CN107817790A - A kind of method and apparatus for the curvature for calculating track of vehicle - Google Patents
A kind of method and apparatus for the curvature for calculating track of vehicle Download PDFInfo
- Publication number
- CN107817790A CN107817790A CN201710792205.1A CN201710792205A CN107817790A CN 107817790 A CN107817790 A CN 107817790A CN 201710792205 A CN201710792205 A CN 201710792205A CN 107817790 A CN107817790 A CN 107817790A
- Authority
- CN
- China
- Prior art keywords
- curvature
- tracing point
- vehicle
- observation
- driving trace
- 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
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000001914 filtration Methods 0.000 claims abstract description 49
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012806 monitoring device Methods 0.000 claims description 14
- 241000208340 Araliaceae Species 0.000 claims description 6
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 6
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 6
- 235000008434 ginseng Nutrition 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 description 18
- 230000006870 function Effects 0.000 description 13
- 230000008569 process Effects 0.000 description 12
- 238000012545 processing Methods 0.000 description 12
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000005259 measurement Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 238000005457 optimization Methods 0.000 description 6
- 230000009897 systematic effect Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 230000002452 interceptive effect Effects 0.000 description 5
- 230000002123 temporal effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005183 dynamical system Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
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
- 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
- B60W40/06—Road conditions
- B60W40/072—Curvature of 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
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0253—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow
-
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- 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
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
- G05D1/0278—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using satellite positioning signals, e.g. GPS
-
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
- G05D1/0285—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using signals transmitted via a public communication network, e.g. GSM network
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- G16Z99/00—Subject matter not provided for in other main groups of this subclass
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
It is an object of the invention to provide a kind of method and apparatus for the curvature for calculating track of vehicle.Compared with prior art, the GPS information for the vehicle that present invention basis collects in real time, the driving trace of the vehicle is obtained by clothoid fitting, calculate the observation of the curvature of some tracing point in the driving trace, the steering wheel angle according to corresponding to the vehicle real-time monitored in the tracing point, the predicted value of the curvature of the tracing point is obtained, further according to the observation and predicted value of the curvature of the tracing point, using the optimal value of the curvature of the Kalman filtering acquisition tracing point；The precision for the curvature for calculating vehicle driving trace is substantially increased, when it is applied in automatic driving vehicle, the feasibility of automatic Pilot can be improved.
Description
Technical field
The present invention relates to Vehicular automatic driving technical field, more particularly to a kind of technology for the curvature for calculating track of vehicle.
Background technology
In vehicle operation, the curvature estimation of tracing point is most important in vehicle driving trace, particularly vehicle from
In dynamic driving procedure, if automatic driving vehicle each tracing point of driving trace during automatic Pilot can be calculated accurately
Curvature, then can further accurate follow-up driving model, steering direction, driving trace etc. determination.However, existing track
The computational methods accuracy deficiency of the curvature of point, can not particularly calculate small curvature.
Therefore, how a kind of method for the curvature for efficiently, accurately calculating track of vehicle is provided, turns into people in the art
One of the problem of member's urgent need to resolve.
The content of the invention
It is an object of the invention to provide a kind of method and apparatus for the curvature for calculating track of vehicle.
According to an aspect of the invention, there is provided a kind of method for the curvature for calculating track of vehicle, wherein, this method bag
Include：
A passes through the traveling rail of the clothoid fitting acquisition vehicle according to the GPS information of the vehicle collected in real time
Mark；
B calculates the observation of the curvature of some tracing point in the driving trace；
C steering wheel angles according to corresponding to the vehicle real-time monitored in the tracing point, obtain the tracing point
Curvature predicted value；
D obtains the tracing point according to the observation and predicted value of the curvature of the tracing point using Kalman filtering
The optimal value of curvature.
Preferably, this method also includes：
According to the actual value of the curvature of the tracing point, learnt by deep neural network, obtain the Kalman filtering
Parameter value.
Preferably, the step b includes：
Using Gauss-Newton method, the observation of the curvature of tracing point described in the driving trace is calculated.
Preferably, the step c includes：
The steering wheel angle according to corresponding to the vehicle real-time monitored in the tracing point, it is former using Ackermann steering
Reason, obtain the predicted value of the curvature of the tracing point.
According to another aspect of the present invention, a kind of device for the curvature for calculating track of vehicle is additionally provided, wherein, the dress
Put including：
Device is fitted, for the GPS information according to the vehicle collected in real time, the car is obtained by clothoid fitting
Driving trace；
Computing device, for calculating the observation of the curvature of some tracing point in the driving trace；
Monitoring device, in steering wheel angle corresponding to the tracing point, being obtained according to the vehicle that real-time monitors
Obtain the predicted value of the curvature of the tracing point；
Optimize device, for the observation and predicted value of the curvature according to the tracing point, obtained using Kalman filtering
The optimal value of the curvature of the tracing point.
Preferably, the device also includes：
Learning device, for the actual value of the curvature according to the tracing point, learnt by deep neural network, obtain institute
State the parameter value of Kalman filtering.
Preferably, the computing device is used for：
Using Gauss-Newton method, the observation of the curvature of tracing point described in the driving trace is calculated.
Preferably, the detection means is used for：
The steering wheel angle according to corresponding to the vehicle real-time monitored in the tracing point, it is former using Ackermann steering
Reason, obtain the predicted value of the curvature of the tracing point.
According to a further aspect of the invention, a kind of computer-readable recording medium is additionally provided, it is described computer-readable
Storage medium is stored with computer code, and when the computer code is performed, the method as described in preceding any one is performed.
According to a further aspect of the invention, a kind of computer program product is additionally provided, when the computer program produces
When product are performed by computer equipment, the method as described in preceding any one is performed.
According to a further aspect of the invention, a kind of computer equipment is additionally provided, the computer equipment includes：
One or more processors；
Memory, for storing one or more computer programs；
When one or more of computer programs are by one or more of computing devices so that it is one or
Multiple processors realize the method as described in preceding any one.
Compared with prior art, the present invention is obtained according to the GPS information of the vehicle collected in real time by clothoid fitting
The driving trace of the vehicle is obtained, calculates the observation of the curvature of some tracing point in the driving trace, according to real-time monitoring
The vehicle arrived obtains the predicted value of the curvature of the tracing point in steering wheel angle corresponding to the tracing point, further according to
The observation and predicted value of the curvature of the tracing point, the optimal value of the curvature of the tracing point is obtained using Kalman filtering；
Substantially increase calculate vehicle driving trace curvature precision, when its be applied to automatic driving vehicle in, can improve and drive automatically
The feasibility sailed.
Further, the key parameter of Kalman filtering learns to obtain using deep neural network, and the present invention passes through depth
Neural network learning, tune ginseng is constantly carried out, so as to optimize the Kalman filtering algorithm, to obtain the track closer to True Data
The accurate curvature of point.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, of the invention is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 shows to be suitable to the block diagram for being used for realizing the exemplary computer system/server 12 of embodiment of the present invention；
Fig. 2 shows the schematic flow sheet for being used to calculate the method for the curvature of track of vehicle according to one aspect of the invention；
Fig. 3 shows the structural representation for being used to calculate the device of the curvature of track of vehicle according to a further aspect of the present invention
Figure.
Same or analogous reference represents same or analogous part in accompanying drawing.
