Unmanned ship route planning method and storage medium based on geodesic
By equivalently equating the environmental factors in the unmanned ship path planning into Riemann surfaces, using geodesic algorithm to generate the unmanned ship's route, the problems of optimal route evaluation and wind and wave interference processing in the existing technology are solved, and the problem of increasing the problem of information of information is achieved. Safety and energy efficiency optimize navigation under high sea conditions.
Patent Information
- Application Number
- CN202211217757.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-09-30
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2042-09-30
AI Technical Summary
When existing unmanned ship path planning algorithms face random interference such as wind and waves, it is difficult to generate the optimal route, and the evaluation criteria are mainly focused on the algorithm's calculation time and convergence, and lack effective evaluation of the optimal route.
The geodesic-based route planning method is used to equivalently use external environmental factors and rudder input to Riemann surfaces, and the motion trajectory of the unmannated ship is obtained through vector synthesis, and the triangular mesh model is used to represent wind and waves and other interferences in Riemann space. , find the geodesic line between two points on the curved surface as the route.
In high sea conditions, through the optimization of motion trajectory of unconstrained mechanical systems, the unmanned ship can safely and reliably reach the destination according to the expected route, reduce energy consumption, and avoid complex solutions to contact coefficients and differential equations.
Smart Images

Figure CN115657665B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of route planning and design, and in particular to a method and storage medium for unmanned ship route planning based on geodesic lines. Background Art
[0002] The system of unmanned ships is a complex system, which contains multiple functional modules. Route planning is one of the important modules of the system. When unmanned ships sail at sea, they are required to sail along a specific route, that is, the expected trajectory, from the perspectives of economy and safety. However, since ships are inevitably affected by random interference such as wind, waves and currents, the ships will deviate from the planned track, which will not only consume more energy, but may even cause navigation accidents. Therefore, planning a reasonable route is of great significance to the navigation of unmanned ships.
[0003] The current technical problems are:
[0004] Although the path planning algorithms for unmanned ships, such as A* algorithm, artificial potential field method, genetic algorithm, ant colony algorithm, etc., have achieved good results, they all have their own problems and limitations. At present, path planning mainly focuses on the realization of obstacle avoidance function and the rapid generation of feasible paths. The main evaluation criteria rely on the algorithm calculation time and convergence, while the evaluation criteria of the optimal path itself and the selection of the optimal path are less involved. Summary of the invention
[0005] The present invention proposes a method for unmanned ship route planning based on geodesic lines, which can solve at least one of the above technical problems.
[0006] To achieve the above object, the present invention adopts the following technical solutions:
[0007] A method for unmanned ship route planning based on geodesic line includes the following steps:
[0008] S1. Equivalent the influence of external environmental factors on the unmanned ship to a Riemann surface;
[0009] S2, equating the influence of the rudder input and obstacles on the unmanned ship to a Riemann surface;
[0010] S3, vector synthesis of the tangent vectors generated by external environmental factors, rudder input and obstacles at any particle point on the surface;
[0011] S4. Obtain the geodesic line between two points on the surface as the planned route of the unmanned ship.
[0012] Furthermore, the step S1, equating the influence of external environmental factors on the unmanned ship to a Riemann surface specifically includes:
[0013] (1) Ocean waves
[0014] Taking ξ-η as a horizontal plane, the wave height can be expressed as:
[0015]
[0016] In the formula, a i is the amplitude of the i-th harmonic; ε i is the initial phase of the i-th harmonic, which is a random variable uniformly distributed between 0 and 2π; ω i is the angular frequency of the i-th harmonic; k i is the wave number of the ith harmonic, k i =ω i 2 / g, g is the acceleration of gravity; μ is the direction angle of the wave;
[0017] Under the dual effects of gravity and wind, the water flow deforms to form waves, and the Riemann space representation is the wave shape itself;
[0018] (2) Sea Breeze
[0019] The wind generated at sea is divided into two categories according to the time constant relative to the sailing time of the unmanned ship; the first type of sea breeze steady wind has a larger time period and its amplitude obeys the Rayleigh distribution; the influence of sea breeze steady wind on the movement of ships is related to the wind direction angle encountered by the ship. In Riemann geometry, the change of the unmanned ship's navigation trajectory by the inclined plane is consistent with the movement trajectory of the unmanned ship after the sea breeze blows on it. For different encountering wind direction angles, the steady wind is equivalent to inclined planes with different degrees of inclination; the second type of sea breeze turbulent wind is composed of countless harmonics, and its amplitude, direction and frequency all change randomly. The random wave theory is used to analyze its changing characteristics.
