An intelligent perception-based unmanned ship navigation state control method and system

Abstract

The application relates to the technical field of unmanned ship navigation control, and discloses an unmanned ship navigation state control method and system based on intelligent sensing. Multidimensional data of a navigation environment is acquired, and a multi-dimensional data fusion technology is used to construct an environment state matrix, so that discrete environment elements are converted into a structured matrix expression. In an initial path generation stage, data acquisition value evaluation is integrated, obstacle avoidance requirements are considered, and a high-value detection area is actively covered. In a correction path stage, a multi-target cost function including energy consumption, threat degree and path length is constructed, so that real-time path optimization under a dynamic environment is realized. In a propulsion control link, the propulsion force and rudder angle parameters are calculated by comprehensively considering the unmanned ship posture, ship speed and ocean current speed. The method solves the contradiction among real-time dynamic obstacle avoidance, data acquisition efficiency and energy consumption optimization by cooperating the global-local double-layer path planning with the propulsion force and rudder angle control of the unmanned ship.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned ship navigation control, and particularly relates to an unmanned ship navigation state control method and system based on intelligent perception. BACKGROUND

[0002] Digital twin technology is a digital concept and technical means, which is based on and core of the integration of data and models, and simulates, verifies, predicts and controls the whole life cycle process of physical entities through real-time and accurate construction of physical objects in digital space based on data fusion and analysis prediction. The development of digital twin technology provides a new solution for virtual-real fusion and real-time interaction, iterative operation and optimization of the channel, and digital transformation and intelligent upgrading of all factors of the channel. The key lies in the acquisition of channel depth measurement, sensor perception, channel maintenance and operation history data, and ultimately realizes the simulation process of multi-physical quantity, multi-scale and multi-probability.

[0003] The unmanned ship has the characteristics of information perception, communication navigation, route planning and autonomous navigation, and has incomparable advantages over traditional ships in channel data collection, autonomous navigation and positioning, providing strong support for data collection of digital twin channel construction. First, it can efficiently and accurately complete the channel data collection task and provide real-time and reliable data support for the construction of digital twin channel. In addition, the real-time perception and communication capability of the unmanned ship enables the channel data to be quickly transmitted to the digital twin platform, supporting dynamic modeling and simulation of the channel and providing a scientific basis for channel management. Secondly, through autonomous navigation and intelligent obstacle avoidance, the unmanned ship can safely and stably operate in complex and variable channel environments, ensuring the coverage and accuracy of data collection.

[0004] Therefore, how to accurately control the navigation of the unmanned ship plays an important role in the establishment of the digital twin channel. SUMMARY

[0005] To solve the above technical problems, the present application provides an unmanned ship navigation state control method based on intelligent perception, which comprises the following steps:

[0006] S1: obtaining the navigation environment information of the unmanned ship during navigation; the navigation environment information includes static obstacle position, static obstacle shape, AIS ship dynamic information, unmanned ship attitude, water depth and current speed;

[0007] S2: constructing an environment state matrix according to the navigation environment information;

[0008] S3: obtaining the initial path of the unmanned ship navigation through the improved weighted Voronoi diagram according to the starting position, ending position, static obstacle position, static obstacle shape and data collection priority of the unmanned ship;

[0009] S4: based on the initial path of the unmanned ship sailing, combining the environment state matrix, energy consumption and threat degree evaluation of the unmanned ship, an improved algorithm is used to obtain a corrected path of the unmanned ship sailing;

[0010] S5: at the current position of the unmanned ship, the propulsion force and rudder angle of the unmanned ship are determined by comprehensively considering the attitude, speed and current speed of the unmanned ship;

[0011] S6: the propulsion force and rudder angle are used to control the unmanned ship to sail according to the corrected path.

[0012] Preferably, the edge weight formula of the improved weighted Voronoi diagram is:

[0013] ;

[0014] Wherein, d safe (e) is the safety distance of edge e to the nearest obstacle; γ is the data value weight coefficient; P(x,y) represents the data collection priority of the unmanned ship at coordinate point (x,y).

[0015] Preferably, the calculation method of the data collection priority is:

[0016] P(x,y)=α×Δh(x,y)+β×Dship(x,y);

[0017] Wherein, Δh(x,y) is the water depth change rate of the unmanned ship at coordinate point (x,y), D ship is the ship density, and α and β are weight coefficients.

