Parallel safe berthing control method and system for full-drive unmanned ship
Through the planning-guidance-controlled hierarchical structure method, the safety and efficiency problems of unmanned ships' berthing control in complex marine environments are solved, and collision avoidance and stable berthing in dynamic and static obstacles are achieved, improving the improvement of The berthing performance and safety of unmanned ships.
Patent Information
- Application Number
- CN202410958554.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-08
AI Technical Summary
The existing unmanned ship berthing control methods are difficult to achieve safe and efficient berthing in complex and changing marine environments, and ignore dynamic constraints and obstacle collision avoidance problems, resulting in limited berthing performance and safety.
Using the planning-guidance-control hierarchical structure method, a virtual unmanned ship system is established through neural networks, and a berthing trajectory planner, nominal speed guidance law and anti-interference dynamic control law are designed to realize the virtual unmanned ship berthing. Avoid collisions of static and dynamic obstacles during the process and transmit the control law to the actual unmanned ship system.
It improves the execution efficiency and safety of unmanned ship berthing tasks, enhances stability and reliability in complex marine environments, and ensures the safety and accuracy of unmanned ships during berthing.
Smart Images

Figure CN118915736A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the field of unmanned ship berthing control, mainly studies the problem of parallel safe berthing control of a fully driven unmanned ship, and proposes a design method of a parallel safe berthing controller of a fully driven unmanned ship with a planning-guidance-control hierarchical structure. Background Art
[0002] With the rapid development of science and technology and the increasingly stringent requirements of human beings for marine development tools, modern ships are moving towards intelligence, digitization and autonomy. Unmanned ships, with their many advantages such as autonomy, intelligence, remote control, strong adaptability, low risk, energy saving and environmental protection, have become an indispensable important tool and technical means in the field of marine development and monitoring. Berthing, as one of the core functions of ship operation, its autonomy is undoubtedly a key task in the development of unmanned ships.
[0003] In recent years, although some researchers have conducted in-depth research on the berthing of unmanned ships, the current berthing strategies mainly focus on the kinematic characteristics of unmanned ships, but often ignore the complex model uncertainties and variable ocean environmental disturbances in the actual system dynamics. These uncertainties and environmental disturbances will have a significant impact on the berthing process of unmanned ships, and thus affect the final berthing results. In addition, when berthing, unmanned ships need to accurately avoid obstacles in the environment to prevent collisions. Therefore, how to achieve safe and efficient berthing control in a complex and changing marine environment is still a problem that needs further research and solution.
[0004] In summary, the prior art has the following deficiencies:
[0005] First, existing berthing planning schemes are mainly limited to fixed path planning, which is difficult to adjust in real time according to real-time information. In addition, fixed path planning often ignores the dynamic constraints of unmanned ships, which may make the generated path difficult to execute in actual operations, thus affecting the berthing performance and efficiency of unmanned ships.
[0006] Second, current berthing planning schemes often only focus on the feasibility of unmanned ships berthing, while ignoring the risk of collision or conflict with obstacles during the berthing process. This may lead to safety hazards for unmanned ships and pose a threat to the safety and stability of unmanned ship systems.
[0007] Third, the existing berthing control methods are still insufficient in dealing with the nonlinear uncertainty of the unmanned ship dynamics model and unknown environmental disturbances. These factors will bring challenges to berthing control in the real marine environment, making it difficult to achieve accurate berthing control. Summary of the invention
[0008] In order to solve the above problems, the technical solution adopted by the present invention is: a method for controlling parallel safe berthing of a fully driven unmanned ship, characterized in that it comprises the following steps:
[0009] Based on the state of the virtual unmanned ship system established by the neural network, a berthing trajectory planner is designed to plan the process of the virtual unmanned ship avoiding static obstacles during its driving process, and obtain the berthing trajectory of the virtual unmanned ship;
[0010] Based on the berthing trajectory of the virtual unmanned ship, the nominal speed guidance law of the virtual unmanned ship based on the line-of-sight guidance principle is designed;
[0011] Based on the nominal speed guidance law of the virtual unmanned ship, a risk-free guidance law is designed to prevent the virtual unmanned ship from colliding with dynamic obstacles during berthing.
