CN115933715A - Marine garbage cleaning robot and path planning method, device and medium thereof - Google Patents
Marine garbage cleaning robot and path planning method, device and medium thereof Download PDFInfo
- Publication number
- CN115933715A CN115933715A CN202310032296.4A CN202310032296A CN115933715A CN 115933715 A CN115933715 A CN 115933715A CN 202310032296 A CN202310032296 A CN 202310032296A CN 115933715 A CN115933715 A CN 115933715A
- Authority
- CN
- China
- Prior art keywords
- marine
- detection
- record table
- garbage
- acquiring
- 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
Images
Abstract
The embodiment of the invention provides a marine garbage cleaning robot, a path planning method, a path planning device and a path planning medium thereof, and relates to the technical field of marine floating garbage salvage. The path planning method comprises S01, obtaining the garbage detection information. S02, constructing a detection record table according to the garbage detection information. And S07, acquiring a detection distance matrix according to the detection record table. And S08, planning a path according to the detection record table and the detection distance matrix, and acquiring an initial planned path. And S09, acquiring the mobile position according to the initial planned path. S10, calculating the first time length of the marine garbage cleaning robot moving to the moving position. S11, obtaining the flow speed and the flow direction of the seawater, calculating the position of each garbage after a first time period, and obtaining a prediction record table. And S12, acquiring a prediction distance matrix according to the prediction record table. And S13, planning the path according to the prediction record table and the prediction distance matrix, and obtaining a prediction planning path. And S14, acquiring a predicted position according to the predicted planning path so as to enable the marine garbage cleaning robot to move towards the predicted position.
Description
Technical Field
The invention relates to the technical field of salvage of garbage floating on sea, in particular to a marine garbage cleaning robot, a path planning method and a path planning device of the marine garbage cleaning robot, and a medium of the marine garbage cleaning robot.
Background
The garbage floating on the sea is a serious global problem, the influence range is not limited to the areas where people live, the garbage floating on the sea can be dispersed to all parts of the world along with wind or water flow, more than 1 million tons of plastic garbage flowing into the sea every year, and the plastic garbage floating on the sea poses a serious threat to the sea ecosystem and the people.
A common cleaning method for the garbage floating on the sea comprises the steps of establishing an underwater garbage can or arranging an underwater garbage fishing robot. The current common underwater garbage can comprises: train Wheel, seabin, the Ocean Cleanup. The underwater garbage can is simple in structure, adopts a passive mode to collect the garbage floating on the sea, but is limited in cleaning range. The underwater garbage fishing robot can not only actively detect garbage, but also actively salvage the garbage, but also has a complex structure and high manufacturing cost.
Therefore, how to improve the working efficiency of the underwater garbage salvaging robot becomes a technical problem which needs to be solved urgently.
In view of the above, the applicant has specifically proposed the present application after studying the existing technology.
Disclosure of Invention
The invention provides a marine garbage cleaning robot, a path planning method, a path planning device and a path planning medium thereof, which aim to improve at least one of the technical problems.
First aspect,
The embodiment of the invention provides a path planning method for a marine garbage cleaning robot, which comprises steps S01 and S02 and steps S07 to S14.
And S01, acquiring garbage detection information in the detection range of the marine garbage cleaning robot.
S02, constructing a detection record table according to the garbage detection information. Wherein, the detection record table records the number and the position information of each detected marine rubbish.
And S07, acquiring a detection distance matrix according to the detection record table. The detection distance matrix records the distance between any two marine wastes and the distance from the marine waste robot to each marine waste.
And S08, acquiring an initial planning path through a path planning method based on a genetic algorithm according to the detection record table and the detection distance matrix.
And S09, acquiring a first mobile position according to the initial planned path.
S10, acquiring the moving speed of the marine garbage cleaning robot, and acquiring the first time length for the marine garbage cleaning robot to move to the first moving position according to the first moving position and the moving speed.
S11, obtaining the flow speed and the flow direction of the seawater, calculating the positions of the garbage after the first time length according to the detection record table, the flow speed, the flow direction and the first time length, and obtaining a prediction record table.
And S12, acquiring a prediction distance matrix according to the prediction record table.