Embodiment
It should be mentioned that some exemplary embodiments are described as before exemplary embodiment is discussed in greater detail
The processing described as flow chart or method.Although operations are described as the processing of order by flow chart, therein to be permitted
Multioperation can be implemented concurrently, concomitantly or simultaneously.In addition, the order of operations can be rearranged.When it
The processing can be terminated when operation is completed, it is also possible to the additional step being not included in accompanying drawing.The processing
It can correspond to method, function, code, subroutine, subprogram etc..
Alleged within a context " computer equipment ", also referred to as " computer ", referring to can be by running preset program or referring to
Order performs the intelligent electronic device of the predetermined process process such as numerical computations and/or logical calculated, its can include processor with
Memory, the survival that is prestored in memory by computing device are instructed to perform predetermined process process, or by ASIC,
The hardware such as FPGA, DSP perform predetermined process process, or are realized by said two devices combination.Computer equipment includes but unlimited
In server, PC, notebook computer, tablet personal computer, smart mobile phone etc..
The computer equipment includes user equipment and the network equipment.Wherein, the user equipment includes but is not limited to electricity
Brain, smart mobile phone, PDA etc.；The network equipment includes but is not limited to single network server, multiple webservers form
Server group or the cloud being made up of a large amount of computers or the webserver based on cloud computing (Cloud Computing), wherein,
Cloud computing is one kind of Distributed Calculation, a super virtual computer being made up of the computer collection of a group loose couplings.Its
In, the computer equipment can isolated operation realize the present invention, also can access network and by with other calculating in network
The present invention is realized in the interactive operation of machine equipment.Wherein, the network residing for the computer equipment include but is not limited to internet,
Wide area network, Metropolitan Area Network (MAN), LAN, VPN etc..
It should be noted that the user equipment, the network equipment and network etc. are only for example, other are existing or from now on may be used
The computer equipment or network that can occur such as are applicable to the present invention, should also be included within the scope of the present invention, and to draw
It is incorporated herein with mode.
Method (some of them are illustrated by flow) discussed hereafter can be by hardware, software, firmware, centre
Part, microcode, hardware description language or its any combination are implemented.Implement when with software, firmware, middleware or microcode
When, to implement the program code of necessary task or code segment can be stored in machine or computer-readable medium and (for example deposit
Storage media) in.(one or more) processor can implement necessary task.
Concrete structure and function detail disclosed herein are only representational, and are for describing showing for the present invention
The purpose of example property embodiment.But the present invention can be implemented by many alternative forms, and it is not interpreted as
It is limited only by the embodiments set forth herein.
Although it should be appreciated that may have been used term " first ", " second " etc. herein to describe unit,
But these units should not be limited by these terms.It is used for the purpose of using these terms by a unit and another unit
Make a distinction.For example, in the case of the scope without departing substantially from exemplary embodiment, it is single that first module can be referred to as second
Member, and similarly second unit can be referred to as first module.Term "and/or" used herein above include one of them or
Any and all combination of more listed associated items.
It should be appreciated that when a unit is referred to as " connecting " or during " coupled " to another unit, it can directly connect
Connect or be coupled to another unit, or there may be temporary location.On the other hand, when a unit is referred to as " directly connecting
Connect " or " direct-coupling " when arriving another unit, then in the absence of temporary location.It should in a comparable manner explain and be used to retouch
State the relation between unit other words (such as " between being in ... " compared to " between being directly in ... ", " and with ... it is adjacent
Closely " compared to " with ... be directly adjacent to " etc.).
Term used herein above is not intended to limit exemplary embodiment just for the sake of description specific embodiment.Unless
Context clearly refers else, otherwise singulative used herein above "one", " one " also attempt to include plural number.Should also
When understanding, term " comprising " and/or "comprising" used herein above provide stated feature, integer, step, operation,
The presence of unit and/or component, and do not preclude the presence or addition of other one or more features, integer, step, operation, unit,
Component and/or its combination.
It should further be mentioned that in some replaces realization modes, the function/action being previously mentioned can be according to different from attached
The order indicated in figure occurs.For example, depending on involved function/action, the two width figures shown in succession actually may be used
Substantially simultaneously to perform or can perform in a reverse order sometimes.
The present invention is described in further detail below in conjunction with the accompanying drawings.
Fig. 1 shows the block diagram suitable for being used for the exemplary computer system/server 12 for realizing embodiment of the present invention.
The computer system/server 12 that Fig. 1 is shown is only an example, should not be to the function and use range of the embodiment of the present invention
Bring any restrictions.
As shown in figure 1, computer system/server 12 is showed in the form of universal computing device.Computer system/service
The component of device 12 can include but is not limited to：One or more processor or processing unit 16, system storage 28, connection
The bus 18 of different system component (including system storage 28 and processing unit 16).
Bus 18 represents the one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.Lift
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, MCA (MAC)
Bus, enhanced isa bus, VESA's (VESA) local bus and periphery component interconnection (PCI) bus.
Computer system/server 12 typically comprises various computing systems computer-readable recording medium.These media can be appointed
What usable medium that can be accessed by computer system/server 12, including volatibility and non-volatile media, it is moveable and
Immovable medium.
Memory 28 can include the computer system readable media of form of volatile memory, such as random access memory
Device (RAM) 30 and/or cache memory 32.Computer system/server 12 may further include it is other it is removable/no
Movably, volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for reading and writing
Immovable, non-volatile magnetic media (Fig. 1 is not shown, commonly referred to as " hard disk drive ").Although not shown in Fig. 1, can
To provide the disc driver being used for may move non-volatile magnetic disk (such as " floppy disk ") read-write, and to removable non-volatile
Property CD (such as CD-ROM, DVD-ROM or other optical mediums) read-write CD drive.In these cases, it is each to drive
Dynamic device can be connected by one or more data media interfaces with bus 18.Memory 28 can include at least one program
Product, the program product have one group of (for example, at least one) program module, and these program modules are configured to perform the present invention
The function of each embodiment.
Program/utility 40 with one group of (at least one) program module 42, such as memory 28 can be stored in
In, such program module 42 includes --- but being not limited to --- operating system, one or more application program, other programs
Module and routine data, the realization of network environment may be included in each or certain combination in these examples.Program mould
Block 42 generally performs function and/or method in embodiment described in the invention.
Computer system/server 12 can also be (such as keyboard, sensing equipment, aobvious with one or more external equipments 14
Show device 24 etc.) communication, it can also enable a user to lead to the equipment that the computer system/server 12 interacts with one or more
Letter, and/or any set with make it that the computer system/server 12 communicated with one or more of the other computing device
Standby (such as network interface card, modem etc.) communicates.This communication can be carried out by input/output (I/O) interface 22.And
And computer system/server 12 can also pass through network adapter 20 and one or more network (such as LAN
(LAN), wide area network (WAN) and/or public network, such as internet) communication.As illustrated, network adapter 20 passes through bus
18 communicate with other modules of computer system/server 12.It should be understood that although not shown in Fig. 1, computer can be combined
Systems/servers 12 use other hardware and/or software module, include but is not limited to：Microcode, device driver, at redundancy
Manage unit, external disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 16 is stored in the program in memory 28 by operation, so as to perform various function application and data
Processing.
For example, the various functions for performing the present invention and the computer program of processing, processing are stored with memory 28
When unit 16 performs corresponding computer program, the present invention is implemented in the identification that network-side is intended to incoming call.
The present invention described in detail below is used for the concrete function/step for calculating the curvature of track of vehicle.
Fig. 2 shows the schematic flow sheet for being used to calculate the method for the curvature of track of vehicle according to one aspect of the invention.
