CN109782779A - AUV paths planning method under ocean current environment based on population meta-heuristic algorithms - Google Patents
AUV paths planning method under ocean current environment based on population meta-heuristic algorithms Download PDFInfo
- Publication number
- CN109782779A CN109782779A CN201910209731.XA CN201910209731A CN109782779A CN 109782779 A CN109782779 A CN 109782779A CN 201910209731 A CN201910209731 A CN 201910209731A CN 109782779 A CN109782779 A CN 109782779A
- Authority
- CN
- China
- Prior art keywords
- population
- individual
- cost
- auv
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses AUV paths planning methods under the ocean current environment based on population meta-heuristic algorithms, belong to underwater robot field.Initialization population first obtains the initial synthetic cost value of all individuals in entire population further according to cost function；Then population basic operation set and corresponding operation select probability vector are set；The corresponding population basic operation of maximum probability in an individual in selected population, and operation select probability vector, operates the individual, repeats the population basic operation until traversing entire population, completes an iteration；Operation select probability vector is adjusted again, next iteration is carried out, until the number of iterations reaches setting value；Finally after the completion of iteration, the smallest individual of cost value is selected, one group of control point is constituted in conjunction with the starting point of B-spline curves, terminal and fixed control point, regenerates optimal path.The present invention solve the problems, such as the path of existing AUV paths planning method planning is rough, be difficult to track and track consume energy it is high.
Description
Technical field
The invention belongs to underwater robot field, it is related to the path AUV under the ocean current environment based on population meta-heuristic algorithms
Planing method.
Background technique
AUV, Autonomous Underwater Vehicle, are called autonomous underwater robot, big with scope of activities,
The advantages that mobility is good, safety, intelligence, is the important tool for completing various subsea tasks.Traditional mobile robot path
Planing method is mainly to be searched for using searching algorithms such as D and A* from starting point by the grating map for being discretization by environment representation
To the absolute shortest path of terminal.This paths planning method based on search has two, on the one hand when map scale
When increase, when especially expanding to three-dimensional space, searching algorithm efficiency can sharply decline；What another aspect this method obtained is one
Discrete, the rough path of kind, robot are difficult to track, especially the robot of drive lacking type.
It is a typical under-actuated systems since the torpedo AUV propeller for only relying on tail portion generates power, it is existing
The mode that mobile robot obtains discreet paths is difficult to apply on the torpedo AUV of under-actuated systems.So AUV path planning
More stringent requirements are proposed for slickness of the method to the path cooked up, and path not only needs smooth, but also there can be no be more than
The case where its maximum turning radius.
In addition, AUV it is underwater movement influenced by ocean current information it is very big, when the AUV direction of motion and ocean current flow direction difference
When larger, can not only generate large effect to its kinematic accuracy, and AUV can expend to keep original course line also it is additional
The energy.Therefore, the path that the paths planning method of AUV is cooked up not only requires slickness, also to transport as far as possible along ocean current
Dynamic direction, so that AUV has higher kinematic accuracy and more saves the ability of the energy.
AUV motion path is indicated with B-spline curves, and using its control point position as parameter, path planning problem is modeled
For the nonlinear optimal problem under a multi-constraint condition, final path can be made to meet a variety of constraints.Member based on population
Heuritic approach is to having very big advantage in solution nonlinear optimal problem, such as glowworm swarm algorithm, particle swarm algorithm and the shoal of fish
Algorithm etc..Occur many similar algorithms in recent years, there is scholar to think that these algorithms lack innovative, but being will be similar
Thought has changed a kind of simulated scenario.Therefore, a kind of super inspiration of the population for attempting comprehensive population meta-heuristic algorithm is produced
Formula algorithm stopped innovative lower simulated scenario and replace by managing a kind of meta-heuristic algorithms frame of population operational design
Scaling method.
The UUV for disclosing a kind of consideration ocean circulation influence application No. is the patent of " 2018105195080 " is based on energy
Consume the long-range navigation path planing method of optimization.This method first determine the actual route speed over the ground of UUV and in real time more
New Ocean current information；All kinds of parameters needed for initializing optimization algorithm；Path clustering section is randomly generated by spatial decomposition modeling
Point is fitted using B-Spline and generates initial path；Enter QPSO algorithm iteration process later, calculates current path and correspond to particle
Average optimum position calculates the energy consumption that current path corresponds to UUV；It is determined finally most finally by corresponding optimization process
Excellent solution exports final path clustering node, generates the optimal path locus of energy consumption according to final control node fitting.The party
Method indicates path with B-spline curves, and uses QPSO algorithm optimization selection spline curve control point position, but its majorized function
UUV kinetic model is considered using actual consumption as cost, calculates complicated and to expand to other types UUV more difficult.
Application No. is the patents of " 2014107663462 " to disclose a kind of submarine navigation device path rule based on Dynamic Programming
The method of drawing.Then the region rasterizing to be planned first is utilized speed in situation known to the future of ocean current by the invention
Synthetic model is spent to calculate time value spent between Searching point, and using time value as weight, applied dynamic programming algorithm
One is cooked up in two-dimensional surface up to optimal path.This method is searched on the map after rasterizing meets ocean current information
Although path, gained path meet ocean current constraint, but be not able to satisfy slickness constraint.
Therefore, in view of the above-mentioned problems, the invention proposes AUV under a kind of ocean current environment based on population meta-heuristic algorithms
Paths planning method.
Summary of the invention
It is an object of the invention to: provide the path planning side AUV under the ocean current environment based on population meta-heuristic algorithms
Method, solve the problems, such as the path of existing AUV paths planning method planning is rough, be difficult to track and track consume energy it is high.
The technical solution adopted by the invention is as follows:
AUV paths planning method under ocean current environment based on population meta-heuristic algorithms, comprising the following steps:
Step 1: initialization population, further according to combine time efficiency, environmental map, AUV ontology movement radius of curvature and
The information constrained cost function of ocean current obtains the initial synthetic cost value of all individuals in entire population；
Step 2: setting population basic operation set and corresponding operation select probability vector；In selected population one by one
Body, reselection operate the corresponding population basic operation of maximum probability in select probability vector, basic using the population to the individual
Operation, and update its integrate-cost value；Above-mentioned process is repeated until traversing entire population, so far completes an iteration；Then, it adjusts
Whole operation select probability vector carries out next iteration, until the number of iterations reaches setting value；
Step 3: after the completion of iteration, select the smallest individual of cost value, i.e. optimum individual, in conjunction with B-spline curves starting point,
Terminal and fixed control point constitute one group of control point, then generate optimal path by this group of control point.
