CN107792062B - Automatic parking control system - Google Patents
Automatic parking control system Download PDFInfo
- Publication number
- CN107792062B CN107792062B CN201710975324.0A CN201710975324A CN107792062B CN 107792062 B CN107792062 B CN 107792062B CN 201710975324 A CN201710975324 A CN 201710975324A CN 107792062 B CN107792062 B CN 107792062B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- control
- parking
- layer
- track
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims abstract description 6
- 238000004088 simulation Methods 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 7
- 230000005484 gravity Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 5
- 238000003032 molecular docking Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 abstract description 3
- 239000000284 extract Substances 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000031068 symbiosis, encompassing mutualism through parasitism Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/06—Automatic manoeuvring for parking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Geometry (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
Abstract
The invention provides an automatic parking control system. The system divides the whole automatic parking process into an input layer, a strategy layer, a planning layer and a control layer. In the automatic parking control process, the input layer generates control instructions and parking track data sets of different types of vehicles through simulation; the strategy layer learns the simulation data by using a deep neural network algorithm and extracts the general relation between the control instruction and the parking track; the planning layer finds a proper parking strategy through training in a few steps, gives a control instruction under the parking scene and generates a planning track; and the control layer performs control feedback according to the deviation of the actual parking track and the planned track, so that the parking track is closest to the ideal track planned by the system.
Description
Technical field
The present invention relates to automatic parking fields, more particularly to the automatic parking control system towards general scene.
Background technique
For many drivers, parallel parking is a kind of experience of pain, and big city parking space is limited, by vapour
Vehicle drives into narrow space and has become a required skill.Few the case where having stopped vehicle without taking some twists and turns, parking may
Traffic jam, neurolysis and bumper is caused to be hit curved.With the development of automatic parking technology, the above problem has obtained very big
Improvement.Automatic parking technology additionally aids in addition to that can help driver's automatic stopping and solves some of densely populated city
Parking and traffic problems.Sometimes, it can stop in small space and be limited by driver's technology.Automatic parking technology can be with
In a smaller space by automobile parking, these spaces are more much smaller than the space that most of drivers oneself can stop.This just makes
Parking stall can be more easily found by obtaining car owner, while automobile the space occupied of identical quantity is also smaller.
In the prior art, as publication number CN107102642A provides a kind of automatic parking system for pilotless automobile
System, primarily focuses on automatic parking monitoring sensor-based system, carries out estimating for track of vehicle using the detection data of geomagnetic sensor
It calculates.If publication number CN106427996A provides a kind of multi-functional park control method and system, by obtaining vehicle periphery barrier
Hinder object information;Automatic parking mode is selected according to obstacles around the vehicle information or is remotely controlled mode of parking.Such as publication number CN
106043282 A provide a kind of full-automatic parking system and its control method for vehicle, according to the periphery of the vehicle
Environmental information and the running state information of the vehicle cook up parking path, control electric boosting steering system and electronic stability
System and gear box control unit are automatically parked according to parking path completion.
The hardware that the related content of " automatic parking " mainly lays particular emphasis on automated parking system in the prior art constitutes, is each
Part of module be how to work and each module between communication mode, most of technology contents are without reference to parking scene
Consider, all has not been able to the parking problem for solving various parking scenes and different berth types.
Summary of the invention
In order to solve the above technical problem, the present invention provides a kind of automatic parking control systems.
Specifically adopt the following technical scheme that
The system includes input layer, strategic layer, planning layer and control layer;The input layer is for receiving and perceiving current shape
The orientation and size of car speed, position and berth under state;The strategic layer is according to current vehicle letter related to berth
Breath provides the control operational order of automatic parking;The kinetic model of the planning layer combination vehicle provides planning parking rail
Mark;The control layer is according to practical parking trajectory and plans that the deviation of parking trajectory carries out real-time feedback control.
Preferably, the input layer defines vehicle according to car body size, position of centre of gravity, wheel base, front and back wheel rotary inertia
Type;Track generation is carried out to different type of vehicle respectively: entire docking process is divided into N number of stage, the control in N number of stage
Instruction set processed is δf N={ δf(1),…,δf(N)};Specific vehicle control instruction is from K pilot angle in each stage
Set Sδ={ δ1,…,δk, the vehicle of each type can obtain KNA combined result;The time span in each stage is TN,
Total time span is T=T1+…+TN;Simulation step length is t, wherein TN=K*t;
The strategic layer learns to obtain vehicle by deep neural network according to vehicle final position, drift angle and speed
Control instruction combination;
The planning layer is according to control instruction set { δ1,δ2,…,δt, join in conjunction with current specific vehicle dynamic model
Number, obtains vehicle parking track;
The control layer carries out feedback control according to the deviation of actually park track and planned trajectory, generates rail of finally parking
Mark.
Preferably, the planning layer obtains the concrete mode of vehicle parking track are as follows:
1) in forward mode, according to vehicle-state equation of transfer
And
δf=δmax, δr=0,
It obtains
Wherein,For last moment Vehicular system state variable in forward mode,For subsequent time vehicle in forward mode
System state variables;δfFor front wheel steering angle, δrFor rear-axle steering angle, δmaxFor steering locking angle;
2) in reversing mode, according to vehicle-state equation of transfer
And
δr=0, δf=δmax
It obtains
Wherein,For last moment Vehicular system state variable in reversing mode,For subsequent time in reversing mode
Vehicular system state variable.
Preferably, the specific steps of the control layer feedback control are as follows:
Feedback control is carried out according to the rotational angular velocity r under the angle β and inertial coodinate system of car speed and the vehicle longitudinal axis:
The state space vectors of original system are expressed as
The variation real system of system parameter is
The state space vectors of feedback system are expressed as
Wherein, x=[β, r]TFor the state variable of idealized system;X '=[β ', r ']TFor the state variable of real system;A,
B is state constant;U is vehicle corner;K is feedback matrix;
By objective functionMinimum, obtaining state feedback controller is
U=-Kx.
Preferably, the specific steps of the control layer control feedback are as follows:
Feedback control is carried out according to vehicle location and corner deviation:
By objective function
Minimum, obtaining state feedback controller is
U=-Kx
Wherein:
The coordinate of (x ', y ') expression actual path point;
The coordinate of (x, y) expression ideal trajectory point;
The corner of ψ ' expression actual path point;
The corner of ψ expression ideal trajectory point;
K=[k1, k2] indicates feedback matrix.
The invention has the following beneficial effects:
(1) automated parking system proposed by the present invention is to be looked for towards general scene by algorithm study and on-site training
To the parking strategy for adapting to current scene, solve the problems, such as that the applicable berth type of current shutdown system is single;
(2) two kinds of track of vehicle control modes based on control theory algorithm are proposed, are simply provided than in the prior art
The mode of the correction value of one speed or deflection angle is more accurate.
Detailed description of the invention
Fig. 1 is automated parking system block schematic illustration.
Fig. 2 is two kinds of different automobile types simulation track schematic diagrames.
Fig. 3 is neural network structure schematic diagram.
Fig. 4 is planned trajectory schematic diagram.
Fig. 5 is vehicle dynamic model schematic diagram.
Fig. 6 is to carry out feedback control principle schematic diagram to δ _ f according to β and r.
Fig. 7 is that position and corner deviation carry out feedback control principle schematic diagram.
Specific embodiment
Entire automatic parking process is divided into four layers by the automatic parking control system towards general scene of the invention: defeated
Enter layer, strategic layer, planning layer and control layer.As shown in Figure 1:
Input layer is used to receive and perceive car speed, position and the orientation in berth and the size under current state;Plan
Omit the control operational order that layer provides automatic parking according to the relevant information of current vehicle and berth;Planning layer combination vehicle
Kinetic model provide planning parking trajectory;Control layer is according to practical parking trajectory and plans that the deviation of parking trajectory carries out in fact
When feedback control.
The control instruction of different type vehicle is generated by MATLAB simulation software and collateral learning algorithm first and is parked
Track data collection;Secondly emulation data are learnt using deep neural network algorithm, extracts control instruction and rail of parking
General relationship between mark, then can be found by the training of a small number of steps when given one any one parking scene
Suitable parking strategy provides the control instruction under this parking lot scape;Then for the specific dynamics of vehicle of current vehicle
Model provides the track of parking under theoretical condition;Finally, control feedback is carried out according to the deviation generated during actually parking,
Make to park track closest to systems organization ideal trajectory.
(1) define different vehicle type: different automobile types have different characteristics parameter, such as car body size, position of centre of gravity, preceding
Rear axle is away from, front and back wheel rotary inertia etc., we choose two kinds of vehicles, and A represents car, and B represents SUV.
