CN117470239A - Path planning method and device for cleaning robot of underwater end plug of nuclear power station - Google Patents
Path planning method and device for cleaning robot of underwater end plug of nuclear power station Download PDFInfo
- Publication number
- CN117470239A CN117470239A CN202311242931.8A CN202311242931A CN117470239A CN 117470239 A CN117470239 A CN 117470239A CN 202311242931 A CN202311242931 A CN 202311242931A CN 117470239 A CN117470239 A CN 117470239A
- Authority
- CN
- China
- Prior art keywords
- robot
- underwater
- cleaning
- end plug
- image
- 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
- 238000004140 cleaning Methods 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000009471 action Effects 0.000 claims abstract description 11
- 239000002245 particle Substances 0.000 claims description 29
- 230000033001 locomotion Effects 0.000 claims description 19
- 230000001133 acceleration Effects 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 5
- 210000001258 synovial membrane Anatomy 0.000 claims description 3
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000005457 optimization Methods 0.000 description 4
- 238000006073 displacement reaction Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 229910052770 Uranium Inorganic materials 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- JFALSRSLKYAFGM-UHFFFAOYSA-N uranium(0) Chemical compound [U] JFALSRSLKYAFGM-UHFFFAOYSA-N 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Abstract
The invention discloses a path planning method and a path planning device for a cleaning robot of an underwater end plug of a nuclear power station, wherein the method comprises the following steps: acquiring an image of an underwater environment based on a monocular stereoscopic vision algorithm; determining an underwater end plug to be cleaned according to the image of the underwater environment; generating a cleaning path by using a PSO algorithm based on the position information of the underwater end plug to be cleaned; correcting the cleaning path by using a fractional order synovial film backstepping algorithm; and performing a cleaning action based on the corrected cleaning path. According to the method, the PSO algorithm is utilized to generate the cleaning path, the moving distance, the pitch angle and the yaw angle of the robot in the cleaning path are corrected through the fractional order synovial backstepping algorithm on the basis of the PSO algorithm to obtain the optimal cleaning path, and the cleaning position reached by the robot can be more accurate through the method, so that the operation reliability of the robot is improved, and the cleaning work of the underwater end plug is ensured to be smooth.
Description
Technical Field
The invention relates to the technical field of robot path planning, in particular to a path planning method and device for a cleaning robot for an underwater end plug of a nuclear power station.
Background
With the rapid development of nuclear power generation technology and the improvement of industrial automation level, in order to save cost and ensure absolute safety of operators, industrial robots are introduced in the maintenance aspect of a nuclear power station reactor to clean a reaction device so as to improve the service lives of uranium rods and end plugs and the power generation efficiency of the nuclear power station. In general, a robot working path needs to be planned, and then an operator operates the underwater robot to perform work through an onshore control system.
The prior patent CN111290385a discloses a robot path planning method, a robot, an electronic device and a storage medium. The method comprises the following steps: acquiring a target point of the robot in the artificial potential field grid chart; acquiring a plurality of alternative pose points of the robot after a preset time length, and determining a target pose point according to the path cost of each pose point reaching a target point, wherein the target pose point is the pose point with the minimum path cost; and generating a target path according to the state information of the target pose point. According to the method, the path planning is carried out in the artificial potential field grid map, so that the problem that the path planning cannot be carried out due to the fact that the grid map cannot be generated when the target point is on an obstacle is avoided.
The prior patent CN113110509A discloses a warehouse system multi-robot path planning method based on deep reinforcement learning, which comprises the following steps: firstly, defining nodes, states, actions and rewards in a multi-robot path planning problem; secondly, selecting sub-target points, and calculating the state of each robot by a central controller; then, designing a distributed multi-robot path planner based on a deep reinforcement learning method; calculating a loss function, and updating network parameters; and finally, applying the trained model to multi-robot path planning. The method can solve the problem of poor real-time performance of the traditional path planning algorithm.
