CN112161627A - Intelligent path planning method for fire-fighting robot - Google Patents
Intelligent path planning method for fire-fighting robot Download PDFInfo
- Publication number
- CN112161627A CN112161627A CN202011012951.2A CN202011012951A CN112161627A CN 112161627 A CN112161627 A CN 112161627A CN 202011012951 A CN202011012951 A CN 202011012951A CN 112161627 A CN112161627 A CN 112161627A
- Authority
- CN
- China
- Prior art keywords
- fire
- path
- improved
- ant colony
- colony algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 239000003016 pheromone Substances 0.000 claims abstract description 81
- 230000004888 barrier function Effects 0.000 claims abstract description 47
- 230000008569 process Effects 0.000 claims abstract description 23
- 230000001629 suppression Effects 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000012546 transfer Methods 0.000 claims abstract description 4
- 150000001875 compounds Chemical class 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 3
- 230000006872 improvement Effects 0.000 claims description 3
- 238000007789 sealing Methods 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 2
- 230000003247 decreasing effect Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 abstract description 4
- 238000004088 simulation Methods 0.000 abstract 1
- 241000257303 Hymenoptera Species 0.000 description 7
- 238000005457 optimization Methods 0.000 description 5
- 230000007547 defect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000009024 positive feedback mechanism Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/10—Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Automation & Control Theory (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Graphics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to an intelligent path planning method for a fire-fighting robot, which comprises the following steps: preprocessing according to the fire scene space environment information of the fire-fighting robot; constructing a concave-convex polygonal barrier fire scene space environment model according to the extended MAKLINK graph theory; planning an initial path by adopting a Dijkstra algorithm according to the stationing point and the fire suppression point of the fire-fighting robot; and introducing a self-adaptive dynamic adjustment strategy of pheromones and heuristic values based on the fire scene space environment model and the initial path, and performing iterative search on path nodes in the ant transfer process by using an improved ant colony algorithm to finally obtain an optimal planning path. The method combines the advantages of the expanded MAKLINK graph theory and the improved ant colony algorithm, can realize optimal path planning in the complex fire scene space environment containing the concave-convex polygonal obstacles, and has high algorithm convergence speed and strong path planning capability; in addition, the invention verifies the feasibility and the effectiveness of the provided technical scheme through a simulation test.
Description
Technical Field
The invention relates to the field of path planning of fire-fighting robots, in particular to an intelligent path planning method for a fire-fighting robot.
Background
The fire-fighting robot is used as a special fire-fighting device, can enter a fire scene with high danger, harsh environment and the like, which is not easy to be approached by firemen, to execute various fire reconnaissance tasks, and carries out corresponding fire rescue operation. The fire-fighting robot is put into use, can obviously improve the ability of fire departments to put out serious and malignant fires, and plays an important role in reducing national property loss, fire fighters casualties and the like. In recent years, with the rapid development of professional technologies such as artificial intelligence, information processing, intelligent control and the like, a fire-fighting robot has developed a trend of automation and intellectualization, and gradually becomes a robot comprehensive system capable of autonomously navigating and completing a fire extinguishing task in a fire scene environment.
The path planning is an important component in autonomous navigation research of the fire-fighting robot, and the task of the path planning is to construct an optimal fire suppression path from a parking point to a fire suppression point and bypassing all barriers without collision in a fire scene environment with the barriers. Among the conventional path planning methods, the grid map method, the artificial potential field method, and the topological graph method are most commonly used. Although the grid map method is simple and practical, the size of the grid directly affects the amount of environment information stored and the time taken to plan a path. In the process of path planning, the artificial potential field method may cause a situation that the resultant force is zero, resulting in stopping the robot. The topological graph method has the defects that the algorithm complexity is in direct proportion to the number of obstacles, and the planned path quality is not high.
With the continuous development of the intelligent algorithm, the intelligent algorithms such as fuzzy control, genetic algorithm, particle swarm algorithm and the like also play an important role in solving the path planning problem. However, the rule table of fuzzy control is usually based on expert experience, and cannot be modified in real time, and may have an influence on the result of path planning. The genetic algorithm, the particle swarm algorithm and the like also have the defects of large operation amount, low efficiency, complex coding and the like, influence on fire rescue and have limited practical value.
Disclosure of Invention
The invention aims to provide an intelligent path planning method for a fire-fighting robot, which overcomes the defects that the prior art has high calculation resource consumption and poor self-regulation capability and cannot ensure time-consuming shortest path planning.
