CN108045373B - A kind of automatic Pilot longitudinal direction unified planning method and system - Google Patents
A kind of automatic Pilot longitudinal direction unified planning method and system Download PDFInfo
- Publication number
- CN108045373B CN108045373B CN201711145428.5A CN201711145428A CN108045373B CN 108045373 B CN108045373 B CN 108045373B CN 201711145428 A CN201711145428 A CN 201711145428A CN 108045373 B CN108045373 B CN 108045373B
- Authority
- CN
- China
- Prior art keywords
- acceleration
- vehicle
- indicate
- expectation
- candidate
- 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 title claims abstract description 26
- 230000001133 acceleration Effects 0.000 claims abstract description 138
- 230000007613 environmental effect Effects 0.000 claims abstract description 23
- 230000033001 locomotion Effects 0.000 claims abstract description 15
- 230000008569 process Effects 0.000 claims abstract description 7
- 238000011156 evaluation Methods 0.000 claims description 25
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 15
- 230000004888 barrier function Effects 0.000 description 14
- 238000005516 engineering process Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 235000018927 edible plant Nutrition 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012360 testing method Methods 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
- B60W30/18—Propelling the vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
- B60W40/107—Longitudinal acceleration
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a kind of automatic Pilot longitudinal direction unified planning method and system, the planing method is the following steps are included: 1) based on a unified environmental model for describing this vehicle ambient condition information, and acceleration it is expected in planning in real time in vehicle travel process；2) according to the longitudinal movement of the expectation acceleration and actual acceleration control vehicle.The present invention can be achieved longitudinally to plan based on environmental constraints, performance indicator and the local optimum of driving behavior.Compared with prior art, the present invention has many advantages, such as the optimality for having preferable applicability to different traffic scenes, guaranteeing final longitudinal movement.
Description
Technical field
The invention belongs to automobile technical fields, are related to automatic vehicle control system more particularly to automatic driving system
Longitudinal planning technology of system.
Background technique
Vehicular intelligent, the development for netting connectionization, motorized, Lightweight Technology are considered as alleviating traffic congestion, reducing and hand over
Interpreter's event reduces energy consumption and controls the effective way of environmental pollution, while being also the important directions of future automobile development.When
Before, autonomous driving vehicle technology has obtained the extensive concern of industry.Many domestic and international colleges and universities, enterprise and research institution are such as fire
Such as the bitter edible plant carry out related work.
In general, a complete automated driving system includes following items key technology: environment sensing, motion planning, control
System executes, man-machine drive, communicate and platform, information security etc. altogether.Wherein motion planning module is responsible for the horizontal and vertical of vehicle
Movement is planned that, to guarantee the driving safety, riding comfort and usage economy of autonomous driving vehicle, it is to drive automatically
Sail the indispensable link of system.
One perfect automatic Pilot longitudinal movement planning technology needs to comprehensively consider vehicle safety, ride comfort
Property, the driving efficiency and adaptability for different traffic scenes, therefore longitudinal movement planning technology is that automatic Pilot technology is ground
The important directions studied carefully.There are many researchs for vehicle longitudinal movement planning both at home and abroad at present, including full speed adaptive cruise is used
Method, velocity profile generation method, following-speed model method and traditional artificial potential field method etc., above scheme has their own advantages, but
Be still be difficult to meet it is above-mentioned required, objectively there is further improved urgent need.
Summary of the invention
It is longitudinal that it is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide a kind of automatic Pilots
Unified planning method and system.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of automatic Pilot longitudinal direction unified planning method, comprising the following steps:
1) environmental model based on unified description this vehicle ambient condition information, is planned in real time in vehicle travel process
It is expected that acceleration；
2) according to the longitudinal movement of the expectation acceleration and actual acceleration control vehicle.
