CN111260123B - Cluster recovery control method, device and equipment and readable storage medium - Google Patents

Cluster recovery control method, device and equipment and readable storage medium Download PDF

Info

Publication number
CN111260123B
CN111260123B CN202010030544.8A CN202010030544A CN111260123B CN 111260123 B CN111260123 B CN 111260123B CN 202010030544 A CN202010030544 A CN 202010030544A CN 111260123 B CN111260123 B CN 111260123B
Authority
CN
China
Prior art keywords
auvs
recovery
initial
cluster
optimal
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.)
Active
Application number
CN202010030544.8A
Other languages
Chinese (zh)
Other versions
CN111260123A (en
Inventor
黄裘俊
张爱东
李胜全
常亮
朱华
陆海博
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Peng Cheng Laboratory
Original Assignee
Peng Cheng Laboratory
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Peng Cheng Laboratory filed Critical Peng Cheng Laboratory
Priority to CN202010030544.8A priority Critical patent/CN111260123B/en
Publication of CN111260123A publication Critical patent/CN111260123A/en
Application granted granted Critical
Publication of CN111260123B publication Critical patent/CN111260123B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047Optimisation of routes or paths, e.g. travelling salesman problem
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B63SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
    • B63CLAUNCHING, HAULING-OUT, OR DRY-DOCKING OF VESSELS; LIFE-SAVING IN WATER; EQUIPMENT FOR DWELLING OR WORKING UNDER WATER; MEANS FOR SALVAGING OR SEARCHING FOR UNDERWATER OBJECTS
    • B63C11/00Equipment for dwelling or working underwater; Means for searching for underwater objects
    • B63C11/52Tools specially adapted for working underwater, not otherwise provided for
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/23Clustering techniques
    • G06F18/232Non-hierarchical techniques
    • G06F18/2321Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Development Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Mechanical Engineering (AREA)
  • Ocean & Marine Engineering (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The invention discloses a cluster recovery control method, a device, equipment and a medium, wherein the cluster recovery control method realizes recovery of a plurality of Autonomous Underwater Vehicles (AUVs) by using an Unmanned Surface Vessel (USV) through two parts of operations. The first part is used for determining the initial recovery path planning and the recovery sequence of the AUV; in the second part, the MPC is controlled to update the initial recovery path based on model prediction. Specifically, through the established dynamic models of the AUVs and the USVs, and according to the constraint conditions, an objective function for determining the optimal sequence and path of the recovered AUVs is determined, so that the collision condition possibly occurring in the recovery process is avoided; the nonlinear integer programming problem is solved by using an external approximation algorithm to obtain an optimal recovery sequence and an initial recovery path, and compared with a traditional manual recovery mode, the time cost is greatly reduced; the recycling path is continuously optimized by obtaining the actual measured value, the recycling efficiency is further improved, and the purpose of efficiently, quickly, safely and automatically recycling a plurality of AUVs in a cluster manner is achieved.