And S13, obtaining a predicted planned path through a path planning method based on a genetic algorithm according to the predicted record table and the predicted distance matrix.
And S14, acquiring a first predicted position according to the predicted planned path so that the marine garbage cleaning robot moves towards the first predicted position to a picking range of the marine garbage.
The second aspect,
The embodiment of the invention provides a path planning device of a marine garbage cleaning robot, which comprises:
and the detection information acquisition module is used for acquiring the garbage detection information in the detection range of the marine garbage cleaning robot.
And the first information input module is used for constructing a detection record table according to the garbage detection information. Wherein, the detecting record table records the number and the position information of each detected marine rubbish.
And the first distance calculation module is used for acquiring a detection distance matrix according to the detection record table. The detection distance matrix records the distance between any two marine wastes and the distance from the marine waste robot to each marine waste.
And the first path planning module is used for acquiring an initial planned path through a path planning method based on a genetic algorithm according to the detection record table and the detection distance matrix.
And the mobile position acquisition module is used for acquiring a first mobile position according to the initial planned path.
And the moving duration calculation module is used for acquiring the moving speed of the marine garbage cleaning robot and acquiring the first duration of the marine garbage cleaning robot moving to the first moving position according to the first moving position and the moving speed.
And the second information recording module is used for acquiring the flow speed and the flow direction of the seawater, calculating the positions of the garbage after the first time length according to the detection record table, the flow speed, the flow direction and the first time length, and acquiring the prediction record table.
And the second distance calculation module is used for acquiring a prediction distance matrix according to the prediction record table.
And the second path planning module is used for acquiring a predicted planned path through a path planning method based on a genetic algorithm according to the predicted record table and the predicted distance matrix.
And the predicted position acquisition module is used for acquiring a first predicted position according to the predicted planned path so as to enable the marine garbage cleaning robot to move towards the first predicted position to a picking range of the marine garbage.
The third aspect,
The embodiment of the invention provides a marine garbage cleaning robot, which comprises a processor, a memory and a computer program stored in the memory. A computer program is executable by a processor to implement the method for path planning for a marine waste cleaning robot as described in any of the paragraphs above.
The fourth aspect,
An embodiment of the present invention provides a computer-readable storage medium. The computer-readable storage medium comprises a stored computer program, wherein the apparatus in which the computer-readable storage medium is located is controlled to perform the path planning method for the marine garbage cleaning robot as described in any one of the paragraphs of the first aspect when the computer program is executed.
By adopting the technical scheme, the invention can obtain the following technical effects:
the path planning method provided by the embodiment of the invention not only predicts the position of the marine garbage at the next moment in advance according to the water flow, but also enables the marine garbage cleaning robot to directly move to the position to which the marine garbage can possibly move at the next moment, and avoids the phenomenon that the moving distance is increased due to the fact that the marine garbage runs all the time. And the moving path of the marine garbage cleaning robot is planned by using a population algorithm which takes the minimum total path length as a target, so that the moving distance of the marine garbage cleaning robot in garbage cleaning is further reduced, the fishing efficiency of the marine garbage is greatly improved, the energy utilization rate is improved, and the method has good practical significance.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a flow chart diagram of a path planning method.
Fig. 2 is a schematic diagram of a planned path of the marine garbage cleaning robot.
FIG. 3 is a schematic diagram of individual codes of a genetic algorithm.
Fig. 4 is a schematic diagram of location prediction of marine debris.
Fig. 5 is a schematic structural diagram of a path planning method apparatus.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The first embodiment,
Referring to fig. 1 to 4, a first embodiment of the invention provides a path planning method for a marine garbage cleaning robot, which can be executed by the marine garbage cleaning robot. In particular, it is executed by one or more processors in the marine debris cleaning robot to implement steps S01, S02, and steps S07 to S14.
And S01, acquiring garbage detection information in the detection range of the marine garbage cleaning robot.
Specifically, marine waste clearance robot is provided with camera and laser radar, detects the environment around the marine waste clearance robot through camera and radar to rubbish to in the certain extent discerns one by one.
