Unmanned ship path planning method and device, storage medium and equipment
By combining the improved progressive optimal rapid exploration random tree algorithm with the constraints of ship motion characteristics, the path point sequence of the unmanned ship is optimized, which solves the feasibility and inefficiency problems of path planning under complex sea conditions and generates a smooth path that meets the maneuvering limit of the ship.
Patent Information
- Application Number
- CN202511144040.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-15
- Publication Date
- 2025-09-26
- Estimated Expiration
- 2045-08-15
AI Technical Summary
Existing technologies lack feasibility and efficiency in unmanned ship path planning under complex sea conditions. Traditional methods fail to effectively combine the motion characteristics of ships, resulting in long voyages, frequent turns, and large twists and turns, making it difficult to accurately reach planned waypoints.
An improved progressively optimal rapid exploration random tree algorithm is used to generate the initial path point sequence. Combined with the ship's motion characteristic constraints, the path point sequence is optimized through path pruning, skip connection and multi-objective comprehensive evaluation to generate a smooth path that meets the physical maneuvering limit of the ship.
The feasibility and efficiency of path planning are improved, and the generated path can be efficiently executed by the tracking controller, avoiding the problems of long paths, frequent turns and unstable control, and adapting to complex sea conditions.
Smart Images

Figure CN120702479A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of transportation ship technology, and in particular to a path planning method, device, storage medium and equipment for an unmanned ship. Background Art
[0002] With the rapid development of global marine resource development and intelligent shipping, unmanned surface vehicles (USVs) have become a research hotspot in the intelligent shipping field due to their widespread applications in environmental monitoring, military reconnaissance, and maritime search and rescue. In this context, achieving efficient path planning for vessels in dynamic obstacle environments has become a focus of both academic and industrial attention.
[0003] At present, traditional methods are insufficient in adapting to the motion characteristics of ships. Ships are prone to problems such as long voyages, frequent turns, and large turns, which make it impossible for ships to accurately reach planned waypoints.
[0004] Therefore, how to improve the feasibility and efficiency of ship path planning under complex sea conditions is a problem that needs to be solved urgently. Summary of the Invention
[0005] The main purpose of this application is to provide a path planning method, device, storage medium and equipment for an unmanned ship, aiming to solve the technical problems of insufficient feasibility and low efficiency of ship path planning under complex sea conditions.
[0006] To achieve the above objectives, the present application proposes a path planning method for an unmanned vessel, the method comprising: Create an environmental map based on the ship's current location information, destination location information, ship status information, and obstacle location information; In the environment map, based on the ship motion characteristic constraints, an initial path point sequence is generated by an improved progressive optimal rapid exploration random tree algorithm; Performing motion constraint-aware path optimization processing on the initial path point sequence and outputting an optimized path point sequence, wherein the path optimization processing is used to optimize problems such as lengthy paths, frequent turns, and direct flight feasibility; Obtaining multiple groups of optimized path point sequences based on ship characteristic parameters with different degrees of constraint; A multi-objective comprehensive evaluation of path quality is performed on multiple groups of the optimized path point sequences to screen out the optimal target planning path.
[0007] In one embodiment, the step of generating an initial pathpoint sequence in the environment map by using an improved progressively optimal rapid exploration random tree algorithm based on the ship motion characteristic constraints includes: Constructing a dual-constraint model for ship motion, wherein the dual-constraint model for ship motion is used to constrain a maximum steering angle constraint and a minimum turning radius; A dynamic hybrid sampling mechanism is used to generate random sampling points, wherein the dynamic hybrid sampling mechanism includes path reinforcement sampling, target bias sampling, heuristic sampling and uniform random sampling; Performing node expansion on the random sampling points to obtain an expanded node set; The dual-constraint model of ship motion is applied to the extended node set, collision detection and steering feasibility verification are performed on each node, and an initial path point sequence is iteratively generated.
[0008] In one embodiment, the step of performing motion constraint-aware path optimization on the initial path point sequence and outputting an optimized path point sequence includes: Removing intermediate nodes that meet redundancy conditions from the initial path point sequence through path pruning to obtain initial optimized path points; Performing jump connections on the initial optimized path points to obtain intermediate optimized path points; Based on the redundant point geometry elimination criterion, the intermediate optimized path points are optimized to obtain an optimized path point sequence.
[0009] In one embodiment, the step of performing a multi-objective comprehensive evaluation of path quality on multiple groups of optimized path point sequences to screen out the optimal target planning path includes: Construct a multi-dimensional evaluation vector based on the path length index, average turning angle index and path complexity index; Based on the effectiveness penalty mechanism and the multidimensional evaluation vector, a weighted comprehensive evaluation algorithm is used to calculate the comprehensive evaluation value of each group of the optimized path point sequences; The optimal target planning path is obtained by screening according to the comprehensive evaluation value.
[0010] In one embodiment, the step of calculating the comprehensive evaluation value of each group of the optimized path point sequences using a weighted comprehensive evaluation algorithm based on the effectiveness penalty mechanism and the multi-dimensional evaluation vector includes: Calculate intermediate evaluation parameters through the effectiveness penalty mechanism; The comprehensive evaluation value of each group of the optimized path point sequences is calculated using a weighted comprehensive evaluation algorithm.
[0011] In one embodiment, the step of calculating the intermediate evaluation parameter using the effectiveness penalty mechanism includes: defining a path identification vector, wherein the identification vector includes a valid state and an invalid state; When the optimized path point sequence violates the motion constraint, the corresponding identification vector is set to an invalid state, and the optimized path point sequence that violates the motion constraint is defined as an invalid path; The quality evaluation parameter of the invalid path is multiplied by the preset penalty coefficient to obtain the intermediate evaluation parameter.
[0012] In one embodiment, after the step of performing a multi-objective comprehensive evaluation of path quality on the plurality of optimized path point sequences to screen out the optimal target planning path, the following step is further included: Based on the optimal target planning path, a desired heading angle is calculated using an adaptive guidance strategy; Obtain the actual heading angle according to the real-time motion status of the ship; Based on the deviation between the desired heading angle and the actual heading angle, a fuzzy adaptive PID controller is used to generate a rudder angle command; The ship's motion state is updated according to the rudder angle command, and the guidance strategy is cyclically executed to perform path tracking.
[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a path planning device for an unmanned ship, the path planning device for the unmanned ship comprising: An environmental map building module is used to build an environmental map based on the ship's current location information, destination location information, ship status information, and obstacle location information; An initial path generation module is used to generate an initial path point sequence in the environment map based on the ship motion characteristic constraints by using an improved progressive optimal rapid exploration random tree algorithm; An optimized path generation module is used to perform motion constraint-aware path optimization processing on the initial path point sequence and output an optimized path point sequence. The path optimization processing is used to optimize the problems of lengthy paths, frequent turns, and direct flight feasibility; A multiple-group path generation module, configured to obtain multiple groups of optimized path point sequences based on ship characteristic parameters with different degrees of constraint; The target path planning module is used to perform a multi-objective comprehensive evaluation of the path quality of multiple groups of the optimized path point sequences to screen out the optimal target planning path.
[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the unmanned ship path planning method as described above are implemented.
[0015] In addition, to achieve the above-mentioned purpose, the present application also proposes a path planning device for an unmanned ship, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the path planning method for an unmanned ship as described above.
[0016] One or more technical solutions proposed in this application have at least the following technical effects: (1) Based on the ship’s current location information, destination location information, ship status information, and obstacle location information, an environmental map is established to provide a complete obstacle avoidance basis for path search.
[0017] (2) In the environmental map, based on the constraints of the ship's motion characteristics, an improved asymptotically optimal rapid exploration random tree algorithm is used to generate an initial path point sequence. This solves the problem of missing path curvature constraints caused by the traditional algorithm not considering the under-actuated characteristics of the ship. The initial path point sequence strictly conforms to the physical maneuvering limit of the ship, eliminating the risk of planned waypoints exceeding the ship's motion performance.
[0018] (3) The initial path point sequence is subjected to motion constraint-aware path optimization processing, and the optimized path point sequence is output. This solves the problem of path post-processing damaging obstacle avoidance safety and curvature discontinuity, and generates a smooth path that can be directly and efficiently executed by the tracking controller.
[0019] (4) Based on the characteristic parameters of ships with different degrees of constraints, multiple sets of optimized path point sequences are obtained, which breaks through the limitation that the path under a single ship motion constraint condition is difficult to adapt to complex sea conditions. Finally, a multi-objective comprehensive evaluation of the path quality of multiple sets of optimized path point sequences is performed, and the optimal target planning path is screened out. This avoids the problems of mismatch between the motion performance required for path tracking and the ship working conditions, lengthy paths, and unstable control caused by frequent path turns in the unmanned ship path planning, and solves the problems of insufficient feasibility and low efficiency of ship path planning under complex sea conditions. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0022] Figure 1 This is a flow chart of the first embodiment of the path planning method for an unmanned ship of the present application; Figure 2 This is a flow chart of the second embodiment of the path planning method for an unmanned ship of the present application; Figure 3 This is a schematic diagram of the expansion of the waypoints without considering motion constraints in an embodiment of the present application; Figure 4 A schematic diagram of the expansion of a waypoint taking motion constraints into account according to an embodiment of the present application; Figure 5 This is a flow chart of the third embodiment of the path planning method for an unmanned ship of the present application; Figure 6 This is a schematic diagram of an embodiment of the present application before redundant points are eliminated; Figure 7 This is a schematic diagram of an embodiment of the present application after redundant points are eliminated; Figure 8 This is a flow chart of a fourth embodiment of the path planning method for an unmanned vessel of the present application; Figure 9 This is a schematic diagram of improving the RRT-star ship path planning results according to an embodiment of the present application; Figure 10 This is a schematic diagram of the visualization results of the turning angle parameters of the multi-constraint model of the ship according to the embodiment of the present application; Figure 11 This is a schematic diagram of the visualization results of the index parameters of the ship multi-constraint model according to the embodiment of the present application; Figure 12 Schematic diagram comparing the path planning results of traditional RRT, RRT-Star, and improved RRT-Star according to an embodiment of the present application; Figure 13 This is a flow chart of the ship path planning and tracking control system according to an embodiment of the present application; Figure 14 This is a schematic diagram of the module structure of the path planning device of the unmanned ship according to the embodiment of the present application; Figure 15 This is a schematic diagram of the device structure of the hardware operating environment involved in the path planning method of the unmanned ship in the embodiment of the present application.
[0023] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0024] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.
[0025] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0026] With the rapid development of global marine resource development and intelligent shipping, unmanned surface vessels (USVs) have become a research hotspot in the intelligent shipping field due to their widespread applications in environmental monitoring, military reconnaissance, and maritime search and rescue. Real-time path planning and robust tracking control in complex waters are key challenges hindering the large-scale deployment of USVs. In this context, achieving efficient path planning and precise tracking control for vessels in dynamic obstacle environments has become a focus of both academic and industrial attention.
[0027] Most current path planning algorithms are not suitable for ships and have not been improved based on the ship's motion characteristics. Since ships need to plan routes as quickly as possible, the planning algorithm must be fast. However, most current algorithms consume a lot of time and computing resources when faced with a large search space. Traditional improvement methods have two major limitations: first, path planning efficiency is low in complex sea conditions, making it difficult to match the physical maneuverability of the ship and the path feasibility is insufficient; second, path post-processing (such as Bezier curve smoothing) may undermine obstacle avoidance safety. In addition, most studies have not fully considered the constraints on path curvature imposed by the under-actuated characteristics of USVs, making it difficult for the planned path to be efficiently executed by the tracking controller.
[0028] Therefore, how to improve the feasibility and efficiency of ship path planning under complex sea conditions is a problem that needs to be solved urgently.
[0029] Based on this, the present application embodiment provides a path planning method for an unmanned ship, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the path planning method for an unmanned vessel of the present application.
[0030] In this embodiment, the path planning method of the unmanned ship includes steps S10 to S50: Step S10: creating an environment map based on the current position information of the ship, the position information of the destination, the status information of the ship, and the position information of obstacles.