Description

Cluster recovery control method, device and equipment and readable storage medium
Technical Field
The invention relates to the technical field of robots, in particular to a cluster recovery control method, a cluster recovery control device, cluster recovery control equipment and a readable storage medium.
Background
An Autonomous Underwater Vehicle (AUV) is an Autonomous unmanned Underwater robot that performs Underwater tasks without the need for control by an operator. The recovery technology of the AUV is to ensure that the AUV can be quickly recovered after the AUV performs the specified task and returns, and is a leading-edge technology in the field of marine application. At present, the most common recovery mode is manual salvage by a mother ship crew, the automation level and efficiency of the recovery mode are low, time and labor are wasted, the time for recovering one AUV is usually more than 30 minutes, and the technical problem that the efficiency for manually salvaging a plurality of AUVs is low is caused. In addition, the manual salvage mode also has higher requirements on the sea state environment, and the manual recovery mode also poses threats to the safety of people.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a cluster recovery control method, and aims to solve the technical problem that manual salvaging of a plurality of AUVs is low in efficiency.
In order to achieve the above object, the present invention provides a cluster recovery control method, which is applied to a cluster recovery control device, and includes the following steps:
acquiring a dynamic model required by recycling a plurality of Autonomous Underwater Vehicles (AUVs), and determining an objective function based on a preset AUV constraint condition, wherein the objective function is used for solving the optimal sequence and path of recycling the AUVs;
solving a nonlinear integer programming problem constructed based on the dynamic model based on an external approximation algorithm to obtain the optimal recovery sequence and the initial recovery path of the AUVs corresponding to the objective function;
and acquiring a target measurement value acquired at a preset sampling time point, and updating the initial recovery path based on the target measurement value to obtain the optimal recovery paths of the AUVs.
Optionally, the step of obtaining a target measurement value acquired at a preset sampling time point, and updating the initial recovery path based on the target measurement value to obtain an optimal recovery path of the plurality of AUVs includes:
when the current time point is the preset sampling time point, acquiring position and angle measurement values of the AUVs based on preset trajectory tracking equipment;
and updating the initial recovery path according to the position and angle measurement values, and determining the optimal recovery path of the AUVs at each sampling time interval.
Optionally, after the step of obtaining the optimal recycling order and the initial recycling path of the plurality of AUVs corresponding to the objective function, the method further includes:
and updating the optimal path by utilizing a Model Predictive Control (MPC) based on the sampling time interval.
Optionally, before the step of solving the nonlinear integer programming problem constructed based on the dynamic model based on the external approximation algorithm and obtaining the optimal recovery sequence and the initial recovery path of the plurality of AUVs corresponding to the objective function, the method further includes:
converting the nonlinear integer programming problem into a multi-traveler problem, and converting the multi-traveler problem into a plurality of independent traveler problems by using a K-means clustering algorithm.
Optionally, the step of converting the multi-traveler question into a plurality of independent traveler questions using a K-means clustering algorithm comprises:
acquiring the number of USVs of the unmanned surface vessels for salvaging the AUVs, and determining the number of the USVs as the initial clustering centers of the number of the USVs;
distributing the AUVs to one of the initial clusters one by one according to a shortest distance principle to generate an initial target set with the number of the USVs;
calculating a mean vector of each initial target set, and taking the mean vector as a new clustering center;
and when the distance between the new clustering center and the initial clustering center is smaller than a preset threshold value, taking the new clustering center as a target clustering center, and determining the independent travelling salesman problems according to the target clustering center.
Optionally, the step of solving a nonlinear integer programming problem constructed based on the dynamic model based on an external approximation algorithm to obtain the optimal recovery sequence and the initial recovery path of the plurality of AUVs corresponding to the objective function includes:
establishing a completely undirected graph corresponding to the target clustering center, and selecting any vertex in the completely undirected graph as a root node, wherein the vertex is the position of the AUVs corresponding to the completely undirected graph;
determining a minimum spanning tree of the completely undirected graph using Prim algorithm;
traversing the minimum spanning tree in a forward sequence, acquiring a vertex table determined based on the traversal sequence, and adding the root node to the tail of the vertex table;
and determining the optimal recovery sequence and the initial recovery path according to the sequence of each vertex in the vertex table and by combining the preset AUV constraint condition.
Optionally, before the step of obtaining a dynamic model required for recovering a plurality of autonomous underwater vehicles AUV and determining an objective function based on preset AUV constraint conditions, the method further includes:
and initializing the dynamic model according to the preset initial conditions of the AUVs.
In addition, to achieve the above object, the present invention further provides a cluster recycling control apparatus, including:
the target function determining module is used for acquiring a dynamic model required by recovering a plurality of AUVs, and determining a target function based on a preset AUV constraint condition and the dynamic model, wherein the target function is used for solving the optimal sequence and path of recovering the AUVs;
the optimal problem solving module is used for solving a nonlinear integer programming problem constructed based on the dynamic model based on an external approximation algorithm to obtain the optimal recovery sequence and the initial recovery path of the AUVs corresponding to the objective function;
and the recovery path updating module is used for acquiring a target measurement value acquired at a preset sampling time point and updating the initial recovery path based on the target measurement value so as to acquire the optimal recovery paths of the AUVs.
In addition, to achieve the above object, the present invention further provides a cluster recycling control apparatus, including: the cluster recycling control method comprises a memory, a processor and a cluster recycling control program which is stored on the memory and can run on the processor, wherein when the cluster recycling control program is executed by the processor, the steps of the cluster recycling control method are realized.
In addition, to achieve the above object, the present invention also provides a computer readable storage medium, on which a cluster recovery control program is stored, and the cluster recovery control program realizes the steps of the cluster recovery control method as described above when executed by a processor.
