CN110147098A - Control method, device, equipment and the readable storage medium storing program for executing of automatic driving vehicle - Google Patents
Control method, device, equipment and the readable storage medium storing program for executing of automatic driving vehicle Download PDFInfo
- Publication number
- CN110147098A CN110147098A CN201910360784.1A CN201910360784A CN110147098A CN 110147098 A CN110147098 A CN 110147098A CN 201910360784 A CN201910360784 A CN 201910360784A CN 110147098 A CN110147098 A CN 110147098A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- state
- current
- sequence
- 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 47
- 238000004590 computer program Methods 0.000 claims description 12
- 230000005484 gravity Effects 0.000 claims description 12
- 238000012937 correction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000001351 cycling effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- 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
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Electromagnetism (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The disclosure provides control method, device, equipment and the readable storage medium storing program for executing of a kind of automatic driving vehicle, method includes: the current state for acquiring vehicle, present speed, current control information, and determines predicted state sequence according to current state, present speed, current control information；Obtain parameter preset corresponding with present speed；Control sequence is determined according to predicted state sequence, parameter preset, expectation state sequence；Vehicle driving is controlled according to control sequence, and the step of continuing to execute the current state of acquisition vehicle, present speed, current control information.Control method, device, equipment and the readable storage medium storing program for executing for the automatic driving vehicle that the disclosure provides can make its practical output state be consistent with expectation state when controlling vehicle driving by determining control sequence.Meanwhile control sequence is not determined using different parameter presets simultaneously in car speed, additionally it is possible to improve the control precision of vehicle.
Description
Technical field
This disclosure relates to automatic Pilot technology more particularly to a kind of control method of automatic driving vehicle, device, equipment and
Readable storage medium storing program for executing.
Background technique
Currently, the trend in autonomous driving vehicle field needs to control turning for vehicle to enable the vehicle to normally travel
To so that vehicle can be realized path trace.Currently, many algorithms can realize the path trace of degree of precision, using compared with
More has pid algorithm, the control of pure point tracking, Feedforward-feedback control, takes aim at tracking optimum control, linear quadratic regulator and mould in advance
Type predictive control algorithm etc..
The 1970s, model predictive control method was suggested, and was widely used to every field at present.Model prediction
Control has the essential characteristics such as prediction model, rolling optimization and feedback correction, is particularly suitable for being not easy to establish mathematical models
And the control system of Existence restraint condition, path trace control under the conditions of solution intelligent vehicle is in high speed and ice and snow complex road surface
There is unique advantage in problem processed.
In model predictive control method, the driving status in vehicle future can be predicted by prediction model, further according to pre-
It surveys result and determines the control input of vehicle, and how to determine control input, so that the reality output result and desired output of vehicle
As a result it is consistent, is the difficult point that those skilled in the art need to overcome.
Summary of the invention
The disclosure provides control method, device, equipment and the readable storage medium storing program for executing of a kind of automatic driving vehicle, to realize standard
Determine the effect of the control input information of vehicle.
The first aspect of the disclosure is to provide a kind of control method of automatic driving vehicle, comprising:
Acquire the current state of vehicle, present speed, current control information, and according to the current state, present speed,
Current control information determines predicted state sequence；
Obtain parameter preset corresponding with the present speed；
Control sequence is determined according to the predicted state sequence, the parameter preset, expectation state sequence；
Control the vehicle driving according to the control sequence, and continue to execute the acquisition vehicle current state, when
The step of preceding speed, current control information.
Another aspect of the disclosure is to provide a kind of control device of automatic driving vehicle, comprising:
Prediction module, for acquiring current state, the present speed, current control information of vehicle, and according to described current
State, present speed, current control information determine predicted state sequence；
Module is obtained, for obtaining parameter preset corresponding with the present speed；
Determining module, for determining control sequence according to the predicted state sequence, the parameter preset, expectation state sequence
Column；
Control module, for controlling the vehicle driving according to the control sequence, the prediction module continues to execute institute
The step of stating current state, the present speed, current control information of acquisition vehicle.
The another aspect of the disclosure is to provide a kind of control equipment of automatic driving vehicle, comprising:
Memory；
Processor；And
Computer program；
Wherein, the computer program stores in the memory, and is configured to be executed by the processor to realize
The control method of automatic driving vehicle as described in above-mentioned first aspect.
The another aspect of the disclosure is to provide a kind of computer readable storage medium, is stored thereon with computer program,
The computer program is executed by processor the control method to realize the automatic driving vehicle as described in above-mentioned first aspect.