Further, the specific steps of the step 1 are as follows:
Step 1.1: the beginning and end in the setting path AUV, connection source and terminal, and M etc. are generated on the line
Branch makees vertical line according to the line of beginning and end on each Along ent, obtains M vertical line, generates i on every vertical linemaxIt is a
Random point, to obtain imaxGroup random point, i-th group of random point are expressed as RPM,i(rp1,i,rp2,i,…rpk,i,…rpM,i, rpk,i
∈R2), i ∈ (1,2 ..., imax)；
Step 1.2: from starting point, the prime direction short distance along AUV increases a fixed control point p1, go out from terminal
Hair, the opposite direction along the termination direction of AUV increase a fixed control point p with short distance2, starting for controlling curve path
Direction and termination direction；
Step 1.3: according to step 1.1 and step 1.2, with starting point, terminal, one group of random point RPM,i(rp1,i,rp2,i,…
rpk,i,…rpM,i, rpk,i∈R2), fixed control point p1With fixed control point p2As the control point of a B-spline curves, then control
The quantity of system point is n, and the position of n=M+4, control point areIn conjunction with curve
Order K obtains the i of discrete point compositionmaxB-spline curves, curvilinear equation are as follows:
Wherein, Bi,K(t) be K B-spline curves basic function；
Step 1.4: by imaxB-spline curves obtain imaxThe path AUV, path representation are as follows:
Wherein, AUV towards ψ are as follows:
Step 1.5: by imaxGroup random point initializes to obtain population, one group of random point RPM,i(rp1,i,rp2,i,…
rpk,i,…rpM,i, rpk,i∈R2) indicate an individual, i.e., one solution xi, wherein individual dimension is M, and individual quantity is
imax, population P are as follows:
That is,
Step 1.6: according to combining, time efficiency, environmental map, AUV ontology movement radius of curvature and ocean current are information constrained
The each individual of cost function calculation initial cost value, the cost function combines time and penalty function, expression formula are as follows:
Wherein, TcostIt is time cost, passage path distance is obtained divided by average speed,
ρcostIt is curvature cost, is obtained by the approximate curvature at each discrete point that adds up,
McostIt is map cost, by adding up, (barrier 1 can be value of each discrete point on map by region
0) it obtains,
OcostThat ocean current is information constrained, by the angle of add up each discrete point path direction and water (flow) direction and water flow to
The product of amount mould obtains, and h is the quantity of discrete point on B-spline curves；
Step 1.7: four initial cost values being normalized respectively, since different cost values is with different
Dimension passes through maximum cost valueWith minimum cost valueTo obtain normalized cost value
Step 1.8: four cost values after normalization are summed by different Weights, available entire population
The initial synthetic cost value of all individuals in P:
Wherein, ω1, ω2, ω3, ω4It is the weight of different cost values.
Further, the specific steps of the step 2 are as follows:
Step 2.1: setting population basic operation set and corresponding operation select probability vector, the population basic operation
It is indicated with o<>, to the solution xt of input, a new explanation x is exported after an iterationt+1, expression formula is o < xt>=xt+1, institute
Population basic operation is stated to be random movement, beat over long distances at random, cost value is followed to be less than the individual of itself, follow cost value most
Small individual follows history optimized individual or mutation, and above-mentioned population basic operation is merged table by the population basic operation set
It is shown as O- { o1,o2,…,ok, wherein each population basic operation corresponds to an operation select probability vector, the operation selection
Probability vector is P- { p1,p2,...,pk}；
Step 2.2: the individual in selection step 1.5 population P, reselection operate maximum probability in select probability vector
Corresponding population basic operation oi；
Step 2.3: population basic operation o is used to the individual that step 2.2 selectsi, and according to step 1.6 to 1.8, it updates
The integrate-cost value of current individual；
Step 2.4: repeating step 2.2 and 2.3, until traversing entire population, a population base is used to each individual
This operation oiLater, an iteration is so far completed；
Step 2.5: the operating condition of the iteration of appraisal procedure 2.4, and adjust operation select probability vector after, return step
2.2 carry out next iteration, until the number of iterations reaches setting value.
Further, in the population basic operation of the step 2.1:
The random movement refers to mobile solution xiTo its neighborhood, expression formula are as follows: xi:=xi+λminRandu, wherein
λminIt is the step-length of centralization search,It is to obey equally distributed random number, u is random units direction vector；
The random long range bounce refers to mobile solution xiTo remote position, expression formula are as follows: xi:=xi+λmaxU,
In, λmaxIt is the step-length of diversification search, u is the vector in random units direction；
It is described to follow cost value to be less than itself individual and refer to solve xiIt is less than x to all cost valuesiSolution it is mobile, expression
Formula are as follows: xi:=xi+λ·rand·(xj-xi), meet f (x for allj) < f (xi) solution xj, solve xiIt will be moved to it；
It is described to follow the smallest individual of cost value to refer to solve xiSolution the smallest to cost value that is, optimal is mobile,
Expression formula are as follows: xi:=xi+λ·rand·(xb-xi), wherein xbIt is the solution that the optimum individual in population indicates；
It is described to follow history optimized individual to refer to solve xiIt is the smallest in the multiple cost values obtained after repeatedly evolving to it
Individual, that is, the position of history optimized individual are mobile, expression formula are as follows:Wherein,
Indicate solution xiHistory optimum position；
The mutation, which refers to, will solve xiMutation obtains a new explanation xi′。
Further, the operating condition of the iteration of appraisal procedure 2.4 refers to that centralization to be guaranteed refers in the step 2.5
Several to reach balance with index of diversification, the centralization index is assessed by cost value best before and after iteration, i.e. basisWithSize relation determine；The index of diversification is commented by the sum of the distance of all solutions and center solution
Estimate, formula are as follows:Wherein, center solvesI.e. according to dt-1And dtSize relation
To determine.