The search limitation of the path planning methods in the above two prior patents is large, the path obtained by the method is not an optimal path, and the accuracy of the working position reached by the robot in the working scene is not high enough.
Disclosure of Invention
Based on the technical problems, the invention provides a path planning method and device for a cleaning robot for an underwater end plug of a nuclear power station, and solves the problems that in the prior art, the limitation is large when an optimal path is searched, and the accuracy of an operation position reached by the robot is not high enough.
In order to achieve the above object, the present invention provides a path planning method for a cleaning robot for an underwater end plug of a nuclear power station, the method comprising:
acquiring an image of an underwater environment based on a monocular stereoscopic vision algorithm;
determining an underwater end plug to be cleaned according to the image of the underwater environment;
generating a cleaning path by using a PSO algorithm based on the position information of the underwater end plug to be cleaned;
correcting the cleaning path by using a fractional order synovial film backstepping algorithm;
and performing a cleaning action based on the corrected cleaning path.
Further, the capturing an image of an underwater environment based on the monocular stereoscopic algorithm includes:
acquiring initial position coordinates of a robot, and tracking a track of the robot;
and acquiring images of the underwater environment based on the monocular stereoscopic vision algorithm.
Further, the determining the underwater end plug to be cleaned from the image of the underwater environment comprises:
carrying out refinement treatment on the image of the underwater environment, and acquiring the image characteristics of the underwater plug in the image;
comparing the acquired image characteristics of the underwater end plug with preset characteristics, and determining the underwater end plug to be cleaned according to the comparison result.
Further, the generating a cleaning path by using a PSO algorithm based on the position information of the underwater end plug to be cleaned includes:
the position and velocity of the particles corresponding to the cleaning path are determined using equations one and two,
wherein,for the speed of the ith particle in the kth iteration,/and->For the d-dimensional component of each particle's position in the kth iteration, r 1 、r 2 Is [0,1]Random number, c 1 、c 2 As a learning factor, ω is an inertial weight;
iteratively updating the weight value in the formula I by using the formula III, iteratively updating the learning factors in the formula I by using the formula IV and the formula V, obtaining k iteratively updated cleaning paths,
wherein τ is a control coefficient; c max 、c min Maximum and minimum values for learning factors; coefficient alpha beta 1 、β 2 ＞0。
An optimal cleaning path is selected from the k cleaning paths.
Further, the generating a cleaning path by using a PSO algorithm based on the position information of the underwater end plug to be cleaned, further includes:
judging whether the current iteration number K reaches the total iteration number K or not;
stopping iteratively updating the cleaning path if the current iteration number K reaches the total iteration number K;
and if the current iteration number K does not reach the total iteration number K, continuing to iteratively update the cleaning path.
Further, the correcting the cleaning path by using a fractional order synovial back-off algorithm includes:
correcting the moving distance of the robot in the cleaning path through a formula six and a formula seven,
wherein k is x1 >0，k x2 >0，Representing gain coefficients e x1 、/>Position error of robot along x, y axis, respectively,>as fractional order coefficient, u x 、u y The distances of movement of the robot along the x, y axes, respectively.
Further, the correcting the cleaning path by using a fractional order synovial film back-off algorithm further includes:
correcting the pitch angle and yaw angle of the robot in the cleaning path according to a formula eight, wherein the formula eight is as follows:
wherein U is 1 Is the control rate of the robot, m is the mass of the robot, theta d Is the pitch angle phi of the robot d Is the yaw angle of the robot, e x1 For positional errors of the robot along the x-axis,k is the speed error of the robot moving along the y axis y Gain factor for fractional order synovial membrane, < ->s y And g is gravitational acceleration, which is a fractional order coefficient.
In order to achieve the above object, the present invention further provides a path planning device of a cleaning robot for an underwater end plug of a nuclear power station, the device comprising:
the acquisition module is used for acquiring an image of the underwater environment based on a monocular stereoscopic vision algorithm;
the determining module is used for determining an underwater end plug to be cleaned according to the image of the underwater environment;
the generating module is used for generating a cleaning path by using a PSO algorithm based on the position information of the underwater end plug to be cleaned;
the correction module is used for correcting the cleaning path by using a fractional order synovial film back-off algorithm;
and the execution module is used for executing the cleaning action based on the corrected cleaning path.
