CN109508003A - A kind of unmanned road machine group of planes dynamic preventing collision method - Google Patents
A kind of unmanned road machine group of planes dynamic preventing collision method Download PDFInfo
- Publication number
- CN109508003A CN109508003A CN201811478547.7A CN201811478547A CN109508003A CN 109508003 A CN109508003 A CN 109508003A CN 201811478547 A CN201811478547 A CN 201811478547A CN 109508003 A CN109508003 A CN 109508003A
- Authority
- CN
- China
- Prior art keywords
- barrier
- grid
- barrier block
- block
- moving obstacle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000004888 barrier function Effects 0.000 claims abstract description 120
- 238000010276 construction Methods 0.000 claims abstract description 21
- 230000001133 acceleration Effects 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 230000006735 deficit Effects 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 230000002093 peripheral effect Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 241000196324 Embryophyta Species 0.000 description 4
- 230000006399 behavior Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 239000000523 sample Substances 0.000 description 3
- FNMKZDDKPDBYJM-UHFFFAOYSA-N 3-(1,3-benzodioxol-5-yl)-7-(3-methylbut-2-enoxy)chromen-4-one Chemical compound C1=C2OCOC2=CC(C2=COC=3C(C2=O)=CC=C(C=3)OCC=C(C)C)=C1 FNMKZDDKPDBYJM-UHFFFAOYSA-N 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004387 environmental modeling Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0287—Control of position or course in two dimensions specially adapted to land vehicles involving a plurality of land vehicles, e.g. fleet or convoy travelling
- G05D1/0291—Fleet control
- G05D1/0293—Convoy travelling
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a kind of unmanned road machine group of planes dynamic preventing collision methods, obtain the ambient data of each body in construction area, moving obstacle is subjected to grid division, and it matches to obtain the movement state information of barrier block by dynamic grid, judge the collision relationship of the collision relationship and each body and edges of regions between each body and moving obstacle；According to above-mentioned collision relationship, plan that the motion path of each body, the motion path of body include the direction of motion, speed；According to the motion path of the body of planning, controls corresponding body and moved.
Description
Technical field
The present invention relates to a kind of unmanned road machine group of planes dynamic preventing collision methods, belong to technical field of engineering machinery.
Background technique
Moving obstacle detection, prediction and avoidance of the unmanned road roller under tunnel complex environment are always that nobody drives
Sail the key points and difficulties of road roller research and the emphasis of engineering machinery group operation research.
Summary of the invention
Purpose: in order to overcome the deficiencies in the prior art, the present invention provides an a kind of unmanned road machine group of planes
Dynamic preventing collision method.
Technical solution: in order to solve the above technical problems, the technical solution adopted by the present invention are as follows:
A kind of group of planes dynamic preventing collision method, comprising:
1) ambient data of each body in construction area is obtained；
2) ambient data based on each body extracts the barrier feature in construction area, by one
A barrier grid is clustered into barrier block, passes through the position where the barrier block disturbance in judgement object of formation；
3) after the completion of construction area barrier block cluster, barrier block is tracked, creates a moving obstacle column
Table stores the obtained barrier block message of cluster, and the tracking result of real-time update barrier block；
4) it is associated with the barrier block stored in the barrier block message and moving obstacle list that current time clusters
Information；And it matches to obtain the movement state information of barrier block by dynamic grid；
5) ambient data to each body and barrier block message merge, and obtain each body in region
Relative position, and the relative position with peripheral motor impairment object；
6) judge, screen collision relationship between each body and moving obstacle and each body and edges of regions
Collision relationship；
7) according to above-mentioned collision relationship, plan that the motion path of each body, the motion path of the body include movement
Direction, speed；
8) it according to the motion path of the body of planning, controls corresponding body and is moved.
Further, the group of planes dynamic preventing collision method, it is characterised in that: use a kind of region growing clustering algorithm pair
Barrier in grid map occupies grid and is clustered, and creates an open list to store all grid occupied by barrier
Lattice are investigated from randomly selecting a grid in open list and being put into closed list, then are carried out to its adjacent cells
Investigate, and so on, until and list be all sky until, the barrier in cluster areas occupies grid and is just clustered into one by one
Barrier block.
