CN109927716A - Autonomous method of vertically parking based on high-precision map - Google Patents
Autonomous method of vertically parking based on high-precision map Download PDFInfo
- Publication number
- CN109927716A CN109927716A CN201910196482.5A CN201910196482A CN109927716A CN 109927716 A CN109927716 A CN 109927716A CN 201910196482 A CN201910196482 A CN 201910196482A CN 109927716 A CN109927716 A CN 109927716A
- Authority
- CN
- China
- Prior art keywords
- parking
- point
- precision map
- track
- vehicle
- 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
Landscapes
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
Abstract
The autonomous method of vertically parking based on high-precision map that the invention proposes a kind of, it include: that vehicle obtains the environmental information based on the parking position information of high-precision map and parking lot and road edge drive test sensor, determine the position attribution wait park and the positional relationship attribute under global coordinate system, so that it is determined that switching point, and switching point is fitted by circular arc or spline curve, under conditions of meeting vertical parking path constraint and minimum parking position constraint, component cost function chooses the smallest track of cost function as final optimal trajectory；Method of the invention can guarantee the ride comfort of vehicle motion control, eliminate the shake of vehicle in parking process steering wheel, realize that safety is parked.
Description
Technical field
The present invention relates to automatic Pilot technical field more particularly to a kind of autonomous vertical sides of parking based on high-precision map
Method.
Background technique
The problem of parking is broadly divided into parking for road edge and parking lot in city, and trajectory planning of independently vertically parking is pool
The important technology component part of one of vehicle system provides on the berth from vehicle for the intelligent driving technology based on high-precision map
Current location and posture near parking stall provide required input to the position for terminal of parking and posture.
Currently, track of vertically parking mainly considers to moor on the basis of vehicle minimum turning radius using geometric construction mode
Wheel paths are specifically stated at mathematical model, are utilized in the case where considering barrier and vehicle kinematics constraint condition and are generated optimal rail offline
The method of mark is excessively single, is unable to reach real-time rule for the automatic Pilot scene for this narrow space environment complexity of vertically parking
It draws, can not also adapt to more complicated environment of parking.Only pass through imitation experienced driver by neural network and fuzzy controller
Prior information of the driving behavior as reference locus, track-wise is different because of driver's difference in this, and lack flexibility,
It is not adapted dynamically vertical parking path.And with smart city；Intelligent transportation；The Internet of Things skill of the net connection automatic Pilot of V2X
The continuous development of art and high-precision map engine map technology with it is perfect, using the autonomous vertical pool based on high-precision map
Vehicle generates track cluster by sampling, constructs cost function, selects the smallest optimal track of vertically parking of cost value, the intelligence made
Vehicle can be driven being capable of flexible navigation in narrow vertical parking position environment.
Summary of the invention
In view of this, the invention proposes it is a kind of can adapt to road edge and parking lot based on high-precision map from
Main method of vertically parking.
The technical scheme of the present invention is realized as follows: the present invention provides a kind of the autonomous of high-precision map vertically to park
Method includes the following steps:
Step 1: wait an acquisition of parking based on the parking position information of high-precision map and parking lot and road edge drive test
The environmental information of sensor determines the position attribution wait park in high-precision map, determines wait park and selected vertical pool
The positional relationship attribute under global coordinate system between parking stall；
Step 2: determining each switching point wait park by flat square parking position coordinate system；
Step 3: being fitted using circular arc or spline curve to switching point, the spline curve of fitting forms rail of parking
Mark；
Step 4: choosing wait a place control point of parking is starting point of parking, meeting vertical parking path constraint and minimum
Under conditions of parking position the constraint relationship, track cluster of vertically parking is generated by sampled point, assigns velocity information, structure to every track
Cost function is built, the cost value of every track in track cluster of vertically parking is calculated, chooses the smallest track conduct of cost value
Final optimal trajectory.
On the basis of above technical scheme, it is preferred that in the step 1, obtain parking position information method include,
The cloud server that road edge or parking lot are registered by V2X technology after succeeding in registration, obtains road edge or parking
Cloud server issue based on high-precision map parking position information.
On the basis of above technical scheme, it is preferred that the position attribution includes: the ID, coordinate, head of body control point
Direction, curvature, rate, the connectivity of place high-precision map lane and adjacent lane, place high-precision map track direction and
The topological structure at control point.
On the basis of above technical scheme, it is preferred that it is characterized in that, the body control point is vehicle rear axle center
Point, the ID include the specific number letter that lane information and body control point where body control point are located on the lane of place
Breath, the coordinate are the coordinate of body control point, which is the coordinate of opposite global coordinate system, and the head is oriented to vehicle body control
Lane angulation, the curvature are by the vehicle body control where the suggestion driving direction and body control point of vehicle at system point
Curvature of the path curve of point at the body control point is made, rate is that suggestion of the vehicle at the body control point travels speed
The connectivity of degree, place high-precision map lane and adjacent lane is lane and its left-lane and right vehicle where the body control point
The connectivity in road, place high-precision map track direction be the body control point position whether keep straight on, turn left, turning right and
It can turn around, the topological structure at place high-precision map control point indicates the company between the body control point and adjacent body control point
Connect relationship.
Still more preferably, the positional relationship attribute includes: the terminal A that parks3Coordinate, park terminal A3Direction is parked
Terminal A3Curvature and parking position size H × B, wherein H is the length of parking position, and B is the width of parking position.
