CN110400491A - A kind of Open sea area multiple target auxiliary Decision of Collision Avoidance method and decision system - Google Patents
A kind of Open sea area multiple target auxiliary Decision of Collision Avoidance method and decision system Download PDFInfo
- Publication number
- CN110400491A CN110400491A CN201910496804.8A CN201910496804A CN110400491A CN 110400491 A CN110400491 A CN 110400491A CN 201910496804 A CN201910496804 A CN 201910496804A CN 110400491 A CN110400491 A CN 110400491A
- Authority
- CN
- China
- Prior art keywords
- ship
- algorithm
- decision
- initial
- evacuation
- 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- Withdrawn
Links
Classifications
-
- 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)
- Ocean & Marine Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a kind of Open sea area multiple target auxiliary Decision of Collision Avoidance method and decision systems, this method comprises: obtaining initial distance, orientation, course and the speed of a ship or plane of the initial heading of this ship, the speed of a ship or plane and the basic manipulated parameter of ship and multiple object ships；Calculate the target moving element and collision prevention parameter between object ship and this ship；Whether the target moving element and collision prevention parameter for judging each object ship respectively meet threshold condition；This ship and all risk object ships are carried out to assert that evacuation attribute and danger level determine；Obtain the initial avoidingcollis ionscheme of this ship；Machine executes the initial avoidingcollis ionscheme when being executed；After judgement executes avoidingcollis ionscheme, if there are also risks of collision, if so, carrying out Second Decision and executing secondary avoidingcollis ionscheme.Open sea area multiple target auxiliary Decision of Collision Avoidance method of the invention and decision system can realize the simulation for the excellent sailing that outstanding crewman is showed during Decision of Collision Avoidance automatically, while avoid 3~5 risk object ships.
Description
Technical field
The present invention relates to boat collision prevention technical fields more particularly to a kind of Open sea area multiple target to assist Decision of Collision Avoidance method
And decision system.
Background technique
According to marine actual navigation environment, the intelligent Collision Avoidance decision basic process of ship is as follows:
First, the identification and extraction of object are avoided, the automatic acquisition including water sailing ship Yu underwater obstruction information
Multidate information with pretreatment, water sailing ship can be by such as AIS (Automatic identification
System, ship automatic identification system), RADAR (radio detection and ranging, radio detection and ranging)/
ARPA (Automatic radar plotting aid, automatic radar plotting aid) or both fused ship information conduct
Its information source；
Second, the processing of information of anti-collision, the collision preventions such as position, speed, distance, relative bearing including all kinds of evacuation objects
Master data, this category information are the input information that Decision of Collision Avoidance is supported；
Third, danger judgement and best decision automatically generate be Ship Intelligent Collision Avoidance decision key point, how to differentiate
How danger using the Anti-collision Actions of safety allows the core of all ships and static obstruction thing intelligent Collision Avoidance decision process
Link.Abiding by COLREGs (Convention on the international regulations for preventing
Collisions at sea 1972, International Rules of the Road) or Ordinary Practice of Seaman and outstanding sailor excellent sailing
Under the premise of being avoided between progress ship；The evacuation scheme for determining safety economy is that Ship Intelligent Collision Avoidance Technical investment reality ship uses
Basic demand, any one, which casts aside COLREGs and carries out the mode that avoids automatically of ship, all runs counter to navigation practice, cannot be by
Deck officer receives.
Be currently, there are Open sea area single goal intelligent Collision Avoidance decision-making technique: this method constructs scattered background mathematics model
And its algorithm, the feasibility of intelligent Collision Avoidance method is substantially demonstrated, is able to achieve single goal Decision of Collision Avoidance substantially, for example, application number
It is entitled to be based on PIDVCA (Personifying intelligent decision-making for CN201310101500.X
For vessel collision avoidance, ship human-imitating intelligent Decision of Collision Avoidance) principle two ships coordinate evacuation optimization
The patent application of method.
Automatic Collision Avoidance problem between ship can be divided into single goal and multiple target can meet two kinds of situations, and single goal is kept away automatically
Make problem relatively easy, because of related COLREGs relatively clear between the responsibility and duty division two ships.But
COLREGs is more fuzzy for the Avoidance description between more ships, only with " Ordinary Practice of Seaman, good seamanship, with reference to two ships
Between rule of ac-tion " etc. the entries of poor operabilities be illustrated, it is most important among these the reason is that Ship avoiding-bump problem still
Specific rule is not found and provides corresponding measures to keep clear, thus the Avoidance of marine multiple target just becomes intricate.
According to the description in above-mentioned COLREGs, the Decision of Collision Avoidance problem in the case of multiple target can be met is uncertain with very strong scheme
And subjectivity.Original method uses when determining dangerous ship collision and danger level and initially applies rudder opportunity as the master judged
Will foundation, this single judgment mode can not from angle of overall importance determine Collision Risk Index.Original method is being located
Reason multiple target can meet under Models of Decision-making in Ship Collision Avoidance when that there are processes is not clear enough, the various problems such as constraint condition complexity cause
Algorithm fails under many Meeting Situations.
Therefore it provides a kind of Open sea area multiple target auxiliary Decision of Collision Avoidance method and decision system.
Summary of the invention
In view of the above problems, the present invention is proposed to overcome the above problem in order to provide one kind or at least be partially solved
The Open sea area multiple target auxiliary Decision of Collision Avoidance method and decision system of the above problem.
According to an aspect of the present invention, a kind of Open sea area multiple target auxiliary Decision of Collision Avoidance method is provided, comprising:
Obtain the basic manipulated parameter of initial heading, the speed of a ship or plane and ship of this ship and the initial distance of multiple object ships,
Orientation, course and the speed of a ship or plane；
The target moving element and collision prevention parameter between object ship and this ship are obtained by object aware algorithm；
Judge that algorithm judges the target moving element and collision prevention ginseng of each object ship respectively by current potential risk of collision
Whether number meets threshold condition, wherein the object ship for meeting threshold condition is risk object ship；
This ship and all risk object ships are carried out to assert evacuation attribute and danger level by the way that Study on Trend algorithm can be met；
This is obtained according to the evacuation attribute and danger level of this ship and all risk object ships by intelligent Collision Avoidance decision making algorithm
The initial avoidingcollis ionscheme of ship；
The initial avoidingcollis ionscheme is executed according to the execution opportunity being arranged in initial avoidingcollis ionscheme；
Execute initial avoidingcollis ionscheme and then the secondary target obtained between object ship and this ship by object aware algorithm
Kinematicchain element and collision prevention parameter；
Judge each object ship after algorithm judges the initial avoidingcollis ionscheme of execution respectively by current potential risk of collision
Whether target moving element and collision prevention parameter meet threshold condition, wherein the object ship for meeting threshold condition is risk object
Ship；
Risk object ship if it exists then carries out secondary determine by avoidingcollis ionscheme of the uncoordinated Second Decision algorithm to this ship
Plan simultaneously executes；
Risk object ship if it does not exist then predicts restoring navigation opportunity for this ship, is restored navigation according to the opportunity of restoring navigation to this ship.
