Unmanned ship path planning method and system based on fusion model predictive control

Abstract

The present invention discloses a method and system for unmanned ship path planning based on fusion model predictive control, which belongs to the field of unmanned ship path planning and obstacle avoidance. It includes step S1: modeling and processing the uncertainty of external interference of the unmanned ship's marine environment; step S2: constructing a dual-mode control strategy according to the real-time status of the unmanned ship and the changes in the marine environment and introducing a collaborative successive linearization method; step S3: rationally optimizing the weights of each element in the unmanned ship path planning parameter matrix; designing the cost function of the unmanned ship path planning; step S4: constructing a simulation environment that matches the marine mission scenario in the actual execution of the unmanned ship, recording the path trajectory, navigation time, and key information of the control input sequence in detail throughout the process, analyzing the simulation results, and verifying the effectiveness. The technical solution provided by the present invention effectively solves the problem that the unmanned ship path planning and obstacle avoidance cannot be accurately and efficiently performed in the technology.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned ship navigation and obstacle avoidance, and in particular to an unmanned ship path planning method and system based on fusion model predictive control. Background Art

[0002] Unmanned vessels (UVVs) are playing an increasingly important role in today's marine applications. However, their operation in the marine environment faces numerous complex challenges. The marine environment is rife with uncertainties, including unpredictable wind, wave, and current disturbances, unpredictable sea conditions, and potential obstacles. Accurate path planning for UVVs is crucial in such complex marine environments. Traditional path generation methods, including A* and its improved algorithms and artificial potential field (APF) and its improved algorithms, are unable to meet these requirements. Summary of the Invention

[0003] In response to the defects of related technologies, the present invention provides an unmanned ship path planning method and system based on fusion model predictive control, aiming to solve the problem in the existing technology that it is impossible to predict and control based on water environment interference to accurately achieve path planning for unmanned ship collision avoidance.

[0004] The technical solution is as follows:

[0005] A path planning method for an unmanned vessel based on fusion model predictive control includes the following steps:

[0006] Step S1: Model and process the uncertainty of external interference in the unmanned ship's marine environment, define interference boundary parameters, consider the maximum possible value range of external interference under a certain probability level, optimize the calculation of the uncertain disturbance set, determine the scope of the impact of external interference on the unmanned ship's state, and make the unmanned ship path planning fully consider uncertainty;

[0007] Step S2: A dual-mode control strategy is constructed based on the real-time status of the unmanned vessel and changes in the ocean environment. A simple control strategy is used in the safe area to ensure stable navigation. Outside the safe area, an optimization problem is solved to obtain the optimal control input to cope with complex situations. At the same time, a collaborative successive linearization method is introduced to reduce the computational complexity of the dynamic model. Under different control modes, the optimization solution is further performed based on the linear time-varying model.

[0008] Step S3: Dynamically balance system performance and robustness based on the requirements of the unmanned ship's mission, the conditions of the ocean environment, and its own resource conditions. According to the complexity of the ocean environment and the type of mission, reasonably optimize the weights of each element in the unmanned ship path planning parameter matrix; design a cost function for the unmanned ship path planning, and by reasonably determining the value range of the penalty coefficient parameter, adjust the various parameters in the cost function under different ocean environments and mission scenarios to ensure that the unmanned ship path planning strikes a balance between performance and robustness.

[0009] Step S4: Construct a simulation environment that matches the marine mission scenario in the actual execution of the unmanned ship, and obtain detailed results by executing path planning; in the scene setting link, comprehensively consider the task-related factors, and in the process of executing path planning, use the improved fusion method to evaluate the impact of the current wind, wave and current interference on the state of the unmanned ship at each sampling moment based on the uncertainty model constructed in the early stage, and then determine the control input with the help of the optimized control strategy, update the state through the unmanned ship dynamics model, and record the path trajectory, navigation time, and key information of the control input sequence in the whole process in detail, analyze the simulation results, and verify the effectiveness.

