CN113095627A - Irregular restricted area ship scheduling method - Google Patents

Irregular restricted area ship scheduling method Download PDF

Info

Publication number
CN113095627A
CN113095627A CN202110287094.5A CN202110287094A CN113095627A CN 113095627 A CN113095627 A CN 113095627A CN 202110287094 A CN202110287094 A CN 202110287094A CN 113095627 A CN113095627 A CN 113095627A
Authority
CN
China
Prior art keywords
ship
scheduling
command
time
navigation
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
CN202110287094.5A
Other languages
Chinese (zh)
Other versions
CN113095627B (en
Inventor
王燕霞
甘少君
陈艳艳
王德军
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.)
Beijing University of Technology
Original Assignee
Beijing University of Technology
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 Beijing University of Technology filed Critical Beijing University of Technology
Priority to CN202110287094.5A priority Critical patent/CN113095627B/en
Publication of CN113095627A publication Critical patent/CN113095627A/en
Application granted granted Critical
Publication of CN113095627B publication Critical patent/CN113095627B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Landscapes

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

Abstract

In inland river shipping, how to schedule ships to pass through restricted areas in an optimal sequence is one of important work contents of management departments such as a maritime office, a channel office, a three gorges navigation management office and the like. The conventional ship dispatching command is carried out according to a determination rule, is easily influenced by subjective factors of annunciators, cannot adapt to a dynamic environment with constantly changing restricted areas, and causes the condition that a large amount of waiting time is consumed by ships and the passing efficiency is low. The patent provides an irregular ship scheduling command method, which utilizes a machine learning method, particularly a reinforcement learning algorithm, and explores the benefits of ship scheduling schemes in different application scenes through a computer to finally obtain the optimal scheduling scheme under a specific scene, so that the ship passing efficiency is improved and the waiting time is reduced on the basis of ensuring the ship navigation safety.

Description

Irregular restricted area ship scheduling method
Technical Field
The patent relates to a ship scheduling method for an irregular restricted area, and belongs to the technical field of inland river shipping.
Background
In inland river shipping, how to schedule ships to pass through restricted areas in an optimal sequence is one of important work contents of management departments such as a maritime office, a channel office, a three gorges navigation management office and the like. The restricted area refers to an area where a ship cannot freely navigate and needs to pass through orderly according to traffic command signals, such as a three gorges dam area and a control river reach in the middle and upstream of the Yangtze river. The ship passing command signal not only needs to ensure that the ship passes safely, but also needs to reduce the waiting time of the ship in the queuing process as much as possible and improve the passing efficiency.
Almost all existing dispatch guidance methods are of a rule-oriented type, i.e., there are definite rules to guide how to dispatch the ship traffic sequence. For example, in the process of passing through a restricted channel at the upstream of the Yangtze river, a ship is mainly scheduled and commanded according to the rule of 'launching first and walking first'; and dispatching and commanding are carried out according to the principle of first-come first-walk in the process that the ship passes the dam in the three gorges dam region. According to the fixed rule, the ship is guided to orderly pass through the restrictive area, the navigation safety of the ship can be guaranteed, the passing efficiency of the ship cannot be guaranteed, and the commanding process is very easily influenced by the subjective psychological factors of the annunciator. In the existing ship dispatching and commanding process, a ship usually needs to wait for tens of minutes at a command section to pass through a restricted area, and even needs to wait for hours in an extreme case.
Disclosure of Invention
The invention provides a ship scheduling method in an irregular restrictive area, which aims to overcome the technical problems in the technical background and provide the ship scheduling method in the irregular restrictive area. The irregular ship scheduling command method mainly refers to the technical scheme that the benefit of ship scheduling schemes in different application scenes is explored through a computer by using machine learning, particularly a reinforcement learning method, so that the optimal scheduling scheme under a specific scene is finally obtained, the ship passing efficiency is improved on the basis of ensuring the ship navigation safety, and the waiting time is shortened. Different application scenes comprise occasions where ships pass through a dam in a three gorges dam area, ships enter and exit a port at a wharf, control river reach ship scheduling and the like in sequence according to scheduling commands, and the occasions are passed by different types and different numbers of ships in different modes.
In order to achieve the above purpose, the invention provides the following technical scheme:
(1) randomly initializing the value of Q (s, a), wherein s is a ship state characterization vector, a represents a adopted ship dispatching command, and the value of Q (s, a) characterizes the score of the dispatching command a in the ship sailing state s. The larger the value of Q (s, a) is, the higher the score of the dispatching command a is, the closer the dispatching command a is to the optimal command in the ship sailing state s is, namely, the shorter the waiting time of the ship is, the higher the traffic efficiency is.
(2) Generating n pieces of ship information about to pass through the restricted navigation channel area by the computer according to the restricted area scene needing to be dispatched, wherein the n pieces of ship information comprise the specific position (longitude and latitude), the navigation speed and the heading information of the ship.
(3) Predicting the time PAT of the n ships reaching the command section according to the navigation information of the n ships at the current time ttAnd the time PCT required for passing in a restricted areatWherein
Figure BDA0002980916950000021
(4) PAT according to all ships near the restricted areatAnd PCTtAnd constructing a current ship navigation state characterization vector s.
(5) Randomly selecting a ship scheduling scheme selection factor lambda between 0 and 1. If the lambda is larger than or equal to the preset value delta, selecting a scheduling instruction with the highest score from the selectable scheduling instructions of the current ship state s; and if the lambda is smaller than the preset value delta, randomly selecting one dispatching command from the selectable dispatching commands of the current ship state s. The convergence speed and effect of the delta control algorithm are improved, the smaller the delta is, the faster the convergence speed of the algorithm is, but the algorithm is easy to fall into local optimum; the algorithm with larger delta is easier to search the optimal scheduling command scheme, but the relative convergence speed is slow. In practical application, δ may take the value of 1-k/T, where k is the current iteration number and T is the maximum iteration number.
(6) Let the scheduling instruction selected in step 5 be a. Execution scheduling fingerLet a, set the current ship passing through the restricted channel as ship j, and record the actual arrival time of ship j at the restricted channel
Figure BDA0002980916950000022
And actual voyage time in restricted channels
Figure BDA0002980916950000023
(7) Update all ships' PATt +1 and PCT at time t +1t+1Wherein the jth ship has passed the restricted path at time t +1, the actual recorded arrival time of the ship at the restricted path can be used according to equations (1) (2)
Figure BDA0002980916950000031
And passing restricted channel time
Figure BDA0002980916950000032
Instead of predicting the time:
Figure BDA0002980916950000033
Figure BDA0002980916950000034
(8) calculating the influence delta of the dispatching command a on the current navigation states of all ships according to the formula (3):
Δ＝PATt+1+PCTt+1-PATt-PCTt (3)
(9) updating the score Q (s, a) of the scheduling command a in the ship sailing state s, as shown in formula (4):
Q(s，a)←Q(s，a)-Δ (4)
(10) repeating the processes (2) - (9) T times until the Q (s, a) value is not changed any more, i.e. the scores of all the dispatching orders a have converged under all the ship states s.
(11) And after the stable Q (s, a) value is obtained, the dynamic and static information such as the position, the speed, the course and the like of the ship near the restricted area can be obtained and analyzed through AIS equipment/radar/video monitoring.
(12) And predicting the time for the ship to reach the command section and the time required for the ship to sail in the restricted area according to the ship position information and the speed information.
(13) Constructing a sailing state s for the ship near the restricted area according to the time for the ship to reach the command section and the time required for sailing in the restricted area.
(14) Traverse the scheduling instruction a that makes Q (s,) get the maximum value as the current scheduling instruction, "·" is all feasible scheduling instruction sets in the current state s, i.e., a ═ argmax Q (s,). In the last process, a stable Q (s, a) value is obtained by learning, that is, the scores of all dispatching instructions are known in all ship states s, so that the step only needs to traverse the dispatching instruction a obtaining the maximum Q (s, ·) value in the current state s.
(15) Sending a dispatch instruction a to the ship.
Compared with the prior art, the invention has the following advantages: according to the irregular ship scheduling command method, the benefits of ship scheduling schemes in different application scenes are explored through a machine learning algorithm, the optimal scheduling scheme under a specific scene is finally obtained, the personalized scheduling of ship navigation is realized, the ship passing efficiency is improved, the interference of subjective factors of annunciators in the manual command process is avoided, the ship passing efficiency is improved on the basis of ensuring the ship navigation safety, and the waiting time is shortened.
Drawings
FIG. 1 is a flow chart of a general technical scheme of a ship scheduling method in an irregular restricted area;
FIG. 2 is a ship scheduling command flow in an irregular restrictive area;
FIG. 3 is a flowchart of a technical scheme of a specific irregular restricted area ship scheduling method;
Detailed Description
The example is studied for the process of dispatching and commanding a ship through a charter-mouth restrictive channel in Sichuan province. The length of the Shenbei nozzle-limited channel is about 3km, about 30 minutes is needed for passing the backwater ship, about 15 minutes is needed for passing the tailrace ship, and the number of the ships passing the Shenbei nozzle-limited channel is about 50.
Referring to fig. 1, the present embodiment provides a general technical solution flow:
referring to fig. 2, the present embodiment provides a ship dispatching command process:
referring to fig. 3, an embodiment of the process:
the implementation process of the technical scheme of the embodiment is as follows:
(1) randomly initialize the neural network Q. The number of hidden layers and the number of nodes of the hidden layers are determined according to the complexity of the scene. The more complex the scenario, the greater the number of hidden layers and hidden layer nodes. In the embodiment, Q comprises 4 hidden layers, and each hidden layer comprises 10 hidden layer nodes; the input layer comprises 5 nodes; the output layer comprises 8 nodes; the hidden layer activation function adopts a sigmoid function, and the output layer adopts a softmax function. And taking the ship state characterization vector s and the ship dispatching command a as input variables, and taking Q (s, a) as an output variable to represent the fraction of the dispatching command a which can be taken.
(2) Generating, by the computer, 2000 ship information including longitude, latitude, sailing speed, and heading of the ship, depending on the specific scenario of the restricted area.
(3) Calculating and predicting the time PAT for the ship to reach the command sectiontAnd the time PCT required to navigate within a restricted areatAnd constructing a ship navigation state vector s ═ PATt，PCTt]Wherein
Figure BDA0002980916950000041
Figure BDA0002980916950000042
(4) And selecting a ship scheduling scheme selection factor lambda at equal probability of 0-1, wherein delta is set to be 1-k/1000, and k is the current iteration number. And if lambda is smaller than delta, inputting the ship navigation state vector s into the network Q, and adopting the scheduling instruction corresponding to the node with the maximum network output value as the optimal scheduling instruction of the ship in the navigation state through the hidden node operation of each hidden layer. And if the lambda is larger than or equal to the delta, randomly selecting one dispatching command from the selectable dispatching commands of the current ship state s.
(5) And (5) setting the dispatching command selected in the step (4) as a, sending the dispatching command a to all ships near the restricted area by adopting a ship passing signal revealing device, and allowing the ships to pass according to the dispatching command a. Setting the current ship passing through the restrictive channel as a ship j, and recording the time of the ship j actually reaching the restrictive channel
Figure BDA0002980916950000051
Actual voyage time in restricted channel
Figure BDA0002980916950000052
(6) After the scheduling instruction a is executed, acquiring and analyzing the longitude, the latitude, the navigation speed and the course of the ship near the restricted area again through AIS equipment/radar/video monitoring.
(7) Calculating and predicting the time of the ship reaching the command section and the time required for the ship to sail in the restricted area, and updating a ship sailing state vector s', s ═ PATt+1，PCTt+1]Where vessel j has passed through the control river reach, the actual recorded time may be substituted for the predicted time according to equations (5) (6)
Figure BDA0002980916950000053
Figure BDA0002980916950000054
(8) Calculating the influence delta of the dispatching command a on the current navigation states of all ships according to the formula (7):
Δ＝PATt+1+PCTt+1-PATt-PCTt (7)
(9) updating the score Q (s, a) of the scheduling command a in the ship sailing state s, as shown in formula (8):
Q(s，a)←Q(s，a)-Δ (8)
(10) and (5) taking the score of the dispatching instruction a in the step (9) as the output of the neural network Q, taking the ship navigation state variable s and the dispatching instruction a in the step (3) as the input of the neural network Q, and training network parameters by adopting a Levenberg-Marquarelt algorithm.
(11) And (5) repeating the steps (2) to (10) for 1000 times to obtain a stable Q (s, a) value, namely completing the establishment of the ship dispatching command model Q.
(12) And acquiring and analyzing dynamic and static information such as the position, the speed, the course and the like of the ship near the restricted area through AIS equipment/radar/video monitoring.
(13) And predicting the time for the ship to reach the command section and the time required for the ship to sail in the restricted area according to the ship position information and the speed information.
(14) Constructing a sailing state s for the ship near the restricted area according to the time for the ship to reach the command section and the time required for sailing in the restricted area.
(15) Traverse the scheduling instruction a that makes Q (s,) get the maximum value as the current scheduling instruction, "·" is all feasible scheduling instruction sets in the current state s, i.e., a ═ argmax Q (s,). In the last process, a stable Q (s, a) value is obtained by learning, that is, the scores of all dispatching instructions are known in all ship states s, so that the step only needs to traverse the dispatching instruction a obtaining the maximum Q (s, ·) value in the current state s.
(16) Sending a dispatch instruction a to the ship.

Claims (1)

1. An irregular ship dispatching command method is characterized in that: the method comprises the following steps:
the method comprises the following steps: randomly initializing a numerical value of Q (s, a), wherein s is a ship state characterization vector, a represents a adopted ship scheduling command, and the numerical value of Q (s, a) characterizes the fraction obtained by the scheduling command a in a ship navigation state s; the larger the value of Q (s, a) is, the higher the score obtained by the dispatching command a is, the closer the dispatching command a is to the optimal command in the ship navigation state s is, namely, the shorter the waiting time of the ship is, the higher the traffic efficiency is;
step two: generating n pieces of ship information about to pass through a restricted navigation channel area by a computer according to a restricted area scene needing scheduling, wherein the n pieces of ship information comprise longitude and latitude of specific positions of a ship, navigation speed and course information;
step three: predicting the time PAT of the n ships reaching the command section according to the navigation information of the n ships at the current time ttAnd the time PCT required for passing in a restricted areatWherein
Figure FDA0002980916940000011
Figure FDA0002980916940000012
Step four: PAT according to all ships near the restricted areatAnd PCTtConstructing a current ship navigation state characterization vector s;
step five: randomly selecting a ship scheduling scheme selection factor lambda between 0 and 1; if the lambda is larger than or equal to the preset value delta, selecting a scheduling instruction with the highest score from the selectable scheduling instructions of the current ship state s; if lambda is smaller than a preset value delta, randomly selecting a scheduling instruction from the selectable scheduling instructions of the current ship state s; the convergence speed and effect of the delta control algorithm are improved, the smaller the delta is, the faster the convergence speed of the algorithm is, but the algorithm is easy to fall into local optimum; the algorithm is easier to search the optimal scheduling command scheme when the delta is larger, but the relative convergence speed is slow; in practical application, the value of delta can be 1-k/T, wherein k is the current iteration frequency, and T is the maximum iteration frequency;
step six: setting the scheduling instruction selected in the fifth step as a; executing a dispatching instruction a, setting the current ship passing through the restricted channel as a ship j, and recording the time of the ship j actually reaching the restricted channel
Figure FDA0002980916940000013
And actual voyage time in restricted channels
Figure FDA0002980916940000014
Step seven: updating PAT of all ships at t +1 momentt+1And PCTt+1Wherein the j-th ship passes through the restricted navigation channel at the time t +1, the actual recorded arrival time of the ship in the restricted area can be used according to the formulas (1) and (2)
Figure FDA0002980916940000015
And the time when the ship actually passes through the restricted area
Figure FDA0002980916940000016
Instead of predicting the time:
Figure FDA0002980916940000017
Figure FDA0002980916940000018
step eight: calculating the influence delta of the dispatching command a on the current navigation states of all ships according to a formula (3):
Δ＝PATt+1+PCTt+1-PATt-PCTt (3)
step nine: updating the score Q (s, a) of the scheduling command a in the ship sailing state s, as shown in formula (4):
Q(s，a)←Q(s，a)-Δ (4)
step ten: repeating the steps from two times to nine times until the Q (s, a) value is not changed any more, namely under all ship states s, the scores of all the dispatching commands a are converged;
step eleven: after a stable Q (s, a) value is obtained, position, speed and course information of a ship near a restricted area are obtained and analyzed through AIS equipment/radar/video;
step twelve: predicting the time of the ship reaching the command section and the time required by navigation in the restricted area according to the position information and the speed information of the ship;
step thirteen: constructing a sailing state s of the ship near the restricted area according to the time of the ship reaching the command section and the time required by sailing in the restricted area;
fourteen steps: traversing the scheduling instruction a which enables the Q (s, ·) to obtain the maximum value as the current scheduling instruction, "·" represents all feasible scheduling instruction sets in the current state s, namely a ═ argmax Q (s, ·);
step fifteen: and sending a dispatching command a to the ship.
CN202110287094.5A 2021-03-17 2021-03-17 Irregular restricted area ship scheduling method Active CN113095627B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110287094.5A CN113095627B (en) 2021-03-17 2021-03-17 Irregular restricted area ship scheduling method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110287094.5A CN113095627B (en) 2021-03-17 2021-03-17 Irregular restricted area ship scheduling method

Publications (2)

Publication Number Publication Date
CN113095627A true CN113095627A (en) 2021-07-09
CN113095627B CN113095627B (en) 2024-03-12

Family

ID=76669289

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110287094.5A Active CN113095627B (en) 2021-03-17 2021-03-17 Irregular restricted area ship scheduling method

Country Status (1)

Country Link
CN (1) CN113095627B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115410417A (en) * 2022-07-20 2022-11-29 国能浙江北仑第一发电有限公司 Ship dispatching berthing prediction system based on environmental factors

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103531043A (en) * 2013-09-27 2014-01-22 重庆大学 Point-to-point ship sailing time estimation method based on ship route matching
CN104657538A (en) * 2015-01-04 2015-05-27 河海大学 Simulation method for scheduling multi-code channel
CN104882028A (en) * 2015-05-11 2015-09-02 长江泸州航道局 Ship traffic command method for dual control reach
CN112309173A (en) * 2020-11-02 2021-02-02 长江重庆航道局 Intelligent command supervision system for controlling navigation of ships in river reach

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103531043A (en) * 2013-09-27 2014-01-22 重庆大学 Point-to-point ship sailing time estimation method based on ship route matching
CN104657538A (en) * 2015-01-04 2015-05-27 河海大学 Simulation method for scheduling multi-code channel
CN104882028A (en) * 2015-05-11 2015-09-02 长江泸州航道局 Ship traffic command method for dual control reach
CN112309173A (en) * 2020-11-02 2021-02-02 长江重庆航道局 Intelligent command supervision system for controlling navigation of ships in river reach

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115410417A (en) * 2022-07-20 2022-11-29 国能浙江北仑第一发电有限公司 Ship dispatching berthing prediction system based on environmental factors
CN115410417B (en) * 2022-07-20 2023-11-14 国能浙江北仑第一发电有限公司 Ship scheduling berthing prediction system based on environmental factors

Also Published As

Publication number Publication date
CN113095627B (en) 2024-03-12

Similar Documents

Publication Publication Date Title
US11914376B2 (en) USV formation path-following method based on deep reinforcement learning
Xiaofei et al. Global path planning algorithm based on double DQN for multi-tasks amphibious unmanned surface vehicle
Holzhüter LQG approach for the high-precision track control of ships
CN105302126A (en) Control method of autonomously descending and landing on warship of unmanned shipboard helicopter
CN115016496A (en) Water surface unmanned ship path tracking method based on deep reinforcement learning
CN111880546A (en) Virtual guide ship automatic berthing control method based on self-adaptive dynamic programming algorithm
CN113741449A (en) Multi-agent control method for air-sea cooperative observation task
CN112445847A (en) Ship track prediction method and device based on Beidou navigation time-frequency data
CN116306790B (en) Offshore ship track real-time prediction method, system, equipment and medium based on CNN-GRU and attention mechanism
CN113095627A (en) Irregular restricted area ship scheduling method
CN117311142A (en) DP ship motion control and thrust distribution cooperative control method integrating particle swarm optimization and neural network predictive control
CN111538349A (en) Long-range AUV autonomous decision-making method oriented to multiple tasks
CN105446136A (en) Ship course intelligence controller based on incomplete recursive branch-set dynamic neural network
CN114841635A (en) Ecological route planning method considering underwater radiated sound of ship
Zhou et al. Application of PSO-LSTM for forecasting of ship traffic flow
Huang et al. The USV path planning of Dueling DQN algorithm based on tree sampling mechanism
CN110175406A (en) Based on more ship following behavior analogy methods under the conditions of ship networking
CN116430856A (en) Ship track control method based on variable forward looking distance LOS algorithm
Sun et al. Predicting the Trajectory tracking control of unmanned surface vehicle based on deep learning
Fang et al. Evaluation Model of Ship Berthing Behavior Based on AIS Data
Rodriguez et al. Adaptive Learning and Optimization of High-Speed Sailing Maneuvers for America's Cup
Farbrother et al. Fuzzy self-organising control of a remotely operated submersible
Bejaoui et al. Novel model-based decision support system for reliable human machine systems in complex situations
Zhuo A Hybrid Intelligent Anti-disturbance Control Approach for Unmanned Surface Ship Autopilot
Huang et al. Unit-based trajectory planning methods for MASS in restricted waters

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