Further, the acquisition module is configured to:
acquiring initial position coordinates of a robot, and tracking a track of the robot;
and acquiring images of the underwater environment based on the monocular stereoscopic vision algorithm.
Further, the determining module is configured to:
carrying out refinement treatment on the image of the underwater environment, and acquiring the image characteristics of the underwater plug in the image;
comparing the acquired image characteristics of the underwater end plug with preset characteristics, and determining the underwater end plug to be cleaned according to the comparison result.
Based on the technical scheme, the invention has at least the following beneficial effects:
1. according to the method, after the underwater environment image is acquired and the position of the end plug to be cleaned is determined, a cleaning path is generated by using a PSO algorithm, and meanwhile, the moving distance, the pitch angle and the yaw angle of the robot in the cleaning path are corrected by using a fractional order sliding film back-off algorithm to obtain an optimal cleaning path.
2. According to the invention, the underwater environment image is acquired based on the monocular stereoscopic vision algorithm, and the image is processed to restore the real underwater environment, so that a more accurate underwater environment map is conveniently formed, the position of the underwater end plug to be cleaned can be more accurately determined, and a foundation is provided for searching an optimal path.
3. According to the invention, the weight and the learning factors are iteratively updated, so that the searching direction and speed of particles in the PSO algorithm are adjusted in real time, the limitation in searching the optimal path in the prior art can be solved, and the optimal path can be found more quickly.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of a method for path planning for a cleaning robot for an underwater end plug of a nuclear power plant according to an embodiment of the present invention;
FIG. 2 is a flow chart of generating a cleaning path using a PSO algorithm in one embodiment of the present invention;
FIG. 3 is a flow chart of generating a cleaning path using a PSO algorithm in accordance with another embodiment of the present invention;
fig. 4 is a schematic diagram of a path planning apparatus of a cleaning robot for an underwater end plug of a nuclear power station according to an embodiment of the present invention.
Detailed Description
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other. The invention will be described in detail below with reference to the drawings in connection with embodiments.
The invention is described in further detail below in connection with specific examples which are not to be construed as limiting the scope of the invention as claimed.
Examples
In order to solve the problems in the prior art, the invention provides a path planning method for a cleaning robot for an underwater end plug of a nuclear power station, which utilizes a PSO algorithm to generate a cleaning path, and corrects the moving distance, pitch angle and yaw angle of the robot in the cleaning path through a fractional order sliding film back-step algorithm on the basis of the cleaning path to obtain an optimal cleaning path, so that the cleaning position reached by the robot is more accurate.
In order to achieve the above purpose, the invention provides a path planning method of a cleaning robot for an underwater end plug of a nuclear power station.
A flow chart of a path planning method of a cleaning robot for an underwater end plug of a nuclear power station according to an embodiment of the present invention is shown in fig. 1, and the method includes the steps of:
s1, acquiring an image of an underwater environment based on a monocular stereoscopic vision algorithm.
Specifically, the method for acquiring the image of the underwater environment based on the monocular stereoscopic vision algorithm comprises two substeps of S101 and S102, which are described in detail as follows:
s101, acquiring initial position coordinates of a robot, and tracking the track of the robot.
In this step S101, first, the robot initial position coordinates, specifically, three-dimensional coordinates of the four end angles before and after the robot initial position, need to be acquired. And then, the robot is required to track, so that a complete underwater environment image is conveniently acquired.
S102, image acquisition is carried out on the underwater environment based on the monocular stereoscopic vision algorithm.
According to the invention, the underwater environment image is acquired, and meanwhile, the robot movement angle parameter, the robot acceleration parameter and the robot movement track parameter are acquired based on three-dimensional attitude sensors arranged on the front end corner and the rear end corner of the robot.