[0010] An unmanned vessel path planning system based on fusion model predictive control, the system comprising:

[0011] The external environment construction module is used to model and process the uncertainty of external interference in the unmanned ship's marine environment, define interference boundary parameters, consider the maximum possible value range of external interference under a certain probability level, optimize the calculation of uncertain disturbance sets, determine the scope of influence of external interference on the unmanned ship's state, and enable the unmanned ship's path planning to fully consider uncertainty;

[0012] The fusion model predictive control module is used to build a dual-mode control strategy based on the real-time status of the unmanned vessel and changes in the ocean environment. A simple control strategy is used to ensure stable navigation in the safe area, while an optimization problem is solved to obtain the optimal control input to cope with complex situations outside the safe area. At the same time, a collaborative successive linearization method is introduced to reduce the computational complexity of the dynamic model, and further optimization solutions are performed based on the linear time-varying model under different control modes.

[0013] The path planning module is used to dynamically balance system performance and robustness based on the requirements of the unmanned ship's mission, the conditions of the ocean environment, and its own resource conditions. The weights of each element in the unmanned ship's path planning parameter matrix are rationally optimized according to the complexity of the ocean environment and the type of mission. The cost function for the unmanned ship's path planning is designed. By reasonably determining the value range of the penalty coefficient parameter, the various parameters in the cost function are adjusted under different ocean environments and mission scenarios to ensure that the unmanned ship's path planning strikes a balance between performance and robustness.

[0014] The simulation verification module is used to build a simulation environment that matches the marine mission scenario in the actual execution of the unmanned ship, and obtain detailed results by executing path planning; in the scene setting link, the task-related factors are fully considered. In the process of executing path planning, the improved fusion method is used to evaluate the impact of the current wind, wave and current interference on the state of the unmanned ship at each sampling moment based on the uncertainty model constructed in the early stage, and then determine the control input with the help of the optimized control strategy, update the state through the unmanned ship dynamics model, and record the path trajectory, navigation time, and key information of the control input sequence in the whole process in detail, analyze the simulation results, and verify the effectiveness.

[0015] The present invention has the following beneficial effects:

[0016] The present invention provides an unmanned ship path planning method and system based on fusion model predictive control, which accurately models and processes the uncertainty of the marine environment faced by the unmanned ship, defines similar interference boundary parameters, optimizes the calculation of uncertain disturbance sets, and provides a more accurate uncertainty information basis for the unmanned ship path planning; at the same time, in terms of control strategy, a dual-mode control strategy and a collaborative successive linearization method are introduced to flexibly select appropriate control strategies according to the real-time status of the unmanned ship and changes in the marine environment, thereby improving the path planning capability and accuracy of the unmanned ship in complex situations; in addition, through a comprehensive trade-off between system performance and robustness, parameters are dynamically adjusted according to the task, environment and resource conditions, and the path planning performance and robustness are balanced to ensure the optimal performance of the unmanned ship in different tasks and environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of an unmanned vessel path planning method based on fusion model predictive control provided by an embodiment of the present invention;

[0018] Figure 2 This is a flowchart of uncertainty modeling and processing of external interference in the marine environment of an unmanned ship provided by an embodiment of the present invention;

[0019] Figure 3 This is a flow chart of the dual-mode control strategy for an unmanned ship provided by an embodiment of the present invention;

[0020] Figure 4 This is a flow chart of the path planning of an unmanned ship provided by an embodiment of the present invention;

[0021] Figure 5 This is a simulation verification flow chart of the actual execution of tasks by the unmanned ship provided by the embodiment of the present invention;

[0022] Figure 6 This is a structural diagram of an unmanned vessel path planning system based on fusion model predictive control provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0024] It will be understood by those skilled in the art that, unless expressly stated otherwise, the singular forms "a", "an", "said" and "the" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the description of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, "connected" or "coupled" as used herein may include wireless connections or wireless couplings. The term "and / or" used herein includes all or any units and all combinations of one or more associated listed items.

[0025] See Figure 1 The present invention provides a path planning method for an unmanned ship based on fusion model predictive control, comprising the following steps:

[0026] Step S1: Model and process the uncertainty of external interference in the unmanned ship's marine environment, define interference boundary parameters, consider the maximum possible value range of external interference under a certain probability level, optimize the calculation of the uncertain disturbance set, determine the scope of the impact of external interference on the unmanned ship's state, and make the unmanned ship path planning fully consider uncertainty;

[0027] Step S2: A dual-mode control strategy is constructed based on the real-time status of the unmanned vessel and changes in the ocean environment. A simple control strategy is used in the safe area to ensure stable navigation. Outside the safe area, an optimization problem is solved to obtain the optimal control input to cope with complex situations. At the same time, a collaborative successive linearization method is introduced to reduce the computational complexity of the dynamic model. Under different control modes, the optimization solution is further performed based on the linear time-varying model.