The invention provides a cluster recovery control method, a cluster recovery control device, cluster recovery control equipment and a computer readable storage medium. The cluster recovery control method comprises the steps of determining an objective function based on preset AUV constraint conditions by acquiring a dynamic model required by recovery of a plurality of Autonomous Underwater Vehicles (AUVs), wherein the objective function is used for solving the optimal sequence and path of the recovery of the AUVs; solving a nonlinear integer programming problem constructed based on the dynamic model based on an external approximation algorithm to obtain the optimal recovery sequence and the initial recovery path of the AUVs corresponding to the objective function; and acquiring a target measurement value acquired at a preset sampling time point, and updating the initial recovery path based on the target measurement value to obtain the optimal recovery paths of the AUVs. Through the mode, the established kinematic and dynamic models of the AUVs and the USVs are used for determining the objective function for solving the optimal sequence and path of the recovered AUVs according to the preset constraint conditions, so that the collision condition possibly occurring in the recovery process is avoided, and the practicability of the method is improved; the nonlinear integer programming problem is solved by using an external approximation algorithm to obtain an optimal recovery sequence and an initial recovery path, and compared with a traditional manual recovery mode, the recovery time and the recovery cost are greatly reduced; the recovery path is continuously optimized by obtaining the actual measurement value, the recovery efficiency is further improved, the cluster recovery of the AUVs is efficiently, quickly, safely and automatically realized, and the technical problem of low efficiency of manually salvaging the AUVs is solved.
Drawings
FIG. 1 is a schematic diagram of an apparatus architecture of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a cluster recycling control method according to a first embodiment of the present invention;
FIG. 3 is a schematic diagram of a system structure of a cluster recovery control method according to the present invention;
fig. 4 is a functional block diagram of an embodiment of the apparatus of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
As shown in fig. 1, fig. 1 is a schematic terminal structure diagram of a hardware operating environment according to an embodiment of the present invention.
The terminal of the embodiment of the invention can be a PC, and can also be a mobile terminal device with a display function, such as a smart phone, a tablet personal computer and the like.
As shown in fig. 1, the terminal may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a memory device separate from the processor 1001 described above.
Optionally, the terminal may further include a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WiFi module, and the like. Such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor that adjusts the brightness of the display according to the brightness of ambient light, and a proximity sensor that turns off the display and/or the backlight when the mobile terminal moves to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally three axes), detect the magnitude and direction of gravity when the mobile terminal is stationary, and can be used for applications (such as horizontal and vertical screen switching, related games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer and tapping) and the like for recognizing the attitude of the mobile terminal; of course, the mobile terminal may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which are not described herein again.
Those skilled in the art will appreciate that the terminal structure shown in fig. 1 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a cluster reclamation control program.
In the terminal shown in fig. 1, the network interface 1004 is mainly used for connecting to a backend server and performing data communication with the backend server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to call the cluster reclamation control program stored in the memory 1005 and perform the following operations:
acquiring a dynamic model required by recycling a plurality of Autonomous Underwater Vehicles (AUVs), and determining an objective function based on a preset AUV constraint condition, wherein the objective function is used for solving the optimal sequence and path for recycling the AUVs;
solving a nonlinear integer programming problem constructed based on the dynamic model based on an external approximation algorithm to obtain the optimal recovery sequence and the initial recovery path of the AUVs corresponding to the objective function;
and acquiring a target measurement value acquired at a preset sampling time point, and updating the initial recovery path based on the target measurement value to obtain the optimal recovery paths of the AUVs.
Further, the processor 1001 may call the cluster reclamation control program stored in the memory 1005, and further perform the following operations:
when the current time point is the preset sampling time point, acquiring position and angle measurement values of the AUVs based on preset trajectory tracking equipment;
and updating the initial recovery path according to the position and angle measurement values, and determining the optimal recovery path of the AUVs at each sampling time interval.
Further, the processor 1001 may call the cluster reclamation control program stored in the memory 1005, and further perform the following operations:
and updating the optimal path by using a Model Predictive Control (MPC) based on the sampling time interval.
Further, the processor 1001 may call the cluster reclamation control program stored in the memory 1005, and further perform the following operations:
converting the nonlinear integer programming problem into a multi-traveler problem, and converting the multi-traveler problem into a plurality of independent traveler problems by using a K-means clustering algorithm.
Further, the processor 1001 may call the cluster reclamation control program stored in the memory 1005, and further perform the following operations:
acquiring the number of USVs of the unmanned surface vessels for salvaging the AUVs, and determining the number of the USVs as the initial clustering centers of the number of the USVs;
distributing the AUVs to one of the initial clusters one by one according to a shortest distance principle to generate an initial target set with the number of the USVs;
calculating a mean vector of each initial target set, and taking the mean vector as a new clustering center;
and when the distance between the new clustering center and the initial clustering center is smaller than a preset threshold value, taking the new clustering center as a target clustering center, and determining the independent travelling business problems according to the target clustering center.
Further, the processor 1001 may call the cluster reclamation control program stored in the memory 1005, and further perform the following operations:
establishing a complete undirected graph corresponding to the target clustering center, and selecting any vertex in the complete undirected graph as a root node, wherein the vertex is a position of the AUVs corresponding to the complete undirected graph;
determining a minimum spanning tree of the completely undirected graph using Prim algorithm;
traversing the minimum spanning tree in a forward sequence, acquiring a vertex table determined based on the traversal sequence, and adding the root node to the tail of the vertex table;
and determining the optimal recovery sequence and the initial recovery path according to the sequence of each vertex in the vertex table and by combining the preset AUV constraint condition.
Further, the processor 1001 may call the cluster reclamation control program stored in the memory 1005, and further perform the following operations:
and initializing the dynamic model according to the preset initial conditions of the AUVs.
Based on the above hardware structure, embodiments of the cluster recycling control method of the present invention are provided.