In conclusion by adopting the above-described technical solution, the beneficial effects of the present invention are:
1. AUV paths planning method under the ocean current environment based on population meta-heuristic algorithms, is indicated using B-spline curves
The path AUV, with the control point position of population meta-heuristic algorithms optimum option B-spline curves, and then obtain meeting time efficiency,
Environmental map, AUV ontology movement radius of curvature and the information constrained optimal path of ocean current, obtained path is continuous, smooth
And meet that ocean current is information constrained, reduce the tracking difficulty and tracking energy consumption of AUV.
2. the B-spline curves that the present invention uses, the less control point of usage quantity can obtain complicated and smooth road
Diameter, and only the geometrical relationship of passage path and ocean current information defines that ocean current is information constrained, reduces the complexity of method.
3. path planning problem is modeled as a nonlinear optimization problem with a cost function by the present invention, population is used
Meta-heuristic algorithms are solved, and then obtain B-spline curves control point, and population meta-heuristic algorithms combine various population members
The advantages of heuritic approach, there is greater advantage when solving nonlinear optimal problem, and it is more preferable to calculate simple and convergence.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings, in which:
Fig. 1 is the flow chart of AUV paths planning method under the ocean current environment based on population meta-heuristic algorithms；
Fig. 2 is the schematic diagram that control point is fixed in step 1.2 of the invention；
Fig. 3 is the present invention only comprising the route programming result schematic diagram in ocean current information environment；
Fig. 4 is the present invention comprising the route programming result schematic diagram in barrier and ocean current information environment；
Fig. 5 is time and the cost stability analysis figure that the present invention runs 200 times.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention, i.e. described embodiment is a part of the embodiments of the present invention, instead of all the embodiments.It is logical
It is often described herein as to arrange and designing with a variety of different configurations with the component of the embodiment of the present invention shown in the accompanying drawings.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art
Member's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
It should be noted that the relational terms of term " first " and " second " or the like be used merely to an entity or
Operation is distinguished with another entity or operation, and without necessarily requiring or implying between these entities or operation, there are any
This actual relationship or sequence.Moreover, the terms "include", "comprise" or its any other variant be intended to it is non-exclusive
Property include so that include a series of elements process, method, article or equipment not only include those elements, but also
Further include other elements that are not explicitly listed, or further include for this process, method, article or equipment it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described
There is also other identical elements in the process, method, article or equipment of element.
AUV paths planning method under ocean current environment based on population meta-heuristic algorithms solves existing AUV path planning
The path of method planning is rough, is difficult to track and track the high problem that consumes energy.
AUV paths planning method under ocean current environment based on population meta-heuristic algorithms, comprising the following steps:
Step 1: initialization population, further according to combine time efficiency, environmental map, AUV ontology movement radius of curvature and
The information constrained cost function of ocean current obtains the initial synthetic cost value of all individuals in entire population；
Step 2: setting population basic operation set and corresponding operation select probability vector；In selected population one by one
Body, reselection operate the corresponding population basic operation of maximum probability in select probability vector, basic using the population to the individual
Operation, and update its integrate-cost value；Above-mentioned process is repeated until traversing entire population, so far completes an iteration；Then, it adjusts
Whole operation select probability vector carries out next iteration, until the number of iterations reaches setting value；
Step 3: after the completion of iteration, select the smallest individual of cost value, i.e. optimum individual, in conjunction with B-spline curves starting point,
Terminal and fixed control point constitute one group of control point, then generate optimal path by this group of control point.
The present invention indicates that the path AUV, the less control point of usage quantity can obtain complicated and light using B-spline curves
Sliding path；Path planning problem is modeled as a nonlinear optimization problem with a cost function, is inspired with population is super
Formula algorithm optimization chooses the control point position of B-spline curves, and population meta-heuristic algorithms combine various population meta-heuristics and calculate
The advantages of method, there is greater advantage when solving nonlinear optimal problem, and it is more preferable to calculate simple and convergence；And then when obtaining meeting
Between efficiency, environmental map, AUV ontology movement radius of curvature and the information constrained optimal path of ocean current, passage path and ocean current
The geometrical relationship of information defines that ocean current is information constrained, reduces the complexity of method；The path finally obtained is continuous, light
It is sliding and meet that ocean current is information constrained, reduce the tracking difficulty and track path energy consumption of robot.
Feature and performance of the invention are described in further detail below with reference to embodiment.