[0012] Based on the risk-free guidance law and the state of the virtual unmanned ship system, the anti-interference dynamic control law of the virtual unmanned ship system is designed;
[0013] The anti-interference dynamic control law of the virtual unmanned ship system is transmitted to the controller of the actual full-drive unmanned ship to realize the parallel safe berthing control of the actual full-drive unmanned ship.
[0014] Furthermore: the virtual unmanned ship system established based on the neural network twin is as follows:
[0015]
[0016] In the formula, Indicates the position of the virtual system unmanned ship The pitch angle of the unmanned ship in the virtual system The vector composed of Represent the forward speed of the unmanned ship of the virtual system Lateral speed Yaw angular velocity The vector composed of; R(ψ) is the rotation matrix; is the estimated value of the function reconstruction error ε; yes The derivative of yes The derivative of is the derivative of the ε estimate; Y(ν) is the continuous activation function; is the estimated value of the unknown weight θ; represents the diagonal gain matrix;
[0017] In order to approximate the physical ship model, The update law is designed as follows:
[0018]
[0019] In the formula, is the derivative of the estimate of θ; Y T (ν) is the transpose of Y(ν); represents the diagonal gain matrix.
[0020] Further: The design process of the berthing trajectory planner is as follows:
[0021] The kinematic model of the virtual system unmanned ship is discretized as follows:
[0022]
[0023] In the formula, is a constant; R(ψ k ) is the rotation matrix; Respectively represent the state at the kth moment The value of Represents the state at time k+1 The value of .
[0024] To avoid collision with static obstacles during berthing, the obstacle function is controlled The design is as follows:
[0025]
[0026] In the formula, p n =[x n ,y n ] T is the position vector of the static obstacle, is the position vector of the unmanned ship of the virtual system, For safe distance;
[0027] The safety constraint conditions of the discretized control barrier function are designed as follows:
[0028]
[0029] In the formula, γ n ∈(0,1] is the control parameter to be designed;
[0030] Define the berthing end position coordinates and berthing direction as η d =[x d ,y d ,ψ d ] T ,,in In order to plan a safe and stable berthing trajectory, a control Lyapunov function is designed. as follows:
[0031]
[0032] The objective constraint conditions of the discretized control Lyapunov function are designed as follows:
[0033]
[0034] In the formula, α o ∈(0,1] is the control parameter to be designed, δ0 is the relaxation variable;
[0035] Based on the above constraints, the nonlinear model prediction berthing trajectory planner is designed as follows:
[0036]
[0037] Affiliated to:
[0038]
[0039] Where ν=[u,v,r] T and is the speed constraint of the unmanned ship, and is a constant. Indicates the starting trajectory point in the current prediction sequence.
[0040] Further: The design process of the nominal guidance law of the virtual unmanned ship is as follows:
[0041] Definition η r =[x r ,y r ,ψ r ] T is the berthing trajectory of the virtual unmanned ship, the unmanned ship nominal speed guidance law based on the line-of-sight guidance principle,...ν c =[u c ,v c ,r c ] T The design is as follows:
[0042]
[0043] In the formula, u c ,v c ,r c They represent the nominal forward velocity guidance law, the nominal lateral velocity guidance law, and the nominal yaw angular velocity guidance law, respectively. e ,y e ,ψ e They represent the forward, lateral and heading tracking errors of the virtual unmanned ship system in the earth coordinate system respectively; is a constant; is a constant; is c The derivative of represents the heading estimation error; u r ,v r They represent the forward velocity and lateral velocity solved by the planner respectively.
[0044] Further: The design process of the risk-free guidance law is as follows:
[0045] In order to avoid collision with dynamic obstacles during berthing, the control obstacle function is designed as follows:
[0046]
[0047] In the formula, .p m =[x m ,y m ] T . is the position vector of the dynamic obstacle, The horizontal and vertical coordinates of the dynamic obstacle in the earth coordinate system, For a safe distance.
[0048] The safety constraint condition of the control barrier function is constructed as follows:
[0049]
[0050] Based on the above safety constraints and input constraints, the secondary optimization problem is constructed as follows:
[0051]
[0052] In the formula, Respectively represent the upper and lower bounds of the speed constraint, where is a constant;
[0053] The risk-free forward velocity guidance signal and risk-free lateral velocity guidance signal A vector of estimates of ;
[0054] Furthermore: the design of the anti-interference dynamic control law τ is as follows:
[0055]
[0056] In the formula, represents the error vector, where represents the error between the speed of the virtual unmanned ship and the guidance signal; ν s =[u1,v1,r c ] T Guidance signal for risk-free speed; Yes s The derivative of is the diagonal control gain matrix.
[0057] A parallel safe berthing control system for a fully driven unmanned ship, comprising:
[0058] Berthing trajectory planner design module: It is used to design a berthing trajectory planner based on the state of the virtual unmanned ship system established by the neural network twin, to plan the process of the virtual unmanned ship avoiding static obstacles during its driving process, and to obtain the berthing trajectory of the virtual unmanned ship;
[0059] Nominal speed guidance law design module: Based on the berthing trajectory of the virtual unmanned ship, the nominal speed guidance law of the virtual unmanned ship based on the line-of-sight guidance principle is designed;
[0060] Risk-free guidance law design module: used to design a risk-free guidance law based on the nominal speed guidance law of the virtual unmanned ship, so that the virtual unmanned ship can avoid collision with dynamic obstacles during berthing;
[0061] Anti-interference dynamic control law design module: Based on the risk-free guidance law and the state of the virtual unmanned ship system, the anti-interference dynamic control law of the virtual unmanned ship system is designed;
[0062] Output module: used to transmit the anti-interference dynamic control law of the virtual unmanned ship system to the controller of the actual full-drive unmanned ship, so as to realize the parallel safe berthing control of the actual full-drive unmanned ship.
[0063] The present invention provides a design method for a parallel safe berthing controller for a fully driven unmanned ship. The present invention studies the parallel safe berthing control problem of a fully driven unmanned ship, proposes a parallel safe berthing control method for a fully driven unmanned ship with a planning-guidance-control hierarchical structure, and solves the problem of safe berthing of an unmanned ship under the constraints of dynamic and static obstacles and uncertain ship models.
[0064] Compared with the prior art, the present invention has the following beneficial effects:
[0065] First, compared with the existing berthing planning schemes that are limited to fixed path planning, the proposed method designs a berthing trajectory planning method based on model prediction, which can adjust the trajectory planning in real time and fully considers the dynamic and kinematic characteristics of the unmanned boat, thereby improving the execution efficiency of the unmanned boat berthing mission.
[0066] Second, compared with the existing berthing planning scheme that does not consider the collision avoidance problem, the proposed method designs a berthing trajectory optimization method based on the control obstacle function, which avoids the collision of the unmanned ship with static and dynamic obstacles during the berthing process and improves the safety of the unmanned ship berthing mission.
[0067] Third, compared with the existing berthing control methods that do not deal with the nonlinear uncertainty of the unmanned ship dynamics model and the unknown environmental disturbance problems, the proposed method designs an anti-interference parallel control law, which improves the stability and reliability of the unmanned ship berthing mission in complex marine environments. BRIEF DESCRIPTION OF THE DRAWINGS
[0068] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0069] Figure 1 The design diagram of the control method for parallel safe berthing of unmanned ships;
[0070] Figure 2 It is the berthing curve diagram of unmanned ship;
[0071] Figure 3 It is a curve diagram of the relative distance between the unmanned ship and the static obstacle;
[0072] Figure 4 It is a curve diagram of the relative distance between the unmanned ship and the dynamic obstacle;
[0073] Figure 5 This is the curve diagram of the lateral trajectory tracking error of the unmanned ship;
[0074] Figure 6 It is the longitudinal trajectory tracking error curve of the unmanned ship;
[0075] Figure 7 This is the estimated curve diagram of the uncertainty of the unmanned ship model in the longitudinal direction;
[0076] Figure 8 This is the estimated curve diagram of the uncertainty of the unmanned ship model in the sway direction;
[0077] Fig. 9 This is the estimated curve diagram of the uncertainty of the unmanned ship model in the bow rolling direction;
[0078] Fig.10 Input curve diagram for the surge direction system control;
[0079] Fig.11 Input curve diagram for sway direction system control;
[0080] Fig.12 Input curve diagram for the heading direction system control. DETAILED DESCRIPTION
[0081] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0082] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0083] The present invention is further described below in conjunction with the accompanying drawings.
[0084] The present invention relates to a design of a parallel safe berthing method for a fully driven unmanned ship with a planning-guidance-control hierarchical structure. Figure 1 As shown in the figure. Based on the neural network predictor, the twin modeling obtains a virtual system that is parallel to the actual system. The berthing trajectory planner is designed based on the nonlinear model prediction. The trajectory tracking nominal guidance law is designed based on the line-of-sight guidance principle. The risk-free guidance law is designed based on the control obstacle function to ensure that the berthing trajectory is tracked while avoiding collisions with dynamic obstacles. Based on the information learned from the twin modeling of the unmanned ship, the dynamic anti-interference parallel control law is designed to achieve parallel control of the virtual system and the actual system.
[0085] Considering the berthing system of a large unmanned ship, in the trajectory planning layer, in order to observe the nonlinear uncertain functions in the unmanned ship model, a neural network predictor is used to model the unmanned ship twin to obtain a virtual system parallel to the actual system. The berthing trajectory planner is designed based on the nonlinear model prediction, in which the discrete control Lyapunov function is used to implement the berthing terminal constraint, the discrete control obstacle function is used to implement the collision avoidance constraint for static obstacles, and the slack variables are introduced in the discrete control Lyapunov function to ensure the solvability of the planner. In the trajectory tracking layer, the trajectory tracking nominal guidance law is designed based on the line-of-sight guidance principle, and considering the motion characteristics of the fully driven unmanned ship, the sway speed and the sway speed are optimized based on the first-order control obstacle function to achieve collision avoidance of dynamic obstacles. In the parallel control layer, the anti-interference parallel control law is designed based on the unmanned ship model information observed by the neural network predictor, and the ship is manipulated at the dynamic level to achieve berthing.
[0086] A method for controlling parallel safe berthing of a fully-driven unmanned ship comprises the following steps:
[0087] Based on the state of the virtual unmanned ship system established by the neural network twin, a berthing trajectory planner is designed to plan the process of the virtual unmanned ship avoiding static obstacles during its driving process, and obtain the berthing trajectory of the virtual unmanned ship;
[0088] Based on the berthing trajectory of the virtual unmanned ship, the nominal speed guidance law of the virtual unmanned ship based on the line-of-sight guidance principle is designed;
[0089] Based on the nominal speed guidance law of the virtual unmanned ship, a risk-free guidance law is designed to prevent the virtual unmanned ship from colliding with dynamic obstacles during berthing.
[0090] Based on the risk-free guidance law and the state of the virtual unmanned ship system, the anti-interference dynamic control law of the virtual unmanned ship system is designed;
[0091] The anti-interference dynamic control law of the virtual unmanned ship system is transmitted to the controller of the actual full-drive unmanned ship to realize the parallel safe berthing control of the actual full-drive unmanned ship.
[0092] The actual virtual unmanned ship system is as follows:
[0093] Considering the three-degree-of-freedom maneuvering model of the unmanned ship, its kinematic and dynamic models are expressed as follows:
[0094]
[0095] and
[0096]
[0097] Where η=[x,y,ψ] T is the position and yaw angle vector of the unmanned ship, ν=[u,v,r] T is the velocity vector of the unmanned ship, τ=[τ u ,τ v ,τ r ] T is the control input vector of the unmanned ship, τ ω =[τ ωu ,τ ωv ,τ ωr ] T is the environmental disturbance vector, M(ν), C(ν), D(ν) are the inertial mass matrix, the centripetal force and Coriolis force coefficient matrix, and the damping matrix, respectively, and R(ψ) is the rotation matrix, as shown below:
[0098]
[0099] Furthermore, the virtual unmanned ship system established based on the neural network twin is as follows:
[0100]
[0101] In the formula, and They represent the position, bow angle and velocity vector of the unmanned ship in the virtual system respectively; is the estimated value of the function reconstruction error ε; yes The derivative of yes The derivative of is the derivative of the ε estimate; Y(ν) is the continuous activation function; is the estimated value of the unknown weight θ; represents the diagonal gain matrix;
[0102] In order to approximate the physical ship model, The update law is designed as follows:
[0103]
[0104] In the formula, is the derivative of the estimate of θ; Y T (ν) is the transpose of Y(ν); represents the diagonal gain matrix.
[0105] Furthermore, the design process of the berthing trajectory planner is as follows:
[0106] The kinematic model of the virtual system unmanned ship is discretized as follows:
[0107]
[0108] In the formula, is a constant; R(ψ k ) is the rotation matrix; Respectively represent the state at the kth moment The value of Represents the state at time k+1 The value of .
[0109] To avoid collision with static obstacles during berthing, the obstacle function is controlled The design is as follows:
[0110]
[0111] In the formula, p n =[x n ,y n ] T is the position vector of the static obstacle, is the position vector of the unmanned ship of the virtual system, For safe distance;
[0112] The safety constraint conditions of the discretized control barrier function are designed as follows:
[0113]
[0114] In the formula, γ n ∈(0,1] is the control parameter to be designed;
[0115] Define the berthing end position coordinates and berthing direction as η d =[x d ,y d ,ψ d ] T ,in In order to plan a safe and stable berthing trajectory, a control Lyapunov function is designed. as follows:
[0116]
[0117] The objective constraint conditions of the discretized control Lyapunov function are designed as follows:
[0118]
[0119] In the formula, α o ∈(0,1] is the control parameter to be designed, δ0 is the relaxation variable;
[0120] Based on the above constraints, the nonlinear model prediction berthing trajectory planner is designed as follows:
[0121]
[0122] Affiliate
[0123]
[0124] Where ν=[u,v,r] T and is the speed constraint of the unmanned ship, and is a constant. Indicates the starting trajectory point in the current prediction sequence, which is also the trajectory point calculated in the previous prediction sequence.
[0125] In order to avoid collision with dynamic obstacles during berthing, the control obstacle function is designed as follows:
[0126]
[0127] In the formula, .p m =[x m ,y m ]T . is the position vector of the dynamic obstacle, The horizontal and vertical coordinates of the dynamic obstacle in the earth coordinate system, For a safe distance.
[0128] The safety constraint condition of the control barrier function is constructed as follows:
[0129]
[0130] Based on the above safety constraints and input constraints, the secondary optimization problem is constructed as follows:
[0131]
[0132] In the formula, Respectively represent the upper and lower bounds of the speed constraint, where is a constant; The risk-free forward velocity guidance signal and risk-free lateral velocity guidance signal A vector of estimates of ;
[0133] Further: the design of the anti-interference dynamic control law is as follows:
[0134]
[0135] In the formula, represents the error vector, where represents the error between the speed of the virtual unmanned ship and the guidance signal; ν s =[u1,v1,r c ] T Guidance signal for risk-free speed; Yes s The derivative of is the diagonal control gain matrix.
[0136] A parallel safe berthing control system for a fully driven unmanned ship, comprising:
[0137] Berthing trajectory planner design module: It is used to design a berthing trajectory planner based on the state of the virtual unmanned ship system established by the neural network twin, to plan the process of the virtual unmanned ship avoiding static obstacles during its driving process, and to obtain the berthing trajectory of the virtual unmanned ship;
[0138] Nominal speed guidance law design module: Based on the berthing trajectory of the virtual unmanned ship, the nominal speed guidance law of the virtual unmanned ship based on the line-of-sight guidance principle is designed;
[0139] Risk-free guidance law design module: used to design a risk-free guidance law based on the nominal speed guidance law of the virtual unmanned ship, so that the virtual unmanned ship can avoid collision with dynamic obstacles during berthing;
[0140] Anti-interference dynamic control law design module: Based on the risk-free guidance law and the state of the virtual unmanned ship system, the anti-interference dynamic control law of the virtual unmanned ship system is designed;
[0141] Output module: used to transmit the anti-interference dynamic control law of the virtual unmanned ship system to the controller of the actual full-drive unmanned ship, so as to realize the parallel safe berthing control of the actual full-drive unmanned ship.
[0142] The simulation results are as follows Figure 2-12 shown. Figure 2 This is the berthing curve of the unmanned ship. It can be seen that when berthing, the unmanned ship can avoid dynamic and static obstacles and finally sail to the berthing point, and the posture of the unmanned ship is stable during the navigation process. Figure 3 is the relative distance curve between the unmanned ship and the static obstacle. Figure 4 This is a curve diagram of the relative distance between the unmanned ship and the dynamic obstacle. It can be seen that the proposed collision avoidance algorithm can realize the safe berthing and navigation of the unmanned ship. Figure 5 This is the lateral trajectory tracking error curve of the unmanned ship. Figure 6 This is the longitudinal trajectory tracking error curve of the unmanned ship. It can be seen that the tracking error of the unmanned ship can converge to the origin, that is, the unmanned ship can accurately track the trajectory of the trajectory generator. Figure 7 This is the estimated curve diagram of the uncertainty of the unmanned ship model in the longitudinal direction. Figure 8 This is the estimated curve diagram of the uncertainty of the unmanned ship model in the sway direction. Fig. 9 This is an estimation curve of the uncertainty of the unmanned ship model in the bow roll direction. It can be seen that the neural network predictor can accurately estimate the unknown functions in the unmanned ship dynamics model and achieve accurate modeling of the ship. Fig.10 This is the control input curve of the surge direction system. Fig.11 is the control input curve of the sway direction system, Fig.12 It is a control input curve diagram of the bowing direction system. It can be seen from the above simulation result diagram that the parallel safe berthing control method of the fully driven unmanned ship with a planning-guidance-control hierarchical structure proposed by the present invention is a complete berthing system and performs effective berthing tasks in complex environments.
[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for controlling parallel safe berthing of a fully-driven unmanned ship. Features: The following steps are involved: Based on the state of the virtual unmanned ship system established by the neural network, a berthing trajectory planner is designed to plan the process of the virtual unmanned ship avoiding static obstacles during its driving process, and obtain the berthing trajectory of the virtual unmanned ship; Based on the berthing trajectory of the virtual unmanned ship, the nominal speed guidance law of the virtual unmanned ship based on the line-of-sight guidance principle is designed; Based on the nominal speed guidance law of the virtual unmanned ship, a risk-free guidance law is designed to prevent the virtual unmanned ship from colliding with dynamic obstacles during berthing. Based on the risk-free guidance law and the state of the virtual unmanned ship system, the anti-interference dynamic control law of the virtual unmanned ship system is designed; The anti-interference dynamic control law of the virtual unmanned ship system is transmitted to the controller of the actual full-drive unmanned ship to realize the parallel safe berthing control of the actual full-drive unmanned ship.
2. According to the method for controlling parallel safe berthing of a fully-driven unmanned ship according to claim 1, Features: The virtual unmanned ship system established based on the neural network twin is as follows: In the formula, Indicates the position of the virtual system unmanned ship The pitch angle of the unmanned ship in the virtual system The vector composed of Represent the forward speed of the unmanned ship of the virtual system Lateral speed Yaw angular velocity The vector composed of; R(ψ) is the rotation matrix; is the estimated value of the function reconstruction error ε; yes The derivative of yes The derivative of is the derivative of the ε estimate; Y(ν) is the continuous activation function; is the estimated value of the unknown weight θ; represents the diagonal gain matrix; In order to approximate the physical ship model, The update law is designed as follows: In the formula, is the derivative of the estimate of θ; Y T (ν) is the transpose of Y(ν); represents the diagonal gain matrix.
3. According to the method for controlling parallel safe berthing of a fully-driven unmanned ship as described in claim 1, Features: The design process of the berthing trajectory planner is as follows: The kinematic model of the virtual system unmanned ship is discretized as follows: In the formula, is a constant; R(ψ k ) is the rotation matrix; ψ k ,η k Respectively represent the state at the kth moment The values of ψ,η; Represents the state at time k+1 The value of . To avoid collision with static obstacles during berthing, the obstacle function is controlled The design is as follows: In the formula, p n =[x n ,y n ] T is the position vector of the static obstacle, is the position vector of the unmanned ship of the virtual system, For safe distance; The safety constraint conditions of the discretized control barrier function are designed as follows: In the formula, γ n ∈(0,1] is the control parameter to be designed; Define the berthing end position coordinates and berthing direction as η d =[x d ,y d ,ψ d ] T ,,in In order to plan a safe and stable berthing trajectory, a control Lyapunov function is designed. as follows: The objective constraint conditions of the discretized control Lyapunov function are designed as follows: In the formula, α o ∈(0,1] is the control parameter to be designed, δ 0 is the slack variable; Based on the above constraints, the nonlinear model prediction berthing trajectory planner is designed as follows: Affiliated to: Where ν=[u,v,r] T and is the speed constraint of the unmanned ship, and is a constant. Indicates the starting trajectory point in the current prediction sequence.
4. According to the method for controlling parallel safe berthing of a fully-driven unmanned ship as described in claim 1, Features: The design process of the nominal guidance law of the virtual unmanned ship is as follows: Definition η r =[x r ,y r ,ψ r ] T is the berthing trajectory of the virtual unmanned ship, the unmanned ship nominal speed guidance law based on the line-of-sight guidance principle,...ν c =[u c ,v c ,r c ] T The design is as follows: In the formula, u c ,v c ,r c They represent the nominal forward velocity guidance law, the nominal lateral velocity guidance law, and the nominal yaw angular velocity guidance law, respectively. e ,y e ,ψ e They represent the forward, lateral and heading tracking errors of the virtual unmanned ship system in the earth coordinate system respectively; is a constant; ψ c = ψ r -atan(y e / Δ); is a constant number; is c The derivative of represents the heading estimation error; u r ,v r They represent the forward velocity and lateral velocity solved by the planner respectively.
5. According to claim 1, a method for controlling parallel safe berthing of a fully-driven unmanned ship, Features: The design process of the risk-free guidance law is as follows: In order to avoid collision with dynamic obstacles during berthing, the control obstacle function is designed as follows: In the formula, .p m =[x m ,y m ] T . is the position vector of the dynamic obstacle, The horizontal and vertical coordinates of the dynamic obstacle in the earth coordinate system, For a safe distance. The safety constraint condition of the control barrier function is constructed as follows: Based on the above safety constraints and input constraints, the secondary optimization problem is constructed as follows: In the formula, Respectively represent the upper and lower bounds of the velocity constraint, where is a constant; The risk-free forward velocity guidance signal and risk-free lateral velocity guidance signal A vector of estimates of ; 6. A method for controlling parallel safe berthing of a fully-driven unmanned ship according to claim 1, Features: The design of the anti-interference dynamic control law τ is as follows: In the formula, represents the error vector, where represents the error between the speed of the virtual unmanned ship and the guidance signal; ν s =[u 1 ,v 1 ,r c ] T Guidance signal for risk-free speed; Yes s The derivative of is the diagonal control gain matrix.
7. A parallel safe berthing control system for a fully driven unmanned ship. Features: include: Berthing trajectory planner design module: It is used to design a berthing trajectory planner based on the state of the virtual unmanned ship system established by the neural network twin, to plan the process of the virtual unmanned ship avoiding static obstacles during its driving process, and to obtain the berthing trajectory of the virtual unmanned ship; Nominal speed guidance law design module: Based on the berthing trajectory of the virtual unmanned ship, the nominal speed guidance law of the virtual unmanned ship based on the line-of-sight guidance principle is designed; Risk-free guidance law design module: used to design a risk-free guidance law based on the nominal speed guidance law of the virtual unmanned ship, so that the virtual unmanned ship can avoid collision with dynamic obstacles during berthing; Anti-interference dynamic control law design module: Based on the risk-free guidance law and the state of the virtual unmanned ship system, the anti-interference dynamic control law of the virtual unmanned ship system is designed; Output module: used to transmit the anti-interference dynamic control law of the virtual unmanned ship system to the controller of the actual full-drive unmanned ship, so as to realize the parallel safe berthing control of the actual full-drive unmanned ship.
Citation Information
Cited By
Anti-interference autonomous berthing regulation and control method and system for unmanned ship
CN121596799A
Anti-interference autonomous berthing regulation method and system for unmanned ship
CN121596799B
Hierarchical double-closed-loop control method and system for ship berthing based on tug cooperation
CN122151567A