[0028] Step S3: Dynamically balance system performance and robustness based on the requirements of the unmanned ship's mission, the conditions of the ocean environment, and its own resource conditions. According to the complexity of the ocean environment and the type of mission, reasonably optimize the weights of each element in the unmanned ship path planning parameter matrix; design a cost function for the unmanned ship path planning, and by reasonably determining the value range of the penalty coefficient parameter, adjust the various parameters in the cost function under different ocean environments and mission scenarios to ensure that the unmanned ship path planning strikes a balance between performance and robustness.

[0029] Step S4: Construct a simulation environment that matches the marine mission scenario in the actual execution of the unmanned ship, and obtain detailed results by executing path planning; in the scene setting link, comprehensively consider the task-related factors, and in the process of executing path planning, use the improved fusion method to evaluate the impact of the current wind, wave and current interference on the state of the unmanned ship at each sampling moment based on the uncertainty model constructed in the early stage, and then determine the control input with the help of the optimized control strategy, update the state through the unmanned ship dynamics model, and record the path trajectory, navigation time, and key information of the control input sequence in the whole process in detail, analyze the simulation results, and verify the effectiveness.

[0030] See Figure 2 ,Step S1: Model and process the uncertainty of external interference in the ,unmanned ship's marine environment, define the interference boundary ,parameters, consider the maximum possible value range of external interference under ,a certain probability level, optimize the calculation of the uncertain disturbance set, determine the ,scope of the external interference on the state of the unmanned ship, and make the ,unmanned ship path planning fully consider the uncertainty, ,specifically:

[0031] Step S11: Define the interference boundary parameters of the external interference of the unmanned ship's marine environment, where the interference of the marine environment on the unmanned ship is ω i (t), define σ max is the maximum value of interference at the 95% confidence level, and the interference bound ρ i To express the interference ω i (t) intensity range, when ρ i ≤ρ -i When the ocean environment is considered suitable for unmanned boats to operate, otherwise it is considered unsuitable for unmanned boats to operate. -i is defined as:

[0032]

[0033] Among them, the positive definite matrix Q i It is the weight matrix related to the performance of the unmanned ship system, reflecting the importance of the unmanned ship position and tracking error performance indicators; the positive definite matrix P i is the weighted norm matrix of the state parameters of the unmanned ship system, reflecting whether the unmanned ship meets the stability requirements; α i and εi is the design parameter of the unmanned ship system terminal, which is determined according to the system design and stability requirements; T is the prediction time domain parameter, which determines the time range of future states considered in path planning; L i is a constant related to the unmanned ship system model and is related to the nonlinear characteristics of the unmanned ship dynamics model; the matrix eigenvalues ​​λ and are the minimum and maximum eigenvalues ​​of the matrix;

[0034] In the actual application process, firstly, according to the system design analysis of the unmanned ship, the positive definite matrix Q is preliminarily determined through theoretical calculations, experimental tests or empirical data. i 、P i , design parameter α i and ε i , prediction time domain T and parameter L i The value of , and then calculate the matrix where R i is the matrix that limits the control input energy consumption, K i Is the gain matrix related to the system feedback control, and solve the minimum eigenvalue of the corresponding matrix and the maximum eigenvalue of the corresponding matrix

[0035] Then according to σ max and ρ -i The relationship between σ max The value of σ, for example max The value can be slightly smaller than ρ -i , σ max The value of is used as an important basis for judging the interference intensity and adjusting the control input when calculating the control input during path planning. i The norm of (t) is close to σ max When the vehicle is in a state of disturbance, the path planning algorithm will appropriately increase the adjustment range of the control input according to the pre-designed rules, such as increasing the adjustment of the rudder angle or propulsion force, so that the unmanned ship can better resist interference and stay near the predetermined path, ensuring that the unmanned ship maintains a certain performance under interference;