[0018] Preferably, the cost function Cost of the improved algorithm is

[0019] ;

[0020] Wherein, L path represents the path length, T k (t) represents the threat degree evaluation, E consumption represents the energy consumption of the unmanned ship, ω1 is the path length weight coefficient, ω2 is the threat degree evaluation weight coefficient, and ω3 is the energy consumption weight coefficient, respectively.

[0021] Preferably, the threat degree evaluation is calculated using the following formula:

[0022] ;

[0023] Wherein, d k (t) represents the real-time distance between the unmanned ship and obstacle k, v obs,k ​represents the speed of the obstacle k approaching the unmanned ship, v max represents the maximum speed of the unmanned ship.

[0024] Preferably, the energy consumption of the unmanned ship is calculated based on the propulsion force and the ship speed of the unmanned ship.

[0025] Preferably, in S5, the propulsion force and the rudder angle of the unmanned ship are determined by the MPC controller by comprehensively considering the unmanned ship attitude, the ship speed and the ocean current speed.

[0026] Preferably, the objective function of the MPC controller is:

[0027] ;

[0028] wherein v ship represents the actual sailing speed of the unmanned ship, v ref represents the expected speed of the unmanned ship, F thrust represents the propulsion force output by the propulsion system of the unmanned ship, and λ represents the energy consumption optimization weight.

[0029] The constraint condition of the MPC controller is:

[0030] ;

[0031] wherein (x, y) represents the current coordinate position of the unmanned ship, (x ref , y ref ) represents the expected coordinate position of the unmanned ship, and ε represents the path tracking error threshold.

[0032] Another aspect of the present application provides an intelligent perception-based unmanned ship sailing state control system, which executes any one of the intelligent perception-based unmanned ship sailing state control methods described above, and the control system comprises a sailing environment information acquisition module, an environment state matrix construction module, an unmanned ship sailing path planning module and an unmanned ship sailing control module.

[0033] The environment information acquisition module is used to acquire sailing environment information when the unmanned ship sails; the sailing environment information comprises static obstacle position, static obstacle shape, AIS ship dynamic information, unmanned ship attitude, water depth and ocean current speed.

[0034] The environment state matrix construction module is used to construct an environment state matrix according to the sailing environment information.

[0035] The unmanned ship navigation path planning module is configured to obtain an initial navigation path of the unmanned ship according to a starting position, an ending position, a static obstacle position, a static obstacle shape and a data collection priority of the unmanned ship by using an improved weighted Voronoi diagram; based on the initial navigation path of the unmanned ship, in combination with the environment state matrix, energy consumption and threat degree evaluation of the unmanned ship, an improved algorithm is used to obtain a corrected navigation path of the unmanned ship; and the propulsion force and the rudder angle of the unmanned ship are determined by comprehensively considering the attitude, the ship speed and the ocean current speed of the unmanned ship at the current position of the unmanned ship.

[0036] The unmanned ship navigation control module is configured to control the unmanned ship to navigate according to the corrected path by using the propulsion force and the rudder angle.

[0037] The embodiments of the present application have the following technical effects:

[0038] The unmanned ship navigation state control method provided by the present application realizes intelligent navigation in a complex environment through multi-stage path planning and dynamic adjustment mechanism. First, the navigation environment information of multi-dimensional data is obtained, and the construction of the environment state matrix uses multi-dimensional data fusion technology to convert discrete environmental elements into a structured matrix expression, providing a unified data interface for subsequent path planning. In the initial path generation stage, an improved weighted Voronoi diagram algorithm is introduced, and the data collection value evaluation is integrated, so that the path planning not only considers the obstacle avoidance requirement, but also actively covers the high-value detection area. In the corrected path stage, an enhanced algorithm is used to realize real-time path optimization in a dynamic environment by constructing a multi-objective cost function including energy consumption, threat degree and path length. In the propulsion control link, the propulsion force and the rudder angle parameters are accurately calculated by comprehensively considering the attitude, the ship speed and the ocean current speed of the unmanned ship. The method solves the contradiction between real-time obstacle avoidance, data collection efficiency and energy consumption optimization in the traditional algorithm through the cooperation of global-local double path planning and the propulsion force and rudder angle control of the unmanned ship. The global path guides the unmanned ship to cover the high-value area, the local dynamic adjustment ensures safe obstacle avoidance, and the ocean current power is used to realize energy self-balancing, thereby improving the comprehensive performance of the unmanned ship in a complex channel. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0040] Figure 1 is a flowchart of an intelligent perception-based unmanned ship navigation state control method provided by the embodiments of the present application. DETAILED DESCRIPTION

[0041] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work belong to the scope of protection of the present application.