[0020] Furthermore, the S2, equating the influence of the rudder input and the obstacle on the unmanned ship to a Riemann surface, specifically includes:
[0021] (1) Rudder input control amount
[0022] When a ship is sailing, when the rudder blade is parallel to the direction of travel of the ship, the water forces on both sides of the rudder blade are equal, and the direction of movement of the ship will not be affected at this time; when the rudder blade is controlled by the steering wheel, a deflection angle is generated, and the water flow on both sides is no longer consistent, and a pressure difference is generated on the water-facing surface and the water-receiving surface, coupled with the friction between the water flow and the rudder blade, which pushes the ship to turn; assuming that the turning radius is R, the turning torque of the rudder propeller is equivalent to a conical rotating surface in Riemann geometry;
[0023] (2) Obstacles
[0024] Considering the safety of unmanned ship navigation, if the obstacle encountered by the ship is other ships, the equivalent three-dimensional graphics of the obstacle ship need to be expanded, and the direction and position information of the moving ship need to be obtained through GPS. The motion information of the dynamic obstacle is calculated through AIS and ARPA, and the risk of collision with the ship is predicted according to its speed and direction, so as to avoid collision.
[0025] According to the size, orientation, speed and direction of the obstacle, it is equivalent to a three-dimensional figure on the curved surface, which is expressed as a protruding cylinder on the plane. Its area is related to the length and width of the obstacle, its height is related to the volume of the obstacle, and its position on the plane is related to the speed and direction of its movement.
[0026] Furthermore, the S3, vector synthesis of the tangent vectors generated by the external environmental factors, the rudder input and the obstacle at any particle point on the curved surface, specifically includes:
[0027] The nonlinear mechanical system is presented in geometric space. The state position and velocity in the mechanical system are represented by the geometric manifold position space and tangent vector velocity space. The control input is represented by the manifold input space, and its motion trajectory is represented as the integral curve of the tangent vector in the manifold space.
[0028] The motion space of the unmanned ship is affected by various factors at a certain point. The tangent vector at the point satisfies the principle of vector synthesis, and a new space is generated after synthesis.
[0029] Furthermore, the step S4 of obtaining a geodesic line between two points on the curved surface as the planned route of the unmanned ship specifically includes:
[0030] The test area map was gray-scaled and divided into feasible and infeasible areas, and then vectorized into a triangular mesh model, represented by edges, faces, and points. The shore was represented as a convex surface with higher energy, which was expressed as the higher part of the surface. The river channel was represented as a concave surface with lower energy, which was expressed as the lower part of the surface. At the same time, random wind and wave interference was superimposed in the river channel to observe the route planning effect.
[0031] The obstacle ship is equivalent to a three-dimensional figure with a polygonal bottom in the map. The size of the figure is determined by the size of the target obstacle. The three-dimensional figure equivalent to the obstacle ship is expanded, and at the same time, it is predicted and judged whether there is a risk of collision with the ship according to its sailing speed and direction, so as to avoid collision.
[0032] Determine the starting point and the end point on the map. Next, find the geodesic from the starting point to the end point on the synthetic surface. This is achieved using the MMP algorithm and the Dijkstra algorithm.
[0033] The MMP algorithm uses the window propagation as a path to gradually cover the entire surface of the model, thereby calculating the geodesic distance and geodesic path from any point in the model to the source point;
[0034] The Dijkstra algorithm increases the shortest path length from the source point to the destination point, and generates the shortest path one by one.
[0035] On the other hand, the present invention further discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the above method.
[0036] It can be seen from the above technical scheme that the autonomous navigation track of unmanned ships is greatly disturbed in high sea conditions (≥4 sea conditions) due to the huge influence of external factors such as wind, waves, and currents. Inspired by the theory of Riemannian geometry, the unmanned ship route planning method based on geodesics of the present invention represents environmental interference such as wind, waves, and currents in Riemann space with a triangular mesh model, and turns the unmanned ship system into an unconstrained mechanical system for control. The motion trajectory of the system is a geodesic between two points on the Riemann surface, thereby planning the route of the unmanned ship.
[0037] The main innovation of the present invention is that it does not adopt the previous unmanned ship path planning method, but instead converts the environmental model into a Riemann surface, performs numerical calculations on it to obtain geodesics on the three-dimensional surface, and uses it as a planned route in the unmanned ship autonomous navigation system.
