under tunnel and bridge and other places for losing satellite-signal will be used to using camera identification positioning
It leads and realizes positioning in intermediate vehicle, to turn to executing agency's realization lane to control the steering of vehicle or fine tuning and function is kept to mention
For foundation.
Two, determine vehicle position information
(1) it can be shown on the image with the information of synchronization catch to front part of vehicle by the video camera being installed on vehicle,
And pass to dependent image data in processor, it is converted into the image with multiple pixels, so that image information is obtained, in conjunction with
Location algorithm identifies lane line and vehicle location, it is contemplated that the electric car of multiaxis heavy duty needs to control multiple transfers, also oriented
The demand of both direction operation.Therefore, it is necessary to which former and later two cameras are arranged to identify lane line jointly, to completely determine vehicle
And lane line relative position, and vehicle location is judged according to lane line.
(2) vehicle is connected by run-through channel, is determined in head vehicle and trailer by camera, remaining steering mechanism according to
PID control, fuzzy-adaptation PID control, PREDICTIVE CONTROL, the methods of nonlinear Control complete wheel Following effect.And that installs on vehicle defends
Star system and inertial navigation system realize the positioning within the sub-meter grade of vehicle is other, so that vehicle is maintained at then by comprehensive positioning
In lane line, specific installation site is as shown in Fig. 2, satellite and inertial navigation system synthesis identify vehicle in satellite by positioning device
Position in plane, and guarantee vehicle in lane line, and camera capture lane line information, give satellite system determine position
One feedback signal, thus the more accurate steering and fine tuning for judging vehicle.Meanwhile when satellite system data is not accurate enough
In the case of (such as in tunnel, high building effect has barrier to block on high), will mainly based on optical identification,
Kp, Ki, Kd in adjustment algorithm in PID, and strengthen the specific gravity of nonlinear algorithm, at the same use inertial navigation system will as supplement,
Enable positioning system remain positioned in as far as possible sub-meter grade not or centimetre rank, and when satellite positioning lose overlong time or
Global position system failure, then direct switchable optics system and inertial navigation system, replace defending in certain length by inertial navigation system
The function of star system, optical system continue identify lane line keep vehicle precise positioning, complete this section operation and being capable of self-conductance
Maintenance is completed to factory is gone back to, and when wet weather, the bad weathers such as Thunderstorm Weather cover lane line, then directly pass through satellite system and inertial navigation
System realizes positioning function, and is assisted by inertial navigation, to obtain complete vehicle location, therefore, the method can be
It is round-the-clock, the position of vehicle is obtained under the conditions of any, to provide foundation for steering-by-wire.Scene analysis is as follows:
The lane keeping method schematic diagram that straightway finely tunes corner is Fig. 5, and it is Fig. 6 that vehicle, which crosses bend method schematic diagram,.
Three, vehicle controls and execution
(1) as shown in fig. 6, under the premise of known vehicle position, there is the profile constraints line of vehicle inside controller, often
One wheel is no more than wheel constrained line, thus switched to the model of Prescribed Properties, it is comprehensive further according to PID control method
Design the control system of steering mechanism's run-through channel:After main controller completes data analysis, further according to biography
The stability and controllability of delivery function matrix guarantee system, it is contemplated that PID system can only control linear system and relatively simple
Nonlinear system, therefore also need to design the nonlinear Controls such as predictive control model and gain scheduling, thus it is more accurate really
Determine the track that vehicle is run in constrained line.Main controller is calculated and is handled running track for electric signal after running track, and will
Calculated electric signal feeds back to executing agency and completes the rotating requires in constrained line, to make steering mechanism according to pre- orbit determination
Mark turns to, and is checked according to lane line, and provide feedback signal, so that it is guaranteed that turning function completion is accurate and stable；
Executing agency, respectively to each wheel to controlling, turns to, and complete lane guarantor according to electric signal to realize that multiaxis wheel is synchronous
It holds and turning function.
Consider to have multivalue under constraint condition as a result, and considering vehicle dynamic model and mistake that may be present
Difference, it is therefore necessary to generate multiple spline curve or by emulation mode, i.e., according to rule is driven in main controller, comfort is wanted
It asks, the demands such as length of every route are assessed, and the cost value function Y of track is constructedcost(R drives=f (R, S, L, W, O)
Rule, S comfort requirement, L line length, W noise, O other conditions) and Yopt=Max (Ycost1,Ycost2,Ycost3...) come
It determines that final driving trace finds optimal track of vehicle, the running track of vehicle is found by control algolithm, to construct
Its transfer function matrix, and vehicle dynamic model is constructed, steering mechanism and run-through channel are built into a multidimensional control matrix,
Guarantee the robustness and stability of vehicle, meanwhile, completion track of vehicle is corresponding with the position of wheel under constraint condition, thus
Whether analysis vehicle needs to finely tune each wheel pair, or executes wheel to steering order, and generate electric signal on this basis, passes to
Executing agency.
