CN107168309A - A kind of underwater multi-robot paths planning method of Behavior-based control - Google Patents
A kind of underwater multi-robot paths planning method of Behavior-based control Download PDFInfo
- Publication number
- CN107168309A CN107168309A CN201710301455.0A CN201710301455A CN107168309A CN 107168309 A CN107168309 A CN 107168309A CN 201710301455 A CN201710301455 A CN 201710301455A CN 107168309 A CN107168309 A CN 107168309A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- auv
- msup
- particle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000002245 particle Substances 0.000 claims abstract description 86
- 238000004134 energy conservation Methods 0.000 claims abstract description 23
- 238000005457 optimization Methods 0.000 claims abstract description 23
- 230000006399 behavior Effects 0.000 claims description 50
- 230000003044 adaptive effect Effects 0.000 claims description 16
- 230000004888 barrier function Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 230000009471 action Effects 0.000 abstract description 2
- 238000005267 amalgamation Methods 0.000 abstract description 2
- 230000004913 activation Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0217—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with energy consumption, time reduction or distance reduction criteria
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)
- Feedback Control In General (AREA)
Abstract
The present invention provides a kind of underwater multi-robot paths planning method of Behavior-based control, belongs to Path Planning Technique field.The present invention proposes a kind of underwater multi-robot Path Planning being applied under Dynamic Unknown Environment, specifically includes:First, basic act is defined to add constraint to AUV navigation path, basic act is respectively energy-conservation behavior, agreement and safety behavior;Then, performance-based objective function corresponding with basic act is set up, the time variable and space variable relevant with AUV are combined;Finally, global objective function is set up to realize the action amalgamation of 3 kinds of basic acts, and global objective function is solved using a kind of particle swarm optimization algorithm with inertia weight, and one can be generated from colliding and being most short path by the optimal solution of output.
Description
Technical field
It is a kind of many water of Behavior-based control the present invention relates to a kind of underwater multi-robot paths planning method of Behavior-based control
The paths planning method of lower robot cooperative information collection.
Background technology
Underwater multi-robot (Multiple Autonomous underwater Vehicles, abbreviation MAUV) refer to by
The AUV of multiple relatively simple isomorphisms or isomery may finally complete specific jointly by some form of cooperative cooperating
More complicated job task system.The concurrency of underwater multi-robot can significantly improve AUV service behaviours, shorten and appoint
The business time, and the possibility for the task of successfully completing is increased by the coordination of Different Individual in system.In addition, many underwaters
People's system has the advantages that more efficient, cost is lower, flexibility is high, strong robustness compared to single underwater robot.
The key for playing underwater multi-robot cooperation advantage is the premise that each AUV is allocated tasks clear in systems
Under, by set planning and control strategy, composition one makes different AUV itself to be taken into account while carrying out job task
The team for cooperating and coordinating with other AUV, the task of complexity is finally completed by playing sense of community and team spirit.For number
According to the task of collection, AUV is needed safely close to the node and then communication acquisition data being distributed in ocean.Marine environment under water
In, in order to independently complete Data Collection task, for multiple autonomous underwater vehicle system, effective Path Planning is very
It is necessary.When traditional underwater multi-robot paths planning method only considers that AUV performs task mostly, do not sent out with other AUV
Raw collision, does not consider that AUV may be out of touch with other members, so that cotasking can not be completed.
The present invention proposes a kind of underwater multi-robot path planning plan for being applied to Behavior-based control under Dynamic Unknown Environment
Slightly, constrained by defining basic act to be added to AUV navigation path, performance-based objective function and global object letter are set up afterwards
Count to solve the problems, such as the safety in cooperative information gatherer process and cooperation.The present invention uses a kind of population with inertia weight
Optimized algorithm solves global objective function, by the optimal solution of output can generate one from colliding and being most short road
Footpath.
The content of the invention
The invention aims to provide a kind of cooperate with the multiple underwater robots of guarantee to complete Data Collection tasks
Meanwhile, use the safe path planning algorithm of minimum energy consumption.
The object of the present invention is achieved like this:(1) motion that 3 basic acts are used for constraining AUV is defined, it is ensured that in peace
On the premise of complete, AUV distance to go is most short, and realizes and to be cooperateed with other AUV;
(2) performance-based objective function is corresponding with basic act, is the specific mathematicization of basic act, is defined on AUV decision-making
In space, and to ensure the convergence of function;
(3) global objective function take into account the combined influence of 3 basic acts, utilize the population with inertia weight
Optimized algorithm solves not the optimal solution of global objective function in the same time, not the optimal solution composition of global objective function in the same time
AUV path locus.
Present invention additionally comprises some such architectural features:
1. described in the object functions of 3 basic acts be specially:
The ambient As of path planning be two dimensional surface, u be t AUV velocity magnitude, θ be current bow to angle,
(xt,yt) be the moment position coordinates, Δ t be time interval, AUV decision-making output include speed and bow to angle, it is assumed that (fx,
fy) be subsequent time AUV position coordinates, obtain:
fx=xt+u·Δt·cosθ
fy=yt+u·Δt·sinθ
A, energy conservation object function f1(θ, u, t) is:
Wherein:(xs,ys) be target point position coordinates, d1For the Euclidean distance between subsequent time AUV and target point, s1
And s2It is scaling coefficient;
B, collaboration object function f2(θ, u, t) is:
fbx=xb+ub·Δt·cosθb,fby=yb+ub·Δt·cosθb
Wherein:(fbx,fby) be the AUV subsequent time closest with the AUV position, d2For two of subsequent time
AUV Euclidean distance, [dmin,dmax] it is d2Expectation span, s1And s2It is scaling coefficient, M2For the constant value of setting;
C, safety behavior object function f3(θ, u, t) is:
Wherein:(xo,yo) be obstacle object point position coordinates, d3For AUV and barrier subsequent time Euclidean distance, ds
For apart from d3Secure threshold, M3For the constant value of setting.