[0038] Compared with the prior art, the present invention has the following advantages:
[0039] (1) No longer limited to the force analysis and solution of nonlinear mechanical system equations, we discuss the use of manifold space to represent the forces of mechanical systems, equating the input of the system and the influence of the environment into a surface representation in Riemann space, and making the constrained mechanical system unconstrained.
[0040] (2) The optimal motion trajectory of an unconstrained mechanical system in Riemann space is the geodesic of Riemann space, which ensures that the system reaches its destination safely and reliably in a short time with minimal energy consumption along the expected route.
[0041] (3) The computer-based method of obtaining geodesics avoids the complicated work of obtaining connection coefficients and solving differential equations. In addition, the geodesic algorithms currently implemented by computers are relatively mature and can be selected according to system requirements.
[0042] (4) The model is represented in the form of a triangular mesh. In computer graphics, triangular meshes are often used to represent three-dimensional geometric models. They can be constructed from data obtained from a scanner. Data represented by triangular meshes is supported in many software and hardware to enable operations such as drawing and analysis. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 is a flow chart of the method of the present invention;
[0044] Figure 2 This is a schematic diagram of the equivalent of ocean waves;
[0045] Figure 3 This is a schematic diagram of sea breeze equivalent;
[0046] Figure 4 Enter the equivalent schematic for the rudder;
[0047] Figure 5 is an equivalent schematic diagram of obstacles;
[0048] Figure 6 A schematic diagram of the effects of wind, waves and rudder on the unmanned ship at a certain point;
[0049] Figure 7 Synthesize surface visualization results for the effects of wind, waves, rudders, and obstacles on unmanned ships;
[0050] Figure 8 A map of the test area;
[0051] Fig. 9 For the test area Figure 3 Corner gridding processing diagram;
[0052] Fig.10 To implement two geodesic algorithms under the test area map;
[0053] Fig.11 The operation time and calculation distance of the two algorithms. DETAILED DESCRIPTION
[0054] 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.
[0055] Using Riemannian geometry as a mathematical tool, general relativity believes that the gravitational force on celestial bodies is a manifestation of the geometric properties of space-time curvature caused by the existence of material mass. In curved space-time, objects still move along the shortest path, that is, the movement of objects must satisfy the geodesic equation in curved space-time (the shortest line between two points on the Riemann surface).
[0056] Inspired by the above ideas, the influence of external factors on the unmanned ship is equivalent to the obstruction of the movement of the object in the Riemannian geometry manifold space, and the track of the unmanned ship is the solution of the geodesic equation in the manifold space. Therefore, the force analysis and solution of the unmanned ship system are turned to the discussion of the establishment of various manifold spaces of Riemannian geometry and the solution of the geodesic equation, and then the position, speed and track curve of the unmanned ship are obtained.
[0057] Establish the state space equation of the system, solve the connection coefficient to obtain the geodesic differential equation, and it is very troublesome to obtain the geodesic by solving the differential equation. For the navigation control system of unmanned ships, since the rotation of the rudder and the speed of the engine are typical nonlinear inputs, and the effects of wind, waves and currents on the ship are time-varying, such nonlinear mechanical systems have non-deterministic and time-varying characteristics, which makes the system force very complex, and the connection coefficient term in the geodesic equation cannot be solved. Therefore, the embodiment of the present invention adopts a method of obtaining geodesics by computer. The geodesic algorithm uses the propagation of the window as a path to gradually cover the entire surface of the model, thereby calculating the geodesic distance and geodesic path from any point in the model to the source point.
[0058] Specifically, Figure 1 As shown, a method for unmanned ship route planning based on geodesic lines in an embodiment of the present invention includes the following steps:
[0059] S1. Equivalent the influence of external environmental factors on the unmanned ship to a Riemann surface;
[0060] S2, equating the influence of the rudder input and obstacles on the unmanned ship to a Riemann surface;
[0061] S3, vector synthesis of the tangent vectors generated by external environmental factors, rudder input and obstacles at any particle point on the surface;
[0062] S4. Obtain the geodesic line between two points on the surface as the planned route of the unmanned ship.
[0063] The following are specific instructions:
[0064] Step 1: The impact of external environmental factors such as wind, waves and currents on the unmanned ship is represented by an equivalent Riemann surface.