In order to facilitate visual positioning and calculate the position, posture and movement of an object, the embodiment fastens a high-contrast characteristic mark on a working table surface before image acquisition, and acquires characteristic mark movement sequence images with a sufficient frame number through a camera. In order to facilitate the calculation of the edge position, edge sub-pixel extraction is required for the acquired linear motion characteristics of the characteristic mark motion sequence image with a sufficient frame number in the X and Y directions. The high contrast feature markers refer to markers that are unique and highly contrasted, such as grids, checkerboards, etc., and such markers are relatively easy to detect and track in an image or video.
Specifically, the process of edge sub-pixel extraction includes: and determining the region of interest on the feature marker image, and extracting the sub-pixel coordinates of the long and short edge points of the feature marker rectangle in the region of interest. Based on the result of the edge sub-pixel coordinate extraction, the world coordinates of the characteristic edge points of the linear motion in the X and Y directions can be obtained by solving. And (3) solving the motion displacement of the characteristic edges in the X and Y directions based on the world coordinates obtained by solving, and finally fitting the motion displacement in the X and Y directions respectively by utilizing a sine approximation method to obtain a corresponding displacement peak value and an initial phase, so as to obtain a plane motion track and realize the detection of the position and the gesture of the robot.
Monocular stereoscopic vision SLAM initialization is achieved based on collected initial position coordinates of a robot, underwater environment image data, robot motion angle parameters, robot acceleration parameters, robot motion track parameters and robot motion speed parameters, and a map is constructed. The map comprises a three-dimensional obstacle model, a three-dimensional robot model, three-dimensional coordinates of front and rear end angles and relative distance parameters between the robot surface of each obstacle and the robot.
Through the operation, the underwater environment image position and the underwater environment map can be obtained, and a foundation is provided for determining the position of the underwater end plug to be cleaned and planning the path.
S2, determining the underwater end plug to be cleaned according to the image of the underwater environment.
The steps include two sub-steps S201 and S202, which are described in detail as follows:
s201, carrying out refinement treatment on the image of the underwater environment, and acquiring the image characteristics of the underwater end plug in the image.
Specifically, the refinement of the image of the underwater environment includes the following:
first, color or spatial domain adjustment is performed on an image of an underwater environment, color difference correction is completed on a per-pixel basis, difference information is recorded, and a tone dynamic range of the image is mapped to an appropriate range.
Secondly, in order to eliminate noise influence and keep image detail information as far as possible, in the embodiment, the image of the underwater environment is processed by adopting a bilateral filtering method so as to improve the signal to noise ratio of the image, and edge texture detail in the image is kept by introducing the difference of pixel neighborhoods.
Finally, the transmission rate transfer function is refined by adopting the guide filter, so that the influence of water scattering and absorption on the image can be effectively reduced, and the definition and contrast of the underwater environment image are improved.
Based on the operation, the refinement processing of the underwater environment image can be realized. In this step, it is also necessary to obtain the image features of the underwater plug in the image for image feature analysis.
S202, comparing the acquired image characteristics of the underwater end plug with preset characteristics, and determining the underwater end plug to be cleaned according to the comparison result.
Comparing the image features of the underwater end plug obtained in the step S201 with preset features, wherein the preset features refer to the image features of the initial underwater end plug, and determining the underwater end plug to be cleaned and the position information thereof according to the comparison result.
And S3, generating a cleaning path by using a PSO algorithm based on the position information of the underwater end plug to be cleaned.
The particle swarm optimization algorithm (Particle Swarm Optimization, PSO) is an optimization algorithm based on swarm intelligence, which is used for solving the continuous optimization problem. The basic idea of the PSO algorithm is to consider the search space as a collection of particles, each particle representing a potential solution, and find the optimal solution by simulating the flight process of each particle in the search space, continuously updating the position and speed of the particle, and recording the global optimal position and the historical optimal position of the particle. The PSO algorithm is utilized in the present invention to generate the cleaning path.
Specifically, as shown in fig. 2, in one embodiment of the present invention, the step S3 specifically includes the following sub-steps:
s301, determining the position and the speed of particles corresponding to the cleaning path by using the formula I and the formula II.
Wherein,for the speed of the ith particle in the kth iteration,/and->For the d-dimensional component of each particle's position in the kth iteration, r 1 、r 2 Is [0,1]Random number, c 1 、c 2 As a learning factor, ω is an inertial weight.
In particular, the effect of the weight ω is to control the inertia of the particle, i.e. the speed and direction of movement of the particle in the search space according to equation one. In general, a larger weight may cause the particles to have a stronger inertia, thereby accelerating the search, but may cause the search process to be too localized; smaller weights may cause the particles to have weaker inertia, thus having a greater chance to jump out of the locally optimal solution, but the search speed may slow down.
Learning factor c 1 、c 2 The function of (a) is to control the influence degree of particles on the history optimal solution, and a larger learning factor c 1 、c 2 Particles can be influenced by the historical optimal solution more, so that the convergence speed is accelerated, but searching is too local and a global optimal solution is not easy to find; while smaller learning factors may allow the particle to explore more of the search space, but convergence speed may slow.
Therefore, the invention proposes the weight omega and the learning factor c 1 、c 2 Iterative updating is performed to adjust the search direction and speed of the particles in the PSO algorithm so as to find the optimal path more quickly. In the present embodiment, the weight ω and the learning factor c 1 、c 2 The specific updating method is as follows in step S302.
S302, carrying out iterative updating on the weight value in the formula I by using the formula III, carrying out iterative updating on the learning factors in the formula I by using the formula IV and the formula V, and obtaining k iteratively updated cleaning paths.
Wherein τ is a control coefficient, c max 、c min For learning the maximum and minimum values of the factors, the coefficients α, β 1 、β 2 ＞0。
Specifically, the weight value omega in the formula one is iteratively updated by using the formula three, and the learning factor c in the formula one is updated by using the formula four and the formula five 1 、c 2 Iterative updating is carried out on the weight value omega and the learning factor c 1 、c 2 After updating, the position and the speed of the particles are correspondingly updated according to the formula I and the formula II.
And updating the historical optimal position and the global optimal position of the particles according to the iteration result, and obtaining k cleaning paths according to the global optimal position.
S303, selecting an optimal cleaning path from k cleaning paths.
In this embodiment, the cleaning path having the smallest fitness among the k cleaning paths is taken as the optimal cleaning path. Specifically, the fitness can reflect the error of the cleaning path, and the smaller the fitness is, the smaller the error of the cleaning path is, and the more accurate the cleaning position the robot reaches according to the cleaning path.
Furthermore, as shown in fig. 3, in another embodiment of the present invention, the generating a cleaning path by using a PSO algorithm based on the position information of the underwater end plug to be cleaned further includes the following sub-steps:
s304, judging whether the current iteration number K reaches the total iteration number K.
S305, if the current iteration number K reaches the total iteration number K, stopping iteratively updating the cleaning path.
And if the current iteration number K is judged to reach the total iteration number K, stopping iteratively updating the cleaning path, and determining the optimal cleaning path.
S306, if the current iteration number K does not reach the total iteration number K, continuing to update the cleaning path in an iteration mode.
If the current iteration number K is judged to not reach the total iteration number K, continuing to iteratively update the weight and the learning factor, and further updating the position and the speed of the particles to generate a new cleaning path.
S4, correcting the cleaning path by using a fractional order synovial film backstepping algorithm.
Specifically, in one embodiment of the present invention, the moving distance of the robot in the cleaning path is corrected by the formula six and the formula seven.
Wherein k is x1 >0，k x2 >0，Representing gain coefficients e x1 、/>Position error of robot along x, y axis, respectively,>as fractional order coefficient, u x 、u y The distances of movement of the robot along the x, y axes, respectively.