[0042] In order to accurately control the navigation of the unmanned ship, the present application provides an unmanned ship navigation state control method based on intelligent perception. The method realizes efficient and safe navigation of the unmanned ship in a dynamic channel environment through multi-level perception, decision-making and control cooperation. The core is to build a "perception-decision-execution" closed-loop system, as shown in Figure 1 , which specifically includes the following steps:

[0043] S1: obtaining navigation environment information when the unmanned ship navigates; the navigation environment information includes static obstacle position, static obstacle shape, AIS ship dynamic information, unmanned ship attitude, water depth and current velocity;

[0044] The unmanned ship collects the navigation environment information in real time through multi-source sensors. The position of the static obstacle (such as the rock) and the shape of the static obstacle are obtained by analyzing the LiDAR point cloud data; the real-time position, speed and heading of the dynamic obstacle (such as other ships) are obtained through the AIS (Automatic Identification System); the attitude (heading angle, acceleration) of the unmanned ship is measured by the IMU (Inertial Measurement Unit); the water depth information is detected in real time by the ship-borne depth finder; and the current velocity is collected by the flow velocity sensor. These data are fused through space-time alignment and Kalman filtering to form a unified environment perception basis.

[0045] S2: constructing an environment state matrix according to the navigation environment information;

[0046] The environment state matrix E(t) is a digital abstraction of the navigation environment, and its structure is as follows:

[0047] ;

[0048] Among them, the static obstacle position and the static obstacle shape are stored in the form of coordinate set O static ; the dynamic obstacle O dynamic contains the real-time position, speed and heading of the AIS ship dynamic information; the water depth h(x, y) is modeled according to the gridding distribution; and the current velocity v current (x, y) is represented in the form of a vector field. This matrix provides dynamic updated environment input for subsequent path planning and control.

[0049] S3: obtaining an initial path of the unmanned ship through an improved weighted Voronoi diagram according to the start position, the end position, the static obstacle position, the static obstacle shape and the data collection priority of the unmanned ship;

[0050] Based on the start position, the end position and the static obstacle position of the unmanned ship, an improved weighted Voronoi diagram algorithm is used to generate a global initial path, i.e., an initial path of the unmanned ship. The traditional Voronoi diagram only considers the distance of the obstacle to generate a safe corridor. The present application introduces the data collection priority as part of the edge weight, so that the path is preferentially passed through the area with significant change in water depth or high ship density, and the data collection value and safety are considered. After the global path is generated, it is used as a reference for local dynamic adjustment.

[0051] Preferably, the edge weight formula of the improved weighted Voronoi diagram is:

[0052] ;

[0053] wherein d safe (e) is the safety distance of the edge e to the nearest obstacle, ensuring that the unmanned ship is away from the obstacle; γ is a data value weight coefficient, 0.1≤γ≤0.5, adjusting the influence of P(x,y) on path selection; P(x,y) represents the data collection priority of the unmanned ship at the coordinate point (x,y). The formula balances the safety of the path and the data collection value through double weight design. For example, in the area where the water depth of the channel changes frequently, the value of P(x,y) is high, and the path tends to pass through such an area to improve the data collection efficiency. By dynamically adjusting γ, different task requirements can be flexibly adapted. For example, in the data collection task, increase γ and set it to 0.5, so that the path is more biased towards the high-value area; in the emergency obstacle avoidance scene, reduce γ and set it to 0.1, to prioritize safety. This method significantly improves the adaptability and task orientation of the global path.

[0054] The traditional Voronoi diagram only uses the distance of the obstacle as the weight, which may cause the path to detour the low-value area. The present application introduces the data priority and integrates the channel monitoring demand into the path planning, so that the unmanned ship maximizes the data value under the premise of safety. This design is particularly suitable for the digital twin channel construction scene, which needs to consider data coverage and navigation efficiency.

[0055] In some embodiments, the calculation method of the data collection priority is:

[0056] P(x,y)=α×Δh(x,y)+β×D ship (x,y);

[0057] wherein, Ah(x, y) is the rate of change of water depth of the unmanned ship at the coordinate point (x, y), reflecting the fluctuation degree of the bottom topography of the channel, and is obtained by differentiating the historical water depth data. The area with high change rate may have reefs or siltation and needs to be monitored. ship (x, y) is the ship density, which is based on the AIS historical data to count the ship passing frequency per unit area, and the high-density area is usually the key node of the channel, which needs to strengthen data collection to support traffic management. Alpha and beta are weight coefficients, 0.6≤alpha≤0.8, 0.2≤beta≤0.4 and alpha+beta=1, which are used to balance the contribution of the two types of factors. For example, in the dredging operation scenario, alpha can be increased to focus on the change of water depth, and alpha=0.8, beta=0.2; in the port monitoring scenario, beta is increased to focus on the ship dynamics, and alpha=0.6, beta=0.4. By adjusting the weights, the priority calculation can adapt to different task requirements.

[0058] The formula converts the actual needs of channel management into quantifiable path planning parameters, enabling the unmanned ship to autonomously select high-value routes and improve the pertinence and efficiency of data collection.

[0059] S4: based on the initial path of the unmanned ship, combining the environmental state matrix, the energy consumption and threat degree evaluation of the unmanned ship, an improved algorithm is used to obtain the corrected path of the unmanned ship;

[0060] On the basis of the global path, the real-time environmental state matrix E(t) is combined to use the improved algorithm for local path optimization. The algorithm quantifies the risk of obstacles through threat degree evaluation and dynamically adjusts the path in combination with the energy consumption model. The threat degree is calculated by the real-time distance and approach speed of the obstacle and the unmanned ship, and the improved algorithm energy consumption model is constructed based on the relationship between the propelling force and the ship speed. Finally, the corrected path is output to ensure the dual goals of dynamic obstacle avoidance and energy consumption optimization.

[0061] In some embodiments, the cost function Cost of the improved algorithm is

[0062] ;

[0063] wherein, L path represents the path length, which directly affects the sailing time; T k (t) represents the threat degree evaluation, which quantifies the real-time threat of all obstacles to the unmanned ship, and is calculated by the distance and approach speed of the obstacle; E consumptionThe energy consumption of the unmanned ship is represented by an integral model based on the product of the propulsion force and the ship speed, reflecting the energy consumption in the navigation process; ω1 is a path length weight coefficient, ω2 is a threat assessment weight coefficient, and ω3 is an energy consumption weight coefficient, respectively, ω1 + ω2 + ω3 = 1, for adjusting the priority of each target. For example, ω2 is increased to prioritize obstacle avoidance in a high-threat environment, and ω1 = 0.3, ω2 = 0.5, and ω3 = 0.2 are set; ω3 is increased to optimize energy consumption in a long-distance mission, and ω1 = 0.3, ω2 = 0.2, and ω3 = 0.5 are set.

[0064] The traditional algorithm takes path length as the main optimization target, but needs to deal with obstacle threats and energy consumption restrictions in dynamic channels. The present application integrates the uncertainty of the dynamic environment and the economy of the task into path decision-making by introducing threat and energy consumption terms. The threat assessment updates the obstacle state in real time, and the energy consumption model dynamically adjusts the propulsion force requirement in combination with the ocean current, making the path planning more adaptive and significantly improving the robustness of local path planning.

[0065] In local path re-planning, the algorithm traverses the candidate nodes near the global path, and calculates the Cost value of each potential path. For example, if a path is shorter but close to a ship approaching at high speed (∑T k (t) is high), its total cost may be higher than that of a slightly longer but safer path. At the same time, the algorithm predicts the energy consumption E consumption of the path, and if a path needs to frequently sail against the current, resulting in a sharp increase in energy consumption, it will be suppressed by the weight ω3. Finally, the path with the minimum total cost is selected as the correction result.

[0066] In some embodiments, the threat assessment is calculated using the following formula:

[0067] ;

[0068] Where d k (t) represents the real-time distance between the unmanned ship and obstacle k, which is calculated in real time through LiDAR or AIS data; v obs,k represents the speed at which obstacle k approaches the unmanned ship, which is derived from the difference between the speed and heading vector provided by AIS; and v max represents the maximum speed of the unmanned ship, i.e., the highest speed allowed by the unmanned ship's power system, used to normalize the influence of the approach speed.

[0069] The core of the threat assessment is to identify high-risk obstacles that are close and approach quickly. In the formula, gives a higher threat value to close-range obstacles, while reflects the motion threat of the obstacle. For example, a ship approaching from the side at high speed may be judged as a high-risk target even if the current distance is far.