The technical effect of the control method of automatic driving vehicle, device, equipment and readable storage medium storing program for executing that the disclosure provides
It is:
Control method, device, equipment and the readable storage medium storing program for executing for the automatic driving vehicle that the disclosure provides, comprising: acquisition
The current state of vehicle, present speed, current control information, and determined according to current state, present speed, current control information
Predicted state sequence；Obtain parameter preset corresponding with present speed；According to predicted state sequence, parameter preset, expectation state
Sequence determines control sequence；Vehicle driving is controlled according to control sequence, and continues to execute the current state of acquisition vehicle, current speed
The step of degree, current control information.Control method, device, equipment and the readable storage for the automatic driving vehicle that the disclosure provides
Medium, can be according to the current state and speed of vehicle, control information prediction its following state, and according to the prediction shape
The corresponding parameter preset of state, present speed and expectation sequence determine control sequence, to control vehicle according to control sequence
When driving, its practical output state is made to be consistent with expectation state.Meanwhile different parameter presets is not used simultaneously in car speed
Determine control sequence, additionally it is possible to improve the control precision of vehicle.
Detailed description of the invention
Fig. 1 is the flow chart of the control method of the automatic driving vehicle shown in an exemplary embodiment of the invention；
Fig. 2 is the flow chart of the control method of the automatic driving vehicle shown in another exemplary embodiment of the present invention；
Fig. 3 is the structure chart of the control device of the automatic driving vehicle shown in an exemplary embodiment of the invention；
Fig. 4 is the structure chart of the control device of the automatic driving vehicle shown in another exemplary embodiment of the present invention；
Fig. 5 is the structure chart of the control equipment of the automatic driving vehicle shown in an exemplary embodiment of the invention.
Specific embodiment
Automatic driving vehicle in motion, is first to cook up travel route, then control vehicle and carry out path trace, makes it
It can be travelled based on programme path.Model predictive control method can acquire the current running data of vehicle, further according to these numbers
It is predicted that the driving information of vehicle, so that the control information of control vehicle driving is determined according to predictive information and programme path,
So that route or travel by vehicle is more close with programme path.
Fig. 1 is the flow chart of the control method of the automatic driving vehicle shown in an exemplary embodiment of the invention.
As shown in Figure 1, the control method of automatic driving vehicle provided in this embodiment includes:
Step 101, current state, the present speed, current control information of vehicle are acquired, and according to current state, current
Speed, current control information determine predicted state sequence.
Method provided in this embodiment can be by having the execution of the electronic equipment of computing function, such as computer.Electronics is set
Standby specifically to can also be the car-mounted computer being set on automatic driving vehicle, which can plan road for vehicle
Line, control vehicle carry out path trace.
Wherein, sensor can be set in vehicle, for acquiring current state, the present speed, current control letter of vehicle
Breath.For example, positioning device can be arranged in the car, the driving status of vehicle is obtained based on positioning device, it is specific as vehicle moves
Dynamic rail mark, moving direction etc..For another example the location information that can also be obtained according to positioning device, calculates the mobile message of vehicle,
Such as movement speed.
Specifically, imaging sensor, radar etc. can also be set on vehicle, it, can be based on week for perceiving ambient enviroment
The sensing results in collarette border determine the current state of vehicle.Such as the information such as angle between vehicle and lane line.
If acquiring these information by sensor, electronic equipment can be sent by collected data by sensor
In, so that electronic equipment can collect these data.
When practical application, many vehicles can collect the speed and direction disk corner information of itself, electronic equipment
These information can also be directly read, to obtain the data that can change vehicle-state.
Further, in method provided in this embodiment, can according to the current state of vehicle and current speed and
Information is controlled, vehicle can be predicted in the state of subsequent time.
Electronic equipment can predict status switch of the vehicle within following a period of time, for example, when can predict the following 1s
Status switch in length.For example, 50 states of the vehicle in the following 1s can be predicted, 1s can be divided into 50 moment, in advance
State of the measuring car at this 50 moment.
Specifically, can predict the next of vehicle according to the current state and present speed of vehicle, current control information
A state, further according to the next state and the present speed, current control information of vehicle, next state under prediction.It can be with
Vehicle is predicted in the case where present speed, current control information are constant, the state of vehicle in following a period of time.
Further, method provided in this embodiment can be used for controlling the transverse shifting direction of vehicle, therefore, prediction
State may include: lateral error, lateral error change rate, the driving direction of vehicle and lane line angle and the angle
Change rate.
Step 102, parameter preset corresponding with present speed is obtained.
Wherein it is possible to preset the corresponding parameter preset of speed.The corresponding relationship of parameter preset and speed can be deposited
It stores up in the electronic device, so that electronic equipment be enable to read corresponding parameter based on the present speed of acquisition.
Specifically, parameter preset may include the first parameter value Q, the second parameter value R, respectively as predicted state and expectation
The adjusting parameter of the adjusting parameter of error and control sequence between state.Control sequence refers to the control for inputting vehicle
Information sequence can make the state of vehicle be intended to expectation state by predicted state by input control information, to make vehicle
Realizing route tracking.