In step s 201, device 1 is fitted by clothoid and obtained according to the GPS information of the vehicle collected in real time
The driving trace of the vehicle.
Specifically, in step s 201, device 1 for example passes through the real-time, interactive with the GPS device on vehicle, in real time collection
The GPS information of the vehicle, the GPS information is such as high-precision GPS position information, GPS time information, and GPS time information is also
GPS weeks second temporal information, GPS nanoseconds information can be further refined as.Here, the high-precision GPS information for example may be used
To be obtained by RTK (Real-time kinematic, real-time dynamic positioning) technology, the RTK technologies have used GPS carrier wave
Phase observations amount, and the spatial coherence of observation error between reference station and movement station is make use of, removed by way of difference
Most of error in movement station observation data, so as to realize high-precision positioning, it can obtain Centimeter Level in real time in the wild
Positioning precision.
Then, after device 1 collects multigroup high-precision GPS information of vehicle in real time, in step s 201, device
The 1 multigroup high-precision GPS information collected in real time according to these, it is fitted and is obtained by clothoid (clothoid spline)
The driving trace of the vehicle.Here, because rondo curvature of a curve is linear, and track of vehicle is second order can lead and curvature
Continuously, both are similar, it is therefore possible to use clothoid is fitted the driving trace of vehicle.
Here, the vehicle can be common vehicle, can also be further automatic driving vehicle.The automatic driving vehicle exists
Automatic Pilot process or by human assistance driving procedure, vehicle-mounted GPS apparatus thereon constantly gathers the automatic driving vehicle
High-precision GPS information, such as high-precision GPS position information, GPS weeks second temporal information, GPS nanoseconds information, in step
In S201, device 1 is interacted by the vehicle-mounted GPS apparatus with the automatic driving vehicle, collects the high-precision GPS of vehicle in real time
Information, and the driving trace for obtaining the automatic driving vehicle is fitted by clothoid.
Here, end-to-end driving model of the which for example suitable for Vehicular automatic driving, end-to-end driving model are
Refer to automatic driving vehicle and utilize onboard sensor, such as vehicle-mounted camera, trailer-mounted radar, perception surroundings come determine how into
Row automatic Pilot, such as judge to step on the gas or touch on the brake, determine how and beat steering wheel, the free degree of its Vehicular automatic driving
It is higher；On the other side is tracking driving model, and tracking driving model refers to that automatic driving vehicle is known certainly using high-precision GPS
The position of body, automatic Pilot is carried out along desired guiding trajectory, although comparatively very safe, driving trace is to immobilize
, without so flexible.
Further, above-mentioned end-to-end driving model or tracking driving model are, for example, what is carried out in garden is closed,
This, closing garden refers to the limited scene with limited route, limited physical region, in reality it is more typical as harbour,
Parking lot, fair ground, campus inside etc., certainly, the closing garden can also be customized.
Those skilled in the art will be understood that the mode of above-mentioned collection vehicle GPS information is only for example, and other are existing or modern
The mode for the collection vehicle GPS information being likely to occur afterwards, is such as applicable to the present invention, also should be included in the scope of the present invention with
It is interior, and be incorporated herein by reference herein.
Those skilled in the art should also be understood that the mode that above-mentioned fitting obtains the driving trace of vehicle is only for example, its
His fitting that is existing or being likely to occur from now on obtains the mode of the driving trace of vehicle, is such as applicable to the present invention, should also include
Within the scope of the present invention, and it is incorporated herein by reference herein.
In step S202, device 1 calculates the observation of the curvature of some tracing point in the driving trace.
Specifically, for the driving trace for the vehicle for being fitted to obtain in step s 201, in step S202, device
1 can be directed to wherein some tracing point, calculate the curvature of the tracing point, and the song using the value that the calculating obtains as the tracing point
The observation of rate.Here, the device 1 can calculate the observation of the curvature of multiple tracing points in the driving trace.Here, certain rail
The curvature of mark point is the instantaneous curvature that this refers to tracing point.
Preferably, in step S202, device 1 uses Gauss-Newton method, calculates tracing point described in the driving trace
Curvature observation.
Specifically, in step S202, device can use Gauss-Newton method, to calculate in step s 201 by returning
The curvature of some tracing point in driving trace obtained by rotation curve matching, and the value that the calculating is obtained is as the tracing point
The observation of curvature.Here, some tracing point on the driving trace of vehicle is for example exactly actually the corresponding GPS positions of the vehicle
Put a little, when device 1 is fitted the driving trace of the vehicle using clothoid, can be regarded as these GPS locations of the vehicle
Point is fitted to a clothoid.Due to when the driving trace according to the GPS location point of vehicle using clothoid fitting vehicle
When, may not be that all GPS location points are all fitted on the clothoid, in these GPS location points and the clothoid
Actual point there may be deviation, therefore, in step S202, device 1 can use Gauss-Newton method, calculate these GPS positions
Put a little, i.e. tracing point, curvature observation.
Here, the basic thought of Gauss-Newton method is to go approx to replace nonlinear regression using taylor series expansion
Model, then by successive ignition, regression coefficient is repeatedly corrected, regression coefficient is constantly approached the optimal of nonlinear regression model (NLRM)
Regression coefficient, the residual sum of squares (RSS) of master mould is finally set to reach minimum.
Those skilled in the art will be understood that the mode of the observation of the curvature of above-mentioned calculating tracing point is only for example, its
He it is existing or be likely to occur from now on calculating tracing point curvature observation mode, be such as applicable to the present invention, should also wrap
It is contained within the scope of the present invention, and is incorporated herein by reference herein.
In step S203, the steering wheel according to corresponding to the vehicle real-time monitored in the tracing point of device 1 turns
Angle, obtain the predicted value of the curvature of the tracing point.
Specifically, the curvature of tracing point is due to caused by turn inside diameter in vehicle driving trace, and turn inside diameter is then
Necessarily correspond to the steering wheel on the vehicle has certain corner, here, the vehicle can be carried out with a larger angle
Turn, then now the curvature of corresponding tracing point with regard to larger, only can also be turned, then now with a less angle
The curvature of corresponding tracing point is just smaller.In step S203, device 1 can monitor the steering wheel of the steering wheel of the vehicle in real time
Corner, for example, the steering wheel of the vehicle can be preinstalled with corresponding sensor, and device 1 interacts with the sensor in real time, can be with
The corner of direction disk is obtained by the sensor；Hereafter, the device 1 can travel extremely according to the vehicle real-time monitored
Steering wheel angle corresponding to steering wheel thereon during the tracing point, calculated by certain conversion, obtain the curvature of the tracing point,
And the predicted value using the value that the calculating obtains as the curvature of the tracing point.
Preferably, in step S203, the side according to corresponding to the vehicle real-time monitored in the tracing point of device 1
To disk corner, using Ackermann steering principle, the predicted value of the curvature of the tracing point is obtained.
Specifically, Ackermann steering (Ackermann steerings) be one kind in order to solve vehicle turn when, inside and outside steering
The different geometry in the center of circle pointed in path is taken turns, in step S203, device 1 can use Ackermann steering principle, and combine
Vehicle dynamic parameters build the equation of curvature and steering wheel angle, so as to which device 1 can be according to the car real-time monitored
In steering wheel angle corresponding to the tracing point, the curvature for obtaining tracing point is calculated using the equation, and the calculating is obtained
Predicted value of the value as the curvature of the tracing point.