[0036] Step S12: Optimize the calculation of the uncertain disturbance set to determine the impact range of external disturbance on the state of the unmanned ship. The offline dynamic model of the unmanned ship is x k+1 =f(x k ,u k ,ω k ), where x k is the state vector of the unmanned ship system at time k, including the position, speed, and heading information of the unmanned ship, u k is the control input vector, including the rudder angle command and thrust force, ω kis the interference of the ocean environment; the offline dynamic model of the unmanned ship is linearized and approximated as A k 、B k and E k is the matrix related to the system state and control input, obtained by linearizing the dynamic model at the current state; Assume that the uncertain perturbation dynamic equation is Δω k+1 =F k Δω k +G k ξ k , F k and G k is a matrix related to system dynamics and disturbance characteristics, ξ k For ω k The random noise vector associated with the probability distribution; define the uncertain perturbation set X Δ (k) = {Δω k :||Δω k ||≤σ max},calculate Where W k is a compact set associated with random noise, whose size is determined by the interference ω k The probability distribution is determined by real-time monitoring and calculation of X Δ (k) and X Δ (k+1), adjust the control strategy according to its changing trend, and increase the control input adjustment amplitude when the disturbance set increases to keep the unmanned ship sailing stably;

[0037] See Figure 3 ,Step S2: Construct a dual-mode control strategy based on the real-time status of the unmanned ship and the changes in the ocean environment. A simple control strategy is used in the safe area to ensure stable navigation. Beyond the safe area, the optimization problem is solved to obtain the optimal control input to deal with complex situations. At the same time, the collaborative successive linearization method is introduced to reduce the computational complexity of the dynamic model. Under different control modes, the optimization solution is further performed based on the linear time-varying model. Specifically:

[0038] Step S21: Introduce the dual-mode control strategy. When the state of the unmanned ship meets the When the unmanned ship is in the safe area, the control strategy based on linear feedback is adopted, which is determined by system stability analysis and performance index design; the sensor is used to monitor the state of the unmanned ship in real time, and the calculation and with ε i Compare and decide whether to switch the control mode;

[0039] When the unmanned ship approaches an obstacle or deviates from the planned route, that is, the state exceeds the safe area, it switches to the optimization control mode. In the optimization control mode, the interference ω is set. k The probability distribution ofk ), add the constraint P(ω k ∈W k )≥p0, p0 is the preset probability threshold, which is set according to the reliability requirements of the task; the control input u is retained min ≤u k ≤u max and state x min ≤x k ≤x max Constraints, where u min and u max are the lower and upper limits of the control input, which depend on the physical limitations of the UAV actuator, x min and x max The reasonable range of the unmanned ship state; determine the optimization problem:

[0040]

[0041] in, tk is the moment value, and the definitions of matrices T, Q, R, and P are the same as in step S11.

[0042] Step S22: The real-time state of the unmanned ship and the environment are coordinated using a successive linearization processing model, and the nonlinear dynamic model of the unmanned ship is processed at the sampling time k. Linearize and obtain the initial control input trajectory u at the current moment by translating the optimal control input sequence at the previous moment 0 (i|k), apply this initial control input trajectory to obtain the initial state trajectory x 0 (i|k), the interference input uses the predicted mean Then the nonlinear dynamic model is linearized to obtain x(i+1|k)=x 0 (i+1|k)+A(i|k)Δx(i|k)+B(i|k)Δu(i|k)+C(i|k)Δω(i|k), where A(i|k), B(i|k), and C(i|k) are Jacobian matrices;

[0043] Step S23: Under the dual-mode control strategy, the path planning is performed using a sequentially linearized model based on the UAV's real-time state and environment. Within the safe zone, the control input is calculated using a simple sequentially linearized model to reduce computational resource consumption. In the optimization control mode, the optimization problem is solved based on the sequentially linearized model. When the path needs to be adjusted, the linearized model in the optimization control mode is used to obtain a more appropriate control input, ensuring that the UAV can cope with complex environments and mission requirements.

[0044] See Figure 4Step S3: Dynamically balance system performance and robustness based on the requirements of the unmanned ship's mission, the conditions of the ocean environment, and its own resource conditions. According to the complexity of the ocean environment and the type of mission, reasonably optimize the weights of each element in the unmanned ship path planning parameter matrix; design a cost function for the unmanned ship path planning, and by reasonably determining the value range of the penalty coefficient parameter, adjust the various parameters in the cost function under different ocean environments and mission scenarios to ensure that the unmanned ship path planning is balanced between performance and robustness. Specifically:

[0045] Step S31: Adjust the weights based on the intensity of wind, wave and current in the ocean environment, the distribution of obstacles, and the transport or monitoring mission of the unmanned vessel. In the transport mission, increase the weights of adjacent path points in areas with strong winds and waves to ensure that the unmanned vessel maintains a stable path and avoids damage to the cargo. In the monitoring mission, adjust the weights of path points based on the importance of the monitoring area to ensure comprehensive monitoring while improving robustness.