In a kind of embodiment, the corresponding parameter preset of each speed can be obtained by experience.For example, work can be passed through
Make the practical ride-on vehicles of personnel, and allows the vehicle to automatic Pilot by the way that parameter preset is arranged.Staff can be by vehicle
It is adjusted to a pre-set velocity, vehicle can determine control sequence based on the parameter preset, and staff can during seating
Experience actual ride experience, it, can be no using current parameter preset as the corresponding parameter of pre-set velocity if experience is preferably
Experience bad, then adjustable parameter preset, allows the vehicle to bring preferable ride experience for passenger.
In another middle embodiment, training can be first passed through in advance and obtains parameter preset.For example, can control vehicle pre-
If speed downward driving.Meanwhile one group of parameter Q1, R can be generated1, and vehicle is based on this group of parameter, is capable of determining that vehicle most
Excellent control sequence, i.e., with pre-set velocity, Q1、R1Corresponding optimal control sequence.Further, it is also possible to be determined according to other parameters group
Multiple optimal control sequences are compared corresponding optimal control sequence, determine target control sequence, and its is corresponding
Parameter combination, as the corresponding parameter preset of pre-set velocity.
Wherein, predicted state sequence is determined according to current state, present speed, current control information, with acquisition and currently
The step timing of the corresponding parameter preset of speed is not limited.
Step 103, control sequence is determined according to predicted state sequence, parameter preset, expectation state sequence.
Further, electronic equipment can determine control sequence based on predicted state sequence, parameter preset, expectation state sequence
Column control vehicle by the control sequence, the state of vehicle can be made more to be consistent with expectation state.
When practical application, predicted state sequence is consistent with expectation state sequence timing, and control sequence is earlier than status switch one
A moment.For example, first in control sequence control information is the status information at kth moment (such as the first moment), then two
First state in status switch is the status information at (k+1) moment (such as the second moment).Here k can be used for representing
At the time of control information corresponds to, k+1 then indicates next moment of moment k.Such as the first moment, the second moment, adjacent moment
Between duration can be configured according to demand, such as can be 100ms.
Since control information function is when vehicle, the state of vehicle can change in subsequent time, for example, by the k moment
Control information input vehicle, thus control vehicle change state, then the state of vehicle can become the k+1 moment from k moment state
State, the state at k+1 moment is result of the control information superposition at k moment in the state at k moment.
Wherein, in order to enable the vehicle to accurately arrive at the destination, it can be vehicle planning path, be based on the planning path
It can determine the expectation state sequence of vehicle, information is corresponding at the time of information is with car state sequence at the time of in the sequence.I.e.
In two status switches, including mutually corresponding state value in the same time.
Specifically, control sequence can be determined so that vehicle based on the control information in control sequence when driving, reality
State is consistent with expectation state.
Further, Optimized model can be preset, for determining control sequence.The Optimized model aims at,
A control sequence is determined, when which acts on vehicle, so that the reality output state of vehicle is consistent with expectation state.Vehicle
Reality output state may be considered vehicle current time predicted state and last moment control information stack result.
For example, predicted state of the vehicle at the k moment is A, the control information at k moment is a, then reality output shape of the vehicle at the k+1 moment
State is the result of A Yu a superposition.
When practical application, the number of states for including in status switch can be configured according to demand, can be one
It can be multiple.Correspondingly, the control information content in control sequence can be identical as amount of state information, it is also possible to one
Or it is multiple.
Step 104, vehicle driving is controlled according to control sequence.
Wherein it is possible to select first control information in control sequence, vehicle driving is controlled.Side provided in this embodiment
In method, control information can be wheel steering, can be according to first control information adjustment direction disk corner, to change vehicle
Driving status.
Specifically, can determine the wheel steering of vehicle according to the first control information, and steering order is generated, will turned to
Instruction is sent to the driving device for controlling steering wheel rotation, so that vehicle can change according to first control information
It turns to.
Further, due in a step 101, being the current control information prediction vehicle-state by vehicle, and
After executing step 104, the control information of vehicle is changed, at this point it is possible to continue to execute step 101, and then is determined new
Control sequence, and vehicle driving is controlled based on new control sequence.
Method provided in this embodiment for control automatic driving vehicle traveling, this method by be provided with the present embodiment provides
The equipment of method execute, which realizes usually in a manner of hardware and/or software.