Further, above-mentioned Open sea area multiple target assists Decision of Collision Avoidance method, further includes:
If this ship is both stand-on vessel, and all risk object ships as give-way vessel are not performed both by Anti-collision Actions all,
Then judge whether this ship misses best evacuation opportunity, if it is not, then carrying out coordination evacuation by coordinating collision avoidance decision optimization algorithm；
Judge to coordinate whether evacuation succeeds, if it is not, then determining the initial evacuation scheme of this ship according to the last opportunity of steering rudder；
Judge whether the initial evacuation scheme of this ship allows clear all risk object ships, if it is not, then judging not allow clear danger
Whether object ship and this ship fall into immediate danger state, if it is not, then being calculated by space search optimizing algorithm from intelligent Collision Avoidance decision
New evacuation scheme is searched in Faku County；
Judge whether to find new evacuation scheme, if it is not, then adjusting initial evacuation side by immediate danger decision making algorithm
Case.
Further, above-mentioned Open sea area multiple target assists Decision of Collision Avoidance method, further includes:
If this ship is both give-way vessel, judge whether this ship misses best evacuation opportunity, if so, according to evacuation opportunity
Determine the initial evacuation scheme of this ship；
Judge whether the initial evacuation scheme of this ship allows clear all risk object ships, if it is not, then from the universal algorithm of sailor
New evacuation scheme is found in library；
Judge whether to find new evacuation scheme, if it is not, then calculating by time search optimizing algorithm from intelligent Collision Avoidance decision
New evacuation scheme is searched again in Faku County；
Judge whether to find new evacuation scheme again, if it is not, then passing through the initial evacuation of immediate danger decision making algorithm adjustment
Scheme.
Further, above-mentioned Open sea area multiple target assists Decision of Collision Avoidance method, further includes: when this ship is both give-way vessel, and
And this ship does not miss when most preferably avoiding opportunity, according to the best evacuation opportunity of this ship and changed course amplitude, passes through and predicts target component
Algorithm and actual algorithm prediction of restoring navigation are restored navigation opportunity.
Further, above-mentioned Open sea area multiple target assists Decision of Collision Avoidance method, further includes: if this ship be not only stand-on vessel but also
For give-way vessel, then according to as give-way vessel when evacuation opportunity and the last opportunity of steering rudder as stand-on vessel determine this ship by
Directly boat or give-way vessel generate avoidingcollis ionscheme.
Further, above-mentioned Open sea area multiple target assists Decision of Collision Avoidance method, further includes:
When evacuation opportunity when this ship is as give-way vessel is more early than the last opportunity of steering rudder as stand-on vessel, it is determined that this
Ship generates avoidingcollis ionscheme according to give-way vessel；
When evacuation opportunity when this ship is as give-way vessel is more late than the last opportunity of steering rudder as stand-on vessel, it is determined that this
Ship generates avoidingcollis ionscheme according to stand-on vessel.
Further,
Object aware algorithm includes target component derivation algorithm, target danger threshold quantization algorithm and target intersection feature
Recognizer.
Further,
It includes that target can meet Attribute Recognition algorithm, target evacuation Attribute Recognition algorithm, target point that Study on Trend algorithm, which can be met,
Class and subsumption algorithm and danger level decision threshold quantization algorithm.
Further,
Uncoordinated Second Decision algorithm includes that setting Second Decision identifies, can meet Study on Trend algorithm and evacuation scheme life
At algorithm.
According to another aspect of the present invention, a kind of decision system of Open sea area multiple target auxiliary collision prevention is provided, comprising:
Parameter collection module on ship, for obtaining the basic manipulated parameter of initial heading, the speed of a ship or plane and ship of this ship, and
Initial distance, orientation, course and the speed of a ship or plane of multiple object ships；
Object ship and this ship associated data obtain module, for by object aware algorithm obtain object ship and this ship it
Between target moving element and collision prevention parameter；It is also used to execute initial avoidingcollis ionscheme and then secondary is obtained by object aware algorithm
Take the target moving element and collision prevention parameter between object ship and this ship；
Risk object ship screening module, for judging that algorithm judges each target respectively by current potential risk of collision
Whether the target moving element and collision prevention parameter of ship meet threshold condition, wherein meet the object ship of threshold condition for dangerous mesh
Mark ship；It is also used to judge that algorithm judges each target after the initial avoidingcollis ionscheme of execution respectively by current potential risk of collision
Whether the target moving element and collision prevention parameter of ship meet threshold condition, wherein meet the object ship of threshold condition for danger
Object ship；
Risk object ship attribute determination module, for by the way that Study on Trend algorithm can be met to this ship and all risk objects
Ship carries out evacuation attribute identification and danger level determines；
Initial avoidingcollis ionscheme obtains module, for passing through intelligent Collision Avoidance decision making algorithm according to this ship and all risk objects
The evacuation attribute identification of ship and danger level obtain the initial avoidingcollis ionscheme of this ship；
Initial avoidingcollis ionscheme execution module, for machine to execute this initially when being executed according to the initial avoidingcollis ionscheme of this ship
Avoidingcollis ionscheme；
Initial avoidingcollis ionscheme adjusts module, for risk object ship time to be not present, passes through uncoordinated Second Decision algorithm
Second Decision is carried out to the avoidingcollis ionscheme of this ship and is executed；
Opportunity prediction module of restoring navigation predicts restoring navigation opportunity for this ship, according to multiple for risk object ship time to be not present
Endurance machine restores navigation to this ship.
The present invention has the advantage that compared with prior art
Open sea area multiple target auxiliary Decision of Collision Avoidance method of the invention and decision system can realize that outstanding crewman exists automatically
The simulation of the excellent sailing showed during Decision of Collision Avoidance, while avoiding 3~5 risk object ships.
Detailed description of the invention
Below in conjunction with drawings and examples, the invention will be further described.
Fig. 1 is Open sea area multiple target auxiliary Decision of Collision Avoidance method and step figure of the invention；
Fig. 2 is Open sea area multiple target auxiliary Decision of Collision Avoidance system block diagram of the invention；
Fig. 3 is the theoretical framework of PIDVCA process automation of the invention；
Fig. 4 is automatically generating and policing algorithm implementation flow chart for intelligent Collision Avoidance decision scheme of the invention；
Fig. 5 is that two ships of the invention can meet situation and object ship and can meet Attribute transposition figure；
Fig. 6 is that object ship relative bearing of the present invention is divided into 8 regions；
Fig. 7 is entire Open sea area multiple target auxiliary Decision of Collision Avoidance principle flow chart of the invention；
Fig. 8 is Open sea area multiple target auxiliary Decision of Collision Avoidance system block diagram of the invention.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing this public affairs in attached drawing
The exemplary embodiment opened, it being understood, however, that may be realized in various forms the disclosure without the implementation that should be illustrated here
Example is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the disclosure
Range is fully disclosed to those skilled in the art.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in specification of the invention
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology
Term and scientific term), there is meaning identical with the general understanding of those of ordinary skill in fields of the present invention.Also
It should be understood that those terms such as defined in the general dictionary, it should be understood that have and the context of the prior art
In the consistent meaning of meaning otherwise will not be solved with idealization or meaning too formal and unless by specific definitions
It releases.
Fig. 1 is Open sea area multiple target auxiliary Decision of Collision Avoidance method and step figure of the invention, provided by the invention referring to Fig. 1
Open sea area multiple target assists Decision of Collision Avoidance method, comprising:
S1, obtain this ship the basic manipulated parameter of initial heading, the speed of a ship or plane and ship and multiple object ships it is initial away from
From, orientation, course and the speed of a ship or plane.
S2 obtains target moving element and collision prevention parameter between object ship and this ship by object aware algorithm.
Specifically, object aware algorithm includes that target component derivation algorithm, target danger threshold quantization algorithm and target are handed over
It can feature recognition algorithms.
S3 judge that algorithm judges the target moving element of each object ship respectively and keeps away by current potential risk of collision
Touch whether parameter meets threshold condition, wherein the object ship for meeting threshold condition is risk object ship.
S4 carries out this ship and all risk object ships to assert evacuation attribute and danger by that can meet Study on Trend algorithm
Degree.
Specifically, can meet Study on Trend algorithm includes that target can meet Attribute Recognition algorithm, target evacuation Attribute Recognition is calculated
Method, target classification and subsumption algorithm and danger level decision threshold quantization algorithm.
S5, by intelligent Collision Avoidance decision making algorithm according to the identification of evacuation attribute and danger of this ship and all risk object ships
Degree obtains the initial avoidingcollis ionscheme of this ship.
Specifically, uncoordinated Second Decision algorithm includes that setting Second Decision identifies, can meet Study on Trend algorithm and evacuation
Schemes generation algorithm.
Specifically, intelligent Collision Avoidance decision making algorithm can be PIDVCA (Personifying intelligent
Decision-making for vessel collision avoidance, ship human-imitating intelligent Decision of Collision Avoidance) algorithm." sea
The intuition and good seamanship of member " refers to that sailor can correctly hold evacuation opportunity, amplitude during ship is grasped in collision prevention and restore navigation opportunity,
Staircase bidding processing to uncoordinated Second Decision adaptability to changes and far and near risk object, keeps evacuation implementation result both true
The safety of evacuation is protected, and meets the economy of evacuation.
The present invention can using PIDVCA mathematical model and algorithm as the representation of machine learning and PIDVCA method and
The basis of its evaluation criterion, PIDVCA formation basic theory are as shown in Figure 2:
Machine learning link is based in the case where the automated reasoning mechanism sum aggregate that inference machine pre-establishes is controlled at inference strategy
The object mark information that original knowledge of dynamic collision prevention knowledge base and scene obtain, with integrated machine learning construction of strategy dynamic
Collision prevention knowledge base.
Dynamic collision prevention knowledge base: integrated approach is indicated by the Heterogeneous Knowledge of carrier of Object-oriented knowledge representation, passes through intelligence
Energy program representation is by the causality knowledge that sex knowledge, production rule indicate the fact that database representation and by member
Decision (intelligent Collision Avoidance solution bank) knowledge, that is, procedural knowledge that knowledge embodies combines together, realizes dynamic collision prevention knowledge
Automatically it obtains, the real-time estimation of potential dynamic risk criterion and dynamic risk degree decision threshold, potential danger judgement and prediction
And it the automatically generating of PIDVCA embodiment, verifies and optimization.
PIDVCA may include the following key algorithm of a few classes according to the process of entire intelligent Collision Avoidance decision: target intersection
Feature recognition algorithms；Target potential danger parser；The intersection attribute of potential danger target and this ship keep away respective objects
Allow attribute algorithm；Dynamic risk degree judges algorithm；Risk object can meet Study on Trend and sorting algorithm；Uncoordinated avoidance algorithm,
Formation, verification and optimization algorithm of Decision of Collision Avoidance embodiment etc..The theoretical framework of PIDVCA process automation such as Fig. 3 institute
Show.
It is generated by the target process of cognition, target Study on Trend, target danger judgement, Decision of Collision Avoidance, decision scheme optimization
With a series of automatic method of verification and study, reasoning and the optimization of decision coordination, the artificial collision prevention of collision prevention expert is simulated
Whole Decision-making process, the final automation for realizing PIDVCA generates and optimization.
S6 executes the initial avoidingcollis ionscheme according to the execution opportunity being arranged in initial avoidingcollis ionscheme.
S7 executes initial avoidingcollis ionscheme and then the secondary mesh obtained between object ship and this ship by object aware algorithm
Mark kinematicchain element and collision prevention parameter.
S8 judge each target after algorithm judges the initial avoidingcollis ionscheme of execution respectively by current potential risk of collision
Whether the target moving element and collision prevention parameter of ship meet threshold condition, wherein meet the object ship of threshold condition for dangerous mesh
Mark ship.
S9, risk object ship, then carried out secondary by avoidingcollis ionscheme of the uncoordinated Second Decision algorithm to this ship if it exists
Decision simultaneously executes.
S10, risk object ship, then predict restoring navigation opportunity for this ship if it does not exist, is answered according to the opportunity of restoring navigation this ship
Boat.
Fig. 4 be intelligent Collision Avoidance decision scheme of the invention automatically generate with policing algorithm implementation flow chart, referring to fig. 4,
Realize that specific step is as follows for ship collision prevention:
Step 1: system initialization solves this ship initial heading, the speed of a ship or plane and the basic manipulated parameter of ship and object ship is initial
The acquisition of distance, orientation, course and the speed of a ship or plane.
Step 2: object aware.
(1) invocation target parametric solution algorithm obtains target moving element and collision prevention parameter (such as DCPA, TCPA, phase first
To speed, virtual course, relative bearing etc.).
(2) then, danger judging threshold value quantizing algorithm is called, uses SDA belowmax(unit: nautical mile) and MSDA (unit:
Rice) respectively indicate the maximum SDA of SDA between object ship and this shipmaxWith minimum decision threshold MSDA:
MSDA=2 × P+ (Lo÷135+Lt÷45)×π
SDAmax=(Vt×Tn÷60+MSDA+Fd)÷1852
Wherein, Lo and Lt is respectively captain's (unit: rice) of this ship and object ship；P filters mean square deviation from target position
(unit: rice)；Vt is the speed (unit: m/h) of object ship；Tn and Fd be respectively 90 ° of cycle of this ship full speed full-helm when
Between (unit: minute) and cycle into away from (unit: rice).
(3) target intersection feature recognition algorithms are recalled and learn that target intersects feature TEC.
TEC depends on object ship speed Vt and course Ct, the speed Vo of this ship and course Co and object ship relative motion
Course Cr, for from same orientation, the object ship with identical virtual course, when two ship true motion course angles and speed
The different TEC than not may be constructed simultaneously, 16 kinds of TEC value rule such as tables 1.
Table 1
Step 3: risk of collision judgement.Current potential risk of collision is called to judge algorithm, there are the mesh of risk of collision for judgement
Mark.If object ship parameter meets the following conditions, then it is assumed that there are risks of collision with this ship for object ship.
0.728 × SDA of DCPA <maxAnd TCPA > 0
Wherein, DCPA is Distance of close point of approaching, and minimum when two ships can be met is logical
Cross distance；TCPA is Time of close point of approaching, and two ship minimums can be met the time.
Step 4: Study on Trend can be met.
First, first invocation target can meet Attribute Recognition algorithm and know that the target of International Rules of the Road agreement can be met
Attribute, Fig. 5, which can meet situation and object ship for two ships, can meet Attribute transposition figure；
Object ship, which can meet attribute, following 6 kinds:
(1) TEP=1: carry out the situation that ship is overtaken vessel, be defined as E class ship.My shipowner is dynamic at this time overtakes his ship, due to
This ship overtakes the middle variation that spatial position can occur, if always according to the division principle of upper figure, can meet attribute will be sent out
Changing.But overtaking in clause for defining in International Rules of the Road is pointed out: overtaking situation once being formed, this ship answer one
It is straight to keep overtaking state until Past And Clear overtaken vessel.When my ship overtakes beyond after overtaking section, TEP is always
It is 1, his ship is determined as E class ship always, and the clause that overtakes in this machine rule and International Rules of the Road keeps one
It causes.
(2) it TEP=2: to carry out the situation that ship intersects with this ship starboard, is defined as starboard and intersects A class ship
(3) TEP=6: for the situation for coming ship Yu my ship end-on, it is defined as A class ship
(4) TEP=3: to carry out the kind situation that ship intersects with this ship starboard wide-angle, it is defined as B class ship
(5) TEP=4: to carry out the situation that ship overtakes my ship, according to preventing collision method difference, by relative bearing less than 210 °
Overtaking vessel is defined as C class ship, and the overtaking vessel by relative bearing more than or equal to 210 ° is defined as D class ship.Object ship overtakes me at this time
Ship, since object ship overtakes the middle variation that spatial position can occur, if can meet always according to the division principle of upper figure
Attribute will change.But overtaking in clause for defining in International Rules of the Road is pointed out: overtaking office once being formed
Face, this ship should be always maintained at the state of overtaking until Past And Clear overtaken vessel.Exceed when object ship overtakes and overtakes section
Later, TEP is always 4, and object ship is determined as C class ship always, overtakes item in machine rule and International Rules of the Road
Money is consistent.
(6) TEP=5: relative bearing is that the ship that comes of { 247.5 °, 354 ° } constitutes the situation that larboard intersects, definition with this ship
For D class ship.
Second, further invocation target evacuation Attribute Recognition algorithm knows the mesh of International Rules of the Road agreement
Mark evacuation attribute, target evacuation attribute includes giving way or sailing through to attribute: two ships that can in sight of one another meet can be divided into stand-on vessel and give way
Ship, meets above-mentioned meeting the object ship of A, B and E class in situation, this ship is give-way vessel (or obliged ship)；Relative to C and D
Object ship is met in the meeting of class, this ship is stand-on vessel (or privileged vessel).In the case where poor visibility, two ships, which can be met, is not present direct route
Concept should all fulfil the obligation of give-way vessel.
Third, then invocation target classification and subsumption algorithm obtain the place orientation section of object ship: same intersection is special
In sign, the difference of the relative bearing of object ship causes two ships evacuation decision scheme also not identical, it is therefore desirable to the phase of object ship
Orientation is divided in detail.8 regions are divided into according to object ship relative bearing, as shown in fig. 6, a, b are indicated in Fig. 6
End-on (larboard, starboard)；C, h indicates front cross (larboard, starboard)；D, g indicates that beam nearby intersects (larboard, starboard)；
E, f expression is overtaken (larboard, starboard).
In multiple risk object ships, it is combined classification according to the evacuation attribute of its two ship, is given way according to only having
Ship, only stand-on vessel and existing give-way vessel have stand-on vessel classification again.
4th, recall danger level decision threshold value algorithm, danger level decision threshold cannot be only used for judging object ship with
Whether this ship falls into close quarters situation or immediate danger situation, it may also be used for reflect this ship with it is potential on risk object ship time sky
Risk of collision degree.
For example, the judgment criteria whether object ship and this ship fall into close quarters situation or immediate danger situation can be with are as follows: target
The distance between ship and this ship are less than or equal to 0.3DCPA.
Step 5: calling the automation of intelligent Collision Avoidance decision to generate and obtain evacuation scheme with optimization algorithm.
Step 6: judging whether execution opportunity reaches, if going to step 7 if, otherwise go to step 2.
Step 7: execute the operation of evacuation scheme: the evacuation course of setting course autopilot and initial set rudder angle and interface are joined
Number.
Step 8: risk of collision monitoring and judgement after executing evacuation scheme: invocation target cognitive algorithm and current potential
Risk of collision judges that algorithm judges whether there is risk of collision target, if there is risk object ship, shows that the ship is taken and does not assist
The Anti-collision Actions of tune then go to step 9, otherwise go to step 10.
Step 9: uncoordinated Second Decision algorithm is identified by setting Second Decision, and Study on Trend algorithm can be met by recalling
And evacuation schemes generation algorithm, Second Decision is provided as modification on the basis of first time evacuation scheme, and turns to walk immediately
Rapid 7 carry into execution a plan.
Step 10: opportunity judgement of restoring navigation: calling prediction target component algorithm and prediction danger judgement algorithm, prediction
It whether there is dangerous ship after restoring former course if dangerous ship has been not present, illustrate that the opportunity of restoring navigation, oneself passed through to going to step
11；Otherwise step 8 is gone to.
Herein, restore navigation opportunity acquisition process it is as follows:
Target component is predicted according to prediction target component algorithm；
The evacuation path prediction of combining target parameter and this ship is restored navigation opportunity.
Step 11: setting course is autopilot original course, and initial set rudder angle and interface parameters is arranged, and executes and restores course
Operation, goes to step 2.
For multiple target collision prevention scene, entire Open sea area multiple target auxiliary Decision of Collision Avoidance principle flow chart is as shown in Figure 7.
Referring to Fig. 7, above-mentioned Open sea area multiple target assists Decision of Collision Avoidance method, further includes:
S71, if this ship is both stand-on vessel, and all risk object ships as give-way vessel are not performed both by evacuation all
Action, then judge whether this ship misses best evacuation opportunity, if it is not, then being coordinated by coordinating collision avoidance decision optimization algorithm
Evacuation；If so, going to S74；If this ship is stand-on vessel, and all risk object ships as give-way vessel are performed both by evacuation row
Dynamic, then this ship fulfils the obligation of stand-on vessel keeping course and speed, and exports PIDVCA embodiment；Coordinating collision avoidance decision optimization algorithm
To carry out both sides' coordination by communication by this ship and risk object ship, both sides can carry out the evacuation of certain angle respectively.
S72 judges to coordinate whether evacuation succeeds, if it is not, then determining the initial evacuation side of this ship according to the last opportunity of steering rudder
Case；If so, output PIDVCA embodiment；
S73 judges whether the initial evacuation scheme of this ship allows clear all risk object ships；
S74, if it is not, then judging that clear risk object ship and this ship is not allowed whether to fall into immediate danger state, if it is not, then
New evacuation scheme is searched for from intelligent Collision Avoidance decision making algorithm library by space search optimizing algorithm；If so, passing through urgent danger
The dangerous initial evacuation scheme of decision making algorithm adjustment；Wherein, immediate danger decision making algorithm is that this ship turns to ± 90 °.
S75 judges whether to find new evacuation scheme, if it is not, then passing through the initial evacuation of immediate danger decision making algorithm adjustment
Scheme.
Referring to Fig. 7, above-mentioned Open sea area multiple target assists Decision of Collision Avoidance method, further includes:
If this ship is both give-way vessel, judge whether this ship misses best evacuation opportunity, if so, according to evacuation opportunity
Determine the initial evacuation scheme of this ship；If it is not, then being restored navigation opportunity according to best evacuation opportunity and changed course amplitude prediction；
Judge whether the initial evacuation scheme of this ship allows clear all risk object ships, if it is not, then from the universal algorithm of sailor
New evacuation scheme is found in library；If so, obtaining evacuation scheme by PIDVCA；
Judge whether to find new evacuation scheme, if it is not, then calculating by time search optimizing algorithm from intelligent Collision Avoidance decision
New evacuation scheme is searched again in Faku County；If so, output PIDVCA embodiment；
Judge whether to find new evacuation scheme again, if it is not, then passing through the initial evacuation of immediate danger decision making algorithm adjustment
Scheme；If so, output PIDVCA embodiment.
Referring to Fig. 7, above-mentioned Open sea area multiple target assists Decision of Collision Avoidance method, further includes: if visibility poor, this ship is made
For give-way vessel.
Referring to Fig. 7, above-mentioned Open sea area multiple target assists Decision of Collision Avoidance method, further includes: when this ship is both give-way vessel, and
And this ship does not miss when most preferably avoiding opportunity, according to the best evacuation opportunity of this ship and changed course amplitude, passes through and predicts target component
Algorithm and actual algorithm prediction of restoring navigation are restored navigation opportunity.
Referring to Fig. 7, above-mentioned Open sea area multiple target assists Decision of Collision Avoidance method, further includes: if this ship had not only been stand-on vessel but also had been
Give-way vessel, then according to as give-way vessel when evacuation opportunity and the last opportunity of steering rudder as stand-on vessel determine this ship according to
Stand-on vessel or give-way vessel generate avoidingcollis ionscheme.
Referring to Fig. 7, above-mentioned Open sea area multiple target assists Decision of Collision Avoidance method, further includes:
When evacuation opportunity when this ship is as give-way vessel is more early than the last opportunity of steering rudder as stand-on vessel, it is determined that this
Ship generates avoidingcollis ionscheme according to give-way vessel；
When evacuation opportunity when this ship is as give-way vessel is more late than the last opportunity of steering rudder as stand-on vessel, it is determined that this
Ship generates avoidingcollis ionscheme according to stand-on vessel.
Wherein, " the usual way of sailor " in Fig. 7 refers to usual way of sailor during multiobjective decision-making, i.e. needle
Between the International Rules of the Road requirement evacuation emphasis ship habit " applying " two ship.
" intuition and good seamanship of sailor " refers to that sailor can correctly hold evacuation opportunity, amplitude during ship is grasped in collision prevention
And restore navigation opportunity, the staircase bidding of uncoordinated Second Decision adaptability to changes and far and near risk object is handled, keeps evacuation real
Applying effect not only ensures the safety of evacuation, but also meets the economy of evacuation.
Space search optimizing algorithm is when the last opportunity of steering rudder fails to find suitable evacuation scheme, in its safety meeting
The variable section { SDAmin, SDAmax } for meeting distance SDA (Safe distance of approach, safe meeting distance) is searched
Rope makes two ship DCPA (Distance of close point of approaching, minimum when two ships can be met pass through distance)
Maximum evacuation scheme.
Time search optimizing algorithm is to call the excellent sailing general-purpose algorithm of sailor and calling space search optimizing algorithm not
Suitable embodiment can be found, is applied in rudder opportunity variable section { 0, TLS } and { TIS, TLS } in this ship and carries out time search
Optimizing reduces the suitable reality that the method that this ship applies rudder opportunity finds the maximum DCPA between object ship according to certain step-length
Apply scheme.
TIS:Time of initial steering, optimal initial avoid opportunity；TLS:Time of last
Steering, the last opportunity of steering rudder.
Open sea area multiple target auxiliary Decision of Collision Avoidance method of the invention can realize outstanding crewman in Decision of Collision Avoidance mistake automatically
The simulation of the excellent sailing showed in journey, while avoiding 3~5 risk object ships.
Fig. 8 is Open sea area multiple target auxiliary Decision of Collision Avoidance system block diagram of the invention, referring to Fig. 8, width provided by the invention
The decision system of waters multiple target auxiliary collision prevention, comprising:
Parameter collection module on ship, for obtaining the basic manipulated parameter of initial heading, the speed of a ship or plane and ship of this ship, and
Initial distance, orientation, course and the speed of a ship or plane of multiple object ships；
Object ship and this ship associated data obtain module, for by object aware algorithm obtain object ship and this ship it
Between target moving element and collision prevention parameter；It is also used to execute initial avoidingcollis ionscheme and then secondary is obtained by object aware algorithm
Take the target moving element and collision prevention parameter between object ship and this ship；
Risk object ship screening module, for judging that algorithm judges each target respectively by current potential risk of collision
Whether the target moving element and collision prevention parameter of ship meet threshold condition, wherein meet the object ship of threshold condition for dangerous mesh
Mark ship；It is also used to judge that algorithm judges each target after the initial avoidingcollis ionscheme of execution respectively by current potential risk of collision
Whether the target moving element and collision prevention parameter of ship meet threshold condition, wherein meet the object ship of threshold condition for danger
Object ship；
Risk object ship attribute determination module, for by the way that Study on Trend algorithm can be met to this ship and all risk objects
Ship carries out evacuation attribute identification and danger level determines；
Initial avoidingcollis ionscheme obtains module, for passing through intelligent Collision Avoidance decision making algorithm according to this ship and all risk objects
The evacuation attribute identification of ship and danger level obtain the initial avoidingcollis ionscheme of this ship；
Initial avoidingcollis ionscheme execution module, for machine to execute this initially when being executed according to the initial avoidingcollis ionscheme of this ship
Avoidingcollis ionscheme；
Initial avoidingcollis ionscheme adjusts module, for risk object ship time to be not present, passes through uncoordinated Second Decision algorithm
Second Decision is carried out to the avoidingcollis ionscheme of this ship and is executed；
Opportunity prediction module of restoring navigation predicts restoring navigation opportunity for this ship, according to multiple for risk object ship time to be not present
Endurance machine restores navigation to this ship.
The present invention assists Decision of Collision Avoidance using ship human-imitating intelligent Decision of Collision Avoidance method PIDVCA building Open sea area multiple target
System, the basic thought of PIDVCA are the priori knowledges combination people such as the usual way for utilizing COLREGs, ship's manoeuverability, crewman
The relevant knowledge of work intelligence, qualitative analysis and the quantitative calculating of target information, automated reasoning, In by expertise knowledge
Line automatically analyzes and evaluates decision scheme, realizes automatically generating and optimizing for PIDVCA embodiment.
Open sea area multiple target auxiliary Decision of Collision Avoidance system of the invention can realize outstanding crewman in Decision of Collision Avoidance mistake automatically
The simulation of the excellent sailing showed in journey, while avoiding 3~5 risk object ships.
Intelligent Collision Avoidance decision making algorithm library and collision prevention process of the invention, intelligent Collision Avoidance decision making algorithm library effectively support
The decision tree of whole system can provide rationally effective collision prevention suggestion, and collision prevention process has fully taken into account collision prevention in the process can
The a series of problems that can occur, and give solution.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments
Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation
Technical solution documented by example is modified or equivalent replacement of some of the technical features；And these modification or
Replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of Open sea area multiple target assists Decision of Collision Avoidance method characterized by comprising
Obtain the basic manipulated parameter of initial heading, the speed of a ship or plane and ship of this ship and the initial distance of multiple object ships, orientation,
Course and the speed of a ship or plane；
The target moving element and collision prevention parameter between object ship and this ship are obtained by object aware algorithm；
Judge that algorithm judges the target moving element of each object ship respectively and collision prevention parameter is by current potential risk of collision
It is no to meet threshold condition, wherein the object ship for meeting threshold condition is risk object ship；
This ship and all risk object ships are carried out to assert evacuation attribute and danger level by the way that Study on Trend algorithm can be met；
This ship is obtained according to the evacuation attribute and danger level of this ship and all risk object ships by intelligent Collision Avoidance decision making algorithm
Initial avoidingcollis ionscheme；
The initial avoidingcollis ionscheme is executed according to the execution opportunity being arranged in initial avoidingcollis ionscheme；
It executes initial avoidingcollis ionscheme and then the secondary target movement obtained between object ship and this ship by object aware algorithm is wanted
Element and collision prevention parameter；
Judge the target of each object ship after algorithm judges the initial avoidingcollis ionscheme of execution respectively by current potential risk of collision
Whether kinematicchain element and collision prevention parameter meet threshold condition, wherein the object ship for meeting threshold condition is risk object ship；
Risk object ship if it exists then carries out Second Decision by avoidingcollis ionscheme of the uncoordinated Second Decision algorithm to this ship and holds
Row；
Risk object ship if it does not exist then predicts restoring navigation opportunity for this ship, is restored navigation according to the opportunity of restoring navigation to this ship.
2. Open sea area multiple target according to claim 1 assists Decision of Collision Avoidance method, which is characterized in that further include:
If this ship is both stand-on vessel, and all risk object ships as give-way vessel are not performed both by Anti-collision Actions all, then sentence
Whether this ship that breaks misses best evacuation opportunity, if it is not, then carrying out coordination evacuation by coordinating collision avoidance decision optimization algorithm；
Judge to coordinate whether evacuation succeeds, if it is not, then determining the initial evacuation scheme of this ship according to the last opportunity of steering rudder；
Judge whether the initial evacuation scheme of this ship allows clear all risk object ships, if it is not, then judging not allow clear risk object
Whether ship and this ship fall into immediate danger state, if it is not, then passing through space search optimizing algorithm from intelligent Collision Avoidance decision making algorithm library
The new evacuation scheme of middle search；
Judge whether to find new evacuation scheme, if it is not, then passing through the initial evacuation scheme of immediate danger decision making algorithm adjustment.
3. Open sea area multiple target according to claim 2 assists Decision of Collision Avoidance method, which is characterized in that further include:
If this ship is both give-way vessel, judge whether this ship misses best evacuation opportunity, if so, determining this according to evacuation opportunity
The initial evacuation scheme of ship；
Judge whether the initial evacuation scheme of this ship allows clear all risk object ships, if it is not, then from the universal algorithms library of sailor
Find new evacuation scheme；
Judge whether to find new evacuation scheme, if it is not, then passing through time search optimizing algorithm from intelligent Collision Avoidance decision making algorithm library
In search again for new evacuation scheme；
Judge whether to find new evacuation scheme again, if it is not, then passing through the initial evacuation scheme of immediate danger decision making algorithm adjustment.
4. Open sea area multiple target according to claim 3 assists Decision of Collision Avoidance method, which is characterized in that further include: when this
Ship is both give-way vessel, and this ship does not miss when most preferably avoiding opportunity, according to the best evacuation opportunity of this ship and changed course amplitude, leads to
It crosses prediction target component algorithm and actual algorithm prediction of restoring navigation is restored navigation opportunity.
5. Open sea area multiple target according to claim 4 assists Decision of Collision Avoidance method, which is characterized in that further include: if this
Ship had not only been stand-on vessel but also had been give-way vessel, then according to as give-way vessel when evacuation opportunity and as stand-on vessel when applying rudder the latest
Machine determines that this ship generates avoidingcollis ionscheme according to stand-on vessel or give-way vessel.
6. Open sea area multiple target according to claim 5 assists Decision of Collision Avoidance method, which is characterized in that further include:
When evacuation opportunity when this ship is as give-way vessel is more early than the last opportunity of steering rudder as stand-on vessel, it is determined that this ship according to
Give-way vessel generates avoidingcollis ionscheme；
When evacuation opportunity when this ship is as give-way vessel is more late than the last opportunity of steering rudder as stand-on vessel, it is determined that this ship according to
Stand-on vessel generates avoidingcollis ionscheme.
7. Open sea area multiple target according to claim 6 assists Decision of Collision Avoidance method, which is characterized in that
Object aware algorithm includes that target component derivation algorithm, target danger threshold quantization algorithm and target intersection feature identification are calculated
Method.
8. Open sea area multiple target according to claim 7 assists Decision of Collision Avoidance method, which is characterized in that
Can meet Study on Trend algorithm include target can meet Attribute Recognition algorithm, target evacuation Attribute Recognition algorithm, target classification and
Subsumption algorithm and danger level decision threshold quantization algorithm.
9. Open sea area multiple target according to claim 8 assists Decision of Collision Avoidance method, which is characterized in that
Uncoordinated Second Decision algorithm includes that setting Second Decision identifies, can meet Study on Trend algorithm and evacuation schemes generation calculation
Method.
10. a kind of decision system of Open sea area multiple target auxiliary collision prevention characterized by comprising
Parameter collection module on ship, for obtaining the basic manipulated parameter of initial heading, the speed of a ship or plane and ship and multiple mesh of this ship
Mark initial distance, orientation, course and the speed of a ship or plane of ship；
Object ship and this ship associated data obtain module, for obtaining the mesh between object ship and this ship by object aware algorithm
Mark kinematicchain element and collision prevention parameter；It is also used to execute initial avoidingcollis ionscheme and then secondary by object aware algorithm acquisition target
Target moving element and collision prevention parameter between ship and this ship；
Risk object ship screening module, for judging that algorithm judges the mesh of each object ship respectively by current potential risk of collision
Whether mark kinematicchain element and collision prevention parameter meet threshold condition, wherein the object ship for meeting threshold condition is risk object ship；Also
For judge the target of each object ship after algorithm judges the initial avoidingcollis ionscheme of execution respectively by current potential risk of collision
Whether kinematicchain element and collision prevention parameter meet threshold condition, wherein the object ship for meeting threshold condition is risk object ship；
Risk object ship attribute determination module, for being carried out by the way that Study on Trend algorithm can be met to this ship and all risk object ships
It avoids attribute identification and danger level determines；
Initial avoidingcollis ionscheme obtains module, for the keeping away according to this ship and all risk object ships by intelligent Collision Avoidance decision making algorithm
Attribute identification and danger level is allowed to obtain the initial avoidingcollis ionscheme of this ship；
Initial avoidingcollis ionscheme execution module, for machine to execute the initial collision prevention side when being executed according to the initial avoidingcollis ionscheme of this ship
Case；
Initial avoidingcollis ionscheme adjusts module, for risk object ship time to be not present, by uncoordinated Second Decision algorithm to this
The avoidingcollis ionscheme of ship carries out Second Decision and executes；
Opportunity prediction module of restoring navigation predicts restoring navigation opportunity for this ship, according to the opportunity of restoring navigation for risk object ship time to be not present
It restores navigation to this ship.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910496804.8A CN110400491A (en) | 2019-06-10 | 2019-06-10 | A kind of Open sea area multiple target auxiliary Decision of Collision Avoidance method and decision system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910496804.8A CN110400491A (en) | 2019-06-10 | 2019-06-10 | A kind of Open sea area multiple target auxiliary Decision of Collision Avoidance method and decision system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110400491A true CN110400491A (en) | 2019-11-01 |
Family
ID=68323048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910496804.8A Withdrawn CN110400491A (en) | 2019-06-10 | 2019-06-10 | A kind of Open sea area multiple target auxiliary Decision of Collision Avoidance method and decision system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110400491A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110956853A (en) * | 2019-11-12 | 2020-04-03 | 武汉理工大学 | Multi-ship collision prediction method, system and storage medium |
| CN111007859A (en) * | 2019-12-24 | 2020-04-14 | 智慧航海（青岛）科技有限公司 | Ship meeting situation generation method for unmanned ship autonomous navigation simulation test |
| CN111176271A (en) * | 2019-11-21 | 2020-05-19 | 智慧航海（青岛）科技有限公司 | Intelligent ship collision avoidance aid decision-making system based on shore-based radar and implementation method thereof |
| CN111260963A (en) * | 2020-03-11 | 2020-06-09 | 武汉理工大学 | Multi-ship meeting collision avoidance method |
| CN111445086A (en) * | 2020-04-17 | 2020-07-24 | 集美大学 | Method for predicting fly-back time based on PIDVCA |
| CN111951606A (en) * | 2020-07-29 | 2020-11-17 | 武汉理工大学 | Ship collision risk assessment and early warning method and system |
| CN112149237A (en) * | 2020-10-15 | 2020-12-29 | 北京海兰信数据科技股份有限公司 | Real-time ship collision avoidance method and system |
| CN112820150A (en) * | 2020-12-29 | 2021-05-18 | 大连海事大学 | AIS-based ship collision avoidance decision method |
| CN114664118A (en) * | 2022-03-18 | 2022-06-24 | 陕西正整数科技有限公司 | Intelligent ship collision avoidance automatic test scene generation method and system |
| CN115273555A (en) * | 2022-06-23 | 2022-11-01 | 集美大学 | Ship collision avoidance decision method for channel intersection area |
| CN115273556A (en) * | 2022-06-24 | 2022-11-01 | 大连海事大学 | Ship collision avoidance decision method and system based on interoperation technology |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809529A (en) * | 2015-05-13 | 2015-07-29 | 哈尔滨工程大学 | Multi-ship encounter collision prevention method for bacterial foraging optimization |
| CN105022270A (en) * | 2015-03-20 | 2015-11-04 | 武汉理工大学 | Automatic ship collision avoidance method based on velocity vector coordinate system |
| CN105185162A (en) * | 2015-10-26 | 2015-12-23 | 中国电子科技集团公司第二十八研究所 | AIS information-based multi-target anti-collision warning method |
| CN106249232A (en) * | 2016-08-24 | 2016-12-21 | 中国电子科技集团公司第二十八研究所 | Method for tracking target based on target travel situation information data association strategy |
| CN107577230A (en) * | 2017-08-16 | 2018-01-12 | 武汉理工大学 | A kind of intelligent avoidance collision system towards unmanned boat |
| CN108820157A (en) * | 2018-04-25 | 2018-11-16 | 武汉理工大学 | A kind of Ship Intelligent Collision Avoidance method based on intensified learning |
| CN109448442A (en) * | 2018-10-12 | 2019-03-08 | 天津大学 | The efficient monitoring method of more foul danger levels in a kind of sea area |
-
2019
- 2019-06-10 CN CN201910496804.8A patent/CN110400491A/en not_active Withdrawn
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105022270A (en) * | 2015-03-20 | 2015-11-04 | 武汉理工大学 | Automatic ship collision avoidance method based on velocity vector coordinate system |
| CN104809529A (en) * | 2015-05-13 | 2015-07-29 | 哈尔滨工程大学 | Multi-ship encounter collision prevention method for bacterial foraging optimization |
| CN105185162A (en) * | 2015-10-26 | 2015-12-23 | 中国电子科技集团公司第二十八研究所 | AIS information-based multi-target anti-collision warning method |
| CN106249232A (en) * | 2016-08-24 | 2016-12-21 | 中国电子科技集团公司第二十八研究所 | Method for tracking target based on target travel situation information data association strategy |
| CN107577230A (en) * | 2017-08-16 | 2018-01-12 | 武汉理工大学 | A kind of intelligent avoidance collision system towards unmanned boat |
| CN108820157A (en) * | 2018-04-25 | 2018-11-16 | 武汉理工大学 | A kind of Ship Intelligent Collision Avoidance method based on intensified learning |
| CN109448442A (en) * | 2018-10-12 | 2019-03-08 | 天津大学 | The efficient monitoring method of more foul danger levels in a kind of sea area |
Non-Patent Citations (6)
| Title |
|---|
| WILSON P A 等: "A line of sight counteraction navigation algorithm for ship encounter collision avoidance", 《THE JOURNAL OF NAVIGATION》 * |
| 刘静: "海上多船避碰决策系统的研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
| 周伟: "宽水域船舶智能避碰决策算法验证及优化", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
| 廖河树 等: "基于模拟器的宽水域船舶碰撞危险性评价模型", 《中国航海》 * |
| 李丽娜 等: "多船避碰智能决策的生成与优化方法", 《信息与控制》 * |
| 陈立家 等: "基于最优控制的海上多目标船避碰研究", 《中国安全科学学报》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110956853B (en) * | 2019-11-12 | 2022-02-22 | 武汉理工大学 | Multi-ship collision prediction method, system and storage medium |
| CN110956853A (en) * | 2019-11-12 | 2020-04-03 | 武汉理工大学 | Multi-ship collision prediction method, system and storage medium |
| CN111176271A (en) * | 2019-11-21 | 2020-05-19 | 智慧航海（青岛）科技有限公司 | Intelligent ship collision avoidance aid decision-making system based on shore-based radar and implementation method thereof |
| CN111176271B (en) * | 2019-11-21 | 2023-05-02 | 智慧航海（青岛）科技有限公司 | Intelligent ship collision avoidance auxiliary decision-making system based on shore radar and implementation method thereof |
| CN111007859A (en) * | 2019-12-24 | 2020-04-14 | 智慧航海（青岛）科技有限公司 | Ship meeting situation generation method for unmanned ship autonomous navigation simulation test |
| CN111007859B (en) * | 2019-12-24 | 2023-06-02 | 智慧航海（青岛）科技有限公司 | Ship meeting situation generation method for unmanned ship autonomous navigation simulation test |
| CN111260963A (en) * | 2020-03-11 | 2020-06-09 | 武汉理工大学 | Multi-ship meeting collision avoidance method |
| CN111260963B (en) * | 2020-03-11 | 2021-02-26 | 武汉理工大学 | Multi-ship meeting collision avoidance method |
| CN111445086B (en) * | 2020-04-17 | 2022-07-26 | 集美大学 | Method for predicting fly-back time based on PIDVCA |
| CN111445086A (en) * | 2020-04-17 | 2020-07-24 | 集美大学 | Method for predicting fly-back time based on PIDVCA |
| CN111951606B (en) * | 2020-07-29 | 2021-07-30 | 武汉理工大学 | Ship collision risk assessment and early warning method and system |
| CN111951606A (en) * | 2020-07-29 | 2020-11-17 | 武汉理工大学 | Ship collision risk assessment and early warning method and system |
| CN112149237A (en) * | 2020-10-15 | 2020-12-29 | 北京海兰信数据科技股份有限公司 | Real-time ship collision avoidance method and system |
| CN112820150A (en) * | 2020-12-29 | 2021-05-18 | 大连海事大学 | AIS-based ship collision avoidance decision method |
| CN114664118A (en) * | 2022-03-18 | 2022-06-24 | 陕西正整数科技有限公司 | Intelligent ship collision avoidance automatic test scene generation method and system |
| CN114664118B (en) * | 2022-03-18 | 2023-04-07 | 陕西正整数科技有限公司 | Intelligent ship collision avoidance automatic test scene generation method and system |
| CN115273555A (en) * | 2022-06-23 | 2022-11-01 | 集美大学 | Ship collision avoidance decision method for channel intersection area |
| CN115273555B (en) * | 2022-06-23 | 2024-04-09 | 集美大学 | Ship collision avoidance decision method for navigation channel intersection area |
| CN115273556A (en) * | 2022-06-24 | 2022-11-01 | 大连海事大学 | Ship collision avoidance decision method and system based on interoperation technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110400491A (en) | A kind of Open sea area multiple target auxiliary Decision of Collision Avoidance method and decision system | |
| CN110083155B (en) | Machine learning method for realizing ship anthropomorphic intelligent collision avoidance decision | |
| Goerlandt et al. | A risk-informed ship collision alert system: Framework and application | |
| Perera et al. | Fuzzy logic based decision making system for collision avoidance of ocean navigation under critical collision conditions | |
| Perera et al. | Intelligent ocean navigation and fuzzy-Bayesian decision/action formulation | |
| Bukhari et al. | An intelligent real-time multi-vessel collision risk assessment system from VTS view point based on fuzzy inference system | |
| Perera et al. | Autonomous guidance and navigation based on the COLREGs rules and regulations of collision avoidance | |
| Wang et al. | Multi-ship encounter situation adaptive understanding by individual navigation intention inference | |
| Shi et al. | Fuzzy logic-based modeling method for regional multi-ship collision risk assessment considering impacts of ship crossing angle and navigational environment | |
| Bakdi et al. | Fullest COLREGs evaluation using fuzzy logic for collaborative decision-making analysis of autonomous ships in complex situations | |
| Ni et al. | An application-orientated anti-collision path planning algorithm for unmanned surface vehicles | |
| Sedova et al. | Automated stationary obstacle avoidance when navigating a marine craft | |
| Mizythras et al. | A novel decision support methodology for oceangoing vessel collision avoidance | |
| Perera et al. | Possible COLREGs failures under digital helmsman of autonomous ships | |
| Li et al. | Simulation on vessel intelligent collision avoidance based on artificial fish swarm algorithm | |
| Hu et al. | A review on COLREGs-compliant navigation of autonomous surface vehicles: From traditional to learning-based approaches | |
| CN114999230A (en) | Collision risk assessment method based on collision area in ship field | |
| Vestre et al. | AIS-based near-collision database generation and analysis of real collision avoidance manoeuvres | |
| Zhang et al. | Collision avoidance method for autonomous ships based on modified velocity obstacle and collision risk index | |
| Zhen et al. | A novel deterministic search-based algorithm for multi-ship collaborative collision avoidance decision-making | |
| Liu et al. | Coordinated multi-stage and multi-objective optimization approach for ship collision avoidance decision-making | |
| Ni et al. | A deterministic collision avoidance decision-making system for multi-MASS encounter situation | |
| Perera et al. | Decision making system for the collision avoidance of marine vessel navigation based on COLREGs rules and regulations | |
| Zhuo et al. | Intelligent collision avoidance control for large ships | |
| Li et al. | Automation method for personifying intelligent decision-making for vessel collision avoidance |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191101 |