[0065] (1) Ocean waves
[0066] Wave types are generally generated by sea breezes, and some waves are generated by other factors such as tidal surges. These waves are superimposed on the sea surface to form a hill shape of different sizes and directions. The amplitude varies according to the strength of the sea breeze and the size of the surge, and it is impossible to use an accurate function to represent it. After statistically analyzing a large amount of observation data, it is found that waves can be treated as a stationary random process. In common numerical simulations, waves are generally composed of superpositions of sine and cosine waves, and their phase, amplitude, and period are generally randomly generated within a certain range.
[0067] Taking ξ-η as a horizontal plane, the wave height can be expressed as:
[0068]
[0069] In the formula, a i is the amplitude of the i-th harmonic; ε i is the initial phase of the i-th harmonic, which is a random variable uniformly distributed between 0 and 2π; ω i is the angular frequency of the i-th harmonic; k i is the wave number of the ith harmonic, k i =ω i 2 / g, g is the acceleration due to gravity; μ is the direction angle of the wave.
[0070] Under the dual effects of gravity and wind, the water flow deforms to form waves. The Riemann space representation is the wave shape itself, such as Figure 2 .
[0071] (2) Sea Breeze
[0072] The wind generated at sea is divided into two categories according to the time constant relative to the navigation time of the unmanned ship. The first type of sea breeze is steady stream wind with a larger time period, and the amplitude generally obeys the Rayleigh distribution. Its wind speed is large and lasts for a long time, so it is much larger than the parameters of the ship in the movement of the ship. It can be regarded as a wind blowing in one direction with a stable speed within a certain period of time. The impact of steady stream wind on the movement of the ship is related to the wind direction angle encountered by the ship. In Riemann geometry, the change of the navigation trajectory of the unmanned ship by the inclined plane is consistent with the movement trajectory of the unmanned ship after the sea breeze blows on it. For different wind direction angles encountered, the steady stream wind can be equivalent to inclined planes with different degrees of inclination (such as Figure 3 The second type of sea breeze is turbulent wind, which is generally composed of countless harmonics. Its amplitude, direction and frequency are all randomly changing. Its changing characteristics can be analyzed by random wave theory.
[0073] (3) Ocean current
[0074] Ocean currents are divided into steady currents and tidal currents. Steady currents are generally ocean currents with fixed directions and speeds, such as ocean currents. Tidal currents refer to the movement of seawater in the ocean due to tidal movement, which is typically manifested as a slow change in the direction of the ocean current. The model of ocean currents can be uniformly established based on constant magnitude and direction. For the unmanned ship studied in this invention, the draft is relatively shallow during navigation, so the influence of ocean currents can be ignored.
[0075] Step 2: The influence of rudder input and obstacles on the unmanned ship is represented by an equivalent Riemann surface.
[0076] (1) Rudder input control amount
[0077] When the unmanned boat is sailing at a certain speed, the driving force of the engine can be considered to be balanced with the resistance generated by the water flow and the ship, so it can be ignored. When the ship is sailing, when the rudder blade is parallel to the direction of travel of the ship, the water forces on both sides of the rudder blade are equal, which will not affect the direction of movement of the ship; when the rudder blade produces a deflection angle through the control of the steering wheel, the water flow on both sides is no longer consistent, and a pressure difference is generated between the water surface and the back surface. Coupled with the friction between the water flow and the rudder blade, the ship is pushed to turn. Assuming the turning radius is R, the turning torque of the rudder propeller is equivalent to a conical rotating surface in Riemann geometry, such as Figure 4 .
[0078] (2) Obstacles
[0079] When unmanned ships are sailing in the water, they will encounter various obstacles, which are not included in the global plan. Therefore, unmanned ships need to continuously obtain information about the surrounding environment through relevant sensors. At this time, it is necessary to equate the obstacle to a part of the surface and correct the local route. Considering the safety of unmanned ship navigation, if the obstacle encountered by the ship is other ships, the three-dimensional stereographic equivalent to the obstacle ship must be expanded. It is also necessary to obtain the direction and position information of the moving ship through GPS, calculate the movement information of the dynamic obstacle through AIS and ARPA, and predict whether there is a risk of collision with the ship based on its speed and direction, so as to avoid collision.
[0080] According to the size, position, speed and direction of the obstacle, it is equivalent to a three-dimensional figure on the surface, which is expressed as a protruding cylinder on the plane (such as Figure 5 ), the three-dimensional figure is randomly generated according to the size of the obstacle, and its position on the plane is related to the speed and direction of its movement.
[0081] Step 3: Surface synthesis of external environmental factors, rudders and obstacles.