The purpose of the invention can be realized by the following technical scheme, comprising the following steps:
and (3) environmental information preprocessing: establishing a world coordinate system according to fire scene space environment information of a fire-fighting robot, describing the edge of an obstacle by adopting a polygon, acquiring the vertex coordinates of the obstacle in the fire scene space environment, and determining a parking point and a fire suppression point of the fire-fighting robot in the world coordinate system;
a fire scene space environment modeling step: constructing a fire scene space environment model by adopting an extended MAKLINK graph theory, wherein the fire scene space environment model comprises a movable path of a fire-fighting robot;
an initial path planning step: based on the fire scene space environment model, planning an initial path by adopting Dijkstra algorithm with the shortest path length as a target according to the determined stationing point and the fire suppression point;
planning an optimal path: initializing a pre-established improved ant colony algorithm based on the fire scene space environment model and the initial path, and performing iterative search on path nodes in the ant transfer process through an introduced pheromone and heuristic value self-adaptive dynamic adjustment strategy until a preset maximum iteration number is reached, thereby finally obtaining an optimal planning path.
Further, in the modeling of the fire scene space environment, the extended MAKLINK graph theory is adopted to construct the fire scene space environment model, specifically, for the convex polygonal barrier, the construction of the fire scene space environment model is directly carried out according to the traditional MAKLINK graph theory; dividing the concave polygonal barrier into an independent outer concave polygonal barrier and a combined inner concave polygonal barrier according to the geometric characteristics of the concave polygonal barrier; filling the independent outer concave polygonal barrier into a convex polygon for processing, and setting the middle point of the filled auxiliary connecting line as a path node; and (3) for the combined concave polygonal barrier, extending and sealing the gap of the combined concave polygonal barrier, setting the middle point of an extension connecting line as a path node, and processing the rest internal structures according to the traditional MAKINK graph theory.
Furthermore, in the iterative search process, the improved heuristic value importance factor definition formula is adopted to realize the self-adaptive dynamic update of the heuristic value. In the initial stage of algorithm iterative search, in order to improve efficiency, avoid blind random free exploration and increase the importance factor of the heuristic value; in the middle stage of iterative search, the concentration of pheromones on part of shorter paths starts to be gradually higher than that of other paths, and at the moment, the importance degree factor of the heuristic value is reduced; in the later stage of iterative search, due to the accumulation of long-time pheromones, the concentration of the pheromones on the shorter path is far higher than that of other paths, and in order to prevent local optimization, the importance degree factor of the heuristic value is increased again. The improved heuristic value importance factor defines an expression of a formula as follows:
in the formula (I), the compound is shown in the specification,for the improved importance factor of the heuristic value in the nth iteration, n is the current iteration number, R is a reference coefficient, nmaxIs the maximum number of iterations.
Further, in the iterative search process, the improved pheromone volatilization parameter definition formula is adopted by the improved ant colony algorithm to perform the self-adaptive dynamic update of the pheromone. At the initial stage of the algorithm, the concentration of the pheromone on each path is low, so that ants can find a better path more quickly and the convergence speed of the algorithm is accelerated, and the numerical value of the pheromone volatilization parameter is required to be large; at the later stage of the algorithm, the pheromone concentration is increasing with time, and the value should be small in order to prevent the global search capability from being reduced. The expression of the improved pheromone volatilization parameter definition formula is as follows:
in the formula (I), the compound is shown in the specification,for the pheromone volatilization parameter at the nth iteration after improvement, lambdamaxIs the maximum value of the pheromone volatilization parameter, lambdaminIs the minimum value of the pheromone volatilization parameter.
Further, in the iterative search process, the improved ant colony algorithm determines the position of the next path node according to the pheromone and the heuristic value, and the expression of the node position determination method is as follows:
in the formula (I), the compound is shown in the specification,i is the set of all the alternative nodes on the jth line of MAKLINK,is a pheromone, xii,k(n) is a heuristic value, q is a random adjustable parameter, and q belongs to [0,1 ]],q0Selecting a threshold value for the pheromone, q0∈[0,1]P is the node position with the highest selection probability determined by the roulette strategy, the selection probabilityThe expression of (a) is:
further, in the iterative search process of the improved ant colony algorithm, after each ant selects a certain path node, local updating needs to be performed on the pheromone of the node, and the expression of the improved local pheromone updating formula is as follows:
in the formula (I), the compound is shown in the specification,0is the initial value of pheromone.