Further, the group of planes dynamic preventing collision method, it is characterised in that: grid is occupied to the barrier of construction area
It is being clustered as a result, feature of the minimum rectangle parameter for using one can cover barrier block as the barrier block, its ginseng
Number includes: long side length, and short side is long, the occupancy k of center position O (x, y) and barrier block to this rectangle.
Further, the group of planes dynamic preventing collision method, it is characterised in that: be stored in the moving obstacle list
Each barrier block, include following information: number, it is newest it is primary cluster obtain time, plant oneself, velocity magnitude and
Direction, acceleration magnitude and direction, velocity covariance, acceleration covariance and there are confidence level and movement confidence level.
Further, the group of planes dynamic preventing collision method, it is characterised in that: the obstacle that association current time clusters
The barrier block message stored in object block message and moving obstacle list, is associated it by maximum correlation value method.
Further, the group of planes dynamic preventing collision method, it is characterised in that: believed by the moving obstacle of construction area
Breath, is drawn out a model according to the appearance profile of barrier, is then drawn out barrier lattice in the form of basic unit lattice again
Grid figure, forming region block side length a, b, center O (x, y) and speed v size and Orientation grid map.
Further, the group of planes dynamic preventing collision method, it is characterised in that: using Confidence distance theory to each body
Ambient data and barrier block message merged.
The group of planes dynamic preventing collision method, it is characterised in that: (x, y, z, t) is carried out according to space-time dynamic model with unit
Case form infinitely expands and extends；If space-time dynamic coordinate system point p (x, y, z, t) (0≤x≤Xm, 0≤y≤Ym, 0
≤ z≤Zm, 0≤t), T (P)=1 indicates that, in t moment, grid (x, y, z, t) can be occupied by other vehicles or barrier；T
(P)=0 indicate that grid (x, y, z, t) is not occupied by other vehicles or barrier in t moment.
The utility model has the advantages that unmanned road machine group of planes dynamic preventing collision method provided by the invention, for unmanned pressure
Road machine carries out moving obstacle detection, prediction and avoidance problem encountered in tunnel complex environment and the totality of system is set
Meter requires, and on the basis of the local map of foundation, the present invention devises a kind of unmanned road machine group of planes dynamic evacuation
Method.
Detailed description of the invention
Fig. 1 is sports equipment in embodiment in grating position schematic diagram.
Fig. 2 is distribution of obstacles cloud atlas in embodiment.
Fig. 3 is that barrier block parameterizes schematic diagram in embodiment.
Fig. 4 is moving obstacle grid profile diagram in embodiment.
Fig. 5 is space-time detection of obstacles figure in embodiment.
Fig. 6 is space-time barrier intersection-type collision figure in embodiment.
Specific embodiment
The invention will be further described with reference to the accompanying drawings and examples.Following embodiment is only used for clearly saying
Bright technical solution of the present invention, and not intended to limit the protection scope of the present invention.
Embodiment 1
The headstock of unmanned road roller is oriented Y-axis positive direction, creates one 512 by X-axis positive direction of left direction
The sustainable extension map of × 512 grid, the size for setting each grid are unmanned road roller in the grating map
Position coordinates are that (100,100) are as shown in Figure 1.
Moving obstacle in complicated construction environment is mainly other Construction traffics and construction personnel, be all it is relatively high,
Biggish barrier carries out rasterizing using maximin method to the detection of such barrier, all three-dimensional points is projected
Onto grating map, the difference of the maximum height value and minimum height values in each grid is recorded, as long as this difference is greater than setting
Threshold value, be just arranged the grid be occupied state, be labeled as T (X)=1, be otherwise unoccupied state, be labeled as T (X)=0.It adopts
Grid map is occupied with the barrier that laser data rasterizing of the maximin method to a construction area obtains, as shown in Fig. 2,
Wherein white point is occupied state, and black color dots are non-occupied states.