[0082] The nonlinear mechanical system is displayed in the geometric space. The state (position, velocity) in the mechanical system can be represented by the geometric manifold position space and tangent vector velocity space. The control input is represented by the manifold input space, and its motion trajectory is represented as the integral curve of the tangent vector in the manifold space.
[0083] The motion space of the unmanned boat is affected by various factors at a certain point. The tangent vector at the point satisfies the principle of vector synthesis, and a new space is generated after synthesis. The effects of wind, wave, and rudder input surface are combined. Figure 6 A schematic diagram of the tangent vector synthesis at a certain point of the impact of the above three factors on the unmanned ship is given. Figure 7 The visualization results of the synthetic surface of the above three factors and obstacles are given.
[0084] Step 4: Find the geodesic between two points on the surface.
[0085] Map of the test area ( Figure 8 ) is gray-scaled and divided into feasible and infeasible areas, and then vectorized into a triangular mesh model, represented by edges, faces, and points, such as Fig. 9 As shown in the figure. The shore is represented by a convex surface with higher energy, which is expressed as the higher part of the curved surface; the river channel is represented by a concave surface with lower energy, which is expressed as the lower part of the curved surface. At the same time, random wind and waves and other interferences can be superimposed on the river channel to observe the effect of route planning.
[0086] The obstacle ship is equivalent to a three-dimensional figure with a polygonal bottom in the map. The size of the figure is mainly determined by the size of the target obstacle. Considering the navigation safety of ships, the three-dimensional figure equivalent to the obstacle ship must be expanded. At the same time, it is necessary to predict and judge whether there is a risk of collision with the ship based on its navigation speed and direction, so as to avoid collision.
[0087] Determine the starting point and the end point on the map. Next, we will find the geodesic from the starting point to the end point on the synthesized surface.
[0088] According to the accuracy of calculation, geodesic algorithms can be divided into two types. One is an approximate algorithm, which saves running space and improves the running efficiency of calculation at the expense of a certain accuracy. The classic Dijkstra algorithm is the most representative; while the other exact algorithm focuses on the accuracy of the required geodesic distance, which requires more computing space and consumes a higher computing time, causing a certain degree of resource waste. The representative algorithm is the MMP (Mitchell, Mount, Papadimitrious) algorithm. The main disadvantage of exact algorithms is that they generally have a large time or space complexity.
[0089] Considering the accuracy of geodesic calculation and the difficulty of computer implementation, the present invention selects the above two classic geodesic algorithms: MMP algorithm (precise algorithm) and Dijkstra algorithm (approximate algorithm).
[0090] The core idea of the MMP algorithm is to use the window propagation as a path to gradually cover the entire surface of the model, thereby calculating the geodesic distance and geodesic path from any point in the model to the source point. The core idea of the Dijkstra algorithm is to increase the shortest path length from the source point to the destination point, and gradually generate the shortest path. The simulation effect of the geodesic lines generated by the two algorithms is shown in the figure below. Fig.10 .
[0091] Fig.11 The running time and calculated geodesic distance of the two algorithms are given. It can be seen that the MMP algorithm is more accurate than the Dijkstra algorithm, and the geodesic line of the former can pass through the triangle, which is much smoother, and is a straight line between two points on the plane. However, in terms of running time, the MMP algorithm is not as efficient as the Dijkstra algorithm. Considering the actual navigation situation of the unmanned ship, the MMP algorithm is more suitable for global path planning.
[0092] The system's global path planning adopts the geodesic algorithm, which applies the "optimal and most economical" property of the geodesic to the navigation trajectory planning of the unmanned ship, which has great practical significance in saving fuel consumption and time.
[0093] In yet another aspect, the present invention further discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of any of the above methods.
[0094] On the other hand, the present invention further discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of any of the above methods.
[0095] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the steps of any method in the above embodiments.
[0096] It is understandable that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts in the above method.