Further, after one iteration search is completed, the improved ant colony algorithm selects one path with the minimum length from all the ants to perform, and updates pheromones of all nodes on the path to increase the probability of being selected again, so as to strengthen a positive feedback mechanism, wherein an expression of the improved global pheromone updating formula is as follows:
Δi,j=1/L*
in the formula, L*Is the current shortest path length.
Compared with the prior art, the invention has the following advantages:
(1) by expanding and supplementing the MAKLINK graph theory, the method can be suitable for the complex fire scene space environment simultaneously containing concave-convex polygonal obstacles;
(2) the improved heuristic value importance factor defines a formula, and in the initial iteration stage of the ant colony algorithm, the heuristic value importance factor is increased, so that the optimization efficiency is improved; in the middle period of iteration, the importance degree factor of the heuristic value is reduced, and the stability of the pheromone concentration on the shorter path is controlled; in the later iteration stage, the importance degree factor of the heuristic value is increased again, so that the situation of local optimum is effectively prevented, and the accuracy of the path planning result is improved;
(3) the improved pheromone volatilization parameter definition formula increases pheromone volatilization parameter values at the initial iteration stage of the ant colony algorithm, so that ants can find a better path more quickly, and the convergence speed of the algorithm is accelerated; in the later iteration stage, the pheromone volatilization parameter value is reduced, so that the reduction of the global search capability is prevented;
(4) the fire-fighting robot intelligent path planning method adopts an extended MAKLINK graph theory to establish a fire scene space environment model, utilizes a Dijkstra algorithm to roughly plan an initial path, then iteratively searches all optimized paths based on an improved ant colony algorithm, plans a shortest length path from a parking point to a fire disaster extinguishing point of the fire-fighting robot, has high algorithm convergence speed, skips over local optimal results, and has strong path planning capability.
Drawings
FIG. 1 is a schematic flow chart of an intelligent path planning method for a fire-fighting robot according to the present invention;
FIG. 2 is a diagram of the MAKLINK line and its midpoint of the fire scene space environment of the concave-convex polygonal barrier in this embodiment;
FIG. 3 is an expanded MAKLINK diagram of the fire scene space environment of the concave-convex polygonal barrier in the present embodiment;
FIG. 4 is a comparison result between the ant colony algorithm and Dijkstra algorithm in the present embodiment;
fig. 5 is a comparison result between the improved ant colony algorithm and the ant colony algorithm in the embodiment.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
Example 1
The embodiment provides an intelligent path planning method for a fire-fighting robot, which comprises the following steps:
and (3) environmental information preprocessing: establishing a world coordinate system according to the fire scene space environment information of the fire-fighting robot, describing the edge of the barrier by adopting a polygon, acquiring the vertex coordinate of the barrier in the fire scene space environment, and determining the parking point and the fire suppression point of the fire-fighting robot in the world coordinate system;
a fire scene space environment modeling step: constructing a fire scene space environment model by adopting an expanded MAKLINK graph theory according to the fire scene space environment information, wherein the fire scene space environment model comprises a movable path of the fire-fighting robot;
an initial path planning step: based on a fire scene space environment model, planning an initial path by adopting Dijkstra algorithm with the shortest path length as a target according to the determined stationing point and the fire suppression point;
planning an optimal path: initializing a pre-established ant colony algorithm based on a fire scene space environment model and an initial path, performing iterative search on path nodes in an ant transfer process until a preset maximum iteration number is reached, and finally obtaining an optimal planning path.
As a preferred embodiment, in the modeling of the fire scene space environment, an extended MAKLINK graph theory is adopted to construct the fire scene space environment model, specifically, for a convex polygonal barrier, the construction of the fire scene space environment model is directly carried out according to the traditional MAKLINK graph theory; dividing the concave polygonal barrier into an independent outer concave polygonal barrier and a combined inner concave polygonal barrier according to the geometric characteristics of the concave polygonal barrier; for the independent outer concave polygon barrier, filling the independent outer concave polygon barrier into a convex polygon through an auxiliary connecting line for processing, and setting the middle point of the auxiliary connecting line as a path node; and for the combined concave polygonal barrier, the notch of the combined concave polygonal barrier is extended and sealed through an extension connecting line, the midpoint of the extension connecting line is set as a path node, and other internal structures are processed according to the traditional MAKINK graph theory.
In a preferred embodiment, the independent outer concave polygonal barrier is a single concave polygonal barrier, and the combined inner concave polygonal barrier is formed by combining a plurality of barriers.
As a preferred implementation, the ant colony algorithm adopts an improved ant colony algorithm, and the improved ant colony algorithm adopts an improved heuristic value importance factor definition formula in an iterative search process to realize the self-adaptive dynamic update of the heuristic value;
the improved heuristic value importance factor definition formula enables the heuristic value importance factor to be increased, then decreased and finally increased along with the iterative search process of the improved ant colony algorithm.
As a preferred embodiment, the improved heuristic importance factor defines the expression of the formula:
in the formula (I), the compound is shown in the specification,for the improved importance factor of the heuristic value in the nth iteration, n is the current iteration number, R is a reference coefficient, nmaxIs the maximum number of iterations.
As a preferred embodiment, the ant colony algorithm adopts an improved ant colony algorithm, and the improved ant colony algorithm adopts an improved pheromone volatilization parameter definition formula to perform self-adaptive dynamic update of pheromones in an iterative search process;
the improved pheromone volatilization parameter definition formula enables pheromone volatilization parameters to have a variation trend of becoming larger and smaller along with the iterative search process of the improved ant colony algorithm.
As a preferred embodiment, the modified pheromone volatilization parameter defines the formula as follows:
in the formula (I), the compound is shown in the specification,for the pheromone volatilization parameter at the nth iteration after improvement, lambdamaxIs the maximum value of the pheromone volatilization parameter, lambdaminIs the minimum value of the pheromone volatilization parameter.
As a preferred embodiment, the ant colony algorithm is an improved ant colony algorithm, and the improved ant colony algorithm determines the position of the next path node according to the pheromone and the heuristic value in the iterative search process, and the expression of the method for determining the position of the next path node is as follows:
in the formula (I), the compound is shown in the specification,i is the position of the next path node, I is the set of all the alternative nodes on the jth line of MAKLINK,is the pheromone xi from node i to node k at the nth iterationi,k(n) is the heuristic value of node i to node k at the nth iteration,is an importance factor of the heuristic value during the nth iteration, q is a random adjustable parameter, and q belongs to [0,1 ]],q0Selecting a threshold value for the pheromone, q0∈[0,1]And P is the node position with the maximum selection probability determined by the roulette strategy, and the expression of the selection probability is as follows:
in the formula (I), the compound is shown in the specification,the selection probabilities for nodes i through j.
As a preferred embodiment, the ant colony algorithm is an improved ant colony algorithm, the improved ant colony algorithm updates the local pheromone by using an improved local pheromone update formula, and an expression of the improved local pheromone update formula is as follows:
in the formula (I), the compound is shown in the specification,0is the initial value of the pheromone and is,is the pheromone volatilization parameter at the nth iteration,for the pheromones from node i to node j at the nth iteration,the pheromones from node i to node j in the (n + 1) th iteration.
As a preferred embodiment, the ant colony algorithm is an improved ant colony algorithm, the improved ant colony algorithm updates the global pheromone by using an improved global pheromone update formula, and the expression of the improved global pheromone update formula is as follows:
Δi,j=1/L*
in the formula, L*For the length of the current shortest path,is the pheromone volatilization parameter at the nth iteration,for the pheromones from node i to node j at the nth iteration,the pheromones from node i to node j in the (n + 1) th iteration.
The embodiment also provides an optimal implementation method, which includes the following specific implementation processes:
the flow of the fire-fighting robot intelligent path planning method based on the extended MAKLINK graph theory and the improved ant colony algorithm is shown in fig. 1, and specifically comprises the following steps:
s1: construction of fire scene space environment model
S11: the MAKLINK graph theory is an environment modeling method for constructing free space, and an obstacle is defined as a convex polygon;
s12: constructing a MAKLINK line in the space environment, wherein the MAKLINK line is a connecting line between the vertexes of two polygonal barriers or a vertical connecting line from the vertexes of one polygonal barrier to the boundary of the space environment;
s13: aiming at the defect that the traditional MAKLINK graph theory is only suitable for the fire scene space environment containing convex polygonal obstacles, necessary extension and supplement are carried out on the traditional MAKLINK graph theory. Filling independent outer concave polygons (such as hexagons in the middle of fig. 2) into convex polygons; extending and sealing the gap of the combined concave polygon (such as the combined polygon at the lower right corner of fig. 2), setting the center of an extension line as a path node, and processing the rest internal structures according to a traditional MAKLINK graph theory method;
the independent outer concave polygonal barrier is a single concave polygonal barrier, and the combined inner concave polygonal barrier is formed by combining a plurality of barriers.
S14: the middle points of all the MAKLINK lines, the stationer S and the fire suppression point T are connected, namely the space environment of the fire scene is represented as an expanded MAKLINK diagram as shown in figure 3. Each free connecting line represents a movable path of the fire fighting robot.