Barrier feature in construction area is extracted, it is necessary first to obstacle will be clustered by barrier grid one by one
Object block passes through the position where the barrier block disturbance in judgement object of formation.Using a kind of region growing clustering algorithm to grid map
In barrier occupy grid clustered, first create an open list come store it is all by barrier occupy grids,
Then it is investigated from randomly selecting a grid in open list and be put into closed list, then again to its adjacent cells
Investigated, and so on, until and list be all sky until, the barrier in cluster areas occupies grid and is just clustered into one
Each and every one barrier block.To the barrier of construction area occupy that grid clustered as a result, barrier block can be covered with one
Feature of the minimum rectangle parameter as the barrier block, as shown in figure 3, its parameter includes: long side length L, the long R of short side, center
Position O (x, y) and barrier block are put to the occupancy k of this rectangle.
It after the completion of construction area barrier block cluster, also needs to track barrier block, creates a movement barrier first
Hinder object list to store the obtained barrier block message of cluster, and the tracking result of real-time update these barrier blocks.It is stored in
Each of this moving obstacle list barrier block, include following information: number, it is newest it is primary cluster obtain when
Between, plant oneself, velocity magnitude and direction, acceleration magnitude and direction, velocity covariance, acceleration covariance and existing are set
Reliability and movement confidence level.When tracking to barrier block, need to be associated with the barrier block message that current time clusters
Barrier block message with storing in moving obstacle list, is associated it by maximum correlation value method.For construction area
Each of moving obstacle list barrier block OB in domainiEach the barrier block OM clustered with current timejAll
There are a relating value fij.The fijSize depend on barrier block OBiWith barrier block OMjThe parameter of extraction, barrier block OBi
With barrier block OMjCentral point O (x, y) cannot be used directly to compare, therefore needed to barrier since the cluster time is different
Block OBiCenter Oi(xi, yi) be modified, formula is as follows:
tij=tj-ti
T in above formulaiAnd tjIt is OB respectivelyiTime and current time when newest primary cluster obtains,WithIt is OBi?
The most current speed and acceleration stored in moving obstacle list, O 'i(x′i, y 'i) it is to OBiCenter Oi(xi, yi) into
The center obtained after row amendment, can obtain f by following formulaij:
Wherein, a, b and c are weights, by testing available proper empirical value.One thresholding relating value is set
f0A following decision matrix can be obtained afterwards.
Using the more each limit f of the progressive mode of matrixmnWhether specified thresholding relating value f is less than0.If being not less than thresholding
Value then thinks OBmAnd OMnSuccessful association, then by OBmAnd OMnAll relating values all delete to obtain new matrix, it is as follows
It is shown:
Maximum relating value is found from obtained newest decision matrix, and so on, until the maximum correlation value found
Less than threshold value f0Or until decision matrix is emptying.Final result is subjected to classification processing: being stored in moving obstacle list
In there is no the barrier block currently clustered matching barrier block, confidence level subtracts 1, and other values are constant；Current cluster
The obtained barrier block and matching barrier block message being still not stored in moving obstacle list, is added
Add in moving obstacle list, and initial value 0 all set into velocity magnitude direction and acceleration magnitude direction, velocity covariance and plus
Velocity covariance all sets initial value 10, and there are confidence levels to set initial value 10, and movement confidence level sets initial value 0；It is stored in moving obstacle column
In table and the barrier block message that has the barrier block for currently clustering and obtaining matching, there are confidence levels to add 1, updates it
Position, and its speed, acceleration and velocity covariance and acceleration covariance are updated according to Kalman filtering algorithm.Make
With Kalman filter, a discrete control process system need to be introduced: control system processing formula is as follows:
X (k)=AX (k-1)+BU (k)+W (k)
Z (k)=HX (k)+C (k)+V (k)
Variable in formula C (k)=s (k-1), W (k) and V (k) respectively indicate interference of the noise to detection, and covariance is respectively Q and R, lead to
The state for crossing above formula detection can calculate the state appeared in, and prediction equation is as follows:
X (k | k-1)=AX (k-1 | k-1)+BU (k)
X (k | k-1), which is updated, by detection data obtains system covariance P (k | k-1)
P (k | k-1)=AP (k-1 | k-1)+Q
Maximum likelihood estimate X (k | k) can be obtained by this
X (k | k)=X (k | k-1)+Kg (k) (Z (k)-HX (k | k-1))
It is kalman gain, satisfiable formula by Kg (k) known to above formula
Kg (k)=P (k | k-1) H '/(HP (k | k-1) H '+R)
System covariance P (k | k) is obtained according to current state X (k | k)
P (k | k)=(1-Kg (k) H) P (k | k-1)
The motion information of barrier block is obtained by calculation, it is contemplated that the detection error of sensor, when sensor detection is small
Determine that barrier is stationary obstruction in 0.1m/s, the value of the confidence adds 1 if updating numerical value and being greater than the value, otherwise subtracts 1.Pass through inspection
A model can be drawn out according to the appearance profile of barrier by surveying construction area moving obstacle information, then again with basic unit
The form of lattice draws out barrier grid figure, size and the side of forming region block side length a, b, center O (x, y) and speed v
To grid map, as shown in figure 4, moving obstacle grid profile diagram.