2. described in set up and solve global objective function process it is as follows:
The specific form of global objective function is:
F=F (θ, u, t)=ω1f1+ω2f2+ω3f3
In formula:ω1,ω2,ω3It is transformable weight coefficient, 3 kinds of behaviors is ordered as safety according to relative importance
Behavior, agreement and energy-conservation behavior, and set in 3 weight coefficients, global objective function with 2 space variable θ and u, 1
Individual time variable t;
In t, using the particle swarm optimization algorithm with inertia weight, the tool of the optimal solution of global objective function is obtained
Body step is as follows:
Step 1:Using the global objective function of the particle swarm optimization algorithm generation with inertia weight, algorithm is opened
Begin;
Step 2:Particle swarm optimization algorithm parameter of the initialization with inertia weight, including set search space empty for two dimension
Between, wherein attitude angle space span is [θ0-θmax,θ0+θmax], velocity space span is [0, umax], wherein:θ0For
AUV current time attitude angles, θmaxFor AUV hard-over abilities, umaxFor AUV maximum headway;Population size is N, if
Put the initial position and speed of each particle;
Step 3:By the use of global objective function as fitness function, the fitness of each particle is calculated;
Step 4:The individual optimal solution and globally optimal solution of more new particle:
The location of each particle represents a solution in two-dimentional solution space, and the quality of solution is determined by adaptive value, certain
One particle I is vector X in the positional representation of two-dimensional spacei=(θi,ui), particle is searched for by constantly adjusting the position of oneself
New explanation, each particle can remember the optimal solution oneself searched, be denoted as pid;And the best position that whole population is lived through
Put, i.e., the optimal solution searched at present is denoted as pgd;
Step 5:The position of more new particle and speed:
Particle has flying speed, and flying speed can be expressed as vectorAs above-mentioned two optimal solution pid
And pgdAfter all finding, each particle updates position and the speed of oneself according to following formula;
Wherein, Vi k+1Represent speed of i-th of particle in k+1 iteration, c0For inertia weight, c1And c2It is normal to accelerate
Number, rand () is the random number between 0 to 1;
For inertia weight c0, determine that method is using the inertia weight that subtracts inertia weight afterwards is first increased:
In formula, Max Number are the maximum iteration of algorithm.
Step 6:Judge whether to have been maxed out iterations, if reaching maximum iteration, export optimal solution, calculate
Method terminates;Otherwise, the iterations of algorithm adds 1, return to step 3.
3. described in calculate the fitness of each particle and refer to the adaptive value for obtaining each particle, each particle have one by
The adaptive value that object function is determined, adaptive value is directly disposed as global objective function F (θ, u, t).
Compared with prior art, the beneficial effects of the invention are as follows:Invention defines the 3 of AUV kind basic act, including section
Energy behavior, safety behavior and agreement, and the corresponding localized target function of basic act is established, so as to constrain AUV
Navigation, it is possible to realize cooperateed with other AUV navigate by water purpose.Global objective function is finally set up, and using with inertia
The particle swarm optimization algorithm of weight is solved, and method is determined by using the inertia weight that subtracts inertia weight afterwards is first increased, than one
As particle swarm optimization algorithm there are faster convergence capabilities and more preferable local convergence speed.
Brief description of the drawings
Fig. 1 is underwater multi-robot paths planning method schematic diagram proposed by the present invention;
Fig. 2 is the schematic flow sheet of the particle swarm optimization algorithm in the present invention;
Fig. 3 be in the present invention AUV in time and spatial movement schematic diagram;
Fig. 4 is the schematic diagram of particle position change in the present invention.
Embodiment
The present invention is described in further detail with embodiment below in conjunction with the accompanying drawings.
A kind of underwater multi-robot paths planning method of Behavior-based control, including:
1st, the motion that 3 basic acts are used for constraining AUV is defined, it is ensured that on the premise of safety, AUV distance to go is most
It is short, and realize and cooperateed with other AUV.
2nd, performance-based objective function is corresponding with basic act, is the specific mathematicization of basic act, and the decision-making for being defined on AUV is empty
Between in, and to ensure the convergence of function.
3rd, global objective function take into account the combined influence of 3 basic acts, utilize the population with inertia weight
Optimized algorithm solves not the optimal solution of global objective function in the same time, not the optimal solution composition of global objective function in the same time
AUV path locus,
3 performance-based objective functions are specially:
The ambient As of path planning be two dimensional surface, u be t AUV velocity magnitude, θ be current bow to angle,
(xt,yt) be the moment position coordinates, Δ t be time interval, AUV decision-making output include speed and bow to angle.Assuming that (fx,
fy) be subsequent time AUV position coordinates, following formula can be obtained:
fx=xt+u·Δt·cosθ
fy=yt+u·Δt·sinθ
1) energy conservation object function can be expressed as:
(xs,ys) it is that the position coordinates of target point is, d1For the Euclidean distance between subsequent time AUV and target point.Wherein s1
And s2It is scaling coefficient.
2) collaboration object function can be expressed as:
fbx=xb+ub·Δt·cosθb,fby=yb+ub·Δt·cosθb
(fbx,fby) be the AUV subsequent time closest with the AUV position, d2For two AUV of subsequent time Europe
Family name's distance, [dmin,dmax] it is d2Expectation span, s1And s2It is scaling coefficient, M2For the constant value of setting.
3) safety behavior object function can be expressed as follows:
(xo,yo) be obstacle object point position coordinates, d3For AUV and barrier subsequent time Euclidean distance, dsFor distance
d3Secure threshold, M3For the constant value of setting.
The process set up and solve global objective function is as follows:
The specific form of global objective function is shown below:
F=F (θ, u, t)=ω1f1+ω2f2+ω3f3
In formula, ω1,ω2,ω3It is transformable weight coefficient.3 kinds of behaviors are ordered as safety according to relative importance
Behavior, agreement and energy-conservation behavior, 3 weight coefficients are set according to this principle.There are 2 skies in global objective function
Between variable θ and u, 1 time variable t.
In t, below with the particle swarm optimization algorithm with inertia weight, to seek the optimal of global objective function
Solution, is comprised the following steps that:
Step 1:Using the global objective function of the particle swarm optimization algorithm generation with inertia weight, algorithm is opened
Begin;
Step 2:Particle swarm optimization algorithm parameter of the initialization with inertia weight, including set search space empty for two dimension
Between, wherein attitude angle space span is [θ0-θmax,θ0+θmax], velocity space span is [0, umax], θ here0For
AUV current time attitude angles, θmaxFor AUV hard-over abilities, umaxFor AUV maximum headway;Population size is N, if
Put the initial position and speed of each particle;
Step 3:By the use of global objective function as fitness function, the fitness of each particle is calculated.Each particle
There is an adaptive value determined by object function (fitness value), adaptive value can be directly disposed as global object here
Function F (θ, u, t);
Step 4:The individual optimal solution and globally optimal solution of more new particle.The location of each particle represents 2-D solution
A solution in space, the quality of solution is determined that fitness is bigger by adaptive value, and the quality of solution is better.A certain particle I is two-dimentional empty
Between positional representation be vector Xi=(θi,ui), particle searches for new explanation, each particle by constantly adjusting the position of oneself
The optimal solution oneself searched can be remembered, p is denoted asid;And the best position that whole population is lived through, i.e., search at present
Optimal solution, be denoted as pgd;
Step 5:The position of more new particle and speed.Particle has flying speed, so as to adjust the position of oneself.Fly
Scanning frequency degree can be expressed as vectorAs above-mentioned two optimal solution pidAnd pgdAfter all finding, each particle is under
Formula updates oneself position and speed;
Wherein, Vi k+1Represent speed of i-th of particle in k+1 iteration, c0For inertia weight, c1And c2It is normal to accelerate
Number, rand () is the random number between 0 to 1;
For inertia weight c0, method is determined using the inertia weight that subtracts inertia weight afterwards is first increased, this method is in iteration
Initial stage, with faster convergence rate;In the later stage of iteration, with preferable local search ability, specific method such as following formula institute
Show:
In formula, MaxNumber is the maximum iteration of algorithm.
Step 6:Judge whether to have been maxed out iterations, if reaching maximum iteration, export optimal solution, calculate
Method terminates.Otherwise, the iterations of algorithm adds 1, return to step 3.
The present invention will be described in detail below in conjunction with the accompanying drawings:
As shown in figure 1, a kind of underwater multi-robot paths planning method of Behavior-based control proposed by the present invention, is mainly included
Following part:3 basic acts, are energy-conservation behavior, agreement and safety behavior respectively;Row corresponding with 3 basic acts
For object function;The global objective function generated by 3 performance-based objective functions, and global objective function is solved.3
Basic act is used for constraining AUV motion, it is ensured that on the premise of safety, AUV distance to go is most short, and realize with it is other
AUV collaboration.Performance-based objective function is the specific mathematicization of 3 basic acts of correspondence respectively, and performance-based objective function needs definition
In AUV decision space, and to ensure the convergence of function.Global objective function take into account the synthesis of 3 basic acts
Influence, the optimal solution of global objective function does not constitute AUV path locus in the same time, and the present invention utilizes the grain with inertia weight
Subgroup optimized algorithm solves not the optimal solution of global objective function in the same time.
(1) basic act described in is defined in the following manner:
The ambient As of path planning are two dimensional surface, set up the global coordinate system O-XY of environmental map.As shown in figure 1,
After AUV obtains the ambient condition information needed, these information include the position of target point, other AUV position and speed size
With bow to angle, and obstacle position information.Herein, u be t AUV velocity magnitude, θ be current bow to angle, (xt,
yt) be the moment position coordinates, Δ t be time interval, AUV decision-making output include speed and bow to angle, be illustrated in figure 3
The motion schematic diagrames of AUV over time and space.
Assuming that (fx,fy) be subsequent time AUV position coordinates, following formula can be expressed as:
fx=xt+u·Δt·cosθ
fy=yt+u·Δt·sinθ
1.1) behavior is saved
Limited energy when being worked in view of AUV, in order to simplify problem, the present invention only considers the influence of distance to go, and
And think, distance to go is shorter, and energy saving is better.In order to define energy-conservation behavior, some can be added about to AUV navigation condition
Beam, and constraints is set to the distance of AUV and target point.
d1For the Euclidean distance between subsequent time AUV and target point, energy-conservation behavior is constantly in whole task process
State of activation.AUV and target point distance are corresponded into specific decision space, AUV attitude angle, speed and time is utilized
Variable can be by d1It is expressed as follows:
d1=d1(θ,u,t)
1.2) agreement
In view of the limitation of actual underwater sensor and means of communication, under the premise that security is guaranteed, agreement will
The mathematical form asked can be expressed as follows:
dmin< d2< dmax
d2For two AUV of subsequent time Euclidean distance, [dmin,dmax] it is d2Expectation span.With above-mentioned formula
The condition being active for agreement, can be by d using AUV attitude angle, speed and time variable2Represent such as
Under:
d2=d2(θ,u,t)
1.3) safety behavior
The mathematical form of safety behavior can be expressed as follows formula:
d3> dmin
d3For AUV and barrier subsequent time Euclidean distance, dsFor apart from d3Secure threshold.Utilize AUV posture
Angle, speed and time variable can be by d3It is expressed as follows formula:
d3=d3(θ,u,t)
(2) localized target function is set up:
2.1) energy conservation object function
Corresponding with energy-conservation behavior, the variable of energy conservation object function is AUV and target point apart from d1.For energy conservation object
For function, d1Value it is smaller, illustrate AUV closer to target point.When time interval Δ t is determined, apart from d1With AUV speed and
Bow is relevant to angle.To d1Measurement processing is carried out, the object function concrete form such as following formula of energy saving is obtained:
S in formula1And s2It is scaling coefficient.
2.2) object function is cooperateed with
Corresponding with agreement, the variate-value of collaboration object function is AUV and other members distance, in the task of execution
During, work compound should be kept between each AUV, to be in member's distance nearest in system represented here as AUV
One threshold value [dmin,dmax] in the range of.Final collaboration object function is shown below:
fbx=xb+ub·Δt·cosθb,fby=yb+ub·Δt·cosθb
(fbx,fby) be the AUV subsequent time closest with the AUV position, d2For two AUV of subsequent time Europe
Family name's distance, [dmin,dmax] it is d2Expectation span, s1And s2It is scaling coefficient, M2For the constant value of setting.
2.3) Security Target function
The activation of safety behavior needs to meet certain restrictive condition, is embodied as the distance threshold of AUV and barrier
ds.Final safety behavior object function is shown below:
(xo,yo) be obstacle object point position coordinates, d3For AUV and barrier subsequent time Euclidean distance, dsFor distance
d3Secure threshold, M3For the constant value of setting.
(3) the global objective function method for building up and solution procedure described in are as follows:
The effect of global objective function is a series of coordination of basic acts before realizing, the specific shape of global objective function
Formula is shown below:
F=F (θ, u, t)=ω1f1+ω2f2+ω3f3
In formula, ω1,ω2,ω3It is transformable weight coefficient.3 kinds of behaviors are ordered as safety according to relative importance
Behavior, agreement and energy-conservation behavior, 3 weight coefficients are set according to this principle.There are 2 skies in global objective function
Between variable θ and u, 1 time variable t.
In t, using the particle swarm optimization algorithm with inertia weight, to ask the optimal solution of global objective function, letter
Number is output as space variable θ and u.As shown in Fig. 2 comprising the following steps that:
Step 1:Using the global objective function of the particle swarm optimization algorithm generation with inertia weight, algorithm is opened
Begin;
Step 2:Particle swarm optimization algorithm parameter of the initialization with inertia weight, including set search space empty for two dimension
Between, wherein attitude angle space span is [θ0-θmax,θ0+θmax], velocity space span is [0, umax], θ here0For
AUV current time attitude angles, θmaxFor AUV hard-over abilities, umaxFor AUV maximum headway;Population size is N, if
Put the initial position and speed of each particle.
Step 3:By the use of global objective function as fitness function, the fitness of each particle is calculated.Each particle
Have an adaptive value determined by object function (fitness value), here adaptive value be set to global objective function F (θ,
u,t)。
Step 4:The individual optimal solution and globally optimal solution of more new particle.The location of each particle represents 2-D solution
A solution in space, the quality of solution is determined that fitness is bigger by adaptive value, and the quality of solution is better.A certain particle I is two-dimentional empty
Between positional representation be vector Xi=(θi,ui), particle searches for new explanation, each particle by constantly adjusting the position of oneself
The optimal solution oneself searched can be remembered, p is denoted asid;And the best position that whole population is lived through, i.e., search at present
Optimal solution, be denoted as pgd。
Step 5:The position of more new particle and speed.Particle has flying speed, so as to adjust the position of oneself.Fly
Scanning frequency degree can be expressed as vectorAs above-mentioned two optimal solution pidAnd pgdAfter all finding, each particle is under
Formula updates oneself position and speed, and the position of particle and speed renewal process be specifically as shown in Figure 4.
In formula, Vi k+1Represent speed of i-th of particle in k+1 iteration, c0For inertia weight, c1And c2It is normal to accelerate
Number, rand () is the random number between 0 to 1.
For inertia weight c0, method is determined using the inertia weight that subtracts inertia weight afterwards is first increased, this method is in iteration
Initial stage, with faster convergence rate;In the later stage of iteration, with preferable local search ability, specific method such as following formula institute
Show:
In formula, MaxNumber is the maximum iteration of algorithm.
Step 6:Judge whether to have been maxed out iterations, if reaching maximum iteration, export optimal solution, calculate
Method terminates.Otherwise, the iterations of algorithm adds 1, return to step 3.
It will be terminated when algorithm reaches maximum iteration;Now export optimal solution, i.e., what whole population was lived through
Best position pgd, the corresponding vector X in the positioni=(θi,ui) AUV is represented in the moment t attitude angles that should be exported and speed.
Finally, using the corresponding attitude angle of optimal solution and speed that particle swarm optimization algorithm is not exported in the same time, AUV can be generated last
Path.
(1) basic act is defined:
The ambient As of path planning are two dimensional surface, set up the global coordinate system O-XY of environmental map.Needed when AUV is obtained
After the ambient condition information wanted, these information include the position of target point, other AUV position and speed size and bow to angle, with
And obstacle position information.Herein, u be AUV velocity magnitude, θ be bow to angle, (xt,yt) be t position coordinates, Δ
T is time interval, and AUV decision-making output includes speed and bow to angle.
Assuming that (fx,fy) be subsequent time AUV position coordinates, following formula can be expressed as:
fx=xt+u·Δt·cosθ
fy=yt+u·Δt·sinθ
1.1) behavior is saved
Limited energy when being worked in view of AUV, in order to simplify problem, the present invention only considers the influence of distance to go, and
And think, distance to go is shorter, and energy saving is better.In order to define energy-conservation behavior, some can be added about to AUV navigation condition
Beam, and constraints is set to the distance of AUV and target point.d1For the Euclidean distance between subsequent time AUV and target point, energy-conservation
Behavior is constantly in state of activation in whole task process.AUV and target point distance are corresponded into specific decision space,
Can be by d using AUV attitude angle, speed and time variable1It is expressed as follows:
d1=d1(θ,u,t)
1.2) limitation of actual underwater sensor and means of communication is considered, under the premise that security is guaranteed, collaboration row
It can be expressed as follows for desired mathematical form:
dmin< d2< dmax
d2For two AUV of subsequent time Euclidean distance, [dmin,dmax] it is d2Expectation span.With above-mentioned formula
The condition being active for agreement, can be by d using AUV attitude angle, speed and time variable2Represent such as
Under:
d2=d2(θ,u,t)
1.3) safety behavior mathematical form can be expressed as follows:
d3> dmin
d3For AUV and barrier subsequent time Euclidean distance, dsFor apart from d3Secure threshold.Utilize AUV posture
Angle, speed and time variable can be by d3It is expressed as follows:
d3=d3(θ,u,t)
(2) localized target function is set up:
2.1) energy conservation object function
Corresponding with energy-conservation behavior, the variable of energy conservation object function is the distance of AUV and target point.Assuming that the position of target point
Coordinate is put for (xs,ys), d1Formula can be expressed as:
For energy conservation object function, d1Value it is smaller, illustrate AUV closer to target point.Determined in time interval Δ t
When, this distance is relevant to angle with AUV speed and bow.To d1Measurement processing is carried out, the specific shape of object function of energy saving is obtained
Formula such as following formula:
Wherein s1And s2It is scaling coefficient.
2.2) object function is cooperateed with
Corresponding with agreement, the variate-value of collaboration object function is AUV and other members distance, in the task of execution
During, work compound should be kept between each AUV, to be in member's distance nearest in system here embodied as AUV
One threshold value [dmin,dmax] in the range of.Final collaboration object function is shown below:
fbx=xb+ub·Δt·cosθb,fby=yb+ub·Δt·cosθb
(fbx,fby) be the AUV subsequent time closest with the AUV position, d2For two AUV of subsequent time Europe
Family name's distance, [dmin,dmax] it is d2Expectation span, s1And s2It is scaling coefficient, M2For the constant value of setting.
2.3) Security Target function
The activation of safety behavior needs to meet certain restrictive condition, is embodied as the distance threshold of AUV and barrier
ds.Final safety behavior object function is shown below:
(xo,yo) be obstacle object point position coordinates, d3For AUV and barrier subsequent time Euclidean distance, dsFor distance
d3Secure threshold, s1And s2It is scaling coefficient, M3For the constant value of setting.
(3) set up and solve global objective function:
The effect of global objective function is a series of coordination of basic acts before realizing, specific form such as following formula institute
Show:
F=F (θ, u, t)=ω1f1+ω2f2+ω3f3
In formula, ω1,ω2,ω3It is transformable weight coefficient.3 kinds of behaviors are ordered as safety according to relative importance
Behavior, agreement and energy-conservation behavior, 3 weight coefficients are set according to this principle.There are 2 skies in global objective function
Between variable θ and u, 1 time variable t.
Below with the particle swarm optimization algorithm with inertia weight, in t, to seek the optimal of global objective function
Solution.
3.1) path planning parameter, the particle swarm optimization algorithm parameter initialization with inertia weight
Setting search space is two-dimensional space, and wherein attitude angle space span is [θ0-θmax,θ0+θmax], speed is empty
Between span be [0, umax], θ here0For AUV current time attitude angles, θmaxFor AUV hard-over abilities, umaxFor AUV's
Maximum headway.Population size is N, sets the initial position and speed of each particle;
3.2) path is optimized using particle:
After algorithm initialization, into the main body iterative optimization procedure of algorithm;Particle cluster algorithm is by the association between individual
Make and compete, realize the search of optimal solution in complex space.A certain particle I is vector X in the positional representation of two-dimensional spacei=
(θi,ui), the location of each particle represents a solution in two-dimentional solution space.Particle is by constantly adjusting the position of oneself
Put to search for new explanation, each particle can remember the optimal solution oneself searched, be denoted as pid;And whole population is lived through
Best position, i.e., the optimal solution searched at present, is denoted as pgd。
Particle has flying speed, so as to adjust the position of oneself.Flying speed can be expressed as vectorEach particle has an adaptive value determined by object function (fitness value), and adaptive value can here
To be directly disposed as global objective function F (θ, u, t);As above-mentioned two optimal solution pidAnd pgdAfter all finding, each particle according to
Following formula updates oneself position and speed.
In formula, Vi k+1Represent speed of i-th of particle in k+1 iteration, c0For inertia weight, c1And c2It is normal to accelerate
Number, rand () is the random number between 0 to 1.
Judge whether to have been maxed out iterations afterwards, next step is entered if maximum iteration is reached;It is no
Then, the iterations of algorithm adds 1, proceeds next step optimization process.
3.3) optimal solution is exported
It will be terminated when algorithm reaches maximum iteration;Now export optimal solution, i.e., what whole population was lived through
Best position pgd, the corresponding vector X in the positioni=(θi,ui) AUV is represented in the moment t attitude angles that should be exported and speed.
Finally, can be with shape using the corresponding attitude angle of optimal solution and speed that particle swarm optimization algorithm is not exported in the same time
Into the path that AUV is last.
To sum up, the present invention proposes a kind of underwater multi-robot paths planning method of Behavior-based control, belongs to path planning skill
Art field.
The present invention proposes a kind of underwater multi-robot Path Planning being applied under Dynamic Unknown Environment, specific bag
Include:First, basic act is defined to add constraint to AUV navigation path, basic act is respectively energy-conservation behavior, agreement
And safety behavior;Then, performance-based objective function corresponding with basic act is set up, by the time variable relevant with AUV and space
Variable combines;Finally, global objective function is set up to realize the action amalgamation of 3 kinds of basic acts, and is carried using one kind
The particle swarm optimization algorithm of inertia weight solves global objective function, by the optimal solution of output can generate one from touching
Hit and be most short path.
Claims (4)
1. a kind of underwater multi-robot paths planning method of Behavior-based control, it is characterised in that:
(1) motion that 3 basic acts are used for constraining AUV is defined, it is ensured that on the premise of safety, AUV distance to go is most short,
And realization is cooperateed with other AUV's;
(2) performance-based objective function is corresponding with basic act, is the specific mathematicization of basic act, is defined on AUV decision space
In, and to ensure the convergence of function;
(3) global objective function take into account the combined influence of 3 basic acts, utilize the particle group optimizing with inertia weight
Algorithm solves not the optimal solution of global objective function in the same time, not the optimal solution composition AUV of global objective function in the same time
Path locus.
2. a kind of underwater multi-robot paths planning method of Behavior-based control according to claim 1, it is characterised in that institute
The object function for stating 3 basic acts is specially:
The ambient As of path planning be two dimensional surface, u be t AUV velocity magnitude, θ be current bow to angle, (xt,yt)
For the position coordinates at the moment, Δ t is time interval, and AUV decision-making output includes speed and bow to angle, it is assumed that (fx,fy) be under
One moment AUV position coordinates, is obtained:
fx=xt+u·Δt·cosθ
fy=yt+u·Δt·sinθ
A, energy conservation object function f1(θ, u, t) is:
<mrow>
<msub>
<mi>f</mi>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>&theta;</mi>
<mo>,</mo>
<mi>u</mi>
<mo>,</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mrow>
<mo>(</mo>
<mfrac>
<mn>100</mn>
<mrow>
<mn>1</mn>
<mo>+</mo>
<msup>
<mn>1.2</mn>
<mrow>
<mo>(</mo>
<mi>q</mi>
<mo>-</mo>
<mn>1000</mn>
<mo>)</mo>
<mo>/</mo>
<mn>20</mn>
</mrow>
</msup>
</mrow>
</mfrac>
<mo>-</mo>
<msub>
<mi>s</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
<mo>/</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>s</mi>
<mn>2</mn>
</msub>
<mo>-</mo>
<msub>
<mi>s</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mi>q</mi>
<mo>=</mo>
<msub>
<mi>d</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>f</mi>
<mi>x</mi>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mi>s</mi>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>f</mi>
<mi>y</mi>
</msub>
<mo>-</mo>
<msub>
<mi>y</mi>
<mi>s</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
</msqrt>
<mo>,</mo>
<msub>
<mi>s</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mi>min</mi>
<mrow>
<mo>(</mo>
<mfrac>
<mn>100</mn>
<mrow>
<mn>1</mn>
<mo>+</mo>
<msup>
<mn>1.2</mn>
<mrow>
<mo>(</mo>
<mi>q</mi>
<mo>-</mo>
<mn>1000</mn>
<mo>)</mo>
<mo>/</mo>
<mn>20</mn>
</mrow>
</msup>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
<mo>,</mo>
<msub>
<mi>s</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
<mrow>
<mo>(</mo>
<mfrac>
<mn>100</mn>
<mrow>
<mn>1</mn>
<mo>+</mo>
<msup>
<mn>1.2</mn>
<mrow>
<mo>(</mo>
<mi>q</mi>
<mo>-</mo>
<mn>1000</mn>
<mo>)</mo>
<mo>/</mo>
<mn>20</mn>
</mrow>
</msup>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
</mrow>
Wherein:(xs,ys) be target point position coordinates, d1For the Euclidean distance between subsequent time AUV and target point, s1And s2It is
Scaling coefficient;
B, collaboration object function f2(θ, u, t) is:
<mrow>
<mi>q</mi>
<mo>=</mo>
<msub>
<mi>d</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>f</mi>
<mi>x</mi>
</msub>
<mo>-</mo>
<msub>
<mi>f</mi>
<mrow>
<mi>b</mi>
<mi>x</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>f</mi>
<mi>y</mi>
</msub>
<mo>-</mo>
<msub>
<mi>f</mi>
<mrow>
<mi>b</mi>
<mi>y</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<mo>,</mo>
<msub>
<mi>s</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mi>min</mi>
<mrow>
<mo>(</mo>
<mfrac>
<mn>100</mn>
<mrow>
<mn>1</mn>
<mo>+</mo>
<msup>
<mn>1.2</mn>
<mrow>
<mo>(</mo>
<mi>q</mi>
<mo>-</mo>
<mn>1000</mn>
<mo>)</mo>
<mo>/</mo>
<mn>20</mn>
</mrow>
</msup>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
<mo>,</mo>
<msub>
<mi>s</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mi>max</mi>
<mrow>
<mo>(</mo>
<mfrac>
<mn>100</mn>
<mrow>
<mn>1</mn>
<mo>+</mo>
<msup>
<mn>1.2</mn>
<mrow>
<mo>(</mo>
<mi>q</mi>
<mo>-</mo>
<mn>1000</mn>
<mo>)</mo>
<mo>/</mo>
<mn>20</mn>
</mrow>
</msup>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
</mrow>
fbx=xb+ub·Δt·cosθb,fby=yb+ub·Δt·cosθb
Wherein:(fbx,fby) be the AUV subsequent time closest with the AUV position, d2For two AUV of subsequent time
Euclidean distance, [dmin,dmax] it is d2Expectation span, s1And s2It is scaling coefficient, M2For the constant value of setting;
C, safety behavior object function f3(θ, u, t) is:
<mrow>
<mi>q</mi>
<mo>=</mo>
<msub>
<mi>d</mi>
<mn>3</mn>
</msub>
<mo>=</mo>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>f</mi>
<mi>x</mi>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mi>o</mi>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>f</mi>
<mi>y</mi>
</msub>
<mo>-</mo>
<msub>
<mi>y</mi>
<mi>o</mi>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<mo>,</mo>
<msub>
<mi>s</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mi>m</mi>
<mi>i</mi>
<mi>n</mi>
<mrow>
<mo>(</mo>
<mfrac>
<mn>100</mn>
<mrow>
<mn>1</mn>
<mo>+</mo>
<msup>
<mn>1.2</mn>
<mrow>
<mo>(</mo>
<mi>q</mi>
<mo>-</mo>
<mn>1000</mn>
<mo>)</mo>
<mo>/</mo>
<mn>20</mn>
</mrow>
</msup>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
<mo>,</mo>
<msub>
<mi>s</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
<mrow>
<mo>(</mo>
<mfrac>
<mn>100</mn>
<mrow>
<mn>1</mn>
<mo>+</mo>
<msup>
<mn>1.2</mn>
<mrow>
<mo>(</mo>
<mi>q</mi>
<mo>-</mo>
<mn>1000</mn>
<mo>)</mo>
<mo>/</mo>
<mn>20</mn>
</mrow>
</msup>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
</mrow>
Wherein:(xo,yo) be obstacle object point position coordinates, d3For AUV and barrier subsequent time Euclidean distance, dsFor distance
d3Secure threshold, M3For the constant value of setting.
3. a kind of underwater multi-robot paths planning method of Behavior-based control according to claim 1, it is characterised in that institute
State set up and solve global objective function process it is as follows:
The specific form of global objective function is:
F=F (θ, u, t)=ω1f1+ω2f2+ω3f3
In formula:ω1,ω2,ω3It is transformable weight coefficient, 3 kinds of behaviors is ordered as security row according to relative importance
For, agreement and energy-conservation behavior, and set in 3 weight coefficients, global objective function have 2 space variables θ and u, 1
Time variable t;
In t, using the particle swarm optimization algorithm with inertia weight, the specific step of the optimal solution of global objective function is obtained
It is rapid as follows:
Step 1:Using the global objective function of the particle swarm optimization algorithm generation with inertia weight, algorithm starts;
Step 2:Particle swarm optimization algorithm parameter of the initialization with inertia weight, including set search space to be two-dimensional space,
Wherein attitude angle space span is [θ0-θmax,θ0+θmax], velocity space span is [0, umax], wherein:θ0For AUV
Current time attitude angle, θmaxFor AUV hard-over abilities, umaxFor AUV maximum headway;Population size is N, sets each
The initial position and speed of individual particle;
Step 3:By the use of global objective function as fitness function, the fitness of each particle is calculated;
Step 4:The individual optimal solution and globally optimal solution of more new particle:
The location of each particle represents a solution in two-dimentional solution space, and the quality of solution is determined by adaptive value, a certain grain
Sub- I is vector X in the positional representation of two-dimensional spacei=(θi,ui), particle searches for new explanation by constantly adjusting the position of oneself,
Each particle can remember the optimal solution oneself searched, be denoted as pid;And the best position that whole population is lived through, i.e.,
The optimal solution searched at present, is denoted as pgd;
Step 5:The position of more new particle and speed:
Particle has flying speed, and flying speed can be expressed as vectorAs above-mentioned two optimal solution pidAnd pgd
After all finding, each particle updates position and the speed of oneself according to following formula;
<mrow>
<msubsup>
<mi>V</mi>
<mi>i</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mo>=</mo>
<msub>
<mi>c</mi>
<mn>0</mn>
</msub>
<msubsup>
<mi>V</mi>
<mi>i</mi>
<mi>k</mi>
</msubsup>
<mo>+</mo>
<msub>
<mi>c</mi>
<mn>1</mn>
</msub>
<mo>&times;</mo>
<mi>r</mi>
<mi>a</mi>
<mi>n</mi>
<mi>d</mi>
<mrow>
<mo>(</mo>
<mo>)</mo>
</mrow>
<mo>&times;</mo>
<mrow>
<mo>(</mo>
<mi>p</mi>
<mi>b</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