[0031] It should be noted that vessel status information can include data such as the vessel's speed (motor speed can be set to a constant), heading angle, and other data. Obstacle location information can include the geometric boundary data and coordinate location information of static obstacles (islands, reefs, and submerged reefs) and dynamic obstacles (other ships). The environmental map can be understood as a dynamic spatial model that integrates the vessel's current position, destination, vessel status information, and obstacle location information.
[0032] Step S20: In the environment map, based on the ship motion characteristic constraints, an initial path point sequence is generated by using an improved progressive optimal rapid exploration random tree algorithm.
[0033] It should be noted that ship motion characteristic constraints may include maximum steering angle (the ship's instantaneous steering capability), minimum turning radius (the curvature limit to prevent loss of control and deviation from the route), and safety radius (collision buffer distance). The improved asymptotically optimal rapid exploration random tree algorithm can be understood as a free-space search method based on probabilistic exploration, generating feasible paths through constraint guidance. For example, the improved asymptotically optimal rapid exploration random tree algorithm here can be a multimodal improvement strategy based on the classic asymptotically optimal rapid exploration random tree algorithm (RRT-star) framework. It should be noted that the rapidly expanding random tree (RRT) is a sampling-based path planning algorithm suitable for high-dimensional spaces and unstructured environments. Its core concept is to gradually explore free space through random sampling and tree-structured expansion, ultimately generating a feasible path from the starting point to the end point. RRT-star is an improved version of RRT, proposed to address the limitations of suboptimal planning results. The improved Asymptotically Optimal Rapid Exploration Random Tree algorithm in this embodiment further improves RRT-star. It addresses the shortcomings of traditional methods in adapting to ship motion characteristics through a collaborative design approach involving kinematic constraint modeling, probabilistic sampling optimization, and path feasibility verification. The initial pathpoint sequence can be the original set of waypoints output by the improved Asymptotically Optimal Rapid Exploration Random Tree algorithm.
[0034] Step S30 , performing motion constraint-aware path optimization processing on the initial path point sequence, and outputting an optimized path point sequence. The path optimization processing is used to optimize the problems of lengthy paths, frequent turns, and direct flight feasibility.
[0035] It should be noted that motion-constraint-aware path optimization can be understood as a path smoothing technique based on the vessel's maneuverability (turn radius or angle). This includes pruning redundant points in the initial pathpoint sequence, geometric elimination, and path compression through skip connections. Path optimization can address issues such as lengthy paths, frequent turns, and the feasibility of direct navigation.
[0036] Step S40: obtaining multiple groups of optimized path point sequences based on ship characteristic parameters with different degrees of constraint.
[0037] It should be noted that the ship characteristic parameters with different degrees of constraint may include multiple sets of preset maneuverability configurations, and multiple sets of optimized path point sequences are correspondingly obtained according to the multiple sets of preset maneuverability configurations.
[0038] Step S50 , performing a multi-objective comprehensive evaluation of path quality on multiple groups of optimized path point sequences, and screening out the optimal target planning path.
[0039] For example, the multi-objective comprehensive evaluation can be a quantitative evaluation system that integrates path length (economy), average steering angle (smoothness), and number of path points (complexity). The optimal target planning path is the global optimal path selected from the group optimization path point sequence.
[0040] In this embodiment, an environmental map is established based on the vessel's current position information, destination location information, vessel status information, and obstacle location information, providing a comprehensive obstacle avoidance foundation for path search. Within the environmental map, an improved progressively optimal rapid exploration random tree algorithm is used to generate an initial pathpoint sequence based on the constraints of the vessel's motion characteristics. This addresses the lack of path curvature constraints caused by traditional algorithms that fail to consider the underactuated characteristics of the vessel. This ensures that the initial pathpoint sequence strictly complies with the vessel's physical maneuvering limits, eliminating the risk of planned waypoints exceeding the vessel's motion performance. Motion-constraint-aware path optimization is performed on the initial pathpoint sequence, outputting an optimized pathpoint sequence. This addresses the issues of path post-processing compromising obstacle avoidance safety, lengthy paths, frequent turns, and the feasibility of direct navigation, generating a smooth path that can be directly and efficiently executed by the tracking controller. Based on the characteristic parameters of ships with different degrees of constraints, multiple sets of optimized path point sequences are obtained, breaking through the limitation that the path under a single ship motion constraint condition is difficult to adapt to complex sea conditions. Finally, a multi-objective comprehensive evaluation of the path quality of multiple sets of optimized path point sequences is performed to screen out the optimal target planning path. This avoids problems such as the mismatch between the motion performance required to complete path tracking and the ship working conditions, the lengthy path, and the unstable control caused by frequent path turns in the unmanned ship path planning, and solves the problems of insufficient feasibility and low efficiency of ship path planning under complex sea conditions.
[0041] Reference Figure 2 , Figure 2 This is a flow chart of the second embodiment of the path planning method for the unmanned ship of this application, based on the above Figure 1 The first embodiment shown is a second embodiment of the path planning method for the unmanned ship of the present application.
[0042] In the second embodiment, step S20 includes: Step S201: constructing a dual-constraint model for ship motion, which is used to constrain the maximum steering angle and the minimum turning radius.
[0043] It should be noted that the dual-constraint model for ship motion can be understood as a mechanism for quantifying a ship's maneuverability. The classic RRT-star algorithm ignores the consideration of differential constraints on ship kinematics. This is because if a large turning angle occurs between two route segments at a waypoint, it will result in abrupt turns in the path that the ship cannot execute. If the distance between any two adjacent waypoints is too short (i.e., less than the turning radius constraint), then when the ship is traveling at a preset speed and the distance traveled by the ship is calculated from the start of steering, when the heading angle reaches the maximum turning angle, the distance traveled by the ship will be greater than the path length between the waypoints. This makes it impossible for the ship to accurately reach the planned waypoint. In other words, if the planned path does not take into account the ship's kinematic characteristics, the unmanned vessel will easily run off the waypoint and deviate from the route during navigation. Therefore, the dual-constraint model for ship motion in this embodiment ensures that the generated path conforms to the ship's actual maneuverability by setting a maximum turning angle (the limit of a single turn) and a minimum turning radius (the minimum radius of curvature required for the ship to turn).
[0044] For example, the dual-constraint model of ship motion can be expressed as formula (1).
[0045] (1) In formula (1), is the turning angle between two routes, is the maximum steering angle of the unmanned ship, is the distance of the path between two waypoints, is the minimum turning radius, where the turning angle It is determined by the vector space relationship and expressed as formula (2).
[0046] (2) In formula (2), and represents the unit vectors of adjacent flight segments, which are expressed as formula (3) and formula (4) respectively.
[0047] (3) (4) In formula (3) and formula (4), Represents a given sequence of continuous path nodes.
[0048] Step S202 : generating random sampling points using a dynamic hybrid sampling mechanism, where the dynamic hybrid sampling mechanism includes path reinforcement sampling, target biased sampling, heuristic sampling, and uniform random sampling.
[0049] It should be noted that the dynamic hybrid sampling mechanism addresses the inefficiency of traditional uniform random sampling strategies in constrained spaces. It can be understood as an adaptive random sampling strategy used to improve convergence speed. Dynamic hybrid sampling mechanisms can include path-enhanced sampling, target-biased sampling, heuristic sampling, and uniform random sampling.
[0050] For example, the first step is path-enhanced sampling. If a path has been found, there is an 80% probability of sampling near the path. The sampling function is expressed as formula (5).
[0051] (5) In formula (5), is a Gaussian distribution, Controllable expansion step size, For random nodes in the existing path. To improve the efficiency of expansion to the target, set the target bias sampling. When it is less than the preset target bias probability When (here Take 0.5), and the target point can be sampled directly. Heuristic sampling generates bias samples along the line connecting the starting point and the end point. Dynamic sampling has a 30% probability of applying heuristic sampling, which is expressed as formula (6) and formula (7).
[0052] (6) (7) In formula (6) and formula (7), t is a random sampling of the interval (0,1), which determines the position ratio on the line connecting the starting point (start) and the end point (goal), that is, when t =0, As a starting point, when t =1 The purpose is to bias the sampling point toward the direction of the line connecting the starting point and the end point, accelerating the algorithm to search the target area. is a Gaussian distribution, with As the center, generate random points that follow a normal distribution around it. Finally, set up regular random sampling to uniformly sample randomly throughout the map.
[0053] Step S203: perform node expansion on the random sampling points to obtain an expanded node set.
[0054] It should be noted that the process of generating new candidate nodes from random sampling points can form an extended node set by connecting the current node and the sampling point and extending it to a reachable position. The node extension is used to expand the path search space.
[0055] For example, Figure 3As shown in Figure 2, since the node expansion of traditional RRT does not consider motion constraints, this study improves the expansion strategy to make it consistent with the ship's motion characteristics. When the ship expands, it is necessary to consider the angle difference between the current heading and the target heading. If it exceeds the maximum steering angle, it is expanded according to the maximum steering angle, as shown in Figure 2. Figure 4 shown.
[0056] First, set the current node heading angle to , waypoints on the target path 、 They are 、 , then the expected heading angle It is expressed as formula (8).
[0057] (8) The formula for calculating and normalizing the relative steering angle is expressed as formula (9).
[0058] (9) when When the maximum steering angle is used The calculation method of the clipping and constrained heading is expressed as formula (10).
[0059] (10) The new node coordinates can be determined by the constrained heading, expressed as formula (11).
[0060] (11) In formula (11), For distance The nearest node, For the to A controllable step size for directional expansion, A new node is generated.
[0061] Step S204 , applying the dual-constraint model of ship motion to the extended node set, performing collision detection and steering feasibility verification on each node, and iteratively generating an initial path point sequence.
[0062] It's important to note that collision detection verifies whether node positions overlap with obstacles. Steering feasibility verification, based on a dual-constraint model, checks the compliance of steering angles and turning radii between adjacent nodes to ensure a smooth and feasible path. Ultimately, through repeated expansion, verification, and node selection, the initial pathpoint sequence is gradually constructed.
[0063] For example, the dual-constraint model of ship motion is applied to the extended node set, and the dual constraints of the dual-constraint model of ship motion and the collision constraints on obstacles are realized through discretization processing, which is expressed as formula (12).
[0064] (12) In formula (12), and They are steering constraint verification and collision constraint verification functions, is the node of the random tree.
[0065] In this embodiment, by constructing a dual-constraint model of ship motion and imposing hard limits on the maximum steering angle and minimum turning radius, a feasible path space that conforms to the ship's kinematic characteristics is derived. This solves the problem of path curvature discontinuity caused by traditional random tree sampling due to ignoring maneuvering constraints. A dynamic hybrid sampling mechanism is used to dynamically complement local optimization and global guidance, resulting in a more efficient sampling point distribution and addressing the high blindness and slow convergence of random sampling. Node expansion generates an extended node set, enhancing the completeness of the path search. Finally, during the iterative generation process, the extended nodes are double-screened through collision detection and steering feasibility verification to obtain an initial path point sequence, which considers the ship's motion characteristics while also enhancing convergence speed.
[0066] Reference Figure 5 , Figure 5 This is a flow chart of the third embodiment of the path planning method for an unmanned ship of this application, based on the above Figure 2 The second embodiment shown is a third embodiment of the path planning method for the unmanned ship of the present application.
[0067] In the third embodiment, step S30 includes: Step S301: Remove intermediate nodes that meet redundancy conditions in the initial path point sequence through path pruning to obtain initial optimized path points.
[0068] It should be noted that path pruning is a redundant node removal strategy. The core idea of path pruning is to remove redundant points from the path while retaining key turning points. The criterion for determining whether a point is redundant is that the path still satisfies steering constraints and is collision-free after removing the point. By detecting intermediate nodes in the initial path point sequence that meet the redundancy criteria (such as collinear nodes or nodes with a change in motion direction below a threshold), non-essential nodes are removed to generate the initial optimized path points, thus shortening the path length.
[0069] For example, the initial path node sequence is first calculated according to the node expansion strategy of the algorithm. ,The path pruning algorithm removes redundant nodes by verifying the steering constraint and the collision constraint. Select the existing candidate nodes , the steering angle can be calculated as shown in formula (13).
[0070] (13) In formula (13), and They are expressed as formula (14) and formula (15) respectively.
[0071] (14) (15) It should be noted that if the path satisfy ,or If there is a collision in the path segment, or the path length is less than 2 times the minimum turning radius, the current node needs to be retained. Otherwise, it is allowed to skip the intermediate nodes .
[0072] Step S302: Perform jump connections on the initial optimized path points to obtain intermediate optimized path points.
[0073] It should be noted that skip connections can be a path smoothing technique. Its core idea is to connect distant points while satisfying steering constraints and avoiding collisions. A reverse verification strategy is used to find the maximum feasible span, reducing the number of intermediate points in the path. This is essentially a greedy strategy, always attempting to connect to the farthest point that the current point can directly reach. The initial optimized path points after pruning can be tested for long-distance straight-line connections. If there are no obstacles between the two points and the motion constraints are met, the intermediate nodes are skipped and a direct connection is made, generating intermediate optimized path points and reducing path twists.
[0074] For example, the upper limit of the span can be set to ,in is the maximum jump distance, is the number of generated path points. The purpose is to reversely search for the first node that satisfies the ship motion constraints and collision constraints, thereby achieving path compression, which is expressed as formula (16).
[0075] (16) In formula (16), For the optimized path nodes, in order to enhance the safety of the planned path, we expand the range of obstacles to a circular area. , then treat the ship as a point mass and set its safety radius to , the safety factor can be 1.2, and the expansion safety distance of the obstacle can be obtained as , that is, the collision constraint effect is enhanced by expanding the detection distance.
[0076] It should be noted that if the node jump stage has been processed to the last point, the last point is added to the optimized path. In the process, perform another collision check to check its connection with the end point to ensure that there will be no collision with obstacles. If a direct connection causes a collision, insert an intermediate point (midpoint). The midpoint coordinates are selected as the average of the sum of the coordinates of the last point of the current optimized path and the last point of the original path. If the midpoint does not work, try adding the second to last point of the original path.
[0077] Step S303: Based on the redundant point geometry elimination criterion, the intermediate optimized path points are optimized to obtain an optimized path point sequence.
[0078] It should be noted that the redundant point geometric elimination criterion is based on the geometric constraints of the minimum turning radius for the path points after jump connection, and deletes or adjusts the points that do not conform to the straight-line continuity of the ship to generate the final optimized path point sequence.
[0079] For example, when the distance between adjacent nodes is less than 20% of the minimum turning radius, the nodes are merged, which is expressed as formula (17).
[0080] (17) That is, if the current point is too close to the last added point, the current point will be skipped. Calculate the direction vector, expressed as formula (18) and formula (19).
[0081] (18) (19) It should be noted that when the direction deviation is less than 5°, that is, , it means that the three points are approximately collinear and the middle point can be deleted , the schematic diagram can be referred to Figure 6 (before redundant points are eliminated) and Figure 7 (After eliminating redundant points). Finally, the obstacle collision constraint function can be used to check that the entire path will not collide with obstacles. Finally, after a series of optimizations, the optimized path node sequence is obtained. .
[0082] In this embodiment, path pruning is used to remove redundant nodes, solving the problem of excessive nodes and low path efficiency in the initial path point sequence due to sampling redundancy. By deducing the convergence of node collinearity and motion direction, invalid intermediate points are directly reduced. By using jump connections to connect the optimized points in a barrier-free straight line, the problem of too many broken line segments and sudden changes in curvature in the path is solved. Long-distance straight line paths are derived to replace multi-segment broken lines to achieve a reduction in the number of turning points. The geometric compliance of the path after the jump is optimized by combining the redundant point geometric elimination criterion. By merging nodes with too small spacing and deleting approximately collinear intermediate points, the feasibility problem of direct navigation caused by node redundancy is solved, ensuring that frequent course adjustments are reduced and the ship can sail smoothly.
[0083] Reference Figure 8 , Figure 8 This is a flow chart of the fourth embodiment of the path planning method for an unmanned ship of this application, based on the above Figure 5 The third embodiment shown is a fourth embodiment of the path planning method for the unmanned ship of the present application.
[0084] In the fourth embodiment, step S50 includes: Step S501 : constructing a multi-dimensional evaluation vector based on the path length index, the average steering angle index, and the path complexity index.
[0085] It should be noted that the multidimensional evaluation vector is a vector structure that quantifies the path quality with multiple indicators, including the path length indicator, the average turning angle indicator, and the path complexity indicator.
[0086] Taking the three-dimensional feature vector as an example, we can first define the ship multi-constraint model set as , where each multi-constraint model contains a safety radius around the ship , Minimum turning radius of the ship , Maximum turning angle of the ship Kinematic parameters, i.e. ; Let the candidate path set be , each path corresponds to a three-dimensional feature vector, and the three-dimensional feature vector is expressed as formula (20).
[0087] (20) In formula (20), Represents the quality evaluation index of the generated path, and executes the improved RRT-star algorithm to generate paths, and the three-dimensional feature vector of each path corresponds to three groups of evaluation indicators, which are expressed as formula (21).
[0088] (twenty one) In formula (21), represents the path length index, represents the average steering angle index, Represents the path complexity index. For each path , construct the original indicator matrix, expressed as formula (22).
[0089] (twenty two) In formula (22), The matrix containing the indicator parameters of each path is column-normalized to avoid dimension differences, which is expressed as formula (23).
[0090] (twenty three) Step S502 : Based on the effectiveness penalty mechanism and the multi-dimensional evaluation vector, a weighted comprehensive evaluation algorithm is used to calculate the comprehensive evaluation value of each group of optimized path point sequences.
[0091] It should be noted that the validity penalty mechanism can be understood as a path compliance enforcement method. Step S502 includes: calculating intermediate evaluation parameters through the validity penalty mechanism; and calculating the comprehensive evaluation value of each group of optimized path point sequences through a weighted comprehensive evaluation algorithm.