Referring to fig. 2, fig. 2 is a flowchart illustrating a first embodiment of a cluster recycling control method.
An Autonomous Underwater Vehicle (AUV) is an Autonomous unmanned Underwater robot that performs Underwater tasks without the need for control by an operator. The recovery technology of the AUV is to ensure that the AUV can be quickly recovered after the AUV performs the specified task and returns, and is a leading-edge technology in the field of marine application. At present, the most common recovery mode is manual salvage by a mother ship crew, the automation level and efficiency of the recovery mode are low, time and labor are wasted, the time for recovering one AUV is usually more than 30 minutes, and the technical problem that the efficiency for manually salvaging a plurality of AUVs is low is caused. In addition, the manual salvage mode also has higher requirements on the sea state environment, and the manual recovery mode also threatens the safety of people. It should be noted that the AUV has only one propeller, so that the maneuverability is poor, and an Unmanned Surface Vessel (USV) with higher maneuverability is required for the cluster recovery of the AUV to assist the recovery. Future ocean development needs more AUVs to cooperate with offshore operation, and AUV cluster recovery is necessary.
In this embodiment, to solve the above problem, the present invention provides a cluster recovery control method, that is, a nonlinear integer programming problem for solving an optimal sequence and path of recovering AUVs is determined by using a plurality of preset dynamic models of the AUVs and USVs, so as to provide a technical basis for solving the nonlinear integer programming problem; the nonlinear integer programming problem is solved by utilizing an external approximation algorithm and combining various practical constraint conditions, so that the collision condition possibly occurring in the recovery process is avoided, and the practicability of the method is improved; the optimal recovery sequence and the initial recovery path are obtained after the solution, and compared with the traditional manual recovery mode, the recovery time and the recovery cost are greatly reduced; the recovery path is continuously optimized by obtaining the actual measurement value, the recovery efficiency is further improved, the cluster recovery of the AUVs is efficiently, quickly, safely and automatically realized, and the technical problem of low efficiency of manually salvaging the AUVs is solved. The cluster recovery control method is applied to the terminal provided with the cluster recovery control program.
A first embodiment of the present invention provides a cluster recovery control method, including the steps of:
step S10, acquiring a dynamic model required by recycling a plurality of Autonomous Underwater Vehicles (AUVs), and determining an objective function based on a preset AUV constraint condition, wherein the objective function is used for solving the optimal sequence and path for recycling the AUVs;
the preset AUV constraint condition can be an underwater robot boundary constraint condition, an underwater robot collision constraint condition, an underwater robot termination constraint condition, an obstacle avoidance constraint condition and the like.
In this embodiment, it can be understood that, before step S10, corresponding dynamic models need to be established for the multiple AUVs and the USVs required for recovering the multiple AUVs. The dynamic model may be a dynamic model, a kinematic model, or the like. In an actual scene, when a recovery controller needs to recover a plurality of AUVs, a recovery task creation button preset in a terminal with a cluster recovery control program can be clicked. The terminal receives a recovery task creating instruction currently sent by a recovery controller, acquires a plurality of AUVs to be recovered and dynamic models of corresponding USVs, and constructs a Mixed Integer Nonlinear Programming problem (MINLP) by taking the optimal recovery sequence and the time optimal motion path of the AUVs as target functions according to the preset dynamic models and combining constraint conditions such as boundary constraint, collision constraint, termination constraint, obstacle avoidance constraint and the like. The integer programming problem refers to an optimization problem of minimizing or maximizing an objective function under the limitation of some equality constraints, inequality constraints and integer variables. If all functions in the problem are linear, then the problem is linear integer programming; otherwise, it is called the nonlinear integer programming problem. In addition, the number of the USVs for salvaging the AUV may be one or more, which is not limited in this embodiment.
Step S20, solving a nonlinear integer programming problem constructed based on the dynamic model based on an external approximation algorithm, and acquiring the optimal recovery sequence and the initial recovery path of the AUVs corresponding to the objective function;
wherein, the external approximation algorithm is an algorithm for finding an approximation method to solve the optimization problem.
In this embodiment, the terminal solves the nonlinear integer programming problem constructed according to the dynamic model according to a preset approximate algorithm for solving the nonlinear integer programming problem, and converts a solution result into an optimal recovery sequence corresponding to the recovery of the plurality of AUVs and an initial recovery path of the USV. Specifically, if the number of USVs is plural and the number of USVs is smaller than the number of AUVs to be recovered, the MINLP can be regarded as a multi-travel agency Problem (MTSP). The terminal can convert the multi-traveler problem into independent traveler problems with the number equal to the number of the USVs by using a K-means clustering algorithm, then the independent traveler problems are solved by using an approximate algorithm, a plurality of solving results are integrated, and finally the optimal sequence and the initial recycling path for recycling the AUVs are generated.
Step S30, obtaining a target measurement value collected at a preset sampling time point, and updating the initial recovery path based on the target measurement value to obtain an optimal recovery path of the plurality of AUVs.
In this embodiment, it is understood that the recycling control person may set a specific sampling time interval on the terminal before step S30. And the terminal acquires the actual positions, angles and other information of the AUVs to be recovered at each sampling time point based on the trajectory tracking module, updates the initial recovery path according to the information, and generates the optimal recovery path of each AUV to be recovered.
Specifically, as shown in fig. 3, the recycling control personnel may set up a cluster recycling control system on the terminal. The system is divided into two parts, wherein a first part is an initial solving module, a plurality of AUVs and USVs are established by performing off-line path planning on the AUVs to be recovered, and the model is initialized according to initial conditions of the AUVs. The system sets boundary constraint conditions, collision constraint conditions, termination constraint conditions and obstacle avoidance constraint conditions of multiple AUVs and USVs. And constructing the MINLP by taking the AUV optimal recovery sequence and the time optimal motion path as an objective function. The system establishes an MINLP off-line solver based on an external approximation algorithm to solve the MINLP, and a recovery task sequence and an initial optimal path for recovering a plurality of AUV tasks are obtained. The second part is a Model Predictive Control (MPC) module, and the MINLP, namely a priority time open-loop optimization problem, is solved on line by acquiring current measurement information at each sampling time point, and a first element of an obtained Control sequence acts on a controlled object. And at the next sampling time point, using new measurement information as an initial condition for predicting the future dynamic state of the system, updating the optimization problem and solving again to continuously optimize the optimal recovery path of each AUV.
