System and method for generating seafarers' awareness-based domain considering marine conditions in restricted area

The SASD system, utilizing ANFIS to incorporate human perception and maritime data, addresses the limitations of existing ship domain models by generating a dynamic domain for autonomous ships, improving collision avoidance in restricted areas by reflecting human intentions and conditions.

WO2024242229A1PCT designated stage expired Publication Date: 2024-11-28PUKYONG NAT UNIV IND ACADEMIC COOPERATION FOUND
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
PCT/KR2023/009137
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-22
Filing Date
2023-06-29
Publication Date
2024-11-28

AI Technical Summary

Technical Problem

Current ship domain models for autonomous navigation in restricted areas do not adequately consider human operators' intentions and maritime conditions, limiting their effectiveness in collision avoidance, especially in heavy traffic zones like the Singapore Strait.

Method used

A Seafarers' Awareness-Based Ship Domain (SASD) system using an Adaptive Neuro-Fuzzy Inference System (ANFIS) to generate a dynamic ship domain based on maritime situation data, including traffic volume, channel width, and weather, reflecting human perception and maritime conditions.

Benefits of technology

The system effectively creates a dynamic ship domain that considers human factors and maritime conditions, enhancing collision avoidance standards for autonomous ships in restricted areas by providing a more accurate and adaptive collision avoidance strategy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2023009137_28112024_PF_FP_ABST
    Figure KR2023009137_28112024_PF_FP_ABST
Patent Text Reader

Abstract

The present invention relates to a system and a method for generating a seafarers' awareness-based domain considering marine conditions in a restricted area and comprises: receiving a configured seafarers' awareness-based ship domain (SASD) as an input; inputting marine conditions data into an adaptive neuro-fuzzy inference system (ANFIS) to calculate ANFIS values (O 5 Mi , O 5 mi ) that are reflected in the major axis and minor axis of the SASD; and generating an SASD considering marine conditions in a restricted area by using the configured SASD, O 5 Mi , and O 5 mi .
Need to check novelty before this filing date? Find Prior Art

Description

System and method for creating a domain based on the perception of a sailor considering the maritime situation in a restricted area

[0001] The present invention relates to a system and method for generating a domain based on the awareness of seafarers considering the maritime situation of a restricted area, and in particular, by inputting a set SASD (Seafarers' Awareness-Based Ship Domain) and inputting maritime situation data into an ANFIS (Adaptive Neuro-Fuzzy Inference System), the ANFIS values ​​reflected in the major and minor axes of the SASD are generated. , ) and set SASD, and , The present invention relates to a system and method for generating a domain based on the perception of a sailor considering the maritime situation of a restricted area, by generating an SASD considering the maritime situation of a restricted area using the system.

[0002]

[0003] With the advent of the Fourth Industrial Revolution, the maritime industry is conducting research on Massive Aviation Systems (MASS). While research primarily focuses on developing practical algorithms for fully automated MASS, several large vessels have been operated by AI technology to date, with most remaining under human control. This is because MASS technology is not fully validated, and there are limitations to overcome, such as revisions to MASS-related regulations. Notably, MASS did not navigate restricted waterways with high maritime traffic volumes, such as the Singapore Strait. In other words, with current technology, humans are more widely proven than AI as a means of navigating large vessels. Ongoing research on ship collision risks has reduced the frequency of such accidents, although they still occur. Ship collisions can lead to sinkings, oil spills, fires, and loss of life, and research on preventing them is crucial. Therefore, research is ongoing to improve MASS. To reduce ship collisions, various approaches have been studied to assess collision risk between own ship (OS) and target ship (TS). Some researchers have conducted scientific analyses using the closest approach point and the bow crossing range of the two ships, while others have applied and diagrammed the general concept of the ship domain.

[0004] Therefore, the need to propose collision avoidance criteria for MASS using the ship domain has led to the development of various research methods and several ship domain models since the ship domain was first proposed. The ship domain is utilized for maritime safety, assessing collision risks between ships and assessing the suitability of sea lanes. As the ship domain can serve as a criterion for determining MASS avoidance behavior, its importance is likely to increase as follows:

[0005] When MASS avoids a TS, a decision criterion is needed. Collision assessment can be performed in terms of distance and time between two ships. A representative method for ship collision assessment based on distance factors is the ship domain. The ship domain is created as a safe zone around the OS based on a safe distance. Therefore, the OS takes necessary measures to prevent itself from entering the TS domain. Collision avoidance research in MASS is generally based on the ship domain. Therefore, the design of the ship domain can influence the collision avoidance behavior of MASS.

[0006] Recently, some AI models have learned human behavior and subsequently surpassed human performance (e.g., AlphaGo). Therefore, while these types of ship domain models are rare, ship domain research should also propose models that learn human behavior. Ship domain models presented to date can be categorized as follows based on research methods:

[0007] The first model is a statistical vessel domain based on vessel navigation data. The statistical model was based on radar-based vessel navigation data. Later, a statistical vessel domain was proposed based on vessel navigation data using the Automatic Identification System (AIS). However, this model has a drawback: because it relies on vessel traffic within a specific area, the AIS-based vessel domain model may be difficult to apply to other specific areas. Furthermore, AIS data may include situations that were either intended or unintended by the OS. For example, while the OS intended to maintain a distance of 1 nautical mile (NM) from the TS, the data may include instances where the OS navigated at a distance of 0.5 NM due to traffic in the restricted area.

[0008] Second, a mathematical ship domain model based on the ship's parameters and maneuverability was proposed. The proposed model differs from existing domains by being divided into a blocking zone and a surveillance zone. Engineering calculations were used as the basis for these models. However, the proposed mathematical model fails to reflect the sea conditions of a navigating ship.

[0009] Third, there is an AI model. An AI-based domain model using fuzzy logic has been proposed. In this model, the size of the ship domain dynamically changes based on a collision risk assessment using fuzzy logic. However, the proposed fuzzy domain has limitations in that it does not consider human factors and maritime conditions.

[0010] However, the ship domain model mentioned above had a problem in that it did not directly reflect the ship operator's intention.

[0011]

[0012] [Prior Art Literature]

[0013] [Patent Document]

[0014] (Patent Document 1) Korean Patent No. 10-2439261 (Title of the Invention: Method for Calculating Turning Time to Prevent Collision Due to Control Delay in Remote Control of Autonomous Ship)

[0015]

[0016] Accordingly, the present invention has been made to solve the above problems, and the purpose of the present invention is to provide a system and method for generating a ship domain based on the sea conditions of a restricted area and the seamen's perceived values ​​in order to suggest collision avoidance criteria for autonomous ships in a restricted area, and a system and method for generating a domain based on the seamen's perceived values ​​in consideration of the sea conditions of a restricted area.

[0017]

[0018] In order to achieve the above purpose, the system for generating a domain based on the awareness of seafarers considering the maritime situation of a restricted area according to one embodiment of the present invention is configured to input a SASD (Seafarers' Awareness-Based Ship Domain), a SASD input unit configured to input a set SASD (Seafarers' Awareness-Based Ship Domain), and input maritime situation data into an ANFIS (Adaptive Neuro-Fuzzy Inference System) to generate ANFIS values ​​reflected in the major and minor axes of the SASD, respectively. , ) ANFIS result generation unit configured to produce; and the SASD and , It is characterized by including a restricted area maritime situation-considering SASD generation unit configured to generate a SASD considering the restricted area maritime situation using;

[0019] The system for generating a domain based on the recognition of a sailor considering the maritime situation of a restricted area according to the above embodiment may further include a display unit configured to display the SASD considering the maritime situation of the restricted area.

[0020] In the domain generation system based on the recognition of a sailor considering the maritime situation of a restricted area according to the above embodiment, the maritime situation data input to the ANFID result generating unit may be the amount of traffic around the own ship, the channel width of the restricted area, and the weather data of the restricted area.

[0021] In the domain generation system based on the recognition of a sailor that takes into account the maritime situation of a restricted area according to the above embodiment, the SASD that takes into account the maritime situation of a restricted area generated by the SASD generation unit that takes into account the maritime situation of a restricted area can be defined by the following [Mathematical Formula 4].

[0022]

[0023] [Equation 4]

[0024]

[0025]

[0026] [Here, SASD M and SASD m are the major and minor axes of SASD, respectively. is the closest point of contact in the crossing situation between the charity and target ships, is the closest point of contact in the overtaking situation of the charity and target ships, and DA M is the major axis of the ellipse, and DA m is the shorthand value of the ellipse, , are the ANFIS values ​​reflected in the major and minor axes of SASD, respectively]

[0027]

[0028] In the domain creation system based on the recognition of the sailor considering the maritime situation of the restricted area according to the above embodiment, , can be defined by the following [Mathematical Formula 3].

[0029]

[0030] [Equation 3]

[0031]

[0032]

[0033] [Here, is the input variable width of the restricted area, represents the input variable volume of traffic, represents input variables including the size of the opposing vessel, the currents in the sea area, and the group of fishing vessels around the own ship]

[0034]

[0035] In order to achieve the above purpose, a method for generating a seafarer's awareness-based domain considering the maritime situation of a restricted area according to another embodiment of the present invention comprises the steps of: receiving a SASD (Seafarers' Awareness-Based Ship Domain) with a SASD input unit set; and generating an ANFIS result output unit by inputting maritime situation data into an ANFIS (Adaptive Neuro-Fuzzy Inference System) to generate ANFIS values ​​(reflected in the major and minor axes of the SASD, respectively). , ) generating step; and a SASD generating unit considering the restricted area maritime situation, the SASD and , It is characterized by including a step of generating a SASD considering the restricted area maritime situation using;

[0036] The method for generating a domain based on the recognition of a sailor considering the maritime situation of a restricted area according to the above-described other embodiment may further include a step of displaying an SASD considering the maritime situation of the restricted area generated through a display unit.

[0037]

[0038] According to the system and method for generating a domain based on the awareness of seafarers considering the maritime situation of a restricted area according to an embodiment of the present invention, a set SASD (Seafarers' Awareness-Based Ship Domain) is input, maritime situation data is input into the ANFIS (Adaptive Neuro-Fuzzy Inference System), and the ANFIS values ​​reflected in the major and minor axes of the SASD are respectively , ) and calculate the SASD and , By configuring it to generate a SASD that takes into account the maritime situation of the restricted area, it has the outstanding effect of being able to generate a ship domain based on the maritime situation of the restricted area and the perceived value of the crew in order to suggest collision avoidance criteria for autonomous ships in the restricted area.

[0039]

[0040] Figure 1 is a block diagram of a domain generation system based on the recognition of a sailor that takes into account the maritime situation of a restricted area according to an embodiment of the present invention.

[0041] FIG. 2 is a flowchart for explaining a method for creating a domain based on a sailor's perception that takes into account the maritime situation of a restricted area according to an embodiment of the present invention.

[0042] Figure 3 is a drawing showing the set SASD input into the SASD input section of Figure 1.

[0043] Figure 4 is a structural diagram of ANFIS used in the ANFIS result production section of Figure 1.

[0044] Figure 5 is a drawing showing SASD considering the restricted area maritime situation displayed in the display unit of Figure 1.

[0045]

[0046] In describing embodiments of the present invention, if a detailed description of a known technology related to the present invention is judged to unnecessarily obscure the gist of the present invention, the detailed description will be omitted. In addition, the terms described below are terms defined in consideration of their functions in the present invention, and this may vary depending on the intention or custom of the user or operator. Therefore, the definitions should be made based on the contents throughout this specification. The terms used in the detailed description are only for the purpose of describing embodiments of the present invention and should never be construed as limiting. Unless clearly used otherwise, the singular form includes the plural form. In this description, expressions such as "comprises" or "having" are intended to indicate certain features, numbers, steps, operations, elements, parts or combinations thereof, and should not be construed to exclude the presence or possibility of one or more other features, numbers, steps, operations, elements, parts or combinations thereof other than those described.

[0047] In each system depicted in the drawings, elements may in some cases have the same reference number or different reference numbers, indicating that the depicted elements may be different or similar. However, the elements may operate with any or all of the systems shown or described herein, with different implementations. Various elements depicted in the drawings may be the same or different. Which one is referred to as a first element and which one as a second element is arbitrary.

[0048] In this specification, the phrase “transmitting,” “delivering,” or “providing” data or a signal from one component to another component includes not only the component directly transmitting the data or signal to another component, but also the component transmitting the data or signal to another component via at least one other component.

[0049]

[0050] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0051]

[0052] Figure 1 is a block diagram of a domain generation system based on the recognition of a sailor that takes into account the maritime situation of a restricted area according to an embodiment of the present invention.

[0053]

[0054] The system for generating a domain based on the recognition of a sailor considering the maritime situation of a restricted area according to an embodiment of the present invention includes, as illustrated in FIG. 1, an SASD input unit (100), an ANFIS result output unit (110), a SASD generation unit considering the maritime situation of a restricted area (200), and a display unit (300).

[0055]

[0056] The SASD input unit (100) serves to receive the set SASD (Seafarers' Awareness-Based Ship Domain).

[0057] Figure 3 is a drawing showing the set SASD input into the SASD input section of Figure 1.

[0058] The set SASD is displayed as an ellipse, DA M and DA m are the major and minor axes of the ellipse (SASD), respectively. The perceived value of the seafarers was obtained as the nearest point of contact (DCPA) value through interviews with seafarers of different ranks (e.g., 123 seafarers). The perceived value of the seafarers was obtained as the DCPA threshold (DCPA TV ) is expressed as DCPA( in the crossing situation of the charity and target vessel) and the major axis of the presented domain is ) and the abbreviation is DCPA( in the frontal situation of charity and target vessel) ) is rare in a head-on situation between two ships in a restricted area, but the model is designed to shorten the domain for safety. ) value was applied. However, since overtaking occurs more frequently in the restricted area, DCPA( in overtaking situations) ) is expressed as a shortened form of the ellipse.

[0059] To summarize, the configuration of this model is reflected in [Mathematical Formula 1] and [Mathematical Formula 2] below.

[0060]

[0061] [Mathematical Formula 1]

[0062]

[0063]

[0064] [Equation 2]

[0065]

[0066]

[0067] [SASD M Wow SASD m represent the major and minor axes of the ellipse, respectively, and S i is the rank of the crew, such as captain, first mate, petty officer, and third mate, L is the average ship length (240 m), i is the crew group, and j is the person in the ith group. is the jth person in the ith group. lim]

[0068]

[0069] The ANFIS result generation unit (110) inputs maritime situation data (e.g., traffic volume around the own ship, channel width of the restricted area, and weather data of the restricted area) into the ANFIS (Adaptive Neuro-Fuzzy Inference System) to generate ANFIS values ​​(reflected on the major and minor axes of the SASD, respectively). , ) plays a role in producing it.

[0070] ANFIS is the most popular neuro-fuzzy system and an AI technology. ANFIS combines an artificial neural network (ANN) and fuzzy logic (capable of making decisions in ambiguous situations). ANNs can process unstructured knowledge numerically, while fuzzy systems can represent structured knowledge in numerical terms. Therefore, integrating ANNs and fuzzy logic is essential to increasing the efficiency of AI.

[0071] ANFIS possesses the most ideal structure for problem solving through learning using ANNs. However, ANN's biggest drawback is its inability to explain weight values. ANFIS overcomes this shortcoming by using fuzzy inference. The structure of ANFIS is illustrated in Figure 4.

[0072] The ANFIS values ​​reflected in the major and minor axes of the SASD are calculated by inputting maritime situation data (e.g., traffic volume around the vessel, channel width in the restricted area, and meteorological data in the restricted area) into the ANFIS. , ) is defined by the following [Mathematical Formula 3].

[0073]

[0074] [Equation 3]

[0075]

[0076] [Here, is the input variable width of the restricted area, represents the input variable volume of traffic, represents input variables including the size of the opposing vessel, the currents in the sea area, and the group of fishing vessels around the own ship]

[0077]

[0078] The SASD generation unit (200) considering the restricted area maritime situation generates the SASD inputted into the SASD input unit (100) and the ANFIS result generation unit (110). , It plays a role in creating SASD that takes into account the restricted area maritime situation.

[0079] The SASD considering the maritime situation of the generated restricted area is defined by the following [Mathematical Formula 4].

[0080]

[0081] [Equation 4]

[0082]

[0083] [Here, SASD M and SASD m are the major and minor axes of SASD, respectively. is the closest point of contact in the crossing situation between the charity and target ships, is the closest point of contact in the overtaking situation of the charity and target ships, and DA M is the major axis of the ellipse, and DA m is the shorthand value of the ellipse, , are the ANFIS values ​​reflected in the major and minor axes of SASD, respectively]

[0084]

[0085] The display unit (300) serves to display the SASD considering the restricted area maritime situation generated by the restricted area maritime situation-considering SASD generation unit (200).

[0086]

[0087] Figure 5 is a drawing showing SASD considering the restricted area maritime situation displayed in the display unit of Figure 1.

[0088] The SASD considering the restricted area maritime situation generated by the SASD generation unit (200) can be expressed as a dynamic domain indicating a maximum and minimum size, as illustrated in Fig. 5. The size of this dynamic domain changes depending on maritime situation data such as the amount of traffic around the ship, the channel width of the restricted area, and weather data of the restricted area.

[0089] In Fig. 5, the horizontal and vertical axes are expressed as dimensionless values ​​based on the set SASD entered into the SASD input section, with the X and Y axes divided by the average length of the ship (240 m). The solid ellipse represents the largest SASD, and the dotted ellipse represents the smallest SASD. At maximum size, the major axis is 8.1 L and the minor axis is 3.5 L. In the dotted ellipse, the major axis is 5.2 L and the minor axis is 2.7 L.

[0090]

[0091] Hereinafter, a domain creation method using a domain creation system based on the recognition of a sailor that takes into account the maritime situation of a restricted area according to an embodiment of the present invention configured as described above will be described.

[0092] FIG. 2 is a flowchart for explaining a method for creating a domain based on the recognition of a sailor considering the maritime situation of a restricted area according to an embodiment of the present invention, where S represents a step.

[0093]

[0094] First, the SASD input unit (100) receives the set SASD (Seafarers' Awareness-Based Ship Domain) (S10).

[0095]

[0096] Next, the ANFIS result generation unit (110) inputs maritime situation data (amount of traffic around the ship, channel width of the restricted area, and weather data of the restricted area) into the ANFIS (Adaptive Neuro-Fuzzy Inference System) shown in Fig. 4 to generate ANFIS values ​​reflected in the major and minor axes of the SASD, respectively. , ) is produced (S20).

[0097]

[0098] Next, the SASD generation unit (200) considering the restricted area maritime situation generates the SASD set in step (S10) and the SASD calculated in step (S20). , SASD is created by considering the restricted area maritime situation using (S30).

[0099]

[0100] Next, the SASD generation unit (200) considering the restricted area maritime situation inputs a display control signal to the display unit (300) to display the SASD considering the restricted area maritime situation generated through the display unit (300) (S40).

[0101]

[0102] According to the system and method for generating a domain based on the awareness of seafarers considering the maritime situation of a restricted area according to the embodiment of the present invention configured as described above, the set SASD (Seafarers' Awareness-Based Ship Domain) is input, and the maritime situation data is input into the ANFIS (Adaptive Neuro-Fuzzy Inference System) to generate the ANFIS values ​​reflected in the major and minor axes of the SASD, respectively. , ) and calculate the SASD and , By configuring to generate SASD considering restricted area maritime conditions, a ship domain based on restricted area maritime conditions and crew perception values ​​can be generated to suggest collision avoidance criteria for autonomous ships in restricted areas.

[0103]

[0104] The drawings and specification disclose optimal embodiments, and while specific terminology may be used, it is solely for the purpose of describing embodiments of the present invention and is not intended to limit the meaning or scope of the invention as defined in the claims. Therefore, those skilled in the art will appreciate that various modifications and equivalent embodiments are possible. Therefore, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

Claims

1. A domain creation system based on the perception of sailors that takes into account the maritime situation in restricted areas. SASD input port configured to receive an established SASD (Seafarers' Awareness-Based Ship Domain) input; By inputting maritime situation data into ANFIS (Adaptive Neuro-Fuzzy Inference System), ANFIS values ​​are reflected on the major and minor axes of SASD respectively. , ) ANFIS result generation unit configured to produce; and The above set SASD and , A system for generating a domain based on the perception of a sailor, comprising: a restricted area maritime situation-considering SASD generation unit configured to generate a SASD considering the restricted area maritime situation; 2. In paragraph 1, A system for generating a domain based on a mariner's perception, further comprising a display unit configured to display a SASD considering the generated restricted area maritime situation.

3. In paragraph 1, The sea condition data input into the above ANFID result generation unit is a domain generation system based on the perception of the crew, which is the amount of traffic around the ship, the channel width of the restricted area, and the weather data of the restricted area.

4. In paragraph 1, The SASD generated by the SASD generation unit considering the restricted area maritime situation above is a domain generation system based on the perception of the sailor, which is defined by the following [Mathematical Formula 4]. [Mathematical formula 4] [Here, SASD M and SASD m are the major and minor axes of SASD, respectively. is the closest point of contact between the charity and target ships in a crossing situation, is the closest point of contact in the overtaking situation of the charity and target ships, and DA M is the major axis of the ellipse, and DA m is the shorthand value of the ellipse, , are ANFIS values ​​reflected in the major and minor axes of SASD, respectively] 5. In paragraph 4, Above , is a domain generation system based on the perception of a sailor, which is defined by the following [Mathematical Formula 3]. [Mathematical Formula 3] [Here, is the input variable width of the restricted area, represents the input variable volume of traffic, represents input variables including the size of the opposing vessel, the current in the sea area, and the group of fishing vessels around the ship.] 6. A method for creating a domain based on the recognition of a sailor that takes into account the maritime situation of a restricted area using the domain creation system based on the recognition of a sailor described in Article 1, Step for receiving SASD (Seafarers' Awareness-Based Ship Domain) with SASD input section set up; The ANFIS result output unit inputs maritime situation data into the ANFIS (Adaptive Neuro-Fuzzy Inference System) and produces ANFIS values ​​reflected on the major and minor axes of the SASD, respectively. , ) for producing a step; and Considering the restricted area maritime situation, the SASD generation unit sets the SASD and , A method for generating a domain based on the perception of a sailor, comprising: a step of generating a SASD that takes into account the restricted area maritime situation using a method.

7. In paragraph 6, A method for generating a domain based on a sailor's perception, further comprising the step of displaying a SASD that takes into account the restricted area maritime situation generated through a display unit.

Citation Information

Patent Citations

  • Nanoparticle for polymerase chain reaction

    KR1020230148789A

  • Turning time calculation method to prevent collision due to control delay in remote control of autonomous ship

    KR102439261B1

  • A system for operating an unmanned surface vehicle and an operation method therefor

    KR102530977B1

  • Vessel collision avoiding method and system based on artificial potential field

    US20210295708A1