CN113703463A - Elite multi-population evolution algorithm-based ship collision avoidance path planning method - Google Patents

Elite multi-population evolution algorithm-based ship collision avoidance path planning method Download PDF

Info

Publication number
CN113703463A
CN113703463A CN202111115457.3A CN202111115457A CN113703463A CN 113703463 A CN113703463 A CN 113703463A CN 202111115457 A CN202111115457 A CN 202111115457A CN 113703463 A CN113703463 A CN 113703463A
Authority
CN
China
Prior art keywords
ship
collision avoidance
sub
path
population
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.)
Granted
Application number
CN202111115457.3A
Other languages
Chinese (zh)
Other versions
CN113703463B (en
Inventor
左毅
李义亮
北荣辅
张香惠
李铁山
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.)
Dalian Maritime University
Original Assignee
Dalian Maritime University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Dalian Maritime University filed Critical Dalian Maritime University
Priority to CN202111115457.3A priority Critical patent/CN113703463B/en
Publication of CN113703463A publication Critical patent/CN113703463A/en
Application granted granted Critical
Publication of CN113703463B publication Critical patent/CN113703463B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/0206—Control of position or course in two dimensions specially adapted to water vehicles
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation
    • Y02A30/30—Adapting or protecting infrastructure or their operation in transportation, e.g. on roads, waterways or railways

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides a ship collision avoidance path planning method based on an elite multi-population evolution algorithm. The method comprises the following steps: acquiring ship information by utilizing ship navigation aid equipment; judging the collision danger of the ship and the target ship, determining the meeting situation of the ship and the target ship, and determining the ship avoidance responsibility and the avoidance behavior; designing a ship collision avoidance motion process in meeting, and constructing a ship collision avoidance path; solving a ship collision avoidance path by using an elite multi-population evolution algorithm; and outputting the current optimal ship collision avoidance path. According to the ship collision avoidance path planning method based on the elite multi-population evolution algorithm, the collision danger and the meeting situation are judged according to the acquired ship information, the ship collision avoidance path is constructed, and the ship collision avoidance path is solved by using the elite multi-population evolution algorithm, so that the planning efficiency of the ship collision avoidance path is improved, the planning time is reduced, the online planning capability is enhanced, and the ship collision avoidance path planning method is more suitable for the current complex marine traffic environment.

Description

Elite multi-population evolution algorithm-based ship collision avoidance path planning method
Technical Field
The invention relates to the technical field of autonomous navigation of ships, in particular to a ship collision avoidance path planning method based on an elite multi-population evolution algorithm.
Background
In recent years, in order to reduce the occurrence of a collision accident, various vessel navigation aids have been installed on vessels, including a Global Positioning System (GPS), an Electronic Chart Display and Information System (ECDIS), an Automatic Identification System (AIS), and a vessel radar. The method provides more quantitative ship collision avoidance decision support for ship drivers, and researchers provide a ship collision avoidance path planning method.
Masanii Ito et al proposes a ship collision avoidance control method based on Genetic Algorithm (GA), constructs a ship collision avoidance path according to the longitude and latitude of a ship steering point, and updates the ship collision avoidance path through selection, intersection and variation operations of the Genetic Algorithm. Ming-Cheng Tsou and the like provide a ship collision avoidance path planning method based on an ant colony optimization algorithm, and according to the characteristics of ship collision avoidance control, a ship collision avoidance path is constructed by ship waiting navigation time, a ship collision avoidance steering angle, ship collision avoidance navigation time and a ship re-navigation steering angle, and the ship collision avoidance path is planned when a ship meets at a short distance. The decision problem of the genetic algorithm in the ship collision avoidance steering amplitude is researched by Xiaohua and the like, and the optimal collision avoidance steering angle is solved by applying the genetic algorithm according to the Distance to close Point of Approach (DCPA) and the Time To Close Point of Approach (TCPA) of a target ship relative to the ship. Height far away et al propose a navigation path planning method for a ship in an island and reef area, which generates a navigable path of the ship as an initial path by using a scanning search method, and searches an optimal ship island and reef area navigation path by using an Improved Genetic Algorithm (IGA).
In the face of a complex marine traffic environment, the current path planning method has the problems of weak online planning capability and incapability of being suitable for complex ship meeting situations. Therefore, the method for planning the ship path has important significance in improving the efficiency of planning the ship path and providing the path planning method with strong online planning capability.
Disclosure of Invention
According to the planning efficiency problem of the ship collision avoidance path, the invention provides the ship collision avoidance path planning method based on the elite multi-population evolution algorithm, which has the characteristics of short relative planning time and strong adaptability of the planned path and can quickly and effectively provide support for ship collision avoidance auxiliary decision.
The technical means adopted by the invention are as follows:
a ship collision avoidance path planning method based on an elite multi-population evolution algorithm comprises the following steps:
the method comprises the following steps:
s1, acquiring ship information by using the ship navigation aid;
s2, judging the collision risk of the ship and the target ship, determining the meeting situation of the ship and the target ship, and determining the ship avoidance responsibility and avoidance behavior;
s3, designing a ship collision avoidance motion process in meeting, and constructing a ship collision avoidance path;
s4, solving a ship collision avoidance path by using an elite multi-population evolution algorithm;
and S5, outputting the current optimal ship collision avoidance path.
Further, in the step S1, the acquired ship information includes the longitude and latitude, the heading, the speed of the ship, the longitude and latitude, the heading, the speed, the distance, and the direction of the target ship, the latest meeting distance DCPA and the latest meeting time TCPA of the ship and the target ship.
Further, the specific implementation process of step S2 is as follows:
s21, judging whether the ship and the target ship have collision danger or not, firstly setting a safe meeting distance of the ship, wherein the safe meeting distance of the ship is set as the radius of the safe area of the ship; when the nearest meeting distance DCPA between the ship and the target ship is less than the safe meeting distance and the nearest meeting time TCPA between the ship and the target ship is less than the safe meeting time, the two ships are considered to have collision danger;
s22, determining the meeting situation, the avoidance responsibility and the avoidance behavior of the ship and the target ship, and dividing the meeting state of the two ships into three types according to the international maritime collision avoidance rule: and when the ship bears avoidance responsibility, the ship needs to adopt an avoidance behavior of turning right to avoid collision with the target ship.
Further, the specific implementation process of step S3 is as follows:
s31, setting a ship avoidance point as S, a ship re-navigation point as E and a ship route intersection as C;
s32, constructing a ship avoidance steering angle A1And a ship re-voyage steering angle A2And the distance D of the ship avoidance point1Distance D between ship and ship re-navigation point2Ship collision avoidance path P consisting of four path variablesi＝{A1,A2,D1,D2}。
Further, the specific implementation process of step S4 is as follows:
s41, initializing M individuals in the population, namely initializing M ship collision avoidance paths PiGenerating a population P ═ P1,P2,···,PM-1,PM}, collision avoidance Path PiFour path variables are included: avoidance steering angle A1And a compound navigation steering angle A2Distance D of avoidance point1And a distance D of a compound flight point2Determining the value ranges of the four path variables according to the ship navigation condition and the operation habit, and representing the four path variables of the ship collision avoidance path by adopting a binary coding mode;
s42, calculating the fitness of each individual in the population, namely calculating the collision avoidance path P of each shipiFitness f (P) ofi)；
The planning of the ship collision avoidance path aims at providing a safe collision avoidance path with the shortest voyage, wherein the voyage N of the ship collision avoidance path comprises a ship avoidance voyage N1And the ship re-voyage course N2Respectively calculating the avoiding course N of the ship1And a ship re-voyage range N2And the ship collision avoidance path voyage N has the following calculation formula:
N1＝(D1+D2)×sinA2/sin(A1+A2)
N2＝(D1+D2)×sinA1/sin(A1+A2)
N＝(D1+D2)×(sinA1+sinA2)/sin(A1+A2)
the constraint conditions for guaranteeing the collision avoidance safety of the ship are set as follows:
dcpa1≥θsafe
dcpa2≥θsafe
in the above formula, dcpa1Showing the nearest meeting distance between the ship and the target ship in the process of ship avoidance, dcpa2The nearest meeting distance theta between the ship and the target ship in the process of ship re-voyage is shownsafeIndicating the set safe distance between the two ships;
calculating the adaptability f (P) of the ship collision avoidance pathi) The calculation formula is as follows:
f(Pi)＝δ*(NOC/N)
in the above formula, NOCA straight-line distance between the initial point O and the intersection C of the ship is shown, delta represents a ship safety factor, and delta is equal to 1 when the constraint condition in the step S43 is met, and delta is equal to 0 when the constraint condition is not met
S43, determining whether the convergence condition is reached, and setting the convergence condition to the following two conditions:
the first condition is as follows: reaching the set iteration times;
case two: the fitness value of the optimal collision avoidance path reaches the set fitness value;
meeting the convergence condition and outputting an optimal ship collision avoidance path;
s44, adopting a separate population strategy to randomly divide and combine the M ship collision avoidance paths into four sub-populations, namely A1Subset, A2Subset, D1Subset and D2Each sub-population comprises M/4 ship collision avoidance paths, and four path variables are independently optimized;
s45, calculating each sonCollision avoidance path P for ship groupiSub-fitness of (a); the calculation formula is as follows:
Figure BDA0003275415300000041
Figure BDA0003275415300000042
Figure BDA0003275415300000043
Figure BDA0003275415300000044
in the above formula, the first and second carbon atoms are,
Figure BDA0003275415300000045
is represented by A1Collision avoidance path P for sub-populationiThe sub-fitness of (a) is,
Figure BDA0003275415300000046
is represented by A2Collision avoidance path P for sub-populationiThe sub-fitness of (a) is,
Figure BDA0003275415300000047
represents D1Collision avoidance path P for sub-populationiThe sub-fitness of (a) is,
Figure BDA0003275415300000048
represents D2Collision avoidance path P for sub-populationiSub-fitness of (a);
s46, adopting a transfer-settlement strategy, transferring the elite collision-prevention path in one sub-population to other three sub-populations, replacing the collision-prevention paths in other sub-populations, selecting a ship collision-prevention path with good sub-adaptability from one sub-population, and transferring the ship collision-prevention path as the elite collision-prevention path to other sub-populations, for example, A1Elite collision avoidance path P for sub-populationsEMigration to A2、D1And D2The sub-population replaces collision avoidance paths in the sub-population;
s47, updating ship collision avoidance paths in each sub-population;
sorting M/4 ship collision avoidance paths in the sub-population from big to small according to the fitness, wherein the sizes of the sorted population P and the ship collision avoidance paths in the population are shown as the following formula:
P＝{P1,P2,P3,…,P(M-1)/4,PM/4}
f(Pi-1)＞f(Pi),i∈{2,3,4,…,(M-1)/4,M/4}
according to the partial order relation of the ship collision avoidance path sub-fitness, selecting an elite collision avoidance path to form an elite sub-population, namely A1Elite subpopulation, A2Elite subpopulation, D1Elite subpopulations and D2An elite subpopulation; snRepresenting the nth sub-population, wherein the collision avoidance path with the worst fitness is Pw，
Figure BDA0003275415300000049
Represents a sub-population SkAverage fitness of (1), i.e. sub-population SkThe average value of all the collision avoidance path fitness in the process, and the partial order relation is represented by the following formula: #
Figure BDA0003275415300000051
Figure BDA0003275415300000052
Selecting an elite ship collision avoidance path from M/4 ship collision avoidance paths of the sub-populations to form M/4 elite sub-populations S with the largest average sub-fitness, wherein the elite sub-populations are shown as follows:
S＝{S1,S2,S3,…,Sm-1,Sm}
S1＝{P1}
S2＝{P1,P2}
S3＝{P2}
S2n＝Sn∪Pw+1
S2n+1＝(Sn-Pw)∪Pw+1
s48, M new collision-prevention paths are generated by M elite sub-populations, the M new collision-prevention paths form a new population, one sub-population generates a new collision-prevention path, all collision-prevention paths in one elite sub-population are compared bit by bit according to binary codes, the values of corresponding positions are the same and reserved (0 or 1), if the values are different, the position is replaced by a random number 0 or 1, a new ship collision-prevention path is obtained, and the new population is continuously iterated until convergence;
and S49, outputting the optimal individuals, namely the optimal ship collision avoidance path obtained by solving, and outputting the optimal individuals when the set convergence condition is met, wherein the optimal individuals represent the safe collision avoidance path with the shortest solved voyage, so that four path variables for constructing the ship collision avoidance path are obtained, and an auxiliary decision is provided for a ship driver.
Compared with the prior art, the invention has the following advantages:
1. according to the ship collision avoidance path planning method based on the elite multi-population evolution algorithm, the collision danger and the meeting situation are judged according to the acquired ship information, the ship collision avoidance path is constructed, and the ship collision avoidance path is solved by using the elite multi-population evolution algorithm, so that the planning efficiency of the ship collision avoidance path is improved, the planning time is reduced, the online planning capability is enhanced, and the ship collision avoidance path planning method is more suitable for the current complex marine traffic environment.
2. The ship collision avoidance path planning method based on the elite multi-population evolution algorithm provided by the invention constructs a clear ship collision avoidance path comprising four path variables (ship collision avoidance steering angle A)1And a ship re-voyage steering angle A2And the distance D of the ship avoidance point1And the distance D from the ship re-navigation point2) Can simultaneously provide the decision support for avoiding the ship and the decision support for re-navigation of the ship, and is beneficial to improving the safety and the re-navigation of the ship in collision avoidanceAnd (4) economy.
3. The ship collision avoidance path planning method based on the elite multi-population evolution algorithm effectively improves the planning efficiency and the online planning capability of the ship collision avoidance path. Under the current increasingly complex and intensive marine traffic environment, the decision-making time left for the ship driver is reduced, and it is particularly important to provide decision support for the ship driver as soon as possible.
Based on the reason, the invention can be widely popularized in the fields of autonomous navigation of ships and the like.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is an overall flowchart of a ship collision avoidance path planning method provided by the present invention.
Fig. 2 is a schematic view of ship collision avoidance during ship encounter according to the present invention.
Fig. 3 is a flow chart of the elite multi-population evolution algorithm for planning the collision avoidance path of the ship provided by the invention.
FIG. 4 is a schematic diagram of collision avoidance paths generated by the elite multi-population evolution algorithm provided by the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
As shown in fig. 1, the invention provides a ship collision avoidance path planning method based on elite multi-population evolution algorithm, comprising the following steps:
s1, acquiring ship information by using the ship navigation aid; in this embodiment, the ship information to be acquired includes the longitude and latitude, the heading, the speed, the Distance and the direction of the ship, the Distance to close Point of Approach (DCPA) and the Closest Time To Close Point of Approach (TCPA) of the ship and the target ship.
S2, judging the collision risk of the ship and the target ship, determining the meeting situation of the ship and the target ship, and determining the ship avoidance responsibility and avoidance behavior; in the embodiment, the ship safety distance theta is set according to the nearest meeting distance DCPA and the nearest meeting time TCPA of the ship and the target shipsafeIt is determined whether there is a risk of collision.
In specific implementation, as a preferred embodiment of the present invention, the specific implementation process of step S2 is as follows:
s21, judging whether the ship and the target ship have collision danger or not, firstly setting a safe meeting distance of the ship, wherein the safe meeting distance of the ship is set as the radius of the safe area of the ship; when the nearest meeting distance DCPA between the ship and the target ship is less than the safe meeting distance and the nearest meeting time TCPA between the ship and the target ship is less than the safe meeting time, the two ships are considered to have collision danger;
s22, determining the meeting situation, the avoidance responsibility and the avoidance behavior of the ship and the target ship, and dividing the meeting state of the two ships into three types according to the international maritime collision avoidance rule: and when the ship bears avoidance responsibility, the ship needs to adopt an avoidance behavior of turning right to avoid collision with the target ship.
S3, designing a ship collision avoidance motion process in meeting, and constructing a ship collision avoidance path; as shown in fig. 2, a schematic view of collision avoidance of a ship in a meeting is provided. The complete ship collision avoidance motion process comprises the steps that a ship takes collision avoidance action, the ship gives way to a target ship, the ship takes re-voyage action, and the ship re-voyages to the original course of the original course and continues to sail. The ship collision avoidance motion process is divided into a ship collision avoidance decision process and a ship re-voyage decision process. The purpose of planning the ship collision avoidance path is to provide an auxiliary decision for ship driving or support for ship collision avoidance, so that it is particularly important to construct a clear and complete ship collision avoidance path. The complete ship collision avoidance decision process comprises a ship avoidance amplitude decision, a ship re-voyage amplitude decision, a ship avoidance opportunity decision and a ship re-voyage opportunity decision. The ship collision avoidance path consists of the following four path variables: ship avoidance steering angle A1Namely, making a decision on the avoidance amplitude of the ship; ship re-navigation steering angle A2Namely, the decision of the ship re-voyage amplitude; distance D of ship avoidance point1The distance between the avoidance point S and the intersection point C is determined, namely the avoidance opportunity decision of the ship is made; distance D between ship and its re-navigation point2And determining the distance between the re-navigation point S and the intersection C, namely the re-navigation opportunity of the ship. Thus, a ship collision avoidance path P is constructedi＝{A1,A2,D1,D2The whole ship collision avoidance decision process can be clearly represented.
In specific implementation, as a preferred embodiment of the present invention, the specific implementation process of step S3 is as follows:
s31, setting a ship avoidance point as S, a ship re-navigation point as E and a ship route intersection as C;
s32, constructing a ship avoidance steering angle A1And a ship re-voyage steering angle A2And the distance D of the ship avoidance point1Distance D between ship and ship re-navigation point2Ship collision avoidance path P consisting of four path variablesi＝{A1,A2,D1,D2}。
S4, solving a ship collision avoidance path by using an elite multi-population evolution algorithm; the solving speed of the ship collision avoidance path is improved, namely the planning efficiency of the ship collision avoidance path is improved. As shown in fig. 4, a schematic diagram of collision avoidance paths generated by the elite multi-population evolution algorithm provided by the present invention is shown.
In specific implementation, as a preferred embodiment of the present invention, as shown in fig. 3, the specific implementation process of step S4 is as follows:
s41, initializing M individuals in the population, namely initializing M ship collision avoidance paths PiGenerating a population P ═ P1,P2,···,PM-1,PM}, collision avoidance Path PiFour path variables are included: avoidance steering angle A1And a compound navigation steering angle A2Distance D of avoidance point1And a distance D of a compound flight point2Determining the value ranges of the four path variables according to the ship navigation condition and the operation habit, and representing the four path variables of the ship collision avoidance path by adopting a binary coding mode;
s42, calculating the fitness of each individual in the population, namely calculating the collision avoidance path P of each shipiFitness f (P) ofi)；
The planning of the ship collision avoidance path aims at providing a safe collision avoidance path with the shortest voyage, wherein the voyage N of the ship collision avoidance path comprises a ship avoidance voyage N1And the ship re-voyage course N2Respectively calculating the avoiding course N of the ship1And a ship re-voyage range N2And the ship collision avoidance path voyage N has the following calculation formula:
N1＝(D1+D2)×sinA2/sin(A1+A2)
N2＝(D1+D2)×sinA1/sin(A1+A2)
N＝(D1+D2)×(sinA1+sinA2)/sin(A1+A2)
the constraint conditions for guaranteeing the collision avoidance safety of the ship are set as follows:
dcpa1≥θsafe
dcpa2≥θsafe
in the above formula, dcpa1Showing the nearest meeting distance between the ship and the target ship in the process of ship avoidance, dcpa2The nearest meeting distance theta between the ship and the target ship in the process of ship re-voyage is shownsafeIndicating the set safe distance between the two ships;
calculating the adaptability f (P) of the ship collision avoidance pathi) The calculation formula is as follows:
f(Pi)＝δ*(NOC/N)
in the above formula, NOCA straight-line distance between the initial point O and the intersection C of the ship is shown, delta represents a ship safety factor, and delta is equal to 1 when the constraint condition in the step S43 is met, and delta is equal to 0 when the constraint condition is not met
S43, determining whether the convergence condition is reached, and setting the convergence condition to the following two conditions:
the first condition is as follows: reaching the set iteration times;
case two: the fitness value of the optimal collision avoidance path reaches the set fitness value;
meeting the convergence condition and outputting an optimal ship collision avoidance path;
s44, adopting a separate population strategy to randomly divide and combine the M ship collision avoidance paths into four sub-populations, namely A1Subset, A2Subset, D1Subset and D2Each sub-population comprises M/4 ship collision avoidance paths, and four path variables are independently optimized;
s45, respectively calculating collision avoidance paths P of the ships in each sub-populationiSub-fitness of (a); the calculation formula is as follows:
Figure BDA0003275415300000091
Figure BDA0003275415300000092
Figure BDA0003275415300000101
Figure BDA0003275415300000102
in the above formula, the first and second carbon atoms are,
Figure BDA0003275415300000103
is represented by A1Collision avoidance path P for sub-populationiThe sub-fitness of (a) is,
Figure BDA0003275415300000104
is represented by A2Collision avoidance path P for sub-populationiThe sub-fitness of (a) is,
Figure BDA0003275415300000105
represents D1Collision avoidance path P for sub-populationiThe sub-fitness of (a) is,
Figure BDA0003275415300000106
represents D2Collision avoidance path P for sub-populationiSub-fitness of (a); the purpose of planning the ship collision-prevention path is to obtain the safe collision-prevention path with the shortest voyage, and in a formula for calculating the voyage N of the ship collision-prevention path, the voyage N of the collision-prevention path and four path variables A1、A2、D1And D2And positive correlation is formed, so that the safe collision avoidance path with the minimum flight path N is solved, namely the four safe collision avoidance paths with the minimum path variables are solved. By collision avoidance path PiThe fitness formula of (a) obtains the sub-fitness of the four sub-populations.
S46, adopting a transfer strategy, transferring the elite collision avoidance path in one sub-population to other three sub-populations to replace the elite collision avoidance pathCollision avoidance paths in other sub-populations, selecting a ship collision avoidance path with good sub-fitness from one sub-population, and transferring the selected ship collision avoidance path to other sub-populations as an elite collision avoidance path, for example, A1Elite collision avoidance path P for sub-populationsEMigration to A2、D1And D2The sub-population replaces collision avoidance paths in the sub-population;
s47, updating ship collision avoidance paths in each sub-population;
sorting M/4 ship collision avoidance paths in the sub-population from big to small according to the fitness, wherein the sizes of the sorted population P and the ship collision avoidance paths in the population are shown as the following formula:
P＝{P1,P2,P3,…,P(M-1)/4,PM/4}
f(Pi-1)＞f(Pi),i∈{2,3,4,…,(M-1)/4,M/4}
according to the partial order relation of the ship collision avoidance path sub-fitness, selecting an elite collision avoidance path to form an elite sub-population, namely A1Elite subpopulation, A2Elite subpopulation, D1Elite subpopulations and D2An elite subpopulation; snRepresenting the nth sub-population, wherein the collision avoidance path with the worst fitness is Pw，
Figure BDA0003275415300000107
Represents a sub-population SkAverage fitness of (1), i.e. sub-population SkThe average value of all the collision avoidance path fitness in the process, and the partial order relation is represented by the following formula: #
Figure BDA0003275415300000108
Figure BDA0003275415300000109
Selecting an elite ship collision avoidance path from M/4 ship collision avoidance paths of the sub-populations to form M/4 elite sub-populations S with the largest average sub-fitness, wherein the elite sub-populations are shown as follows:
S＝{S1,S2,S3,…,Sm-1,Sm}
S1＝{P1}
S2＝{P1,P2}
S3＝{P2}
S2n＝Sn∪Pw+1
S2n+1＝(Sn-Pw)∪Pw+1
s48, M new collision-prevention paths are generated by M elite sub-populations, the M new collision-prevention paths form a new population, one sub-population generates a new collision-prevention path, all collision-prevention paths in one elite sub-population are compared bit by bit according to binary codes, the values of corresponding positions are the same and reserved (0 or 1), if the values are different, the position is replaced by a random number 0 or 1, a new ship collision-prevention path is obtained, and the new population is continuously iterated until convergence;
and S49, outputting the optimal individuals, namely the optimal ship collision avoidance path obtained by solving, and outputting the optimal individuals when the set convergence condition is met, wherein the optimal individuals represent the safe collision avoidance path with the shortest solved voyage, so that four path variables for constructing the ship collision avoidance path are obtained, and an auxiliary decision is provided for a ship driver.
And S5, outputting the current optimal ship collision avoidance path.
In conclusion, the invention provides a ship collision avoidance path planning method based on an elite multi-population evolution algorithm. According to the acquired ship information, collision danger and meeting situation are judged, a ship collision avoidance path is constructed, and the ship collision avoidance path is solved by using an elite multi-population evolution algorithm, so that the planning efficiency of the ship collision avoidance path is improved, the planning time is reduced, the online planning capability is enhanced, and the method is more suitable for the current complex marine traffic environment.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims (5)

1. A ship collision avoidance path planning method based on an elite multi-population evolution algorithm is characterized by comprising the following steps:
s1, acquiring ship information by using the ship navigation aid;
s2, judging the collision risk of the ship and the target ship, determining the meeting situation of the ship and the target ship, and determining the ship avoidance responsibility and avoidance behavior;
s3, designing a ship collision avoidance motion process in meeting, and constructing a ship collision avoidance path;
s4, solving a ship collision avoidance path by using an elite multi-population evolution algorithm;
and S5, outputting the current optimal ship collision avoidance path.
2. The ship collision avoidance path planning method based on the elite multi-population evolution algorithm according to claim 1, wherein the ship information obtained in the step S1 comprises the longitude and latitude, the heading and the speed of the ship, the longitude and latitude, the heading, the speed, the distance and the orientation of the target ship, the closest meeting distance DCPA and the closest meeting time TCPA of the ship and the target ship.
3. The ship collision avoidance path planning method based on the elite multi-population evolution algorithm according to claim 1, wherein the step S2 is implemented as follows:
s21, judging whether the ship and the target ship have collision danger or not, firstly setting a safe meeting distance of the ship, wherein the safe meeting distance of the ship is set as the radius of the safe area of the ship; when the nearest meeting distance DCPA between the ship and the target ship is less than the safe meeting distance and the nearest meeting time TCPA between the ship and the target ship is less than the safe meeting time, the two ships are considered to have collision danger;
s22, determining the meeting situation, the avoidance responsibility and the avoidance behavior of the ship and the target ship, and dividing the meeting state of the two ships into three types according to the international maritime collision avoidance rule: and when the ship bears avoidance responsibility, the ship needs to adopt an avoidance behavior of turning right to avoid collision with the target ship.
4. The ship collision avoidance path planning method based on the elite multi-population evolution algorithm according to claim 1, wherein the step S3 is implemented as follows:
s31, setting a ship avoidance point as S, a ship re-navigation point as E and a ship route intersection as C;
s32, constructing a ship avoidance steering angle A1And a ship re-voyage steering angle A2And the distance D of the ship avoidance point1Distance D between ship and ship re-navigation point2Ship collision avoidance path P consisting of four path variablesi＝{A1,A2,D1,D2}。
5. The ship collision avoidance path planning method based on the elite multi-population evolution algorithm according to claim 1, wherein the step S4 is implemented as follows:
s41, initializing M individuals in the population, namely initializing M ship collision avoidance paths PiGenerating a population P ═ P1,P2,···,PM-1,PM}, collision avoidance Path PiFour path variables are included: avoidance steering angle A1And a compound navigation steering angle A2Distance D of avoidance point1And a distance D of a compound flight point2Determining the value ranges of the four path variables according to the ship navigation condition and the operation habit, and representing the four path variables of the ship collision avoidance path by adopting a binary coding mode;
s42, calculating the fitness of each individual in the population, namely calculating the collision avoidance path P of each shipiFitness f (P) ofi)；
The planning of the ship collision avoidance path aims at providing a safe collision avoidance path with the shortest voyage, wherein the voyage N of the ship collision avoidance path comprises a ship avoidance voyage N1And the ship re-voyage course N2Respectively calculating the avoiding course N of the ship1And a ship re-voyage range N2And the ship collision avoidance path voyage N has the following calculation formula:
N1＝(D1+D2)×sinA2/sin(A1+A2)
N2＝(D1+D2)×sinA1/sin(A1+A2)
N＝(D1+D2)×(sinA1+sinA2)/sin(A1+A2)
the constraint conditions for guaranteeing the collision avoidance safety of the ship are set as follows:
dcpa1≥θsafe
dcpa2≥θsafe
in the above formula, dcpa1Showing the nearest meeting distance between the ship and the target ship in the process of ship avoidance, dcpa2The nearest meeting distance theta between the ship and the target ship in the process of ship re-voyage is shownsafeIndicating the set safe distance between the two ships;
calculating the adaptability f (P) of the ship collision avoidance pathi) The calculation formula is as follows:
f(Pi)＝δ*(NOC/N)
in the above formula, NOCA straight-line distance between the initial point O and the intersection C of the ship is shown, delta represents a ship safety factor, and delta is equal to 1 when the constraint condition in the step S43 is met, and delta is equal to 0 when the constraint condition is not met
S43, determining whether the convergence condition is reached, and setting the convergence condition to the following two conditions:
the first condition is as follows: reaching the set iteration times;
case two: the fitness value of the optimal collision avoidance path reaches the set fitness value;
meeting the convergence condition and outputting an optimal ship collision avoidance path;
S44、adopting a separate population strategy, randomly dividing and combining M ship collision-preventing paths into four sub-populations, namely A1Subset, A2Subset, D1Subset and D2Each sub-population comprises M/4 ship collision avoidance paths, and four path variables are independently optimized;
s45, respectively calculating collision avoidance paths P of the ships in each sub-populationiSub-fitness of (a); the calculation formula is as follows:
Figure FDA0003275415290000031
Figure FDA0003275415290000032
Figure FDA0003275415290000033
Figure FDA0003275415290000034
in the above formula, the first and second carbon atoms are,
Figure FDA0003275415290000035
is represented by A1Collision avoidance path P for sub-populationiThe sub-fitness of (a) is,
Figure FDA0003275415290000036
is represented by A2Collision avoidance path P for sub-populationiThe sub-fitness of (a) is,
Figure FDA0003275415290000037
represents D1Collision avoidance path P for sub-populationiThe sub-fitness of (a) is,
Figure FDA0003275415290000038
represents D2Collision avoidance path P for sub-populationiSub-fitness of (a);
s46, adopting a transfer-settlement strategy, transferring the elite collision-prevention path in one sub-population to other three sub-populations, replacing the collision-prevention paths in other sub-populations, selecting a ship collision-prevention path with good sub-adaptability from one sub-population, and transferring the ship collision-prevention path as the elite collision-prevention path to other sub-populations, for example, A1Elite collision avoidance path P for sub-populationsEMigration to A2、D1And D2The sub-population replaces collision avoidance paths in the sub-population;
s47, updating ship collision avoidance paths in each sub-population;
sorting M/4 ship collision avoidance paths in the sub-population from big to small according to the fitness, wherein the sizes of the sorted population P and the ship collision avoidance paths in the population are shown as the following formula:
P＝{P1,P2,P3,…,P(M-1)/4,PM/4}
f(Pi-1)＞f(Pi),i∈{2,3,4,…,(M-1)/4,M/4}
according to the partial order relation of the ship collision avoidance path sub-fitness, selecting an elite collision avoidance path to form an elite sub-population, namely A1Elite subpopulation, A2Elite subpopulation, D1Elite subpopulations and D2An elite subpopulation; snRepresenting the nth sub-population, wherein the collision avoidance path with the worst fitness is Pw，
Figure FDA0003275415290000039
Represents a sub-population SkAverage fitness of (1), i.e. sub-population SkThe average value of all the collision avoidance path fitness in the process, and the partial order relation is represented by the following formula: #
Figure FDA0003275415290000041
Figure FDA0003275415290000042
Selecting an elite ship collision avoidance path from M/4 ship collision avoidance paths of the sub-populations to form M/4 elite sub-populations S with the largest average sub-fitness, wherein the elite sub-populations are shown as follows:
S＝{S1,S2,S3,…,Sm-1,Sm}
S1＝{P1}
S2＝{P1,P2}
S3＝{P2}
S2n＝Sn∪Pw+1
S2n+1＝(Sn-Pw)∪Pw+1
s48, M new collision-prevention paths are generated by M elite sub-populations, the M new collision-prevention paths form a new population, one sub-population generates a new collision-prevention path, all collision-prevention paths in one elite sub-population are compared bit by bit according to binary codes, the values of corresponding positions are the same and reserved (0 or 1), if the values are different, the position is replaced by a random number 0 or 1, a new ship collision-prevention path is obtained, and the new population is continuously iterated until convergence;
and S49, outputting the optimal individuals, namely the optimal ship collision avoidance path obtained by solving, and outputting the optimal individuals when the set convergence condition is met, wherein the optimal individuals represent the safe collision avoidance path with the shortest solved voyage, so that four path variables for constructing the ship collision avoidance path are obtained, and an auxiliary decision is provided for a ship driver.
CN202111115457.3A 2021-09-23 2021-09-23 Ship collision avoidance path planning method based on elite multi-population evolution algorithm Active CN113703463B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111115457.3A CN113703463B (en) 2021-09-23 2021-09-23 Ship collision avoidance path planning method based on elite multi-population evolution algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111115457.3A CN113703463B (en) 2021-09-23 2021-09-23 Ship collision avoidance path planning method based on elite multi-population evolution algorithm

Publications (2)

Publication Number Publication Date
CN113703463A true CN113703463A (en) 2021-11-26
CN113703463B CN113703463B (en) 2023-12-05

Family

ID=78661746

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111115457.3A Active CN113703463B (en) 2021-09-23 2021-09-23 Ship collision avoidance path planning method based on elite multi-population evolution algorithm

Country Status (1)

Country Link
CN (1) CN113703463B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115268472A (en) * 2022-09-28 2022-11-01 天津大学 Intelligent ship navigation collision avoidance behavior coding method based on machine language expression
CN115620558A (en) * 2022-08-02 2023-01-17 集美大学 Intelligent ship collision avoidance decision method based on improved brain storm optimization algorithm

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102081752A (en) * 2011-01-27 2011-06-01 西北工业大学 Dynamic flight path planning method based on adaptive mutation genetic algorithm
KR101647743B1 (en) * 2015-07-07 2016-08-11 한국해양과학기술원 Navigation system of ships for avoiding collision using time series graphic interface
CN109765890A (en) * 2019-01-14 2019-05-17 哈尔滨工程大学 A kind of more USV multi-agent synergy collision-avoidance planning methods based on genetic algorithm
CN111063218A (en) * 2019-06-24 2020-04-24 武汉理工大学 Ship collision avoidance decision method
CN111338356A (en) * 2020-04-07 2020-06-26 哈尔滨工程大学 Multi-target unmanned ship collision avoidance path planning method for improving distributed genetic algorithm
LU102400A1 (en) * 2019-08-06 2021-02-09 Nanjing Seawolf Ocean Tech Co Ltd Path planning method and system for unmanned surface vehicle based on improved genetic algorithm
CN113032896A (en) * 2021-02-25 2021-06-25 武汉理工大学 Collision avoidance aid decision-making method based on ship driver preference

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102081752A (en) * 2011-01-27 2011-06-01 西北工业大学 Dynamic flight path planning method based on adaptive mutation genetic algorithm
KR101647743B1 (en) * 2015-07-07 2016-08-11 한국해양과학기술원 Navigation system of ships for avoiding collision using time series graphic interface
CN109765890A (en) * 2019-01-14 2019-05-17 哈尔滨工程大学 A kind of more USV multi-agent synergy collision-avoidance planning methods based on genetic algorithm
CN111063218A (en) * 2019-06-24 2020-04-24 武汉理工大学 Ship collision avoidance decision method
LU102400A1 (en) * 2019-08-06 2021-02-09 Nanjing Seawolf Ocean Tech Co Ltd Path planning method and system for unmanned surface vehicle based on improved genetic algorithm
CN111338356A (en) * 2020-04-07 2020-06-26 哈尔滨工程大学 Multi-target unmanned ship collision avoidance path planning method for improving distributed genetic algorithm
CN113032896A (en) * 2021-02-25 2021-06-25 武汉理工大学 Collision avoidance aid decision-making method based on ship driver preference

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
MING-CHENG TSOU: "Decision Support from Genetic Algorithms for Ship Collision Avoidance Route Planning and Alerts", THE JOURNAL OF NAVIGATION, vol. 63, no. 1, pages 167 - 182 *
陈卓: "基于进化势场模型的无人艇路径规划算法", 武汉理工大学学报, vol. 43, no. 1, pages 113 - 124 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115620558A (en) * 2022-08-02 2023-01-17 集美大学 Intelligent ship collision avoidance decision method based on improved brain storm optimization algorithm
CN115268472A (en) * 2022-09-28 2022-11-01 天津大学 Intelligent ship navigation collision avoidance behavior coding method based on machine language expression
CN115268472B (en) * 2022-09-28 2022-12-20 天津大学 Intelligent ship navigation collision avoidance behavior coding method based on machine language expression

Also Published As

Publication number Publication date
CN113703463B (en) 2023-12-05

Similar Documents

Publication Publication Date Title
KR102673743B1 (en) Device for determining the optimal route of a maritime vessel
CN112327885B (en) Unmanned ship self-adaptive global-local mixed path planning method
CN113703463A (en) Elite multi-population evolution algorithm-based ship collision avoidance path planning method
CN112580261B (en) Multi-ship collision avoidance decision method and device
KR101831264B1 (en) Autonomous navigation system and method for a maneuverable platform
CN109597417B (en) Multi-USV group collaborative collision avoidance planning method based on collision avoidance criterion
CN110196598B (en) Dynamic collision avoidance method for unmanned ship
CN110956853B (en) Multi-ship collision prediction method, system and storage medium
CN106845716A (en) A kind of unmanned surface vehicle local delamination paths planning method based on navigation error constraint
CN113156947B (en) Method for planning path of ship in dynamic environment
Enevoldsen et al. Colregs-informed rrt* for collision avoidance of marine crafts
Pereira et al. Toward risk aware mission planning for autonomous underwater vehicles
CN112578793B (en) Obstacle avoiding method for fast moving surface boat
Tsou Integration of a geographic information system and evolutionary computation for automatic routing in coastal navigation
CN113538973B (en) Automatic ship collision avoidance method based on improved particle swarm optimization
CN113110424A (en) Unmanned ship collision avoidance method based on chart information
Sedova et al. Automated stationary obstacle avoidance when navigating a marine craft
Thyri et al. A domain-based and reactive COLAV method with a partially COLREGs-compliant domain for ASVs operating in confined waters.
Teng et al. A dynamic path planning method for terrain-aided navigation of autonomous underwater vehicles
CN115167404A (en) Offshore autonomous surface ship collision avoidance decision method based on migration reinforcement learning
Mahipala et al. Model Predictive Control for Path Following and Collision-Avoidance of Autonomous Ships in Inland Waterways
Chen et al. Decision support based on artificial fish swarm for ship collision avoidance from AIS data
CN114675652A (en) Multi-target ship route planning method based on AIS data in dynamic environment
CN113625728A (en) Performance-limited ship collision avoidance path planning method
Lamm et al. Statistical maneuver net generation for anomaly detection in navigational waterways

Legal Events

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