The control method of automatic driving vehicle provided in this embodiment, comprising: acquire current state, the current speed of vehicle
Degree, current control information, and predicted state sequence is determined according to current state, present speed, current control information；It obtains and works as
The corresponding parameter preset of preceding speed；Control sequence is determined according to predicted state sequence, parameter preset, expectation state sequence；According to
Control sequence controls vehicle driving, and continues to execute current state, the step of present speed, current control information of acquisition vehicle
Suddenly.The control method of automatic driving vehicle provided in this embodiment, can be according to the current state and speed of vehicle, control
Its following state of information prediction, and determined according to the predicted state, the corresponding parameter preset of present speed and expectation sequence
Control sequence out, to make its practical output state be consistent with expectation state when controlling vehicle driving according to control sequence.Together
When, control sequence is not determined using different parameter presets simultaneously in car speed, additionally it is possible to improve the control precision of vehicle.
Fig. 2 is the flow chart of the control method of the automatic driving vehicle shown in another exemplary embodiment of the present invention.
As shown in Fig. 2, the control method of automatic driving vehicle provided in this embodiment, comprising:
Step 201, current state, the present speed, current control information of vehicle are acquired.
Step 201 with it is in step 101 and acquire data step concrete principle and implementation it is similar, it is no longer superfluous herein
It states.
Step 202, present speed, current control information, current state are inputted into default prediction model, so that default prediction
Model determines predicted state sequence according to the attribute information of present speed, current control information, current state, vehicle.
Wherein it is possible to prediction model be preset, for the current driving data according to vehicle, when predicting that it is one section following
Interior status switch.
Specifically, the attribute information of vehicle can also be arranged in prediction model.For the vehicle of different model, even if working as
Preceding state, speed, control information are all the same, and following driving status will not be identical.Therefore, attribute can be set
Information, to more accurately predict vehicle-state.
Further, vehicle attribute information can be arranged when leaving the factory in the car, can also be after vehicle release, then root
Typing is carried out according to information of vehicles.For example, interactive interface has can be set in electronic equipment, user can operate the user interface, into
And input vehicle attribute information.
When practical application, the attribute information of vehicle is comprised at least one of the following:
Front tyre rigidity, rear tire rigidity, the distance of vehicle's center of gravity to front axle, the distance of vehicle's center of gravity to hind axle, vehicle
Rotary inertia, vehicle weight.
Wherein, front axle refers to that, for connecting the axis of two front-wheels in vehicle, the distance of vehicle's center of gravity to front axle is vehicle
It is used to connect the distance between the axis of two front-wheels to this, the distance of vehicle's center of gravity to hind axle is similar therewith.Vehicle rotation
Inertia, front tyre rigidity, rear tire rigidity can be obtained by test measurement, vehicle weight, vehicle's center of gravity to front axle distance,
The distance of vehicle's center of gravity to hind axle can directly measure to obtain.
Wherein, default prediction model can first according to present speed, current control information, current state, vehicle attribute
Information determines the first predicted state.Specifically it can determine according to the following formula the first predicted state:
X (k+1)=A (k) × x (k)+B × u (k)
X (k+1) is the vehicle-state at (k+1) moment, and x (k) is the vehicle-state at k moment, and u (k) is that the control at k moment is believed
Breath, A (k), B are the coefficient matrix of state space.Wherein:
Wherein, CαfFor the front tyre rigidity of vehicle, CαrFor the rear-wheel rigidity of vehicle, lfFor vehicle's center of gravity to front axle away from
From lrFor the distance of vehicle's center of gravity to hind axle, Iz is vehicle rotary inertia, and specially vehicle vertical direction rotary inertia, m is
Vehicle weight.VxIt (k) is the speed of vehicle.
When determining the first predicted state according to current vehicle data, it is believed that VxIt (k) is the present speed acquired,
X (k) is the current state of acquisition, and u (k) is the current control information of acquisition, and then can obtain the first predicted state x (k+1).
Next, determining the second predicted state according to the first predicted state.Using the first predicted state as current predictive shape
State continues to determine x (k+2) based on above-mentioned prediction model.Control information and the constant feelings of car speed can specifically be predicted
Under condition, state of the vehicle within following a period of time.
Specifically, according to current predictive state, present speed, current control information, current state, vehicle attribute information
Determine next predicted state of current predictive state, it can be by Vx(k), u (k) and x (k+1) inputs above-mentioned model, thus
Obtain x (k+2).
Further, obtained predicted state can be re-used as to current predictive state and execute above-mentioned steps, can be obtained
Multiple predicted states, and then constitute the predicted state sequence of vehicle.
Step 203, parameter preset corresponding with present speed is obtained.
Step 204, control sequence is determined according to predicted state sequence, parameter preset, expectation state sequence.
Step 309-204 is similar with step 102-103.
Wherein, in method provided in this embodiment, the control sequence u (k) can also be determined according to the following formula, so that following formula
Meet default constraint condition:
Specifically, k is the moment, wherein predicted state when x (k+1) is the k+1 moment, er(k+1) be the k+1 moment when
Expectation state.[x(k+1)-er(k+1)] error between predicted state and expectation state.U (k) is that the control at k moment is believed
Breath, Δ is differential sign.Q, R is the parameter preset obtained.N is the number of states in predicted state sequence.It can be and set in advance
The value set is also possible to the value being adjusted by practical operation.