Embodiment one
Presently preferred embodiments of the present invention provides AUV path planning under the ocean current environment based on population meta-heuristic algorithms
Method, as shown in Figure 1, comprising the following steps:
Step 1: initialization population, further according to combine time efficiency, environmental map, AUV ontology movement radius of curvature and
The information constrained cost function of ocean current obtains the initial synthetic cost value of all individuals in entire population；
Step 1.1: the beginning and end in the setting path AUV, connection source and terminal, and M etc. are generated on the line
Branch makees vertical line according to the line of beginning and end on each Along ent, obtains M vertical line, generates i on every vertical linemaxIt is a
Random point, to obtain imaxGroup random point, i-th group of random point are expressed as RPM,i(rp1,i,rp2,i,…rpk,i,…rpM,i, rpk,i
∈R2), i ∈ (1,2 ..., imax)；
Step 1.2: from starting point, the prime direction short distance along AUV increases a fixed control point p1, go out from terminal
Hair, the opposite direction along the termination direction of AUV increase a fixed control point p with short distance2, starting for controlling curve path
Direction and termination direction；
Step 1.3: according to step 1.1 and step 1.2, with starting point, terminal, one group of random point RPM,i(rp1,i,rp2,i,…
rpk,i,…rpM,i, rpk,i∈R2), fixed control point p1With fixed control point p2As the control point of a B-spline curves, then control
The quantity of system point is n, and the position of n=M+4, control point areIn conjunction with curve
Order K obtains the i of discrete point compositionmaxB-spline curves, curvilinear equation are as follows:
Wherein, Bi,K(t) be K B-spline curves basic function；
Step 1.4: by imaxB-spline curves obtain imaxThe path AUV, path representation are as follows:
Wherein, AUV's is towards ψ
Step 1.5: by imaxGroup random point initializes to obtain population, one group of random point RPM,i(rp1,i,rp2,i,…
rpk,i,…rpM,i, rpk,i∈R2) indicate an individual, i.e., one solution xi, wherein individual dimension is M, and individual quantity is
imax, population P are as follows:
That is,
Step 1.6: according to combining, time efficiency, environmental map, AUV ontology movement radius of curvature and ocean current are information constrained
The each individual of cost function calculation initial cost value, the cost function combines time and penalty function, expression formula are as follows:
Wherein, TcostIt is time cost, passage path distance is obtained divided by average speed,
ρcostIt is curvature cost, is obtained by the approximate curvature at each discrete point that adds up,
McostIt is map cost, by adding up, (barrier 1 can be value of each discrete point on map by region
0) it obtains,
OcostThat ocean current is information constrained, by the angle of add up each discrete point path direction and water (flow) direction and water flow to
The product of amount mould obtains, and h is the quantity of discrete point on B-spline curves；
Step 1.7: four initial cost values being normalized respectively, since different cost values is with different
Dimension passes through maximum cost valueWith minimum cost valueTo obtain normalized cost value
Step 1.8: four cost values after normalization are summed by different Weights, available entire population
The initial synthetic cost value of all individuals in P:
Wherein, ω1, ω2, ω3, ω4It is the weight of different cost values, the path AUV integrate-cost value is smaller, and AUV is got in path
It is excellent, AUV path planning problem is modeled as to the minimization problem of a nonlinear cost function；
Step 2: setting population basic operation set and corresponding operation select probability vector；In selected population one by one
Body, reselection operate the corresponding population basic operation of maximum probability in select probability vector, basic using the population to the individual
Operation, and update its integrate-cost value；Above-mentioned process is repeated until traversing entire population, so far completes an iteration；Then, it adjusts
Whole operation select probability vector carries out next iteration, until the number of iterations reaches setting value；
Step 2.1: setting population basic operation set and corresponding operation select probability vector, the population basic operation
It is indicated with o<>, to the solution x of inputt, a new explanation x is exported after an iterationt+1, expression formula is o < xt>=xt+1, described
Population basic operation is random movement, beats over long distances at random, cost value is followed to be less than the individual of itself, follow cost value minimum
Individual, follow history optimized individual or mutation, the population basic operation set, which merges above-mentioned population basic operation, to be indicated
For O- { o1,o2,…,ok, wherein each population basic operation corresponds to an operation select probability vector, the operation selection is general
Rate vector is P- { p1,p2,...,pk, in which:
The random movement refers to mobile solution xiTo its neighborhood, expression formula are as follows: xi:=xi+λminRandu, wherein
λminIt is the step-length of centralization search,It is to obey equally distributed random number, u is random units direction vector；
The random long range bounce refers to mobile solution xiTo remote position, expression formula are as follows: xi:=xi+λmaxU,
In, λmaxIt is the step-length of diversification search, u is the vector in random units direction；
It is described to follow cost value to be less than itself individual and refer to solve xiIt is less than x to all cost valuesiSolution it is mobile, expression
Formula are as follows: xi:=xi+λ·rand·(xj-xi), meet f (x for allj) < f (xi) solution xj, solve xiIt will be moved to it；
It is described to follow the smallest individual of cost value to refer to solve xiSolution the smallest to cost value that is, optimal is mobile,
Expression formula are as follows: xi:=xi+λ·rand·(xb-xi), wherein xbIt is the solution that the optimum individual in population indicates；
It is described to follow history optimized individual to refer to solve xiIt is the smallest in the multiple cost values obtained after repeatedly evolving to it
Individual, that is, the position of history optimized individual are mobile, expression formula are as follows:Wherein,Table
Show solution xiHistory optimum position；
The mutation, which refers to, will solve xiMutation obtains a new explanation xi′；
Step 2.2: the individual in selection step 1.5 population P, reselection operate maximum probability in select probability vector
Corresponding population basic operation oi；
Step 2.3: population basic operation o is used to the individual that step 2.2 selectsi, and according to step 1.6 to 1.8, it updates
The integrate-cost value of current individual；
Step 2.4: repeating step 2.2 and 2.3, until traversing entire population, a population base is used to each individual
This operation oiLater, an iteration is so far completed；
Step 2.5: the operating condition of the iteration of appraisal procedure 2.4, and adjust operation select probability vector after, return step
2.2 carry out next iteration, and until the number of iterations reaches setting value, the operating condition of the iteration of the appraisal procedure 2.4 refers to
Guarantee that centralization index and index of diversification reach balance；The centralization index is commented by cost value best before and after iteration
Estimate, i.e. basisWithSize relation determine；The distance that the index of diversification passes through all solutions and center solution
The sum of assess, formula are as follows:Wherein, center solvesI.e. according to dt-1And dt's
Size relation determines；The incremental relationship of the centralization index and index of diversification is as shown in table 1,
Table 1
According to upper table it is found that when assessing iteration operating condition, ifThen explanation is in this time iteration
Middle centralization index is higher, if d simultaneouslyt-1> dt, then it is smaller to illustrate that there is also index of diversification in this time iteration, therefore,
It needs to reduce centralization index, increases index of diversification, after accordingly adjusting select probability, return again to step 2.2 and continue
Iteration；Other situations correspond to after table 1 is adjusted select probability, and return step 2.2 continues iteration.
Step 3: after the completion of iteration, select the smallest individual of cost value, i.e. optimum individual, in conjunction with B-spline curves starting point,
Terminal and fixed control point constitute one group of control point, then generate optimal path by this group of control point.
Apply the present invention to only comprising in ocean current information environment, the path cooked up is as shown in Figure 3；The present invention is applied
In comprising barrier and ocean current information environment, the path cooked up is as shown in Figure 4；As can be seen that obtained path is continuous
, it is smooth, the tracking difficulty of AUV can be reduced.
During the experiment, the record present invention runs 200 time stabilities and cost stability, makes such as Fig. 5 institute
The analysis chart shown, it is seen that runing time concentrates between 0.6s to 0.64s, occurs two on maximum value and minimum value range
A exceptional value, but all within 0.66s；Final cost value concentrates between 610 to 635, occurs on maximum value 635
Three exceptional values, but all within 655, it follows that stability of the invention is preferable, the path of practical AUV can be applied to
In planning process.
In conclusion the present invention indicates the path AUV using B-spline curves, the less control point of usage quantity can be obtained
To complicated and smooth path；Path planning problem is modeled as a nonlinear optimization problem with a cost function, is used
The control point position of population meta-heuristic algorithms optimum option B-spline curves, population meta-heuristic algorithms combine various populations
The advantages of meta-heuristic algorithm, there is greater advantage when solving nonlinear optimal problem, and it is more preferable to calculate simple and convergence；In turn
It obtains meeting time efficiency, environmental map, AUV ontology movement radius of curvature and the information constrained optimal path of ocean current, only passes through
The geometrical relationship of path and ocean current information defines that ocean current is information constrained, reduces the complexity of method；The path finally obtained
It is continuous, smooth and meets that ocean current is information constrained, reduces the tracking difficulty and track path energy consumption of robot.
The foregoing is merely illustrative of the preferred embodiments of the present invention, the protection scope being not intended to limit the invention, any
Those skilled in the art within the spirit and principles in the present invention made by any modifications, equivalent replacements, and improvements etc.,
It should all be included in the protection scope of the present invention.
Claims (5)
1. AUV paths planning method under the ocean current environment based on population meta-heuristic algorithms, which is characterized in that including following step
It is rapid:
Step 1: initialization population moves radius of curvature and ocean current further according to time efficiency, environmental map, AUV ontology is combined
Information constrained cost function obtains the initial synthetic cost value of all individuals in entire population；
Step 2: setting population basic operation set and corresponding operation select probability vector；An individual in selected population,
Reselection operates the corresponding population basic operation of maximum probability in select probability vector, is grasped substantially to the individual using the population
Make, and updates its integrate-cost value；Above-mentioned process is repeated until traversing entire population, so far completes an iteration；Then, it adjusts
Select probability vector is operated, next iteration is carried out, until the number of iterations reaches setting value；
Step 3: after the completion of iteration, selecting the smallest individual of cost value, i.e. optimum individual, starting point, terminal in conjunction with B-spline curves
One group of control point is constituted with fixed control point, then optimal path is generated by this group of control point.
2. AUV paths planning method under the ocean current environment according to claim 1 based on population meta-heuristic algorithms, special
Sign is, the specific steps of the step 1 are as follows:
Step 1.1: the beginning and end in the setting path AUV, connection source and terminal, and M Along ent is generated on the line,
Vertical line is made according to the line of beginning and end on each Along ent, M vertical line is obtained, generates i on every vertical linemaxIt is a random
Point, to obtain imaxGroup random point, i-th group of random point are expressed as RPM,i(rp1,i,rp2,i,…rpk,i,…rpM,i, rpk,i∈
R2), i ∈ (1,2 ..., imax)；
Step 1.2: from starting point, the prime direction short distance along AUV increases a fixed control point p1, from terminal, edge
The opposite direction in the termination direction of AUV increases a fixed control point p with short distance2, prime direction for controlling curve path
With termination direction；
Step 1.3: according to step 1.1 and step 1.2, with starting point, terminal, one group of random point RPM,i(rp1,i,rp2,i,…
rpk,i,…rpM,i, rpk,i∈R2), fixed control point p1With fixed control point p2As the control point of a B-spline curves, then control
The quantity of system point is n, and the position of n=M+4, control point areIn conjunction with curve
Order K obtains the i of discrete point compositionmaxB-spline curves, curvilinear equation are as follows:
Wherein, Bi,K(t) be K B-spline curves basic function；
Step 1.4: by imaxB-spline curves obtain imaxThe path AUV, path representation are as follows:
Wherein, AUV towards ψ are as follows:
Step 1.5: by imaxGroup random point initializes to obtain population, one group of random point RPM,i(rp1,i,rp2,i,…rpk,i,…
rpM,i, rpk,i∈R2) indicate an individual, i.e., one solution xi, wherein individual dimension is M, and individual quantity is imax, population P
Are as follows:
That is,
Step 1.6: according to combining time efficiency, environmental map, AUV ontology movement radius of curvature and ocean current information constrained generation
Valence function calculates the initial cost value of each individual, and the cost function combines time and penalty function, expression formula are as follows:
Wherein, TcostIt is time cost, passage path distance is obtained divided by average speed,
ρcostIt is curvature cost, is obtained by the approximate curvature at each discrete point that adds up,
McostIt is map cost, by adding up, (barrier 1 can be 0) to obtain by region to value of each discrete point on map
It arrives,
OcostIt is that ocean current is information constrained, passes through the angle and water flow vector mould of add up each discrete point path direction and water (flow) direction
Product obtain, h is the quantity of discrete point on B-spline curves；
Step 1.7: four initial cost values being normalized respectively, since different cost values has different amounts
Guiding principle passes through maximum cost valueWith minimum cost valueTo obtain normalized cost value
Step 1.8: four cost values after normalization being summed by different Weights, in available entire population P
The initial synthetic cost value of all individuals:
Wherein, ω1, ω2, ω3, ω4It is the weight of different cost values.
3. AUV paths planning method under the ocean current environment according to claim 1 based on population meta-heuristic algorithms, special
Sign is, the specific steps of the step 2 are as follows:
Step 2.1: setting population basic operation set and corresponding operation select probability vector, the population basic operation o
<>indicates, to the solution x of inputt, a new explanation x is exported after an iterationt+1, expression formula is o < xt>=xt+1, described kind
Group's basic operation is random movement, beats over long distances at random, cost value is followed to be less than the individual of itself, follow cost value the smallest
Individual follows history optimized individual or mutation, and above-mentioned population basic operation merging is expressed as by the population basic operation set
O-{o1,o2,…,ok, wherein each population basic operation corresponds to an operation select probability vector, the operation select probability
Vector is P- { p1,p2,...,pk}；
Step 2.2: the individual in selection step 1.5 population P, it is corresponding that reselection operates maximum probability in select probability vector
Population basic operation oi；
Step 2.3: population basic operation o is used to the individual that step 2.2 selectsi, and according to step 1.6 to 1.8, it updates current
The integrate-cost value of individual；
Step 2.4: repeating step 2.2 and 2.3, until traversing entire population, each individual is grasped using a population substantially
Make oiLater, an iteration is so far completed；
Step 2.5: the operating condition of the iteration of appraisal procedure 2.4, and adjust operation select probability vector after, return step 2.2
Next iteration is carried out, until the number of iterations reaches setting value.
4. AUV paths planning method under the ocean current environment according to claim 3 based on population meta-heuristic algorithms, special
Sign is, in the step 2.1:
The random movement refers to mobile solution xiTo its neighborhood, expression formula are as follows: xi:=xi+λminRandu, wherein λminIt is
The step-length of centralization search,It is to obey equally distributed random number, u is random units direction vector；
The random long range bounce refers to mobile solution xiTo remote position, expression formula are as follows: xi:=xi+λmaxU, wherein
λmaxIt is the step-length of diversification search, u is random units direction vector；
It is described to follow cost value to be less than itself individual and refer to solve xiIt is less than x to all cost valuesiSolution it is mobile, expression formula are as follows:
xi:=xi+λ·rand·(xj-xi), meet f (x for allj) < f (xI) solution xj, solve xiIt will be moved to it；
It is described to follow the smallest individual of cost value to refer to solve xiSolution the smallest to cost value that is, optimal is mobile, expression formula
Are as follows: xi:=xi+λ·rand·(xb-xi), wherein xbIt is the solution that the optimum individual in population indicates；
It is described to follow history optimized individual to refer to solve xiThe smallest individual in the multiple cost values obtained after repeatedly evolving to it,
The position of namely history optimized individual is mobile, expression formula are as follows:Wherein,Indicate solution
xiHistory optimum position；
The mutation, which refers to, will solve xiMutation obtains a new explanation xi′。
5. AUV paths planning method under the ocean current environment according to claim 3 based on population meta-heuristic algorithms, special
Sign is that the operating condition of the iteration of the appraisal procedure 2.4 in the step 2.5 refers to centralization index to be guaranteed and diversification
Index reaches balance, and the centralization index is assessed by cost value best before and after iteration, i.e. basisWith's
Size relation determines；The index of diversification is assessed by the sum of the distance of all solutions and center solution, formula are as follows:Wherein, center solvesI.e. according to dt-1And dtSize relation determine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910209731.XA CN109782779B (en) | 2019-03-19 | 2019-03-19 | AUV path planning method in ocean current environment based on population hyperheuristic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910209731.XA CN109782779B (en) | 2019-03-19 | 2019-03-19 | AUV path planning method in ocean current environment based on population hyperheuristic algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109782779A true CN109782779A (en) | 2019-05-21 |
| CN109782779B CN109782779B (en) | 2020-11-06 |
Family
ID=66488419
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910209731.XA Active CN109782779B (en) | 2019-03-19 | 2019-03-19 | AUV path planning method in ocean current environment based on population hyperheuristic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109782779B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110187707A (en) * | 2019-05-30 | 2019-08-30 | 北京三快在线科技有限公司 | Planing method, device and the unmanned equipment of unmanned equipment running track |
| CN110347357A (en) * | 2019-07-15 | 2019-10-18 | 北大方正集团有限公司 | Print processing method and device |
| CN110658833A (en) * | 2019-09-18 | 2020-01-07 | 沈阳航空航天大学 | Multi-AUV real-time rescue task allocation algorithm in underwater environment |
| CN110779526A (en) * | 2019-09-29 | 2020-02-11 | 宁波海上鲜信息技术有限公司 | Path planning method, device and storage medium |
| CN111174790A (en) * | 2019-12-03 | 2020-05-19 | 河海大学 | Method for forming topographic profile tracking path |
| CN111259526A (en) * | 2020-01-09 | 2020-06-09 | 鹏城实验室 | Cluster recovery path planning method, device and equipment and readable storage medium |
| CN111307158A (en) * | 2020-03-19 | 2020-06-19 | 哈尔滨工程大学 | AUV three-dimensional route planning method |
| CN112068577A (en) * | 2020-09-24 | 2020-12-11 | 哈尔滨工程大学 | Green dynamic position control method for UUV individuals in UUV cluster |
| CN112612290A (en) * | 2020-12-06 | 2021-04-06 | 西北工业大学 | Underwater vehicle three-dimensional multi-task path planning method considering ocean currents |
| CN112925317A (en) * | 2021-01-25 | 2021-06-08 | 中国人民解放军海军工程大学 | AUV path planning method based on improved brainstorming optimization algorithm |
| CN113110530A (en) * | 2021-04-16 | 2021-07-13 | 大连海事大学 | Underwater robot path planning method for three-dimensional environment |
| CN115077534A (en) * | 2022-08-11 | 2022-09-20 | 合肥井松智能科技股份有限公司 | AGV path planning method based on B spline curve |
| CN115357032A (en) * | 2022-10-20 | 2022-11-18 | 上海仙工智能科技有限公司 | NURBS-based mobile robot path generation method, system and storage medium |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| UST941005I4 (en) * | 1974-08-20 | 1975-12-02 | Examine all blocks in column | |
| EP0526969A2 (en) * | 1991-06-12 | 1993-02-10 | Hughes Aircraft Company | Tactical route planning method for use in simulated tactical engagements |
| US20080313113A1 (en) * | 2005-12-13 | 2008-12-18 | Singapore Technologies Dynamics Pte Ltd | Method and Apparatus for an Algorithm Development Environment for Solving a Class of Real-Life Combinatorial Optimization Problems |
| GB2458077A (en) * | 2006-12-22 | 2009-09-09 | Singapore Tech Dynamics Pte | Method and apparatus for automatic configuration of meta-heuristic algorithms in a problem solving environment |