As shown in figure 1, after the marine garbage cleaning robot salvages the floating garbage one by one, the floating garbage returns to the charging station. However, the water surface garbage cleaning robot can only detect the floating garbage in the detection range. In the prior art, the marine garbage cleaning robot tends to move directly towards the nearest garbage, and does not consider whether the total path taken to recycle all garbage is the shortest. Therefore, the marine garbage cleaning robot has a lot of paths in the garbage salvaging process, and the energy utilization rate is low.
S02, constructing a detection record table according to the garbage detection information. Wherein, the detecting record table records the number and the position information of each detected marine rubbish.
Specifically, the marine garbage cleaning robot records the detected garbage to form a detection record table. And after the marine garbage is salvaged and collected, the marine garbage is deleted from the detection record table.
In this embodiment, the detection record table records the number and the location information of the marine garbage. In other embodiments, other information such as the type and the area size of the marine garbage may also be recorded, which is not specifically limited in the present invention.
And S07, acquiring a detection distance matrix according to the detection record table. The detection distance matrix records the distance between any two marine wastes and the distance from the marine waste robot to each marine waste.
Specifically, after the detection record table is established, the detection record table is converted into a detection distance matrix. The detection distance matrix is used for recording the Euclidean distance between any two points, so that a data basis is provided for the subsequent calculation of the total path length of each path, and the detection distance matrix has good practical significance.
Based on the foregoing embodiments, in an optional embodiment of the present invention, the detection distance matrix is used to record euclidean distances between any two points. The model of the detection distance matrix M is:
wherein n is the number of detected marine wastes.
Specifically, the detection distance matrix is a symmetric matrix:
M＝M T
the diagonal distances of the detection distance matrix are all 0:
Diag(M)＝0
in the present embodiment, the coordinates of the marine debris cleaning robot itself are known. And the coordinates of each detected garbage are recorded in the detection record table. From these coordinates, the distance between any two points can be found. In the present embodiment, these distances are expressed in a matrix form for the convenience of subsequent data extraction.
And S08, acquiring an initial planning path by a path planning method based on a genetic algorithm according to the detection record table and the detection distance matrix.
Specifically, the moving path of the marine garbage cleaning robot with the shortest total path length can be planned and obtained through a genetic algorithm taking the shortest total path length as an optimization target, so that the distance of the marine garbage cleaning robot in the marine garbage salvaging process is reduced, the salvaging efficiency is improved, and the energy consumption is reduced.
On the basis of the foregoing embodiments, in an optional embodiment of the present invention, step S08 specifically includes step S081 to step S083.
S081, according to the detection record table, initializing the population. Wherein each individual in the population represents a movement path.
Specifically, after the detection distance matrix M is calculated, the population is initialized. Randomly generating q individuals from the detection record table. Since the robot needs to return to the origin, i.e. the start and end points of each group of populations coincide, as shown in fig. 3.
The number of initialisation populations is shown below:
q＝pn,wheren≥5
g1 to Gn share n! And (4) breeding individuals. However, when the number of individuals is large, the calculation is complicated, and the operation efficiency of the genetic algorithm is reduced, so in this embodiment, the parameter p is set to 5.
S082, according to detecting the distance matrix, calculate the fitness of each individual in the population separately. The fitness is the total path length of the movement path.
In the present embodiment, the total path length of each individual movement trajectory is calculated, and the total path length is defined as the fitness f i . According to the fitness f i Selecting proper individuals to carry out crossover and mutation operations.
Fitness f i The calculation model of (a) is:
where tdist (i) is the total path length of the ith individual.
And S083, selecting individuals by adopting a wheel disc method according to the fitness, and crossing and mutating the selected individuals to generate a new population until a preset iteration number is reached to obtain the optimal individuals. Wherein, the optimal individual is an initial planning path.
In particularCalculating each individual f i After fitness, q new individuals are selected for crossover, and a roulette wheel method (X) is adopted]Selecting individuals, wherein the higher the fitness, the higher the probability that the individuals will be selected as the offspring individuals for the crossover operation, as shown in the following formula:
after the fitness of each individual is calculated, the individual crossing and mutation operations are carried out to generate new filial generation individuals. Two parents were crossed except that the end point was the same as the starting point. Suppose there are two parents of
And/or>
The generated filial generation individuals
And/or>
Can be obtained by the following formula:
in the mutation process, this embodiment randomly selects one group of nodes (i-th and j-th nodes) from the descendant e to perform mutation operation, i.e. the sequence of the two nodes is exchanged. The probability of variation for each individual offspring is set to 0.01, as shown in the following formula:
and S09, acquiring a first moving position according to the initial planned path.
Specifically, after the path is planned, the first marine garbage to be salvaged can be obtained. The first mobile position is the detection position coordinate of the marine garbage to be salvaged.
S10, acquiring the moving speed of the marine garbage cleaning robot, and acquiring the first time length for the marine garbage cleaning robot to move to the first moving position according to the first moving position and the moving speed.
S11, obtaining the flow speed and the flow direction of the seawater, calculating the positions of the garbage after the first time length according to the detection record table, the flow speed, the flow direction and the first time length, and obtaining a prediction record table.
Specifically, path planning is one of the cores of underwater robot technology research and is a key technology for realizing autonomous navigation and operation. Many researchers have been working on underwater robots to deal with the problem of path planning through various algorithms. However, the inventors have found through extensive research that these methods assume that the target and environment are static. In a real environment, the garbage floating on the sea is in a state of continuously changing positions along with sea currents, so that the marine garbage cleaning robot can only always track the garbage to run and cannot plan a global shortest path, the marine garbage cleaning robot can walk many paths in the garbage salvaging process, and energy waste is caused.
Therefore, in the present embodiment, the position of the marine waste is predicted from the flow velocity and the flow direction of the seawater. The time t required for the marine garbage cleaning robot to move to the first marine garbage is 1 Based on the calculated time t of all the marine garbage 1 The position in seconds. Therefore, the marine garbage robot can directly move to the position of the marine garbage at the next moment, and the marine garbage cleaning robot is prevented from detouring to cause energy waste.
On the basis of the foregoing embodiment, in an optional embodiment of the present invention, step S11 specifically includes step S111 to step S114.
S111, obtaining the flow velocity C of the seawater v And a flow direction θ.
And S112, acquiring the initial position of each marine rubbish according to the detection record table.
S113, according to the initial position and the flow speed C v The flow direction theta and the first time length, and calculating the position of each marine garbage after the first time length. Wherein, the position calculation model is as follows:
dist(G j ，G j ′)＝t i ×C v
in the formula, x Gj Is the initial abscissa, y, of the marine waste Gj Is the initial ordinate, dist (G) of the marine waste j ，G j ') the moving distance of the marine waste, theta the flow direction of the seawater, and t i Is a first duration, C v Is the flow rate of the seawater.
And S114, updating the detection record table according to the position of each marine rubbish after the first duration, and acquiring the prediction record table.
Specifically, the position of the marine refuse in the detection record table is updated to the position of the marine refuse which is predicted to move for the first time, so that the prediction record table is obtained. And path planning is carried out again according to the prediction record table, a path after pre-judgment can be obtained, and the total path of the marine cleaning robot during garbage cleaning is greatly reduced.
And S12, acquiring a prediction distance matrix according to the prediction record table.
Specifically, the specific step of step S12 is the same as the specific step of step S07. The distance between any two points is obtained according to the coordinates, and then the distance is converted into a matrix form. Therefore, the detailed steps of step S12 are not repeated.
And S13, acquiring a predicted planned path through a path planning method based on a genetic algorithm according to the predicted record table and the predicted distance matrix.
Specifically, the specific steps of step S13 are the same as those of step S08. Except that step S08 is performed according to the detection record table and the detection distance matrix. In step S13, planning is performed based on the prediction record table and the prediction distance matrix. Therefore, the detailed steps of step S13 are not repeated.
And S14, acquiring a first predicted position according to the predicted planned path so that the marine garbage cleaning robot moves towards the first predicted position to a picking range of the marine garbage.
The path planning method provided by the embodiment of the invention not only predicts the position of the marine waste at the next moment in advance according to the water flow, but also enables the marine waste cleaning robot to directly move to the position to which the marine waste can move at the next moment, and avoids the phenomenon that the moving distance is increased because the marine waste runs after being traced all the time. And the moving path of the marine garbage cleaning robot is planned by using a population algorithm which takes the minimum total path length as a target, so that the moving distance of the marine garbage cleaning robot in garbage cleaning is further reduced, the fishing efficiency of the marine garbage is greatly improved, the energy utilization rate is improved, and the method has good practical significance.