Further, above formula is used to measure the control information function at k moment in vehicle, reality of the vehicle at the k+1 moment
Error between state and expectation state, therefore, the value of above formula are smaller, then vehicle virtual condition is more close with expectation state.It can
It is, for example, less than preset value so that a preset condition is arranged, can determines a control sequence u (k), so that above formula is less than preset value.
Step 205, vehicle driving is controlled using first control element in control sequence.
When practical application, this yuan can be passed through using first control element in control sequence as the input value of vehicle
Element control vehicle driving.
Wherein, in method provided in this embodiment, the value for including in control sequence can be wheel steering information, because
First wheel steering information, can be sent to the driving device of steering wheel, so that steering wheel can be rotated by this.For example,
First control element is to turn left 3 degree, then steering wheel can be driven to turn left 3 degree by driving device.
Specifically, can be the absolute angle of steering wheel in one embodiment, in control sequence, for example, it can be set to
One 0 degree of lines, the angle in control sequence is compared to the angle of 0 degree of line.It in another embodiment, can be in control sequence
It is steering wheel based on the angle for working as front steering, i.e., on the basis of steering wheel current control information, then the angle adjusted, for example, can
To be set in advance on the basis of front steering, turns left and be negative, turn right and be positive, if first in control sequence element is
3, then it represents on the basis of the steering of current steering wheel, turns right 3 degree.
After step 205, step 201 can be continued to execute.
Optionally, after step 205, can also include:
Step 206, the virtual condition of vehicle is acquired, and error is determined according to predicted state sequence, virtual condition.
Wherein, this step can also execute after step 201, at this point it is possible to directly using current state as practical shape
State, and the step of executing determining error.
Specifically, the control element can be acquired when controlling vehicle using first control element in control sequence
Act on the effect on vehicle, i.e. virtual condition.First state in available predicted state sequence, and by itself and reality
State compares, so that it is determined that difference between the two out.The difference may be considered control element and act on to be generated on vehicle
It influences.For example, the state of prediction k moment vehicle is x, the state of actual vehicle is x ', then can compare the difference between the two
Value, and be compared whether the difference acts on the result generated on vehicle with control element u (k-1), comparison result is
Error.
Correspondingly, step 204, determine that control sequence can be with according to predicted state sequence, parameter preset, expectation state sequence
Further include:
Step 204 ' determines control sequence according to error, predicted state sequence, parameter preset, expectation state sequence.
After step 206 and step 203, step 204 ' can be executed.
Further, due to the control element of prediction act on it is being generated on vehicle as a result, knot with vehicle reality output
There may be errors for fruit, and therefore, the sequence processed determined in conjunction with error is more accurate, and then can more accurately control vehicle row
It sails.
When practical application, when determining first control sequence, it can't be missed based on actual vehicle output situation
Difference can directly execute step 204 at this point it is possible to not combine error to determine control sequence after step 203.Hereafter really
During determining control sequence, then error can be determined based on reality output situation before, and error is combined to determine control sequence
Column, it can step 204 ' is executed after step 203 and step 206.
Fig. 3 is the structure chart of the control device of the automatic driving vehicle shown in an exemplary embodiment of the invention.
As shown in figure 3, the control device of automatic driving vehicle provided in this embodiment, comprising:
Prediction module 31 for acquiring current state, the present speed, current control information of vehicle, and is worked as according to described
Preceding state, present speed, current control information determine predicted state sequence；
Module 32 is obtained, for obtaining parameter preset corresponding with the present speed；
Determining module 33, for determining control according to the predicted state sequence, the parameter preset, expectation state sequence
Sequence；
Control module 34, for controlling the vehicle driving according to the control sequence, the prediction module is continued to execute
The step of current state for acquiring vehicle, present speed, current control information.
The control device of automatic driving vehicle provided in this embodiment, comprising: prediction module, for acquiring the current of vehicle
State, present speed, current control information, and predicted state sequence is determined according to current state, present speed, current control information
Column；Module is obtained, for obtaining parameter preset corresponding with present speed；Determining module is used for according to predicted state sequence, in advance
Setting parameter, expectation state sequence determine control sequence；Control module predicts mould for controlling vehicle driving according to control sequence
Block continues to execute the step of current state of acquisition vehicle, present speed, current control information.It is provided in this embodiment to drive automatically
Sail the control device of vehicle, can according to the current state and speed of vehicle, control information prediction its following state, and
Control sequence is determined according to the predicted state, the corresponding parameter preset of present speed and expectation sequence, thus according to control
When sequence controls vehicle driving, its practical output state is made to be consistent with expectation state.Meanwhile in car speed not simultaneously using not
Same parameter preset determines control sequence, additionally it is possible to improve the control precision of vehicle.
