CN111489054A - Method for building model in navigation safety field of unmanned surface vehicle - Google Patents

Method for building model in navigation safety field of unmanned surface vehicle Download PDF

Info

Publication number
CN111489054A
CN111489054A CN202010180689.6A CN202010180689A CN111489054A CN 111489054 A CN111489054 A CN 111489054A CN 202010180689 A CN202010180689 A CN 202010180689A CN 111489054 A CN111489054 A CN 111489054A
Authority
CN
China
Prior art keywords
attribute
factors
navigation safety
navigation
field
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010180689.6A
Other languages
Chinese (zh)
Inventor
张安民
周健
王晨旭
丁峰
邸明伟
张豪
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.)
Tianjin University
Original Assignee
Tianjin 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 Tianjin University filed Critical Tianjin University
Priority to CN202010180689.6A priority Critical patent/CN111489054A/en
Publication of CN111489054A publication Critical patent/CN111489054A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067—Enterprise or organisation modelling

Abstract

The invention discloses a method for constructing a model in the field of navigation safety of unmanned surface vehicles, which comprises the following steps: acquiring an unmanned ship navigation safety influence factor set, namely collecting factors influencing the navigation safety of the unmanned ship on the water surface, wherein the factors are divided into self factors, navigation factors, environmental factors and traffic factor subsets; constructing a decision table, wherein the decision table comprises a condition attribute and a decision attribute; the equivalence class division is carried out, namely, the equivalence class division is carried out on the data discourse domain in the decision table according to the condition attribute and the decision attribute respectively; determining a positive domain of a decision attribute under each condition attribute; the importance of each condition attribute to the navigation safety field is obtained; setting an importance threshold, extracting factors exceeding the threshold, and taking the factors as main influence factors; determining an influence mechanism of each main factor on the navigation safety field, namely how each factor influences the navigation safety field of the unmanned ship and the influence degree; determining the dimensions of each half shaft in the navigation safety field; and constructing a navigation safety field model.

Description

Method for building model in navigation safety field of unmanned surface vehicle
Technical Field
The invention relates to the technical field of unmanned ship path planning, in particular to a method for constructing a model in the field of navigation safety of an unmanned ship on water.
Background
An Unmanned Surface vehicle (Unmanned Surface Vehicles) is a small-sized water Surface platform which has autonomous planning and autonomous navigation capabilities, can autonomously complete tasks such as environment sensing and target detection, and can bear functions such as information acquisition, environment monitoring, water search and rescue, military reconnaissance, military striking, communication relay and the like. The unmanned ship can adopt various different modules according to different use purposes, carries different sensors or execution equipment, and executes tasks to show diversity.
During the sailing process of the unmanned surface vehicle, especially when meeting with other ships or obstacles, a 'fresh' area is often kept around the unmanned surface vehicle in order to ensure the safety, namely the sailing safety field (Navigation safety domain). The navigation safety field is the basis for carrying out dynamic collision avoidance, path planning and risk assessment on the unmanned ship, and has very important effect on the aspect of ensuring navigation safety. However, the concept and construction method of the sailing security domain of the unmanned surface vehicle are rarely studied. In reference [1] (zhangyang, dianthus superbus, conjun, lie hair, unmanned surface vessel dynamic obstacle avoidance based on a velocity obstacle method and a dynamic window method [ J ]. university college, 2017,23(1):1-16.), the distance between the USV and the obstacle is divided into three types, namely a safe region, a conventional obstacle avoidance region and an emergency obstacle avoidance region, and the essence of the three types of regions is the navigation safety field boundary. However, the boundaries of these three regions are unknown and no specific values are given. Therefore, it is necessary to provide a model construction method specially suitable for the navigation safety field of unmanned surface vehicles.
Disclosure of Invention
The invention aims to overcome the defects of the technology and provides a method for building a model in the field of navigation safety of an unmanned surface vehicle.
In order to achieve the purpose, the invention adopts the following technical scheme: a method for building a model in the field of navigation safety of an unmanned surface vehicle is characterized by comprising the following steps:
step one, acquiring a sailing safety influence factor set of the unmanned ship;
step two, constructing a decision table, wherein the decision table comprises a condition attribute and a decision attribute;
thirdly, performing equivalence class division, namely performing equivalence class division on the data discourse domain in the decision table according to the condition attribute and the decision attribute respectively;
determining the positive domain of the decision attribute under each condition attribute;
fifthly, the importance of each condition attribute to the navigation safety field is obtained;
setting an importance threshold, extracting factors exceeding the threshold, and taking the extracted factors as main influence factors;
determining an influence mechanism of each main factor on the navigation safety field, namely how each factor influences the navigation safety field of the unmanned ship and the influence degree;
eighthly, determining the semi-axis dimensions in the front direction, the rear direction, the left direction and the right direction of the navigation safety field of the unmanned ship according to an influence mechanism of each factor on the navigation safety field dimension and by combining with an external actual environment;
and step nine, constructing a model in the field of navigation safety of the unmanned surface vehicle.
Preferably, in the step one, a set of unmanned ship navigation safety influence factors is obtained and is divided into self factors, navigation factors, environmental factors and traffic factor subsets according to respective attributes.
Preferably, in the second step, the condition attribute refers to each factor in the navigation safety influence factor set after data dispersion, and the decision attribute refers to a decision attribute value under the condition determined according to a given combination of the condition attributes.
Preferably, in step five, the importance of an attribute in a certain attribute set is equal to the change degree of a positive domain after the attribute is removed, and the greater the change degree, the higher the importance; the lower the reverse.
Preferably, the self-factor subset comprises the length, width and maneuverability of the surface unmanned boat; the navigation factor subset comprises navigation speed and navigation load; the subset of environmental factors comprises wind, wave, current, water depth and visibility; the traffic factor subset includes number of obstacles, DCPA, TCPA.
The method has the advantages that the defects in the existing model construction method in the navigation safety field are overcome, accurate basis of risk assessment and path planning can be provided for the unmanned surface ship in navigation, collision early warning and collision avoidance actions of the unmanned surface ship can be caused when other ships or dangerous obstacles invade the navigation safety field, and in addition, the method is favorable for enabling the unmanned surface ship to meet the requirements of CO L REGs (international maritime collision avoidance rules), namely, enough safety distance needs to be kept in the process of ship meeting.
Drawings
FIG. 1 is a flow chart of a method for constructing a model in the field of navigation safety of an unmanned surface vehicle according to the invention;
FIG. 2 is a model schematic diagram in the field of navigation safety of the unmanned surface vehicle.
Detailed Description
FIG. 1 is a flow chart of a method for constructing a model in the field of navigation safety of an unmanned surface vehicle, which specifically comprises the following steps:
step one, acquiring a sailing safety influence factor set of the unmanned ship;
step two, constructing a decision table, wherein the decision table comprises a condition attribute and a decision attribute;
thirdly, performing equivalence class division, namely performing equivalence class division on data discourse domains in the decision table according to the condition attributes and the decision attributes respectively;
determining the positive domain of the decision attribute under each condition attribute;
fifthly, the importance of each condition attribute to the navigation safety field is obtained;
setting an importance threshold, extracting factors exceeding the threshold, and taking the extracted factors as main influence factors;
determining an influence mechanism of each main factor on the navigation safety field, namely how each factor influences the navigation safety field of the unmanned ship and the influence degree;
eighthly, determining the dimensions of each half shaft in the navigation safety field;
and step nine, constructing a model in the field of navigation safety of the unmanned surface vehicle.
Further, the acquiring of the unmanned ship navigation safety influence factor set includes: factors influencing the navigation safety of the unmanned surface vehicle are collected and divided into self factors, navigation factors, environmental factors and traffic factor subsets according to respective attributes.
Furthermore, the sailing safety influence factor set is divided into self factors, sailing factors, environmental factors and traffic factor subsets, and the self factor subsets comprise the length, the width and the maneuverability of the unmanned surface boat; the navigation factor subset comprises navigation speed and navigation load; the subset of environmental factors comprises wind, wave, current, water depth and visibility; the traffic factor subset includes number of obstacles, DCPA, TCPA.
Further, the method for constructing the decision table is characterized in that the decision table comprises a condition attribute and a decision attribute. The condition attribute refers to each factor in the dispersed navigation safety influence factor set, and the decision attribute refers to a decision attribute value under the condition which is judged according to the combination of the given condition attributes. The decision table is shown in table 1.
TABLE 1
Figure BDA0002412431700000041
Further, the equivalence class division, namely, the equivalence class division is performed on the data discourse domain in the decision table according to the condition attribute and the decision attribute respectively, and the method is characterized in that:
(1) and (3) carrying out equivalence class division on the data discourse domain in the table 1 according to the condition attribute and the decision attribute respectively:
U/IND(C)
U/IND(D)
(2) performing equivalence class division on the discourse domain of the data in the table 1 after one condition attribute is removed respectively:
U/IND(C-C1)
U/IND(C-C2)
U/IND(C-C3)
Figure BDA0002412431700000042
U/IND(C-Cn)
further, the determining of the positive domain of the decision attribute under each condition attribute is characterized in that:
(1) the following approximation set: according to the prior knowledge R, judging the set formed by all the objects in the U which definitely belong to the set X, namely
Figure BDA0002412431700000043
Wherein, [ x ]]RRepresenting an equivalence class containing the element x under the equivalence relation R.
(2) The upper approximation set: according to the prior knowledge R, judging a set consisting of objects which are in U and possibly belong to the set X, namely
R-(X)＝{x∈U,[x]R∩X≠φ}
Wherein, [ x ]]RRepresenting an equivalence class containing the element x under the equivalence relation R.
The largest set consisting of those objects that are determined to positively belong to X based on prior knowledge is the positive domain, namely:
POS(X)＝R-(X)
and (3) solving the positive domain of the decision attribute under each condition attribute:
POSC(D)
Figure BDA0002412431700000051
Figure BDA0002412431700000052
Figure BDA0002412431700000053
Figure BDA0002412431700000054
Figure BDA0002412431700000055
furthermore, the importance of each condition attribute to the navigation safety field is obtained, and the method is characterized in that:
Figure BDA0002412431700000056
Figure BDA0002412431700000057
Figure BDA0002412431700000058
Figure BDA0002412431700000059
Figure BDA00024124317000000510
further, an importance threshold is set, the factors exceeding the threshold are extracted, and the extracted factors are regarded as main influence factors.
Furthermore, according to the mechanism of influence of each main factor on the navigation safety field, each half-shaft dimension in the navigation safety field is determined, and the method is characterized in that:
NSD＝f{Rfore,Raft,Rstarb,Rport,ξ(Ω)}
ξ(Ω)＝{ζ(Ω1),ζ(Ω2),ζ(Ω3),…ζ(Ωn)}
wherein R isfore，Raft，Rstarb，RportThe lengths of half shafts in the front direction, the rear direction, the right direction and the left direction of the navigation safety field are respectively ξ (omega) which is an influence mechanism function of each main influence factor on the navigation safety field.
Further, according to Rfore，Raft，Rstarb，RportThe value of (a) constitutes a model of the safety domain of the voyage, as shown in fig. 2.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims (5)

1. A method for building a model in the field of navigation safety of an unmanned surface vehicle is characterized by comprising the following steps:
step one, acquiring a sailing safety influence factor set of the unmanned ship;
step two, constructing a decision table, wherein the decision table comprises a condition attribute and a decision attribute;
thirdly, performing equivalence class division, namely performing equivalence class division on the data discourse domain in the decision table according to the condition attribute and the decision attribute respectively;
determining the positive domain of the decision attribute under each condition attribute;
fifthly, the importance of each condition attribute to the navigation safety field is obtained;
setting an importance threshold, extracting factors exceeding the threshold, and taking the extracted factors as main influence factors;
determining an influence mechanism of each main factor on the navigation safety field, namely how each factor influences the navigation safety field of the unmanned ship and the influence degree;
eighthly, determining the semi-axis dimensions in the front direction, the rear direction, the left direction and the right direction of the navigation safety field of the unmanned ship according to an influence mechanism of each factor on the navigation safety field dimension and by combining with an external actual environment;
and step nine, constructing a model in the field of navigation safety of the unmanned surface vehicle.
2. The method for constructing the model in the field of unmanned surface vehicle navigation safety according to claim 1, wherein in step one, a set of unmanned vehicle navigation safety influencing factors is obtained and divided into self factors, navigation factors, environmental factors and traffic factor subsets according to respective attributes.
3. The method for constructing the model in the field of unmanned surface vehicle navigation safety according to claim 1, wherein in the second step, the condition attribute refers to each factor in the navigation safety influence factor set after data dispersion, and the decision attribute refers to a decision attribute value under a given condition which is determined according to a given combination of the condition attributes.
4. The method for constructing the model of the sailing safety field of the unmanned surface vehicle as claimed in claim 1, wherein in step five, the importance of an attribute in a certain attribute set is equal to the change degree of the attribute in a positive field, and the greater the change degree, the higher the importance is; the lower the reverse.
5. The method for model building of sailing safety domain of surface unmanned craft of claim 2, wherein the self factor subset includes length, width, maneuverability of surface unmanned craft; the navigation factor subset comprises navigation speed and navigation load; the subset of environmental factors comprises wind, wave, current, water depth and visibility; the traffic factor subset includes number of obstacles, DCPA, TCPA.
CN202010180689.6A 2020-03-16 2020-03-16 Method for building model in navigation safety field of unmanned surface vehicle Pending CN111489054A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010180689.6A CN111489054A (en) 2020-03-16 2020-03-16 Method for building model in navigation safety field of unmanned surface vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010180689.6A CN111489054A (en) 2020-03-16 2020-03-16 Method for building model in navigation safety field of unmanned surface vehicle

Publications (1)

Publication Number Publication Date
CN111489054A true CN111489054A (en) 2020-08-04

Family

ID=71811700

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010180689.6A Pending CN111489054A (en) 2020-03-16 2020-03-16 Method for building model in navigation safety field of unmanned surface vehicle

Country Status (1)

Country Link
CN (1) CN111489054A (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110362074A (en) * 2019-06-18 2019-10-22 华南理工大学 A kind of unmanned surface vehicle dynamic collision prevention method drawn based on track weight-normality

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110362074A (en) * 2019-06-18 2019-10-22 华南理工大学 A kind of unmanned surface vehicle dynamic collision prevention method drawn based on track weight-normality

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
徐波: ""邻域粗糙集的启发式属性约简算法研究"", 《硕士电子期刊》 *
王健宇: ""船舶动态路径协同规划研究"", 《硕士电子期刊》 *

Similar Documents

Publication Publication Date Title
Szlapczynski et al. Determining and visualizing safe motion parameters of a ship navigating in severe weather conditions
CN109597417B (en) Multi-USV group collaborative collision avoidance planning method based on collision avoidance criterion
Caccia et al. A practical approach to modeling and identification of small autonomous surface craft
CN111536962B (en) Route planning method and device for intelligent ship, storage medium and computer equipment
Krata et al. Assessment of a critical area for a give-way ship in a collision encounter
CN111599130A (en) Environmental risk early warning system for marine rescue
CN110444046B (en) Method for analyzing cluster situation of non-conflict meeting ship in limited water area
Minne Automatic testing of maritime collision avoidance algorithms
Szelangiewicz et al. The influence of wind, wave and loading condition on total resistance and speed of the vessel
Baldauf et al. Potentials of e-navigation–enhanced support for collision avoidance
EP3420312B1 (en) Fluid vehicle route optimisation
Zhao et al. Decision-making for the autonomous navigation of USVs based on deep reinforcement learning under IALA maritime buoyage system
Zhao et al. A method for correcting the closest point of approach index during vessel encounters based on dimension data from AIS
CN111489054A (en) Method for building model in navigation safety field of unmanned surface vehicle
Gil et al. Ship stability-related effects on a critical distance of collision evasive action
Hinostroza et al. Collision avoidance, guidance and control system for autonomous surface vehicles in complex navigation conditions
CN115019561B (en) External collision risk early warning system of ship towing system under mutual-seeing condition
CN115018304A (en) Method and device for calculating ship-computer collision risk and storage medium
Ariffin et al. Real-time evaluation of second generation intact stability criteria
Benedict et al. Application of fast time simulation technologies for enhanced ship manoeuvring operation
Eder Unmanned vessels: challenges ahead
CN111561932A (en) Ship navigation method based on virtual force
Kim et al. Development of an autonomous docking system for autonomous surface vehicles based on symbol recognition
Zhang et al. Collision prevention of ship towing operation under environmental disturbance
Endo et al. Passage planning system for small inland vessels based on standard paradigms and manoeuvres of experts

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