The invention provides a cluster recovery control method. The cluster recovery control method comprises the steps of determining an objective function based on preset AUV constraint conditions by acquiring a dynamic model required by recovery of a plurality of Autonomous Underwater Vehicles (AUVs), wherein the objective function is used for solving the optimal sequence and path of the recovery of the AUVs; solving a nonlinear integer programming problem constructed based on the dynamic model based on an external approximation algorithm to obtain the optimal recovery sequence and the initial recovery path of the AUVs corresponding to the objective function; and acquiring a target measurement value acquired at a preset sampling time point, and updating the initial recovery path based on the target measurement value to obtain the optimal recovery paths of the AUVs. Through the mode, the established kinematic and dynamic models of the AUVs and the USVs are used for determining the objective function for solving the optimal sequence and path of the recovered AUVs according to the preset constraint conditions, so that the collision condition possibly occurring in the recovery process is avoided, and the practicability of the method is improved; the nonlinear integer programming problem is solved by using an external approximation algorithm to obtain an optimal recovery sequence and an initial recovery path, and compared with a traditional manual recovery mode, the recovery time and the recovery cost are greatly reduced; the recovery path is continuously optimized by obtaining the actual measurement value, the recovery efficiency is further improved, the cluster recovery of the AUVs is efficiently, quickly, safely and automatically realized, and the technical problem of low efficiency of manually salvaging the AUVs is solved.
Not shown in the drawings, a second embodiment of the cluster recycling control method according to the present invention is provided based on the first embodiment shown in fig. 2. In the present embodiment, step S30 includes:
step a, when the current time point is the preset sampling time point, acquiring the position and angle measurement values of the AUVs based on preset trajectory tracking equipment;
in this embodiment, the terminal may adopt a feedback control strategy of MPC. And the terminal acquires position measurement values and angle measurement values of a plurality of AUVs to be recovered, which are acquired by preset trajectory tracking equipment, at each sampling time point according to a preset sampling time interval.
And b, updating the initial recovery path according to the position and angle measurement values, and determining the optimal recovery path of the AUVs at each sampling time interval.
In this embodiment, the terminal solves the MINLP problem on line according to the MPC algorithm by using the position measurement value and the angle measurement value acquired at each sampling time point, and applies the first element of the obtained control sequence to the controlled object. And at the next sampling time point, using new measurement information as an initial condition for predicting future dynamics, updating the problem, and solving the nonlinear integer programming problem again to continuously optimize the optimal recovery path of each AUV.
Further, in this embodiment, before step S20, the method further includes:
and c, updating the optimal path by utilizing a model predictive control MPC based on the sampling time interval.
In this embodiment, the terminal uses the MPC as a feedback control algorithm to predict the future output of the process, and the sampling time interval, i.e. the sampling period, needs to be preset. If the sampling period is too large, the system response is too slow, so that the correction control is difficult to be performed in time, and if the sampling period is too small, a large amount of online optimization calculation is generated by the system, so that a large expense is brought to the system. Therefore, the sampling period design is suggested to adopt one tenth or one twentieth of the open loop response time (10-90% rise time). The terminal obtains current measurement information at each sampling time point based on the MPC, solves the MINLP on line, namely a priority time open loop optimization problem, and enables the first element of the obtained control sequence to act on the controlled object. And at the next sampling time point, using new measurement information as an initial condition for predicting the future dynamic state of the system, updating the optimization problem and solving again to continuously optimize the optimal recovery path of each AUV.
Further, in this embodiment, before step S10, the method further includes:
and d, initializing the dynamic model according to the preset initial conditions of the AUVs.
In this embodiment, before the terminal constructs the MINLP problem and solves the objective function, it needs to perform parameter initialization on the dynamic models corresponding to the plurality of AUVs and USVs to be recovered according to initial conditions such as initial position information and initial angle information of the AUVs and USVs, so as to improve the practicability of the dynamic models.
The invention provides a cluster recovery control method. The cluster recovery control method further performs path tracking on the AUVs to be recovered to acquire information such as actual position angles and the like so as to continuously optimize the recovery path, further perfects the initial recovery path, and further improves the practicability and recovery efficiency of the cluster recovery control method; by adopting the MPC algorithm, the mutual influence parameters between input and output are convenient to construct, the convenient addition of constraint conditions is supported, and the MPC algorithm has prediction capability; the dynamic model is initialized through the preset initial condition of the AUV, the adaptability of the dynamic model and the actual AUV equipment is improved, and the practicability of the final recovery sequence and path is further improved.
Not shown in the drawings, a third embodiment of the cluster recycling control method according to the present invention is proposed based on the first embodiment shown in fig. 2. In this embodiment, before step S20, the method further includes:
and e, converting the nonlinear integer programming problem into a multi-traveler problem, and converting the multi-traveler problem into a plurality of independent traveler problems by using a K-means clustering algorithm.
In this embodiment, if the number of USVs is plural and the number of USVs is smaller than the number of AUVs to be recovered, the MINLP can be regarded as the multi-traveler problem MTSP. The terminal can convert the multi-traveler problem into independent traveler problems with the number equal to the number of the USVs by using a K-means clustering algorithm, then solves the independent traveler problems by using an approximate algorithm, and integrates a plurality of solution results to generate an optimal sequence and an initial recovery path for recovering a plurality of AUVs.
Further, in this embodiment, step d includes:
f, acquiring the number of USVs of the unmanned surface vessels for salvaging the AUVs, and determining the number of the USVs as the initial clustering centers of the number of the USVs;
in this embodiment, according to an approximation algorithm, the terminal determines the number of USVs for executing the current recovery task, sets the number of USVs as K, sets the number of AUVs to be recovered as N, and selects any one of the K initial clustering centers.
Step g, distributing the AUVs to one of the initial clustering centers one by one according to a shortest distance principle to generate an initial target set with the number of the USVs;
in this embodiment, the terminal calculates the distance from each AUV to be recovered to each initial clustering center, and allocates each AUV to the initial clustering center corresponding to the shortest distance, thereby generating K initial target sets. Each initial target set includes an initial cluster center and several AUVs.
H, calculating a mean vector of each initial target set, and taking the mean vector as a new clustering center;
in this embodiment, the terminal calculates mean vectors of K initial target sets, and uses the mean vector corresponding to each initial target set as a new clustering center of each initial target set, that is, updates the K initial target sets.
And i, when the distance between the new clustering center and the initial clustering center is smaller than a preset threshold value, taking the new clustering center as a target clustering center, and determining the independent travelling salesman problems according to the target clustering center.
The preset threshold value may be flexibly set according to actual conditions, and this embodiment does not specifically limit this.
In this embodiment, step h is repeated, and the distance between the new cluster center and the initial cluster center in each iteration is calculated. Until the terminal detects that the distance between a new clustering center and an initial clustering center in the current round number iteration process is smaller than a preset threshold value, the terminal can judge that the convergence condition is met currently, receives iterative computation, takes the current new clustering center as a final target clustering center, and considers a plurality of AUVs corresponding to each target clustering center as a group, wherein each group can correspond to an independent traveler problem.
Further, in the present embodiment, step S20 includes:
step j, establishing a complete undirected graph corresponding to the target clustering center, and selecting any vertex in the complete undirected graph as a root node, wherein the vertex is the position of the AUVs corresponding to the complete undirected graph;
in this embodiment, the terminal constructs K independent traveling salesman questions according to the K sets of AUVs obtained in step i. And the terminal establishes K completely undirected graphs according to the position of each group of AUV, wherein the position of each AUV is a vertex in the graph. The terminal arbitrarily selects one vertex in each completely undirected graph as a root node.
Step k, determining a minimum spanning tree of the completely undirected graph by using a Prim algorithm;
in this embodiment, a single completely undirected graph is taken as an example. And (4) setting the completely undirected graph as G, the minimum spanning tree as T, the set V as all the vertexes in the G, the set U as the vertex already walked in the G, and the set U-V as the vertex not walked in the G. (1) Traversing from a starting point a in G, adding a into the set U, and replacing a from the set U-V; (2) searching the terminal point b of the side which is associated with the a in the set U and has the minimum weight in the rest n-1 vertexes in the set U-V, adding the b into the set U, and replacing the b from the set U-V; (3) similarly, searching the end point c of the side which is associated with the a or the b in the set U and has the minimum weight in the remaining n-2 vertexes in the set U-V, adding the c into the set U, and replacing the c from the set U-V; (4) and (4) repeating the step (3) until all the vertexes in the G are added into the set U and the set U-V is empty, so that the vertexes in the set U form the minimum spanning tree T.
Step l, traversing the minimum spanning tree in a front sequence, acquiring a vertex table determined based on the traversal sequence, and adding the root node to the tail of the vertex table;
in this embodiment, the terminal obtains K minimum spanning trees, performs a forward traversal on each minimum spanning tree, forms a vertex table from traversed nodes, and then adds K root nodes to the end of the corresponding vertex table.
And m, determining the optimal recovery sequence and the initial recovery path according to the sequence of each vertex in the vertex table and by combining the preset AUV constraint condition.
In this embodiment, the terminal obtains the order of the vertices in each vertex table after the root node is added, and integrates the order of K groups of vertices to generate the optimal recovery order of each of the N AUVs to be recovered. And the terminal sequentially connects the vertexes in each vertex table to obtain the Hamiltonian loop of each minimum spanning tree, and determines the initial recovery path corresponding to each AUV to be recovered by combining the constraint conditions such as the boundary constraint, the collision constraint, the termination constraint, the obstacle avoidance constraint and the like.
The invention provides a cluster recovery control method. The cluster recovery control method further converts the multi-traveler problem corresponding to the cluster recovery AUV into a plurality of independent traveler problems through a K-means clustering algorithm, reduces the complexity of the problems and improves the solving efficiency of the nonlinear integer programming problem; the nonlinear integer programming problem is solved by using an approximate algorithm and combining constraint conditions, so that the recovery sequence and the recovery path of a plurality of AUVs to be recovered can be quickly obtained, and the method has higher efficiency, automation degree and safety compared with the traditional manual salvage mode.
The invention also provides a cluster recovery control device.
The cluster recycling control device includes:
the system comprises an objective function determining module, a dynamic model acquiring module and a dynamic model acquiring module, wherein the dynamic model is required by recovering a plurality of Autonomous Underwater Vehicles (AUVs), and an objective function is determined based on preset AUV constraint conditions, wherein the objective function is used for solving the optimal sequence and path of recovering the AUVs;
the optimal problem solving module is used for solving a nonlinear integer programming problem constructed based on the dynamic model based on an external approximation algorithm to obtain the optimal recovery sequence and the initial recovery path of the AUVs corresponding to the objective function;
and the recovery path updating module is used for acquiring a target measurement value acquired at a preset sampling time point and updating the initial recovery path based on the target measurement value so as to acquire the optimal recovery paths of the AUVs.
The invention also provides cluster recovery control equipment.
The cluster recycling control device comprises a processor, a memory and a cluster recycling control program which is stored on the memory and can run on the processor, wherein when the cluster recycling control program is executed by the processor, the steps of the cluster recycling control method are realized.
The method implemented when the cluster recycling control program is executed may refer to each embodiment of the cluster recycling control method of the present invention, and details are not described here again.
The invention also provides a computer readable storage medium.
The computer readable storage medium of the present invention has stored thereon a cluster reclamation control program, which when executed by a processor implements the steps of the cluster reclamation control method as described above.
The method implemented when the cluster recycling control program is executed may refer to each embodiment of the cluster recycling control method of the present invention, and details are not described here again.
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 system 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 system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims (7)

1. A cluster reclamation control method, comprising:
acquiring a dynamic model required by recovering a plurality of Autonomous Underwater Vehicles (AUVs), and determining an objective function based on a preset AUV constraint condition, wherein the objective function is used for solving an optimal recovery sequence and a recovery path for recovering the AUVs;
solving a nonlinear integer programming problem constructed based on the dynamic model based on an external approximation algorithm to obtain the optimal recovery sequence and the initial recovery path of a plurality of AUVs corresponding to the target function;
acquiring target measurement values acquired at preset sampling time points, and updating the initial recovery path based on the target measurement values to obtain the optimal recovery paths of the AUVs;
before the step of solving the nonlinear integer programming problem constructed based on the dynamic model and obtaining the optimal recovery sequence and the initial recovery path of the plurality of AUVs corresponding to the objective function based on the external approximation algorithm, the method further includes:
converting a nonlinear integer programming problem constructed based on the dynamic model into a multi-traveler problem, and converting the multi-traveler problem into a plurality of independent traveler problems by using a K-means clustering algorithm;
the step of converting the multi-traveler question into a plurality of independent traveler questions using a K-means clustering algorithm comprises:
acquiring the number of USVs of the unmanned surface vessels for salvaging the AUVs, and determining the number of initial clustering centers equal to the number of the USVs;
distributing the AUVs to one of the initial clusters one by one according to a shortest distance principle to generate initial target sets with the number equal to that of the USVs;
calculating a mean vector of each initial target set, and taking the mean vector as a new clustering center;
when the distance between the new clustering center and the initial clustering center is smaller than a preset threshold value, taking the new clustering center as a target clustering center, and determining the independent traveling salesman problems according to the target clustering center;
the step of solving the nonlinear integer programming problem constructed based on the dynamic model based on the external approximation algorithm to obtain the optimal recovery sequence and the initial recovery path of the plurality of AUVs corresponding to the objective function comprises the following steps:
establishing a complete undirected graph corresponding to the target clustering center, and selecting any vertex in the complete undirected graph as a root node, wherein the vertex is a position of the AUVs corresponding to the complete undirected graph;
determining a minimum spanning tree of the completely undirected graph using Prim algorithm;
traversing the minimum spanning tree in a forward sequence, acquiring a vertex table determined based on the traversal sequence, and adding the root node to the tail of the vertex table;
and determining the optimal recovery sequence and the initial recovery path according to the sequence of each vertex in the vertex table and by combining the preset AUV constraint condition.
2. The cluster recycling control method of claim 1, wherein the step of obtaining a target measurement value collected at a preset sampling time point, and updating the initial recycling path based on the target measurement value to obtain an optimal recycling path of the plurality of AUVs comprises:
when the current time point is the preset sampling time point, acquiring position and angle measurement values of the AUVs based on preset trajectory tracking equipment;
and updating the initial recovery path according to the position and angle measurement values, and determining the optimal recovery path of the AUVs at each sampling time interval.
3. The cluster reclamation control method of claim 2, wherein after the step of obtaining the optimal reclamation order and the initial reclamation path for the plurality of AUVs corresponding to the objective function, further comprising:
and updating the optimal path by utilizing a Model Predictive Control (MPC) based on the sampling time interval.
4. The cluster reclamation control method of claim 1, wherein before the step of obtaining the dynamic model required for reclaiming the Autonomous Underwater Vehicles (AUVs) and determining the objective function based on the preset AUV constraints, the method further comprises:
and initializing the dynamic model according to the preset initial conditions of the AUVs.
5. A cluster recycling control apparatus, comprising:
the system comprises an objective function determining module, a dynamic model acquiring module and a recovery module, wherein the objective function determining module is used for acquiring the dynamic model required by recovering a plurality of Autonomous Underwater Vehicles (AUVs), and determining an objective function based on a preset AUV constraint condition, and the objective function is used for solving the optimal recovery sequence and recovery path for recovering the AUVs;
the optimal problem solving module is used for solving a nonlinear integer programming problem constructed based on the dynamic model based on an external approximation algorithm to obtain the optimal recovery sequence and the initial recovery path of a plurality of AUVs corresponding to the objective function;
the recovery path updating module is used for acquiring a target measurement value acquired at a preset sampling time point, and updating the initial recovery path based on the target measurement value to acquire an optimal recovery path of the AUVs;
the cluster recycling control device is further configured to:
converting a nonlinear integer programming problem constructed based on the dynamic model into a multi-traveler problem, and converting the multi-traveler problem into a plurality of independent traveler problems by using a K-means clustering algorithm;
acquiring the number of USVs of the unmanned surface vessels for salvaging the AUVs, and determining the number of initial clustering centers equal to the number of the USVs;
distributing the AUVs to one of the initial clusters one by one according to a shortest distance principle to generate initial target sets with the number equal to that of the USVs;
calculating a mean vector of each initial target set, and taking the mean vector as a new clustering center;
when the distance between the new clustering center and the initial clustering center is smaller than a preset threshold value, taking the new clustering center as a target clustering center, and determining the independent traveling salesman problems according to the target clustering center;
the optimal problem solving module is further configured to:
establishing a complete undirected graph corresponding to the target clustering center, and selecting any vertex in the complete undirected graph as a root node, wherein the vertex is a position of the AUVs corresponding to the complete undirected graph;
determining a minimum spanning tree of the completely undirected graph using Prim algorithm;
traversing the minimum spanning tree in a forward sequence, acquiring a vertex table determined based on the traversal sequence, and adding the root node to the tail of the vertex table;
and determining the optimal recovery sequence and the initial recovery path according to the sequence of each vertex in the vertex table and by combining the preset AUV constraint condition.
6. A cluster reclamation control apparatus, characterized in that the cluster reclamation control apparatus comprises: memory, a processor and a cluster reclamation control program stored on the memory and executable on the processor, the cluster reclamation control program when executed by the processor implementing the steps of the cluster reclamation control method as claimed in any one of claims 1 to 4.
7. A computer-readable storage medium, having stored thereon a cluster reclamation control program which, when executed by a processor, implements the steps of the cluster reclamation control method as recited in any one of claims 1 to 4.
CN202010030544.8A 2020-01-09 2020-01-09 Cluster recovery control method, device and equipment and readable storage medium Active CN111260123B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010030544.8A CN111260123B (en) 2020-01-09 2020-01-09 Cluster recovery control method, device and equipment and readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010030544.8A CN111260123B (en) 2020-01-09 2020-01-09 Cluster recovery control method, device and equipment and readable storage medium

Publications (2)

Publication Number Publication Date
CN111260123A CN111260123A (en) 2020-06-09
CN111260123B true CN111260123B (en) 2022-07-01

Family

ID=70950433

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010030544.8A Active CN111260123B (en) 2020-01-09 2020-01-09 Cluster recovery control method, device and equipment and readable storage medium

Country Status (1)

Country Link
CN (1) CN111260123B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106444759A (en) * 2016-09-29 2017-02-22 浙江嘉蓝海洋电子有限公司 Automatic homeward voyaging method and automatic homeward voyaging system of unmanned boat
CN107807670A (en) * 2017-12-21 2018-03-16 合肥灵猫传媒有限公司 A kind of unmanned plane cluster flight control system
CN109238291A (en) * 2018-10-26 2019-01-18 河海大学 A kind of planing method of water surface unmanned boat guiding cable recycling Autonomous Underwater Vehicle
CN110472790A (en) * 2019-08-16 2019-11-19 集美大学 A kind of more unmanned boat paths planning methods, terminal device and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106444759A (en) * 2016-09-29 2017-02-22 浙江嘉蓝海洋电子有限公司 Automatic homeward voyaging method and automatic homeward voyaging system of unmanned boat
CN107807670A (en) * 2017-12-21 2018-03-16 合肥灵猫传媒有限公司 A kind of unmanned plane cluster flight control system
CN109238291A (en) * 2018-10-26 2019-01-18 河海大学 A kind of planing method of water surface unmanned boat guiding cable recycling Autonomous Underwater Vehicle
CN110472790A (en) * 2019-08-16 2019-11-19 集美大学 A kind of more unmanned boat paths planning methods, terminal device and storage medium

Also Published As

Publication number Publication date
CN111260123A (en) 2020-06-09

Similar Documents

Publication Publication Date Title
CN108986801B (en) Man-machine interaction method and device and man-machine interaction terminal
Xiang et al. Robust fuzzy 3D path following for autonomous underwater vehicle subject to uncertainties
US10140719B2 (en) System and method for enhancing target tracking via detector and tracker fusion for unmanned aerial vehicles
Sarabakha et al. Novel Levenberg–Marquardt based learning algorithm for unmanned aerial vehicles
CN109434831B (en) Robot operation method and device, robot, electronic device and readable medium
CN110287941B (en) Concept learning-based thorough perception and dynamic understanding method
US11281208B2 (en) Efficient teleoperation of mobile robots via online adaptation
CN113012219A (en) Information processing apparatus, information processing method, and computer readable medium
US20210264188A1 (en) Image prediction system
Mishra et al. Machine Learning Approach for Unmanned Aerial Vehicle’s Path Scheduling and Precise Circle Detection
Devo et al. Autonomous single-image drone exploration with deep reinforcement learning and mixed reality
EP4204914A1 (en) Remote operation of robotic systems
CN115047890B (en) Unmanned ship control method, unmanned ship control device and computer-readable storage medium
CN111259526B (en) Cluster recovery path planning method, device, equipment and readable storage medium
CN112414401A (en) Unmanned aerial vehicle cooperative positioning system and method based on graph neural network
CN111260123B (en) Cluster recovery control method, device and equipment and readable storage medium
CN109062677B (en) Unmanned aerial vehicle system calculation migration method
Yang et al. Decentralised formation control and stability analysis for multi-vehicle cooperative manoeuvre
Elhaki et al. Saturated output-feedback hybrid reinforcement learning controller for submersible vehicles guaranteeing output constraints
US20220383073A1 (en) Domain adaptation using domain-adversarial learning in synthetic data systems and applications
JP2021099383A (en) Information processing apparatus, information processing method, and program
JP2021099384A (en) Information processing apparatus, information processing method, and program
Zhang et al. Partially-observable monocular autonomous navigation for uav through deep reinforcement learning
Hasankhani et al. Integrated path planning and control through proximal policy optimization for a marine current turbine
Jia et al. An improved semantic segmentation and fusion method for semantic SLAM

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant