Ship trajectory planning method and system, electronic device and storage medium

Abstract

The application discloses a ship trajectory planning method and system, an electronic device and a storage medium. The method comprises the following steps: determining ship navigation information according to a ship maneuvering model; determining a ship speed range interval according to safety navigation time data and the ship navigation information, so as to construct an accessible collision avoidance space-time space through the ship speed range interval; wherein the accessible collision avoidance space-time space comprises preset space-time space voxels; performing voxel connection on the preset space-time space voxels to construct node connection edges; performing weight distribution on the node connection edges according to a preset collision avoidance rule, so as to determine an expected voxel sequence through a preset search algorithm according to the distributed weight data; and performing trajectory optimization through a model predictive control algorithm according to the expected voxel sequence to obtain a ship target trajectory. The application can effectively improve the accuracy of ship collision avoidance decision and path planning, and improve the reliability of ship trajectory planning. The application can be widely applied to the technical field of path planning.

Description

Technical Field

[0001] The present application relates to the field of path planning technology, and in particular to a ship trajectory planning method, system, electronic device and storage medium. Background Art

[0002] With the booming maritime trade, modern ships face increasingly complex and diverse encounter scenarios, making autonomous navigation systems particularly important. Traditional collision avoidance systems struggle to effectively handle the dynamic trajectory of target vessels and the changing maritime environment. For example, they perform poorly in scenarios like multi-ship encounters and suffer from low collision avoidance accuracy.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0004] The main purpose of the embodiments of the present application is to propose a ship trajectory planning method, system, electronic device and storage medium, which can effectively improve the accuracy of ship collision avoidance decisions and path planning, and improve the reliability of ship trajectory planning.

[0005] To achieve the above objectives, an embodiment of the present application provides a ship trajectory planning method, which includes the following steps:

[0006] Determine ship navigation information based on the ship maneuvering model;

[0007] Determining a ship speed range interval based on the safe navigation time data and the ship navigation information, so as to construct a reachable collision avoidance space-time space through the ship speed range interval; wherein the reachable collision avoidance space-time space includes preset space-time space voxels;

[0008] Performing voxel connection on the preset spatiotemporal space voxels to construct node connection edges;

[0009] weights are assigned to the node connection edges according to a preset collision avoidance rule, so as to determine a desired voxel sequence through a preset search algorithm based on the assigned weight data;

[0010] Track optimization is performed according to the desired voxel sequence using a model predictive control algorithm to obtain a target trajectory of the ship.

[0011] In some embodiments, determining the ship navigation information based on the ship maneuvering model includes:

[0012] Constructing a three-degree-of-freedom maneuvering model of the ship to determine a ship dynamics model through the three-degree-of-freedom model of the ship;

[0013] The ship navigation information is determined according to the ship dynamics model in combination with the ship's historical motion state data and the safe navigation time data; wherein the ship navigation information includes navigation range information and navigation direction information.

[0014] In some embodiments, determining a ship speed range interval based on the safe navigation time data and the ship navigation information, so as to construct a reachable collision avoidance space-time space through the ship speed range interval, includes:

[0015] Determining the relative direction information of the ship based on the navigation direction information and the ship motion state data;

[0016] Determining a achievable collision avoidance speed set using a speed barrier algorithm according to the relative direction information of the ships and the safe navigation time data;

[0017] The achievable collision avoidance speed set is converted according to the relationship between the speed space and the safe navigation time data to construct the achievable collision avoidance space-time space.

[0018] In some embodiments, performing voxel connection on the preset spatiotemporal space voxels to construct node connection edges includes:

[0019] Connecting the first spatial voxels in sequence according to the time dimension to obtain a first connection edge; wherein the first spatial voxels include the preset spatiotemporal spatial voxels in the same direction;

[0020] Alternatively, the second spatial voxels are connected according to a preset navigation direction to obtain a second connection edge; wherein the second spatial voxels include the preset spatiotemporal spatial voxels having a velocity space intersection in adjacent navigation directions.

[0021] In some embodiments, the weighting of the node connection edges according to a preset collision avoidance rule, and determining the expected voxel sequence using a preset search algorithm based on the weighted data obtained by the weighting, includes:

[0022] The weight data is constructed based on the preset collision avoidance rules in combination with the preset spatiotemporal voxels and the node connection edges; wherein the weight data includes cost data of violating the preset collision avoidance rules;

[0023] An expected collision avoidance decision is determined according to the weight data through a preset graph search algorithm; wherein the expected collision avoidance decision includes the expected voxel sequence.

[0024] In some embodiments, the weight data is obtained by combining the preset collision avoidance rules with the preset spatiotemporal voxels and the node connection edges, including:

[0025] Constructing a first cost function according to the node connection edges and the preset collision avoidance rules;

[0026] Constructing a second cost function based on the voxel direction boundary data and the preset collision avoidance rule; wherein the voxel direction boundary data is determined by the preset spatiotemporal space voxels;

[0027] Constructing a third cost function based on the voxel velocity boundary data and the preset collision avoidance rule; wherein the voxel velocity boundary data is determined by the preset spatiotemporal space voxels;

[0028] Constructing a fourth cost function based on the voxel direction boundary data, the target point direction information and the preset collision avoidance rule;

[0029] A weight distribution function is constructed according to the first cost function, the second cost function, the third cost function, the fourth cost function and a preset weight coefficient.

[0030] In some embodiments, performing trajectory optimization using a model predictive control algorithm according to the desired voxel sequence to obtain a target trajectory of the ship includes:

[0031] Constructing a preset constraint condition according to the desired voxel sequence;

[0032] The target trajectory of the ship is obtained by performing track optimization through the model predictive control algorithm according to the preset constraints.