[0046] Step S32: Design a cost function for the path planning of the unmanned ship. By reasonably determining the value range of the penalty coefficient parameter, adjust the parameters in the cost function under different marine environments and mission scenarios. The cost function for the path planning of the unmanned ship is:

[0047]

[0048] Among them, x ref,k is the state vector corresponding to the reference path point, Q k The matrix is ​​a weight matrix that is dynamically adjusted according to the surrounding environment of the waypoint, which is related to the complexity of the environment and the task requirements. The R matrix is ​​also a weight matrix that is used to limit the energy consumption of the control input. i is the penalty coefficient, and its value range is reasonably determined by the relationship between stability and interference bound; Φ(x N ) is a function of the state of the unmanned ship at the terminal moment N, which is used to consider the constraints or targets of the terminal state. It is a function of the deviation between the position of the unmanned ship at the terminal moment and the target position, or a constraint function for the terminal speed and heading state of the unmanned ship; ω i (s;t k ) represents the unmanned ship at time s, the range of s is from t k to t k +T, the i-th interference vector received.

[0049] See Figure 5,Step S4: Construct a simulation environment that matches the marine mission scenario in the actual execution of the unmanned ship, and obtain detailed results by executing path planning; in the scene setting link, comprehensively consider the task-related factors. During the execution of path planning, use the improved fusion method to evaluate the impact of the current wind, wave and current interference on the state of the unmanned ship at each sampling moment based on the uncertainty model constructed in the early stage. Then, use the optimized control strategy to determine the control input, update the state through the unmanned ship dynamics model, and record the key information of the path trajectory, navigation time, and control input sequence in detail throughout the process. Analyze the simulation results and verify the effectiveness. Specifically:

[0050] Step S41: Setting simulation scene parameters, ω k Obeying the normal distribution N(0,0.1), the parameters are set based on the actual performance of the unmanned ship to ensure that the simulation is within the actual operation range, where the maximum speed of the unmanned ship v max =5m / s, minimum turning radius r min =10m, the control input constraint is the thruster thrust δ T ∈[-1000,1000]N, rudder angle δ R ∈[-30 0 ,30 0 ]; Multiple obstacles are randomly distributed in the driving area, and their positions and shapes are determined according to the actual environment;

[0051] Step S42: At each sampling time k, based on the uncertainty model improved in step S1, consider the current wind, wave and current interference ω k The control input is determined based on the control strategy optimized in step S2 to determine the state of the unmanned ship. If the unmanned ship is in open waters and the interference is small, the control input is calculated based on the simple control mode in the dual-mode control strategy combined with the successive linearization model. If the unmanned ship is close to a port or a complex area and faces large interference, the control input is switched to the optimization control mode, and the optimization problem is solved based on the successive linearization model to obtain the optimal control input. Then, the state of the unmanned ship is updated through the unmanned ship dynamics model, and information such as the path trajectory, navigation time, and control input sequence are recorded. This process is repeated until the unmanned ship reaches the target position or meets the termination condition, and a complete path planning result including detailed data such as the actual path, arrival time at the target, and control input at each moment is obtained to verify the path planning effect.

[0052] See Figure 6 The present invention provides an unmanned vessel path planning system 100 based on fusion model predictive control, the system comprising:

[0053] The external environment construction module 101 is used to model and process the uncertainty of external interference in the unmanned ship's marine environment, define interference boundary parameters, consider the maximum possible value range of external interference under a certain probability level, optimize the calculation of the uncertain disturbance set, determine the scope of the impact of external interference on the unmanned ship's state, and enable the unmanned ship's path planning to fully consider uncertainty;

[0054] The fusion model predictive control module 102 is used to build a dual-mode control strategy based on the real-time status of the unmanned vessel and changes in the ocean environment. A simple control strategy is used in the safe area to ensure stable navigation. Outside the safe area, an optimization problem is solved to obtain the optimal control input to cope with complex situations. At the same time, a collaborative successive linearization method is introduced to reduce the computational complexity of the dynamic model. Under different control modes, the optimization solution is further performed based on the linear time-varying model.

[0055] The path planning module 103 is used to dynamically balance system performance and robustness based on the requirements of the unmanned vessel's mission, the conditions of the marine environment, and its own resource conditions. The weights of the elements in the unmanned vessel's path planning parameter matrix are rationally optimized according to the complexity of the marine environment and the type of mission. The cost function for the unmanned vessel's path planning is designed. By rationally determining the value range of the penalty coefficient parameter, the various parameters in the cost function are adjusted under different marine environments and mission scenarios to ensure that the unmanned vessel's path planning strikes a balance between performance and robustness.

[0056] The simulation verification module 104 is used to construct a simulation environment that matches the marine mission scenario in the actual execution of the unmanned ship, and obtain detailed results by executing path planning; in the scene setting link, the task-related factors are fully considered, and in the process of executing path planning, the improved fusion method is used to evaluate the impact of the current wind, wave and current interference on the state of the unmanned ship at each sampling moment based on the uncertainty model constructed in the early stage, and then determine the control input with the help of the optimized control strategy, update the state through the unmanned ship dynamics model, and record the path trajectory, navigation time, and key information of the control input sequence in the whole process in detail, analyze the simulation results, and verify the effectiveness.

Claims

1. A path planning method for an unmanned vessel based on fusion model predictive control, characterized in that: The following steps are involved: Step S1: Model and process the uncertainty of external interference in the unmanned ship's marine environment, define interference boundary parameters, consider the maximum possible value range of external interference under a certain probability level, optimize the calculation of the uncertain disturbance set, determine the scope of the impact of external interference on the unmanned ship's state, and make the unmanned ship path planning fully consider uncertainty; Step S2: A dual-mode control strategy is constructed based on the real-time status of the unmanned vessel and changes in the ocean environment. A simple control strategy is used in the safe area to ensure stable navigation. Outside the safe area, an optimization problem is solved to obtain the optimal control input to cope with complex situations. At the same time, a collaborative successive linearization method is introduced to reduce the computational complexity of the dynamic model. Under different control modes, the optimization solution is further performed based on the linear time-varying model. Step S3: Dynamically balance system performance and robustness based on the requirements of the unmanned ship's mission, the conditions of the ocean environment, and its own resource conditions. According to the complexity of the ocean environment and the type of mission, the weights of each element in the unmanned ship's path planning parameter matrix are reasonably optimized. Design a cost function for the path planning of the unmanned vessel. By reasonably determining the value range of the penalty coefficient parameter, adjust the parameters in the cost function under different marine environments and mission scenarios to ensure that the path planning of the unmanned vessel strikes a balance between performance and robustness. Step S4: Construct a simulation environment that matches the marine mission scenario in the actual execution of the unmanned ship, and obtain detailed results by executing path planning; in the scene setting link, comprehensively consider the task-related factors, and in the process of executing path planning, use the improved fusion method to evaluate the impact of the current wind, wave and current interference on the state of the unmanned ship at each sampling moment based on the uncertainty model constructed in the early stage, and then determine the control input with the help of the optimized control strategy, update the state through the unmanned ship dynamics model, and record the path trajectory, navigation time, and key information of the control input sequence in the whole process in detail, analyze the simulation results, and verify the effectiveness.

2. The unmanned vessel path planning method based on fusion model predictive control according to claim 1, characterized in that: The step S1 specifically includes: Step S11: Define the interference boundary parameters of the external interference of the unmanned ship's marine environment, where the interference of the marine environment on the unmanned ship is ω i (t), define σ max is the maximum value of interference at the 95% confidence level, and the interference bound ρ i To express the interference ω i (t) intensity range, when ρ i ≤ρ -i When the ocean environment is considered suitable for unmanned boats to operate, otherwise it is considered unsuitable for unmanned boats to operate. -i is defined as: Among them, the positive definite matrix Q i It is the weight matrix related to the performance of the unmanned ship system, reflecting the importance of the unmanned ship position and tracking error performance indicators; the positive definite matrix P i is the weighted norm matrix of the state parameters of the unmanned ship system, reflecting whether the unmanned ship meets the stability requirements; α i and ε i is the design parameter of the unmanned ship system terminal, which is determined according to the system design and stability requirements; T is the prediction time domain parameter, which determines the time range of future states considered in path planning; L i It is a constant related to the unmanned ship system model and is related to the nonlinear characteristics of the unmanned ship dynamics model; the matrix eigenvalue λ and are the minimum and maximum eigenvalues ​​of the matrix; Step S12: Optimize the calculation of the uncertain disturbance set to determine the impact range of external disturbance on the state of the unmanned ship. The offline dynamic model of the unmanned ship is x k+1 =f(x k ,u k ,ω k ), where x k is the state vector of the unmanned ship system at time k, including the position, speed, and heading information of the unmanned ship, u k is the control input vector, including the rudder angle command and thrust force, ω k is the interference of the ocean environment; the offline dynamic model of the unmanned ship is linearized and approximated as A k 、B k and E k is the matrix related to the system state and control input, obtained by linearizing the dynamic model at the current state; Assume that the uncertain perturbation dynamic equation is Δω k+1 =F k Δω k +G k ξ k , F k and G k is a matrix related to system dynamics and disturbance characteristics, ξ k For ω k The random noise vector associated with the probability distribution; define the uncertain perturbation set X Δ (k) = {Δω k :||Δω k ||≤σ max },calculate Where W k is a compact set associated with random noise, whose size is determined by the interference ω k The probability distribution is determined by real-time monitoring and calculation of X Δ (k) and X Δ (k+1), adjust the control strategy according to its changing trend, and increase the control input adjustment amplitude when the disturbance set increases to keep the unmanned ship sailing stably.

3. The unmanned vessel path planning method based on fusion model predictive control according to claim 1, characterized in that: The step S2 specifically includes: Step S21: Introduce the dual-mode control strategy. When the state of the unmanned ship meets the When the unmanned ship is in the safe area, the control strategy based on linear feedback is adopted, which is determined by system stability analysis and performance index design; the sensor is used to monitor the state of the unmanned ship in real time, and the calculation and with ε i Compare and decide whether to switch the control mode; When the unmanned ship approaches an obstacle or deviates from the planned route, that is, the state exceeds the safe area, it switches to the optimized control mode. In the optimized control mode, the interference ω is set. k The probability distribution of k ), add the constraint P(ω k ∈W k )≥p0, p0 is the preset probability threshold, which is set according to the reliability requirements of the task; the control input u is retained min ≤u k ≤u max and state x min ≤x k ≤x max Constraints, where u min and u max are the lower and upper limits of the control input, which depend on the physical limitations of the UAV actuator, x min and x max The reasonable range of the unmanned ship state; determine the optimization problem: in, tk is the moment value, and the definitions of matrices T, Q, R, and P are the same as those in step S11; Step S22: The real-time state of the unmanned ship and the environment are coordinated using a successive linearization processing model, and the nonlinear dynamic model of the unmanned ship is processed at the sampling time k. Linearize and obtain the initial control input trajectory u at the current moment by translating the optimal control input sequence at the previous moment 0 (i|k), apply this initial control input trajectory to obtain the initial state trajectory x 0 (i|k), the interference input uses the predicted mean Then the nonlinear dynamic model is linearized to obtain x(i+1|k)=x 0 (i+1|k)+A(i|k)Δx(i|k)+B(i|k)Δu(i|k)+C(i|k)Δω(i|k), where A(i|k), B(i|k), and C(i|k) are Jacobian matrices; Step S23: Under the dual-mode control strategy, the path planning is carried out in coordination with the model after successive linearization according to the real-time status and environment of the unmanned ship; within the safe area, the control input is calculated using the simple model after successive linearization to reduce the consumption of computing resources; in the optimization control mode, the optimization problem is solved based on the successive linearization model. When the path needs to be adjusted, a more appropriate control input is obtained based on the linearization model in the optimization control mode to ensure that the unmanned ship can cope with complex environments and mission requirements.

4. The unmanned vessel path planning method based on fusion model predictive control according to claim 1, characterized in that: The step S3 specifically includes: Step S31: Adjust the weights based on the intensity of wind, wave and current in the ocean environment, the distribution of obstacles, and the transport or monitoring mission of the unmanned vessel. In the transport mission, increase the weights of adjacent path points in areas with strong winds and waves to ensure that the unmanned vessel maintains a stable path and avoids damage to the cargo. In the monitoring mission, adjust the weights of path points based on the importance of the monitoring area to ensure comprehensive monitoring while improving robustness. Step S32: Design a cost function for the path planning of the unmanned ship. By reasonably determining the value range of the penalty coefficient parameter, adjust the parameters in the cost function under different marine environments and mission scenarios. The cost function for the path planning of the unmanned ship is: Among them, x ref,k is the state vector corresponding to the reference path point, Q k The matrix is ​​a weight matrix that is dynamically adjusted according to the surrounding environment of the waypoint, which is related to the complexity of the environment and the task requirements. The R matrix is ​​also a weight matrix that is used to limit the energy consumption of the control input. i is the penalty coefficient, and its value range is reasonably determined by the relationship between stability and interference bound; Φ(x N ) is a function of the state of the unmanned ship at the terminal moment N, which is used to consider the constraints or targets of the terminal state. It is a function of the deviation between the position of the unmanned ship at the terminal moment and the target position, or a constraint function for the terminal speed and heading state of the unmanned ship; ω i (s;t k ) represents the unmanned ship at time s, the range of s is from t k to t k +T, the i-th interference vector received.