On the basis of the foregoing embodiment, in an optional embodiment of the present invention, before step S07, the method further includes:
and S03, judging the quantity of the marine garbage in the detection range according to the detection record table.
And S04, when the quantity of the marine garbage is 0, generating a virtual target point in the detection range so as to enable the marine garbage cleaning robot to move towards the virtual point.
And S05, when the quantity of the garbage is smaller than a preset value, setting the marine garbage closest to the marine garbage cleaning robot as a salvaged target position by adopting a greedy algorithm so as to enable the marine garbage cleaning robot to move towards the target position.
And S06, when the quantity of the garbage is not less than a preset value, executing the subsequent steps.
Specifically, in order to enlarge the cleaning range of the marine garbage cleaning robot, the marine garbage cleaning robot needs to continuously move, so that the working range is far larger than the detection range. In order to ensure that the marine garbage cleaning robot continuously moves, when the garbage amount is 0, a virtual target point is randomly set, so that the marine garbage cleaning robot is moved. The inventor finds that when the quantity of garbage is small, a greedy algorithm is adopted to clean the garbage from the nearest distance, the total path traveled by the robot is almost the same as the path planned by a genetic algorithm, and therefore the greedy algorithm is adopted to clean the garbage from the nearest distance under the condition that the quantity of the garbage is small, the calculated amount of the marine garbage cleaning robot is reduced, and energy consumption is reduced.
It should be noted that, as time goes by, the predicted marine waste will be less and less accurate. The marine debris removal robot detects the marine debris once after a fixed time interval td. The path planning method of the embodiment of the invention is executed again after the detection. Therefore, the problem that the position of the marine garbage is not accurate due to the overlong data detection period is avoided. It is doubtful that the periodic detection of the marine garbage can save a large amount of energy compared with the uninterrupted detection of the marine garbage, and the method has good practical significance.
Example II,
As shown in fig. 5, an embodiment of the present invention provides a path planning apparatus for a marine garbage cleaning robot, including:
the detection information acquisition module 1 is used for acquiring the garbage detection information in the detection range of the marine garbage cleaning robot.
And the first information input module 2 is used for constructing a detection record table according to the garbage detection information. Wherein, the detection record table records the number and the position information of each detected marine rubbish.
And the first distance calculation module 7 is configured to obtain a detection distance matrix according to the detection record table. The distance between any two marine wastes and the distance from the marine waste robot to each marine waste are recorded in the detection distance matrix.
And the first path planning module 8 is used for acquiring an initial planned path through a path planning method based on a genetic algorithm according to the detection record table and the detection distance matrix.
And a mobile position obtaining module 9, configured to obtain the first mobile position according to the initial planned path.
And the moving duration calculation module 10 is configured to obtain a moving speed of the marine garbage cleaning robot, and obtain a first duration for the marine garbage cleaning robot to move to the first moving position according to the first moving position and the moving speed.
And the second information recording module 11 is configured to acquire a flow speed and a flow direction of the seawater, calculate positions of the garbage after the first duration according to the detection record table, the flow speed, the flow direction and the first duration, and acquire a prediction record table.
And a second distance calculating module 12, configured to obtain a predicted distance matrix according to the predicted record table.
And a second path planning module 13, configured to obtain a predicted planned path through a path planning method based on a genetic algorithm according to the predicted record table and the predicted distance matrix.
And the predicted position obtaining module 14 is used for obtaining a first predicted position according to the predicted planned path so that the marine garbage cleaning robot moves towards the first predicted position to a picking range of the marine garbage.
On the basis of the foregoing embodiment, in an optional embodiment of the present invention, the path planning apparatus further includes:
and the quantity judging unit is used for judging the quantity of the marine garbage in the detection range according to the detection record table.
The first execution unit is used for generating a virtual target point in the detection range when the quantity of the marine garbage is 0 so as to enable the marine garbage cleaning robot to move towards the virtual point.
And the second execution unit is used for setting the marine garbage closest to the marine garbage cleaning robot as a salvaged target position by adopting a greedy algorithm when the garbage quantity is smaller than a preset value, so that the marine garbage cleaning robot moves towards the target position.