For example, it is assumed that in step S203, device 1 by the real-time, interactive for the sensor pre-installed with the steering wheel of vehicle,
When knowing that the vehicle is expert to some tracing point of driving trace, steering wheel angle corresponding to steering wheel is 30 degree thereon, so as to,
The device 1, using the equation between foregoing constructed curvature and steering wheel angle, calculates according to foregoing Ackermann steering principle
The curvature for obtaining the tracing point is 0.12, and the predicted value using the value as the tracing point curvature.
Those skilled in the art will be understood that the mode of the predicted value of the curvature of above-mentioned calculating tracing point is only for example, its
He it is existing or be likely to occur from now on calculating tracing point curvature predicted value mode, be such as applicable to the present invention, should also wrap
It is contained within the scope of the present invention, and is incorporated herein by reference herein.
In step S204, device 1 is according to the observation and predicted value of the curvature of the tracing point, using Kalman filtering
Obtain the optimal value of the curvature of the tracing point.
Specifically, in step S204, device 1 is according to the observation of the curvature of the tracing point obtained in step S202
Value, and the predicted value of the curvature according to the tracing point obtained in step S203, using Kalman filtering, obtained to calculate
The optimal value of the curvature of the tracing point.
Here, Kalman filtering (Kalman filtering), which is one kind, utilizes linear system state equation, pass through system
Data are observed in input and output, and the algorithm of optimal estimation is carried out to system mode.Include the noise in system due to observation data
With the influence of interference, so optimal estimation is also considered as filtering.Data filtering is to remove noise reduction True Data
A kind of data processing technique, Kalman filtering can be from a series of numbers that measurement noise be present in the case of known to measurement variance
In, the state of dynamical system is estimated.
Kalman filtering is simply introduced below：
The system for introducing a discrete control process, the system can be described with a linear random differential equation：
X (k)=AX (k-1)+B U (k)+W (k)
Along with the measured value of system：
Z (k)=H X (k)+V (k)
In upper two formula, X (k) is the system mode at k moment, and U (k) is controlled quentity controlled variable of the k moment to system, if do not controlled
Amount processed, it can be 0.A and B is systematic parameter, and for Multi-model System, it is matrix.Z (k) is the measured value at k moment, and H is
The parameter of measuring system, for more measuring systems, H is matrix.W (k) and V (k) represents the noise of process and measurement, its quilt respectively
White Gaussian noise is assumed, its covariance is Q, R respectively, it is assumed herein that the white Gaussian noise does not become with system state change
Change.
Assuming that present system mode is k, according to the model of system, appearance can be predicted based on the laststate of system
In state：
X (k | k-1)=AX (k-1 | k-1)+B U (k) ... ... .. (1)
In formula (1), X (k | k-1) is using the result of laststate prediction, and X (k-1 | k-1) is the optimal knot of laststate
Fruit, U (k) are the controlled quentity controlled variable of present status, if without controlled quentity controlled variable, it can be 0.
Till now, the system results have updated, and still, not updated also corresponding to X (k | k-1) covariance.
Herein covariance is represented with P：
P (k | k-1)=AP (k-1 | k-1) A '+Q ... ... (2)
In formula (2), P (k | k-1) is covariance corresponding to X (k | k-1), and P (k-1 | k-1) is assisted corresponding to X (k-1 | k-1)
Variance, A ' represent A transposed matrix, and Q is the covariance of systematic procedure.
Above-mentioned formula (1) and (2) are the predictions to system, are obtaining the prediction result of present status and then are collecting present
The measured value of state.With reference to predicted value and measured value, the optimization estimated value X (k | k) of present status (k) can be obtained：
X (k | k)=X (k | k-1)+Kg (k) (Z (k)-H X (k | k-1)) ... ... (3)
Wherein Kg is kalman gain：
Kg (k)=P (k | k-1) H '/(H P (k | k-1) H '+R) ... ... (4)
Here, estimated value X optimal under k-state (k | k) is obtained.But it is intended to make Kalman filter constantly transport
Row goes down until systematic procedure terminates, and also to update X under k-state (k | k) covariance：
P (k | k)=(I-Kg (k) H) P (k | k-1) ... ... (5)
Wherein I is 1 matrix, is measured for single model list, I=1.When system enters k+1 states, and P (k | k) it is exactly formula
(2) P (k-1 | k-1).So, the autoregressive computing of algorithm can is gone down.
Here, because device 1 has obtained the observation of the curvature of tracing point in step S202, in step S203
The predicted value of curvature through obtaining tracing point, device 1 can be further combined with the parameter of the Kalman filtering, in step S204
In, the optimal value of the curvature of the tracing point is obtained using Kalman filtering.
Preferably, this method also includes step S205 (not shown).In step S205, device 1 is according to the tracing point
Curvature actual value, learnt by deep neural network, obtain the parameter value of the Kalman filtering.
Specifically, the curvature of each tracing point of the driving trace of the vehicle can have actual value, and the actual value is for example
There is provided by vehicular manufacturer, in step S205, device 1 passes through depth nerve net according to the actual value of the curvature of the tracing point
Network learns, and obtains the parameter value of the Kalman filtering.For example, the parameter value of Kalman filtering is foregoing covariance herein, in this way
Covariance matrix, can to the covariance matrix set initial value, the initial value can be rule of thumb set or even with
Meaning is set, and can be restrained by deep neural network study, for example, after the initial value of covariance matrix is set,
According to the calculating of aforementioned formula, an error can be obtained, and then feeds back the error, so as to correct the covariance matrix, not
Disconnected feedback, so as to carry out tune ginseng, is restrained the covariance matrix, optimizes the Kalman filtering algorithm, therefore, in step
In S205, device 1 is learnt by deep neural network, obtains the parameter value of the Kalman filtering.Then, in step S204,
Device 1, using Kalman filtering, obtains further according to the observation and predicted value of the curvature of the foregoing tracing point being calculated to calculate
Obtain the optimal value of the curvature of the tracing point.
Here, GPS information of the device 1 according to the vehicle collected in real time, the vehicle is obtained by clothoid fitting
Driving trace, the observation of the curvature of some tracing point in the driving trace is calculated, according to the car real-time monitored
In steering wheel angle corresponding to the tracing point, the predicted value of the curvature of the tracing point is obtained, further according to the tracing point
Curvature observation and predicted value, the optimal value of the curvature of the tracing point is obtained using Kalman filtering；Substantially increase
The precision of the curvature of vehicle driving trace is calculated, when it is applied in automatic driving vehicle, the feasibility of automatic Pilot can be improved.
Further, the key parameter of Kalman filtering learns to obtain using deep neural network, and device 1 passes through depth god
Through e-learning, tune ginseng is constantly carried out, so as to optimize the Kalman filtering algorithm, to obtain the tracing point closer to True Data
Accurate curvature.
Fig. 3 shows the structural representation for being used to calculate the device of the curvature of track of vehicle according to a further aspect of the present invention
Figure.
Device 1 includes fitting device 301, computing device 302, monitoring device 303 and optimization device 304.The device 1 is for example
In computer equipment, the computer equipment is located in automatic driving vehicle for example in vehicle, or further, can also
It is that with the vehicle or further, automatic driving vehicle, the network equipment being connected by network, further, the device 1 can
It is located at partial devices in the network equipment, partial devices are located in vehicle, for example, foregoing fitting device 301, computing device 302
It is located at optimization device 304 in the network equipment, foregoing monitoring device 303 is located in vehicle.Those skilled in the art will be understood that
Said apparatus present position is only for example, and other device present positions that are existing or being likely to occur from now on, is such as applicable to this hair
It is bright, it should also be included within the scope of the present invention, and be incorporated herein by reference herein.