| CN101604166A (en) * | 2009-07-10 | 2009-12-16 | 杭州电子科技大学 | A kind of method for planning path for mobile robot based on particle swarm optimization algorithm |
| CN101837591A (en) * | 2010-03-12 | 2010-09-22 | 西安电子科技大学 | Robot path planning method based on two cooperative competition particle swarms and Ferguson spline |
| CN103077425A (en) * | 2012-11-23 | 2013-05-01 | 中国科学院沈阳自动化研究所 | Immune genetic algorithm for AUV (Autonomous Underwater Vehicle) real-time path planning |
| CN103464344A (en) * | 2013-09-23 | 2013-12-25 | 电子科技大学中山学院 | Economical spraying robot spray gun track planning method |
| US20140105372A1 (en) * | 2012-10-15 | 2014-04-17 | Twilio, Inc. | System and method for routing communications |
| CN103823466A (en) * | 2013-05-23 | 2014-05-28 | 电子科技大学 | Path planning method for mobile robot in dynamic environment |
| CN103968841A (en) * | 2014-06-03 | 2014-08-06 | 哈尔滨工程大学 | Improved fireflyalgorithm based AUV (autonomous underwater vehicle) three-dimensional track planning method |
| CN104133476A (en) * | 2014-07-31 | 2014-11-05 | 四川阿泰因机器人智能装备有限公司 | Self-adaption path tracking method of inspection robot |
| CN104809523A (en) * | 2015-05-07 | 2015-07-29 | 北京理工大学 | Workpiece production path searching method based on decision blocks and swarm algorithm |
| CN107229287A (en) * | 2017-06-28 | 2017-10-03 | 中国人民解放军海军工程大学 | A kind of unmanned plane global path planning method based on Genetic Ant algorithm |
| CN107368086A (en) * | 2017-07-04 | 2017-11-21 | 哈尔滨工程大学 | The autonomous underwater vehicle path planning apparatus and method in domain are threatened based on detection |
| CN108508893A (en) * | 2018-03-23 | 2018-09-07 | 西安电子科技大学 | A kind of robot efficiency optimum path planning method based on improvement A algorithm |
| CN109062227A (en) * | 2018-09-25 | 2018-12-21 | 电子科技大学 | A kind of more curve local paths planning methods based on dynamic window |
| CN109471446A (en) * | 2018-11-08 | 2019-03-15 | 淮阴师范学院 | A kind of complete coverage path planning method neural network based |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US941005A (en) * | 1906-03-24 | 1909-11-23 | Brandt Company | Designating, recording, and registering mechanism. |
-
2019
- 2019-03-19 CN CN201910209731.XA patent/CN109782779B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| UST941005I4 (en) * | 1974-08-20 | 1975-12-02 | Examine all blocks in column | |
| EP0526969A2 (en) * | 1991-06-12 | 1993-02-10 | Hughes Aircraft Company | Tactical route planning method for use in simulated tactical engagements |
| US20080313113A1 (en) * | 2005-12-13 | 2008-12-18 | Singapore Technologies Dynamics Pte Ltd | Method and Apparatus for an Algorithm Development Environment for Solving a Class of Real-Life Combinatorial Optimization Problems |
| GB2458077A (en) * | 2006-12-22 | 2009-09-09 | Singapore Tech Dynamics Pte | Method and apparatus for automatic configuration of meta-heuristic algorithms in a problem solving environment |
| CN101604166A (en) * | 2009-07-10 | 2009-12-16 | 杭州电子科技大学 | A kind of method for planning path for mobile robot based on particle swarm optimization algorithm |
| CN101837591A (en) * | 2010-03-12 | 2010-09-22 | 西安电子科技大学 | Robot path planning method based on two cooperative competition particle swarms and Ferguson spline |
| US20140105372A1 (en) * | 2012-10-15 | 2014-04-17 | Twilio, Inc. | System and method for routing communications |
| CN103077425A (en) * | 2012-11-23 | 2013-05-01 | 中国科学院沈阳自动化研究所 | Immune genetic algorithm for AUV (Autonomous Underwater Vehicle) real-time path planning |
| CN103823466A (en) * | 2013-05-23 | 2014-05-28 | 电子科技大学 | Path planning method for mobile robot in dynamic environment |
| CN103464344A (en) * | 2013-09-23 | 2013-12-25 | 电子科技大学中山学院 | Economical spraying robot spray gun track planning method |
| CN103968841A (en) * | 2014-06-03 | 2014-08-06 | 哈尔滨工程大学 | Improved fireflyalgorithm based AUV (autonomous underwater vehicle) three-dimensional track planning method |
| CN104133476A (en) * | 2014-07-31 | 2014-11-05 | 四川阿泰因机器人智能装备有限公司 | Self-adaption path tracking method of inspection robot |
| CN104809523A (en) * | 2015-05-07 | 2015-07-29 | 北京理工大学 | Workpiece production path searching method based on decision blocks and swarm algorithm |
| CN107229287A (en) * | 2017-06-28 | 2017-10-03 | 中国人民解放军海军工程大学 | A kind of unmanned plane global path planning method based on Genetic Ant algorithm |
| CN107368086A (en) * | 2017-07-04 | 2017-11-21 | 哈尔滨工程大学 | The autonomous underwater vehicle path planning apparatus and method in domain are threatened based on detection |
| CN108508893A (en) * | 2018-03-23 | 2018-09-07 | 西安电子科技大学 | A kind of robot efficiency optimum path planning method based on improvement A algorithm |
| CN109062227A (en) * | 2018-09-25 | 2018-12-21 | 电子科技大学 | A kind of more curve local paths planning methods based on dynamic window |
| CN109471446A (en) * | 2018-11-08 | 2019-03-15 | 淮阴师范学院 | A kind of complete coverage path planning method neural network based |
Non-Patent Citations (6)
| Title |
|---|
| BURKE, EDMUND K; GENDREAU, MICHEL; HYDE, MATTHEW; KENDALL, GRAHA: "Hyper-heuristics: a survey of the state of the art", 《THE JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY》 * |
| SHENG LIANG，QIU ZHI-MING, LI HENG: "A Survey on Route Planning Methods of AUV Considering Influence of Ocean Current", 《2018 IEEE 4TH INTERNATIONAL CONFERENCE ON CONTROL SCIENCE AND SYSTEMS ENGINEERING》 * |
| 孙海涛等: "基于启发式算法障碍环境中ＡＵＶ路径规划方法研究", 《水雷战与船舰防护》 * |
| 李晔等: "考虑几何约束的AUV回收路径规划", 《机器人》 * |
| 李红等: "洋流影响下的AUV地磁仿生导航方法研究", 《地球物理学进展》 * |