On the basis of above technical scheme, it is preferred that the global coordinate system is the parking position using terminal of parking as origin
Width direction is x-axis, parking position length direction is y-axis, and the switching point further includes the starting point A that parks0, turning starting point A1, turning eventually
Point A2With the terminal A that parks3, wait park from the starting point A that parks0Move in a straight line turning starting point A1, from turning starting point A1Certain
Steering angle under do circular motion to turning terminal A2, finally from turning terminal A2Circular motion is done again reaches the terminal A that parks3,
A1-A2The center of circle of section circular arc is O1。
On the basis of above technical scheme, it is preferred that the switching point A0、A1、A2And A3Method for solving include:
(Rmin-B/2)2+D2=(Rmin-δ2-W/2)2,
The A3[0,0,0 °, 0],
The A2[0, H-D- δ1- l, 0 °, 1/Rmin],
The A1[Rmin, H-D- δ1-l+Rmin, 90 °, 1/Rmin],
The A0[Rmin+ C, H-D- δ1-l+Rmin, 90 °, 0],
The O1(Rmin, H-D- δ1-l)
Wherein, H is garage depth；B is garage width, and C is the center of circle to A0X-direction distance, RminFor minimum turning half
Diameter, L are vehicle commander；W is vehicle width, L1For front and back shaft length；L is that rear overhang is long；δ1For the guard space in tailstock portion and garage bottom；δ2
It is the vehicle-width direction left and right sides at a distance from garage width direction；δ3For the most narrow spacing during vehicle parking with lane
From.
On the basis of above technical scheme, it is preferred that in the step 3, the method for fitting includes establishing more than five times
Item formula carries out the path planning of vertical parking stall automated parking system, and expression formula is as follows:
Y=a0+a1(x-x0)+a2(x-x0)2+a3(x-x0)3+a4(x-x0)4+a5(x-x0)5,
It solves its single order and leads and led with second order:
Y '=a1+2a2(x-x0)+3a3(x-x0)2+4a4(x-x0)3+5a5(x-x0)4,
Y "=a1+2a2(x-x0)+3a3(x-x0)2+4a4(x-x0)3+5a5(x-x0)4,
Known two control point [x0, y0, heading0, k_s0], [x1, y1, heading1, k_s1], boundary condition
Are as follows:
y′(x0)=tan (heading0)
y′(x1)=tan (heading1)
Wherein, the head direction of first point is heading0 and curvature is k_s0；The head of second point is directed toward
Heading1 and curvature are k_sl.
On the basis of above technical scheme, it is preferred that in the step 4, the method for constructing cost function includes counting
The cost value for calculating every alternate trajectory in track cluster of vertically parking chooses the smallest track of cost value as finally optimal
Track, track cost function are as follows:
C (i)=wsafecsafe(i)+wsmocsmo(i)+wdyncdyn(i)+wkinckin(i) mark, wherein i is the mark of alternate trajectory
Number, csafe(i)、csmo(i)、cdyn(i) and ckinIt (i) is respectively safety cost function, flatness cost function, dynamics generation
Valence function and kinematics cost function, wsafe、wsmo、wdynAnd wkinRespectively weight shared by this four cost functions.
On the basis of above technical scheme, it is preferred that when track is bonded expectation lane center, safety cost letter
Number csafe(i) cost value is 0, and the flatness cost function isWherein csmo(i) i-th rail is represented
The flatness cost function of mark, ki(s) be on i-th track arc length be the position s point curvature, it is cumulative upper and lower to be limited to path
Arc length s beginning and end, the dynamics cost function isWherein, cdyn(i) i-th is represented
The dynamics cost function of track,It is the longitudinal acceleration of each point on i-th track,It is each point on i-th track
Transverse acceleration,The kinematics cost function is ckin(i)=min (ki(s))。
Autonomous method of vertically parking based on high-precision map of the invention has below compared with the existing technology beneficial to effect
Fruit:
(1) present invention be issued based on cloud server based on high-precision map parking position information and parking lot and
The environmental information of road edge drive test sensor, vertical parking position information and environmental information are issued to by cloud server wait moor
Vehicle, the positioning navigation module of vehicle determine wait park in road edge or the position attribution of parking lot high-precision map,
Determine the positional relationship attribute under global coordinate system wait park between selected vertical parking position；
(2) autonomous track of vertically parking of the invention can regard the rail being made of continuous multi-section circular arc and curve as
Mark determining each switching point vertically parked under flat square parking position coordinate system, using circular arc to can choose between switching point
Or spline curve fitting, fit approach selection appropriately not only can guarantee the continuity of course angle but also also ensure the company of curvature
It is continuous, to guarantee the ride comfort of vehicle motion control, the shake of vehicle in parking process steering wheel to be eliminated with smoothly, it is real
Now safety is parked；
(3) present invention arbitrarily parks in a certain range starting point according to vehicle near to parking position, vertically parks meeting
Path constraint under the conditions of minimum parking position the constraint relationship, generates track cluster of vertically parking by sampled point, to every rail of track cluster
Mark assigns velocity information, constructs cost function, calculates the cost value of every alternate trajectory in track cluster of vertically parking, chooses cost
It is worth a smallest track as final optimal trajectory.It determines vertically to park and is put in storage optimal track of parking, control module control
Vehicle safety is parked.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the flow diagram of the autonomous method of vertically parking of the invention based on high-precision map.
Specific embodiment
Below in conjunction with embodiment of the present invention, the technical solution in embodiment of the present invention is carried out clearly and completely
Description, it is clear that described embodiment is only some embodiments of the invention, rather than whole embodiments.Base
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts all
Other embodiments shall fall within the protection scope of the present invention.
As shown in Figure 1, the autonomous method of vertically parking of the invention based on high-precision map comprising:
Step 1: wait an acquisition of parking based on the parking position information of high-precision map and parking lot and road edge drive test
The environmental information of sensor determines the position attribution wait park in high-precision map, determines wait park and selected vertical pool
The positional relationship attribute under global coordinate system between parking stall；
Step 2: determining each switching point wait park by flat square parking position coordinate system；
Step 3: being fitted using circular arc or spline curve to switching point, the spline curve of fitting forms rail of parking
Mark；
Step 4: choosing wait a place control point of parking is starting point of parking, meeting vertical parking path constraint and minimum
Under conditions of parking position the constraint relationship, track cluster of vertically parking is generated by sampled point, assigns velocity information, structure to every track
Cost function is built, the cost value of every track in track cluster of vertically parking is calculated, chooses the smallest track conduct of cost value
Final optimal trajectory.
In a specific embodiment, in the step 1, the method for obtaining parking position information includes being infused by V2X technology
Volume road edge or the cloud server in parking lot after succeeding in registration, obtain the cloud service in road edge or parking lot
Device issue based on high-precision map parking position information.
In embodiment of above, cloud server can be supplemented in real time by V2X technology and be updated road edge or be stopped
Parking lot based on high-precision map parking space information, the parking stall for having had vehicle to occupy not may be selected, according to time weighting,
Seleced parking stall late comer not may be selected.
Since the network coverage area of road edge or the cloud server in parking lot is extremely wide, intelligent driving vehicle
When needing road edge or Parking, start autonomous parking function, intelligent driving vehicle obtains nearest cloud service
Device plans a road edge corresponding from nearest cloud server or parking lot parking position, when intelligent driving vehicle reaches
Near road edge or parking lot, the parking stall for wanting to park can choose.
In embodiment of above, the cloud server in road edge described in step 1 or parking lot obtains high-precision
Map, high-precision map include parking position information, road information in road edge or parking lot；One side intelligent driving vehicle
The environmental information of the available vehicle-surroundings of the sensor of installation, so that vehicle is made correctly, safe decision, on the other hand
Cloud server can real-time update road edge or parking position and obstacle information in parking lot, especially vehicle driving
The environmental information of blind area, to make up the deficiency of intelligent driving vehicle sensors.
In a specific embodiment, the position attribution includes: ID, coordinate, head direction, the curvature, speed of body control point
Rate, the connectivity in place high-precision map lane and adjacent lane, place high-precision map track direction and body control point
Topological structure.
In a specific embodiment, the control point of the vehicle body is vehicle rear axle central point, and the ID includes Body Control
Lane information and body control point where point are located at the specific number information on the lane of place, and the coordinate is body control point
Coordinate, which is the coordinate of opposite global coordinate system, and the head is oriented to the suggestion traveling side of vehicle at body control point
The lane angulation to where with body control point, the curvature are path curve by the body control point in the vehicle body
Curvature at control point, rate be suggestion travel speed of the vehicle at the body control point, place high-precision map lane with
The connectivity of adjacent lane is the connectivity in lane and its left-lane and right lane where the control point, place high-precision map vehicle
Road direction is whether the body control point position keeps straight on, turns left, turning right and can turn around, place high-precision map vehicle body control
The topological structure of system point indicates the connection relationship between the body control point and adjacent body control point.
In a specific embodiment, the positional relationship attribute includes: the terminal A that parks3Coordinate, park terminal A3Direction, pool
Vehicle terminal A3Curvature and parking position size H × B, wherein H is the length of parking position, and B is the width of parking position.
In a specific embodiment, the global coordinate system is using terminal of parking as origin, and parking position width direction is x
Axis, parking position length direction are y-axis, and the switching point further includes the starting point A that parks0, turning starting point A1, turning terminal A2With park
Terminal A3, wait park from the starting point A that parks0Move in a straight line turning starting point A1, from turning starting point A1Under certain steering angle
Circular motion is done to turning terminal A2, finally from turning terminal A2Circular motion is done again reaches the terminal A that parks3, A1-A2Section circular arc
The center of circle be O1。
In a specific embodiment, the switching point A0、A1、A2And A3Method for solving include:
(Rmin-B/2)2+D2=(Rmin-δ2-W/2)2,
The A3[0,0,0 °, 0],
The A2[0, H-D- δ1- l, 0 °, 1/Rmin],
The A1[Rmin, H-D- δ1-l+Rmin, 90 °, 1/Rmin],
The A0[Rmin+ C, H-D- δ1-l+Rmin, 90 °, 0],
The O1(Rmin, H-D- δ1-l)。
In a specific embodiment, in the step 3, the method for fitting includes, establish three times, four times, Quintic spline it is bent
Line or three times, four times, quintic B-spline curve matching, quintic algebra curve is established in present embodiment, and to carry out vertical parking stall automatic
The path planning of parking system, expression formula are as follows:
Y=a0+a1 (x-x0)+a2(x-x0)2+a3(x-x0)3+a4(x-x0)4+a5(x-x0)5,
It solves its single order and leads and led with second order:
Y '=a1+2a2 (x-x0)+3a3(x-x0)2+4a4(x-x0)3+5a5(x-x0)4,
Y "=a1+2a2 (x-x0)+3a3(x-x0)2+4a4(x-x0)3+5a5(x-x0)4,
Known two control point [x0, y0, heading0, k_s0], [x1, y1, heading1, k_s1], boundary condition
Are as follows:
y′(x0)=tan (heading0)
y′(x1)=tan (heading1)
Wherein, the head direction of first point is heading0 and curvature is k_s0；The head of second point is directed toward
Heading1 and curvature are k_s1.
In a specific embodiment, in the step 4, the method for constructing cost function includes calculating track of vertically parking
The cost value of every alternate trajectory in cluster chooses the smallest track of cost value as final optimal trajectory, track cost
Function are as follows:
C (i)=wsafecsafe(i)+wsmocsmo(i)+wdyncdyn(i)+wkinckin(i),
Wherein i is the label of alternate trajectory, csafe(i)、csmo(i)、cdyn(i) and ckinIt (i) is respectively safety cost letter
Number, flatness cost function, dynamics cost function and kinematics cost function, wsafe、wsmo、wdynAnd wkinRespectively this four
Weight shared by a cost function.
In a specific embodiment, when track is bonded expectation lane center, safety cost function csafe(i) cost
Value is 0, and the flatness cost function is
Wherein csmo(i) the flatness cost function of i-th track, k are representediIt (s) is that arc length is the position s on i-th track
Point curvature, the beginning and end of the cumulative upper and lower arc length s for being limited to path, the dynamics cost function is
Wherein, cdyn(i) the dynamics cost function of i-th track is represented,It is that the longitudinal direction of each point on i-th track adds
Speed,It is the transverse acceleration of each point on i-th track,The kinematics cost function is ckin(i)=
min(ki(s))。
In a specific embodiment, the automatic vertical process of parking is:
Firstly, driving into vehicle to parking area, usually in roadside or parking lot, driver, which changes, opens automatic parking system
System, automated parking system detect the environmental information of vehicle periphery first, until searching idle parking space information, and prompt driver
Available free parking stall can stop, and driver selects idle parking stall, and parking system then calculates optimal trajectory；
Secondly, vehicle is parked according to optimal trajectory, arrive first at suitable reversing point, start reversing, reversing finishes
And suitable turn point is reached, start to turn round, and vehicle body is made to be parallel to each other with parking position length direction, vehicle body steering wheel returns automatically
Just, start to move backward, finally enter parking position, complete to park.
In embodiment of above, defining successful standard of parking is, during parking, vehicle is not sent out with two sides vehicle
Raw collision；At the end of parking, vehicle is parallel with the vehicle body direction of two sides vehicle, the plane of symmetry of vehicle and the center line weight of parking stall
It closes, vehicle tail is at a distance from the bottom of parking stall in 0.2-0.3m.
In a specific embodiment, based on three sections of path orthogonals of bicircular arcs park method core be determine three sections of paths
A1、A2、A3Three switching points are that vehicle carries out the starting point of circular motion, the terminal of circular motion and terminal of parking, vehicle respectively
A is moved to by other points1Point, and in A1Point starts to do circular motion, until moving to A2Point, vehicle is in A2The direction of point should be with
The length direction of parking position is consistent, and A2Point is located on parking position center line, into A2Point rear vehicle starts back positive direction disk and falls
Vehicle, until moving to A3It puts and completion of stopping is parked.
With A3Point is used as origin, and parking position length direction establishes y-axis, and parking position width direction establishes x-axis, is formed global straight
Angular coordinate system, it be garage depth B is garage width that wherein S, which is curb-to-curb width H,；P1、P2、P3、P4For four, garage vertex；A0、
A1、A2、A3It is four switching points parked；O1For the circular arc center of circle；C is the center of circle to A0X-axis direction distance；RminFor minimum turning
Radius；L is vehicle commander；W is vehicle width；L1For front and back shaft length；L is that rear overhang is long；δ1For the guard space in tailstock portion and garage bottom；
δ2It is the vehicle-width direction left and right sides at a distance from garage width direction；δ3For the most narrow spacing during vehicle parking with lane
From, curb-to-curb width according to the geometrical model of park process and the foundation vertically parked:
(Rmin-B/2)2+D2=(Rmin-δ2-W/2)2
Switching point A is solved in global rectangular coordinate system0、A1、A2、A3；(x, y, heading, k_s)
A3[0,0,0 °, 0]
A2[0, H-D- δ1- l, 0 °, 1/Rmin]
A1[Rmin, H-D- δ1-l+Rmin, 90 °, 1/Rmin]
A0[Rmin+ C, H-D- δ1-l+Rmin, 90 °, 0]
The wherein corresponding center of circle O of arc section1Coordinate are as follows:
O1(Rmin, H-D- δ1-l)
The constraint condition of vehicle in parking process anticollision are as follows:
In embodiment of above, for the process footprint that guarantees to park is smooth and steering wheel it is smooth, it is thus necessary to determine that rail of parking
Mark is in A1And A2The coordinate value zeroth order of two o'clock leads continuous, head direction single order and leads continuous and curvature second order and lead continuously, drives into vehicle
When parking areas starts to park, any known switching point A is set4, A4Attribute be (x4, y4, heading4, k_s4), with choosing
Illustrate for the optimal track selected:
Point A is arbitrarily switched to parking areas4To the starting point A that parks0Curve using quintic algebra curve be fitted；
From the starting point A that parks0To first turning point A1Curve using quintic algebra curve be fitted；
From first turning point A1To second turning point A2Circular arc circle be O1, radius is minimum turning radius Rmin
Circular arc；
From second turning point A2To the terminal A that parks3Curve using quintic algebra curve be fitted.