[0033] To achieve the above objectives, another aspect of the present application provides a ship trajectory planning system, the system comprising:

[0034] The first module is used to determine the ship navigation information according to the ship maneuvering model;

[0035] A second module is configured to determine a ship speed range interval based on the safe navigation time data and the ship navigation information, so as to construct a reachable collision avoidance space-time space through the ship speed range interval; wherein the reachable collision avoidance space-time space includes preset space-time space voxels;

[0036] The third module is used to perform voxel connection on the preset spatiotemporal space voxels to construct node connection edges;

[0037] A fourth module is configured to assign weights to the node connection edges according to a preset collision avoidance rule, and determine a desired voxel sequence using a preset search algorithm based on the assigned weight data;

[0038] The fifth module is used to perform track optimization based on the expected voxel sequence through a model predictive control algorithm to obtain the ship target trajectory.

[0039] To achieve the above-mentioned object, another aspect of the present application provides an electronic device, comprising:

[0040] at least one processor;

[0041] at least one memory for storing at least one program;

[0042] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0043] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above-mentioned method when executed by a processor.

[0044] Embodiments of the present application include at least the following beneficial effects: The present application provides a ship trajectory planning method, system, electronic device, and storage medium. This solution determines ship navigation information using a ship maneuvering model and determines a ship speed range based on safe navigation time data and the ship navigation information, thereby constructing reachable collision avoidance space-time voxels using the ship speed range. Next, the embodiment of the present invention connects the reachable collision avoidance space-time voxels to obtain node-connecting edges, and then weights the node-connecting edges according to preset collision avoidance rules. Based on the weighted data, a preset search algorithm is used to determine a desired voxel sequence. Finally, the embodiment of the present invention optimizes the trajectory based on the desired voxel sequence using a model predictive control algorithm to obtain a target ship trajectory and implement ship trajectory planning. It is readily understood that the embodiment of the present invention, by combining the preset collision avoidance rules for weight allocation and the preset search algorithm for voxel sequence screening, can effectively cope with dynamically changing ship encounter scenarios. Simultaneously, the model predictive control algorithm is used to optimize the trajectory of the desired voxel sequence, ensuring that the collision avoidance trajectory planning is consistent with the ship's maneuverability, thereby effectively improving the accuracy of ship collision avoidance decisions and path planning, and enhancing the reliability of ship trajectory planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is a flowchart of the steps of the ship trajectory planning method provided by an embodiment of the present invention;

[0046] Figure 2 is a schematic diagram of a ship dynamics model provided by an embodiment of the present invention;

[0047] Figure 3 is a schematic diagram of a relative direction boundary determined according to an embodiment of the present invention;

[0048] Figure 4 is a schematic diagram of another relative direction boundary determined according to an embodiment of the present invention;

[0049] Figure 5 is a schematic diagram of another relative direction boundary determined according to an embodiment of the present invention;

[0050] Figure 6 is a schematic diagram of a cut voxel velocity space provided by an embodiment of the present invention;

[0051] Figure 7 This is an overall flow chart of ship trajectory planning provided by an embodiment of the present invention;

[0052] Figure 8 Schematic diagram of the structure of a ship trajectory planning system provided by an embodiment of the present invention;

[0053] Figure 9 It is a schematic diagram of the hardware structure of the electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are merely examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the appended claims.

[0055] It will be understood that the terms "first", "second", etc. used in this application may be used herein to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0056] The terms "at least one", "plurality", "each", "any", etc. used in this application include "at least one", "two" or more, "plurality" or "each", "any" or "any one", "each" or "any one" as used herein.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0058] Before explaining the embodiments of the present application in detail, some of the nouns and terms involved in the embodiments of the present application are first explained. The nouns and terms involved in the embodiments of the present application are subject to the following explanations.

[0059] International Regulations for Preventing Collisions at Sea (COLREGs) refers to the international convention designated by the International Maritime Organization (IMO) to regulate the collision avoidance behavior of ships in maritime traffic.

[0060] Velocity Obstacle (VO) algorithm is a path planning algorithm for collision avoidance that calculates speed obstacles to determine a safe speed range to avoid collisions with other obstacles.

[0061] Model Predictive Control (MPC): This is an optimization control algorithm that uses the system's mathematical model to predict the system's output over a period of time in the future. It then determines the optimal control input at the current moment by solving a finite-time optimization problem. The first value of the control input is then applied to the system, and the above process is repeated at the next sampling moment, resulting in continuous rolling optimization.

[0062] With the booming development of maritime trade, modern ships face increasingly complex and diverse encounter scenarios, making autonomous navigation systems particularly important. Traditional collision avoidance systems struggle to effectively cope with the dynamic trajectory of target vessels and the changing maritime environment. For example, they perform poorly in scenarios like multi-ship encounters and suffer from low collision avoidance accuracy.

[0063] For example, the traditional velocity obstacle method (VO) handles obstacles in the velocity domain, reducing computational complexity. However, this method is prone to local infeasible solutions when the ship motion is nonlinear and the velocity space is nonconvex. Optimization-based methods treat the International Regulations for Preventing Collisions at Sea as a risk field and optimize trajectories to minimize risk. However, the superposition of the potential fields of multiple ships cannot guarantee compliance with the International Regulations for Preventing Collisions at Sea. In addition, the non-convexity caused by the superposition also poses challenges to the optimization solver. An alternative approach is to restrict the solution space to a space-time convex corridor to improve solvability. However, the time spent on finding a reference path hinders its application in complex encounter scenarios. Some researchers simplify this process by representing the solution space as a space-time graph. While structured road regions have known boundaries and directions, ships can sail in any direction in open water, making the demarcation of collision-free zones more difficult. Furthermore, generating decisions that comply with the International Regulations for Preventing Collisions at Sea from the space-time transition graph is also challenging.

[0064] In view of this, a ship trajectory planning method, system, electronic device and storage medium are provided in an embodiment of the present application. The scheme determines the ship navigation information through the ship maneuvering model, and determines the ship speed range interval based on the safe navigation time data and the ship navigation information, so as to construct the reachable collision avoidance space-time voxels through the ship speed range interval. Then, the embodiment of the present invention performs voxel connection construction on the reachable collision avoidance space-time voxels to obtain node connection edges, and then assigns weights to the node connection edges according to the preset collision avoidance rules, so as to determine the expected voxel sequence through the preset search algorithm based on the assigned weight data. Finally, the embodiment of the present invention performs track optimization through the model predictive control algorithm according to the expected voxel sequence to obtain the target trajectory of the ship and realize ship trajectory planning, which can effectively improve the accuracy of ship collision avoidance decision-making and path planning, and improve the reliability of ship trajectory planning.

[0065] The ship trajectory planning method provided by the embodiments of the present application relates to the technical field of path planning. The ship trajectory planning method provided by the embodiments of the present application can be applied to a terminal, can be applied to a server, and can also be software running in the terminal or the server. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, a vehicle-mounted terminal, and the like, but is not limited thereto; the server end can be configured as a stand-alone physical server, can be configured as a server cluster or a distributed system formed by multiple physical servers, can be configured as a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and big data and artificial intelligence platform, and the server can also be a node server in a blockchain network; and the software can be an application that implements the ship trajectory planning method, and the like, but is not limited to the above forms.

[0066] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment in which tasks are performed by remote processing devices connected by a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0067] Figure 1 is an optional flowchart of the ship trajectory planning method provided by the embodiments of the present application, Figure 1 The method in can include but is not limited to steps S110 to S150.

[0068] Step S110, determining ship navigation information according to a ship maneuvering model.

[0069] Step S120, determining a ship speed range interval according to safety navigation time data and the ship navigation information, to construct a reachable collision avoidance space-time space through the ship speed range interval. The reachable collision avoidance space-time space includes preset space-time space voxels.

[0070] Step S130, voxel connection is performed on the preset space-time space voxels, to construct node connection edges.

[0071] Step S140 , weights are assigned to the node connection edges according to a preset collision avoidance rule, so as to determine a desired voxel sequence through a preset search algorithm based on the assigned weight data.

[0072] Step S150 , performing track optimization using a model predictive control algorithm according to the desired voxel sequence to obtain the target trajectory of the ship.

[0073] During the working process of this specific embodiment, the embodiment of the present invention first determines the ship navigation information based on the ship maneuvering model, and then determines the ship speed range interval based on the safe navigation time data and the ship navigation information, so as to construct a achievable collision avoidance space-time space through the ship speed range interval. Specifically, the ship maneuvering model in the embodiment of the present invention refers to a model used to describe and predict the motion state of a ship, such as a multi-degree-of-freedom maneuvering model. In addition, the ship navigation information in the embodiment of the present invention refers to various data parameters related to ship navigation, such as the ship's navigation direction, navigation speed, navigation range, etc. Correspondingly, the safe navigation time data in the embodiment of the present invention refers to the time period data in which the ship can navigate safely under relevant conditions. Among them, the embodiment of the present invention determines the speed space (ship speed range interval) that can ensure the ship's navigation without collision under the safe navigation time data based on the ship navigation information, that is, the achievable collision avoidance speed set RAV (T p Then, based on the constructed ship speed range, i.e., the speed space in which the ship can safely avoid collisions, the embodiment of the present invention performs data conversion between the speed space and the space-time space to construct a reachable collision avoidance space-time space. Accordingly, the embodiment of the present invention constructs the reachable collision avoidance space-time space by calculating the voxels of the reachable collision avoidance data at each time step, i.e., the preset space-time space voxels.

[0074] Furthermore, embodiments of the present invention perform voxel connections on preset spatiotemporal voxels to construct node-connecting edges, and assign weights to the node-connecting edges according to preset collision avoidance rules. A desired voxel sequence is determined using a preset search algorithm based on the assigned weight data. Specifically, after constructing the corresponding preset spatiotemporal voxels, such as voxels existing at corresponding times and directions, embodiments of the present invention use each preset spatiotemporal voxel as a node, connect the nodes, and construct node-connecting edges. Accordingly, the preset collision avoidance rules in embodiments of the present invention refer to collision avoidance rules for ship navigation, such as the International Regulations for Preventing Collisions at Sea (COLREGs) or other pre-defined collision rules. After determining the connecting edges, embodiments of the present invention assign weights to the compliance with the preset collision avoidance rules, i.e., perform weight assignment, thereby obtaining corresponding weight data. Accordingly, the weight data in embodiments of the present invention refers to the cost data for violating the relevant collision avoidance rules. Embodiments of the present invention define various constraints according to the preset collision avoidance rules and determine the weights of each node-connecting edge in a weighted manner to obtain the corresponding weight data. Then, the embodiment of the present invention searches for the optimal voxel sequence using a preset search algorithm and corresponding weight data, thereby determining a desired voxel sequence. Finally, the embodiment of the present invention performs trajectory optimization based on the desired voxel sequence using a model predictive control algorithm to obtain the target trajectory of the ship. Specifically, the desired voxel sequence in the embodiment of the present invention is the optimal collision avoidance decision represented in voxel form. Accordingly, the embodiment of the present invention uses a model predictive control (MPC) algorithm to optimize the trajectory of the optimal collision avoidance decision (desired voxel sequence) represented in voxel form, thereby obtaining the target trajectory of the ship and implementing ship trajectory planning.

[0075] In some embodiments of the present invention, determining the ship navigation information based on the ship maneuvering model includes but is not limited to the following steps:

[0076] A three-degree-of-freedom maneuvering model of the ship is constructed to determine the ship dynamics model through the three-degree-of-freedom model of the ship.

[0077] The ship's navigation information is determined based on the ship's dynamics model combined with the ship's historical motion state data and safe navigation time data. The ship's navigation information includes navigation range information and navigation direction information.

[0078] During the working process of this specific embodiment, the embodiment of the present invention first constructs a three-degree-of-freedom maneuvering model of the ship to determine the ship dynamics model through the three-degree-of-freedom model of the ship, and then determines the ship navigation information by combining the ship's historical motion state data and safe navigation time data. Specifically, the embodiment of the present invention introduces a three-degree-of-freedom (3-DOF) maneuvering model of the ship to determine the ship dynamics model, thereby limiting the ship's navigation range and trajectory optimization. For example, Figure 2As shown, the embodiment of the present invention first uses the three posture vectors η = [N, E, ψ] in the NED (North-East-Down) coordinate system T Define the motion state of the ship, where N and E represent north and east respectively, and ψ is the heading angle. In this embodiment of the present invention, the velocity vector V = [u, v, r] is defined in the fixed coordinate system of the ship. T , where u represents the linear velocity along the forward direction of the hull (longitudinal velocity), v represents the linear velocity along the transverse direction of the hull (lateral velocity), and r represents the angular velocity of the hull around the vertical axis (yaw angular velocity). At the same time, the embodiment of the present invention introduces the rotation matrix J(ψ) and the control input τ=[f u ,f v ,f r ] T The rotation matrix J(ψ) in the embodiment of the present invention is as shown in the following formula (1):

[0079]

[0080] Accordingly, the change rates of the three posture vectors η in the embodiment of the present invention are expressed by the rotation matrix J(ψ) and the velocity vector v, as shown in the following equation (2):

[0081]

[0082] Next, in the embodiment of the present invention, the relationship between the velocity vector V and the control input τ is expressed as a kinematic model of the ship in the hull-fixed coordinate system, as shown in the following equation (3):

[0083]

[0084] Where M represents the rigid body and added mass terms, C represents the Coriolis-centrifugal matrix, D is the hydrodynamic damping matrix, and V represents the velocity vector.

[0085] It should be noted that the embodiment of the present invention determines the transformation relationship and dynamic constraints of the ship in different coordinate systems through the above process. To facilitate calculation, the embodiment of the present invention discretizes the above equations (1) to (3) using the forward Euler method and describes them in the form of state space equations, obtaining the following equations (4) to (6):

[0086]

[0087] q1=[0 0 1 0 0 0] (5)

[0088]

[0089] Where f(·) is the continuous system dynamics, and the control input u(t) = (f u ,f v,f r ) T , the motion state is x(t)=(N,E,ψ,u,v,r) T .

[0090] In some embodiments of the present invention, determining a ship speed range interval based on safe navigation time data and ship navigation information to construct a reachable collision avoidance space-time space through the ship speed range interval includes but is not limited to the following steps:

[0091] The relative direction information of the ship is determined based on the navigation direction information and the ship motion status data.

[0092] The achievable collision avoidance speed set is determined by the speed barrier algorithm based on the relative direction information of the ships and the safe navigation time data.

[0093] According to the relationship between speed space and safe navigation time data, the achievable collision avoidance speed set is transformed to construct the achievable collision avoidance space-time space.

[0094] In some embodiments of the present invention, the embodiments of the present invention first determine the relative direction information of the ship based on the navigation direction information and the ship's motion state, and then determine the achievable collision avoidance speed set through the speed obstacle algorithm based on the relative direction of the ship and the safe navigation time data, and then convert the achievable collision avoidance speed set through the relationship between the speed space and the safe navigation time data to obtain a achievable collision avoidance space-time space. Specifically, in the embodiments of the present invention, the ship state data refers to the current motion state x(t) of the ship, and the navigation direction information refers to the current navigation direction of the ship. Accordingly, the relative direction information of the ship in the embodiments of the present invention refers to a range that is reachable according to the motion characteristics relative to the current ship direction, and is obtained by adaptively dividing according to the navigation direction information and the ship's motion state. For example, the current ship has a lateral speed v, and the range that the ship can reach along this speed is larger, while the range that is reachable against this speed is smaller. Therefore, the divided reachable range is not symmetrically distributed on both sides of the longitudinal speed u as the center line, but is adaptively divided by the current state. In addition, in order to obtain the reachable position of maximum steering, the control input f r Assuming the maximum torque, the propulsion force f u Assume it is 0. In order to evaluate the reachable position within the corresponding time period, the embodiment of the present invention iteratively calculates the reachable position and direction with a fixed time resolution. For example, if the decision and trajectory planning are performed in the next 20 seconds, the ship state will be evaluated at 0 seconds, 5 seconds, 10 seconds and 20 seconds, with a time interval of 5 seconds. Then, the relative direction boundary is determined by the maximum relative direction and position at 0 seconds, 5 seconds, 10 seconds and 20 seconds, as shown in Figure 2. Figure 3 、 Figure 4 as well as Figure 5 shown.

[0095] Next, the embodiment of the present invention determines the safe navigation time data T in the relative direction of the adaptive division, that is, the relative direction information of the ship according to the speed obstacle algorithm (VO). p The speed space that can ensure the ship's navigation without collision is the collision avoidance speed set RAV(T p ).

[0096] For example, in the initial velocity obstacle (VO) calculation process, the embodiment of the present invention first converts the collision avoidance problem from the time-space domain to the velocity space according to the velocity obstacle algorithm. Accordingly, in the embodiment of the present invention, the speed of the target ships (TSs) is assumed to be constant, and the velocity obstacle cones (VOs) are defined according to the ship collision geometry calculation. The feasible speed is located outside these obstacle cones. The expression of is shown in the following formula (7):

[0097]

[0098] Among them, represents the Mincowski sum, qat represents the set of collision velocity vectors, OS represents own ship, TS n Indicates a dynamic obstacle.

[0099] At the same time, due to the limited maneuverability of a ship, it may not be possible for the ship to immediately reach certain feasible speeds. Therefore, the embodiment of the present invention takes into account the maneuverability of the ship. Accordingly, under this limitation, the achievable speed set R(Pat,catmax,vatmax) of the ship in the embodiment of the present invention is defined as the set of speeds within the maximum achievable speed vatmax and the maneuverable direction range catmax, as shown in the following equation (8):

[0100]

[0101] Where Pat represents the current velocity vector, vatmax represents the maximum achievable velocity, and catmax represents the range of velocity direction.

[0102] Accordingly, if the obstacle cannot be avoided at the current speed, the speed barrier algorithm will recalculate an updated speed barrier, considering a shorter safety time interval T p Make a collision avoidance decision. The updated formula in the embodiment of the present invention is shown in the following formula (9):

[0103]

[0104] Where dm represents the minimum safe distance.

[0105] Then, the embodiment of the present invention constructs the reachable collision avoidance speed set RAV(T p )(Reachable AvoidanceVelocity). In this embodiment of the present invention, the reachable velocity set R(Pat,catmax,vatmax) is calculated and the dynamic obstacle VO TS and static obstacle VO SO The Mincowski difference of RAV(T p ), as shown in the following formula (10):

[0106]

[0107] in, represents the Mincowski difference.

[0108] Furthermore, after obtaining the achievable collision avoidance speed set RAV(T p ) After that, the embodiment of the present invention is based on the speed space and safe navigation time data T p The relationship defines the Reachable Avoidance Spatio-temporal Space RAS (ReachableAvoidance Spatio-temporal Space) at each time step, that is, voxels. Among them, the embodiment of the present invention calculates the range of the reachable collision avoidance speed RAV in the relative direction at each time interval through the speed barrier algorithm. Accordingly, the reachable speed selected by the speed barrier algorithm is limited to between 0 and the maximum speed that does not cause the ship to collide, but when RAV intersects with the speed barrier cone at a certain time step, it will be cut into several parts, each of which will correspond to a speed interval (at this time, the lower limit of the speed of a certain part is not 0), then the direction will generate voxels corresponding to multiple different speed intervals. Regarding voxels, the embodiment of the present invention uses and Constrain the relative orientation of the voxel using and Constrain the upper and lower bounds of the voxel velocity range.

[0109] In some embodiments of the present invention, voxel connection is performed on the preset spatiotemporal space voxels to construct node connection edges, including but not limited to the following steps:

[0110] The first spatial voxels are sequentially connected along the time dimension to obtain a first connection edge, wherein the first spatial voxels include preset spatiotemporal spatial voxels in the same direction.

[0111] Alternatively, the second spatial voxels are connected according to a preset navigation direction to obtain a second connection edge, wherein the second spatial voxels include preset spatiotemporal spatial voxels having a velocity space intersection in adjacent navigation directions.

[0112] In this specific embodiment, after obtaining voxels existing at corresponding times and directions, the present invention uses these preset spatiotemporal voxels as nodes and constructs connecting edges about these nodes. The connecting edges constructed in the present invention include a first connecting edge and a second connecting edge. Accordingly, the present invention connects the first spatial voxels sequentially along the time dimension to construct the first connecting edge. Alternatively, the present invention connects the second spatial voxels along the preset navigation direction to construct the second connecting edge. Specifically, the first spatial voxels in the present invention include preset spatiotemporal voxels in the same direction. The present invention uses a relevant preset search algorithm, such as the Dijkstra graph search algorithm, to search for an optimal voxel sequence for decision making. For example, the Dijkstra graph search algorithm searches for a sequence with the lowest cost based on the cost between each node. However, not all voxels can be connected. The connecting edges in the present invention determine which voxels can be connected along the spatiotemporal dimension, thereby obtaining an optimal sequence for decision making. Accordingly, the present invention constructs node connecting edges based on both time and direction. In the time dimension, the ship in this embodiment of the present invention sails in a fixed direction, so voxels in the same direction can naturally be connected sequentially along the time dimension. Therefore, this embodiment of the present invention sequentially connects voxels in the preset spatiotemporal space in the same direction along the time dimension to construct a first connecting edge. Furthermore, given a voxel represents the current position and sailing direction of a ship at a specific time, the ship can sail in an adjacent direction at the next moment. Therefore, in the sailing direction, if voxels representing different and adjacent directions intersect in their speed intervals, they can be connected to adjacent voxels in the same speed interval at the next time step. In this regard, when voxels in adjacent directions intersect in speed space, this embodiment of the present invention connects the current voxel to the voxel in the adjacent direction at the same speed at the next time step. That is, the second spatial voxel is connected to the voxel in the adjacent direction (the preset sailing direction) at the same speed, thereby obtaining a second connecting edge. Accordingly, this embodiment of the present invention determines the nodes that can be expanded for each voxel through a method based on the time and direction dimensions, which is used for graph search.

[0113] In some embodiments of the present invention, weights are assigned to node connecting edges according to a preset collision avoidance rule, and a desired voxel sequence is determined by a preset search algorithm based on the assigned weight data, including but not limited to the following steps:

[0114] The weight data is constructed based on the preset collision avoidance rules in combination with the preset spatiotemporal voxels and node connection edges, wherein the weight data includes cost data of violating the preset collision avoidance rules.

[0115] The expected collision avoidance decision is determined by a preset graph search algorithm according to the weight data, wherein the expected collision avoidance decision includes an expected voxel sequence.

[0116] In this specific embodiment, the present invention first constructs weight data based on preset collision avoidance rules in combination with preset spatiotemporal voxels and node connections. Specifically, the weight data in the present invention includes cost data for violating the preset collision avoidance rules. Accordingly, the present invention constructs a cost function for each preset collision avoidance rule by combining the voxel data of the preset spatiotemporal voxels and the corresponding node connections, thereby obtaining the corresponding cost data, i.e., weight data. The voxel data of the preset spatiotemporal volume in the present invention includes voxel-directional boundaries, velocity boundaries, and the like. Next, the present invention determines a desired collision avoidance decision using a preset graph search algorithm based on the weight data. Specifically, the desired collision avoidance decision in the present invention includes a desired voxel sequence, i.e., the optimal voxel sequence obtained through a graph search. The preset graph search algorithms in the present invention include, for example, the Dijkstra graph search algorithm and the A-star algorithm. Accordingly, the present invention performs a search based on the preset graph search algorithm and the corresponding weight data to obtain the optimal voxel sequence that complies with the preset collision avoidance rules, i.e., the desired voxel sequence.

[0117] In some embodiments of the present invention, weight data is obtained according to a preset collision avoidance rule in combination with preset spatiotemporal voxels and node connection edges, including but not limited to the following steps:

[0118] The first cost function is constructed based on the node connection edges and the preset collision avoidance rules.

[0119] A second cost function is constructed based on the voxel direction boundary data and the preset collision avoidance rule, wherein the voxel direction boundary data is determined by the preset spatiotemporal space voxels.

[0120] A third cost function is constructed based on the voxel velocity boundary data and the preset collision avoidance rules, wherein the voxel velocity boundary data is determined by the preset spatiotemporal voxels.

[0121] A fourth cost function is constructed based on the voxel direction boundary data, the target point direction information, and the preset collision avoidance rules.

[0122] A weight distribution function is constructed according to the first cost function, the second cost function, the third cost function, the fourth cost function and the preset weight coefficient.

[0123] In this specific embodiment, the embodiment of the present invention first constructs a first cost function based on the node connection edge and the preset collision avoidance rules. Specifically, the preset collision avoidance rules in the embodiment of the present invention include the International Regulations for Preventing Collisions at Sea (COLREGs). Among them, 8.b of the International Regulations for Preventing Collisions at Sea in the embodiment of the present invention requires that when changing the course and / or speed to avoid collision, the change should be obvious enough so that other ships can clearly perceive it. In this regard, the embodiment of the present invention defines the first cost function as the penalty for violating the International Regulations for Preventing Collisions at Sea, as shown in the following formula (11):

[0124]

[0125] Among them, C pen Indicates the penalty for course changes that do not comply with COLREGs. Represents connected voxels voxcel i and voxcel j Accordingly, in the subsequent voxel switching process, when a situation that does not comply with COLREGs occurs, weight accumulation will occur, thereby selecting a large-angle steering behavior that complies with COLREGs requirements.

[0126] Next, the embodiment of the present invention constructs a second cost function based on the voxel directional boundary data and the preset collision avoidance rules. Specifically, the voxel directional boundary data in the embodiment of the present invention is determined by the preset spatiotemporal voxels. Accordingly, in the embodiment of the present invention, 8.f of the International Regulations for Preventing Collisions at Sea encourages early changes of course to avoid the target ship. In this regard, the embodiment of the present invention constructs a second cost function based on the voxel directional boundary data, as shown in the following equation (12):

[0127]

[0128] Where t represents the timestamp of taking action, and as well as and Respectively represent the boundaries in the direction of each voxel.

[0129] Furthermore, the embodiment of the present invention constructs a third cost function based on the voxel velocity boundary data and the preset collision avoidance rules. Specifically, in the embodiment of the present invention, the voxel velocity boundary data is determined by the preset spatiotemporal voxels. Accordingly, in the embodiment of the present invention, 8.c of the International Regulations for Preventing Collisions at Sea stipulates that in the event of an urgent collision, the most effective action should be to change course and maintain speed. Therefore, the embodiment of the present invention defines the cost of measuring speed changes, that is, the third cost function, as shown in the following formula (13):

[0130]

[0131] In fact, is the maximum achievable speed, is the upper bound of the velocity of this voxel.

[0132] Then, the embodiment of the present invention constructs a fourth cost function based on the voxel direction boundary data, the target point direction information, and the preset collision avoidance rules. Specifically, after the own ship (OS) avoids the collision, it must return to its initial heading. In this regard, the embodiment of the present invention constructs C based on the voxel direction boundary data and the target point direction information. waypoint Cost is used to measure the deviation between the current ship direction and the destination, as shown in the following formula (14):

[0133]

[0134] Among them, ψ goal Indicates the direction of the target point.

[0135] Finally, the embodiment of the present invention constructs a weight distribution function based on the first cost function, the second cost function, the third cost function, the fourth cost function, and the preset weight coefficient. Specifically, in the embodiment of the present invention, the total cost of the edge is obtained by weighted linear addition of each cost function, that is, the weight distribution function, as shown in the following formula (15):

[0136]

[0137] Among them, Representation from voxel voxcel i to voxcel j The weight of a i (i is 1-4) represents the preset weight coefficient.

[0138] It should be noted that in the embodiments of the present invention, the order of the preset weight coefficients is determined based on the importance of each weight, that is, the importance of the COLREGs rule. For example, based on the importance of each weight, the preset weight coefficients are ranked as follows: a2 > a1 > a4 > a3, so as to facilitate collision avoidance decisions that suppress speed changes and prioritize large-angle maneuvers.