The step 1) specifically:
11) candidate acceleration generates: in conjunction with the expectation acceleration value of last moment, according to longitudinal acceleration of the vehicle and adding
The constraint of acceleration generates a series of candidate acceleration to be screened；
12) vehicle location is predicted: based on vehicle kinematics model and vehicle always along the vacation of current course angle direction running
If the position that it is reached in the following different time domain for each candidate acceleration calculation；
13) expectation acceleration solves: one evaluation function of building, is commented according to vehicle location prediction result each candidate acceleration
Valence obtains desired acceleration in a manner of minimizing evaluation function.
I-th of candidate acceleration at(i) meet:
amin≤at(i)≤amax
Wherein,Indicate the expectation acceleration value of last moment, Δ axIndicate acceleration resolution ratio, MxdecAnd MxaccPoint
Not Biao Shi vehicle acceleration limit coefficient minimum value and maximum value, aminAnd amaxPermitted maximum longitudinal direction is respectively indicated to subtract
Speed and maximum longitudinal acceleration.
The expectation acceleration is obtained by following formula:
Wherein,Indicate expectation acceleration, at(i) i-th of candidate acceleration, J are indicatedxIndicate evaluation function；
The evaluation function JxExpression formula are as follows:
Wherein, Umix(Xp(i,j),Yp(i, j)) it indicates to be located at point [X by the vehicle that environmental model acquiresp(i,j),Yp(i,
J) the potential field value at], v (i, j) indicate that this vehicle predicts speed, and p, q indicate weight coefficient, vdesIndicate target vehicle speed.
The present invention also provides a kind of automatic Pilot longitudinal direction unified planning systems, comprising:
Planning algorithm module, for the environmental model based on unified description this vehicle ambient condition information, in vehicle row
The acceleration of planning expectation in real time during sailing；
Vehicle control module, for the longitudinal movement according to the expectation acceleration and actual acceleration control vehicle.
The planning algorithm module includes:
Candidate acceleration generation unit accelerates for combining the expectation acceleration value of last moment according to longitudinal direction of car
The constraint of degree and acceleration generates a series of candidate acceleration to be screened；
Vehicle location predicting unit, for being based on vehicle kinematics model and vehicle always along current course angle direction running
It is assumed that each candidate acceleration calculation generated for candidate acceleration generation unit its arrived in the following different time domain
The position reached；
It is expected that acceleration solves unit, for constructing an evaluation function, according to the prediction of vehicle location predicting unit output
As a result each candidate acceleration is evaluated, desired acceleration is obtained in a manner of minimizing evaluation function.
I-th of candidate acceleration at(i) meet:
amin≤at(i)≤amax
Wherein,Indicate the expectation acceleration value of last moment, Δ axIndicate acceleration resolution ratio, MxdecAnd MxaccPoint
Not Biao Shi vehicle acceleration limit coefficient minimum value and maximum value, aminAnd amaxPermitted maximum longitudinal direction is respectively indicated to subtract
Speed and maximum longitudinal acceleration.
The expectation acceleration is obtained by following formula:
Wherein,Indicate expectation acceleration, at(i) i-th of candidate acceleration, J are indicatedxIndicate evaluation function；
The evaluation function JxExpression formula are as follows:
Wherein, Umix(Xp(i,j),Yp(i, j)) indicate that the vehicle that acquires of environmental model is located at point [Xp(i,j),Yp(i,j)]
When potential field, v (i, j) indicate this vehicle predict speed, p, q indicate weight coefficient, vdesIndicate target vehicle speed.
