CN113160614A - Ice zone near-field route dynamic optimization method - Google Patents

Ice zone near-field route dynamic optimization method Download PDF

Info

Publication number
CN113160614A
CN113160614A CN202110318737.8A CN202110318737A CN113160614A CN 113160614 A CN113160614 A CN 113160614A CN 202110318737 A CN202110318737 A CN 202110318737A CN 113160614 A CN113160614 A CN 113160614A
Authority
CN
China
Prior art keywords
route
ice
airway
course
ship
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.)
Withdrawn
Application number
CN202110318737.8A
Other languages
Chinese (zh)
Inventor
王胜正
张学生
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.)
Shanghai Maritime University
Original Assignee
Shanghai Maritime University
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 Shanghai Maritime University filed Critical Shanghai Maritime University
Priority to CN202110318737.8A priority Critical patent/CN113160614A/en
Publication of CN113160614A publication Critical patent/CN113160614A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G3/00—Traffic control systems for marine craft
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G3/00—Traffic control systems for marine craft
    • G08G3/02—Anti-collision systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • General Health & Medical Sciences (AREA)
  • Ocean & Marine Engineering (AREA)
  • Molecular Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Computational Linguistics (AREA)
  • Game Theory and Decision Science (AREA)
  • Biomedical Technology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Artificial Intelligence (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Genetics & Genomics (AREA)
  • Physiology (AREA)
  • Primary Health Care (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides a method for dynamically optimizing an ice region near-field route. According to the method, sea ice echo data of an ice region are acquired through a ship self-loading radar device, ship navigation data, the sea ice echo data and sea ice density data are overlapped in an electronic chart, and an ice region navigation scene is established and updated in real time; an ice-avoiding route optimization model which aims at minimizing the route distance and the route risk is constructed based on the actual route planning requirement of the ship navigating in the ice area, and the calculation of the route risk is represented by the distance between the whole route and sea ice; solving and designing the model based on a multi-objective evolutionary algorithm NSGA-II; the method comprises the steps of designing an airway dynamic optimization flow, obtaining a cluster airway and an optimized course by repeatedly carrying out airway optimization on a scene, comparing the optimized course with a ship-to-ground course, and recommending the course. By updating and processing radar echo data in real time, the air route is optimized in real time, the ship course is updated recursively, and the dynamic optimization of the air route in the ice region is realized.

Description

Ice zone near-field route dynamic optimization method
The technical field is as follows:
the application relates to the field of ship ice region navigation, in particular to a dynamic optimization method for an ice region near-field route.
Background art:
under the background of global economy and vigorous international shipping development, the development demand of shipping world in polar regions is more and more intense, and the development of polar shipping in the future is in scale and diversified. The polar region ice region navigation environment is characterized in that the floating ice is dense, the floating ice drifts randomly along with wind current, and the dense floating ice is accompanied with icebergs, so that a crew is difficult to identify the icebergs in the navigation process, and the navigation route selection is difficult. In the current polar region navigation process, the burden of sailers is heavy and the risk index is high. Therefore, how to carry out intelligent route selection and navigation on the ship in the polar region ice region, avoid the risk of touching ice during navigation, ensure the safety and high efficiency of the ship navigation, improve the economic benefit of navigation and be a research hotspot of polar region shipping in the present and even the future.
In recent years, much research has been conducted around the ice region of the polar region at home and abroad. Most of researches mainly focus on extracting and analyzing distribution information of obstructive objects (icebergs and floating ice) in an ice region, mainly use a satellite remote sensing image and a sea ice prediction model, and establish a path planning model on the basis to obtain a safe air route in the ice region, so that the navigation risk in the ice region is effectively reduced. These basically focus on route planning under the macro scale, but the navigation environment in the ice region is dynamically changed, the complexity of the ice condition is high, and when the route planning is performed by only depending on a sea ice model, a satellite image, an ice density map and the like, the route selection problem caused by local ice condition change encountered in actual navigation of a ship cannot be solved, and effective guidance for the ice region near-field route is lacked, so that the ice region intelligent navigation is still a challenging subject.
The invention content is as follows:
an object of the present application is to provide a method for dynamically optimizing an ice zone near-field route, so as to solve the problem of dynamically optimizing a local route in the current ice zone navigation process, that is, obtaining surrounding sea ice coverage information based on a real-time radar echo image of a ship, establishing a multi-target near-field route optimization model with a minimum navigation distance and a minimum navigation risk as targets, solving the route by using a multi-target evolutionary algorithm, and obtaining an optimal route that balances the navigation risk and the navigation distance.
According to one aspect of the application, a method for dynamically optimizing an ice region near-field route is provided, and the method comprises the following steps:
the method comprises the following steps: and constructing a navigation scene in the ice region.
The method comprises the steps of preprocessing sea ice echo data, wherein radar images generally comprise information such as current ship position information, Course On Ground (COG), ship Heading (HDG), measuring range, fixed range marker circle and historical track line, extracting real-time scanning echo images of ship-borne radar equipment to obtain real-time echo data of sea ice, displaying the real-time echo data in an electronic chart, and establishing an ice region near-field airway optimization scene. And meanwhile, extracting effective digital information on the radar.
Step two: and establishing an ice avoidance airway optimization model.
And establishing a near-field route optimization model taking the shortest route distance and the minimum navigation risk as targets. And the model can carry out dynamic optimization on the route based on the real-time position of the ship and the expected position set by a user.
The planning of the route of the ship in the ice area is carried out from the current position p0Past the turning point p1，p2，...，pn-1To pnThe short route can be divided into n sections, and the total sailing distance calculation formula is as follows:
Figure BDA0002991908770000031
wherein, L (p)i，pi+1) Indicating the distance from the turning point.
The vector for each leg that makes up the airway is represented as: v1，V2，…，VnThe linear equation of the Cartesian coordinate system of each flight segment is as follows:
wixi+γi＝0，i＝1，…，n。
further, based on the above equation, the minimum distance from the sea ice echo to each leg can be calculated as follows:
Figure BDA0002991908770000032
wherein the content of the first and second substances,
Figure BDA0002991908770000033
representing the distance from the center of the radar target to the front of the target.
Further, based on the above process, the minimum distance between the whole route and the sea ice echo can be calculated, and the formula is as follows:
dmin＝min{d1，d2，…，dn}
the minimization of the flight risk is actually to keep all flight segments away from the ice floes or icebergs, i.e. the goal of route optimization is to maximize the minimum distance between the route and the ice floes or icebergs. The calculation formula is expressed as follows:
Figure BDA0002991908770000034
thus, the problem of minimizing the sailing risk is expressed as:
Figure BDA0002991908770000035
Figure BDA0002991908770000036
Figure BDA0002991908770000037
∈>0
the problem of minimizing the flight distance is expressed as:
Figure BDA0002991908770000041
Figure BDA0002991908770000042
further, based on the above process, the multi-objective problem model for minimizing the navigation risk and the navigation distance is defined as follows:
minp∈Ω[f1(p)，f2(p)]
wherein f ═ f1，f2]The target vector of the target space is the node p ═ p of the optimized route0，p1，…，pn]Is a decision vector that is a vector of decisions,
Figure BDA0002991908770000043
is the decision space.
Step three: and (5) solving the route optimization model.
Further, based on the model, a model solving algorithm is designed. And solving the multi-target model by using an NSGA-II algorithm.
Consider each route as a chromosome p ═ p for individuals in the population0，p1，…，pn]Navigation node piAs chromosome gene position, the code is carried out by using the Greens code, and the gene sequence is consistent with the sequence of the airway nodes. And (3) evaluating the individuals by using an objective function defined in the model, setting the iteration times of the algorithm, continuously optimizing the population based on the NSGA-II algorithm, and finally obtaining an acceptable pareto frontier, namely an optimized airway solution set. Finally, a proper solution can be selected based on different sea ice scenes and the parameters of the ship, the balance between the airway risk and the airway distance is balanced, and the proper airway is decoded and airway nodes are output.
And further, performing ice region near-field route dynamic optimization based on the pretreatment of the sea ice echo data, the route optimization multi-objective model and the solving algorithm.
Step four: and dynamically optimizing the ice area near-field route.
Step 4.1: and initializing dynamic optimization of the ice area airway. Setting an airway node as an expected position, and setting the number N of times of airway optimization and a preset heading deviation value theta.
Step 4.2: and acquiring a real-time echo image of the shipborne radar equipment, and establishing an optimized scene. And receiving the real-time radar echo scanning video from the ship radar system to obtain radar echo data at the current moment, and displaying the radar echo data on the electronic chart on which the sea ice concentration chart is superimposed. Meanwhile, the current course of the ship to the ground is COG0
Step 4.3: and repeatedly solving the air route for many times by using an algorithm. Based on the navigation scene, the position of the ship is taken as an initial position, N suboptimization is carried out on the air routes by using an NSGA-II algorithm, because the optimized air routes are similar, a central air route is extracted by using a path clustering method, and the optimized course is calculated as COG1。
Step 4.4: calculating the deviation delta COG between the current course and the optimized course, wherein the formula is as follows:
ΔCOG＝|COG1-COG0|
if the course deviation delta COG is larger than the course deviation preset value theta, the optimized course COG is used1And as the recommended course, carrying out dynamic course correction.
Step 4.5: and updating and processing the radar echo image in real time, solving the airway by using an algorithm, and then recursively updating the ship course.
Compared with the prior art, the method has the advantages that sea ice echo data acquired by the shipborne radar equipment are preprocessed to obtain real-time sea ice distribution data around the ship, and the sea ice echo data are superposed on the electronic chart on which the sea ice concentration data are superposed; based on the actual situation of ice region navigation, a ship ice region dynamic optimization multi-target route optimization model with minimized navigation distance and minimized navigation risk is established; solving the multi-target route optimization model based on the NSGA-II algorithm and the Green code; and clustering repeated airway optimization results to obtain an optimized airway and a heading, and recommending the heading based on the set heading deviation. By updating the echo data of the shipborne radar equipment, repeatedly carrying out route solving by using an algorithm and recursively updating the ship course, the near-field route dynamic optimization of the ship in the whole route of the ice region is further realized, so that the ice contact risk in the route is reduced, and the intelligent degree of ice region navigation is improved.
Drawings
FIG. 1 is a schematic diagram of a near-field route optimization modeling based on ice region echo data in the ice region near-field route dynamic optimization method of the present invention;
FIG. 2 is a flow chart of a method for dynamically optimizing near-field routes in an ice region according to the present invention;
FIG. 3 is an image based on sea ice concentration data and ship real-time radar echo data superimposed on an electronic chart in the ice region near-field route dynamic optimization method of the present invention;
FIG. 4 is a schematic diagram of N times of route optimization based on a certain sea ice echo scene in the ice region near-field route dynamic optimization method of the present invention;
FIG. 5 is a schematic diagram of routes obtained after route clustering is performed on N times of route optimization results in the ice region near-field route dynamic optimization method of the present invention.
Detailed Description
The following describes in detail a method for dynamically optimizing a near-field route of an ice region according to the present invention with reference to the accompanying drawings.
As shown in FIG. 1, the method for near-field route optimization by using radar echo data of a ship sailing in an ice region comprises the following steps.
The method comprises the following steps: and constructing a navigation scene in the ice region.
The method includes the steps of determining ship navigation data, determining data required by the ship for route optimization in an ice region, and generally including sea ice echo data, sea ice concentration data and navigation dynamic data (including real-time ship position, ground course, preset course and the like) around the ship.
And (4) preprocessing data. Sea ice echo data; the radar image generally comprises information such as current ship position information, ground heading (COG), ship Heading (HDG), measuring range, fixed range mark circle, historical track line and the like. And extracting the real-time scanning echo image of the shipborne radar equipment to obtain real-time echo data of the sea ice. Navigation dynamic data; and extracting effective digital information such as ship position information, ground course and the like on the radar image. Sea ice concentration data; and downloading the latest sea ice concentration data from the authoritative meteorological website, and rendering the data in the electronic chart system in real time.
Further, the ship position of the ship is displayed in the electronic chart system, the latest sea ice echo data are superposed, and an ice area near-field route optimization scene is established.
Step two: and establishing an ice avoidance airway optimization model.
And (5) defining an ice area route optimization target. The course distance and the course risk are used as two important indexes for the course evaluation. The airway risk is the risk of assessing the airway by calculating the distance between the whole airway and sea ice.
And establishing a near-field route optimization model taking the shortest route distance and the minimum navigation risk as targets. And the model can carry out dynamic optimization on the route based on the real-time position of the ship and the expected position set by a user.
The planning of the route of the ship in the ice area is from the current position,0past the turning point p1，p2，...，pn-1To pnThe short route can be divided into n sections, and the total sailing distance calculation formula is as follows:
Figure BDA0002991908770000071
wherein, L (p)i，pi+1) Indicating the distance from the turning point.
The vector for each leg that makes up the airway is represented as: v1，V2，…，VnThe linear equation of the Cartesian coordinate system of each flight segment is as follows:
wixi+γi＝0，i＝1，…，n。
further, based on the above equation, the minimum distance from the sea ice echo to each leg can be calculated as follows:
Figure BDA0002991908770000072
wherein the content of the first and second substances,
Figure BDA0002991908770000073
representing the distance from the center of the radar target to the front of the target.
Further, based on the above process, the minimum distance between the whole route and the sea ice echo can be calculated, and the formula is as follows:
dmin＝min{d1，d2，…dn}
the minimization of the flight risk is actually to keep all flight segments away from the ice floes or icebergs, i.e. the goal of route optimization is to maximize the minimum distance between the route and the ice floes or icebergs. The calculation formula is expressed as follows:
Figure BDA0002991908770000081
the objective function for minimizing voyage risk is expressed as:
Figure BDA0002991908770000082
Figure BDA0002991908770000083
Figure BDA0002991908770000084
∈>0
the objective function for minimizing the flight distance is expressed as:
Figure BDA0002991908770000085
Figure BDA0002991908770000086
further, based on the above process, the multi-objective problem model for minimizing the navigation risk and the navigation distance is defined as follows:
minp∈Ω[f1(p)，f2(p)]
wherein f ═ f1，f2]The target vector of the target space is the node p ═ p of the optimized route0，p1，…，pn]Is a decision vector that is a vector of decisions,
Figure BDA0002991908770000087
is the decision space.
Step three: and (5) solving the route optimization model.
Further, based on the model, the route optimization is carried out on the real-time sea ice distribution scene around the ship fused with the electronic chart, and the NSGA-II algorithm is used for solving the multi-objective model.
Consider each route as a chromosome p ═ p for individuals in the population0，p1，…，pn]Navigation node piAs chromosome gene position, the code is carried out by using the Greens code, and the gene sequence is consistent with the sequence of the airway nodes. The method comprises the steps of evaluating individuals by using an objective function defined in a model, setting parameters such as iteration times, population size, variation and cross probability of an algorithm, optimizing the population based on an NSGA-II algorithm, sequencing through non-dominant solutions and congestion distances, and finally obtaining a pareto frontier of an acceptable solution, namely an optimized airway solution set.
The method can select a proper solution based on different sea ice scenes and parameters of the ship, balance between the airway risk and the airway distance, decode the proper airway, output airway nodes, and reversely display the airway nodes into the electronic chart system to guide a shipman to drive the ship.
Step four: and dynamically optimizing the ice area near-field route.
Further, based on the preprocessing of the data, a multi-objective model for route optimization and a solving algorithm are established, and ice region near-field route dynamic optimization is carried out, referring to fig. 2.
Step 4.1: and initializing dynamic optimization of the ice area airway. Setting an airway node as an expected position, and setting the number N of times of airway optimization and a preset heading deviation value theta.
Step 4.2: and acquiring a real-time echo image of the shipborne radar equipment, and establishing an optimized scene. Receiving a real-time radar echo scanning video from a ship radar system to obtain radar echo data at the current moment, and displaying the radar echo data on an electronic chart on which an sea ice concentration chart is superimposed as shown in fig. 3. Meanwhile, the current course of the ship to the ground is COG0。
Step 4.3: and repeatedly solving the air route for many times by using an algorithm. Based on the navigation scene, the position of the ship is taken as an initial position, N-time optimization is carried out on the route by using an NSGA-II algorithm, and a result obtained after N times of route planning are carried out on a certain scene is shown in FIG. 4. Because the optimized air routes are similar, a central air route is extracted by using a path clustering method, and the optimized course is calculated to be COG1. FIG. 5 is a final route for clustering the routes shown in FIG. 4.
Step 4.4: calculating the deviation delta COG between the current course and the optimized course, wherein the formula is as follows:
ΔCOG＝|COG1-COG0|
if the course deviation delta COG is larger than the course deviation preset value theta, the optimized course COG is used1And as the recommended course, carrying out dynamic course correction.
Step 4.5: judging whether the current position of the ship reaches an expected position, if not, updating and processing the radar echo image in real time, solving the route by using an algorithm, and then recursively updating the ship course; if so, the route optimization is terminated.

Claims (3)

1. A method for dynamically optimizing an ice region near-field route is characterized by comprising the following steps:
the method comprises the following steps: constructing an ice region navigation scene:
preprocessing the navigation data of the ship in the ice region, mainly acquiring real-time sea ice echo data through ship radar equipment, updating the sea ice density data in real time from a meteorological website and acquiring the navigation dynamic data of the ship, and establishing an ice region route optimization scene by superposing the three data in an electronic chart system;
step two: establishing an ice-avoiding airway optimization model:
the method comprises the following steps of establishing an ice region route optimization model aiming at minimizing the route distance and the route risk by taking two ice region routes as optimization indexes, dividing the route into n route sections, and calculating the total route distance according to the following formula:
Figure RE-FDA0003086573110000011
wherein, L (p)i，pi+1) Represents the distance from the turning point;
the vector for each leg that makes up the airway is represented as: v1，V2，···，VnThe linear equation of the Cartesian coordinate system of each flight segment is as follows:
wixi+γi＝0，i＝1，…，n
and (3) calculating the minimum distance from the sea ice echo to each flight segment, wherein the formula is as follows:
Figure RE-FDA0003086573110000012
wherein the content of the first and second substances,
Figure RE-FDA0003086573110000013
representing the distance from the center of the radar target to the front of the target;
further, based on the above process, the minimum distance between the overall route and the sea ice echo can be calculated, and the calculation formula is as follows:
dmin＝min{d1，d2，…，dn}
the objective of setting the flight risk minimization is to keep all flight segments away from the ice floe or iceberg, and the calculation formula is as follows:
Figure RE-FDA0003086573110000021
the objective function for minimizing voyage risk is expressed as:
Figure RE-FDA0003086573110000022
Figure RE-FDA0003086573110000023
Figure RE-FDA0003086573110000024
∈＞0
the objective function for minimizing the flight distance is expressed as:
Figure RE-FDA0003086573110000025
Figure RE-FDA0003086573110000026
based on the above process, the multi-objective problem model for minimizing the navigation risk and the navigation distance is defined as follows:
minp∈Ω[f1(p)，f2(p)]
wherein f ═ f1，f2]The target vector of the target space is the node p ═ p of the optimized route0，p1，···，pn]Is a decision vector that is a vector of decisions,
Figure RE-FDA0003086573110000027
is a decision space;
step three: solving an airway optimization model:
regarding each airway as a chromosome of an individual in the population, regarding airway nodes as chromosome gene positions, coding by using a Green code, evaluating the individual by using an objective function defined in the model, optimizing the population based on an NSGA-II algorithm, and finally obtaining a pareto frontier of an acceptable solution, namely an optimized airway solution set;
step four: and (3) dynamically optimizing the ice area near-field route:
step 4.1: initializing dynamic optimization of an ice area airway, setting an airway node as an expected position, and setting the number N of airway optimization times and a preset course deviation value theta;
step 4.2: preprocessing navigation data, namely receiving a real-time radar echo scanning video from a ship radar system to obtain radar echo data at the current moment, displaying the radar echo data on an electronic chart on which a sea ice concentration chart is superimposed, and simultaneously obtaining the current course of the ship to the ground as COG0；
Step 4.3: repeatedly solving the airway for many times by using an algorithm, based on the navigation scene, taking the position of the ship as an initial position, performing N suboptimization on the airway by using an NSGA-II algorithm, extracting a central airway by using a path clustering method, and calculating the optimized course as COG1；
Step 4.4: calculating the deviation delta COG between the current course and the optimized course, wherein the formula is as follows:
ΔCOG＝|COG1-COG0|
if the course deviation delta COG is larger than the course deviation preset value theta, the optimized course COG is used1As a recommended course, carrying out dynamic course correction;
step 4.5: and updating and processing the radar echo image in real time, solving the airway by using an algorithm, and then recursively updating the ship course.
2. An ice region near field dynamic route optimization device is characterized by comprising a processor and a memory connected with the processor through a communication bus; wherein the content of the first and second substances,
the memory is used for storing a dynamic route optimization program;
the processor is used for executing a dynamic route optimization program to realize the method for dynamically optimizing the near-field route in the ice region according to claim 1.
3. A storage device, wherein the storage device is a computer storage device on which the dynamic optimization program for airways of claim 1 is stored, the dynamic optimization program being executable by one or more processors to cause the one or more processors to perform the near field dynamic optimization method for airways of ice regions of claim 1.
CN202110318737.8A 2021-03-25 2021-03-25 Ice zone near-field route dynamic optimization method Withdrawn CN113160614A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110318737.8A CN113160614A (en) 2021-03-25 2021-03-25 Ice zone near-field route dynamic optimization method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110318737.8A CN113160614A (en) 2021-03-25 2021-03-25 Ice zone near-field route dynamic optimization method

Publications (1)

Publication Number Publication Date
CN113160614A true CN113160614A (en) 2021-07-23

Family

ID=76884871

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110318737.8A Withdrawn CN113160614A (en) 2021-03-25 2021-03-25 Ice zone near-field route dynamic optimization method

Country Status (1)

Country Link
CN (1) CN113160614A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116757055A (en) * 2023-08-11 2023-09-15 山东科技大学 Buoy platform-based multi-radar ship perception network layout optimization method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116757055A (en) * 2023-08-11 2023-09-15 山东科技大学 Buoy platform-based multi-radar ship perception network layout optimization method
CN116757055B (en) * 2023-08-11 2024-02-06 山东科技大学 Buoy platform-based multi-radar ship perception network layout optimization method

Similar Documents

Publication Publication Date Title
CN108256446B (en) Method, device and equipment for determining lane line in road
Tsou Multi-target collision avoidance route planning under an ECDIS framework
Tsou et al. The study of ship collision avoidance route planning by ant colony algorithm
CN110398250B (en) Unmanned ship global path planning method
CN112906830B (en) Automatic generation method of ship optimal route based on AIS big data
Tsou et al. Decision support from genetic algorithms for ship collision avoidance route planning and alerts
Zamuda et al. Differential evolution and underwater glider path planning applied to the short-term opportunistic sampling of dynamic mesoscale ocean structures
CN109933067A (en) A kind of unmanned boat collision prevention method based on genetic algorithm and particle swarm algorithm
CN113961004A (en) Pirate area ship route planning method and system, electronic equipment and storage medium
Tsou Integration of a geographic information system and evolutionary computation for automatic routing in coastal navigation
Xu et al. Heuristic and random search algorithm in optimization of route planning for Robot’s geomagnetic navigation
CN111721296B (en) Data driving path planning method for underwater unmanned vehicle
CN113283653B (en) Ship track prediction method based on machine learning and AIS data
CN113739807B (en) Navigation route navigation method and system for ship
CN113835102B (en) Lane line generation method and device
CN114152257A (en) Ship prediction navigation method based on attention mechanism and environment perception LSTM
CN113160614A (en) Ice zone near-field route dynamic optimization method
CN116469001A (en) Remote sensing image-oriented construction method of rotating frame target detection model
Seo et al. Ship collision avoidance route planning using CRI-based A∗ algorithm
CN116661479B (en) Building inspection path planning method, equipment and readable storage medium
Moon et al. RoMP-transformer: Rotational bounding box with multi-level feature pyramid transformer for object detection
CN110749325B (en) Flight path planning method and device
CN111259526B (en) Cluster recovery path planning method, device, equipment and readable storage medium
US20230342614A1 (en) Model generation apparatus, pathfinding apparatus, model generation method, and computer-readable storage medium storing a model generation program
CN114255616A (en) Unpowered ship track prediction method, device, equipment and storage medium

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20210723

WW01 Invention patent application withdrawn after publication