In specific embodiment, Chang'an CS555, basic size is it is found that garage vertical protection distance δ1=0.3；Garage is lateral
Guard space δ2=0.2；Coboundary guard space δ3=0.5；Minimum turning radius Rmin=8；Garage width B=2.6；Garage is deep
H=5.3；Curb-to-curb width S=5.5；Vehicle width W=2；Vehicle commander L=5；Distance l=1.0 of the back wheels of vehicle axis center to vehicle rear end；Before
The position L of axis center and rear axle1=2.650；Before needing to walk forward one section of linear distance before reversing to guarantee vehicle backing
The correct C=5 of state.
The minimum turning radius R similarly selectedmin=8m, thus the curvature of third section be -1/8=-0.125, first segment,
Though second segment and the 4th section of curvature have certain fluctuation but fluctuation is not above 1/8 up and down, meets the company of our curvature
It is continuous to require.It is found according to previous actual test, steering wheel angle variation in crosswise joint direction is related with curvature when automatic Pilot
, continual curvature can guarantee that steering wheel is more stable and smooth during rotation.
The foregoing is merely better embodiments of the invention, are not intended to limit the invention, all of the invention
Within spirit and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of autonomous method of vertically parking based on high-precision map, which comprises the steps of:
Step 1: being sensed wait park an acquisition based on the parking position information of high-precision map and parking lot and road edge drive test
The environmental information of device determines the position attribution wait park in high-precision map, determines wait park and selected vertical parking position
Between the positional relationship attribute under global coordinate system；
Step 2: determining each switching point wait park by flat square parking position coordinate system；
Step 3: being fitted using circular arc or spline curve to switching point, the spline curve of fitting forms track of parking；
Step 4: choosing wait a place control point of parking is starting point of parking, park meeting vertical parking path constraint with minimum
Under conditions of the constraint relationship of position, track cluster of vertically parking is generated by sampled point, velocity information is assigned to every track, constructs generation
Valence function calculates the cost value of every track in track cluster of vertically parking, and chooses the smallest track of cost value as final
Optimal trajectory.
2. the autonomous method of vertically parking based on high-precision map as described in claim 1, which is characterized in that the step 1
In, the method for obtaining parking position information includes that the cloud server in road edge or parking lot, note are registered by V2X technology
After volume success, obtain that the cloud server in road edge or parking lot issues based on high-precision map parking position information.
3. the autonomous method of vertically parking based on high-precision map as described in claim 1, which is characterized in that the position belongs to
Property include: ID, coordinate, the head direction of body control point, curvature, rate, place high-precision map lane and adjacent lane company
The topological structure of the general character, place high-precision map track direction and control point.
4. the autonomous method of vertically parking based on high-precision map as claimed in claim 3, which is characterized in that the vehicle body control
System point is vehicle rear axle central point, and the ID includes that lane information and body control point where body control point are located at place vehicle
Specific number information on road, the coordinate are the coordinate of body control point, which is the coordinate of opposite global coordinate system, institute
State lane angulation where head is oriented to the suggestion driving direction and body control point of vehicle at body control point, the song
Rate is curvature of the path curve at the body control point by the body control point, and rate is vehicle in the body control point
The connectivity of the suggestion travel speed at place, place high-precision map lane and adjacent lane be the body control point where lane with
The connectivity of its left-lane and right lane, place high-precision map track direction are whether the body control point position is straight
Row turns left, turns right and can turn around, and the topological structure at place high-precision map control point indicates the body control point and adjacent vehicle body
Connection relationship between control point.
5. the autonomous method of vertically parking based on high-precision map as described in claim 1, which is characterized in that close the position
Set attribute includes: the terminal A that parks3Coordinate, park terminal A3Direction, park terminal A3Curvature and parking position size H × B, wherein H
For the length of parking position, B is the width of parking position.
6. the autonomous method of vertically parking based on high-precision map as described in claim 1, which is characterized in that the global seat
Mark system is using terminal of parking as origin, and parking position width direction is x-axis, parking position length direction is y-axis, and the switching point also wraps
Include the starting point A that parks0, turning starting point A1, turning terminal A2With the terminal A that parks3, wait park from the starting point A that parks0It moves in a straight line
Turn starting point A1, from turning starting point A1Circular motion is done under certain steering angle to turning terminal A2, finally from turning terminal A2
Circular motion is done again reaches the terminal A that parks3, A1-A2The center of circle of section circular arc is O1。
7. the autonomous method of vertically parking based on high-precision map as claimed in claim 6, which is characterized in that the switching point
A0、A1、A2And A3Method for solving include:
(Rmin-B/2)2+D2=(Rmin-δ2-W/2)2,
The A3[0,0,00, 0],
The A2[0, H-D- δ1- l, 00, 1/Rmin],
The A1[Rmin, H-D- δ1-l+Rmin, 900, 1/Rmin],
The A0[Rmin+ C, H-D- δ1-l+Rmin, 900, 0],
The O1(Rmin, H-D- δ1-l)
Wherein, H is garage depth；B is garage width, and C is the center of circle to A0X-direction distance, RminFor minimum turning radius, L
For vehicle commander；W is vehicle width, L1For front and back shaft length；L is that rear overhang is long；δ1For the guard space in tailstock portion and garage bottom；δ2For vehicle
At left and right sides of width direction at a distance from garage width direction；δ3For the minimum range during vehicle parking with lane.
8. the autonomous method of vertically parking based on high-precision map as claimed in claim 6, which is characterized in that the step 3
In, the method for fitting includes the path planning established quintic algebra curve and carry out vertical parking stall automated parking system, and expression formula is such as
Under:
Y=a0+a1(x-x0)+a2(x-x0)2+a3(x-x0)3+a4(x-x0)4+a5(x-x0)5,
It solves its single order and leads and led with second order:
Y '=a1+2a2(x-x0)+3a3(x-x0)2+4a4(x-x0)3+5a5(x-x0)4,
Y "=a1+2a2(x-x0)+3a3(x-x0)2+4a4(x-x0)3+5a5(x-x0)4,
Known two control point [x0, y0, heading0, k_s0], [x1, y1, heading1, k_s1], boundary condition are as follows:
y′(x0)=tan (heading0)
y′(x1)=tan (heading1)
Wherein, the head direction of first point is heading0 and curvature is k_s0；The head direction of second point is heading1
And curvature is k_s1.
9. the autonomous method of vertically parking based on high-precision map as described in claim 1, which is characterized in that the step 4
In, the method for constructing cost function includes calculating the cost value of every alternate trajectory in track cluster of vertically parking, and chooses cost value
A smallest track is as final optimal trajectory, track cost function are as follows:
C (i)=wsafecsafe(i)+wsmocsmo(i)+wdyncdyn(i)+wkinckin(i),
Wherein i is the label of alternate trajectory, csafe(i)、csmo(i)、cdyn(i) and ckinIt (i) is respectively safety cost function, flat
Slip cost function, dynamics cost function and kinematics cost function, wsafe、wsmo、wdynAnd wkinRespectively this four costs
Weight shared by function.
10. the autonomous method of vertically parking based on high-precision map as claimed in claim 9, which is characterized in that when track is pasted
When closing expectation lane center, safety cost function csafe(i) cost value is 0, and the flatness cost function isWherein csmo(i) the flatness cost function of i-th track, k are representediIt (s) is arc on i-th track
The curvature of the point of a length of position s, the beginning and end of the cumulative upper and lower arc length s for being limited to path, the dynamics cost function
ForWherein, cdyn(i) the dynamics cost function of i-th track is represented,It is on i-th track
The longitudinal acceleration of each point,It is the transverse acceleration of each point on i-th track,The kinematics cost function
For ckin(i)=min (ki(s))。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910196482.5A CN109927716B (en) | 2019-03-11 | 2019-03-11 | Autonomous vertical parking method based on high-precision map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910196482.5A CN109927716B (en) | 2019-03-11 | 2019-03-11 | Autonomous vertical parking method based on high-precision map |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109927716A true CN109927716A (en) | 2019-06-25 |
| CN109927716B CN109927716B (en) | 2020-11-10 |
Family
ID=66987089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910196482.5A Active CN109927716B (en) | 2019-03-11 | 2019-03-11 | Autonomous vertical parking method based on high-precision map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109927716B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110435639A (en) * | 2019-06-28 | 2019-11-12 | 惠州市德赛西威汽车电子股份有限公司 | A kind of the multinomial paths planning method and storage medium of automated parking system |
| CN110562244A (en) * | 2019-08-07 | 2019-12-13 | 武汉乐庭软件技术有限公司 | automatic parking trajectory planning method based on target parking space warehouse-out |
| CN111131383A (en) * | 2019-11-18 | 2020-05-08 | 腾讯科技（深圳）有限公司 | Method and device for constructing automobile cloud service signal propagation path and storage medium |
| CN111196271A (en) * | 2020-01-21 | 2020-05-26 | 北京百度网讯科技有限公司 | Automatic parking method, device, equipment and storage medium |
| CN111307152A (en) * | 2020-02-18 | 2020-06-19 | 中国科学院合肥物质科学研究院 | Reverse generation planning method for autonomous parking path |
| CN111785065A (en) * | 2020-06-15 | 2020-10-16 | 北京航空航天大学 | Intelligent remote autonomous parking method based on user travel cost and travel efficiency |
| CN112026752A (en) * | 2020-08-12 | 2020-12-04 | 重庆长安汽车股份有限公司 | Automatic parking path following processing method and system, vehicle and storage medium |
| CN112124304A (en) * | 2020-11-24 | 2020-12-25 | 天津天瞳威势电子科技有限公司 | Library position positioning method and device and vehicle-mounted equipment |
| CN112601869A (en) * | 2020-04-10 | 2021-04-02 | 百度时代网络技术（北京）有限公司 | Secondary planning side-by-side parking method based on path planning |
| CN113386737A (en) * | 2021-07-13 | 2021-09-14 | 东风汽车集团股份有限公司 | Passenger-riding parking method based on fixed line |
| CN113781830A (en) * | 2021-09-15 | 2021-12-10 | 兰昀正 | Automatic intelligent parking management system and method |
| CN114018276A (en) * | 2021-09-14 | 2022-02-08 | 武汉光庭信息技术股份有限公司 | Optimal parking space determining method and system, electronic device and storage medium |
| CN114296452A (en) * | 2021-12-16 | 2022-04-08 | 华人运通(上海)自动驾驶科技有限公司 | Automatic parking path planning method, apparatus and computer-readable storage medium |
| CN114676939A (en) * | 2022-05-26 | 2022-06-28 | 之江实验室 | Multi-vehicle-type parameter self-adaptive reference line smoothing method and system |
| CN115243960A (en) * | 2020-03-02 | 2022-10-25 | 法雷奥开关和传感器有限责任公司 | Method for operating a vehicle, parking assistance system and vehicle |
| CN117058919A (en) * | 2023-10-10 | 2023-11-14 | 北京集度科技有限公司 | Parking stall recommendation method and device, computer equipment and storage medium |
| CN117734676A (en) * | 2024-02-19 | 2024-03-22 | 知行汽车科技(苏州)股份有限公司 | Automatic parking method, device, equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008064892A1 (en) * | 2006-11-29 | 2008-06-05 | Universität Koblenz-Landau | Method for determining a position, device and computer program product |
| CN102398596A (en) * | 2010-09-07 | 2012-04-04 | 北京经纬恒润科技有限公司 | Parking control device and system and parking control method |
| CN104627175A (en) * | 2015-01-22 | 2015-05-20 | 北京理工大学 | Intelligent parking system with man-vehicle interaction function |
| CN105857306A (en) * | 2016-04-14 | 2016-08-17 | 中国科学院合肥物质科学研究院 | Vehicle autonomous parking path programming method used for multiple parking scenes |
| CN106945662A (en) * | 2017-03-30 | 2017-07-14 | 重庆大学 | A kind of vertical automatic parking paths planning method and system |
| CN109084798A (en) * | 2018-08-29 | 2018-12-25 | 武汉环宇智行科技有限公司 | Network issues the paths planning method at the control point with road attribute |
-
2019
- 2019-03-11 CN CN201910196482.5A patent/CN109927716B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008064892A1 (en) * | 2006-11-29 | 2008-06-05 | Universität Koblenz-Landau | Method for determining a position, device and computer program product |
| CN102398596A (en) * | 2010-09-07 | 2012-04-04 | 北京经纬恒润科技有限公司 | Parking control device and system and parking control method |
| CN104627175A (en) * | 2015-01-22 | 2015-05-20 | 北京理工大学 | Intelligent parking system with man-vehicle interaction function |
| CN105857306A (en) * | 2016-04-14 | 2016-08-17 | 中国科学院合肥物质科学研究院 | Vehicle autonomous parking path programming method used for multiple parking scenes |
| CN106945662A (en) * | 2017-03-30 | 2017-07-14 | 重庆大学 | A kind of vertical automatic parking paths planning method and system |
| CN109084798A (en) * | 2018-08-29 | 2018-12-25 | 武汉环宇智行科技有限公司 | Network issues the paths planning method at the control point with road attribute |
Non-Patent Citations (1)
| Title |
|---|
| 梁钊: "自动泊车的路径规划技术研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110435639A (en) * | 2019-06-28 | 2019-11-12 | 惠州市德赛西威汽车电子股份有限公司 | A kind of the multinomial paths planning method and storage medium of automated parking system |
| CN110435639B (en) * | 2019-06-28 | 2021-08-20 | 惠州市德赛西威汽车电子股份有限公司 | Polynomial path planning method and storage medium for automatic parking system |
| CN110562244A (en) * | 2019-08-07 | 2019-12-13 | 武汉乐庭软件技术有限公司 | automatic parking trajectory planning method based on target parking space warehouse-out |
| CN111131383A (en) * | 2019-11-18 | 2020-05-08 | 腾讯科技（深圳）有限公司 | Method and device for constructing automobile cloud service signal propagation path and storage medium |
| CN111131383B (en) * | 2019-11-18 | 2021-10-19 | 腾讯科技（深圳）有限公司 | Method and device for constructing automobile cloud service signal propagation path and storage medium |
| CN111196271A (en) * | 2020-01-21 | 2020-05-26 | 北京百度网讯科技有限公司 | Automatic parking method, device, equipment and storage medium |
| CN111307152A (en) * | 2020-02-18 | 2020-06-19 | 中国科学院合肥物质科学研究院 | Reverse generation planning method for autonomous parking path |
| CN115243960B (en) * | 2020-03-02 | 2024-03-08 | 法雷奥开关和传感器有限责任公司 | Method for operating a vehicle, parking assistance system and vehicle |
| CN115243960A (en) * | 2020-03-02 | 2022-10-25 | 法雷奥开关和传感器有限责任公司 | Method for operating a vehicle, parking assistance system and vehicle |
| CN112601869A (en) * | 2020-04-10 | 2021-04-02 | 百度时代网络技术（北京）有限公司 | Secondary planning side-by-side parking method based on path planning |
| CN112601869B (en) * | 2020-04-10 | 2022-10-28 | 百度时代网络技术（北京）有限公司 | Method for operating an autonomously driven vehicle, machine-readable medium and data processing system |
| WO2021203426A1 (en) * | 2020-04-10 | 2021-10-14 | Baidu.Com Times Technology (Beijing) Co., Ltd. | Pull over method based on quadratic programming for path planning |
| CN111785065A (en) * | 2020-06-15 | 2020-10-16 | 北京航空航天大学 | Intelligent remote autonomous parking method based on user travel cost and travel efficiency |
| CN112026752A (en) * | 2020-08-12 | 2020-12-04 | 重庆长安汽车股份有限公司 | Automatic parking path following processing method and system, vehicle and storage medium |
| CN112026752B (en) * | 2020-08-12 | 2021-08-06 | 重庆长安汽车股份有限公司 | Automatic parking path following processing method and system, vehicle and storage medium |
| CN112124304A (en) * | 2020-11-24 | 2020-12-25 | 天津天瞳威势电子科技有限公司 | Library position positioning method and device and vehicle-mounted equipment |
| CN113386737A (en) * | 2021-07-13 | 2021-09-14 | 东风汽车集团股份有限公司 | Passenger-riding parking method based on fixed line |
| CN114018276A (en) * | 2021-09-14 | 2022-02-08 | 武汉光庭信息技术股份有限公司 | Optimal parking space determining method and system, electronic device and storage medium |
| CN113781830A (en) * | 2021-09-15 | 2021-12-10 | 兰昀正 | Automatic intelligent parking management system and method |
| CN114296452A (en) * | 2021-12-16 | 2022-04-08 | 华人运通(上海)自动驾驶科技有限公司 | Automatic parking path planning method, apparatus and computer-readable storage medium |
| CN114296452B (en) * | 2021-12-16 | 2024-05-28 | 华人运通(上海)自动驾驶科技有限公司 | Automatic parking path planning method, equipment and computer readable storage medium |
| CN114676939A (en) * | 2022-05-26 | 2022-06-28 | 之江实验室 | Multi-vehicle-type parameter self-adaptive reference line smoothing method and system |
| CN114676939B (en) * | 2022-05-26 | 2022-09-02 | 之江实验室 | Multi-vehicle-type parameter self-adaptive reference line smoothing method and system |
| CN117058919A (en) * | 2023-10-10 | 2023-11-14 | 北京集度科技有限公司 | Parking stall recommendation method and device, computer equipment and storage medium |
| CN117058919B (en) * | 2023-10-10 | 2024-01-12 | 北京集度科技有限公司 | Parking stall recommendation method and device, computer equipment and storage medium |
| CN117734676A (en) * | 2024-02-19 | 2024-03-22 | 知行汽车科技(苏州)股份有限公司 | Automatic parking method, device, equipment and storage medium |
| CN117734676B (en) * | 2024-02-19 | 2024-05-03 | 知行汽车科技(苏州)股份有限公司 | Automatic parking method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109927716B (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109927716A (en) | Autonomous method of vertically parking based on high-precision map | |
| CN108256233B (en) | Intelligent vehicle trajectory planning and tracking method and system based on driver style | |
| CN109866762B (en) | Autonomous parallel parking method based on high-precision map | |
| CN107340772B (en) | Unmanned-oriented anthropomorphic reference trajectory planning method | |
| EP3829958B1 (en) | Method for steering a vehicle and apparatus therefor | |
| CN107264531B (en) | The autonomous lane-change of intelligent vehicle is overtaken other vehicles motion planning method in a kind of semi-structure environment | |
| CN111307152B (en) | Reverse generation planning method for autonomous parking path | |
| CN105197010B (en) | Auxiliary parking system and auxiliary are parked control method | |
| CN113492830B (en) | Vehicle parking path planning method and related equipment | |
| CN107479556B (en) | Double-wheel self-balancing car owner moves collision free trajectory and tenacious tracking control method | |
| CN105939920A (en) | Active steering system and method for controlling vehicle traveling | |
| CN106926844A (en) | A kind of dynamic auto driving lane-change method for planning track based on real time environment information | |
| CN110281928A (en) | Controller of vehicle, control method for vehicle and storage medium | |
| CN109709943B (en) | Method for selecting station-entering stop points of automatically driven buses | |
| CN103158703A (en) | Control method for parallel parking | |
| CN112068574A (en) | Control method and system for unmanned vehicle in dynamic complex environment | |
| CN110103962A (en) | Controller of vehicle, control method for vehicle and storage medium | |
| CN113212424B (en) | Vehicle and automatic parking method and device thereof | |
| JP2023518692A (en) | Vehicle Control Schemes for Autonomous Vehicle Systems | |
| CN116710346A (en) | Method and system for monitoring vehicle movement with driver safety alert | |
| CN113173163A (en) | System and method for learning driver preferences and adapting lane centering control to driver behavior | |
| CN114148348A (en) | Stop control method, apparatus and computer program for autonomous vehicle | |
| CN115257746A (en) | Uncertainty-considered decision control method for lane change of automatic driving automobile | |
| CN115489548A (en) | Intelligent automobile park road path planning method | |
| CN114898564A (en) | Intersection multi-vehicle cooperative passing method and system under unstructured scene |
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 |