GPS information of the device 301 according to the vehicle collected in real time is fitted, the vehicle is obtained by clothoid fitting
Driving trace.
Specifically, device 301 is fitted for example by the real-time, interactive with the GPS device on vehicle, gathers the vehicle in real time
GPS information, such as high-precision GPS position information, GPS time information, GPS time information can also enter the GPS information
Step refining is GPS weeks second temporal information, GPS nanoseconds information.Here, the high-precision GPS information can for example pass through
RTK (Real-time kinematic, real-time dynamic positioning) technology obtains, and the RTK technologies have used GPS carrier phase to see
Measurement, and the spatial coherence of observation error between reference station and movement station is make use of, movement station is removed by way of difference
The most of error observed in data, so as to realize high-precision positioning, it can obtain the positioning of Centimeter Level in real time in the wild
Precision.
Then, after device 1 collects multigroup high-precision GPS information of vehicle in real time, fitting device 301 is according to this
A little multigroup high-precision GPS information collected in real time, the vehicle is obtained by clothoid (clothoid spline) fitting
Driving trace.Here, because rondo curvature of a curve is linear, and track of vehicle is second order can lead and continual curvature,
Both are similar, it is therefore possible to use clothoid is fitted the driving trace of vehicle.
Here, the vehicle can be common vehicle, can also be further automatic driving vehicle.The automatic driving vehicle exists
Automatic Pilot process or by human assistance driving procedure, vehicle-mounted GPS apparatus thereon constantly gathers the automatic driving vehicle
High-precision GPS information, such as high-precision GPS position information, GPS weeks second temporal information, GPS nanoseconds information, fitting dress
301 interacting by the vehicle-mounted GPS apparatus with the automatic driving vehicle are put, collect the high-precision GPS information of vehicle in real time, and
The driving trace for obtaining the automatic driving vehicle is fitted by clothoid.
Here, end-to-end driving model of the which for example suitable for Vehicular automatic driving, end-to-end driving model are
Refer to automatic driving vehicle and utilize onboard sensor, such as vehicle-mounted camera, trailer-mounted radar, perception surroundings come determine how into
Row automatic Pilot, such as judge to step on the gas or touch on the brake, determine how and beat steering wheel, the free degree of its Vehicular automatic driving
It is higher；On the other side is tracking driving model, and tracking driving model refers to that automatic driving vehicle is known certainly using high-precision GPS
The position of body, automatic Pilot is carried out along desired guiding trajectory, although comparatively very safe, driving trace is to immobilize
, without so flexible.
Further, above-mentioned end-to-end driving model or tracking driving model are, for example, what is carried out in garden is closed,
This, closing garden refers to the limited scene with limited route, limited physical region, in reality it is more typical as harbour,
Parking lot, fair ground, campus inside etc., certainly, the closing garden can also be customized.
Those skilled in the art will be understood that the mode of above-mentioned collection vehicle GPS information is only for example, and other are existing or modern
The mode for the collection vehicle GPS information being likely to occur afterwards, is such as applicable to the present invention, also should be included in the scope of the present invention with
It is interior, and be incorporated herein by reference herein.
Those skilled in the art should also be understood that the mode that above-mentioned fitting obtains the driving trace of vehicle is only for example, its
His fitting that is existing or being likely to occur from now on obtains the mode of the driving trace of vehicle, is such as applicable to the present invention, should also include
Within the scope of the present invention, and it is incorporated herein by reference herein.
Computing device 302 calculates the observation of the curvature of some tracing point in the driving trace.
Specifically, the obtained driving trace of the vehicle is fitted for fitting device 301, computing device 302 can be with pin
To wherein some tracing point, the curvature of the tracing point, and the sight using the value that the calculating obtains as the curvature of the tracing point are calculated
Measured value.Here, the computing device 1 can calculate the observation of the curvature of multiple tracing points in the driving trace.Here, certain track
The curvature of point is the instantaneous curvature that this refers to tracing point.
Preferably, computing device 302 uses Gauss-Newton method, calculates the curvature of tracing point described in the driving trace
Observation.
Specifically, computing device 302 can use Gauss-Newton method, carry out digital simulation device 301 and intended by clothoid
The curvature of some tracing point in driving trace obtained by closing, and the sight using the value that the calculating obtains as the curvature of the tracing point
Measured value.Here, some tracing point on the driving trace of vehicle is for example exactly actually the corresponding GPS location point of the vehicle, intend
Attach together put 301 using clothoids be fitted the driving trace of the vehicle when, can be regarded as these GPS location points of the vehicle
It is fitted to a clothoid.Due to when according to the GPS location point of vehicle using clothoid fitting vehicle driving trace when,
May not be that all GPS location points are all fitted on the clothoid, these GPS location points and the reality in the clothoid
Border point there may be deviation, and therefore, computing device 302 can use Gauss-Newton method, calculate these GPS location points, i.e. rail
Mark point, curvature observation.
Here, the basic thought of Gauss-Newton method is to go approx to replace nonlinear regression using taylor series expansion
Model, then by successive ignition, regression coefficient is repeatedly corrected, regression coefficient is constantly approached the optimal of nonlinear regression model (NLRM)
Regression coefficient, the residual sum of squares (RSS) of master mould is finally set to reach minimum.
Those skilled in the art will be understood that the mode of the observation of the curvature of above-mentioned calculating tracing point is only for example, its
He it is existing or be likely to occur from now on calculating tracing point curvature observation mode, be such as applicable to the present invention, should also wrap
It is contained within the scope of the present invention, and is incorporated herein by reference herein.
The steering wheel angle according to corresponding to the vehicle real-time monitored in the tracing point of monitoring device 303, obtain
The predicted value of the curvature of the tracing point.
Specifically, the curvature of tracing point is due to caused by turn inside diameter in vehicle driving trace, and turn inside diameter is then
Necessarily correspond to the steering wheel on the vehicle has certain corner, here, the vehicle can be carried out with a larger angle
Turn, then now the curvature of corresponding tracing point with regard to larger, only can also be turned, then now with a less angle
The curvature of corresponding tracing point is just smaller.Monitoring device 303 can monitor the steering wheel angle of the steering wheel of the vehicle, example in real time
Such as, the steering wheel of the vehicle can be preinstalled with corresponding sensor, and monitoring device 303 interacts with the sensor in real time, can be with
The corner of direction disk is obtained by the sensor；Hereafter, the monitoring device 303 can exist according to the vehicle real-time monitored
Travel to the steering wheel angle corresponding to steering wheel thereon during the tracing point, calculated by certain conversion, obtain the tracing point
Curvature, and the predicted value using the value that the calculating obtains as the curvature of the tracing point.
Preferably, the steering wheel according to corresponding to the vehicle real-time monitored in the tracing point of monitoring device 303 turns
Angle, using Ackermann steering principle, obtain the predicted value of the curvature of the tracing point.
Specifically, Ackermann steering (Ackermann steerings) be one kind in order to solve vehicle turn when, inside and outside steering
The different geometry in the center of circle pointed in path is taken turns, monitoring device 303 can use Ackermann steering principle, and combine vehicle power
The equation of parameter structure curvature and steering wheel angle is learned, so as to which monitoring device 303 can be according to the vehicle real-time monitored
In steering wheel angle corresponding to the tracing point, the curvature for obtaining tracing point is calculated using the equation, and the calculating is obtained
It is worth the predicted value of the curvature as the tracing point.