(2) executing agency uses electric-control system, and electric signal is directly passed to automatically controlled steering mechanism, it is contemplated that each wheel pair
It can be controlled, therefore according to vehicle running track, that is, may know that the location of wheel subsequent time, simultaneously as passing through
Channel presence flexible, thus when occur slight error and other because dynamic conditions generate error in the case where, remain to
Enough guarantee that each wheel of vehicle reaches designated position according to the track that main controller generates in subsequent time, to control respectively multiple
Steering mechanism, electric signal is adjusted the requirement for completing to turn to and lane is kept based on the received for steering mechanism.Between change very
To the operation for eliminating artificial control steering, mitigate because of the interference that human factor generates, so that it is every to improve processing vehicle correlation
The efficiency of matters.
(3) vehicle has obtained the position of vehicle by navigation system and video system, and is the traveling of vehicle according to position
Foundation is provided, because of the presence of satellite system and inertial navigation system, vehicle can directly go out the displacement of vehicle by the system detection,
Speed, attitude angle etc. avoid the design of wheel mechanism monitoring wheel steering system.It is directly to turn by the car body position of vehicle
Foundation is provided to the steering of system.Meanwhile it being compared to current vehicle first round steering, rear-wheel follows scheme, this scheme energy
It is enough that vehicle location is more efficiently provided, and each wheel is directly controlled, improve the redundancy of system.Since the method can be real
When synchronous vehicle position data, to avoid error.The fine tuning to corner can also be taken turns simultaneously, avoid the hair of whipping phenomenon
It is raw.
(4) round-the-clock Operational requirements are directed to, satellite system, which is mainly used for providing, to be positioned and complete path in main controller
Planning function, video camera are mainly used for realizing the Lane detection and environment detection of short distance.Satellite and inertial navigation system are comprehensive
According to positioning transposition identify position of the vehicle in satellite plane, and guarantee vehicle in lane line, and camera capture vehicle
Diatom information, to the feedback signal of position one that satellite system determines, thus the more accurate steering and fine tuning for judging vehicle.
Meanwhile (such as in tunnel, high building effect has barrier to block on high in the case that satellite system data is not accurate enough
Deng), by the K mainly based on optical identification, in adjustment algorithm in PIDp,Ki,Kd, and strengthen the specific gravity of nonlinear algorithm,
It uses inertial navigation system as supplement simultaneously, positioning system is enable to remain positioned in a centimetre rank as far as possible, and work as satellite positioning
The overlong time or global position system failure of loss, then direct switchable optics system and inertial navigation system, are existed by inertial navigation system
The function of satellite system is replaced in certain length, optical system continues to identify the precise positioning that lane line keeps vehicle, completes this
Duan Yunying and can self- steering return factory complete maintenance, and when wet weather, the bad weathers such as Thunderstorm Weather cover lane line, then directly lead to
It crosses satellite system and inertial navigation system realizes positioning function, and assisted by inertial navigation, so that complete vehicle location is obtained,
Under the conditions of day and night, adjustable Kp,Ki,Kd, and for the algorithm of weather conditions adjustment nonlinear system, to ensure that day and night
The requirement that condition can be used.Meanwhile the method when encounter road occur the bursts such as barrier change lane the problem of after, can
Original lane is returned to by satellite system, continues to complete operation, redundancy with higher, stability and robustness.Therefore, this
Method influenced by weather and day night environment it is smaller, can round-the-clock, it is most of it is exceedingly odious under the conditions of obtain vehicle
Position, to provide foundation for steering-by-wire.
The present invention is suitable for the electric car of multiaxis heavy duty, can promote the accuracy and redundancy of vehicle self- steering system, and
Integrated use optics turning function synchronous with the lane holding function of satellite-inertial guidance navigation system realization vehicle and more wheels, uses
Electric signal passes to electrically controlled steering device and is also easy to control vehicle；Human-computer interaction interface is provided, driver is facilitated to understand vehicle
Information can also promote the handling of driver in auxiliary driving phase.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than limitation, those skilled in the art
Under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very much
Form, within these are all belonged to the scope of protection of the present invention.
Claims (5)
1. a kind of multiaxis electricity car self- steering method, which comprises the following steps:
The original image that vehicle front and rear sides camera captures is input to mobile unit and carried out to original image pre- by step A.