S2: preliminary planning fire fighting path
Roughly planning a path node S and U in turn in an extended MAKLINK graph by utilizing a Dijkstra algorithm1,U2,…,UtAnd T, initial path.
S21: establishing a set V containing all nodes with shortest paths to be determined, and a set U containing all nodes with shortest paths to be determined; setting the initial path length from the stationing point to be zero, setting the initial path length from the stationing point to other nodes to be infinite, and storing the initial value in a starting point adjacent path length array Len.
S22: and selecting the node i with the shortest path length from the set V, and setting the node i as the current node.
S23: according toFinding out the adjacent connected node j of the current node i by the expanded MAKLINK graph, and calculating the distance l from the node i to the node jij(ii) a According to the calculation result, the path length from the stationing point to the node j in the array Len is updated, and Len [ j ] is enabled]=min(Len[j],Len[j]+lij)。
S24: and setting the current node i as the determined shortest path node, taking out the node from the set V, and putting the node into the set U.
S25: judging whether the set V is an empty set: if yes, the algorithm is terminated; if not, the process returns to S22.
After the algorithm is operated, the shortest path length from the parking point to all other nodes of the fire-fighting robot can be obtained from the arrays Len; the initial path planning result can be obtained through the calculation process of reversely tracking the shortest path length.
S3: fire suppression path optimization
The MAKLINK line where each path node is located is L in sequencei(i ═ 1,2, …, t). Suppose thatAndis LiAt two end points, the MAKLINK line LiThe upper minute point positions can be expressed as:
in the formula, betaiIs a scale factor, betai∈[0,1]And t is the number of MAKINK lines.
Finding a set of scale factor combinations (beta) using an improved ant colony algorithm1,β2,…,βt) And selecting the position of each path node on the corresponding MAKINK line to obtain a new optimal path. The method specifically comprises the following steps:
s31: initializing improved ant colony algorithm and setting parameters including reference coefficient R and pheromone selection threshold q0Initial value of pheromone0Maximum value of pheromone volatilization parameter lambdamaxMinimum value lambda of pheromone volatilization parameterminNumber of ants m and maximum number of iterations nmax;
S32: the improved ant colony algorithm starts the search, and ants on the current node select the node on the next line of MAKLINK according to the following formula:
s33: and locally updating the pheromone concentration of the current path node according to the following formula:
s34: judging whether the current path node reaches the fire suppression point, if so, performing the step S35, otherwise, returning to the step S32;
s35: counting all optimized paths searched by m current ants, selecting a path planning result with the shortest length, and globally updating pheromone concentration according to the following formula:
Δi,j=1/L*
s36: judging whether a preset maximum iteration number is reached or not; if yes, go to step S37, otherwise return to step S32;
s37: and acquiring a global optimal planning path.
In order to verify the feasibility and the effectiveness of the intelligent path planning method for the fire-fighting robot provided by the invention, a 200m × 200m square two-dimensional fire scene space environment is built by using MATLAB 2016b, and whether the fire-fighting robot can move from a left upper-corner stationing point S to a right lower-corner fire extinguishing point T through the shortest distance is observed under the known obstacle environment, and the robot bypasses a concave-convex polygonal obstacle in the fire scene space environment without collision. The initialization parameter settings for the improved ant colony algorithm are shown in table 1.
TABLE 1 initialization parameters for improved ant colony algorithm
Initialization parameters | Numerical value | Description of the invention |
R | 2 | Reference coefficient |
q0 | 0.75 | Pheromone selection threshold |
ε0 | 2.5×10-4 | Initial value of pheromone |
max | 0.7 | Maximum value of pheromone volatilization parameter |
λmin | 0.5 | Minimum value of pheromone volatilization parameter |
m | 10 | Number of ants |
max | 300 | Maximum number of iterations |
In the first experiment, an Ant Colony Optimization (ACO) and an Improved Ant Colony Optimization (IACO) were used to perform path planning in a fire space environment. The experimental results show that compared with Dijkstra's algorithm and the ant colony algorithm, the improved ant colony algorithm provided by the embodiment shortens the path lengths 32.1335m and 22.0853m, respectively.
As can be seen from the comparison between fig. 4 and fig. 5, when the next path node is selected on each MAKLINK line by the improved ant colony algorithm, the included angle between the current node and the next node is reduced, the planned path is closer to the edge of the polygonal barrier, and is particularly reflected in the selection of the nodes at the last stage, so that the length of the fire fighting path of the fire-fighting robot is finally shortened, and the optimal path planning is realized. This shows that the introduced adaptive adjustment pheromone updating strategy can help the algorithm to skip the local optimal solution and enhance the path planning capability.