1 different vehicle type parameter example of table
(2) emulation generates control instruction and parking trajectory: carrying out track respectively for two different type of vehicle A and B
It generates.Entire docking process is divided into N number of stage, the control instruction collection in N number of stage is combined into δf N={ δf(1),…,δf(N)};Often
Set S of the specific vehicle control instruction from K pilot angle in a stageδ={ δ1,…,δk, therefore, each type
Vehicle can obtain KNA combined result;The time span in each stage is TN, total time span is T=T1+…+TN;Emulation
Step-length is t, TN=K*t.Fig. 1 is the simulation track of two kinds of vehicle, δf N=-0.6, -0.4, -0.2,0,0.2,0.4,
0.6 }, K=7, N=4, t=0.01s, TN=3s, symbiosis is at 2401 tracks.
(3) neural network learning: in order to can determine one in the case where learning vehicle final position, drift angle and speed
Vehicle is accurately parked in final position to realize by kind control instruction combination, we solve this using deep neural network algorithm
Problem.Fig. 2 is the structural representation of neural network, is divided into input layer, hidden layer and output layer.Input is the position of vehicle target state
It setsWith velocity vector v, the control instruction set { δ for needs is exported1,δ2,…,δt}。
(4) trajectory planning: in given control instruction set { δ1,δ2,…,δtOn the basis of, in conjunction with current specific vehicle
Kinetic parameters provide vehicle parking track.Fig. 3 is the example of a planned trajectory.
Fig. 4 is vehicle dynamic model rough schematic view, and parameter used has as follows in model:
● v=car speed
● the component of v_x=speed in the horizontal direction
● the component of v_y=speed in the vertical direction
● β=car speed and vehicle longitudinal axis angle
●Rotational angular velocity under=inertial coodinate system
● x=vehicle's center of gravity abscissa
● y=vehicle's center of gravity ordinate
● the lateral force of the center of gravity F=
●δf(δr)=front-wheel (rear-wheel) steering angle
● θ=vehicle front-wheel and berth long axis direction angle, direction of traffic conversion critical view angle
● ψ=from x-axis to the corner of vehicle long axis
1) forward mode
Vehicle-state equation of transfer is
WhereinFor last moment system state variables,For subsequent time system state variables.
Wherein:
Cf=μ cf,Cr=μ cr
Tire stiffness Coefficient mgV is to vehicle corner control amount Cf、CrInfluence coefficient;
Tire stiffness Coefficient mgV is to vehicle corner rate CflfInfluence coefficient;
Tyre rotation inertia IgzTo vehicle corner rate CflfInfluence coefficient;
Tyre rotation inertia is to vehicle corner rate CflfInfluence coefficient;
Influence coefficient of the front-wheel stiffness coefficient to front wheel angle control amount;
Influence coefficient of the rear-wheel stiffness coefficient to rear-wheel corner control amount;
Influence coefficient of the front tyre rotary inertia to front wheel angle control amount;
Influence coefficient of the rear tyre rotary inertia to rear-wheel corner control amount;
Cf=μ cf: front tyre stiffness coefficient when coefficient of road adhesion is μ;
Cr=μ cr: rear tyre stiffness coefficient when coefficient of road adhesion is μ;
(dry pavement μ=1, wet road surface μ=0.5).
When advance, δf=δmax, δr=0, then:
That is:
2) reversing mode
If the model is not influenced by vehicle forerunner's rear-guard, model of moving backward can be regarded as the tailstock as headstock, still
Advance model is so used, then each parameter is exchanged before and after vehicle:
Wherein:
Therefore:
δ when reversingf *=δr=0, δr *=δf=δmax, therefore
Then:
No matter β and r are incremental form due to advancing or retreating, so defining identical;But ψ is cumulant, currently
Into when,
ψ*=ψ+r* Δ t;
When reversing, the tailstock is considered as headstock, so
ψ*=ψ+r* Δ t+ π;
Velocity component
v_x*=| v | * cos (β+ψ*);
v_y*=| v | * sin (β+ψ*);
Position coordinates
x*=x+vx*Δt;
y*=y+vy*Δt;
Deflection angle
ψ*=ψ+r* Δ t;(advance)
ψ*=ψ+r* Δ t+ π;(reversing).
(5) feedback control: the model parameter due to vehicle abrasion, environmental change etc., in actual vehicle operating system
It may be had differences with the model parameter of ideal planning system, so as to cause inclined between practical parking trajectory and planned trajectory
Difference.In order to eliminate as much as or reduce this deviation, we carry out feedback control to system using linear control method.
In practical shutdown system, due to the intrinsic parameter of vehicle such as mg、lf(lr)、Cf(Cr) difference, vehicle running track meeting
It is had differences with the track under idealized system.To eliminate this species diversity, negative feedback control is added to system, to adjust vehicle operation
Track.