When carrying out detection of obstacles, speed and orientation to barrier are drawn by calibrated bolck can obtain barrier wheel
Exterior feature figure.By test record detection of obstacles data, there are errors for the barrier data recorded due to detection, need in grid
Heart position synchronizes alignment, the center O (x, y) of grid is translated S distance to walking opposite direction, the distance of translation must expire
Sufficient following formula:
S=λ (tv+tl)v
Wherein tvAnd tlIt is handled respectively by sensing data and master system is handled, λ is parameter.It will be actually detected
Model is synchronized with offset profile grid, then matches the barrier block message that two sensors detect, there is region overlapping
Barrier block message think successful match, the unit of the barrier block not detected in the detection process successful match therewith
Grid, it is without any processing；The barrier block for not having the sensor of element grid successful match therewith to detect, does not do any yet
Processing, still using the testing result of sensor as final result.In the characterisitic parameter of the same object of multiple sensor measurements
When, it need to consider the statistical property of each sensor output data, judge it effectively using the relationship between each sensor output data
Property.It is merged using two sensing datas of the Confidence distance theory to successful match, it is assumed that x1And x2It is No. 1 and No. 2 respectively
The motion state of laser data output, all Gaussian distributed, it is x respectively that certain, which measures the data that they are obtained,1And x2Then it is general
Rate density function is shown in formula:
xiAnd xjConfidence distance dijMeet:
It is hereby achieved that second order Confidence distance:
Assuming that Confidence distance Critical Matrices are as follows:
Then by the relational matrix R of the available second order of formula2:
Finally satisfaction is exported and supports that number of probes is that 2 sensing data is merged according to formula, is finally obtained
The motion state X of barrier block, wherein l is to meet output to support that number of probes is 2 number of probes.
The information of sensor is after data fusion, since laser sensor data processing time-consuming is bigger, moving obstacle
The position that grill unit lattice are occupied in list can during this period of time change, it is therefore desirable to plant oneself and repair to these
Just.The all of barrier block that those movement confidence levels are greater than the set value in the moving obstacle list that will test plant oneself
Towards the translation of its directional velocity away from S ', the size of S ' meets:
S '=λ ' tvv′
V ' is fused barrier block movement velocity in above formula.These are by fusion, revised barrier block message
It all updates storage in moving obstacle list, obstacle information can accurately be detected.
After obtaining local cartographic information and barrier avoidance data, needs to control the collaboration of cluster road roller path planning and make
Industry.It is common environmental modeling method in unmanned research field that unmanned road roller group of planes barrier, which occupies grid map,
It can express the mode of barrier occupied information three-dimensional instantaneous in environment.The unmanned of all cluster operations sets
It is standby to be used as a kind of loose impediment, using solid space point cloud space-time dynamic grid map as the main tool of expression environment, then
Behaviour decision making and path planning are carried out in spatial point cloud dynamic cascode trrellis diagram.But traditional grid map can only express in environment
Static-obstacle thing, and in fact, there is a large amount of moving obstacle, such expression in the running environment of automatic driving vehicle
Mode is just no longer applicable in.