Compared with prior art, the invention has the following advantages:
1) the present invention is based on longitudinal planning that a unified environmental model carries out automatic Pilot, all to different traffic scenes
With preferable applicability, and avoid frequent behavior pattern switching；
2) present invention when generating candidate acceleration with reference to relevant criterion to longitudinal acceleration of the vehicle and acceleration
Restrict can tentatively meet the requirement of riding comfort；
3) present invention constrains building vehicle kinematics model according to vehicle kinematics, and utilizes the vehicle kinematics model pair
This truck position is predicted, so that program results are executable；
4) present invention by building can quantitatively evaluating function, consider driving safety, riding comfort, driving efficiency, it is right
Each candidate acceleration is evaluated, and the smallest acceleration value of evaluation function value accelerates the expectation as subsequent time
Degree, to guarantee the optimality of final longitudinal movement；
5) vehicle control of the present invention exports vehicle drive force and brake force according to desired acceleration and Ben Che actual acceleration,
Influence of the speed to auto model transmission function is considered, to guarantee that this vehicle actual acceleration can preferably follow expectation to add
Speed.
Detailed description of the invention
Fig. 1 is the principle of the present invention schematic diagram；
Fig. 2 is barrier potential field Energy distribution schematic diagram of the present invention；
Fig. 3 is barrier potential field energy distributed in three dimensions schematic diagram of the present invention；
Fig. 4 is road potential field energy distributed in three dimensions schematic diagram of the present invention；
Fig. 5 is unified environment Model Potential field energy distribution schematic diagram of the present invention；
Fig. 6 is present invention vehicle kinematics model schematic；
Fig. 7 is vehicle longitudinal control block diagram of the present invention；
Fig. 8 is that vehicle of the present invention follows this Che Yuqian vehicle speed schematic diagram under scene；
Fig. 9 is that vehicle of the present invention follows this Che Yuqian following distance schematic diagram under scene；
Figure 10 is that this vehicle travels track schematic diagram under vehicle cut-ins scene of the present invention；
Figure 11 is this vehicle longitudinal acceleration schematic diagram under vehicle cut-ins scene of the present invention；
Figure 12 is this vehicle speed schematic diagram under vehicle cut-ins scene of the present invention.
Specific embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to
Following embodiments.
The present embodiment provides a kind of automatic Pilot longitudinal direction unified planning systems, mainly include planning algorithm module and vehicle control
Molding block.Planning algorithm module is used to consider vehicle based on the environmental model of unified description this vehicle ambient condition information
The requirement such as driving safety, riding comfort and running efficiency, the acceleration of planning expectation in real time in vehicle travel process.Vehicle
Control module is used for the longitudinal movement according to the expectation acceleration and actual acceleration control vehicle.In addition, the planning is calculated
Method module is used for basis, environmental model module according to environment sensing information premised on environmental model module, and according to traffic
The property of rule and traffic participant, constructs unified environmental model, carries out Unify legislation, characterization to this vehicle ambient condition information
Potential degree of hazard around this vehicle.By above three module, realize based on environmental constraints, performance indicator and the office of driving behavior
The optimal longitudinal planning in portion, planning principle frame are as shown in Figure 1.
1, environmental model
Environmental model in environmental model module is the premise and base of the unified automatic Pilot longitudinal direction planing method of the present invention
Plinth.In this embodiment, environmental model is characterized by way of a unified potential field model.Consider actual traffic rule
With the property of traffic participant, the environmental information around this vehicle is reflected in the potential field model, and different traffic participants is logical
It crosses different sub- potential field models to be described, final potential field model is the combination of all sub- potential field models.It is begged in the present embodiment
By two seed potential field models: the sub- potential field model of barrier and road way potential field model, it in other embodiments can be as needed
Using different sub- potential field models.
1) the sub- potential field model of barrier
There are many obstacle species in actual traffic scene, including moving obstacle and stationary obstruction.Establish barrier gesture
The purpose of field is the degree of danger for describing this vehicle and peripheral obstacle and colliding.According to driving for the kinematic constraint of vehicle and people
Habit is sailed, vehicle is different with the degree of danger transversely to collide along longitudinal direction, what general vehicle collided along longitudinal direction
Degree of danger is higher than the degree of danger that it transversely collides.In addition, with the increase of movement velocity, the potential field point of vehicle
It is furnished with the trend of Forward, therefore the Distribution of Potential Field of barrier can be described by Fig. 2.