<mo>-</mo>
<msubsup>
<mi>X</mi>
<mi>i</mi>
<mi>k</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mo>+</mo>
<msub>
<mi>c</mi>
<mn>2</mn>
</msub>
<mo>&times;</mo>
<mi>r</mi>
<mi>a</mi>
<mi>n</mi>
<mi>d</mi>
<mrow>
<mo>(</mo>
<mo>)</mo>
</mrow>
<mo>&times;</mo>
<mrow>
<mo>(</mo>
<mi>g</mi>
<mi>b</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
<mo>-</mo>
<msubsup>
<mi>X</mi>
<mi>i</mi>
<mi>k</mi>
</msubsup>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msubsup>
<mi>X</mi>
<mi>i</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mo>=</mo>
<msubsup>
<mi>X</mi>
<mi>i</mi>
<mi>k</mi>
</msubsup>
<mo>+</mo>
<msubsup>
<mi>V</mi>
<mi>i</mi>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msubsup>
</mrow>
Wherein, Vi k+1Represent speed of i-th of particle in k+1 iteration, c0For inertia weight, c1And c2For aceleration pulse,
Rand () is the random number between 0 to 1;
For inertia weight c0, determine that method is using the inertia weight that subtracts inertia weight afterwards is first increased:
<mrow>
<msub>
<mi>c</mi>
<mn>0</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mn>1</mn>
<mo>&times;</mo>
<mfrac>
<mi>k</mi>
<mrow>
<mi>M</mi>
<mi>a</mi>
<mi>x</mi>
<mi>N</mi>
<mi>u</mi>
<mi>m</mi>
<mi>b</mi>
<mi>e</mi>
<mi>r</mi>
</mrow>
</mfrac>
<mo>+</mo>
<mn>0.4</mn>
</mrow>
</mtd>
<mtd>
<mrow>
<mn>0</mn>
<mo>&le;</mo>
<mfrac>
<mi>k</mi>
<mrow>
<mi>M</mi>
<mi>a</mi>
<mi>x</mi>
<mi>N</mi>
<mi>u</mi>
<mi>m</mi>
<mi>b</mi>
<mi>e</mi>
<mi>r</mi>
</mrow>
</mfrac>
<mo>&le;</mo>
<mn>0.5</mn>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>-</mo>
<mn>1</mn>
<mo>&times;</mo>
<mfrac>
<mi>k</mi>
<mrow>
<mi>M</mi>
<mi>a</mi>
<mi>x</mi>
<mi>N</mi>
<mi>u</mi>
<mi>m</mi>
<mi>b</mi>
<mi>e</mi>
<mi>r</mi>
</mrow>
</mfrac>
<mo>+</mo>
<mn>1.4</mn>
</mrow>
</mtd>
<mtd>
<mrow>
<mn>0.5</mn>
<mo>&le;</mo>
<mfrac>
<mi>k</mi>
<mrow>
<mi>M</mi>
<mi>a</mi>
<mi>x</mi>
<mi>N</mi>
<mi>u</mi>
<mi>m</mi>
<mi>b</mi>
<mi>e</mi>
<mi>r</mi>
</mrow>
</mfrac>
<mo>&le;</mo>
<mn>1</mn>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
In formula, Max Number are the maximum iteration of algorithm.
Step 6:Judge whether to have been maxed out iterations, if reaching maximum iteration, export optimal solution, algorithm knot
Beam;Otherwise, the iterations of algorithm adds 1, return to step 3.
4. a kind of underwater multi-robot paths planning method of Behavior-based control according to claim 3, it is characterised in that institute
State and calculate the fitness of each particle and refer to the adaptive value for obtaining each particle, each particle has one to be determined by object function
Adaptive value, adaptive value is directly disposed as global objective function F (θ, u, t).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710301455.0A CN107168309B (en) | 2017-05-02 | 2017-05-02 | Behavior-based multi-underwater robot path planning method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710301455.0A CN107168309B (en) | 2017-05-02 | 2017-05-02 | Behavior-based multi-underwater robot path planning method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107168309A true CN107168309A (en) | 2017-09-15 |
CN107168309B CN107168309B (en) | 2020-02-14 |
Family
ID=59812784
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710301455.0A Active CN107168309B (en) | 2017-05-02 | 2017-05-02 | Behavior-based multi-underwater robot path planning method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107168309B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108768712A (en) * | 2018-05-21 | 2018-11-06 | 中南大学 | Non- directional communication movable body cluster posture planing method towards connectivity |
CN108958028A (en) * | 2018-05-24 | 2018-12-07 | 大连理工大学 | Based on the group robot collaboratively searching method for improving particle swarm algorithm |
CN109241552A (en) * | 2018-07-12 | 2019-01-18 | 哈尔滨工程大学 | A kind of underwater robot motion planning method based on multiple constraint target |
CN109752015A (en) * | 2018-12-29 | 2019-05-14 | 青岛海洋科学与技术国家实验室发展中心 | Route planning method, computer-readable medium and control device |
CN109976158A (en) * | 2019-03-28 | 2019-07-05 | 沈阳航空航天大学 | Based on the AUV energy source optimization path search method apart from evolution N-PSO |
CN110181508A (en) * | 2019-05-09 | 2019-08-30 | 中国农业大学 | Underwater robot three-dimensional Route planner and system |
CN110764518A (en) * | 2019-10-31 | 2020-02-07 | 五邑大学 | Underwater dredging robot path planning method and device, robot and storage medium |
CN111307158A (en) * | 2020-03-19 | 2020-06-19 | 哈尔滨工程大学 | AUV three-dimensional route planning method |
CN112124299A (en) * | 2020-09-14 | 2020-12-25 | 东南大学 | Intelligent networking new energy automobile layered energy consumption optimization method |
CN117369507A (en) * | 2023-10-31 | 2024-01-09 | 河海大学 | Unmanned aerial vehicle dynamic path planning method of self-adaptive particle swarm algorithm |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101436073A (en) * | 2008-12-03 | 2009-05-20 | 江南大学 | Wheeled mobile robot trace tracking method based on quantum behavior particle cluster algorithm |
CN102129249A (en) * | 2011-01-10 | 2011-07-20 | 中国矿业大学 | Method for planning global path of robot under risk source environment |
US20130289870A1 (en) * | 2012-04-26 | 2013-10-31 | The Government Of The United States Of America, As Represented By The Secretary Of The Navy | Collaborative Robot Manifold Tracker |
CN105138000A (en) * | 2015-08-06 | 2015-12-09 | 大连大学 | Seven-freedom-degree space manipulator track planning method optimizing position and posture disturbance of pedestal |
CN106503837A (en) * | 2016-10-11 | 2017-03-15 | 哈尔滨工程大学 | A kind of time optimal Route planner based on improvement level set algorithm |
-
2017
- 2017-05-02 CN CN201710301455.0A patent/CN107168309B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101436073A (en) * | 2008-12-03 | 2009-05-20 | 江南大学 | Wheeled mobile robot trace tracking method based on quantum behavior particle cluster algorithm |
CN102129249A (en) * | 2011-01-10 | 2011-07-20 | 中国矿业大学 | Method for planning global path of robot under risk source environment |