And the third execution unit is used for executing the subsequent steps when the garbage amount is not less than the preset value.
On the basis of the foregoing embodiment, in an optional embodiment of the present invention, the first path planning module 8 specifically includes:
and the population initialization unit is used for initializing the population according to the detection record table. Wherein each individual in the population represents a movement path.
And the fitness calculating unit is used for respectively calculating the fitness of each individual in the population according to the detection distance matrix. The fitness is the total path length of the movement path.
And the circulating unit is used for selecting individuals by adopting a wheel disc method according to the fitness, and crossing and varying the selected individuals to generate a new population until a preset iteration number is reached to obtain an optimal individual. Wherein the optimal individual is an initial planned path.
On the basis of the foregoing embodiment, in an optional embodiment of the present invention, the second information entry module 11 specifically includes:
a water flow information acquiring unit for acquiring the flow velocity C of the seawater v And a flow direction θ.
And the initial position acquisition unit is used for acquiring the initial position of each marine garbage according to the detection record table.
A position prediction unit for predicting the flow rate C according to the initial position v The flow direction theta and the first time length, and calculating the position of each marine garbage after the first time length. Wherein, the position calculation model is as follows:
dist(G j ,G j ′)＝t i ×C v
in the formula, x Gj Is the initial abscissa, y, of the marine waste Gj Is the initial ordinate, dist (G) of the marine waste j ,G j ') the moving distance of the marine waste, theta the flow direction of the seawater, and t i Is a first duration, C v Is the flow rate of the seawater.
And the position updating unit is used for updating the detection record table according to the position of each marine rubbish after the first duration to obtain the prediction record table.
Example III,
The embodiment of the invention provides a marine garbage cleaning robot, which comprises a processor, a memory and a computer program stored in the memory. The computer program can be executed by a processor to implement the path planning method for the marine waste cleaning robot as described in any one of the paragraphs above.
Examples IV,
An embodiment of the present invention provides a computer-readable storage medium. The computer readable storage medium comprises a stored computer program, wherein the computer readable storage medium is controlled to execute the path planning method of the marine garbage cleaning robot according to any one of the paragraphs of the embodiment when the computer program is executed.
In the embodiments provided in the embodiments of the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus and method embodiments described above are merely illustrative and, for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be understood that the term "and/or" as used herein is merely a relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B, may represent: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The word "if," as used herein, may be interpreted as "at \8230; \8230when" or "when 8230; \823030when" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
In the embodiments, the references to "first \ second" are merely to distinguish similar objects and do not represent a specific ordering for the objects, and it is to be understood that "first \ second" may be interchanged with a specific order or sequence, where permitted. It should be understood that "first \ second" distinguishing objects may be interchanged under appropriate circumstances such that the embodiments described herein may be implemented in sequences other than those illustrated or described herein.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A path planning method for a marine garbage cleaning robot is characterized by comprising the following steps:
acquiring garbage detection information in a detection range of the marine garbage cleaning robot;
constructing a detection record table according to the garbage detection information; the detection record table records the number and the position information of each detected marine rubbish;
acquiring a detection distance matrix according to the detection record table; the detection distance matrix records the distance between any two marine wastes and the distance from the marine waste robot to each marine waste;
acquiring an initial planning path by a path planning method based on a genetic algorithm according to the detection record table and the detection distance matrix;
acquiring a first mobile position according to the initial planned path;
acquiring the moving speed of the marine garbage cleaning robot, and acquiring a first time length for the marine garbage cleaning robot to move to the first moving position according to the first moving position and the moving speed;
acquiring the flow speed and the flow direction of seawater, and calculating the positions of various wastes after the first time according to the detection record table, the flow speed, the flow direction and the first time to acquire a prediction record table;
obtaining a prediction distance matrix according to the prediction record table;
obtaining a predicted planning path through a path planning method based on a genetic algorithm according to the predicted recording table and the predicted distance matrix;
and acquiring a first predicted position according to the predicted planned path so that the marine garbage cleaning robot moves towards the first predicted position to a picking range of the marine garbage.