In the second test, four different maximum iteration times of 50, 100, 150 and 200 are set, the other initialization parameters are completely the same as those used in the first test, the ant colony algorithm and the improved ant colony algorithm are respectively used for path planning, the influence of the maximum iteration times on the path planning result is observed, and the planning results of the maximum iteration times and the improved ant colony algorithm are compared and analyzed. The experimental results of the two algorithms are shown in table 2.
As can be seen from table 2, under the condition that the maximum iteration times are the same, the number of optimized paths obtained by the improved ant colony algorithm is significantly greater, and the path length is significantly shortened; although the number of the optimized paths of the ant colony algorithm is slightly increased along with the increase of the iteration times, the number is relatively low, and the improved ant colony algorithm is further explained to have stronger path planning capability; in addition, as can also be seen from the change rule of the optimized path length, when the maximum iteration number is changed from 50 to 100, the numerical value of the improved ant colony algorithm changes maximally, and then the amplification is obviously reduced and gradually approaches to the optimal solution; the optimal path length of the ant colony algorithm is always gradually shortened, but the required optimal path cannot be determined. This indicates improved pheromone volatilization parametersBy using the method, the search step length can be dynamically adjusted by the improved ant colony algorithm according to the change of the iteration times, and the convergence speed is finally improved.
Table 2 algorithm test results comparative data
From the above, it can be seen that the fire-fighting robot intelligent path planning method based on the extended MAKLINK graph theory and the improved ant colony algorithm provided by the embodiment can realize optimal path planning in a complex fire scene space environment containing concave-convex polygonal obstacles, and the planning result is obviously superior to the Dijkstra algorithm and the ant colony algorithm, so that the path planning capability is stronger, and the algorithm convergence speed is faster.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (10)
1. An intelligent path planning method for a fire-fighting robot is characterized by comprising the following steps:
and (3) environmental information preprocessing: establishing a world coordinate system according to fire scene space environment information of a fire-fighting robot, describing the edge of an obstacle by adopting a polygon, acquiring the vertex coordinates of the obstacle in the fire scene space environment, and determining a parking point and a fire suppression point of the fire-fighting robot in the world coordinate system;
a fire scene space environment modeling step: constructing a fire scene space environment model by adopting an expanded MAKLINK graph theory according to the fire scene space environment information, wherein the fire scene space environment model comprises a movable path of a fire-fighting robot;
an initial path planning step: based on the fire scene space environment model, planning an initial path by adopting Dijkstra algorithm with the shortest path length as a target according to the determined stationing point and the fire suppression point;
planning an optimal path: initializing a pre-established ant colony algorithm based on the fire scene space environment model and the initial path, performing iterative search on path nodes in the ant transfer process until a preset maximum iteration number is reached, and finally obtaining an optimal planning path.
2. The intelligent path planning method for the fire-fighting robot as recited in claim 1, wherein in the modeling of the fire scene space environment, the extended MAKLINK graph theory is adopted to construct the fire scene space environment model, specifically, for the convex polygonal obstacle, the construction of the fire scene space environment model is directly performed according to the traditional MAKLINK graph theory; dividing the concave polygonal barrier into an independent outer concave polygonal barrier and a combined inner concave polygonal barrier according to the geometric characteristics of the concave polygonal barrier; for the independent outer concave polygon barrier, filling the independent outer concave polygon barrier into a convex polygon through an auxiliary connecting line for processing, and setting the middle point of the auxiliary connecting line as a path node; and for the combined concave polygonal barrier, extending and sealing the gap of the combined concave polygonal barrier by an extending connecting line, setting the middle point of the extending connecting line as a path node, and processing the rest internal structures according to the traditional MAKLINK graph theory.
3. A fire-fighting robot intelligent path planning method according to claim 2, characterized in that the independent outer concave polygonal barrier is a single concave polygonal barrier, and the combined inner concave polygonal barrier is formed by combining a plurality of the barriers.
4. The intelligent path planning method for the fire-fighting robot as recited in claim 1, wherein the ant colony algorithm is an improved ant colony algorithm, and the improved ant colony algorithm adopts an improved heuristic value importance factor definition formula in an iterative search process to realize adaptive dynamic update of the heuristic value;
the improved heuristic value importance factor definition formula enables the heuristic value importance factor to be increased, then decreased, and finally increased along with the iterative search process of the improved ant colony algorithm.