To realize that above-mentioned barrier Distribution of Potential Field is drawn for any point (x, y) under global coordinate system by barrier i
The potential field value U risenobsi(x, y) meets:
Wherein, AobsIndicate the maximum potential field value of barrier i, v indicates this vehicle speed, (xobs(i),yobs(i)) represent barrier
The nearest point of upper this vehicle of distance of i, σx,σyThe convergence coefficient of barrier potential field in the x and y direction is represented, c represents barrier potential field
The adjustment factor of shape, k represent constant, and the coefficient can be, but not limited to the potential field three-dimensional point according to off-line simulation as the result is shown
Cloth effect picture is modified and is adjusted.The potential field distributed in three dimensions schematic diagram of barrier i is as shown in Figure 3.
2) road way potential field model
During automatic Pilot, this vehicle needs to consider lane line and road boundary constraint, avoids run-off-road and is driven out to
The risk in lane.In general, lane line can be divided into two classes according to traffic rules: allowing across lane line and do not allow across vehicle
Diatom.In the present embodiment, road boundary can be approximately not allow across lane line.
In the present embodiment, each lane line is synthesized to as a cubic polynomial, expression are as follows:
Y=ax3+b·x2+c (4)
Wherein, a, b and c be multinomial coefficient, the coefficient be practical lane detection after, under global coordinate system, adopt
The result that lane line is fitted with cubic polynomial.
For the Distribution of Potential Field situation for describing any one lane line, for any point (x, y) under global coordinate system, by
Potential field value U caused by lane line jline,j(x, y) meets:
Wherein, djIt is the shortest distance that point (x, y) arrives lane line j, b is this vehicle vehicle width, dcFor secure threshold, hjFor lane
Line potential field amplitude adjustment factor, the coefficient can be, but not limited to the potential field distributed in three dimensions effect picture according to off-line simulation as the result is shown
It modifies and adjusts.
As previously mentioned, lane line is divided into and not allowing to cross over and allow across two classes, for allowing across lane line, center
Amplitude should guarantee that this vehicle travels in lane under normal circumstances, and need to guarantee to meet lane-change demand.And for not allowing
Across lane line, center amplitude should be sufficiently large, to avoid the leap of this vehicle.In the present embodiment, above-mentioned requirements pass through coefficient
hjIt is adjusted.Road potential field distributed in three dimensions schematic diagram is as shown in Figure 4.
Final environmental model is the combination of all sub- potential field models in the present embodiment, according to above-mentioned analysis, final ring
Border model can carry out Unify legislation by following formula:
Wherein, Umix(x, y) is the final potential field of point (x, y), and m is barrier quantity, and n is to allow across lane line quantity,
Q is not allow across lane line quantity, hcAnd hncFor lane line center amplitude adjustment factor, the coefficient can be, but not limited to root
It modifies and adjusts according to the potential field distributed in three dimensions effect picture of off-line simulation as the result is shown.Final environmental model Distribution of Potential Field is shown
It is intended to as shown in Figure 5.
2, planning algorithm
The planning algorithm may be based on but not limited to above-mentioned potential field model, plan vehicle in real time in this vehicle driving process
Desired longitudinal acceleration, and consider the requirements such as safety, comfort and driving efficiency.The planning algorithm includes waiting
Acceleration is selected to generate, vehicle location prediction and expectation acceleration solve three parts.
1) candidate acceleration generates
Candidate acceleration generates submodule for generating a series of candidate acceleration value at(i), definition can be with table
It states are as follows:
Wherein,Indicate the expectation acceleration value of last moment, Δ axIndicate acceleration resolution ratio, MxdecAnd MxaccTable
Show vehicle acceleration limit coefficient minimum value and maximum value, the determination of specific value can refer to relevant criterion and accelerate to vehicle
The limitation of degree.