Processing, obtains pretreated image；
Step B. is directed to pretreated image, carries out local enhancement to vehicle driving region；
Step C. extracts lane line；
Step D. determines vehicle location according to the position of camera and lane line；
Step E. according to vehicle driving constraint condition, with PID control method, fuzzy PID control method, forecast Control Algorithm,
Nonlinear control method control vehicle is run in the track of permission.
2. multiaxis electricity car self- steering method as described in claim 1, which is characterized in that
It further include determining vehicle position using the global position system and/or inertial navigation system that are mounted on intermediate vehicle in the step D
It sets.
3. multiaxis electricity car self- steering method as described in claim 1, which is characterized in that pretreated in the step A
Cheng Yici includes: compression of images, gray scale conversion, filtering processing, equilibrium treatment.
4. multiaxis electricity car self- steering method as described in claim 1, which is characterized in that in the step E, controlled according to PID
The control system of method design steering mechanism's run-through channel processed:Wherein KdFor the micro- of PID control system
Molecular group, KpScale factor, K for PID control systemiFor the integrating factor of PID control system.
5. multiaxis electricity car self- steering method as described in claim 1, which is characterized in that further include basis in the step E
Rule, comfort requirement, line length, noise limitation building cost value function are driven, best vehicle running track is found.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811382390.8A CN109492599A (en) | 2018-11-20 | 2018-11-20 | A kind of multiaxis electricity car self- steering method |
| PCT/CN2019/104833 WO2020103532A1 (en) | 2018-11-20 | 2019-09-09 | Multi-axis electric bus self-guiding method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811382390.8A CN109492599A (en) | 2018-11-20 | 2018-11-20 | A kind of multiaxis electricity car self- steering method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109492599A true CN109492599A (en) | 2019-03-19 |
Family
ID=65696311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811382390.8A Pending CN109492599A (en) | 2018-11-20 | 2018-11-20 | A kind of multiaxis electricity car self- steering method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109492599A (en) |
| WO (1) | WO2020103532A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110472578A (en) * | 2019-08-15 | 2019-11-19 | 宁波中车时代传感技术有限公司 | Lane line keeping method based on lane curvature |
| CN110597252A (en) * | 2019-09-03 | 2019-12-20 | 安徽江淮汽车集团股份有限公司 | Fusion positioning control method, device and equipment for automatic driving automobile and storage medium |
| WO2020103532A1 (en) * | 2018-11-20 | 2020-05-28 | 中车株洲电力机车有限公司 | Multi-axis electric bus self-guiding method |
| CN112224203A (en) * | 2019-06-28 | 2021-01-15 | 北汽福田汽车股份有限公司 | Vehicle control method and device and automobile |
| CN113064344A (en) * | 2021-03-19 | 2021-07-02 | 中山大学 | Trajectory tracking control method for multi-axis unmanned heavy-load vehicle |
| CN113942522A (en) * | 2021-05-31 | 2022-01-18 | 重庆工程职业技术学院 | An intelligent driving safety protection system |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113709344B (en) * | 2021-08-25 | 2023-08-01 | 佛吉亚歌乐电子(丰城)有限公司 | Image data processing method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102167082A (en) * | 2011-03-21 | 2011-08-31 | 武汉理工大学 | Difference active steering system of electric wheel driving automobile and control method thereof |
| CN105718865A (en) * | 2016-01-15 | 2016-06-29 | 武汉光庭科技有限公司 | System and method for road safety detection based on binocular cameras for automatic driving |
| CN106441319A (en) * | 2016-09-23 | 2017-02-22 | 中国科学院合肥物质科学研究院 | A system and method for generating a lane-level navigation map of an unmanned vehicle |
| CN107065689A (en) * | 2017-05-27 | 2017-08-18 | 广东天物新材料科技有限公司 | A kind of novel electric vehicle electric supply installation |
| CN108036794A (en) * | 2017-11-24 | 2018-05-15 | 华域汽车系统股份有限公司 | A kind of high accuracy map generation system and generation method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226354A (en) * | 2013-02-27 | 2013-07-31 | 广东工业大学 | Photoelectricity-navigation-based unmanned road recognition system |
| CN106627582B (en) * | 2016-12-09 | 2019-01-22 | 重庆长安汽车股份有限公司 | Bicycle road automatic Pilot surmounts the path planning system and method for fellow road-users |
| CN108303103B (en) * | 2017-02-07 | 2020-02-07 | 腾讯科技（深圳）有限公司 | Method and device for determining target lane |
| CN107200020B (en) * | 2017-05-11 | 2019-05-31 | 江苏大学 | It is a kind of based on mixing theoretical pilotless automobile self-steering control system and method |
| CN107972663B (en) * | 2018-01-03 | 2024-03-01 | 一汽-大众汽车有限公司 | Vehicle control system, device and method based on intelligent driving technology |
| CN109492599A (en) * | 2018-11-20 | 2019-03-19 | 中车株洲电力机车有限公司 | A kind of multiaxis electricity car self- steering method |
-
2018
- 2018-11-20 CN CN201811382390.8A patent/CN109492599A/en active Pending
-
2019
- 2019-09-09 WO PCT/CN2019/104833 patent/WO2020103532A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102167082A (en) * | 2011-03-21 | 2011-08-31 | 武汉理工大学 | Difference active steering system of electric wheel driving automobile and control method thereof |
| CN105718865A (en) * | 2016-01-15 | 2016-06-29 | 武汉光庭科技有限公司 | System and method for road safety detection based on binocular cameras for automatic driving |
| CN106441319A (en) * | 2016-09-23 | 2017-02-22 | 中国科学院合肥物质科学研究院 | A system and method for generating a lane-level navigation map of an unmanned vehicle |
| CN107065689A (en) * | 2017-05-27 | 2017-08-18 | 广东天物新材料科技有限公司 | A kind of novel electric vehicle electric supply installation |
| CN108036794A (en) * | 2017-11-24 | 2018-05-15 | 华域汽车系统股份有限公司 | A kind of high accuracy map generation system and generation method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020103532A1 (en) * | 2018-11-20 | 2020-05-28 | 中车株洲电力机车有限公司 | Multi-axis electric bus self-guiding method |
| CN112224203A (en) * | 2019-06-28 | 2021-01-15 | 北汽福田汽车股份有限公司 | Vehicle control method and device and automobile |
| CN110472578A (en) * | 2019-08-15 | 2019-11-19 | 宁波中车时代传感技术有限公司 | Lane line keeping method based on lane curvature |
| CN110597252A (en) * | 2019-09-03 | 2019-12-20 | 安徽江淮汽车集团股份有限公司 | Fusion positioning control method, device and equipment for automatic driving automobile and storage medium |
| CN113064344A (en) * | 2021-03-19 | 2021-07-02 | 中山大学 | Trajectory tracking control method for multi-axis unmanned heavy-load vehicle |
| CN113942522A (en) * | 2021-05-31 | 2022-01-18 | 重庆工程职业技术学院 | An intelligent driving safety protection system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020103532A1 (en) | 2020-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492599A (en) | A kind of multiaxis electricity car self- steering method | |
| CN109556615B (en) | Driving map generation method based on multi-sensor fusion cognition of automatic driving | |
| CN113168708B (en) | Lane line tracking method and device | |
| CN106441319B (en) | A system and method for generating a lane-level navigation map of an unmanned vehicle | |
| CN112539755B (en) | Updating point cloud registration pipeline based on ADMM algorithm for autonomous vehicles | |
| Alonso et al. | Accurate global localization using visual odometry and digital maps on urban environments | |
| US20190266748A1 (en) | Crowd-sensed point cloud map | |
| CN114063090B (en) | A method and device for positioning a movable device and a movable device | |
| CN112540593B (en) | Method and device for registering a point cloud for an autonomous vehicle | |
| WO2019052567A1 (en) | Virtual turnout system and method for virtual rail vehicle | |
| CN108572663A (en) | Target Tracking | |
| CN107063275A (en) | Intelligent vehicle map emerging system and method based on roadside device | |
| DE112018004507T5 (en) | INFORMATION PROCESSING DEVICE, MOTION DEVICE AND METHOD AND PROGRAM | |
| CN103940434A (en) | Real-time lane line detecting system based on monocular vision and inertial navigation unit | |
| CN102700548A (en) | Robust vehicular lateral control with front and rear cameras | |
| CN113252022B (en) | A method and device for processing map data | |
| JP2015102449A (en) | Vehicle self position estimation apparatus and vehicle self position estimation method | |
| WO2019065564A1 (en) | Automatic driving controller and method | |
| CN111413990A (en) | Lane change track planning system | |
| KR20220064407A (en) | Onboard cluster tracking system | |
| CN110780287A (en) | Distance measurement method and distance measurement system based on monocular camera | |
| CN113366488A (en) | Autonomous driving data set generation with automatic object tagging method and apparatus | |
| WO2022141240A1 (en) | Determining vehicle positions for autonomous driving based on monocular vision and semantic map | |
| Hara et al. | Vehicle localization based on the detection of line segments from multi-camera images | |
| Lee et al. | Infrastructure node-based vehicle localization for autonomous driving |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190319 |
|
| RJ01 | Rejection of invention patent application after publication |