[0070] Traditional threat models often ignore the motion trend of obstacles, resulting in delayed obstacle avoidance decisions. The present invention introduces a proximity velocity term, enabling prediction of future obstacle positions and achieving proactive obstacle avoidance. For example, a ship that is moving away laterally has a negative v obs,k , indicating a low threat level, and the algorithm can allow the unmanned ship to maintain its original path, avoiding unnecessary detours.

[0071] During the local path planning cycle, the algorithm iterates through all detected obstacles, calculates their T k (t) values, and sums them up. For static obstacles (e.g., reefs), v obs,k = 0, and the threat level is determined solely by distance; for dynamic obstacles (e.g., ships), both factors contribute. When T k (t) exceeds a pre-set threshold, path re-planning is triggered, ensuring that the unmanned ship avoids risks in advance. By linearly combining obstacle distance and proximity velocity, the real-time threat level of dynamic obstacles is quantified.

[0072] In some embodiments, the energy consumption of the unmanned ship is calculated based on its propulsion force and ship speed.

[0073] For example, the calculation of the energy consumption of the unmanned ship is based on the dynamic relationship between the propulsion force and the ship speed, and the model is:

[0074] ;

[0075] The energy consumption for the entire journey is quantified by integrating the product of the propulsion force and the ship speed.

[0076] The propulsion force F thrust represents the thrust output of the propeller, which is calculated by the MPC controller. The ship speed v ship represents the actual sailing speed of the unmanned ship, which is measured by the fusion of IMU and GPS.

[0077] The greater the propulsion force or the higher the ship speed, the more energy is consumed per unit time. However, in actual sailing, the ship speed is significantly affected by ocean currents. For example, when sailing against the current, v ship= v prop+ v current , v prop is the propeller propulsion speed), the required propulsion force F thrust is smaller under the same ship speed, thereby reducing energy consumption.

[0078] In the path planning stage, the algorithm predicts the energy consumption of the candidate path: first, estimate v ship for each segment based on the path length and ocean current distribution, then back-propagate the required F thrust, through the dynamic model, and finally integrate the time to get the total energy consumption. For example, a path against the current may be preferred due to low propulsion force requirements, even though its actual length is slightly longer.

[0079] The present application incorporates ocean current assistance into energy consumption calculation, so that the planned path not only considers geometric length, but also pays attention to energy economy. For example, in a strong ocean current area, the algorithm can generate a zigzag path to maximize the proportion of down-current segments, thereby reducing total energy consumption.

[0080] S5: At the current position of the unmanned ship, the propulsion force and rudder angle of the unmanned ship are determined by comprehensively considering the attitude, speed and ocean current speed of the unmanned ship.

[0081] Based on the current target point of the modified path, the propulsion force and rudder angle are calculated by an MPC (Model Predictive Control) controller. The MPC considers the ship speed, ocean current speed and attitude parameters to minimize the path tracking error and minimize the propulsion force energy consumption as the optimization goal, and dynamically adjusts the power output. For example, when the ocean current direction is consistent with the sailing direction, the propulsion force is reduced to utilize the ocean current kinetic energy; when the current is reversed, the propulsion force is appropriately increased to ensure the sailing speed. For the unmanned ship, it needs to meet the path tracking accuracy, power system limitation and energy consumption optimization at the same time. For example, when the ship speed deviates from the expectation due to sudden change of ocean current, the MPC adjusts the propulsion force and rudder angle to make the ship body return to the target path, while suppressing the propulsion force fluctuation to reduce energy consumption.

[0082] For example, the MPC performs the following steps:

[0083] State prediction: based on the current ship speed v ship , ocean current v current and the dynamics model, the ship body trajectory in the future few seconds is predicted.

[0084] Optimization solution: taking the minimization of the objective function as the criterion, the propulsion force and rudder angle sequence in the future time domain are calculated.

[0085] Instruction execution: only the first step control instruction (propulsion force and rudder angle) is adopted, and the remaining instructions are used as reference.

[0086] Feedback update: the actual ship position is measured by IMU and GPS, the prediction model error is corrected, and the next cycle is entered.

[0087] The MPC realizes the closed-loop control of "prediction-execution-correction" by online rolling optimization and incorporates environmental disturbance into control decision. For example, when a lateral ocean current is detected, the MPC adjusts the rudder angle in advance to compensate for the drift, rather than waiting for the error to accumulate and then reacting.