2. The method as claimed in claim 1, wherein before obtaining the detection distance matrix according to the detection record table, the method further comprises:
judging the quantity of the marine garbage in the detection range according to the detection record table;
when the quantity of the marine garbage is 0, generating a virtual target point in a detection range so as to enable the marine garbage cleaning robot to move towards the virtual point;
when the quantity of the garbage is smaller than a preset value, setting the marine garbage closest to the marine garbage cleaning robot as a salvaged target position by adopting a greedy algorithm so as to enable the marine garbage cleaning robot to move towards the target position;
and when the garbage amount is not less than the preset value, executing the subsequent steps.
3. The path planning method for the marine garbage cleaning robot according to claim 1, wherein an initial planned path is obtained by a path planning method based on a genetic algorithm according to the detection record table and the detection distance matrix, and the method specifically comprises:
initializing a population according to the detection record table; wherein each individual in the population represents a movement path;
respectively calculating the fitness of each individual in the population according to the detection distance matrix; the fitness is the total path length of the moving path;
selecting individuals by adopting a wheel disc method according to the fitness, and crossing and mutating the selected individuals to generate a new population until a preset iteration number is reached to obtain an optimal individual; wherein the optimal individual is the initial planned path.
4. The path planning method for the marine garbage cleaning robot as claimed in any one of claims 1 to 3, wherein the detection distance matrix is a symmetric matrix, and the diagonal distances are both 0, so as to record Euclidean distances between any two points; the model of the detection distance matrix M is:
in the formula, n is the number of the detected marine garbage.
5. The path planning method for the marine garbage cleaning robot according to any one of claims 1 to 3, wherein the steps of obtaining the flow velocity and the flow direction of the seawater, calculating the position of each garbage after the first time period according to the detection record table, the flow velocity, the flow direction and the first time period, and obtaining the prediction record table specifically comprise:
obtaining the flow velocity C of seawater v And a flow direction θ;
acquiring the initial position of each marine rubbish according to the detection record table;
according to the initial position, the flow rate C v Calculating the position of each marine garbage after the first time length; wherein, the position calculation model is as follows:
dist(G j ,G j ′)＝t i ×C v
in the formula, x Gj Is the initial abscissa, y, of the marine waste Gj Is the initial ordinate, dist (G) of the marine waste j ，G j ') the moving distance of the marine waste, theta the flow direction of the seawater, and t i Is the first duration, C v Is the flow rate of the seawater;
and updating the detection record table according to the position of each marine rubbish after the first duration to obtain the prediction record table.
6. The utility model provides a path planning device of marine rubbish clearance robot which characterized in that contains:
the detection information acquisition module is used for acquiring the garbage detection information in the detection range of the marine garbage cleaning robot;
the first information input module is used for constructing a detection record table according to the garbage detection information; the detection record table records the number and the position information of each detected marine garbage;
the first distance calculation module is used for acquiring a detection distance matrix according to the detection record table; the detection distance matrix records the distance between any two marine wastes and the distance from the marine waste robot to each marine waste;
the first path planning module is used for acquiring an initial planning path through a path planning method based on a genetic algorithm according to the detection record table and the detection distance matrix;
a mobile position obtaining module, configured to obtain a first mobile position according to the initial planned path;
the moving duration calculation module is used for acquiring the moving speed of the marine garbage cleaning robot and acquiring the first duration of the marine garbage cleaning robot moving to the first moving position according to the first moving position and the moving speed;
the second information input module is used for acquiring the flow speed and the flow direction of the seawater, calculating the positions of all the garbage after the first time length according to the detection record table, the flow speed, the flow direction and the first time length, and acquiring a prediction record table;
the second distance calculation module is used for acquiring a prediction distance matrix according to the prediction record table;
the second path planning module is used for acquiring a predicted planned path through a path planning method based on a genetic algorithm according to the predicted record table and the predicted distance matrix;
and the predicted position acquisition module is used for acquiring a first predicted position according to the predicted planned path so as to enable the marine garbage cleaning robot to move towards the first predicted position to a picking range of the marine garbage.
7. A marine garbage cleaning robot comprising a processor, a memory, and a computer program stored in the memory; the computer program is executable by the processor to implement the path planning method of the marine garbage cleaning robot according to any one of claims 1 to 5.