Movement of the robot along the x, y axis obtained by equation six and equation sevenDistance ux, u y And (3) correcting the optimal cleaning path obtained in the step (S3) so that the cleaning position reached by the robot is more accurate, and the accuracy of the operation is ensured.
In addition, to further improve the accuracy of reaching the cleaning position by the robot, in another embodiment of the present invention, the cleaning path is modified by using a fractional order synovial film back-step algorithm, and further includes: and correcting the pitch angle and the yaw angle of the robot in the cleaning path according to a formula eight. The formula eight is as follows:
wherein U is 1 Is the control rate of the robot, m is the mass of the robot, theta d Is the pitch angle phi of the robot d Is the yaw angle of the robot, e x1 For positional errors of the robot along the x-axis,k is the speed error of the robot moving along the y axis y Gain factor for fractional order synovial membrane, < ->s y And g is gravitational acceleration, which is a fractional order coefficient.
Specifically, the above formula eight is derived by the following expression:
wherein u is x 、u y The moving distance of the robot along the x and y axes is expressed by the formula six and the formula seven; pitch angle phi of robot d Yaw angle theta d The method can be obtained by solving and calculating a position subsystem, and can be specifically expressed as:
the pitch angle phi of the robot is combined with the parameters d Yaw angle theta d Distance of movement u of robot along x, y axis x 、u y Can be solved to obtain the control rate U 1 Through U 1 And correcting the pitch angle and the yaw angle of the robot in the cleaning path.
S5, executing cleaning action based on the corrected cleaning path.
And taking the correction result of the cleaning path by using the fractional order synovial film back-off algorithm in the step as a final cleaning path, and controlling the robot to execute cleaning action on the underwater end plug to be cleaned according to the cleaning path.
In order to achieve the above purpose, the invention further provides a path planning device of the cleaning robot for the underwater end plugs of the nuclear power station.
A schematic diagram of a path planning apparatus of a cleaning robot for an underwater end plug of a nuclear power plant according to an embodiment of the present invention is shown in fig. 4, the apparatus including: an acquisition module 41, a determination module 42, a generation module 43, a correction module 44, an execution module 45.
An acquisition module 41 for acquiring an image of the underwater environment based on a monocular stereoscopic algorithm.
Further, the obtaining module 41 is configured to:
and acquiring initial position coordinates of the robot, and tracking the track of the robot.
And acquiring images of the underwater environment based on the monocular stereoscopic vision algorithm.
A determining module 42 for determining an underwater end plug to be cleaned from an image of said underwater environment.
Further, the determining module 42 is configured to:
and carrying out refinement treatment on the image of the underwater environment, and acquiring the image characteristics of the underwater plug in the image.
Comparing the acquired image characteristics of the underwater end plug with preset characteristics, and determining the underwater end plug to be cleaned according to the comparison result.
It should be understood that, the path planning device of the cleaning robot for the underwater end plug of the nuclear power station is consistent with the description of the corresponding path planning method embodiment of the cleaning robot for the underwater end plug of the nuclear power station, so that the description of the embodiment is omitted.
In summary, as can be seen from the above description, the above embodiments of the path planning method and apparatus for a cleaning robot for an underwater end plug of a nuclear power station of the present invention achieve the following technical effects:
1. according to the method, after the underwater environment image is acquired and the position of the end plug to be cleaned is determined, a cleaning path is generated by using a PSO algorithm, and meanwhile, the moving distance, the pitch angle and the yaw angle of the robot in the cleaning path are corrected by using a fractional order sliding film back-off algorithm to obtain an optimal cleaning path.
2. According to the invention, the underwater environment image is acquired based on the monocular stereoscopic vision algorithm, and the image is processed to restore the real underwater environment, so that a more accurate underwater environment map is conveniently formed, the position of the underwater end plug to be cleaned can be more accurately determined, and a foundation is provided for searching an optimal path.