The feedback control that track of vehicle is adjusted is divided into two kinds: first is that according to the deviation of internal system variable quantity β and r to δfInto
Row feedback control;Second is that according to system cumulant, that is, position and angular deviation to δfCarry out feedback control.
1) according to β and r to δfCarry out feedback control
According to vehicle dynamic model it is found that the change of system parameter can cause the variation of system change amount β and r, in turn
Influence track of vehicle.Feedback principle is as shown in Figure 5.
The state space vectors of original system can be expressed as
Since the variation real system of system parameter is
According to LQR control method, we will design a state feedback controller u=-Kx and make objective functionIt is minimum.So, the state space vectors of feedback system can be expressed as
Wherein x=[β, r]T: the state variable of idealized system;
X '=[β ', r ']T: the state variable of real system;
A, B are state constant;
U=δf: vehicle corner;
K: feedback matrix K=[k1, k2], circular refers to LQR control algolithm.
Emulation step number is set to 12000 steps in MATLAB discrete system, step-length 0.001s is divided into four-stage:
Stage1:step1-step3000, δf=-0.4 (v=-1)/δf=0.4 (v=1);
Stage2:step3001-step6000, δf=0;
Stage3:step6001-step9000, δf=0.4 (v=-1)/δf=-0.4 (v=1);
Stage4:step9001-step12000, δf=0.Emulation step number is set to 12000 in MATLAB discrete system
Step, step-length 0.001s are divided into four-stage:
Stage1:step1-step3000, δf=-0.4 (v=-1)/δf=0.4 (v=1);
Stage2:step3001-step6000, δf=0;
Stage3:step6001-step9000, δf=0.4 (v=-1)/δf=-0.4 (v=1);
Stage4:step9001-step12000, δf=0.
2) feedback control is carried out according to vehicle location and corner deviation, feedback principle is as shown in Figure 6.
Under the premise of knowing last moment feedback ideal trajectory point and actual path point, we can find a steering
Angle makes the actual path of vehicle next step closest to the track of planning path, and makes objective function
It is minimum.Wherein:
The coordinate of (x ', y ') expression actual path point;
The coordinate of (x, y) expression ideal trajectory point;
The corner of ψ ' expression actual path point;
The corner of ψ expression ideal trajectory point;
K=[k1, k2] indicates feedback matrix, herein k1, k2=1;
According to the limitation of vehicle steering locking angle, δ is takenf∈[-0.70,0.70].Feedback procedure are as follows:
● step1: original system δf=0.4, feedback system δf=0.4
● step2-step300: original system δf=0.4, [- 0.70,0.70]
● step301-step600: original system δf=0, feedback system δf=[- 0.70,0.70]
● step601-step900: original system δf=-0.4, feedback system δf=[- 0.70,0.70]
● step900-step1200: original system δf=0, feedback system δf=[- 0.70,0.70].
Claims (4)
1. a kind of automatic parking control system, which is characterized in that
The system includes input layer, strategic layer, planning layer and control layer;
The input layer is used to receiving and perceiving car speed, position and the orientation in berth and the size under current state;
The strategic layer provides the control operational order of automatic parking according to the relevant information of current vehicle and berth;
The kinetic model of the planning layer combination vehicle provides planning parking trajectory;
The control layer is according to practical parking trajectory and plans that the deviation of parking trajectory carries out real-time feedback control;
The input layer defines type of vehicle according to car body size, position of centre of gravity, wheel base, front and back wheel rotary inertia;To not
Same type of vehicle carries out track generation respectively: entire docking process is divided into N number of stage, the control instruction set in N number of stage
For δf N={ δf(1),…,δf(N)};Set S of the specific vehicle control instruction from K pilot angle in each stageδ=
{δ1,…,δk, the vehicle of each type can obtain KNA combined result;The time span in each stage is TN, total time
Length is T=T1+…+TN;Simulation step length is t, wherein TN=K*t;
The strategic layer learns to obtain the control of vehicle by deep neural network according to vehicle final position, drift angle and speed
Instructing combination;
The planning layer is according to control instruction set deltaf N={ δf(1),…,δf(N) }, in conjunction with current specific dynamics of vehicle mould
Shape parameter obtains vehicle parking track;
The control layer carries out feedback control according to the deviation of actually park track and planned trajectory, generates track of finally parking.
2. a kind of automatic parking control method towards general parking scene as described in claim 1, which is characterized in that described
Planning layer obtains the concrete mode of vehicle parking track are as follows:
1) in forward mode, according to vehicle-state equation of transfer
And
δf=δmax, δr=0,
It obtains
Wherein,For last moment Vehicular system state variable in forward mode,For subsequent time vehicle system in forward mode
System state variable;δfFor front wheel steering angle, δrFor rear-axle steering angle, δmaxFor steering locking angle;
2) in reversing mode, according to vehicle-state equation of transfer
And
δr=0, δf=δmax
It obtains
Wherein,For last moment Vehicular system state variable in reversing mode,For subsequent time vehicle in reversing mode
System state variables, a11For tire stiffness Coefficient mgInfluence coefficient of the v to vehicle corner control amount;a12For tire stiffness coefficient
mgV is to vehicle corner rate CflfInfluence coefficient;a21For tyre rotation inertia IgzTo the influence coefficient of vehicle corner rate;a22
For tyre rotation inertia IgzTo the influence coefficient of vehicle corner rate;b11It is front-wheel stiffness coefficient to front wheel angle control amount
Influence coefficient;b12It is rear-wheel stiffness coefficient to the influence coefficient of rear-wheel corner control amount;b21For front tyre rotary inertia IgzIt is right
The influence coefficient of front wheel angle control amount;b22For rear tyre rotary inertia IgzTo the influence coefficient of rear-wheel corner control amount;Cf
Front tyre stiffness coefficient when for coefficient of road adhesion being μ;CrRear tyre rigidity system when for coefficient of road adhesion being μ
Number.
3. a kind of automatic parking control method towards general parking scene as described in claim 1, which is characterized in that described
The specific steps of control layer feedback control are as follows:
Feedback control is carried out according to the rotational angular velocity r under the angle β and inertial coodinate system of car speed and the vehicle longitudinal axis:
The state space vectors of original system are expressed as
The variation real system of system parameter is
The state space vectors of feedback system are expressed as
Wherein, x=[β, r]TFor the state variable of idealized system;X '=[β ', r ']TFor the state variable of real system;A, B are
State constant;U is vehicle corner;K is feedback matrix;
By objective functionMinimum, obtaining state feedback controller is u=-Kx.
4. a kind of automatic parking control method towards general parking scene as described in claim 1, which is characterized in that described
The specific steps of control layer control feedback are as follows:
Feedback control is carried out according to vehicle location and corner deviation:
By objective function
Minimum, obtaining state feedback controller u is u=-Kx
Wherein:
The coordinate of (x ', y ') expression actual path point;
The coordinate of (x, y) expression ideal trajectory point;
The corner of ψ ' expression actual path point;
The corner of ψ expression ideal trajectory point;
K=[k1, k2] indicates feedback matrix.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710975324.0A CN107792062B (en) | 2017-10-16 | 2017-10-16 | Automatic parking control system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710975324.0A CN107792062B (en) | 2017-10-16 | 2017-10-16 | Automatic parking control system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107792062A CN107792062A (en) | 2018-03-13 |
CN107792062B true CN107792062B (en) | 2019-11-05 |
Family
ID=61534130
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710975324.0A Active CN107792062B (en) | 2017-10-16 | 2017-10-16 | Automatic parking control system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107792062B (en) |
Families Citing this family (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108407805B (en) * | 2018-03-30 | 2019-07-30 | 中南大学 | A kind of vehicle automatic parking method based on DQN |
CN108860139B (en) * | 2018-04-11 | 2019-11-29 | 浙江零跑科技有限公司 | A kind of automatic parking method for planning track based on depth enhancing study |
CN110654374B (en) * | 2018-06-29 | 2022-03-18 | 比亚迪股份有限公司 | Automatic parking simulation system and test method thereof |
CN110654373A (en) * | 2018-06-29 | 2020-01-07 | 比亚迪股份有限公司 | Automatic parking method and device and vehicle |
CN109895764B (en) | 2018-06-29 | 2023-06-27 | 华为技术有限公司 | Method and device for determining automatic parking strategy |
CN110136481B (en) * | 2018-09-20 | 2021-02-02 | 初速度(苏州)科技有限公司 | Parking strategy based on deep reinforcement learning |
CN111098850A (en) * | 2018-10-25 | 2020-05-05 | 北京初速度科技有限公司 | Automatic parking auxiliary system and automatic parking method |
CN111434550B (en) * | 2019-01-15 | 2021-12-31 | 魔门塔(苏州)科技有限公司 | Simulation-based parking strategy generation method and system |
CN109823348B (en) * | 2019-02-19 | 2021-04-30 | 百度在线网络技术(北京)有限公司 | Unmanned vehicle reverse model control method, device, equipment and computer readable medium |
CN110525428B (en) * | 2019-08-29 | 2020-09-04 | 合肥工业大学 | Automatic parking method based on fuzzy depth reinforcement learning |
CN111047948B (en) * | 2019-11-27 | 2022-06-10 | 康忠文 | Auxiliary method and system for learning to train |
CN111098852B (en) * | 2019-12-02 | 2021-03-12 | 北京交通大学 | Parking path planning method based on reinforcement learning |
CN113110500B (en) * | 2021-05-10 | 2023-01-03 | 的卢技术有限公司 | Transverse control method for low-speed automatic parking of automatic-driving automobile |
CN113252366A (en) * | 2021-06-23 | 2021-08-13 | 奇瑞新能源汽车股份有限公司 | Automatic parking evaluation method and device for vehicle, vehicle and storage medium |
CN113978547B (en) * | 2021-10-21 | 2022-08-02 | 江铃汽车股份有限公司 | Automatic driving steering control method and system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104057950A (en) * | 2014-05-21 | 2014-09-24 | 重庆长安汽车股份有限公司 | Full-automatic parking system |
CN104260722A (en) * | 2014-09-23 | 2015-01-07 | 北京理工大学 | Automatic parking system |
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 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10304335B2 (en) * | 2016-04-12 | 2019-05-28 | Ford Global Technologies, Llc | Detecting available parking spaces |
-
2017
- 2017-10-16 CN CN201710975324.0A patent/CN107792062B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104057950A (en) * | 2014-05-21 | 2014-09-24 | 重庆长安汽车股份有限公司 | Full-automatic parking system |
CN104260722A (en) * | 2014-09-23 | 2015-01-07 | 北京理工大学 | Automatic parking system |
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 |
Non-Patent Citations (1)
Title |
---|
基于RBF神经网络的自动泊车路径规划;吴冰等;《合肥工业大学学报(自然科学版)》;20120428;第459-462,540页 * |
Also Published As
Publication number | Publication date |
---|---|
CN107792062A (en) | 2018-03-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107792062B (en) | Automatic parking control system | |
CN107697065B (en) | Automatic parking control method for general parking scene | |
Li et al. | A potential field approach-based trajectory control for autonomous electric vehicles with in-wheel motors | |
EP3932761A1 (en) | Vehicle abnormal lane change control method, device and system | |
CN110235071B (en) | Automatic car guiding and trajectory tracking | |
CN107943071B (en) | Formation maintaining control method and system for unmanned vehicle | |
Ni et al. | Dynamics control of autonomous vehicle at driving limits and experiment on an autonomous formula racing car | |
Pérez et al. | Cascade architecture for lateral control in autonomous vehicles | |
CN104742959B (en) | The track of vehicle keeps control device | |
Guo et al. | Lane changing trajectory planning and tracking controller design for intelligent vehicle running on curved road | |
CN103121451B (en) | A kind of detour changes the tracking and controlling method of track | |
CN103057436B (en) | Yawing moment control method of individual driven electromobile based on multi-agent | |
US20220169247A1 (en) | Motor-vehicle trajectory planning and control to cause automated motor-vehicles to perform low-speed manoeuvres in automated driving | |
Subosits et al. | Impacts of model fidelity on trajectory optimization for autonomous vehicles in extreme maneuvers | |
CN107618504A (en) | It is a kind of applied to the crawl speed control method and device automatically parked | |
Subosits et al. | Autonomous vehicle control for emergency maneuvers: The effect of topography | |
CN107490968A (en) | The adaptive layered of autonomous driving vehicle passs rank path tracking control method | |
Lin et al. | Coordinated control architecture for motion management in ADAS systems | |
WO2019170346A1 (en) | Method for calculating a trajectory limitation, and method for regulating a drive dynamic | |
CN207274660U (en) | It is a kind of applied to the crawl speed control device automatically parked | |
CN109969165B (en) | Target-optimization-based torque distribution method considering tire lateral force contribution | |
Yang et al. | ESO-based lateral control for electrical vehicles with unmodeled tire dynamics on uneven road | |
CN115268464A (en) | Automatic driving automobile track tracking control method and device based on hierarchical constraint | |
Chen et al. | Ribbon model based path tracking method for autonomous ground vehicles | |
Guo et al. | Integrated control of variable torque distribution and electronic stability program based on slip angle phase |
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 |