In addition, to meet the requirement of riding comfort and driving safety, the extreme value of candidate acceleration should be constrained on
Particular range, constraint condition can be stated are as follows:
amin≤at(i)≤amax (8)
Wherein, aminAnd amaxRespectively indicate permitted maximum longitudinal deceleration and maximum longitudinal acceleration.
2) vehicle location is predicted
Comprehensively consider model applicability and operation efficiency, the present embodiment is predicted using vehicle kinematics model as vehicle location
With model, model schematic is as shown in fig. 6, its equation can state are as follows:
Wherein, v represents this vehicle speed, and β represents Ben Che side slip angle, and ψ represents Ben Che yaw angle, and θ represents the course Ben Che
Angle.
It is assumed that this vehicle is along its current course angular direction, with acceleration at(i) it travels, then in a certain section of time-domain tp(j)
It is interior, the estimated position [X reached of Ben Chep(i,j),Yp(i, j)] it can state are as follows:
Wherein, [Xe(t),Ye(t)] the current position Ben Che, v are represented0(t) the current speed of Ben Che is represented, θ (t) is represented
The current course angle of this vehicle.In addition, time-domain tp(j) it is defined as follows, wherein NyIndicate the number of variable j:
tp(j)=0.1j (j=1,2,3 ..., Ny) (11)
3) expectation acceleration solves
It is expected that acceleration, which solves, to be predicted in conjunction with vehicle location as a result, by one evaluation function of building to the time of generation
Acceleration is selected to be evaluated, the minimum candidate acceleration of evaluation of estimate is by the expectation acceleration as subsequent time.Above-mentioned evaluation letter
Number synthesis considers the requirement of safety, comfort and efficiency of driving a vehicle.
(1) evaluation function
The effect of evaluation function is evaluated each candidate acceleration of generation, is with the acceleration that guarantee filters out
Safety, comfort and efficiency optimization of driving a vehicle.In this embodiment, evaluation function consists of three parts, including dangerous cost
Value, speed penalty value and acceleration penalty value, they characterize safety, driving efficiency and comfort performance indicator respectively.
A) dangerous cost value
Dangerous cost value is the summation of the corresponding potential field value of each vehicle predicted position.In general, dangerous cost value is got over
Small, vehicle collides or the degree of danger of run-off-road is also smaller.So that the candidate acceleration that dangerous cost value is smaller
It may preferentially be selected.
B) speed penalty value
Speed penalty value refers to the quadratic term of the deviation of this vehicle prediction speed and target vehicle speed.Target vehicle speed can be used but
It is not limited to the speed limit speed of present road；This vehicle prediction speed v (i, j) is defined as follows:
V (i, j)=v0(t)+at(i)tp(j) (11)
It is not difficult to know, speed penalty value is smaller, and driving efficiency is higher, and expenses are also smaller.So that this vehicle speed
Candidate acceleration close to target vehicle speed may be preferentially screened.
C) acceleration penalty value
Acceleration penalty value refers to the quadratic term of current candidate acceleration.Obviously, acceleration penalty value is smaller, takes and relaxes
Adaptive is better.Therefore the smaller candidate acceleration of absolute value may be preferentially screened.
According to above-mentioned analysis, evaluation function JxIt can state are as follows:
Wherein p, q are weight coefficient, vdesFor target vehicle speed, for a certain candidate acceleration at(i), when corresponding to different j
Between domain tp(j) different costs can be corresponded to；Above-mentioned parameter can be, but not limited to apply this method to be imitated according under different scenes
The result really obtained is adjusted and modifies.
(2) acceleration calculation
Based on candidate acceleration and evaluation function, so that it may filter out optimal acceleration conduct from all candidate acceleration
The candidate acceleration of subsequent time.The embodiment calculates expectation acceleration at *Mode be shown below:
3, vehicle control
Vehicle control is the expectation acceleration provided according to planning algorithm and Ben Che actual acceleration output vehicle drive force
And brake force, influence of the speed to auto model transmission function is considered in control algolithm, to guarantee this vehicle actual acceleration
Desired acceleration can be preferably followed, specific control block diagram is as shown in Figure 7.