The concrete principle and implementation of the control device of automatic driving vehicle provided in this embodiment with it is shown in FIG. 1
Embodiment is similar, and details are not described herein again.
Fig. 4 is the structure chart of the control device of the automatic driving vehicle shown in another exemplary embodiment of the present invention.
As shown in figure 4, on the basis of the above embodiments, the control device of automatic driving vehicle provided in this embodiment,
Optionally, the prediction module 31 is specifically used for
The present speed, the current control information, the current state are inputted into default prediction model, so that described
Default prediction model according to the present speed, the current control information, the current state, the vehicle attribute information
Determine the predicted state sequence.
Optionally, the attribute information of the vehicle comprises at least one of the following:
Front tyre rigidity, rear tire rigidity, the distance of vehicle's center of gravity to front axle, the distance of vehicle's center of gravity to hind axle, vehicle
Rotary inertia, vehicle weight.
Optionally, the prediction module 31, comprising:
Predicting unit 311, for according to the present speed, the current control information, the current state, the vehicle
Attribute information determine the first predicted state；
Cycling element 312, for using first predicted state as current predictive state；
The predicting unit 311 be also used to according to current predictive state, the present speed, the current control information,
The current state, the vehicle attribute information determine next predicted state of the current predictive state；
The cycling element 312 using next predicted state as current predictive state, the predicting unit 311 after
It is continuous to execute according to current predictive state, the present speed, the current control information, the current state, the vehicle
Attribute information determines the step of next predicted state of the current predictive state.
The determining module 33 is specifically used for:
The control sequence u (k) is determined according to the following formula, so that following formula meets default constraint condition:
Wherein, x (k+1) is the predicted state at k+1 moment, erIt (k+1) is the expectation state at k+1 moment.U (k) is the k moment
Control information, Δ is differential sign.Q, R is the parameter preset.N is the status number for including in the predicted state sequence
Amount.
Optionally, the control module 34 is specifically used for:
The vehicle driving is controlled using first control element in the control sequence.
Optionally, described device further includes correction module 35；
The correction module 35 is used for after control module 34 controls the vehicle driving according to the control sequence:
The virtual condition of the vehicle is acquired, and error is determined according to the predicted state sequence, the virtual condition；
Response, the determining module 33 is specifically used for:
The control sequence is determined according to the error, the predicted state sequence, the parameter preset, expectation state sequence
Column.
The concrete principle and implementation of the control device of automatic driving vehicle provided in this embodiment with it is shown in Fig. 2
Embodiment is similar, and details are not described herein again.
Fig. 5 is the structure chart of the control equipment of the automatic driving vehicle shown in an exemplary embodiment of the invention.
As shown in figure 5, the control equipment of automatic driving vehicle provided in this embodiment includes:
Memory 51；
Processor 52；And
Computer program；
Wherein, the computer program is stored in the memory 51, and be configured to by the processor 52 execute with
Realize the control method of any automatic driving vehicle as described above.
The present embodiment also provides a kind of computer readable storage medium, is stored thereon with computer program,
The computer program is executed by processor the controlling party to realize any automatic driving vehicle as described above
Method.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence；And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (10)
1. a kind of control method of automatic driving vehicle characterized by comprising
Acquire the current state of vehicle, present speed, current control information, and according to the current state, present speed, current
Control information determines predicted state sequence；
Obtain parameter preset corresponding with the present speed；
Control sequence is determined according to the predicted state sequence, the parameter preset, expectation state sequence；
The vehicle driving is controlled according to the control sequence, and continues to execute the current state of the acquisition vehicle, current speed
The step of degree, current control information.
2. the method according to claim 1, wherein described according to the current state, present speed, current control
Information processed determines that predicted state sequence includes:
The present speed, the current control information, the current state are inputted into default prediction model, so that described default
Prediction model is determined according to the attribute information of the present speed, the current control information, the current state, the vehicle
The predicted state sequence.
3. according to the method described in claim 2, it is characterized in that, the attribute information of the vehicle comprises at least one of the following:
Front tyre rigidity, rear tire rigidity, the distance of vehicle's center of gravity to front axle, the distance of vehicle's center of gravity to hind axle, vehicle rotation
Inertia, vehicle weight.
4. according to the method described in claim 2, it is characterized in that, the default prediction model is according to the present speed, institute
State current control information, the current state, the vehicle attribute information determine the predicted state sequence, comprising:
First is determined according to the attribute information of the present speed, the current control information, the current state, the vehicle
Predicted state；
Using first predicted state as current predictive state；
According to current predictive state, the present speed, the current control information, the current state, the vehicle category
Property information determines next predicted state of the current predictive state；
Using next predicted state as current predictive state, and continue to execute according to current predictive state, described current
Speed, the current control information, the current state, the vehicle attribute information determine under the current predictive state
The step of one predicted state.