[0097] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0098] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0099] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for unmanned ship route planning based on geodesic, characterized in that: The following steps are included: S1. Equivalent the influence of external environmental factors on the unmanned ship to a Riemann surface; S2, equating the influence of the rudder input and obstacles on the unmanned ship to a Riemann surface; S3, vector synthesis of the tangent vectors generated by external environmental factors, rudder input and obstacles at any particle point on the surface; S4, finding the geodesic line between two points on the surface as the planned route of the unmanned ship; S1, equating the influence of external environmental factors on the unmanned ship to a Riemann surface specifically includes: (1) Ocean waves Taking ξ-η as a horizontal plane, the wave height can be expressed as: In the formula, a i is the amplitude of the i-th harmonic; ε i is the initial phase of the i-th harmonic, which is a random variable uniformly distributed between 0 and 2π; ω i is the angular frequency of the i-th harmonic; k i is the wave number of the ith harmonic, k i =ω i 2 / g, g is the acceleration of gravity; μ is the direction angle of the wave; Under the dual effects of gravity and wind, water flow deforms to form waves, and the Riemann space representation is the wave shape itself; (2) Sea Breeze The wind generated at sea is divided into two categories according to the time constant relative to the sailing time of the unmanned ship. The first type of sea breeze steady wind has a larger time period and its amplitude follows the Rayleigh distribution. The effect of sea breeze steady wind on the movement of ships is related to the wind direction angle encountered by the ship. In Riemann geometry, the change of the navigation trajectory of the unmanned ship by the inclined plane is consistent with the movement trajectory of the unmanned ship after the sea breeze blows on it. For different encounter wind direction angles, the steady wind is equivalent to inclined planes with different inclinations. The second type of sea breeze turbulent wind is composed of countless harmonics, and its amplitude, direction and frequency are all randomly changing. The random wave theory is used to analyze its changing characteristics. S2, equating the influence of the rudder input and obstacles on the unmanned ship to a Riemann surface, specifically includes: (1) Rudder input control amount When a ship is sailing, when the rudder blade is parallel to the direction of travel of the ship, the water forces on both sides of the rudder blade are equal, and the direction of movement of the ship will not be affected at this time; when the rudder blade is controlled by the steering wheel, a deflection angle is generated, and the water flow on both sides is no longer consistent, and a pressure difference is generated on the water-facing surface and the water-receiving surface, coupled with the friction between the water flow and the rudder blade, which pushes the ship to turn; assuming that the turning radius is R, the turning torque of the rudder propeller is equivalent to a conical rotating surface in Riemann geometry; (2) Obstacles Considering the safety of unmanned ship navigation, if the obstacle encountered by the ship is other ships, the equivalent three-dimensional graphics of the obstacle ship need to be expanded, and the direction and position information of the moving ship need to be obtained through GPS. The motion information of the dynamic obstacle is calculated through AIS and ARPA, and the risk of collision with the ship is predicted according to its speed and direction, so as to avoid collision. According to the size, orientation, speed and direction of the obstacle, it is equivalent to a three-dimensional figure on the surface, which is expressed as a protruding cylinder on the plane. Its area is related to the length and width of the obstacle, its height is related to the volume of the obstacle, and its position on the plane is related to the speed and direction of its movement. S3, vector synthesis of the tangent vectors generated by the external environmental factors, the rudder input and the obstacles at any particle point on the curved surface, specifically includes: The nonlinear mechanical system is presented in geometric space. The state position and velocity in the mechanical system are represented by the geometric manifold position space and tangent vector velocity space. The control input is represented by the manifold input space, and its motion trajectory is represented as the integral curve of the tangent vector in the manifold space. The motion space of the unmanned ship is affected by various factors at a certain point. The tangent vector at the point satisfies the vector synthesis principle, and a new space is generated after synthesis. The step S4, obtaining a geodesic line between two points on the curved surface as a planned route for the unmanned ship, specifically includes: The test area map was gray-scaled and divided into feasible and infeasible areas, and then vectorized into a triangular mesh model, represented by edges, faces, and points. The shore was represented as a convex surface with higher energy, which was expressed as the higher part of the surface. The river channel was represented as a concave surface with lower energy, which was expressed as the lower part of the surface. At the same time, random wind and wave interference was superimposed in the river channel to observe the route planning effect. The obstacle ship is equivalent to a three-dimensional figure with a polygonal bottom in the map. The size of the figure is determined by the size of the target obstacle. The three-dimensional figure equivalent to the obstacle ship is expanded, and at the same time, it is predicted and judged whether there is a risk of collision with the ship according to its sailing speed and direction, so as to avoid collision. Determine the starting point and the end point on the map. Next, find the geodesic from the starting point to the end point on the synthetic surface. This is achieved using the MMP algorithm and the Dijkstra algorithm. The MMP algorithm uses the window propagation as a path to gradually cover the entire surface of the model, thereby calculating the geodesic distance and geodesic path from any point in the model to the source point; The Dijkstra algorithm increases the shortest path length from the source point to the destination point, and generates the shortest path one by one.
2. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the method according to claim 1.