Fig. 8 to 12 shows that carrying out hardware under different scenes based on the unified automatic Pilot longitudinal direction planing method of the present invention exists
Ring emulation testing and the simulation result obtained.Fig. 8, shown in 9, the respectively emulation knot of this vehicle speed and spacing in the case where following scene
Fruit.Dotted line indicates the speed of front truck in Fig. 8, and solid line indicates the speed of this vehicle.Figure 10 show row of this vehicle under scene of overtaking other vehicles
Track schematic diagram is sailed, dark rectangular indicates that obstacle vehicle, light rectangle indicate this vehicle in figure.Shown in Figure 11 and Figure 12, respectively originally
The change curve of vehicle longitudinal acceleration and speed, solid line indicates that the expectation acceleration of this vehicle, dotted line indicate the reality of this vehicle in Figure 11
Border acceleration.Change from this vehicle speed of Fig. 8,12 as can be seen that the speed variation in this vehicle driving process is more steady, not
There is apparent fluctuation and shake, while guaranteeing efficiency of driving a vehicle.From this vehicle longitudinal acceleration change curve of Figure 11 it can be found that
The longitudinal acceleration of this vehicle and its variation meet the requirement of relevant criterion always, and actual acceleration also can preferably follow expectation
Acceleration, thus the riding comfort of this vehicle is met the requirements.This vehicle shown from Fig. 9 then may be used with leading vehicle distance variation
Out, when this vehicle follows front truck when driving, this vehicle can preferably follow front truck always and keep appropriate spacing, the traveling of this vehicle
Safety is met.
The preferred embodiment of the present invention has been described in detail above.It should be appreciated that those skilled in the art without
It needs creative work according to the present invention can conceive and makes many modifications and variations.Therefore, all technologies in the art
Personnel are available by logical analysis, reasoning, or a limited experiment on the basis of existing technology under this invention's idea
Technical solution, all should be within the scope of protection determined by the claims.
Claims (6)
1. a kind of automatic Pilot longitudinal direction unified planning method, which comprises the following steps:
1) environmental model based on unified description this vehicle ambient condition information, the planning expectation in real time in vehicle travel process
Acceleration；
2) according to the longitudinal movement of the expectation acceleration and actual acceleration control vehicle；
The step 1) specifically:
11) candidate acceleration generates: in conjunction with the expectation acceleration value of last moment, according to longitudinal acceleration of the vehicle and plus accelerating
The constraint of degree generates a series of candidate acceleration to be screened；
12) vehicle location is predicted: based on vehicle kinematics model and vehicle always along current course angle direction running it is assumed that needle
The position that it is reached in the following different time domain to each candidate acceleration calculation；
13) expectation acceleration solves: one evaluation function of building, is evaluated according to vehicle location prediction result each candidate acceleration,
Desired acceleration is obtained in a manner of minimizing evaluation function.
2. unified planning method in automatic Pilot longitudinal direction according to claim 1, which is characterized in that i-th of candidate adds
Speed at(i) meet:
amin≤at(i)≤amax
Wherein,Indicate the expectation acceleration value of last moment, Δ axIndicate acceleration resolution ratio, MxdecAnd MxaccTable respectively
Show the minimum value and maximum value of vehicle acceleration limit coefficient, aminAnd amaxRespectively indicate permitted maximum longitudinal deceleration
With maximum longitudinal acceleration.
3. unified planning method in automatic Pilot longitudinal direction according to claim 1, which is characterized in that the expectation acceleration is logical
Cross following formula acquisition:
Wherein,Indicate expectation acceleration, at(i) i-th of candidate acceleration, J are indicatedxIndicate evaluation function；
The evaluation function JxExpression formula are as follows:
Wherein, Umix(Xp(i,j),Yp(i, j)) it indicates to be located at point [X by the vehicle that environmental model acquiresp(i,j),Yp(i, j)] at
Potential field value, v (i, j) indicate this vehicle predict speed, p, q indicate weight coefficient, vdesIndicate target vehicle speed.