[0092] Specifically, the steps of calculating the intermediate evaluation parameters through the validity penalty mechanism include: defining a path identification vector, the identification vector includes a valid state and an invalid state; when the optimized path point sequence violates the motion constraint, the corresponding identification vector is set to an invalid state, and the optimized path point sequence that violates the motion constraint is defined as an invalid path; the quality evaluation parameter of the invalid path is multiplied by the preset penalty coefficient to obtain the intermediate evaluation parameter.
[0093] For example, a validity penalty mechanism is set, and the path validity identification vector A is defined as formula (24).
[0094] (twenty four) In formula (24), It is expressed as formula (25).
[0095] (25) The penalty imposed on invalid paths is expressed as formula (26).
[0096] (26) In formula (26), is the Hadamard product, and its purpose is to expand the quality evaluation of invalid paths by 1.5 times.
[0097] Step S503: Filter according to the comprehensive evaluation value to obtain the optimal target planning path.
[0098] It should be noted that the weighted comprehensive evaluation algorithm can assign weights according to the importance of each indicator, integrate the multi-dimensional evaluation vector and the penalty-adjusted intermediate evaluation parameters, and calculate the comprehensive evaluation value of the path.
[0099] For example, the optimal path selection by weighted comprehensive evaluation can be expressed as formula (27).
[0100] (27) In formula (27), the weight vector for , then the optimal path index It can be determined by formula (28).
[0101] (28) It should be noted that the advantage of the multi-path planning strategy is that the generated path can adapt to different types of ship working conditions, provide multiple alternatives, increase the planning success rate, and at the same time, conduct a comprehensive evaluation based on actual needs to screen out the most suitable path.
[0102] This embodiment addresses the problem of traditional single-metric evaluations failing to fully reflect path quality by constructing a multidimensional evaluation vector. A validity penalty mechanism applies a penalty coefficient to paths that violate motion constraints, generating intermediate evaluation parameters and addressing the problem of invalid paths being included in the evaluation. A weighted comprehensive evaluation algorithm, integrating the multidimensional vector with the penalty results, addresses the limitation of irrational weight distribution for multiple objectives. Ultimately, the optimal target planning path is selected based on the comprehensive evaluation value, addressing the randomness inherent in manual selection. Global comparison is then used to directly output the global optimal solution under multiple constraints.
[0103] In one implementation, to verify the effectiveness of the improved RRT-star algorithm described in the above examples, an experimental environment was constructed based on the topological characteristics of the Zhoushan Archipelago waters. The core of this experimental environment was to couple obstacle modeling with ship motion constraint analysis. In constructing this simulation environment, vector polygon modeling technology was employed to achieve high-precision ocean terrain reconstruction. By defining a structure array containing polygon vertex coordinates, the irregular contours of the major islands were accurately depicted.
[0104] Specifically, in terms of motion constraint modeling, this study constructed a ship motion model with five different constraint levels. Table 1 shows the parameters of the ship's multi-constraint model. Based on the combined effects of the ship's navigation safety distance constraint, minimum turning radius constraint, and maximum turning angle, the constraints are divided into five levels: super strict (SS), strict (S), medium (M), loose (L), and ultra flexible (UF). Through this hierarchical setting, the system evaluates the adaptability of the algorithm for unmanned ship path planning under different constraint levels.
[0105] Table 1
[0106] Table 2 shows the parameter details of the algorithm to complete USV path planning under different degrees of constraints.
[0107] Table 2
[0108] Figure 9 It represents the five planned paths planned by the improved RRT algorithm based on the five ship multi-constraint models in Table 1. It can be seen that the direction changes of each feasible path segment are smoothly transitioned to the next segment within the allowable range of its multi-constraint parameters, and are all suitable as tracking paths for unmanned ships. Finally, the path length, average turning angle and number of path points are used as fitness indicators for evaluation. The optimal path is the fourth path (strict constraint S), which is smoother and has a total path length of 23338.9m. There are only three heading change points and the average change in route direction is about 13.4°. It can be selected as the optimal target path for the unmanned ship. The visualization results of the indicator parameters of the ship multi-constraint model can be referred to Figure 10 and Figure 11 .
[0109] To verify the superior performance of the improved RRT-Star algorithm designed in this paper in ship path planning, we compared it with the traditional RRT algorithm and the conventional RRT-Star algorithm. First, using the Zhoushan Archipelago waters map, we set the starting point to (2000m, 2000m) and the end point to (18000m, 18000m). The basic algorithm parameters are shown in Table 3.
[0110] Table 3
[0111] Through simulation calculation, we can obtain the paths and parameters planned by the three algorithms: traditional RRT, conventional RRT-Star, and improved RRT-Star. Figure 12 , as shown in Table 4.
[0112] Table 4
[0113] The data shows that the distance planned by the improved RRT-Star algorithm is 8177.68 meters shorter than that of the traditional RRT algorithm, which is a 25.95% reduction in distance. It is 3809.23 meters shorter than that of the RRT-Star algorithm, which is a 14.03% reduction in distance. In terms of path smoothness, the improved RRT-Star algorithm improves performance by 64.69% compared with the traditional RRT algorithm and by 48.22% compared with the RRT-Star algorithm. The path complexity is reduced by 91.46% compared with the traditional RRT algorithm and by 88.1% compared with the RRT-Star algorithm.
[0114] It should be noted that the traditional method lacks collaborative design between planning and control, which leads to frequent path switching and large fluctuations in rudder angle commands; as well as the limited robustness of traditional solutions to multi-source disturbances (such as ocean currents, wind and waves) and the lack of adaptability. The following implementation method is proposed.
[0115] In one embodiment, based on the above embodiment, after step S50, it also includes: planning a path based on the optimal target, calculating the desired heading angle through an adaptive guidance strategy; obtaining the actual heading angle according to the real-time motion state of the ship; generating a rudder angle instruction through a fuzzy adaptive PID controller based on the deviation between the desired heading angle and the actual heading angle; updating the ship motion state according to the rudder angle instruction, and cyclically executing the guidance strategy for path tracking.
[0116] For example, Figure 13 As shown in the figure, after determining the optimal target planning path, the real-time coordinates of the ship can be obtained through the mathematical model of ship motion. Then, the actual desired heading angle of the ship can be obtained by calculating the line-of-sight guidance algorithm or strategy. , and then obtain the real-time heading angle of the ship according to the ship motion equation, and obtain the heading deviation by subtracting the observed heading angle from the actual expected heading angle , and the heading deviation rate is also calculated , and then this heading deviation , heading deviation rate The parameters are input into the fuzzy adaptive PID control algorithm program. The heading deviation and heading deviation rate are calculated by the fuzzy algorithm and the three gain parameters of PID are output in real time. At this time, the fuzzy algorithm output Gain parameters, and heading deviation Input into the PID controller, and after calculation, the rudder angle of the ship can be output Inputting the ship's rudder angle into the steering gear (which can be calculated using the ship's motion equations) calculates and outputs the ship's motion state at the next moment, thereby forming a closed loop that continuously updates the ship's state at the next moment, gradually bringing the ship closer to the target path point. Finally, after updating the ship's motion state information, it is determined whether the target waypoint has been reached. If not, the adaptive guidance strategy link is returned to continue the tracking process. If so, it is determined whether the current waypoint is the last point of the planned track. If not, the tracking is continued at the next waypoint. If so, the process ends and the path tracking task is completed.
[0117] In this implementation, the problem of control input response hysteresis is addressed by obtaining the deviation between the actual and desired heading angles in real time. Precise feedback from the deviation provides a basis for immediate deviation correction. A fuzzy adaptive PID controller generates rudder angle commands based on the deviation, addressing the issue of insufficient robustness under multi-source disturbances. Disturbance resistance is derived through adaptive parameter adjustment based on fuzzy rules (dynamically optimizing PID coefficients based on deviation and rate of change of deviation). Finally, the ship's state is updated based on the rudder angle command, and the guidance strategy is cyclically executed, collaboratively achieving a breakthrough in path tracking stability.
[0118] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the path planning method of the unmanned boat of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.
[0119] This application also provides a path planning device for an unmanned ship, please refer to Figure 14 , the path planning device of the unmanned ship includes: An environment map building module 10 is used to build an environment map based on the current position information of the ship, the position information of the destination, the state information of the ship, and the position information of obstacles; An initial path generation module 20 is configured to generate an initial path point sequence in the environment map based on the ship motion characteristic constraints by using an improved progressive optimal rapid exploration random tree algorithm; An optimized path generation module 30 is configured to perform motion constraint-aware path optimization processing on the initial path point sequence and output an optimized path point sequence, wherein the path optimization processing is used to optimize the problems of lengthy paths, frequent turns, and direct flight feasibility; A multiple-group path generation module 40 is used to obtain multiple groups of optimized path point sequences based on ship characteristic parameters with different degrees of constraint; The target path planning module 50 is used to perform a multi-objective comprehensive evaluation of path quality on multiple groups of the optimized path point sequences, and screen out the optimal target planning path.
[0120] The unmanned ship path planning device provided in this application adopts the unmanned ship path planning method of the above-mentioned embodiment, which can solve the technical problems of insufficient feasibility and low efficiency of ship path planning in complex sea conditions. Compared with the existing technology, the beneficial effects of the unmanned ship path planning device provided in this application are the same as the beneficial effects of the unmanned ship path planning method provided in the above-mentioned embodiment, and the other technical features of the unmanned ship path planning device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.
[0121] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, and the computer-readable program instructions are used to execute the path planning method for the unmanned ship in the above-mentioned embodiment.
[0122] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.
[0123] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the path planning device of the unmanned ship, the path planning device of the unmanned ship: establishes an environmental map based on the current position information of the ship, the destination position information, the ship status information and the obstacle position information; in the environmental map, based on the ship motion characteristic constraints, generates an initial path point sequence through an improved progressive optimal rapid exploration random tree algorithm; performs motion constraint-aware path optimization processing on the initial path point sequence, and outputs an optimized path point sequence, and the path optimization processing is used to optimize the problems of long paths, frequent turns and direct navigation feasibility; obtains multiple groups of the optimized path point sequences based on ship characteristic parameters with different degrees of constraints; performs a multi-objective comprehensive evaluation of path quality on the multiple groups of the optimized path point sequences, and screens out the optimal target planning path.
[0124] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.
[0125] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned unmanned vessel path planning method. This computer-readable storage medium can address the technical issues of insufficient feasibility and inefficiency in vessel path planning under complex sea conditions. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the unmanned vessel path planning method provided in the aforementioned embodiments and are not further elaborated here.
[0126] The present application provides a path planning device for an unmanned ship, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the path planning method for the unmanned ship in the above-mentioned embodiment one.
[0127] Reference below Figure 15, which shows a schematic diagram of the structure of a path planning device suitable for implementing an unmanned vessel in an embodiment of the present application. The path planning device for the unmanned vessel in an embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and fixed terminals such as digital TVs and desktop computers. Figure 15 The path planning device of the unmanned ship shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0128] like Figure 15 As shown, the path planning device for the unmanned vessel may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the path planning device for the unmanned vessel. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008, such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003, such as a magnetic tape or hard disk; and communication device 1009. The communication device 1009 can allow the path planning device of the unmanned ship to communicate with other devices wirelessly or by wire to exchange data. Figure 15 The path planning device for an unmanned ship is shown with various systems, but it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have alternatively.
[0129] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0130] The unmanned vessel path planning device provided in this application, which adopts the unmanned vessel path planning method of the above-mentioned embodiment, can solve the technical problems of insufficient feasibility and low efficiency of vessel path planning in complex sea conditions. Compared with the prior art, the beneficial effects of the unmanned vessel path planning device provided in this application are the same as those of the unmanned vessel path planning method provided in the above-mentioned embodiment, and the other technical features of the unmanned vessel path planning device are the same as those disclosed in the above-mentioned embodiment method, which will not be repeated here.