[0139] In some embodiments of the present invention, trajectory optimization is performed using a model predictive control algorithm based on a desired voxel sequence to obtain a target trajectory of a ship, including but not limited to the following steps:

[0140] Construct preset constraints based on the desired voxel sequence.

[0141] According to the preset constraints, the trajectory optimization is performed through the model predictive control algorithm to obtain the target trajectory of the ship.

[0142] In this specific embodiment, the embodiment of the present invention first constructs preset constraints based on the desired voxel sequence, and then optimizes the trajectory through the model predictive control algorithm based on the preset constraints to obtain the target trajectory of the ship. Specifically, after determining the optimal collision avoidance decision expressed in the form of voxels, the embodiment of the present invention converts the sequence into the constraints of the model predictive control (MPC) to derive the optimized track, that is, the target trajectory of the ship. Among them, the relative direction of the ship in the embodiment of the present invention is obtained by and Constraints are made as shown in the following formula (16):

[0143]

[0144] At the same time, the speed limit of the ship in the embodiment of the present invention is The following is shown in formula (17):

[0145]

[0146] In addition, for the lower bound of speed in the embodiment of the present invention, when When it is not 0, the velocity space of the voxel is in the shape of an annular sector, forming a non-convex set. Therefore, in the embodiment of the present invention, the annular sector is cut by the tangent line passing through the inner midpoint (such as Figure 6 To simplify the calculation, the geometric relationship is shown in the following formula (18):

[0147]

[0148] Furthermore, the objective function determined in the embodiment of the present invention is shown in the following formula (19):

[0149]

[0150] Among them, T p represents the safe navigation time data, that is, the time period of prediction and planning, the Q matrix and R matrix represent the state weight matrix and the control input weight matrix respectively, and st represents the constraint conditions.

[0151] The following describes the solution of the embodiment of the present invention in detail with reference to a specific ship trajectory planning scenario:

[0152] For example, Figure 7 As shown, Figure 7This is an overall flow chart of ship trajectory planning provided by an embodiment of the present invention. Specifically, the embodiment of the present invention first introduces a three-degree-of-freedom model of the ship, and imposes dynamic constraints to determine the relative direction of the ship's navigation and the boundary of the reachable position. Then, the embodiment of the present invention determines the feasible speed range of the relative direction within the safe navigation time, and constructs a reachable collision avoidance space-time voxel based on the speed range, and then connects adjacent voxels from the time dimension and speed space respectively to obtain node connection edges. Then, the embodiment of the present invention defines various constraints based on different collision avoidance rules in the International Regulations for Preventing Collisions at Sea, and defines the weights of the edges in a weighted form. Furthermore, the embodiment of the present invention predicts the optimal voxel sequence that complies with the national regulations for preventing collisions at sea based on the Dijkstra graph search algorithm to obtain the expected voxel sequence. Finally, the embodiment of the present invention performs trajectory optimization on the expected voxel sequence according to the model predictive control algorithm (MPC) to obtain the target trajectory of the ship.

[0153] It is easy to understand that in the embodiment of the present invention, by assigning weights to different rule cost functions according to the importance of the national maritime collision avoidance rules, and then screening the optimal voxel sequence based on the graph search method, a planning decision that complies with COLREGs is obtained for trajectory optimization, which is more in line with reality and can effectively improve the accuracy of ship collision avoidance decisions and path planning, and improve the reliability of ship trajectory planning. At the same time, the embodiment of the present invention constrains the ship's maneuvering restrictions through model predictive control (MPC) to ensure that the collision avoidance trajectory planning complies with the ship's actual maneuvering capabilities. In addition, the embodiment of the present invention introduces a speed barrier (VO) algorithm to adaptively segment the ship's reachable area in the space-time graph and generate a voxel sequence, which significantly improves the computational efficiency of collision avoidance decisions and can respond to the collision avoidance needs of multiple ships in a complex dynamic environment in real time.

[0154] See also Figure 8 The present application also provides a ship trajectory planning system that can implement the above-mentioned ship trajectory planning method. The system includes:

[0155] The first module 210 is configured to determine ship navigation information according to a ship maneuvering model.

[0156] The second module 220 is configured to determine a ship speed range based on the safe navigation time data and the ship navigation information, and construct a achievable collision avoidance space-time space using the ship speed range. The achievable collision avoidance space-time space includes preset space-time space voxels.

[0157] The third module 230 is used to perform voxel connection on the preset spatiotemporal space voxels to construct node connection edges.

[0158] The fourth module 240 is used to assign weights to the node connection edges according to the preset collision avoidance rules, so as to determine the expected voxel sequence through a preset search algorithm based on the assigned weight data.

[0159] The fifth module 250 is configured to perform path optimization according to a model predictive control algorithm based on the desired voxel sequence, to obtain a target trajectory of the ship.

[0160] It can be understood that the contents in the above method embodiments are all applicable to the present system embodiment, the present system embodiment specifically implements the same functions as the above method embodiments, and achieves the same beneficial effects as the above method embodiments.

[0161] The present application also provides an electronic device, which comprises a memory and a processor. The memory stores a computer program, and the processor implements the ship trajectory planning method when executing the computer program. The electronic device can be any intelligent terminal, such as a tablet computer or a vehicle-mounted computer.

[0162] It can be understood that the contents in the above method embodiments are all applicable to the present device embodiment, the present device embodiment specifically implements the same functions as the above method embodiments, and achieves the same beneficial effects as the above method embodiments.