4. a kind of automatic Pilot longitudinal direction unified planning system characterized by comprising
Planning algorithm module, for the environmental model based on unified description this vehicle ambient condition information, in vehicle driving mistake
The acceleration of planning expectation in real time in journey；
Vehicle control module, for the longitudinal movement according to the expectation acceleration and actual acceleration control vehicle；
The planning algorithm module includes:
Candidate acceleration generation unit, for combining the expectation acceleration value of last moment, according to longitudinal acceleration of the vehicle and
The constraint of acceleration generates a series of candidate acceleration to be screened；
Vehicle location predicting unit, for based on vehicle kinematics model and vehicle always along the vacation of current course angle direction running
If each candidate acceleration calculation generated for candidate acceleration generation unit its reached in the following different time domain
Position；
It is expected that acceleration solves unit, for constructing an evaluation function, according to the prediction result of vehicle location predicting unit output
Each candidate acceleration is evaluated, desired acceleration is obtained in a manner of minimizing evaluation function.
5. unified planning system in automatic Pilot longitudinal direction according to claim 4, which is characterized in that i-th of candidate adds
Speed at(i) meet:
amin≤at(i)≤amax
Wherein,Indicate the expectation acceleration value of last moment, Δ axIndicate acceleration resolution ratio, MxdecAnd MxaccTable respectively
Show the minimum value and maximum value of vehicle acceleration limit coefficient, aminAnd amaxRespectively indicate permitted maximum longitudinal deceleration
With maximum longitudinal acceleration.
6. unified planning system in automatic Pilot longitudinal direction according to claim 4, which is characterized in that the expectation acceleration is logical
Cross following formula acquisition:
Wherein,Indicate expectation acceleration, at(i) i-th of candidate acceleration, J are indicatedxIndicate evaluation function；
The evaluation function JxExpression formula are as follows:
Wherein, Umix(Xp(i,j),Yp(i, j)) it indicates to be located at point [X by the vehicle that environmental model acquiresp(i,j),Yp(i, j)] at
Potential field value, v (i, j) indicate this vehicle predict speed, p, q indicate weight coefficient, vdesIndicate target vehicle speed.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710811802 | 2017-09-11 | ||
| CN2017108118024 | 2017-09-11 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108045373A CN108045373A (en) | 2018-05-18 |
| CN108045373B true CN108045373B (en) | 2019-09-27 |
Family
ID=62120282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711145428.5A Active CN108045373B (en) | 2017-09-11 | 2017-11-17 | A kind of automatic Pilot longitudinal direction unified planning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108045373B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10908613B2 (en) * | 2018-10-15 | 2021-02-02 | Baidu Usa Llc | Optimal longitudinal trajectory generation under varied lateral acceleration constraints |
| CN109814574B (en) * | 2019-02-22 | 2022-07-19 | 百度在线网络技术（北京）有限公司 | Method and device for planning speed of junction of automatic driving lanes and storage medium |
| CN111445697B (en) * | 2020-03-22 | 2022-06-14 | 华南理工大学 | Expressway cooperative vehicle lane changing control method under intelligent network connection condition |
| CN112092813B (en) * | 2020-09-25 | 2022-04-01 | 阿波罗智能技术(北京)有限公司 | Vehicle control method, device, electronic device and storage medium |
| CN114516342B (en) * | 2020-11-19 | 2024-05-03 | 上海汽车集团股份有限公司 | Vehicle control method and device and vehicle |
| CN112622932B (en) * | 2020-12-23 | 2022-02-01 | 同济大学 | Automatic driving track-changing planning algorithm based on heuristic search of potential energy field |
| CN113492882B (en) * | 2021-07-14 | 2022-09-23 | 清华大学 | Method and device for realizing vehicle control, computer storage medium and terminal |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101372230A (en) * | 2007-08-24 | 2009-02-25 | 株式会社爱德克斯 | Vehicle drive control apparatus |
| CN103963785A (en) * | 2014-05-20 | 2014-08-06 | 武汉理工大学 | Dual-mode control method for automobile self-adaptive cruise system |
| CN104002808A (en) * | 2014-06-05 | 2014-08-27 | 大连理工大学 | Active anti-collision automatic brake control system of automobile and working method |
| CN106371439A (en) * | 2016-09-13 | 2017-02-01 | 同济大学 | Unified automatic driving transverse planning method and system |
| CN106560367A (en) * | 2015-09-30 | 2017-04-12 | 上海汽车集团股份有限公司 | Vehicle adaptive cruise controller, method and system |
-
2017
- 2017-11-17 CN CN201711145428.5A patent/CN108045373B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101372230A (en) * | 2007-08-24 | 2009-02-25 | 株式会社爱德克斯 | Vehicle drive control apparatus |
| CN103963785A (en) * | 2014-05-20 | 2014-08-06 | 武汉理工大学 | Dual-mode control method for automobile self-adaptive cruise system |
| CN104002808A (en) * | 2014-06-05 | 2014-08-27 | 大连理工大学 | Active anti-collision automatic brake control system of automobile and working method |
| CN106560367A (en) * | 2015-09-30 | 2017-04-12 | 上海汽车集团股份有限公司 | Vehicle adaptive cruise controller, method and system |
| CN106371439A (en) * | 2016-09-13 | 2017-02-01 | 同济大学 | Unified automatic driving transverse planning method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108045373A (en) | 2018-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108045373B (en) | A kind of automatic Pilot longitudinal direction unified planning method and system | |
| Ye et al. | Prediction-based eco-approach and departure at signalized intersections with speed forecasting on preceding vehicles | |
| CN109375632B (en) | Real-time trajectory planning method for automatic driving vehicle | |
| CN107792065B (en) | Method for planning road vehicle track | |
| CN110488802A (en) | A kind of automatic driving vehicle dynamic behaviour decision-making technique netted under connection environment | |
| CN111795832B (en) | Intelligent driving vehicle testing method, device and equipment | |
| CN107499262A (en) | ACC/AEB systems and vehicle based on machine learning | |
| CN107798861A (en) | A kind of vehicle cooperative formula formation running method and system | |
| CN109324620A (en) | The dynamic trajectory planing method for carrying out avoidance based on lane line parallel offset and overtaking other vehicles | |
| CN107544518A (en) | The ACC/AEB systems and vehicle driven based on personification | |
| CN109501799A (en) | A kind of dynamic path planning method under the conditions of car networking | |
| CN108698595A (en) | The control system of method and vehicle for controlling vehicle movement | |
| CN110304074A (en) | A kind of hybrid type driving method based on stratification state machine | |
| CN108944943A (en) | A kind of bend following-speed model based on risk shifting balance theory | |
| CN109823339A (en) | Vehicle traffic light intersection passing control method and control system | |
| Zhang et al. | Data-driven based cruise control of connected and automated vehicles under cyber-physical system framework | |
| CN104608765A (en) | Intelligent overtaking method and system for automobile | |
| CN106371439A (en) | Unified automatic driving transverse planning method and system | |
| Zhao et al. | A traffic light signal control system with truck priority | |
| Zhang et al. | A cruise control method for connected vehicle systems considering side vehicles merging behavior | |
| CN106997675A (en) | Target vehicle speed Forecasting Methodology based on Dynamic Programming | |
| Choe et al. | Deep Q learning with LSTM for traffic light control | |
| CN108845509A (en) | A kind of adaptive learning algorithms algorithm development system and method | |
| Yu et al. | Modeling and simulation of overtaking behavior involving environment | |
| CN115257819A (en) | Decision-making method for safe driving of large-scale commercial vehicle in urban low-speed environment |
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 |