[0131] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0132] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A path planning method for an unmanned ship, characterized in that: The method includes: Create an environmental map based on the ship's current location information, destination location information, ship status information, and obstacle location information; In the environment map, based on the ship motion characteristic constraints, an initial path point sequence is generated by an improved progressive optimal rapid exploration random tree algorithm; Performing motion constraint-aware path optimization processing on the initial path point sequence and outputting an optimized path point sequence, wherein the path optimization processing is used to optimize problems such as lengthy paths, frequent turns, and direct flight feasibility; Obtaining multiple groups of optimized path point sequences based on ship characteristic parameters with different degrees of constraint; Performing a multi-objective comprehensive evaluation of path quality on multiple groups of optimized path point sequences to screen out the optimal target planning path; The step of performing a multi-objective comprehensive evaluation of path quality on multiple groups of optimized path point sequences to screen out the optimal target planning path includes: Construct a multi-dimensional evaluation vector based on the path length index, average turning angle index and path complexity index; Based on the effectiveness penalty mechanism and the multi-dimensional evaluation vector, a comprehensive evaluation value of each group of the optimized path point sequences is calculated by a weighted comprehensive evaluation algorithm; The optimal target planning path is obtained by screening according to the comprehensive evaluation value.
2. The method according to claim 1, wherein The step of generating an initial path point sequence in the environment map by using an improved progressive optimal rapid exploration random tree algorithm based on the ship motion characteristic constraints includes: Constructing a dual-constraint model for ship motion, wherein the dual-constraint model for ship motion is used to constrain a maximum steering angle constraint and a minimum turning radius; A dynamic hybrid sampling mechanism is used to generate random sampling points, wherein the dynamic hybrid sampling mechanism includes path reinforcement sampling, target bias sampling, heuristic sampling and uniform random sampling; Performing node expansion on the random sampling points to obtain an expanded node set; The dual-constraint model of ship motion is applied to the extended node set, collision detection and steering feasibility verification are performed on each node, and an initial path point sequence is iteratively generated.
3. The method according to claim 1, wherein The step of performing motion constraint-aware path optimization processing on the initial path point sequence and outputting an optimized path point sequence comprises: Removing intermediate nodes that meet redundancy conditions from the initial path point sequence through path pruning to obtain initial optimized path points; Performing jump connections on the initial optimized path points to obtain intermediate optimized path points; Based on the redundant point geometry elimination criterion, the intermediate optimized path points are optimized to obtain an optimized path point sequence.
4. The method according to claim 1, wherein The step of calculating the comprehensive evaluation value of each group of the optimized path point sequences by a weighted comprehensive evaluation algorithm based on the effectiveness penalty mechanism and the multi-dimensional evaluation vector includes: Calculate intermediate evaluation parameters through the effectiveness penalty mechanism; The comprehensive evaluation value of each group of the optimized path point sequences is calculated using a weighted comprehensive evaluation algorithm.
5. The method according to claim 4, wherein The step of calculating the intermediate evaluation parameter through the effectiveness penalty mechanism includes: defining a path identification vector, wherein the identification vector includes a valid state and an invalid state; When the optimized path point sequence violates the motion constraint, the corresponding identification vector is set to an invalid state, and the optimized path point sequence that violates the motion constraint is defined as an invalid path; The quality evaluation parameter of the invalid path is multiplied by the preset penalty coefficient to obtain the intermediate evaluation parameter.
6. The method according to any one of claims 1 to 5, characterized in that After the step of performing a multi-objective comprehensive evaluation of path quality on the plurality of optimized path point sequences to screen out the optimal target planning path, the method further includes: Based on the optimal target planning path, a desired heading angle is calculated using an adaptive guidance strategy; Obtain the actual heading angle according to the real-time motion status of the ship; Based on the deviation between the desired heading angle and the actual heading angle, a fuzzy adaptive PID controller is used to generate a rudder angle command; The ship's motion state is updated according to the rudder angle command, and the guidance strategy is cyclically executed to perform path tracking.
7. A path planning device for an unmanned ship, characterized in that: The device comprises: An environmental map building module is used to build an environmental map based on the ship's current location information, destination location information, ship status information, and obstacle location information; An initial path generation module is used to generate an initial path point sequence in the environment map based on the ship motion characteristic constraints by using an improved progressive optimal rapid exploration random tree algorithm; An optimized path generation module is used to perform motion constraint-aware path optimization processing on the initial path point sequence and output an optimized path point sequence. The path optimization processing is used to optimize the problems of lengthy paths, frequent turns, and direct flight feasibility; A multiple-group path generation module, configured to obtain multiple groups of optimized path point sequences based on ship characteristic parameters with different degrees of constraint; A target path planning module is used to perform a multi-objective comprehensive evaluation of path quality on multiple groups of optimized path point sequences to screen out the optimal target planning path; The target path planning module is further used to construct a multidimensional evaluation vector based on the path length index, the average steering angle index and the path complexity index; based on the effectiveness penalty mechanism and the multidimensional evaluation vector, calculate the comprehensive evaluation value of each group of the optimized path point sequence through a weighted comprehensive evaluation algorithm; and screen according to the comprehensive evaluation value to obtain the optimal target planning path.
8. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the path planning method for the unmanned ship according to any one of claims 1 to 6 are implemented.
9. A path planning device for an unmanned ship, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the path planning method for the unmanned ship according to any one of claims 1 to 6.
Citation Information
Patent Citations
Unmanned ship path optimization method and system based on multi-objective optimization
CN114111824A
Multi-task-point path planning method for multiple unmanned surface vessels based on event triggering mechanism
CN118274837A
Unmanned ship track planning system for underwater data acquisition
CN119289999A
Cited By
Auxiliary control method and device for under-actuated ocean vessel and electronic equipment
CN121349084A
Unmanned ship multi-agent collaborative obstacle avoidance method and system for complex sea conditions
CN121386793A
Unmanned ship dynamic path re-planning method based on elastic emergency route network
CN121415630A
Target tracking and trend prediction method and system based on open and closed source information fusion
CN122360508A