For example, it is assumed that monitoring device 303 knows the car by the real-time, interactive for the sensor pre-installed with the steering wheel of vehicle
When being expert to some tracing point of driving trace, steering wheel angle corresponding to steering wheel is 30 degree thereon, so as to which the monitoring fills
303 are put according to foregoing Ackermann steering principle, using the equation between foregoing constructed curvature and steering wheel angle, calculating obtains
The curvature for obtaining the tracing point is 0.12, and the predicted value using the value as the tracing point curvature.
Those skilled in the art will be understood that the mode of the predicted value of the curvature of above-mentioned calculating tracing point is only for example, its
He it is existing or be likely to occur from now on calculating tracing point curvature predicted value mode, be such as applicable to the present invention, should also wrap
It is contained within the scope of the present invention, and is incorporated herein by reference herein.
Optimize observation and predicted value of the device 304 according to the curvature of the tracing point, institute is obtained using Kalman filtering
State the optimal value of the curvature of tracing point.
Specifically, the observation of the curvature for the tracing point that optimization device 304 is obtained according to computing device 302, Yi Jigen
The predicted value of the curvature of the tracing point obtained according to monitoring device 303, using Kalman filtering, the tracing point is obtained to calculate
Curvature optimal value.
Here, Kalman filtering (Kalman filtering), which is one kind, utilizes linear system state equation, pass through system
Data are observed in input and output, and the algorithm of optimal estimation is carried out to system mode.Include the noise in system due to observation data
With the influence of interference, so optimal estimation is also considered as filtering.Data filtering is to remove noise reduction True Data
A kind of data processing technique, Kalman filtering can be from a series of numbers that measurement noise be present in the case of known to measurement variance
In, the state of dynamical system is estimated.
Kalman filtering is simply introduced below：
The system for introducing a discrete control process, the system can be described with a linear random differential equation：
X (k)=AX (k-1)+B U (k)+W (k)
Along with the measured value of system：
Z (k)=H X (k)+V (k)
In upper two formula, X (k) is the system mode at k moment, and U (k) is controlled quentity controlled variable of the k moment to system, if do not controlled
Amount processed, it can be 0.A and B is systematic parameter, and for Multi-model System, it is matrix.Z (k) is the measured value at k moment, and H is
The parameter of measuring system, for more measuring systems, H is matrix.W (k) and V (k) represents the noise of process and measurement, its quilt respectively
White Gaussian noise is assumed, its covariance is Q, R respectively, it is assumed herein that the white Gaussian noise does not become with system state change
Change.
Assuming that present system mode is k, according to the model of system, appearance can be predicted based on the laststate of system
In state：
X (k | k-1)=A X (k-1 | k-1)+B U (k) ... ... .. (1)
In formula (1), X (k | k-1) is using the result of laststate prediction, and X (k-1 | k-1) is the optimal knot of laststate
Fruit, U (k) are the controlled quentity controlled variable of present status, if without controlled quentity controlled variable, it can be 0.
Till now, the system results have updated, and still, not updated also corresponding to X (k | k-1) covariance.
Herein covariance is represented with P：
P (k | k-1)=A P (k-1 | k-1) A '+Q ... ... (2)
In formula (2), P (k | k-1) is covariance corresponding to X (k | k-1), and P (k-1 | k-1) is assisted corresponding to X (k-1 | k-1)
Variance, A ' represent A transposed matrix, and Q is the covariance of systematic procedure.
Above-mentioned formula (1) and (2) are the predictions to system, are obtaining the prediction result of present status and then are collecting present
The measured value of state.With reference to predicted value and measured value, the optimization estimated value X (k | k) of present status (k) can be obtained：
X (k | k)=X (k | k-1)+Kg (k) (Z (k)-H X (k | k-1)) ... ... (3)
Wherein Kg is kalman gain：
Kg (k)=P (k | k-1) H '/(H P (k | k-1) H '+R) ... ... (4)
Here, estimated value X optimal under k-state (k | k) is obtained.But it is intended to make Kalman filter constantly transport
Row goes down until systematic procedure terminates, and also to update X under k-state (k | k) covariance：
P (k | k)=(I-Kg (k) H) P (k | k-1) ... ... (5)
Wherein I is 1 matrix, is measured for single model list, I=1.When system enters k+1 states, and P (k | k) it is exactly formula
(2) P (k-1 | k-1).So, the autoregressive computing of algorithm can is gone down.
Here, because computing device 302 has obtained the observation of the curvature of tracing point, monitoring device 303 has obtained
The predicted value of the curvature of tracing point, optimization device 304 can be filtered further combined with the parameter of the Kalman filtering using Kalman
Ripple obtains the optimal value of the curvature of the tracing point.
Preferably, the device 1 also includes learning device (not shown).Learning device is true according to the curvature of the tracing point
Real value, learnt by deep neural network, obtain the parameter value of the Kalman filtering.
Specifically, the curvature of each tracing point of the driving trace of the vehicle can have actual value, and the actual value is for example
There is provided by vehicular manufacturer, learning device is learnt by deep neural network, obtained according to the actual value of the curvature of the tracing point
The parameter value of the Kalman filtering.For example, the parameter value of Kalman filtering is foregoing covariance herein, covariance matrix in this way,
Initial value can be set to the covariance matrix, and the initial value can rule of thumb be set or even arbitrarily set, and pass through
Deep neural network study can be restrained, for example, after the initial value of covariance matrix is set, according to aforementioned formula
Calculating, an error can be obtained, and then feed back the error, so as to correct the covariance matrix, and constantly fed back, so as to enter
Row adjusts ginseng, is restrained the covariance matrix, optimizes the Kalman filtering algorithm, and therefore, learning device passes through depth nerve
E-learning, obtain the parameter value of the Kalman filtering.Then, device 304 is optimized further according to the foregoing tracing point being calculated
Curvature observation and predicted value, using Kalman filtering, to calculate the optimal value for the curvature for obtaining the tracing point.
Here, GPS information of the device 1 according to the vehicle collected in real time, the vehicle is obtained by clothoid fitting
Driving trace, the observation of the curvature of some tracing point in the driving trace is calculated, according to the car real-time monitored
In steering wheel angle corresponding to the tracing point, the predicted value of the curvature of the tracing point is obtained, further according to the tracing point
Curvature observation and predicted value, the optimal value of the curvature of the tracing point is obtained using Kalman filtering；Substantially increase
The precision of the curvature of vehicle driving trace is calculated, when it is applied in automatic driving vehicle, the feasibility of automatic Pilot can be improved.
Further, the key parameter of Kalman filtering learns to obtain using deep neural network, and device 1 passes through depth god
Through e-learning, tune ginseng is constantly carried out, so as to optimize the Kalman filtering algorithm, to obtain the tracing point closer to True Data
Accurate curvature.
Present invention also offers a kind of computer-readable recording medium, the computer-readable recording medium storage has calculating
Machine code, when the computer code is performed, the method as described in preceding any one is performed.
Present invention also offers a kind of computer program product, when the computer program product is performed by computer equipment
When, the method as described in preceding any one is performed.
Present invention also offers a kind of computer equipment, the computer equipment includes：
One or more processors；
Memory, for storing one or more computer programs；
When one or more of computer programs are by one or more of computing devices so that it is one or
Multiple processors realize the method as described in preceding any one.