US20130289870A1 (en) * | 2012-04-26 | 2013-10-31 | The Government Of The United States Of America, As Represented By The Secretary Of The Navy | Collaborative Robot Manifold Tracker |
CN105138000A (en) * | 2015-08-06 | 2015-12-09 | 大连大学 | Seven-freedom-degree space manipulator track planning method optimizing position and posture disturbance of pedestal |
CN106503837A (en) * | 2016-10-11 | 2017-03-15 | 哈尔滨工程大学 | A kind of time optimal Route planner based on improvement level set algorithm |
Non-Patent Citations (2)
Title |
---|
QIULING JIA,等: "Formation Control and Obstacle Avoidance Algorithm of Multiple Autonomous Underwater Vehicles(AUVs) Based on Potential Function and Behavior Rules", 《PROCEEDINGS OF THE IEEE INTERNATIONAL CONFERENCE ON AUTOMATION AND LOGISTICS》 * |
马家辰,等: "基于多行为融合的移动机器人路径规划方法", 《北京理工大学学报》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108768712B (en) * | 2018-05-21 | 2021-04-02 | 中南大学 | Non-omnidirectional communication moving body cluster attitude planning method facing connectivity |
CN108768712A (en) * | 2018-05-21 | 2018-11-06 | 中南大学 | Non- directional communication movable body cluster posture planing method towards connectivity |
CN108958028A (en) * | 2018-05-24 | 2018-12-07 | 大连理工大学 | Based on the group robot collaboratively searching method for improving particle swarm algorithm |
CN109241552A (en) * | 2018-07-12 | 2019-01-18 | 哈尔滨工程大学 | A kind of underwater robot motion planning method based on multiple constraint target |
CN109241552B (en) * | 2018-07-12 | 2022-04-05 | 哈尔滨工程大学 | Underwater robot motion planning method based on multiple constraint targets |
CN109752015A (en) * | 2018-12-29 | 2019-05-14 | 青岛海洋科学与技术国家实验室发展中心 | Route planning method, computer-readable medium and control device |
CN109976158B (en) * | 2019-03-28 | 2021-10-15 | 沈阳航空航天大学 | AUV energy optimization path searching method based on distance evolution N-PSO |
CN109976158A (en) * | 2019-03-28 | 2019-07-05 | 沈阳航空航天大学 | Based on the AUV energy source optimization path search method apart from evolution N-PSO |
CN110181508B (en) * | 2019-05-09 | 2021-01-12 | 中国农业大学 | Three-dimensional route planning method and system for underwater robot |
CN110181508A (en) * | 2019-05-09 | 2019-08-30 | 中国农业大学 | Underwater robot three-dimensional Route planner and system |
CN110764518A (en) * | 2019-10-31 | 2020-02-07 | 五邑大学 | Underwater dredging robot path planning method and device, robot and storage medium |
CN110764518B (en) * | 2019-10-31 | 2021-05-11 | 五邑大学 | Underwater dredging robot path planning method and device, robot and storage medium |
CN111307158A (en) * | 2020-03-19 | 2020-06-19 | 哈尔滨工程大学 | AUV three-dimensional route planning method |
CN112124299A (en) * | 2020-09-14 | 2020-12-25 | 东南大学 | Intelligent networking new energy automobile layered energy consumption optimization method |
CN112124299B (en) * | 2020-09-14 | 2021-11-02 | 东南大学 | Intelligent networking new energy automobile layered energy consumption optimization method |
CN117369507A (en) * | 2023-10-31 | 2024-01-09 | 河海大学 | Unmanned aerial vehicle dynamic path planning method of self-adaptive particle swarm algorithm |
Also Published As
Publication number | Publication date |
---|---|
CN107168309B (en) | 2020-02-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107168309A (en) | A kind of underwater multi-robot paths planning method of Behavior-based control | |
CN109241552B (en) | Underwater robot motion planning method based on multiple constraint targets | |
CN109343341B (en) | Carrier rocket vertical recovery intelligent control method based on deep reinforcement learning | |
Shi et al. | Multi pseudo Q-learning-based deterministic policy gradient for tracking control of autonomous underwater vehicles | |
Li et al. | Robust time-varying formation control for underactuated autonomous underwater vehicles with disturbances under input saturation | |
CN108873687B (en) | Intelligent underwater robot behavior system planning method based on deep Q learning | |
WO2020056875A1 (en) | Parking strategy based on deep reinforcement learning | |
CN109240091B (en) | Underwater robot control method based on reinforcement learning and tracking control method thereof | |
Zhu et al. | Task assignment and path planning of a multi-AUV system based on a Glasius bio-inspired self-organising map algorithm | |
Wang et al. | Target tracking control of a biomimetic underwater vehicle through deep reinforcement learning | |
CN106055522A (en) | Minimum base attitude disturbance track planning method for redundant space manipulator | |
CN105139072A (en) | Reinforcement learning algorithm applied to non-tracking intelligent trolley barrier-avoiding system | |
CN104501816A (en) | Multi-unmanned aerial vehicle coordination and collision avoidance guide planning method | |
CN111045453A (en) | Cooperative control system and method based on unmanned ship and multi-underwater robot | |
CN108363393B (en) | A kind of smart motion equipment and its air navigation aid and storage medium | |
kumar Panigrahi et al. | Navigation of autonomous mobile robot using different activation functions of wavelet neural network | |
Tian et al. | Learning to drive like human beings: A method based on deep reinforcement learning | |
Sun et al. | A novel fuzzy control algorithm for three-dimensional AUV path planning based on sonar model | |
CN109739094A (en) | A kind of mobile robot trace tracking new method based on adaptive sliding-mode observer | |
Panigrahi et al. | A novel intelligent mobile robot navigation technique for avoiding obstacles using RBF neural network | |
Lan et al. | Path planning for underwater gliders in time-varying ocean current using deep reinforcement learning | |
CN113093804A (en) | Unmanned ship formation control method and control system based on inversion sliding mode control | |
Gao et al. | Constrained path-planning control of unmanned surface vessels via ant-colony optimization | |
Lv et al. | A collision-free planning and control framework for a biomimetic underwater vehicle in dynamic environments | |
Sundarraj et al. | Route planning for an autonomous robotic vehicle employing a weight-controlled particle swarm-optimized Dijkstra algorithm |
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 |