5. The intelligent path planning method for fire-fighting robot as recited in claim 4, wherein the improved heuristic value importance factor defines the expression of the formula:
6. The intelligent path planning method for the fire-fighting robot as recited in claim 5, wherein the ant colony algorithm is an improved ant colony algorithm, and the improved ant colony algorithm adopts an improved pheromone volatilization parameter definition formula to perform self-adaptive dynamic updating of pheromones in an iterative search process;
the improved pheromone volatilization parameter definition formula enables the pheromone volatilization parameter to be in a variation trend of first becoming larger and then becoming smaller along with the iterative search process of the improved ant colony algorithm.
7. The intelligent path planning method for the fire-fighting robot as recited in claim 6, wherein the modified pheromone volatilization parameter definition formula has an expression as follows:
8. The intelligent path planning method for the fire-fighting robot as recited in claim 7, wherein the ant colony algorithm is an improved ant colony algorithm, the improved ant colony algorithm updates the local pheromone by using an improved local pheromone update formula, and the expression of the improved local pheromone update formula is as follows:
9. The intelligent path planning method for the fire-fighting robot as recited in claim 8, wherein the ant colony algorithm is an improved ant colony algorithm, the improved ant colony algorithm updates the global pheromone by using an improved global pheromone update formula, and the expression of the improved global pheromone update formula is as follows:
Δi,j=1/L*
in the formula, L*Is the current shortest path length.
10. The intelligent path planning method for the fire-fighting robot as recited in claim 9, wherein the ant colony algorithm is an improved ant colony algorithm, the improved ant colony algorithm determines the position of the next path node according to the pheromone and the heuristic value in the iterative search process, and the expression of the method for determining the position of the next path node is as follows:
in the formula (I), the compound is shown in the specification,is the position of the next path node, I is the set of all the alternative nodes on the jth MAKLINK line, xii,k(n) is a heuristic value from a node i to a node k in the nth iteration, q is a random adjustable parameter, and q belongs to [0,1 ]],q0Selecting a threshold value for the pheromone, q0∈[0,1]And P is the node position with the maximum selection probability determined by the roulette strategy, and the expression of the selection probability is as follows:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011012951.2A CN112161627A (en) | 2020-09-23 | 2020-09-23 | Intelligent path planning method for fire-fighting robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011012951.2A CN112161627A (en) | 2020-09-23 | 2020-09-23 | Intelligent path planning method for fire-fighting robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112161627A true CN112161627A (en) | 2021-01-01 |
Family
ID=73863624
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011012951.2A Pending CN112161627A (en) | 2020-09-23 | 2020-09-23 | Intelligent path planning method for fire-fighting robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112161627A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113190026A (en) * | 2021-05-10 | 2021-07-30 | 河海大学 | Energy-saving underwater path planning method based on re-excitation mechanism particle swarm algorithm |
CN113642092A (en) * | 2021-10-18 | 2021-11-12 | 西南交通大学 | Building space path capturing method |
CN113805597A (en) * | 2021-09-28 | 2021-12-17 | 福州大学 | Obstacle self-protection artificial potential field method local path planning method based on particle swarm optimization |
CN114217607A (en) * | 2021-11-23 | 2022-03-22 | 桂林航天工业学院 | Takeout delivery path planning method, system and storage medium |
CN114489081A (en) * | 2022-02-07 | 2022-05-13 | 国网上海市电力公司 | Multi-fire-source fire-extinguishing optimal path planning method |
CN114967679A (en) * | 2022-04-24 | 2022-08-30 | 南通倍佳机械科技有限公司 | Fire-fighting robot path self-adaptive control method and system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105589461A (en) * | 2015-11-18 | 2016-05-18 | 南通大学 | Parking system path planning method on the basis of improved ant colony algorithm |
CN110196061A (en) * | 2019-05-29 | 2019-09-03 | 华北理工大学 | Based on the mobile robot global path planning method for improving ant group algorithm |
CN111026126A (en) * | 2019-12-27 | 2020-04-17 | 哈尔滨工程大学 | Unmanned ship global path multi-target planning method based on improved ant colony algorithm |
-
2020
