Optimal fault-tolerant control method and system for robust path tracking of coastal tugboat

Abstract

The invention relates to an optimal fault-tolerant control method and system for coastal tugboat robust path tracking. The method comprises the steps of establishing three-degree-of-freedom tugboat kinematics and dynamics equations, constructing an error system which considers external ocean disturbance and internal propeller faults at the same time according to information of a reference trajectory, constructing a proper discount performance function in combination with the error system, and calculating the discount performance of the tugboat according to the discount performance function. Wherein the discount performance function comprises estimation for external ocean disturbance and internal thruster faults, and an optimal solution of the discount performance function is obtained through de-iterative optimization of an action home-approval home neural network based on an adaptive dynamic programming method. According to the method, tugboat path tracking control under the multi-constraint condition can be overcome, and the parameter setting process is simplified.

Description

Technical Field

[0001] The invention relates to an optimal fault-tolerant control method and system for robust path tracking of a nearshore tugboat, and belongs to the field of intelligent control. Background Art

[0002] In recent years, classification societies around the world have been advocating the development of "smart ships" to improve the efficiency and safety of maritime operations. Among various types of ships, tugboats are particularly important in facilitating the connection between cargo ships, offshore platforms and ports. Among them, tugboats are the first choice for "smart ships" because of their strong maneuverability, high power, small size and wide range of applications. However, the development of autonomous control systems for tugboats in nearshore environments still faces two challenges. First, the external ocean disturbances in the nearshore environment - wind, waves and currents are very complex. Although some models have been proposed to describe these disturbances, it is still challenging to achieve accurate real-time observations. In addition, tugboats may have internal thruster failures, which may seriously affect their operational capabilities. In order to keep the tugboat stable and accurately tracking the path, it is very necessary to design a suitable robust fault-tolerant control method. In addition, marine experiments are high in human and material resources, and the complexity of the parameter tuning process of the control algorithm further increases the deployment performance of smart ships. Therefore, it is also very necessary to design a method to simplify the parameter tuning process.

[0003] At present, control methods based on backstepping frameworks are usually used for robust path tracking of systems under disturbance and fault environments, and in recent years, adaptive dynamic programming methods have also been used for robust path tracking under ocean disturbances. The former is relatively mature and has a simple framework form, but the characteristics of its framework inevitably lead to the accumulation of disturbance estimation errors. The adaptive dynamic programming method can avoid the problem of interference estimation error accumulation, but there is currently no adaptive dynamic programming method that can handle both ocean disturbances and thruster failures at the same time.

[0004] The existing ship path tracking control method, for underactuated cargo ships, can reduce the amount of calculation and improve the performance and control accuracy by adopting PID control, Euler discretization, and the ability to handle constraints based on regression variables and linear regression, and by the model predictive control law when applying model predictive control to nonlinear system models. In addition, the existing integrated ship path tracking and rudder anti-roll control method based on neural network optimization has the following advantages: (1) The output of ship path tracking is converted into tracking error and heading angle error through the line of sight guidance method, reducing the dimension of control output, and designing the controller based on the model predictive control algorithm; (2) The terminal cost function is introduced into the objective function of the model predictive control to ensure closed-loop stability; (3) In the neural dynamic optimization module, the parallel computing architecture of the recursive neural network is used for rapid solution, so that the ship can respond to the changing environment more quickly when sailing.

[0005] However, although the methods used in the above prior art take into account the disturbance phenomenon existing in the environment, they do not pay attention to the damage of the marine environment to the ship's propeller. Under frequent marine missions, the ship's propeller will inevitably be damaged, resulting in failures. External ocean disturbances and internal propeller failures are key factors affecting the accuracy of the path following of the autonomous tugboat and the stability and safety of the tugboat's hull during marine operations. Therefore, the path tracking method designed for the autonomous tugboat needs to consider the impact of disturbances and failures at the same time (more constraints), and it is necessary to simplify the parameter setting process as much as possible to reduce the sea trial performance, which increases the difficulty of method design. Summary of the invention

[0006] The present invention provides an optimal fault-tolerant control method and system for robust path tracking of a nearshore tugboat, aiming to solve at least one of the technical problems existing in the prior art.

[0007] The technical solution of the present invention relates to an optimal fault-tolerant control method for robust path tracking of a nearshore tugboat. The method according to the present invention comprises the following steps:

[0008] S100. Establish the kinematic and dynamic equations of the tugboat with three degrees of freedom;

[0009] S200, constructing an error system that simultaneously considers external ocean disturbances and internal thruster failures based on information of the reference trajectory;

[0010] S300, constructing a suitable discounted performance function in combination with the error system, wherein the discounted performance function includes estimates for external ocean disturbances and internal thruster failures;

[0011] S400, based on the adaptive dynamic programming method, uses the actor-critic neural network to iteratively optimize and obtain the optimal solution of the discounted performance function.

[0012] Further, in step S100:

[0013] The three-degree-of-freedom kinematic and dynamic model of the tugboat is expressed in the following equations:

[0014]

[0015] Where t represents the time of the system, η(t)=[x(t),y(t),φ(t)] T Represents position (x(t), y(t)) and heading φ(t), v(t) = [u(t), v(t), r(t)] T represents the velocity variables, including swell u(t), roll v(t) and yaw r(t); G represents the coordinate transformation matrix; represents the mass (inertia) matrix; represents the Coriolis centripetal force matrix; D represents the damping matrix; τ′(t) represents the force acting on the tugboat; τ l represents the external ocean disturbance including wind, waves and currents; τ′ represents the force applied after the failure of the tugboat propulsion system, where τ′=τ-τ f , where τ=[τ u ,τ v ,τ r ] T represents the force applied by the thruster, τ f Indicates the loss of force due to thruster failure.

[0016] Further, in step S200:

[0017] The reference kinematic and dynamic models are expressed as follows:

[0018]

[0019] In the formula, represents the position and heading of the reference system, G d represents the coordinate transformation matrix of the reference system, v d represents the velocity variable of the reference system, τ d represents the thrust acting on the reference system;

[0020] According to the three-degree-of-freedom kinematic and dynamic models of the tugboat, and according to the reference kinematic and dynamic models, the constructed error system is expressed as follows:

[0021] e η =η-η d

[0022] e v =vv d

[0023] e τ =τ-τ d

[0024] In which, define z = [e η ,e v ] T , z represents the matrix error; where e η represents the position and heading error, e v represents the speed error, e τ Indicates the error in the acting thrust;.

[0025] Further, in step S300:

[0026] Based on the error system, the constructed discounted performance function is expressed as follows:

[0027]

[0028] In the formula, e represents the natural base, τ f and τ l They are τ f and τ l The estimated value of ; σ1 and σ2 are both positive constants; U(z,e τ ) represents the objective function of optimization, Q and P are both positive symmetric matrices; γ is the discount factor, and 0≤γ≤1; e τ represents the optimal control input.

[0029] Further, in step S300:

[0030] The Hamilton-Jacobi-Bellman equation obtained according to the discounted performance function is expressed as follows:

[0031]

[0032] In the formula, express The partial derivative with respect to z is f(z) represents the matrixed error system variable function; α(z) represents the matrixed error system coefficient;

[0033] And according to the optimal performance function of the system, it is expressed as follows:

[0034]

[0035] Obtain the optimal control input for the system It is expressed as follows:

[0036]

[0037] In the formula, express The partial derivative with respect to z is The difference t-δ represents the offset time.

[0038] Further, in step S300:

[0039] The optimal solution of the optimal control input of the system is obtained by continuous approximation through an iterative strategy algorithm, which includes the following steps:

[0040] S310, Strategy Evaluation: It is known that Updated by the following equation:

[0041]

[0042] In the formula, j represents the jth step; represents the input of step j; Represents the initial input; represents the performance function of the jth step;

[0043] S320, Strategy Improvement: pass To update;

[0044] S330, policy termination: To obtain the optimal control input In the formula is any given normal number.

[0045] Further, in step S400:

[0046] The actor-critic neural network is represented as follows:

[0047]

[0048] in s c ,∈ c denote the weight vector, activation function and approximation error of the critic neural network respectively;

[0049] Calculate the partial derivative of F1(z,τ) with respect to z:

[0050]

[0051] in

[0052] Furthermore, the weight update rate of the actor-critic neural network and It is expressed as follows:

[0053]

[0054] In the formula, σ5 represents the learning rate, as the residual of the neural network approximation, and

[0055]

[0056] In the formula, σ6 represents the learning rate;

[0057] Among them, the control signal e τ Approximately:

[0058]

[0059] Then construct the following variables:

[0060]

[0061] In the formula, s a ,∈ a denote the weight vector, activation function and approximation error of the actor neural network respectively;

[0062] The optimal control signal is obtained by continuously updating the control signal e τ get.

[0063] The technical solution of the present invention also relates to a computer-readable storage medium on which program instructions are stored, and the above-mentioned method is implemented when the program instructions are executed by a processor.

[0064] The technical solution of the present invention also relates to an optimal fault-tolerant control system for robust path tracking of near-shore tugboats, wherein the system comprises a computer device, and the computer device comprises the above-mentioned computer-readable storage medium.

[0065] The beneficial effects of the present invention are as follows:

[0066] The optimal fault-tolerant control method for robust path tracking of nearshore tugboats of the present invention can overcome the tugboat path tracking control under multiple constraints and simplify the parameter setting process. It transforms the tugboat robust path tracking problem into an optimal fault-tolerant control problem, and by uniformly considering external ocean disturbances and internal propeller failures, it avoids the accumulation of estimation errors, realizes disturbance suppression, and ensures the stability and accuracy of path tracking. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 Schematic diagram of an application scenario of the method according to the present invention.

[0068] Figure 2 is a basic flow chart of the method according to the present invention. DETAILED DESCRIPTION

[0069] The concept, specific structure and technical effects of the present invention will be clearly and completely described below in combination with the embodiments and drawings to fully understand the purpose, scheme and effect of the present invention.

[0070] It should be noted that, unless otherwise specified, when a feature is referred to as being "fixed" or "connected" to another feature, it may be directly fixed or connected to another feature, or it may be indirectly fixed or connected to another feature. The singular forms of "," "said" and "the" used herein are also intended to include the plural forms, unless the context clearly indicates otherwise. In addition, unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art. The terms used in this specification are intended to describe specific embodiments only and are not intended to limit the invention. The term "and / or" used herein includes any combination of one or more of the related listed items.

[0071] It should be understood that, although the term first, second, third etc. may be adopted to describe various elements in the present disclosure, these elements should not be limited to these terms. These terms are only used to distinguish the same type of elements from each other. For example, without departing from the scope of the present disclosure, the first element may also be referred to as the second element, and similarly, the second element may also be referred to as the first element. The use of any and all examples or exemplary language ("for example", "such as" etc.) provided herein is only intended to better illustrate embodiments of the present invention, and unless otherwise required, the scope of the present invention will not be limited.

[0072] Reference Figure 1 to Figure 2 In some embodiments, the optimal fault-tolerant control method for robust path tracking of a nearshore tugboat according to the present invention comprises at least the following steps:

[0073] S100. Establish the kinematic and dynamic equations of the tugboat with three degrees of freedom;

[0074] S200, constructing an error system that simultaneously considers external ocean disturbances and internal thruster failures based on information of the reference trajectory;

[0075] S300, combining the error system to construct a suitable discounted performance function, which includes estimates of external ocean disturbances and internal thruster failures;

[0076] S400, based on the adaptive dynamic programming method, uses the actor-critic neural network to iteratively optimize and obtain the optimal solution of the discounted performance function.

[0077] The optimal fault-tolerant control method for robust path tracking of nearshore tugboats of the present invention can overcome the tugboat path tracking control under multiple constraints and simplify the parameter setting process. It transforms the tugboat robust path tracking problem into an optimal fault-tolerant control problem, and by uniformly considering external ocean disturbances and internal propeller failures, it avoids the accumulation of estimation errors, realizes disturbance suppression, and ensures the stability and accuracy of path tracking.

[0078] Specific implementation of step S100

[0079] The present invention establishes the three-degree-of-freedom kinematics and dynamics equations of the tugboat based on the world Cartesian coordinate system and the coordinate system of the tugboat itself. Specifically, the three-degree-of-freedom kinematics and dynamics model of the tugboat is expressed as follows:

[0080]

[0081] Where t represents the time of the system, η(t)=[x(t),y(t),φ(t)] T represents the position (x(t), y(t)) and heading φ(t) (see Figure 1 ), v(t)=[u(t),v(t),r(t)] T represents the velocity variables, including swell u(t), roll v(t) and yaw r(t); G represents the coordinate transformation matrix; represents the mass (inertia) matrix; represents the Coriolis centripetal force matrix; D represents the damping matrix; τ′(t) refers to the force acting on the tugboat; τ l is the external ocean disturbance including wind, waves and currents; τ′ is actually the force applied after the tugboat propulsion system fails, specifically expressed as τ′=τ-τ f , where τ=[τ u ,τ v ,τ r ] T is the force applied by the thruster, τ f It is the loss of force due to thruster failure.

[0082] Specific implementation of step S200

[0083] The present invention constructs an error system that takes into account both external ocean disturbances and internal propeller failures based on the information of the reference trajectory. Specifically, the reference kinematic and dynamic models are expressed as follows:

[0084]

[0085] In the formula, represents the position and heading of the reference system, Gd represents the coordinate transformation matrix of the reference system, v d represents the velocity variable of the reference system, τ d represents the thrust acting on the reference system;

[0086] Then, the error system is constructed according to formulas (1) and (2):

[0087] e η =η-η d

[0088] e v =vv d

[0089] e τ =τ-τ d (3)

[0090] Then define z = [e η ,e v ] T , where z represents the matrix error; where e η represents the position and heading error, e v represents the speed error, e τ It is understood that the error system (3) designed by the present invention includes the ocean disturbance and propeller failure mentioned in the system (1).

[0091] Specific implementation of step S300

[0092] Based on the error system formula (3) designed in step S200, a discount performance function of the following form is constructed:

[0093]

[0094] In the formula, e represents the natural base, τ f and τ l They are τ f and τ l The estimated value of ; σ1 and σ2 are both positive constants; U(z,e τ ) represents the objective function of optimization, Q and P are both positive symmetric matrices; γ is the discount factor, and 0≤γ≤1.

[0095] Among them, the optimal control input It can be obtained by minimizing formula (4), where Φ(Ω) is an admissible set of control inputs.

[0096] According to equation (4), the Hamilton-Jacobi-Bellman equation can be designed as:

[0097]

[0098] In the formula, yes The partial derivative with respect to z is thus f(z) represents the matrixed error system variable function; α(z) represents the matrixed error system coefficient;

[0099] Then, the optimal performance function is defined as:

[0100]

[0101] Where t-δ represents the offset time.

[0102] According to equations (5) and (6), the optimal control input e τ Must meet:

[0103]

[0104] in

[0105] According to the above, the optimal control input Calculated as:

[0106]

[0107] In order to obtain the optimal solution of formula (6), the following iterative strategy algorithm can be used for continuous approximation:

[0108] 1. Strategy evaluation: It is known that Updated by the following equation:

[0109]

[0110] In the formula, j represents the jth step; represents the input of step j; Represents the initial input; represents the performance function of the jth step;

[0111] 2. Strategy Improvement: pass to update.

[0112] 3. Strategy termination: Finally, when Optimal control input We can get, where is any given normal number.

[0113] Specific implementation of step S400

[0114] However, it is actually very difficult to solve equation (8) by equation (7) because the steps are complicated and the calculation of partial derivatives is also complex. Therefore, the present invention adopts adaptive dynamic programming to solve equation (8).

[0115] Based on the powerful approximation ability of neural networks, external ocean disturbances and internal thruster failures can be approximated as and In the formula and s denote the weight vector and activation function, respectively, ∈ denotes the approximation error, where the subscripts l and f denote external ocean disturbances and internal thruster failures, respectively.

[0116] Based on the above approximation results, the derivative calculation of z is expressed as follows:

[0117]

[0118] in,

[0119] f(z)=[G(e η +η d )(e v +v d )-G(η d )v d -e τ +τ l ,-M -1 C(e v +v d ) v

[0120] -M -1 D(e v +v d ) v -τ f )-M -1 D(e v +v d ) v -τ f )

[0121] -M -1 [C(e v +v d )-C(v d )]v d -M -1 [D(e v +v d )-D(v d )]v d ] T ;

[0122] Where M represents the mass (inertia) matrix.

[0123] Then define As an estimated value of z, based on formula (9), The derivative of can be obtained as:

[0124]

[0125] in, and yes and The estimated value of Represents the constant matrix that needs to be designed.

[0126] definition e z represents the estimated error of the matrix error, then and The derivative of can be calculated as:

[0127]

[0128] Among them, σ3 and σ4 are both positive constants.

[0129] Then design the Lyapunov function as:

[0130]

[0131] Taking the derivative of equation (12) and based on the Lyapunov stability criterion, we can obtain is bounded.

[0132] The present invention adopts an actor-critic neural network. Specifically, the following function is defined:

[0133]

[0134] in s c ,∈ c The definitions of are the same as above, representing the weight vector, activation function, and approximation error of the critic neural network respectively.

[0135] Calculate the partial derivative of F1(z,τ) with respect to z:

[0136]

[0137] in

[0138] definition As the residual of the neural network approximation, Estimated value of It is expressed as follows:

[0139]

[0140] Where σ5 is the learning rate,

[0141] Similarly, the control signal e τ can be approximated as:

[0142]

[0143] Next, construct the following variables:

[0144]

[0145] Finally, we can get the weight update rate of the agent-critic network:

[0146]

[0147] In the formula, σ6 represents the learning rate; s a ,∈ a denote the weight vector, activation function, and approximation error of the actor neural network, respectively.

[0148] Among them, formula (15) and formula (18) are the weight update rates of the actor-critic network designed by the present invention: and The optimal control signal can be obtained by continuously updating equation (16).

[0149] It should be appreciated that the method steps in the embodiments of the present invention can be implemented or implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The method can use standard programming techniques. Each program can be implemented in a high-level process or object-oriented programming language to communicate with a computer system. However, if necessary, the program can be implemented in an assembly or machine language. In any case, the language can be a compiled or interpreted language. In addition, the program can be run on a programmed ASIC for this purpose.

[0150] Furthermore, the operations of the processes described herein may be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and / or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed collectively on one or more processors, by hardware, or a combination thereof. The computer program includes a plurality of instructions that may be executed by one or more processors.

[0151] Further, the method can be implemented in any type of computing platform that is operably connected to a suitable computer, including but not limited to a personal computer, a minicomputer, a mainframe, a workstation, a network or distributed computing environment, a separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, etc. Various aspects of the present invention can be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, an optical read and / or write storage medium, an RSM, a ROM, etc., so that it can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the process described herein. In addition, the machine-readable code, or portions thereof, can be transmitted via a wired or wireless network. When such media includes instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor, the invention described herein includes these and other different types of non-transitory computer-readable storage media. When programmed according to the methods and techniques of the present invention, the present invention can also include the computer itself.

[0152] The computer program can be applied to input data to perform the functions described herein, thereby converting the input data to generate output data stored in a non-volatile memory. The output information can also be applied to one or more output devices such as a display. In a preferred embodiment of the present invention, the converted data represents physical and tangible objects, including specific visual depictions of physical and tangible objects produced on the display.

[0153] The above is only a preferred embodiment of the present invention. The present invention is not limited to the above implementation. As long as the technical effect of the present invention is achieved by the same means, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of protection of the present invention. Within the scope of protection of the present invention, its technical scheme and / or implementation method may have various modifications and changes.

Claims

1. An optimal fault-tolerant control method for robust path tracking of a nearshore tugboat, characterized in that: The method comprises the following steps: S100. Establish the kinematic and dynamic equations of the tugboat with three degrees of freedom; S200, constructing an error system that simultaneously considers external ocean disturbances and internal thruster failures based on information of the reference trajectory; S300, constructing a suitable discounted performance function in combination with the error system, wherein the discounted performance function includes estimates for external ocean disturbances and internal thruster failures; S400, based on the adaptive dynamic programming method, uses the actor-critic neural network to iteratively optimize and obtain the optimal solution of the discounted performance function.

2. The method according to claim 1, characterized in that In step S100: The three-degree-of-freedom kinematic and dynamic model of the tugboat is expressed in the following equations:. η(t)=G(η(t))v(t). τ′(t)+τ l (t)=Mv(t)+C(v(t))v(t)+Dv(t) Where t represents the time at which the system is located, η(t) = [x(t), y(t), φ(t)] T Represents position (x(t), y(t)) and heading φ(t), v(t) = [u(t), v(t), r(t)] T represents the velocity variables, including swell u(t), roll v(t) and yaw r(t); G represents the coordinate transformation matrix; represents the mass (inertia) matrix; represents the Coriolis centripetal force matrix; D represents the damping matrix; τ′(t) represents the force acting on the tugboat; τ l represents the external ocean disturbance including wind, waves and currents; τ′ represents the force applied after the failure of the tugboat propulsion system, where τ′=τ-τ f , where τ=[τ u ,τ v ,τ r ] T represents the force applied by the thruster, τ f Indicates the loss of force due to thruster failure.

3. The method according to claim 2, characterized in that In step S200: The reference kinematic and dynamic models are expressed as follows: In the formula, represents the position and heading of the reference system, G d represents the coordinate transformation matrix of the reference system, v d represents the velocity variable of the reference system, τ d represents the thrust acting on the reference system; According to the three-degree-of-freedom kinematic and dynamic models of the tugboat, and according to the reference kinematic and dynamic models, the constructed error system is expressed as follows: e η =th-th d yes v =vv d e τ =t-t d In which, define z = [e η ,e v ] T , z represents the matrix error; where e η represents the position and heading error, e v represents the speed error, e τ Indicates the error in the applied thrust.

4. The method according to claim 3, characterized in that In step S300: Based on the error system, the constructed discounted performance function is expressed as follows: In the formula, e represents the natural base, τ f and τ l They are τ f and τ l The estimated value of ; σ1 and σ2 are both positive constants; U(z,e τ ) represents the objective function of optimization, Q and P are both positive symmetric matrices; γ is the discount factor, and 0≤γ≤1; e τ represents the optimal control input.

5. The method according to claim 4, characterized in that In step S300: The Hamilton-Jacobi-Bellman equation obtained according to the discounted performance function is expressed as follows: In the formula, express The partial derivative with respect to z is f(z) represents the matrixed error system variable function; α(z) represents the matrixed error system coefficient; And according to the optimal performance function of the system, it is expressed as follows: Obtain the optimal control input for the system It is expressed as follows: In the formula, express The partial derivative with respect to z is The difference t-δ represents the offset time.

6. The method according to claim 5, characterized in that In step S300: The optimal solution of the optimal control input of the system is obtained by continuous approximation through an iterative strategy algorithm, which includes the following steps: S310, Strategy Evaluation: It is known that Updated by the following equation: In the formula, j represents the jth step; represents the input of step j; Represents the initial input; represents the performance function of the jth step; S320, Strategy Improvement: pass To update; S330, policy termination: To obtain the optimal control input In the formula is any given normal number.

7. The method according to claim 6, characterized in that In step S400: The actor-critic neural network is represented as follows: in s c ,∈ c denote the weight vector, activation function and approximation error of the critic neural network respectively; Calculate the partial derivative of F1(z,τ) with respect to z: in 8. The method according to claim 7, characterized in that The weight update rate of the actor-critic neural network and It is expressed as follows: In the formula, σ5 represents the learning rate, as the residual of the neural network approximation, and In the formula, σ6 represents the learning rate; Among them, the control signal e τ Approximately: Then construct the following variables: In the formula, s a ,∈ a denote the weight vector, activation function and approximation error of the actor neural network respectively; The optimal control signal is obtained by continuously updating the control signal e τ get.

9. A computer-readable storage medium having program instructions stored thereon, wherein the program instructions are executed by a processor to implement the method according to any one of claims 1 to 8.

10. An optimal fault-tolerant control system for robust path tracking of a nearshore tugboat, characterized in that: include: A computer device comprising a computer readable storage medium according to claim 9.

Images