5. The unmanned vessel path planning method based on fusion model predictive control according to claim 1, characterized in that: The step S4 specifically includes: Step S41: Setting simulation scene parameters, ω k Obeying the normal distribution N(0,0.1), the parameters are set based on the actual performance of the unmanned ship to ensure that the simulation is within the actual operation range, where the maximum speed of the unmanned ship v max =5m / s, minimum turning radius r min =10m, the control input constraint is the thruster thrust δ T ∈[-1000,1000]N, rudder angle δ R ∈[-30°,30°]; multiple obstacles are randomly distributed in the driving area, and their positions and shapes are determined according to the actual environment; Step S42: At each sampling time k, based on the uncertainty model improved in step S1, consider the current wind, wave and current interference ω k The control input is determined based on the control strategy optimized in step S2 to determine the state of the unmanned ship. If the unmanned ship is in open waters and the interference is small, the control input is calculated based on the simple control mode in the dual-mode control strategy combined with the successive linearization model. If the unmanned ship is close to a port or a complex area and faces large interference, the control input is switched to the optimization control mode, and the optimization problem is solved based on the successive linearization model to obtain the optimal control input. Then, the state of the unmanned ship is updated through the unmanned ship dynamics model, and information such as the path trajectory, navigation time, and control input sequence are recorded. This process is repeated until the unmanned ship reaches the target position or meets the termination condition, and a complete path planning result including detailed data such as the actual path, arrival time at the target, and control input at each moment is obtained to verify the path planning effect.

6. An unmanned vessel path planning system 100 based on fusion model predictive control, characterized in that: The system includes: The external environment construction module 101 is used to model and process the uncertainty of external interference in the unmanned ship's marine environment, define interference boundary parameters, consider the maximum possible value range of external interference under a certain probability level, optimize the calculation of the uncertain disturbance set, determine the scope of the impact of external interference on the unmanned ship's state, and enable the unmanned ship's path planning to fully consider uncertainty; The fusion model predictive control module 102 is used to build a dual-mode control strategy based on the real-time status of the unmanned vessel and changes in the ocean environment. A simple control strategy is used in the safe area to ensure stable navigation. Outside the safe area, an optimization problem is solved to obtain the optimal control input to cope with complex situations. At the same time, a collaborative successive linearization method is introduced to reduce the computational complexity of the dynamic model. Under different control modes, the optimization solution is further performed based on the linear time-varying model. The path planning module 103 is used to dynamically balance system performance and robustness based on the requirements of the unmanned vessel's mission, the conditions of the marine environment, and its own resource conditions. The weights of the elements in the unmanned vessel's path planning parameter matrix are rationally optimized according to the complexity of the marine environment and the type of mission. The cost function for the unmanned vessel's path planning is designed. By rationally determining the value range of the penalty coefficient parameter, the various parameters in the cost function are adjusted under different marine environments and mission scenarios to ensure that the unmanned vessel's path planning strikes a balance between performance and robustness. The simulation verification module 104 is used to construct a simulation environment that matches the marine mission scenario in the actual execution of the unmanned ship, and obtain detailed results by executing path planning; in the scene setting link, the task-related factors are fully considered, and in the process of executing path planning, the improved fusion method is used to evaluate the impact of the current wind, wave and current interference on the state of the unmanned ship at each sampling moment based on the uncertainty model constructed in the early stage, and then determine the control input with the help of the optimized control strategy, update the state through the unmanned ship dynamics model, and record the path trajectory, navigation time, and key information of the control input sequence in the whole process in detail, analyze the simulation results, and verify the effectiveness.

Images