8. A computer-readable storage medium, comprising a stored computer program, wherein when the computer program is executed, the computer-readable storage medium controls a device to execute the path planning method of the marine garbage cleaning robot according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310032296.4A CN115933715A (en) | 2023-01-10 | 2023-01-10 | Marine garbage cleaning robot and path planning method, device and medium thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310032296.4A CN115933715A (en) | 2023-01-10 | 2023-01-10 | Marine garbage cleaning robot and path planning method, device and medium thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115933715A true CN115933715A (en) | 2023-04-07 |
Family
ID=86550859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310032296.4A Pending CN115933715A (en) | 2023-01-10 | 2023-01-10 | Marine garbage cleaning robot and path planning method, device and medium thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115933715A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117075484A (en) * | 2023-10-18 | 2023-11-17 | 山东科技大学 | Underwater unmanned aerial vehicle return route planning method |
| CN117456395A (en) * | 2023-12-26 | 2024-01-26 | 广州大学 | Sea and land two-domain garbage recycling planning method based on machine vision |
-
2023
- 2023-01-10 CN CN202310032296.4A patent/CN115933715A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117075484A (en) * | 2023-10-18 | 2023-11-17 | 山东科技大学 | Underwater unmanned aerial vehicle return route planning method |
| CN117075484B (en) * | 2023-10-18 | 2024-01-30 | 山东科技大学 | Underwater unmanned aerial vehicle return route planning method |
| CN117456395A (en) * | 2023-12-26 | 2024-01-26 | 广州大学 | Sea and land two-domain garbage recycling planning method based on machine vision |
| CN117456395B (en) * | 2023-12-26 | 2024-03-29 | 广州大学 | Sea and land two-domain garbage recycling planning method based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115933715A (en) | Marine garbage cleaning robot and path planning method, device and medium thereof | |
| Jeong et al. | Image preprocessing for efficient training of YOLO deep learning networks | |
| KR102296507B1 (en) | Method for tracking object by using convolutional neural network including tracking network and computing device using the same | |
| CN110989352B (en) | Group robot collaborative search method based on Monte Carlo tree search algorithm | |
| CN113485375B (en) | Indoor environment robot exploration method based on heuristic bias sampling | |
| CN106873599A (en) | Unmanned bicycle paths planning method based on ant group algorithm and polar coordinate transform | |
| JP6980289B2 (en) | Learning method and learning device that can detect lanes using a lane model, and test method and test device using this {LEARNING METHOD, LEARNING DEVICE FOR DETECTING LANE USING LANE MODEL AND TEST METHOD, TEST DEVICE | |
| Jung et al. | Cooperative multi-robot target tracking | |
| JP2020123346A (en) | Method and device for performing seamless parameter switching by using location based algorithm selection to achieve optimized autonomous driving in each of regions | |
| CN111609848B (en) | Intelligent optimization method and system for multi-robot cooperation mapping | |
| CN110906935A (en) | Unmanned ship path planning method | |
| CN115147790A (en) | Vehicle future trajectory prediction method based on graph neural network | |
| KR102349975B1 (en) | Method and device for managing smart database for face recognition based on continual learning | |
| Liu et al. | Robot search path planning method based on prioritized deep reinforcement learning | |
| Lu et al. | Shape-based vessel trajectory similarity computing and clustering: A brief review | |
| Zhao et al. | BUPT-MCPRL at TRECVID 2016. | |
| Stogiannos et al. | Vessel trajectory prediction using radial basis function neural networks | |
| CN109976158A (en) | Based on the AUV energy source optimization path search method apart from evolution N-PSO | |
| CN115908508A (en) | Coastline ship real-time tracking method based on array camera | |
| Ding et al. | Capture uncertainties in deep neural networks for safe operation of autonomous driving vehicles | |
| Islam et al. | Active learning-based pedestrian and road sign detection | |
| Teng et al. | The Object Detection of Underwater Garbage with an Improved YOLOv5 Algorithm | |
| CN117806334B (en) | Underwater robot obstacle avoidance path planning method and system based on artificial intelligence | |
| CN113252861A (en) | Water quality detection method and device, electronic equipment and storage medium | |
| Zhou et al. | Learning Bayesian network structure from environment and sensor planning for mobile robot localization |
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 |