[0088] In some embodiments, in S5, the propulsion force and rudder angle of the unmanned ship are determined by the MPC controller by comprehensively considering the attitude, speed and ocean current speed of the unmanned ship.

[0089] In some embodiments, the objective function of the MPC controller is:

[0090] ;

[0091] wherein, v ship represents the actual sailing speed of the unmanned ship, v ref represents the desired speed of the unmanned ship, F thrust represents the propulsion force output by the propulsion system of the unmanned ship, and λ represents the energy consumption optimization weight, 0.01≤λ≤0.1.

[0092] The constraint condition of the MPC controller is:

[0093] ;

[0094] wherein, (x, y) represents the current coordinate position of the unmanned ship, (x ref , y ref ) represents the desired coordinate position of the unmanned ship, and ε represents the path tracking error threshold, i.e., the allowable ship position deviation threshold, ε=5.

[0095] In the objective function, the first term forces the actual ship speed to track the reference speed, avoiding path deviation due to speed mismatch; the second term λF 2 thrust suppresses the propulsion force fluctuation and reduces the energy consumption. The energy consumption optimization weight λ adjusts the priority of the two: when λ is high, the energy saving is emphasized, and λ is set to 0.08; when λ is low, the tracking accuracy is emphasized, and λ is set to 0.02.

[0096] In the optimization solution, the MPC needs to meet the dynamic constraint and the path error constraint at the same time. For example, if the ocean current causes the ship speed v ship to be lower than v ref , the MPC may moderately increase F thrust to compensate, but it is limited by F 2 thrust to avoid excessive energy consumption. At the same time, the path error constraint ensures that the adjusted ship position is always within the safe corridor.

[0097] The present application cooperates with the energy consumption term and the constraint to achieve Pareto optimality between accuracy and energy saving. For example, in the downstream sailing section, the MPC allows the ship speed to be slightly higher than v ref to utilize the ocean current kinetic energy, while reducing the propulsion force output, and the overall still satisfies the ε constraint.

[0098] S6: controlling the unmanned ship to sail according to the corrected path according to the propulsion force and the rudder angle.

[0099] The propulsion force and the rudder angle instructions output by the MPC are sent to the unmanned ship execution mechanism to drive the propeller and the rudder to act, so that the unmanned ship sails along the corrected path. At the same time, the sailing state is fed back to the perception layer in real time to form a closed-loop control.

[0100] Another aspect of the present application provides an intelligent perception-based unmanned ship navigation state control system, which executes any one of the intelligent perception-based unmanned ship navigation state control methods described above, and the control system comprises a navigation environment information acquisition module, an environment state matrix construction module, an unmanned ship navigation path planning module, and an unmanned ship navigation control module.

[0101] The environment information acquisition module is configured to acquire navigation environment information when the unmanned ship is navigating, and the navigation environment information comprises static obstacle position, static obstacle shape, AIS ship dynamic information, unmanned ship attitude, water depth, and ocean current speed.

[0102] The environment state matrix construction module is configured to construct an environment state matrix according to the navigation environment information.

[0103] The unmanned ship navigation path planning module is configured to obtain an initial navigation path of the unmanned ship by using an improved weighted Voronoi diagram according to the starting position, the ending position, the static obstacle position, the static obstacle shape, and the data acquisition priority of the unmanned ship, to obtain a corrected navigation path of the unmanned ship by using an improved A* algorithm based on the initial navigation path of the unmanned ship, in combination with the environment state matrix, the energy consumption, and the threat degree evaluation of the unmanned ship, to determine the propelling force and the rudder angle of the unmanned ship at the current position of the unmanned ship by comprehensively considering the unmanned ship attitude, the ship speed, and the ocean current speed.

[0104] The unmanned ship navigation control module is configured to control the unmanned ship to navigate according to the corrected navigation path by using the propelling force and the rudder angle.