3. According to the invention, the weight and the learning factors are iteratively updated, so that the searching direction and speed of particles in the PSO algorithm are adjusted in real time, the limitation in searching the optimal path in the prior art can be solved, and the optimal path can be found more quickly.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, 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 phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
It should be noted that in the description of the present specification, descriptions of terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Claims (10)
1. The path planning method of the cleaning robot for the underwater end plug of the nuclear power station is characterized by comprising the following steps of:
acquiring an image of an underwater environment based on a monocular stereoscopic vision algorithm;
determining an underwater end plug to be cleaned according to the image of the underwater environment;
generating a cleaning path by using a PSO algorithm based on the position information of the underwater end plug to be cleaned;
correcting the cleaning path by using a fractional order synovial film backstepping algorithm;
and performing a cleaning action based on the corrected cleaning path.
2. The method of claim 1, wherein the monocular-based stereoscopic algorithm acquires an image of an underwater environment, comprising:
acquiring initial position coordinates of a robot, and tracking a track of the robot;
and acquiring images of the underwater environment based on the monocular stereoscopic vision algorithm.
3. The method of claim 1, wherein the determining the subsea end plug to be cleaned from the image of the subsea environment comprises:
carrying out refinement treatment on the image of the underwater environment, and acquiring the image characteristics of the underwater plug in the image;
comparing the acquired image characteristics of the underwater end plug with preset characteristics, and determining the underwater end plug to be cleaned according to the comparison result.
4. The method of claim 1, wherein generating a cleaning path using a PSO algorithm based on position information of the subsea end plug to be cleaned comprises:
the position and velocity of the particles corresponding to the cleaning path are determined using equations one and two,
equation one:
formula II:
wherein,for the speed of the ith particle in the kth iteration,/and->For the d-dimensional component of each particle's position in the kth iteration, r 1 、r 2 Is [0,1]Random number, c 1 、c 2 As a learning factor, ω is an inertial weight;
iteratively updating the weight value in the formula I by using the formula III, iteratively updating the learning factors in the formula I by using the formula IV and the formula V, obtaining k iteratively updated cleaning paths,
and (3) a formula III:
equation four:
formula five:
wherein τ is a control coefficient; c max 、c min Maximum and minimum values for learning factors; coefficient alpha beta 1 、β 2 ＞0；
An optimal cleaning path is selected from the k cleaning paths.
5. The method of claim 4, wherein generating a cleaning path using a PSO algorithm based on position information of the subsea end plug to be cleaned, further comprises:
judging whether the current iteration number K reaches the total iteration number K or not;
stopping iteratively updating the cleaning path if the current iteration number K reaches the total iteration number K;
and if the current iteration number K does not reach the total iteration number K, continuing to iteratively update the cleaning path.
6. The method of claim 1, wherein modifying the cleaning path using a fractional slip film back-off algorithm comprises:
correcting the moving distance of the robot in the cleaning path through a formula six and a formula seven,
formula six:
formula seven:
wherein k is x1 >0，k x2 >0，Representing gain coefficients e x1 、e y1 Position error of robot along x, y axis, respectively,>as fractional order coefficient, u x 、u y The distances of movement of the robot along the x, y axes, respectively.
7. The method of claim 6, wherein modifying the cleaning path using a fractional slip film back-off algorithm further comprises:
correcting the pitch angle and yaw angle of the robot in the cleaning path according to a formula eight, wherein the formula eight is as follows:
wherein U is 1 Is the control rate of the robot, m is the mass of the robot, theta d Is the pitch angle phi of the robot d Is the yaw angle of the robot, e x1 For positional errors of the robot along the x-axis,k is the speed error of the robot moving along the y axis y Gain factor for fractional order synovial membrane, < ->s y And g is gravitational acceleration, which is a fractional order coefficient.
8. A path planning apparatus for a nuclear power station underwater end plug cleaning robot, comprising:
the acquisition module is used for acquiring an image of the underwater environment based on a monocular stereoscopic vision algorithm;
the determining module is used for determining an underwater end plug to be cleaned according to the image of the underwater environment;
the generating module is used for generating a cleaning path by using a PSO algorithm based on the position information of the underwater end plug to be cleaned;
the correction module is used for correcting the cleaning path by using a fractional order synovial film back-off algorithm;
and the execution module is used for executing the cleaning action based on the corrected cleaning path.