A group of planes and moving obstacle are moved as time change position can change, but has ignored unmanned pressure road
Time-space relationship between machine and these moving obstacles, it only estimates the occupancy shape of each grid after same a period of time
State.In practice for different grids, unmanned road roller needs to consider after the different time their occupied state, these
Positional relationship between time and automatic driving vehicle and each grid is related.In order to solve this problem, point cloud space-time is proposed
Dynamic cascode trrellis diagram is being analyzed the movement relation between unmanned road roller and barrier in space-time coordinates, to not
Its space hold state after same raster symbol-base different time sections.This grid map can will be interested in unmanned road roller
Event occupied state express, the behaviour decision making for being unmanned road roller in dynamic environment and path planning provide
Foundation.Intensified learning is to establish space-time to the environment of fixed size around unmanned road roller at 0 moment with group of planes construction starting point
Coordinate system, (x, y, z, t) as shown in Figure 5 infinitely expanded and extended with unit case form according to space-time dynamic model.If
The point p (x, y, z, t) (0≤x≤Xm, 0≤y≤Ym, 0≤z≤Zm, 0≤t) of space-time dynamic coordinate system, T (P)=1
Indicate that, in t moment, grid (x, y, z, t) can be occupied by other vehicles or barrier；T (P)=0 is indicated in t moment, grid
(x, y, z, t) is not occupied by other vehicles or barrier.
Group of planes moving obstacle occupy grid map as unmanned road roller behaviour decision making and path planning it is main according to
According to the barrier occupied information at current time or some particular moment in environment being only depicted, when constructing by supervised learning
When empty solid grid map, this built-up pattern is no longer formed using particular moment plane, but is similar to the conical surface with one
Time face extends this three-dimensional modelling body, integral face rather than cuboid or square, forms the time face for being similar to the conical surface
Cut this space body, the vertex of this conical surface is unmanned road roller current time the location of in space-time coordinates
(x, y, z, 0), the shape of this conical surface are related with unmanned road roller current motion state.Any point p on curved surface (x, y, z,
T) all meet formula: t=t(x, y, z, s)
Wherein, t(x, y, z, s)Be unmanned road roller at current running state S from current location (x0, y0, z0) traveling
To the time needed for position (x, y, z), can be obtained by way of obtaining offline.In general, working as unmanned road roller
Travel speed is small and the conical surface that is formed when distant apart from barrier is more sharp.The mark value of all the points on this conical surface is thrown
On shadow to corresponding grid, a space-time barrier grid map is just generated.
On spatial point cloud space-time barrier grid map exist prediction the point of impingement, indicate when unmanned road roller towards that
Prediction point of impingement traveling will collide with moving obstacle, in this way, space-time barrier grid map is just unmanned pressure road
Machine provides the information of all safety and danger zone.Space-time barrier grid map is that three-dimensional is described with three-dimensional grid face
Event, it by those unconcerned of unmanned road roller (those i.e. in space-time coordinates point) not on the conical surface events
It filters out, only expresses the occupied information in these event cloud spaces on the conical surface that unmanned road roller is concerned about.It can thus incite somebody to action
Moving object information in environment is expressed in a manner of a kind of static state, is mentioned for the behaviour decision making and path planning of rear phase process
For complete environment describing mode.
It is predicting the collision relationship between unmanned road roller and other moving vehicles and is generating space-time spatial obstacle object
Before grid map, need to obtain t offline(x, y, z, s).Assuming that unmanned road roller is to drive at a constant speed so t(x, y, z, s)With position
(x0, y0, z0) and the distance between position (x, y, z) direct proportionality, coordinate with nobody to drive centimetre for standard block lattice
The inversely proportional relationship of road roller current driving speed is sailed, i.e.,
Since speed is in x, elevation information z=0 is carried out measuring and calculation, calculates touching under friction speed by y-coordinate operation
Hit time such as table.