[0163] Please refer to Figure 9 , Figure 9 The hardware structure of the electronic device of another embodiment is illustrated, which comprises:

[0164] The processor 310 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, and is used to execute related programs to implement the technical solutions provided by the present application;

[0165] The memory 320 can be implemented in the form of a ROM (Read Only Memory), a static storage device, a dynamic storage device, or a RAM (Random Access Memory). The memory 320 can store an operating system and other application programs. When the technical solutions provided by the present application are implemented by software or firmware, the related program codes are stored in the memory 320 and are called and executed by the processor 310 to implement the ship trajectory planning method of the present application;

[0166] The input / output interface 330 is used to realize information input and output.

[0167] Communication interface 340, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0168] bus 350 , which transmits information between the various components of the device (e.g., processor 310 , memory 320 , input / output interface 330 , and communication interface 340 );

[0169] The processor 310 , the memory 320 , the input / output interface 330 and the communication interface 340 are connected to each other in communication within the device via the bus 350 .

[0170] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned ship trajectory planning method is implemented.

[0171] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiment, the functions specifically implemented by the present storage medium embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0172] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0173] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0174] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0175] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0176] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0177] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0178] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0179] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0180] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0181] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0182] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0183] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A ship trajectory planning method, characterized in that: The method comprises the following steps: Determine ship navigation information based on the ship maneuvering model; Determining a ship speed range interval based on the safe navigation time data and the ship navigation information, so as to construct a reachable collision avoidance space-time space through the ship speed range interval; wherein the reachable collision avoidance space-time space includes preset space-time space voxels; Performing voxel connection on the preset spatiotemporal space voxels to construct node connection edges; weights are assigned to the node connection edges according to a preset collision avoidance rule, so as to determine a desired voxel sequence through a preset search algorithm based on the assigned weight data; Track optimization is performed according to the desired voxel sequence using a model predictive control algorithm to obtain a target trajectory of the ship.

2. The method according to claim 1, characterized in that Determining the ship navigation information according to the ship maneuvering model includes: Constructing a three-degree-of-freedom maneuvering model of the ship to determine a ship dynamics model through the three-degree-of-freedom model of the ship; The ship navigation information is determined according to the ship dynamics model in combination with the ship's historical motion state data and the safe navigation time data; wherein the ship navigation information includes navigation range information and navigation direction information.

3. The method according to claim 2, characterized in that The determining of the ship speed range interval according to the safe navigation time data and the ship navigation information, so as to construct a reachable collision avoidance space-time space through the ship speed range interval, includes: Determining the relative direction information of the ship based on the navigation direction information and the ship motion state data; Determining a achievable collision avoidance speed set using a speed barrier algorithm according to the relative direction information of the ships and the safe navigation time data; The achievable collision avoidance speed set is converted according to the relationship between the speed space and the safe navigation time data to construct the achievable collision avoidance space-time space.

4. The method according to claim 1, wherein The voxel connection of the preset spatiotemporal space voxels to construct node connection edges includes: Connecting the first spatial voxels in sequence according to the time dimension to obtain a first connection edge; wherein the first spatial voxels include the preset spatiotemporal spatial voxels in the same direction; Alternatively, the second spatial voxels are connected according to a preset navigation direction to obtain a second connection edge; wherein the second spatial voxels include the preset spatiotemporal spatial voxels having a velocity space intersection in adjacent navigation directions.

5. The method according to claim 1, wherein The weighting of the node connection edges is performed according to a preset collision avoidance rule, and the expected voxel sequence is determined by a preset search algorithm based on the weighted data obtained by the weighting, including: The weight data is constructed based on the preset collision avoidance rules in combination with the preset spatiotemporal voxels and the node connection edges; wherein the weight data includes cost data for violating the preset collision avoidance rules; An expected collision avoidance decision is determined according to the weight data through a preset graph search algorithm; wherein the expected collision avoidance decision includes the expected voxel sequence.

6. The method according to claim 5, characterized in that The weight data is obtained by combining the preset space-time voxels and the node connection edges according to the preset collision avoidance rules, including: Constructing a first cost function according to the node connection edges and the preset collision avoidance rules; Constructing a second cost function based on the voxel direction boundary data and the preset collision avoidance rule; wherein the voxel direction boundary data is determined by the preset spatiotemporal space voxels; Constructing a third cost function based on the voxel velocity boundary data and the preset collision avoidance rule; wherein the voxel velocity boundary data is determined by the preset spatiotemporal space voxels; Constructing a fourth cost function based on the voxel direction boundary data, the target point direction information and the preset collision avoidance rule; A weight distribution function is constructed according to the first cost function, the second cost function, the third cost function, the fourth cost function and a preset weight coefficient.

7. The method according to claim 1, characterized in that The method of performing track optimization by a model predictive control algorithm according to the desired voxel sequence to obtain a target trajectory of the ship includes: Constructing a preset constraint condition according to the desired voxel sequence; The target trajectory of the ship is obtained by performing track optimization through the model predictive control algorithm according to the preset constraints.

8. A ship trajectory planning system, characterized in that: The system comprises: The first module is used to determine the ship navigation information according to the ship maneuvering model; A second module is configured to determine a ship speed range interval based on the safe navigation time data and the ship navigation information, so as to construct a reachable collision avoidance space-time space through the ship speed range interval; wherein the reachable collision avoidance space-time space includes preset space-time space voxels; The third module is used to perform voxel connection on the preset spatiotemporal space voxels to construct node connection edges; A fourth module is configured to assign weights to the node connection edges according to a preset collision avoidance rule, and determine a desired voxel sequence using a preset search algorithm based on the assigned weight data; The fifth module is used to perform track optimization based on the expected voxel sequence through a model predictive control algorithm to obtain the ship target trajectory.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images