9. The apparatus of claim 8, wherein the acquisition module is configured to:
acquiring initial position coordinates of a robot, and tracking a track of the robot;
and acquiring images of the underwater environment based on the monocular stereoscopic vision algorithm.
10. The apparatus of claim 8, wherein the means for determining is configured to:
carrying out refinement treatment on the image of the underwater environment, and acquiring the image characteristics of the underwater plug in the image;
comparing the acquired image characteristics of the underwater end plug with preset characteristics, and determining the underwater end plug to be cleaned according to the comparison result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311242931.8A CN117470239A (en) | 2023-09-21 | 2023-09-21 | Path planning method and device for cleaning robot of underwater end plug of nuclear power station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311242931.8A CN117470239A (en) | 2023-09-21 | 2023-09-21 | Path planning method and device for cleaning robot of underwater end plug of nuclear power station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117470239A true CN117470239A (en) | 2024-01-30 |
Family
ID=89632057
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311242931.8A Pending CN117470239A (en) | 2023-09-21 | 2023-09-21 | Path planning method and device for cleaning robot of underwater end plug of nuclear power station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117470239A (en) |
-
2023
- 2023-09-21 CN CN202311242931.8A patent/CN117470239A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109579849B (en) | Robot positioning method, robot positioning device, robot and computer storage medium | |
| WO2017028653A1 (en) | Method and system for automatically establishing map indoors by mobile robot | |
| CN109416843B (en) | Real-time altitude mapping | |
| CN110163968A (en) | RGBD camera large-scale three dimensional scenario building method and system | |
| CN105910604A (en) | Multi-sensor-based autonomous obstacle avoidance navigation system | |
| Kim et al. | UAV-UGV cooperative 3D environmental mapping | |
| Al-Mutib et al. | Stereo vision SLAM based indoor autonomous mobile robot navigation | |
| Quan et al. | AGV localization based on odometry and LiDAR | |
| Zhao et al. | Review of slam techniques for autonomous underwater vehicles | |
| CN116619358A (en) | Self-adaptive positioning optimization and mapping method for autonomous mining robot | |
| CN113778096B (en) | Positioning and model building method and system for indoor robot | |
| Malayjerdi et al. | Mobile robot navigation based on fuzzy cognitive map optimized with grey wolf optimization algorithm used in augmented reality | |
| CN112975939A (en) | Dynamic trajectory planning method for cooperative mechanical arm | |
| Taherian et al. | Image-based visual servoing improvement through utilization of adaptive control gain and pseudo-inverse of the weighted mean of the Jacobians | |
| Zhou et al. | RETRACTED: uncalibrated dynamic visual servoing via multivariate adaptive regression splines and improved incremental extreme learning machine | |
| CN117470239A (en) | Path planning method and device for cleaning robot of underwater end plug of nuclear power station | |
| Jones et al. | Using neural networks to learn hand-eye co-ordination | |
| CN111207754A (en) | Particle filter-based multi-robot formation positioning method and robot equipment | |
| CN109542094B (en) | Mobile robot vision stabilization control without desired images | |
| CN115855086A (en) | Indoor scene autonomous reconstruction method, system and medium based on self-rotation | |
| Tahara et al. | Ex-dof: Expansion of action degree-of-freedom with virtual camera rotation for omnidirectional image | |
| Vonásek et al. | Techniques for modeling simulation environments for modular robotics | |
| Chen et al. | Active scene reconstruction via self-rotation driven by optimized information theory | |
| WO2023100282A1 (en) | Data generation system, model generation system, estimation system, trained model production method, robot control system, data generation method, and data generation program | |
| Sinisa | Evaluation of SLAM Methods and Adaptive Monte Carlo 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 |