By testing the time look-up table collected under different coordinates, it can be deduced that these times are not to fully meet
Formula is stated, especially four row data below.This is because being not located at the target position immediately ahead of unmanned road roller, nobody is driven
Sailing road roller is not straight-line travelling to target position, need to be to above-mentioned formula t(x, y, z, s)Space correction processing is carried out, due to walking
It is plane walking, elevation information is set to origin and carries out position calculating:
Numerical solution is substituted into obtain
Plane projection equation of motion is calculated by simulated experiment:
Whether can collide within following a period of time between unmanned road roller and moving obstacle, utilize movement
Space-time analysis method judges in the motion profile of space-time coordinates, between the driving trace and space curved surface of moving obstacle whether
There are intersection points, if it does not, indicating will not between unmanned road roller and moving obstacle or other automatic driving vehicles
Track interaction occurs；If there are intersection point P (x, y, z, t) for projection, then it represents that unmanned road roller is towards projection (x, y) position row
It sails, can collide in t moment and the position.Therefore between unmanned road roller and moving obstacle and other moving vehicles
Prediction collision problem be converted into the solution intersection point problem between three-dimensional system of coordinate interior lines and face.
Unmanned road roller on bend when driving, if carrying out prediction of collision to it still according to straight line model, it
Between may collide, and this Driving Scene if it is considered that bend is constructed, unmanned road roller is not mutually
Same rolling in lane travels, they are possible virtually free from colliding.Therefore, it detects locating for unmanned road roller not
Tunnel environment path planning and evacuation are realized by speed and efficiency comprehensively control with position.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
The above is only a preferred embodiment of the present invention, it should be pointed out that: for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (8)
1. a kind of group of planes dynamic preventing collision method, comprising:
1) ambient data of each body in construction area is obtained；
2) ambient data based on each body extracts the barrier feature in construction area, will hinder one by one
Hinder object grid to be clustered into barrier block, passes through the position where the barrier block disturbance in judgement object of formation；
3) after the completion of construction area barrier block cluster, barrier block is tracked, a moving obstacle list is created
The barrier block message that storage cluster obtains, and the tracking result of real-time update barrier block；
4) it is associated with the barrier block message stored in the barrier block message and moving obstacle list that current time clusters；
And it matches to obtain the movement state information of barrier block by dynamic grid；
5) ambient data to each body and barrier block message merge, and obtain phase of each body in region
To position, and the relative position with peripheral motor impairment object；
6) judge, screen touching for collision relationship between each body and moving obstacle and each body and edges of regions
Hit relationship；
7) according to above-mentioned collision relationship, plan the motion path of each body, the motion path of the body include the direction of motion,
Speed；
8) it according to the motion path of the body of planning, controls corresponding body and is moved.
2. group of planes dynamic preventing collision method according to claim 1, it is characterised in that: use a kind of region growing clustering algorithm
Grid is occupied to the barrier in grid map to cluster, and creates an open list to store all grid occupied by barrier
Lattice are investigated from randomly selecting a grid in open list and being put into closed list, then are carried out to its adjacent cells
Investigate, and so on, until and list be all sky until, the barrier in cluster areas occupies grid and is just clustered into one by one
Barrier block.
3. group of planes dynamic preventing collision method according to claim 2, it is characterised in that: occupy grid to the barrier of construction area
It is that lattice are clustered as a result, the minimum rectangle parameter for using one can cover barrier block as the barrier block feature, it
Parameter includes: long side length, and short side is long, the occupancy k of center position O (x, y) and barrier block to this rectangle.
4. group of planes dynamic preventing collision method according to claim 1, it is characterised in that: be stored in the moving obstacle list
Each of barrier block, include following information: number, it is newest it is primary cluster obtain time, plant oneself, velocity magnitude
With direction, acceleration magnitude and direction, velocity covariance, acceleration covariance and there are confidence level and movement confidence level.
5. group of planes dynamic preventing collision method according to claim 1, it is characterised in that: the barrier that association current time clusters
Hinder the barrier block message stored in object block message and moving obstacle list, it is associated by maximum correlation value method.
6. group of planes dynamic preventing collision method according to claim 1, it is characterised in that: pass through the moving obstacle of construction area
Information draws out a model according to the appearance profile of barrier, then draws out barrier in the form of basic unit lattice again
Grid figure, forming region block side length a, b, center O (x, y) and speed v size and Orientation grid map.
7. group of planes dynamic preventing collision method according to claim 1, it is characterised in that: using Confidence distance theory to each machine
The ambient data and barrier block message of body are merged.
8. group of planes dynamic preventing collision method according to claim 1, it is characterised in that: (x, y, z, t) is according to space-time dynamic mould
Type progress is infinitely expanded and is extended with unit case form；If point p(x, the y of space-time dynamic coordinate system, z, t), T(P)=1 indicate
In t moment, grid (x, y, z, t) can be occupied by other vehicles or barrier；T (P)=0 indicates in t moment, grid (x, y,
Z, t) do not occupied by other vehicles or barrier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811478547.7A CN109508003A (en) | 2018-12-05 | 2018-12-05 | A kind of unmanned road machine group of planes dynamic preventing collision method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811478547.7A CN109508003A (en) | 2018-12-05 | 2018-12-05 | A kind of unmanned road machine group of planes dynamic preventing collision method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109508003A true CN109508003A (en) | 2019-03-22 |
Family
ID=65751616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811478547.7A Pending CN109508003A (en) | 2018-12-05 | 2018-12-05 | A kind of unmanned road machine group of planes dynamic preventing collision method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109508003A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111830998A (en) * | 2020-06-05 | 2020-10-27 | 科沃斯机器人股份有限公司 | Operation method, virtual wall adding method, equipment and storage medium |
| CN112012269A (en) * | 2019-05-29 | 2020-12-01 | 纳博特斯克有限公司 | Operation assistance system and method, maintenance assistance method, and construction machine |
| CN112731944A (en) * | 2021-01-15 | 2021-04-30 | 同济大学 | Autonomous obstacle avoidance method for unmanned road roller |
| CN113884026A (en) * | 2021-09-30 | 2022-01-04 | 天津大学 | Unmanned rolling model prediction contour control method in dynamic environment |
| US11348464B1 (en) | 2022-01-11 | 2022-05-31 | Ecotron LLC | System and method for dispatch control for autonomous driving engineering |
| CN114779794A (en) * | 2022-06-21 | 2022-07-22 | 东风悦享科技有限公司 | Street obstacle identification method based on unmanned patrol vehicle system in typhoon scene |
| CN117148848A (en) * | 2023-10-27 | 2023-12-01 | 上海伯镭智能科技有限公司 | Intelligent obstacle avoidance method and system for unmanned vehicle |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105717923A (en) * | 2016-01-16 | 2016-06-29 | 上海大学 | Unmanned surface vessel ocean dynamic obstacle avoiding control algorithm based on ellipse clustering-collision awl deduction |
| CN105717942A (en) * | 2016-01-31 | 2016-06-29 | 中国人民解放军海军航空工程学院 | Unmanned plane space obstacle avoidance method and correlative path online planning method |
| CN106291736A (en) * | 2016-08-16 | 2017-01-04 | 张家港长安大学汽车工程研究院 | Pilotless automobile track dynamic disorder object detecting method |
| WO2018176593A1 (en) * | 2017-03-31 | 2018-10-04 | 深圳市靖洲科技有限公司 | Local obstacle avoidance path planning method for unmanned bicycle |
-
2018
- 2018-12-05 CN CN201811478547.7A patent/CN109508003A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105717923A (en) * | 2016-01-16 | 2016-06-29 | 上海大学 | Unmanned surface vessel ocean dynamic obstacle avoiding control algorithm based on ellipse clustering-collision awl deduction |
| CN105717942A (en) * | 2016-01-31 | 2016-06-29 | 中国人民解放军海军航空工程学院 | Unmanned plane space obstacle avoidance method and correlative path online planning method |
| CN106291736A (en) * | 2016-08-16 | 2017-01-04 | 张家港长安大学汽车工程研究院 | Pilotless automobile track dynamic disorder object detecting method |