[0105] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present application.​

Claims

1. A method for controlling the navigation state of an unmanned surface vessel based on intelligent sensing, characterized in that, The control method includes the following steps: S1: Acquire navigation environment information during unmanned vessel navigation; the navigation environment information includes the position and shape of static obstacles, AIS vessel dynamic information, unmanned vessel attitude, water depth and ocean current speed; S2: Construct an environmental state matrix based on the navigation environment information; S3: Based on the starting position, ending position, static obstacle position, static obstacle shape, and data acquisition priority of the unmanned vessel, the initial navigation path of the unmanned vessel is obtained through an improved weighted Voronoi diagram. The improved formula for edge weights in a weighted Voronoi diagram is: ； Where, d safe (e) represents the safe distance from edge e to the nearest obstacle; γ is the data value weighting coefficient; P(x,y) represents the data collection priority of the unmanned vessel at coordinate point (x,y); The method for calculating the data acquisition priority is as follows: P(x,y)=α×Δh(x,y)+β×D ship (x,y); Where Δh(x,y) is the rate of change of water depth of the unmanned vessel at coordinate point (x,y), and D ship Where α is the ship density, and β are weighting coefficients; S4: Based on the initial navigation path of the unmanned surface vessel (USV), and combined with the environmental state matrix, the USV's energy consumption, and threat assessment, an improved approach is adopted. The algorithm obtains the corrected navigation path for the unmanned vessel. S5: Based on the current position of the unmanned vessel, determine the propulsion force and rudder angle of the unmanned vessel by combining its attitude, speed and ocean current speed. S6: Control the unmanned vessel to navigate along the corrected path using the propulsion force and rudder angle.

2. The method for controlling the navigation status of an unmanned vessel based on intelligent perception according to claim 1, characterized in that, The improvements The cost function of the algorithm is: ； Among them, L path T represents the path length. k (t) represents the threat assessment, E consumption The energy consumption of the unmanned vessel is represented by ω1, which is the path length weight coefficient, ω2 is the threat assessment weight coefficient, and ω3 is the energy consumption weight coefficient.

3. The method for controlling the navigation status of an unmanned vessel based on intelligent perception according to claim 2, characterized in that, The threat assessment is calculated using the following formula: ； Where, d k (t) represents the real-time distance between the unmanned vessel and obstacle k, v obs,k v represents the speed at which obstacle k approaches the unmanned boat. max This indicates the maximum speed of the unmanned vessel.

4. The method for controlling the navigation status of an unmanned vessel based on intelligent perception according to claim 1, characterized in that, The energy consumption of the unmanned vessel is calculated based on its propulsion and speed.

5. The method for controlling the navigation status of an unmanned vessel based on intelligent perception according to claim 1, characterized in that, In S5, the MPC controller integrates the unmanned vessel's attitude, speed, and ocean current speed to determine the unmanned vessel's propulsion and rudder angle.

6. The method for controlling the navigation status of an unmanned vessel based on intelligent perception according to claim 5, characterized in that, The objective function of the MPC controller is: ； Among them, v ship The actual speed of the unmanned vessel, v ref F represents the desired speed of the unmanned vessel. thrust λ represents the propulsion force output by the unmanned vessel propulsion system, and λ represents the energy consumption optimization weight. The constraints of the MPC controller are: ； Where (x, y) represents the current coordinates of the unmanned surface vessel, (x...y ... ref ,y ref ) represents the desired coordinate position of the unmanned vessel, and ε represents the path tracking error threshold.

7. A navigation status control system for unmanned vessels based on intelligent sensing, characterized in that, The method for controlling the navigation status of an unmanned vessel based on intelligent perception, as described in any one of claims 1-6, comprises a navigation environment information acquisition module, an environment state matrix construction module, an unmanned vessel navigation path formulation module, and an unmanned vessel navigation control module. The environmental information acquisition module is used to acquire navigation environment information during the unmanned vessel's navigation; the navigation environment information includes the position and shape of static obstacles, AIS vessel dynamic information, unmanned vessel attitude, water depth, and ocean current speed. The environmental state matrix construction module is used to construct an environmental state matrix based on the navigation environment information. The unmanned vessel navigation path planning module is used to obtain the initial navigation path of the unmanned vessel based on the starting position, ending position, static obstacle position, static obstacle shape and data acquisition priority of the unmanned vessel through an improved weighted Voronoi diagram. Based on the initial navigation path of the unmanned surface vessel (USV), and combined with the environmental state matrix, the USV's energy consumption, and threat assessment, an improved approach is adopted. The algorithm obtains the corrected path for the unmanned vessel's navigation; at the unmanned vessel's current position, it determines the unmanned vessel's propulsion and rudder angle by combining the unmanned vessel's attitude, speed, and ocean current speed. The unmanned vessel navigation control module is used to control the unmanned vessel to navigate according to the corrected path using the propulsion force and rudder angle.

Images