- 2020-09-23 CN CN202011012951.2A patent/CN112161627A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105589461A (en) * | 2015-11-18 | 2016-05-18 | 南通大学 | Parking system path planning method on the basis of improved ant colony algorithm |
CN110196061A (en) * | 2019-05-29 | 2019-09-03 | 华北理工大学 | Based on the mobile robot global path planning method for improving ant group algorithm |
CN111026126A (en) * | 2019-12-27 | 2020-04-17 | 哈尔滨工程大学 | Unmanned ship global path multi-target planning method based on improved ant colony algorithm |
Non-Patent Citations (1)
Title |
---|
YANG M , ET AL: "Robot Path Planning Based on Extended MAKLINK Graph and Improved Ant Colony Optimization", 《THE 5TH INTERNATIONAL CONFERENCE》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113190026A (en) * | 2021-05-10 | 2021-07-30 | 河海大学 | Energy-saving underwater path planning method based on re-excitation mechanism particle swarm algorithm |
CN113805597A (en) * | 2021-09-28 | 2021-12-17 | 福州大学 | Obstacle self-protection artificial potential field method local path planning method based on particle swarm optimization |
CN113805597B (en) * | 2021-09-28 | 2023-04-11 | 福州大学 | Obstacle self-protection artificial potential field method local path planning method based on particle swarm optimization |
CN113642092A (en) * | 2021-10-18 | 2021-11-12 | 西南交通大学 | Building space path capturing method |
CN113642092B (en) * | 2021-10-18 | 2022-01-04 | 西南交通大学 | Building space path capturing method |
CN114217607A (en) * | 2021-11-23 | 2022-03-22 | 桂林航天工业学院 | Takeout delivery path planning method, system and storage medium |
CN114489081A (en) * | 2022-02-07 | 2022-05-13 | 国网上海市电力公司 | Multi-fire-source fire-extinguishing optimal path planning method |
CN114489081B (en) * | 2022-02-07 | 2024-02-02 | 国网上海市电力公司 | Multi-fire-source extinguishment optimal path planning method |
CN114967679A (en) * | 2022-04-24 | 2022-08-30 | 南通倍佳机械科技有限公司 | Fire-fighting robot path self-adaptive control method and system |
CN114967679B (en) * | 2022-04-24 | 2024-03-22 | 河北航瑞信科精密机械有限公司 | Self-adaptive control method and system for fire-fighting robot path |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112161627A (en) | Intelligent path planning method for fire-fighting robot | |
CN106979785B (en) | Complete traversal path planning method for multi-robot system | |
CN109164810B (en) | Robot self-adaptive dynamic path planning method based on ant colony-clustering algorithm | |
CN109116841B (en) | Path planning smooth optimization method based on ant colony algorithm | |
CN110231824B (en) | Intelligent agent path planning method based on straight line deviation method | |
CN112650229B (en) | Mobile robot path planning method based on improved ant colony algorithm | |
CN110181508B (en) | Three-dimensional route planning method and system for underwater robot | |
CN111174798A (en) | Foot type robot path planning method | |
CN110986953B (en) | Path planning method, robot and computer readable storage medium | |
CN111880561B (en) | Unmanned aerial vehicle three-dimensional path planning method based on improved whale algorithm in urban environment | |
CN113199474B (en) | Robot walking and operation intelligent cooperative motion planning method | |
CN113296520B (en) | Routing inspection robot path planning method integrating A and improved gray wolf algorithm | |
CN111610786A (en) | Mobile robot path planning method based on improved RRT algorithm | |
CN110471426A (en) | Unmanned intelligent vehicle automatic Collision Avoidance method based on quantum wolf pack algorithm | |
CN113359746A (en) | Path planning method and device based on improved bidirectional RRT and Dijkstra fusion algorithm | |
Bai et al. | Design and Simulation of a Collision-free Path Planning Algorithm for Mobile Robots Based on Improved Ant Colony Optimization. | |
CN113189988A (en) | Autonomous path planning method based on Harris algorithm and RRT algorithm composition | |
CN113110455A (en) | Multi-robot collaborative exploration method, device and system for unknown initial state | |
CN113442140A (en) | Bezier optimization-based Cartesian space obstacle avoidance planning method | |
Tian et al. | An improved RRT robot autonomous exploration and SLAM construction method | |
CN114815801A (en) | Adaptive environment path planning method based on strategy-value network and MCTS | |
CN109977455B (en) | Ant colony optimization path construction method suitable for three-dimensional space with terrain obstacles | |
CN114397894B (en) | Mobile robot target searching method imitating human memory | |
CN115357050A (en) | Unmanned aerial vehicle path planning method based on hierarchical particle swarm optimization and application thereof | |
CN111896001A (en) | Three-dimensional ant colony track optimization method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210101 |