| WO2018176593A1 (en) * | 2017-03-31 | 2018-10-04 | 深圳市靖洲科技有限公司 | Local obstacle avoidance path planning method for unmanned bicycle |
Non-Patent Citations (1)
| Title |
|---|
| 辛煜: "无人驾驶车辆运动障碍物检测、预测和避撞方法研究", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112012269A (en) * | 2019-05-29 | 2020-12-01 | 纳博特斯克有限公司 | Operation assistance system and method, maintenance assistance method, and construction machine |
| CN111830998A (en) * | 2020-06-05 | 2020-10-27 | 科沃斯机器人股份有限公司 | Operation method, virtual wall adding method, equipment and storage medium |
| CN112731944A (en) * | 2021-01-15 | 2021-04-30 | 同济大学 | Autonomous obstacle avoidance method for unmanned road roller |
| CN113884026A (en) * | 2021-09-30 | 2022-01-04 | 天津大学 | Unmanned rolling model prediction contour control method in dynamic environment |
| US11348464B1 (en) | 2022-01-11 | 2022-05-31 | Ecotron LLC | System and method for dispatch control for autonomous driving engineering |
| CN114779794A (en) * | 2022-06-21 | 2022-07-22 | 东风悦享科技有限公司 | Street obstacle identification method based on unmanned patrol vehicle system in typhoon scene |
| CN114779794B (en) * | 2022-06-21 | 2022-10-11 | 东风悦享科技有限公司 | Street obstacle identification method based on unmanned patrol vehicle system in typhoon scene |
| CN117148848A (en) * | 2023-10-27 | 2023-12-01 | 上海伯镭智能科技有限公司 | Intelligent obstacle avoidance method and system for unmanned vehicle |
| CN117148848B (en) * | 2023-10-27 | 2024-01-26 | 上海伯镭智能科技有限公司 | Intelligent obstacle avoidance method and system for unmanned vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109508003A (en) | A kind of unmanned road machine group of planes dynamic preventing collision method | |
| US11726477B2 (en) | Methods and systems for trajectory forecasting with recurrent neural networks using inertial behavioral rollout | |
| CN111670468B (en) | Moving body behavior prediction device and moving body behavior prediction method | |
| CN110832279B (en) | Alignment of data captured by autonomous vehicles to generate high definition maps | |
| CN108268483A (en) | The method for the grid map that generation controls for unmanned vehicle navigation | |
| WO2012086029A1 (en) | Autonomous movement system | |
| CN108268518A (en) | The device for the grid map that generation controls for unmanned vehicle navigation | |
| Artuñedo et al. | A decision-making architecture for automated driving without detailed prior maps | |
| CN112578673B (en) | Perception decision and tracking control method for multi-sensor fusion of formula-free racing car | |
| Revilloud et al. | A new multi-agent approach for lane detection and tracking | |
| CN114442621A (en) | Autonomous exploration and mapping system based on quadruped robot | |
| CN110111359A (en) | Multiple target method for tracing object, the equipment and computer program for executing this method | |
| CN111721279A (en) | Tail end path navigation method suitable for power transmission inspection work | |
| CN105204511B (en) | A kind of decision-making technique of object autonomous | |
| CN114003035A (en) | Method, device, equipment and medium for autonomous navigation of robot | |
| CN114237256B (en) | Three-dimensional path planning and navigation method suitable for under-actuated robot | |
| Farag | Multiple road-objects detection and tracking for autonomous driving | |
| CN117109620A (en) | Automatic driving path planning method based on interaction of vehicle behaviors and environment | |
| US20220326395A1 (en) | Device and method for autonomously locating a mobile vehicle on a railway track | |
| US11555928B2 (en) | Three-dimensional object detection with ground removal intelligence | |
| CN116203973A (en) | Intelligent control system of track AI inspection robot | |
| CN114407919B (en) | Collision detection method and system based on automatic driving | |
| KR102539363B1 (en) | Method and system for estimating the geographic location of a target | |
| Sama et al. | Learning how to drive in blind intersections from human data | |
| CN115246394A (en) | Intelligent vehicle overtaking obstacle avoidance method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190322 |
|
| RJ01 | Rejection of invention patent application after publication |