It should be noted that the present invention can be carried out in the assembly of software and/or software and hardware, for example, this hair
Bright each device can using application specific integrated circuit (ASIC) or any other realized similar to hardware device.In one embodiment
In, software program of the invention can realize steps described above or function by computing device.Similarly, it is of the invention
Software program (including related data structure) can be stored in computer readable recording medium storing program for performing, for example, RAM memory,
Magnetically or optically driver or floppy disc and similar devices.In addition, some steps or function of the present invention can employ hardware to realize, example
Such as, coordinate as with processor so as to perform the circuit of each step or function.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit requires rather than described above limits, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Any reference in claim should not be considered as to the involved claim of limitation.This
Outside, it is clear that the word of " comprising " one is not excluded for other units or step, and odd number is not excluded for plural number.That is stated in system claims is multiple
Unit or device can also be realized by a unit or device by software or hardware.The first, the second grade word is used for table
Show title, and be not offered as any specific order.
Claims (11)
1. a kind of method for the curvature for calculating track of vehicle, wherein, this method includes：
A passes through the driving trace of the clothoid fitting acquisition vehicle according to the GPS information of the vehicle collected in real time；
B calculates the observation of the curvature of some tracing point in the driving trace；
C steering wheel angles according to corresponding to the vehicle real-time monitored in the tracing point, obtain the song of the tracing point
The predicted value of rate；
D obtains the curvature of the tracing point using Kalman filtering according to the observation and predicted value of the curvature of the tracing point
Optimal value.
2. according to the method for claim 1, wherein, this method also includes：
According to the actual value of the curvature of the tracing point, learnt by deep neural network, obtain the ginseng of the Kalman filtering
Numerical value.
3. method according to claim 1 or 2, wherein, the step b includes：
Using Gauss-Newton method, the observation of the curvature of tracing point described in the driving trace is calculated.
4. according to the method in any one of claims 1 to 3, wherein, the step c includes：
The steering wheel angle according to corresponding to the vehicle real-time monitored in the tracing point, using Ackermann steering principle,
Obtain the predicted value of the curvature of the tracing point.
5. a kind of device for the curvature for calculating track of vehicle, wherein, the device includes：
Device is fitted, for the GPS information according to the vehicle collected in real time, the vehicle is obtained by clothoid fitting
Driving trace；
Computing device, for calculating the observation of the curvature of some tracing point in the driving trace；
Monitoring device, for the vehicle that basis real-time monitors in steering wheel angle corresponding to the tracing point, acquisition institute
State the predicted value of the curvature of tracing point；
Optimize device, for the observation and predicted value of the curvature according to the tracing point, obtained using Kalman filtering described in
The optimal value of the curvature of tracing point.
6. device according to claim 5, wherein, the device also includes：
Learning device, for the actual value of the curvature according to the tracing point, learnt by deep neural network, obtain the card
The parameter value of Kalman Filtering.
7. the device according to claim 5 or 6, wherein, the computing device is used for：
Using Gauss-Newton method, the observation of the curvature of tracing point described in the driving trace is calculated.
8. the device according to any one of claim 5 to 7, wherein, the detection means is used for：
The steering wheel angle according to corresponding to the vehicle real-time monitored in the tracing point, using Ackermann steering principle,
Obtain the predicted value of the curvature of the tracing point.
9. a kind of computer-readable recording medium, the computer-readable recording medium storage has computer code, when the meter
When calculation machine code is performed, the method as any one of Claims 1-4 is performed.
10. a kind of computer program product, when the computer program product is performed by computer equipment, such as claim 1
It is performed to the method any one of 4.
11. a kind of computer equipment, the computer equipment includes：
One or more processors；
Memory, for storing one or more computer programs；
When one or more of computer programs are by one or more of computing devices so that one or more of
Processor realizes the method as any one of Claims 1-4.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710792205.1A CN107817790B (en) | 2017-09-05 | 2017-09-05 | Method and device for calculating curvature of vehicle track |
| PCT/CN2018/098609 WO2019047639A1 (en) | 2017-09-05 | 2018-08-03 | Method and device for calculating curvature of vehicle trajectory |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710792205.1A CN107817790B (en) | 2017-09-05 | 2017-09-05 | Method and device for calculating curvature of vehicle track |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107817790A true CN107817790A (en) | 2018-03-20 |
| CN107817790B CN107817790B (en) | 2020-12-22 |
Family
ID=61600898
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710792205.1A Active CN107817790B (en) | 2017-09-05 | 2017-09-05 | Method and device for calculating curvature of vehicle track |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107817790B (en) |
| WO (1) | WO2019047639A1 (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108445886A (en) * | 2018-04-25 | 2018-08-24 | 北京联合大学 | A kind of automatic driving vehicle lane-change method and system for planning based on Gauss equation |
| WO2019047639A1 (en) * | 2017-09-05 | 2019-03-14 | 百度在线网络技术（北京）有限公司 | Method and device for calculating curvature of vehicle trajectory |
| CN109606467A (en) * | 2018-12-29 | 2019-04-12 | 百度在线网络技术（北京）有限公司 | A kind of vehicle steering method and vehicle |
| CN109795484A (en) * | 2018-12-24 | 2019-05-24 | 百度在线网络技术（北京）有限公司 | Control method for vehicle and equipment |
| CN110262509A (en) * | 2019-07-10 | 2019-09-20 | 百度在线网络技术（北京）有限公司 | Vehicular automatic driving method and apparatus |
| CN110286671A (en) * | 2019-04-29 | 2019-09-27 | 北京工业大学 | A kind of automatic driving vehicle path generating method based on clothoid |
| CN111829540A (en) * | 2020-06-04 | 2020-10-27 | 北京百度网讯科技有限公司 | Driving track generation method and device, electronic equipment and storage medium |
| CN112622934A (en) * | 2020-12-25 | 2021-04-09 | 上海商汤临港智能科技有限公司 | Reference track point and reference track generation method, driving method and vehicle |
| CN113460084A (en) * | 2021-06-11 | 2021-10-01 | 北京汽车研究总院有限公司 | Method and device for determining vehicle driving intention, vehicle and storage medium |
| CN113650618A (en) * | 2021-09-23 | 2021-11-16 | 东软睿驰汽车技术（上海）有限公司 | Vehicle track determination method and related device |
| CN114312770A (en) * | 2020-10-09 | 2022-04-12 | 郑州宇通客车股份有限公司 | Vehicle, and vehicle driving track prediction method and device |
| CN117584982A (en) * | 2023-12-28 | 2024-02-23 | 上海保隆汽车科技股份有限公司 | Curve radius estimation method, system, medium, electronic equipment, vehicle machine and vehicle |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114877904A (en) * | 2022-05-07 | 2022-08-09 | 广西睛智汽车技术有限公司 | Road curvature estimation method, road curvature measurement device and computer equipment |