| 杨俊成等: "路径规划算法的研究与发展", 《控制工程》 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110187707A (en) * | 2019-05-30 | 2019-08-30 | 北京三快在线科技有限公司 | Planing method, device and the unmanned equipment of unmanned equipment running track |
| CN110187707B (en) * | 2019-05-30 | 2022-05-10 | 北京三快在线科技有限公司 | Unmanned equipment running track planning method and device and unmanned equipment |
| CN110347357A (en) * | 2019-07-15 | 2019-10-18 | 北大方正集团有限公司 | Print processing method and device |
| CN110658833A (en) * | 2019-09-18 | 2020-01-07 | 沈阳航空航天大学 | Multi-AUV real-time rescue task allocation algorithm in underwater environment |
| CN110658833B (en) * | 2019-09-18 | 2022-06-14 | 沈阳航空航天大学 | Multi-AUV real-time rescue task allocation algorithm in underwater environment |
| CN110779526A (en) * | 2019-09-29 | 2020-02-11 | 宁波海上鲜信息技术有限公司 | Path planning method, device and storage medium |
| CN111174790A (en) * | 2019-12-03 | 2020-05-19 | 河海大学 | Method for forming topographic profile tracking path |
| CN111259526A (en) * | 2020-01-09 | 2020-06-09 | 鹏城实验室 | Cluster recovery path planning method, device and equipment and readable storage medium |
| CN111259526B (en) * | 2020-01-09 | 2023-08-18 | 鹏城实验室 | Cluster recovery path planning method, device, equipment and readable storage medium |
| CN111307158A (en) * | 2020-03-19 | 2020-06-19 | 哈尔滨工程大学 | AUV three-dimensional route planning method |
| CN112068577A (en) * | 2020-09-24 | 2020-12-11 | 哈尔滨工程大学 | Green dynamic position control method for UUV individuals in UUV cluster |
| CN112612290A (en) * | 2020-12-06 | 2021-04-06 | 西北工业大学 | Underwater vehicle three-dimensional multi-task path planning method considering ocean currents |
| CN112612290B (en) * | 2020-12-06 | 2023-03-07 | 西北工业大学 | Underwater vehicle three-dimensional multi-task path planning method considering ocean currents |
| CN112925317A (en) * | 2021-01-25 | 2021-06-08 | 中国人民解放军海军工程大学 | AUV path planning method based on improved brainstorming optimization algorithm |
| CN112925317B (en) * | 2021-01-25 | 2022-05-17 | 中国人民解放军海军工程大学 | AUV path planning method based on improved brainstorming optimization algorithm |
| CN113110530A (en) * | 2021-04-16 | 2021-07-13 | 大连海事大学 | Underwater robot path planning method for three-dimensional environment |
| CN113110530B (en) * | 2021-04-16 | 2023-11-21 | 大连海事大学 | Underwater robot path planning method for three-dimensional environment |
| CN115077534B (en) * | 2022-08-11 | 2022-11-15 | 合肥井松智能科技股份有限公司 | AGV path planning method based on B spline curve |
| CN115077534A (en) * | 2022-08-11 | 2022-09-20 | 合肥井松智能科技股份有限公司 | AGV path planning method based on B spline curve |
| CN115357032A (en) * | 2022-10-20 | 2022-11-18 | 上海仙工智能科技有限公司 | NURBS-based mobile robot path generation method, system and storage medium |
| CN115357032B (en) * | 2022-10-20 | 2023-01-31 | 上海仙工智能科技有限公司 | NURBS-based mobile robot path generation method, system and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109782779B (en) | 2020-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109782779A (en) | AUV paths planning method under ocean current environment based on population meta-heuristic algorithms | |
| Sang et al. | The hybrid path planning algorithm based on improved A* and artificial potential field for unmanned surface vehicle formations | |
| Kala et al. | Fusion of probabilistic A* algorithm and fuzzy inference system for robotic path planning | |
| Yang et al. | A new robot navigation algorithm based on a double-layer ant algorithm and trajectory optimization | |
| Quan et al. | Survey of UAV motion planning | |
| Jun et al. | Multi-objective mobile robot path planning based on improved genetic algorithm | |
| Rao et al. | Large-scale path planning for underwater gliders in ocean currents | |
| CN109542106A (en) | A kind of paths planning method under mobile robot multi-constraint condition | |
| Hildebrandt et al. | Real-time path planning in unknown environments for bipedal robots | |
| CN110045732B (en) | Heuristic path planning method | |
| CN110333659A (en) | A kind of pilotless automobile local paths planning method based on improvement A star search | |
| CN113848919A (en) | Ant colony algorithm-based indoor AGV path planning method | |
| Guo et al. | The path planning for mobile robot based on bat algorithm | |
| Geetha et al. | Multi objective mobile robot path planning based on hybrid algorithm | |
| Yang et al. | LF-ACO: an effective formation path planning for multi-mobile robot | |
| Liu et al. | Cooperative path planning for multi-AUV in time-varying ocean flows | |
| Premebida et al. | Applying probabilistic mixture models to semantic place classification in mobile robotics | |
| Hsu et al. | Path planning for mobile robots based on improved ant colony optimization | |
| CN112859855A (en) | Robot multi-target path planning based on locust optimization algorithm | |
| Silva et al. | Online social robot navigation in indoor, large and crowded environments | |
| Sudhakara et al. | Probabilistic roadmaps-spline based trajectory planning for wheeled mobile robot | |
| Zhang et al. | Mi-rrt-connect algorithm for quadruped robotics navigation with efficiently path planning | |
| CN115951682A (en) | Constraint four-target AUV global path planning method under condition of considering ocean current existence | |
| Hadi Amoozgar et al. | A fuzzy logic‐based formation controller for wheeled mobile robots | |
| Wang et al. | Improved A* algorithm and model predictive control-based path planning and tracking framework for hexapod robots |
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 |