5. method according to claim 1-4, which is characterized in that described according to the predicted state sequence, institute
State parameter preset, expectation state sequence determines control sequence, comprising:
The control sequence u (k) is determined according to the following formula, so that following formula meets default constraint condition:
Wherein, x (k+1) is the predicted state at k+1 moment, erIt (k+1) is the expectation state at k+1 moment, u (k) is the control at k moment
Information processed, Δ are differential sign, and Q, R are the parameter preset, and N is the number of states for including in the predicted state sequence.
6. method according to claim 1-4, which is characterized in that described according to control sequence control
Vehicle driving, comprising:
The vehicle driving is controlled using first control element in the control sequence.
7. method according to claim 1-4, which is characterized in that described according to control sequence control
After vehicle driving, further includes:
The virtual condition of the vehicle is acquired, and error is determined according to the predicted state sequence, the virtual condition；
It is described that control sequence is determined according to the predicted state sequence, the parameter preset, expectation state sequence, comprising:
The control sequence is determined according to the error, the predicted state sequence, the parameter preset, expectation state sequence.
8. a kind of control device of automatic driving vehicle characterized by comprising
Prediction module, for acquiring current state, the present speed, current control information of vehicle, and according to the current state,
Present speed, current control information determine predicted state sequence；
Module is obtained, for obtaining parameter preset corresponding with the present speed；
Determining module, for determining control sequence according to the predicted state sequence, the parameter preset, expectation state sequence；
Control module, for controlling the vehicle driving according to the control sequence, the prediction module continues to execute described adopt
The step of collecting current state, the present speed, current control information of vehicle.
9. a kind of control equipment of automatic driving vehicle characterized by comprising
Memory；
Processor；And
Computer program；
Wherein, the computer program stores in the memory, and is configured to be executed by the processor to realize such as power
Benefit requires any method of 1-7.
10. a kind of computer readable storage medium, which is characterized in that it is stored thereon with computer program,
The computer program is executed by processor to realize the method as described in claim 1-7 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910360784.1A CN110147098A (en) | 2019-04-30 | 2019-04-30 | Control method, device, equipment and the readable storage medium storing program for executing of automatic driving vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910360784.1A CN110147098A (en) | 2019-04-30 | 2019-04-30 | Control method, device, equipment and the readable storage medium storing program for executing of automatic driving vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110147098A true CN110147098A (en) | 2019-08-20 |
Family
ID=67594489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910360784.1A Pending CN110147098A (en) | 2019-04-30 | 2019-04-30 | Control method, device, equipment and the readable storage medium storing program for executing of automatic driving vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110147098A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111025907A (en) * | 2019-12-20 | 2020-04-17 | 苏州智加科技有限公司 | Transverse control method and system for automatic driving truck and storage medium |
| CN112015180A (en) * | 2020-08-28 | 2020-12-01 | 哈尔滨理工大学 | Intelligent experiment trolley and control system thereof |
| CN112406889A (en) * | 2019-08-22 | 2021-02-26 | 初速度（苏州）科技有限公司 | Vehicle prediction control method based on kinematics and processor |
| CN112543899A (en) * | 2019-12-26 | 2021-03-23 | 深圳市大疆创新科技有限公司 | Control method and control device for movable carrier and computer readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103085816A (en) * | 2013-01-30 | 2013-05-08 | 同济大学 | Trajectory tracking control method and control device for driverless vehicle |
| CN107161207A (en) * | 2017-05-08 | 2017-09-15 | 江苏大学 | A kind of intelligent automobile Trajectory Tracking Control System and control method based on active safety |
| CN108334086A (en) * | 2018-01-25 | 2018-07-27 | 江苏大学 | A kind of automatic driving vehicle path tracking control method based on soft-constraint quadratic programming MPC |
| CN108845568A (en) * | 2018-04-27 | 2018-11-20 | 榛硕（武汉）智能科技有限公司 | Trajectory Tracking Control System and its control method for Vehicular automatic driving |
| CN108973769A (en) * | 2018-06-15 | 2018-12-11 | 吉林大学 | A kind of all fronts control electric car path tracking control method |
| CN109407677A (en) * | 2018-12-24 | 2019-03-01 | 清华大学 | The trace tracking method of automatic driving vehicle |
-
2019
- 2019-04-30 CN CN201910360784.1A patent/CN110147098A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103085816A (en) * | 2013-01-30 | 2013-05-08 | 同济大学 | Trajectory tracking control method and control device for driverless vehicle |
| CN107161207A (en) * | 2017-05-08 | 2017-09-15 | 江苏大学 | A kind of intelligent automobile Trajectory Tracking Control System and control method based on active safety |
| CN108334086A (en) * | 2018-01-25 | 2018-07-27 | 江苏大学 | A kind of automatic driving vehicle path tracking control method based on soft-constraint quadratic programming MPC |
| CN108845568A (en) * | 2018-04-27 | 2018-11-20 | 榛硕（武汉）智能科技有限公司 | Trajectory Tracking Control System and its control method for Vehicular automatic driving |
| CN108973769A (en) * | 2018-06-15 | 2018-12-11 | 吉林大学 | A kind of all fronts control electric car path tracking control method |
| CN109407677A (en) * | 2018-12-24 | 2019-03-01 | 清华大学 | The trace tracking method of automatic driving vehicle |
Non-Patent Citations (7)
| Title |
|---|
| 余如等: "自主驾驶车辆的预测避障控制", 《信息与控制》 * |
| 李金良等: "基于模型预测控制的无人驾驶汽车的轨迹跟踪", 《汽车工程师》 * |
| 王艺等: "基于模型预测控制的智能网联汽车路径跟踪控制器设计", 《机械工程学报》 * |
| 王艺等: "基于模型预测控制的智能车辆路径跟踪控制器设计", 《汽车技术》 * |
| 赵洁: "智能车辆的路径跟踪及底层控制研究", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅱ辑》 * |
| 邓涛等: "基于MPC与EKF算法的电动汽车状态估计与横向稳定性控制", 《汽车安全与节能学报》 * |
| 郝亮等: "基于MPC的无人驾驶车辆的轨迹跟踪", 《汽车实用技术》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112406889A (en) * | 2019-08-22 | 2021-02-26 | 初速度（苏州）科技有限公司 | Vehicle prediction control method based on kinematics and processor |
| CN112406889B (en) * | 2019-08-22 | 2022-05-27 | 魔门塔(苏州)科技有限公司 | Vehicle prediction control method based on kinematics and processor |
| CN111025907A (en) * | 2019-12-20 | 2020-04-17 | 苏州智加科技有限公司 | Transverse control method and system for automatic driving truck and storage medium |
| CN112543899A (en) * | 2019-12-26 | 2021-03-23 | 深圳市大疆创新科技有限公司 | Control method and control device for movable carrier and computer readable storage medium |
| CN112015180A (en) * | 2020-08-28 | 2020-12-01 | 哈尔滨理工大学 | Intelligent experiment trolley and control system thereof |
| CN112015180B (en) * | 2020-08-28 | 2022-12-16 | 润达光伏盐城有限公司 | Intelligent experiment trolley and control system thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110147098A (en) | Control method, device, equipment and the readable storage medium storing program for executing of automatic driving vehicle | |
| CN110471428B (en) | Path tracking method based on variable pre-aiming distance and speed constraint of model | |
| CN110568758B (en) | Parameter self-adaptive transverse motion LQR control method for automatically driving automobile | |
| CN106061814B (en) | Advance alarm to the steering torque limit more than LCC | |
| CN106080598B (en) | Real-time goal pace control | |
| CN103204162B (en) | There is the Lane tracking system of effective rear steering | |
| CN111547066B (en) | Vehicle trajectory tracking method, device, equipment and storage medium | |
| CN102269995B (en) | Variable structure control method of wheeled mobile robot | |
| CN113120001A (en) | Transverse control method and device for automatic driving vehicle and vehicle | |
| CN107264534A (en) | Intelligent driving control system and method, vehicle based on driver experience's model | |
| CN110395250A (en) | Method and system for vehicle bend rate limitation | |
| CN110525436A (en) | Vehicle lane-changing control method, device, vehicle and storage medium | |
| CN107664504A (en) | A kind of path planning apparatus | |
| CN108357595B (en) | Model-based self-balancing unmanned bicycle and model driving control method thereof | |
| EP2752347A1 (en) | Vehicular information-processing device and vehicular information-processing method | |
| CN109656240A (en) | A kind of vehicle route follow-up control apparatus, method and vehicle | |
| CN108710294A (en) | A kind of unmanned vehicle path trace feed forward control method | |
| US11814073B2 (en) | Learning based controller for autonomous driving | |
| CN106708044A (en) | Full-hovering hovercraft course control method based on grey prediction hybrid genetic algorithm-PID | |
| US20220266903A1 (en) | Vehicle control method, vehicle control system, and vehicle | |
| CN115042816B (en) | Path tracking method, device, apparatus, medium, and program | |
| CN112092825A (en) | Lane keeping method based on machine learning | |
| CN112799384A (en) | Vehicle and driving track planning method and planning device thereof | |
| CN114942642A (en) | Unmanned automobile track planning method | |
| Domina et al. | Modelling the dynamic behavior of the steering system for low speed autonomous path tracking |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190820 |