| CN115035185B (en) * | 2022-05-26 | 2024-02-27 | 郑州大学 | Method for identifying flat curve by using curvature and curvature change rate |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202987136U (en) * | 2012-12-07 | 2013-06-12 | 长安大学 | Front-road curvature estimation device |
| WO2014149042A1 (en) * | 2013-03-20 | 2014-09-25 | International Truck Intellectual Property Company, Llc | Smart cruise control system |
| CN106681335A (en) * | 2017-01-22 | 2017-05-17 | 无锡卡尔曼导航技术有限公司 | Obstacle-avoiding route planning and control method for unmanned agricultural machine driving |
| CN106965801A (en) * | 2015-12-08 | 2017-07-21 | 福特全球技术公司 | Vehicle curvature is determined |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3911492B2 (en) * | 2003-06-26 | 2007-05-09 | トヨタ自動車株式会社 | Vehicle travel support device |
| JP4801637B2 (en) * | 2007-07-19 | 2011-10-26 | 三菱重工業株式会社 | Vehicle steering control method and apparatus |
| JP5429234B2 (en) * | 2011-03-23 | 2014-02-26 | トヨタ自動車株式会社 | Information processing apparatus for vehicle |
| US9393996B2 (en) * | 2012-01-06 | 2016-07-19 | Honda Motor Co., Ltd. | Reverse drive assist for long wheelbase dual axle trailers |
| CN106515722B (en) * | 2016-11-08 | 2018-09-21 | 西华大学 | A kind of method for planning track of vertically parking |
| CN107817790B (en) * | 2017-09-05 | 2020-12-22 | 百度在线网络技术（北京）有限公司 | Method and device for calculating curvature of vehicle track |
-
2017
- 2017-09-05 CN CN201710792205.1A patent/CN107817790B/en active Active
-
2018
- 2018-08-03 WO PCT/CN2018/098609 patent/WO2019047639A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202987136U (en) * | 2012-12-07 | 2013-06-12 | 长安大学 | Front-road curvature estimation device |
| WO2014149042A1 (en) * | 2013-03-20 | 2014-09-25 | International Truck Intellectual Property Company, Llc | Smart cruise control system |
| CN106965801A (en) * | 2015-12-08 | 2017-07-21 | 福特全球技术公司 | Vehicle curvature is determined |
| CN106681335A (en) * | 2017-01-22 | 2017-05-17 | 无锡卡尔曼导航技术有限公司 | Obstacle-avoiding route planning and control method for unmanned agricultural machine driving |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019047639A1 (en) * | 2017-09-05 | 2019-03-14 | 百度在线网络技术（北京）有限公司 | Method and device for calculating curvature of vehicle trajectory |
| CN108445886A (en) * | 2018-04-25 | 2018-08-24 | 北京联合大学 | A kind of automatic driving vehicle lane-change method and system for planning based on Gauss equation |
| CN109795484A (en) * | 2018-12-24 | 2019-05-24 | 百度在线网络技术（北京）有限公司 | Control method for vehicle and equipment |
| CN109606467A (en) * | 2018-12-29 | 2019-04-12 | 百度在线网络技术（北京）有限公司 | A kind of vehicle steering method and vehicle |
| CN109606467B (en) * | 2018-12-29 | 2023-05-09 | 百度在线网络技术（北京）有限公司 | Vehicle steering method and vehicle |
| CN110286671B (en) * | 2019-04-29 | 2022-03-29 | 北京工业大学 | Automatic driving vehicle path generation method based on clothoid curve |
| CN110286671A (en) * | 2019-04-29 | 2019-09-27 | 北京工业大学 | A kind of automatic driving vehicle path generating method based on clothoid |
| US11338853B2 (en) | 2019-07-10 | 2022-05-24 | Apollo Intelligent Driving Technology (Beijing) Co., Ltd. | Methods, devices, and media for autonomously driving vehicle |
| CN110262509B (en) * | 2019-07-10 | 2022-06-28 | 百度在线网络技术（北京）有限公司 | Automatic vehicle driving method and device |
| CN110262509A (en) * | 2019-07-10 | 2019-09-20 | 百度在线网络技术（北京）有限公司 | Vehicular automatic driving method and apparatus |
| CN111829540A (en) * | 2020-06-04 | 2020-10-27 | 北京百度网讯科技有限公司 | Driving track generation method and device, electronic equipment and storage medium |
| CN114312770A (en) * | 2020-10-09 | 2022-04-12 | 郑州宇通客车股份有限公司 | Vehicle, and vehicle driving track prediction method and device |
| CN114312770B (en) * | 2020-10-09 | 2023-07-07 | 宇通客车股份有限公司 | Vehicle, vehicle running track prediction method and device |
| CN112622934A (en) * | 2020-12-25 | 2021-04-09 | 上海商汤临港智能科技有限公司 | Reference track point and reference track generation method, driving method and vehicle |
| CN113460084A (en) * | 2021-06-11 | 2021-10-01 | 北京汽车研究总院有限公司 | Method and device for determining vehicle driving intention, vehicle and storage medium |
| CN113650618A (en) * | 2021-09-23 | 2021-11-16 | 东软睿驰汽车技术（上海）有限公司 | Vehicle track determination method and related device |
| CN117584982A (en) * | 2023-12-28 | 2024-02-23 | 上海保隆汽车科技股份有限公司 | Curve radius estimation method, system, medium, electronic equipment, vehicle machine and vehicle |
| CN117584982B (en) * | 2023-12-28 | 2024-04-23 | 上海保隆汽车科技股份有限公司 | Curve radius estimation method, system, medium, electronic equipment, vehicle machine and vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107817790B (en) | 2020-12-22 |
| WO2019047639A1 (en) | 2019-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107817790A (en) | A kind of method and apparatus for the curvature for calculating track of vehicle | |
| US20240011776A9 (en) | Vision-aided inertial navigation | |
| Llorca et al. | Autonomous pedestrian collision avoidance using a fuzzy steering controller | |
| Klančar et al. | A control strategy for platoons of differential drive wheeled mobile robot | |
| CN111923927B (en) | Method and apparatus for interactive perception of traffic scene prediction | |
| Erfani et al. | Comparison of two data fusion methods for localization of wheeled mobile robot in farm conditions | |
| CN109416539A (en) | The method and system of the course changing control of the autonomous vehicle of use ratio, integral and differential (PID) controller | |
| Marin et al. | Event-based localization in ackermann steering limited resource mobile robots | |
| CN111208814B (en) | Memory-based optimal motion planning for an automatic vehicle using dynamic models | |
| Khan et al. | Design and experimental validation of a robust model predictive control for the optimal trajectory tracking of a small-scale autonomous bulldozer | |
| CN112433531A (en) | Trajectory tracking method and device for automatic driving vehicle and computer equipment | |
| Dai et al. | A novel STSOSLAM algorithm based on strong tracking second order central difference Kalman filter | |
| CN111708010B (en) | Mobile equipment positioning method, device and system and mobile equipment | |
| Fu et al. | An improved integrated navigation method based on RINS, GNSS and kinematics for port heavy-duty AGV | |
| Parra-Tsunekawa et al. | A kalman-filtering-based approach for improving terrain mapping in off-road autonomous vehicles | |
| Drage | Development of a navigation control system for an autonomous formula sae-electric race car | |
| Rowduru et al. | A critical review on automation of steering mechanism of load haul dump machine | |
| Chen et al. | From perception to control: an autonomous driving system for a formula student driverless car | |
| Pentzer et al. | On‐line estimation of power model parameters for skid‐steer robots with applications in mission energy use prediction | |
| Zhang et al. | Learning end-to-end inertial-wheel odometry for vehicle ego-motion estimation | |
| Song et al. | Slip parameter estimation for tele-operated ground vehicles in slippery terrain | |
| Gruyer et al. | Experimental comparison of Bayesian positioning methods based on multi-sensor data fusion | |
| Gao et al. | Interacting multiple model for improving the precision of vehicle-mounted global position system | |
| EP3797939B1 (en) | Control command based adaptive system and method for estimating motion parameters of differential drive vehicles | |
| Liu et al. | Optimum Path Tracking Control for the Inverse Problem of Vehicle Handling Dynamics Based on the hp‐Adaptive Gaussian Pseudospectral Method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |