A Path Planning Method for Unmanned Surface Vessels
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2026-06-01
- Publication Date
- 2026-08-14
AI Technical Summary
[0006]有鉴于此，本发明提出了一种水面无人艇路径规划方法，通过设计动态竞争强度调节机制和自适应学习因子更新策略，有效解决了算法在多威胁环境下探索与开发能力失衡的问题，显著提升了路径规划的全局优化能力和收敛速度
（1）本发明设计了随适应度值动态变化的撤退因子，适应度较差的成员面临更强的竞争压力，加速了劣势个体的淘汰和优势信息的传播，提升了算法快速定位全局最优解的能力。
Smart Images
Figure CN122281940B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of autonomous navigation technology for unmanned surface vessels, specifically relating to a path planning method for unmanned surface vessels in multi-threat water environments. Background Technology
[0002] Unmanned surface vessels (USVs) have been widely used in recent years in fields such as marine scientific research, environmental monitoring, and disaster relief due to their safety, high efficiency, and maneuverability. Because USVs can operate autonomously in complex and dangerous aquatic environments, effectively avoiding the safety risks and high costs associated with manual operation, they have become a key component of future intelligent marine equipment.
[0003] Path planning is one of the core technologies of the USV autonomous navigation system. Its core task is to generate an optimal or feasible route between a given starting point and a destination that meets various constraints, so as to ensure safe and efficient navigation in aquatic environments with obstacles and threats.
[0004] Among existing path planning algorithms, swarm intelligence-based optimization methods are better suited than traditional deterministic algorithms to handle the dynamic obstacle avoidance and multi-objective optimization challenges faced by USVs due to their parallel computing capabilities and global search characteristics. Among these, the Tribal Competition and Member Cooperation (CTCM) algorithm, by simulating inter-tribal competition and member collaborative learning, demonstrates superior performance compared to traditional particle swarm optimization and genetic algorithms in balancing exploration and development capabilities.
[0005] However, the CTCM algorithm still has key shortcomings in practical USV path planning. Its competition mechanism relies primarily on static fitness evaluation, lacking the ability to respond to dynamic changes in tribe fitness, which limits the speed and accuracy of finding the global optimum in complex threat environments. Furthermore, its cooperative learning among members employs a fixed update strategy, making it difficult to achieve a good balance between the algorithm's global exploration capabilities in the early stages of iteration and its local development capabilities in the later stages. Summary of the Invention
[0006] In view of this, this invention proposes a path planning method for unmanned surface vessels. By designing a dynamic competition intensity adjustment mechanism and an adaptive learning factor update strategy, it effectively solves the problem of imbalance between the exploration and development capabilities of the algorithm in a multi-threat environment, and significantly improves the global optimization capability and convergence speed of path planning.
[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution:
[0008] This invention provides a path planning method for unmanned surface vessels, comprising: Determine the navigable boundaries of unmanned surface vessels in a water environment; A tribe is initialized based on the boundary of the passable area. The tribe contains multiple members, and each member corresponds to a path of an unmanned surface vessel. Construct a multi-objective fitness function, calculate the fitness value of each member in the initial tribe, and update the fitness values of the best member of each tribe, the best member of the opponent tribe, and the fitness value of the global best member based on the fitness values. Perform iterative optimization of tribal competition and member cooperation, which includes: calculating a retreat factor based on the target's best fitness value and the opponent's tribe's best fitness value, updating the speed and position of tribe members based on the retreat factor to generate a new unmanned surface vessel path, and updating the tribe's optimal path and the global optimal path. After the iteration termination condition is met, the globally optimal path obtained in the last iteration is output as the final planned path of the unmanned surface vessel.
[0009] Furthermore, the boundaries of the navigable area for unmanned surface vessels in a water environment are determined, including: Get or set the coordinates of the starting point and the target point; Acquire or set information about the water surface environment, including the geometric boundaries of static obstacles and the location and range of dynamic threat areas; The entire surface water space, excluding obstacles and threat areas, is marked as a passable area.
[0010] Further, initializing the tribe based on the boundary of the passable area includes: Configure algorithm parameters, including the number of tribes. Number of members in a single tribe Number of path nodes Maximum number of iterations Inertia weight upper limit Lower bound of inertia weight Individual factors The range of values, population factor The range of values and the withdrawal factor The range of values for; Each member is encoded as a path, and the path is... The path is represented by a continuous coordinate sequence of two-dimensional path points, where the starting point and the target point are fixed. Set constraints for path planning, including that the path must not pass through any obstacles or threat areas, and that the sequence of path points must be located within a passable area; Randomly initialize the position vectors of all members within the passable area. and velocity vector Ensure the initial path does not cross obstacles or threat areas; The members are divided equally into There are 10 tribes, each tribe containing One member; Each member's individual position is initialized to its initial position, and the tribe's optimal position is the position of the most fit member in that tribe.
[0011] Furthermore, the multi-objective fitness function is: ,in, , , These are the weighting coefficients in the fitness function, used to adjust the importance of each path's evaluation index; Evaluation function for cumulative length:
[0012] in, and The first The and the first Cartesian coordinates of the path points The total number of nodes; For the smoothness evaluation function:
[0013] in, This is the penalty coefficient for cornering. The angle between the two paths. for:
[0014] in, and The vectors represent adjacent path segments; if the turning changes and maximum yaw rate in the planned route exceed the limits, the current execution is deemed an invalid plan. For safety performance evaluation functions:
[0015] in, Z To represent the number of threats, assuming each threat is a cylinder, Let the radius of the regular cylindrical obstacle be . The diameter of the unmanned surface vessel. The safe distance for the collision zone, The safety value of unmanned surface vessels reaching every obstacle. This is the distance from the unmanned surface vessel to the center of the obstacle.
[0016] Furthermore, the withdrawal factor for:
[0017] in, and They are respectively The minimum and maximum values; The fitness value of the globally optimal member. The fitness value of the best member of the opposing tribe.
[0018] Furthermore, iterative optimization of tribal competition and member cooperation also includes: The positions of tribe members are updated based on an adaptive inertial weight strategy to generate new paths for unmanned surface vessels; the inertial weights are:
[0019] in, For inertial weights, This represents the current iteration number. The maximum number of iterations, This is the inertia weight adjustment factor, used to control the nonlinearity of the inertia weight as it changes with the number of iterations.
[0020] Furthermore, iterative optimization of tribal competition and member cooperation also includes: Based on sinusoidal acceleration optimization and Update tribe member locations to generate new unmanned surface vessel paths; and for:
[0021]
[0022] in, and They are respectively and The minimum value, and They are respectively and The maximum value.
[0023] Furthermore, the member's velocity update formula is:
[0024] The formula for updating member positions is:
[0025]
[0026]
[0027] in, For the first The first in the tribe The member in the During the nth iteration, at the... Speed in each spatial dimension For the first The first in the tribe The member in the During the nth iteration, at the... The update speed of each spatial dimension For the first The first in the tribe The member in the In the next iteration, the result after correction by the competition disturbance mechanism is... Speed in each spatial dimension; For the first The first in the tribe The member in the During the nth iteration, at the... Location in a spatial dimension For the first The first in the tribe The member in the During the nth iteration, at the... The update position of each spatial dimension For the first The first in the tribe The member found during the entire iteration process is the [number]th [member]. The optimal fitness position in each spatial dimension; This represents the optimal fitness position found by the tribe throughout the entire iteration process; , , These are the first chaotic random factor, the second chaotic random factor, and the third chaotic random factor, respectively. The optimal fitness position obtained by a competing tribe that is competing with the current tribe; The fitness value of the globally optimal member. The fitness value of the best member of the opposing tribe; For the first In the next iteration, the optimal position of the opponent member is related to the... The first in the tribe The member in the The competing perturbation term generated by the velocity update of each spatial dimension.
[0028] Furthermore, boundary constraint processing is applied to the updated positions, projecting path points that exceed the passable area back onto the legal area boundary.
[0029] Furthermore, the iteration termination condition includes: The current iteration count is greater than the maximum iteration count, or the absolute value of the change in the global optimal fitness value over a consecutive preset number of iterations is less than a preset threshold.
[0030] The beneficial effects of adopting the above technical solution are as follows: (1) The present invention designs a withdrawal factor that changes dynamically with fitness value. Members with poor fitness face stronger competitive pressure, which accelerates the elimination of inferior individuals and the spread of advantageous information, and improves the algorithm's ability to quickly locate the global optimal solution.
[0031] (2) The present invention adopts an adaptive optimization inertia weight strategy. The inertia weight decreases linearly with the number of iterations and random perturbation is added, so that the algorithm has a strong global exploration capability in the early stage of iteration and enhances the local development capability in the later stage, thereby effectively balancing the contradiction between exploration and development, and overcoming the defects of slow convergence speed and easy to get trapped in local optima in the traditional CTCM algorithm.
[0032] (3) The present invention introduces a sinusoidal acceleration optimization learning factor mechanism. The learning factor includes individual factors and group factors, which are dynamically adjusted according to the sinusoidal law with the number of iterations. This alleviates the problem of limited search ability caused by static learning factors and enhances the search vitality of the algorithm in complex environments.
[0033] (4) The present invention constructs a multi-objective fitness function that comprehensively considers path length, smoothness and safety, and uses a continuous two-dimensional coordinate space for path encoding, which can directly output a smooth continuous path coordinate sequence, thus achieving a dual balance between path optimality and navigation safety in a multi-threat water environment. Attached Figure Description
[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0035] Figure 1 This is a flowchart of a path planning method for an unmanned surface vessel in an embodiment of the present invention; Figure 2 This is a schematic diagram of a path planning method for an unmanned surface vessel in an embodiment of the present invention. Figure 3 This is a convergence curve of the inertia weight as a function of the number of iterations in an embodiment of the present invention. Figure 4The figures shown are curves of individual factors and group factors changing with the number of iterations in this embodiment of the invention: (a) curve of individual factors changing with iteration time, and (b) curve of group factors changing with iteration time. Figure 5 The following diagrams compare the path planning routes of this invention and other mainstream algorithms in marine environments with different levels of complexity: (a) is a comparison of the path planning routes of this algorithm and other mainstream algorithms in simple marine environments, and (b) is a comparison of the path planning routes of this algorithm and other mainstream algorithms in complex marine environments. Figure 6 The diagrams show the convergence curves of the fitness curves of the path planning of this invention and other mainstream algorithms with the number of iterations in marine environments of different complexity. (a) is a comparison of the convergence curves of the fitness curves of the path planning of this algorithm and other mainstream algorithms with the number of iterations in simple marine environments, and (b) is a comparison of the convergence curves of the fitness curves of the path planning of this algorithm and other mainstream algorithms with the number of iterations in complex marine environments. Detailed Implementation
[0036] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0037] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0038] This invention proposes a path planning method for unmanned surface vessels (USVs) based on the Adaptive Inertial Weights and Multiple Learning Factors Tribal Competition and Membership Cooperation Algorithm (AIWL-CTCM). Improvements are made to the Tribal Competition and Membership Cooperation Algorithm (CTCM): a withdrawal factor that dynamically changes with fitness values is designed to enhance the algorithm's ability to quickly locate the global optimum; an adaptively optimized inertial weight strategy is adopted, dynamically adjusting weights with the number of iterations to balance global exploration and local development capabilities; and a sinusoidal acceleration-optimized learning factor mechanism is introduced to dynamically adjust individual factors, group factors, and the global withdrawal factor to alleviate the limitations of static learning factors. This invention improves convergence speed while considering path length, smoothness, and safety, achieving a dual balance between path optimality and navigation safety, and is suitable for complex marine environments with multiple threats. It should be noted that in specific implementations, only one of the above three improvements may be implemented, or multiple improvements may be implemented simultaneously, all within the scope of this invention.
[0039] like Figure 1 As shown, a path planning method for unmanned surface vessels includes the following steps: Step 1: Determine the navigable area boundaries of unmanned surface vessels in a multi-threat surface environment.
[0040] The specific steps are as follows: Step 1-1: Obtain information on the starting point, target point, and water surface environment, including the location and extent of obstacles; obstacles may be polygonal or circular.
[0041] Steps 1-2: Mark the entire water surface space, excluding the area covered by obstacles and the boundary of the threat zone, as a passable area, and use a continuous two-dimensional coordinate space to represent the path points.
[0042] Steps 1-3: Set constraints for path planning, including that the path must not pass through any obstacles or threat areas, and that the sequence of path points must be located within passable areas.
[0043] like Figure 2 As shown, the unmanned surface vessel needs to travel from the starting point to the finish line at a speed of ( , ), waypoints include: , , , , , ; The angle between two paths is used to evaluate the turning change of the unmanned surface vessel (USV) at this node. The red area is the danger zone; entering this area is considered a collision. The constraint function ensures that the USV cannot enter this area. It is divided into two layers: the inner layer within the dashed line represents the actual obstacle size, and the area between the red solid line and the red dashed line represents the transformation of the USV's actual size (that is, although the USV is represented as a point mass, its actual size is transferred here, which is consistent with reality); the yellow area represents the warning zone. When the USV enters this area, the penalty from the safety constraint function is strengthened, but no danger will occur; it is only a warning; the green area outside the yellow solid line represents the absolutely safe zone, within which the safety constraint of the USV is 0.
[0044] Step 2: Initialize the tribe based on the passable area boundary. The tribe contains multiple tribe members, and each tribe member corresponds to a path of unmanned surface vessels.
[0045] The specific steps are as follows: Step 2-1: Set algorithm parameters, including the number of tribes. =5, number of members in a single tribe =20, number of path nodes =12 / 15 (12 in simple sea areas, 15 in complex sea areas), maximum number of iterations =600, Inertia weight upper and lower limits , Individual factor and group factor value range withdrawal factor .
[0046] Step 2-2: Encode each member as a path, the path is formed by... A continuous coordinate sequence consisting of two-dimensional path points, where the starting point and the target point remain fixed.
[0047] Steps 2-3: Randomly initialize the position vectors of all members within the passable area. and velocity vector Ensure the initial path does not cross obstacles or threat areas. The members are divided equally into There are 10 tribes, each tribe containing One member.
[0048] Steps 2-4: Initialize the individual position of each member to its initial position, and the optimal position of each tribe is the position of the most fit member in that tribe.
[0049] Step 3: Construct a multi-objective fitness function, calculate the fitness value of each member in the initial tribe, and update the fitness values of the best member of each tribe, the best member of the opponent tribe, and the fitness value of the global best member based on the fitness values.
[0050] The specific steps are as follows: Step 3-1: Construct the fitness function ; in, , , These are the weighting coefficients in the fitness function, used to adjust the importance of each path's evaluation metrics. Specifically, , , These are used to characterize the importance of path length, path smoothness, and navigation safety, with the preferred values being [values to be filled in]. Among these factors, path length affects travel time and energy consumption; path smoothness directly affects the steering stability, servo response, and trajectory tracking efficiency of the unmanned surface vessel (USV); and navigation safety ensures a safe distance between the USV and obstacles to avoid excessive obstacle avoidance and path detours. Sensitivity analysis of multiple weight combinations reveals that: , , At this point, a good balance can be achieved between path length, maximum steering angle, and minimum obstacle distance, ensuring navigation safety and a smooth path while avoiding excessive path length. Therefore, this set of weighting coefficients is used as the preferred parameters in this embodiment.
[0051] This formula shows that path planning for unmanned surface vessels (USVs) involves multiple factors such as path length, smoothness, and safety. A higher fitness value indicates superior path planning performance, specifically manifested in shorter path lengths, better smoothness, and a higher safety margin for the USV.
[0052] The evaluation function for the cumulative length is given by the following formula: (1) in, and The first The and the first Cartesian coordinates of the path points Given the total number of nodes, this formula can accurately describe the travel distance of unmanned surface vessels.
[0053] The smoothness evaluation function has the following formula: (2) in, This is the penalty coefficient for cornering. Given the angle between the two path segments, evaluate the change in steering of the unmanned surface vessel at this node. The range is set in [ [30°, 30°]; the maximum yaw rate is limited to 20° / s. If the values in the planned route are outside the range, the current execution will be deemed an invalid plan. The specific formula is: (3) in, and These are vectors of adjacent path segments.
[0054] The safety performance evaluation function has the following formula: (4) Where Z represents the number of threats, and each threat is assumed to be a cylinder. Let the radius of the regular cylindrical obstacle be denoted as . In real-world scene simulations, all irregular islands or obstacles are simplified to circular obstacles using the minimum circumcircle, and the corresponding radius is used as . . The physical meaning is to ensure that unmanned surface vessels maintain a sufficient safe distance from obstacles during navigation, avoid collisions, and ensure navigational safety. For a given path segment... The associated threat cost is proportional to the distance from the unmanned surface vessel to the center point of the cylinder. The diameter of the unmanned surface vessel. The safe distance for the collision zone. By integrating all the index functions, the comprehensive fitness function of the unmanned surface vessel is obtained.
[0055] Step 3-2: Calculate the fitness value of each member in the initial tribe. .
[0056] Step 3-3: Update the fitness value of the best member in each tribe. Fitness values of the best members of the opposing tribe and the fitness value of the globally optimal member .
[0057] Step 4: Implement iterative optimization of tribal competition and member cooperation.
[0058] Tribal competition and member cooperation iterative optimization includes: calculating the retreat factor based on the target's best fitness value and the opponent tribe's best fitness value, updating the positions of tribe members based on the retreat factor to generate new unmanned surface vessel paths, and updating the tribe's optimal path and the global optimal path.
[0059] When tribal competition occurs, the AIWL-CTCM algorithm determines tribal behavior by simulating resource competition and conflict between tribes. Specifically, stronger tribes will hold their ground, while weaker tribes will retreat. The speed of retreat is influenced by the tribe's strength and the nature of the conflict. To simulate this behavior, the algorithm updates the position and speed of tribe members based on a retreat factor.
[0060] withdrawal factor The formula is: (5) in, and They are respectively The minimum and maximum values; The fitness value of the globally optimal member. The fitness value of the best member of the opposing tribe.
[0061] In another embodiment, iterative optimization of tribal competition and member cooperation further includes: The positions of tribe members are updated based on an adaptive inertial weight strategy to generate new paths for unmanned surface vessels; inertial weight The formula is: (6) in, For minimum inertia weight, For maximum inertia weight, This represents the current iteration number. The maximum number of iterations, This is the inertia weight adjustment factor, used to control the nonlinearity of the inertia weight change with the number of iterations. The inertia weight change curve is shown below. Figure 3 As shown. By Figure 3 As can be seen, under the adaptive inertia weight strategy designed in this invention, a larger inertia weight is used in the early stage of iteration to facilitate the expansion of the search space, and the inertia weight is gradually reduced in the later stage of iteration to strengthen the local search. The dynamic adjustment mechanism of inertia weight effectively improves the convergence characteristics and optimization performance of the algorithm.
[0062] In another embodiment, iterative optimization of tribal competition and member cooperation further includes: Based on sinusoidal acceleration optimization Update tribe member locations to generate new unmanned surface vessel paths; and The specific formula is as follows: (7) (8) in, and They are respectively and The minimum value, and They are respectively and The maximum value. Its convergence curve is shown below. Figure 4 (a) Figure 4 As shown in (b), from Figure 4 (a) Figure 4 As seen in (b), the addition of the adaptive mechanism makes the balance between global and local exploration more stable. In the early stages of exploration, Larger values prioritize global exploration, accelerating member location finding; as the number of iterations increases... The value gradually decreases. As the numerical value gradually increases, the focus of exploration shifts from global exploration to local development, better helping the target find its optimal location.
[0063] Member speed and position updates, where the specific update formula for member speed is: (9) in, For the first The first in the tribe The member in the During the nth iteration, at the... Speed in each spatial dimension For the first The first in the tribe The member in the During the nth iteration, at the... The update speed of each spatial dimension; For the first The first in the tribe The member in the During the nth iteration, at the... Location in a spatial dimension For the first The first in the tribe The member found during the entire iteration process is the [number]th [member]. The optimal fitness position in each spatial dimension; This represents the optimal fitness position found by the tribe throughout the entire iteration process; The best fitness position obtained by a competing tribe that is competing with the current tribe.
[0064] , , These are the first chaotic random factor, the second chaotic random factor, and the third chaotic random factor, respectively, and their formulas are as follows: (10) The velocity vector of each member is updated according to formula (9), and the position update formula for each member is: (11) The specific update formula is as follows: (12) (13) in, For the first The first in the tribe The member in the In the next iteration, the result after correction by the competition disturbance mechanism is... Speed in each spatial dimension; The optimal fitness value for the target. The optimal fitness value for the opposing tribe; For the first The first in the tribe The member in the During the nth iteration, at the... The update position of each spatial dimension For the first In the next iteration, the optimal position of the opponent member is related to the... The first in the tribe The member in the The competing perturbation term generated by the velocity update of each spatial dimension.
[0065] At the same time, boundary constraints are applied to the updated locations, projecting path points that exceed the passable area back onto the legal area boundary.
[0066] Step 5: After the iteration termination condition is met, output the globally optimal path obtained in the last iteration as the final planned path of the unmanned surface vessel.
[0067] The specific steps are as follows: Step 5-1: Determine if the termination condition is met: current iteration number. Or, the absolute value of the change in the global optimal fitness value over 20 consecutive generations is less than a preset threshold. ; If none of the termination conditions are met, then let Return to step 5-1 and continue iterating; if any termination condition is met, terminate the iteration and obtain the global optimal position vector. It is decoded into a continuous two-dimensional path point sequence.
[0068] Step 5-2: Output the path point sequence as the final planned route of the unmanned surface vessel.
[0069] like Figure 5 (a) Figure 5(b) Figure 6 (a) Figure 6 As shown in (b), the method of this invention performs particularly well in handling two key tasks: firstly, the AIWL-CTCM algorithm of this invention stably avoids irregularly shaped obstacles in irregular and complex environments, demonstrating its powerful obstacle avoidance capability; secondly, the generated path can effectively pass through complex environmental constraints while maintaining continuous and smooth motion characteristics. Furthermore, the method of this invention exhibits fast and stable convergence characteristics in various complex environments, reaching stability within 100 iterations. Compared with other algorithms (including Standard Particle Swarm Optimization (SPSO), CTCM, Grey Wolf Optimization (GWO), and Whale Optimization (WOA)), the method of this invention can find a better solution from the beginning, and the fitness value of the final planned path is lower than that of other comparative algorithms, demonstrating the effectiveness of the method in finding the initial solution and the optimality in determining the final solution.
[0070] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. A path planning method for unmanned surface vessels, characterized in that, include: Determine the navigable boundaries of unmanned surface vessels in a water environment; A tribe is initialized based on the boundary of the passable area. The tribe contains multiple members, and each member corresponds to a path of an unmanned surface vessel. Construct a multi-objective fitness function, calculate the fitness value of each member in the initial tribe, and update the fitness values of the best member of each tribe, the best member of the opponent tribe, and the fitness value of the global best member based on the fitness values. Iterative optimization of tribal competition and member cooperation; After the iteration termination condition is met, the globally optimal path obtained in the last iteration is output as the final planned path of the unmanned surface vessel. The iterative optimization of tribal competition and member cooperation includes: calculating a retreat factor based on the target's best fitness value and the opponent's tribe's best fitness value; updating the speed and position of tribe members based on the retreat factor to generate a new unmanned surface vessel path; and updating the tribe's optimal path and the global optimal path. The withdrawal factor for: in, and They are respectively The minimum and maximum values; The fitness value of the globally optimal member. The fitness value of the best member of the opposing tribe; The iterative optimization of tribal competition and member cooperation also includes: The positions of tribe members are updated based on an adaptive inertial weight strategy to generate new paths for unmanned surface vessels; the inertial weights are: in, For inertial weights, This represents the current iteration number. The maximum number of iterations, This is the inertia weight adjustment factor, used to control the degree of nonlinearity in the change of inertia weight with the number of iterations; The iterative optimization of tribal competition and member cooperation also includes: Based on sinusoidal acceleration optimization and Update tribe member locations to generate new unmanned surface vessel paths; and for: in, and They are respectively and The minimum value, and They are respectively and The maximum value; The member speed update formula is: The formula for updating member positions is: in, For the first The first in the tribe The member in the During the nth iteration, at the... Speed in each spatial dimension For the first The first in the tribe The member in the During the nth iteration, at the... The update speed of each spatial dimension For the first The first in the tribe The member in the In the next iteration, the result after correction by the competition disturbance mechanism is... Speed in each spatial dimension; For the first The first in the tribe The member in the During the nth iteration, at the... Location in a spatial dimension For the first The first in the tribe The member in the During the nth iteration, at the... The update position of each spatial dimension For the first The first in the tribe The member found during the entire iteration process is the [number]th [member]. The optimal fitness position in each spatial dimension; This represents the optimal fitness position found by the tribe throughout the entire iteration process; , , These are the first chaotic random factor, the second chaotic random factor, and the third chaotic random factor, respectively. The optimal fitness position obtained by a competing tribe that is competing with the current tribe; The fitness value of the globally optimal member. The fitness value of the best member of the opposing tribe; For the first In the next iteration, the optimal position of the opponent member is related to the... The first in the tribe The member in the The competing perturbation term generated by the velocity update of each spatial dimension.
2. The path planning method for an unmanned surface vessel according to claim 1, characterized in that, Determine the navigable boundaries of unmanned surface vessels in a water environment, including: Get or set the coordinates of the starting point and the target point; Acquire or set information about the water surface environment, including the geometric boundaries of static obstacles and the location and range of dynamic threat areas; The entire surface water space, excluding obstacles and threat areas, is marked as a passable area.
3. The path planning method for an unmanned surface vessel according to claim 2, characterized in that, Initializing a tribe based on the boundaries of the passable area includes: Configure algorithm parameters, including the number of tribes. Number of members in a single tribe Number of path nodes Maximum number of iterations Inertia weight upper limit Lower bound of inertia weight Individual factors The range of values, population factor The range of values and the withdrawal factor The range of values for; Each member is encoded as a path, and the path is... The path is represented by a continuous coordinate sequence of two-dimensional path points, where the starting point and the target point are fixed. Set constraints for path planning, including that the path must not pass through any obstacles or threat areas, and that the sequence of path points must be located within a passable area; Randomly initialize the position vectors of all members within the passable area. and velocity vector Ensure the initial path does not cross obstacles or threat areas; The members are divided equally into There are 10 tribes, each tribe containing One member; Each member's individual position is initialized to its initial position, and the tribe's optimal position is the position of the most fit member in that tribe.
4. The path planning method for an unmanned surface vessel according to claim 1, characterized in that, The multi-objective fitness function is: ,in, , , These are the weighting coefficients in the fitness function, used to adjust the importance of each path's evaluation index; Evaluation function for cumulative length: in, and The first The and the first Cartesian coordinates of the path points The total number of nodes; For the smoothness evaluation function: in, This is the penalty coefficient for cornering. The angle between the two paths. for: in, and The vectors represent adjacent path segments; if the turning changes and maximum yaw rate in the planned route exceed the limits, the current execution is deemed an invalid plan. For safety performance evaluation functions: in, Z To represent the number of threats, assuming each threat is a cylinder, Let the radius of the regular cylindrical obstacle be . The diameter of the unmanned surface vessel. The safe distance for the collision zone, The safety value of unmanned surface vessels reaching every obstacle. This is the distance from the unmanned surface vessel to the center of the obstacle.
5. The path planning method for an unmanned surface vessel according to claim 1, characterized in that, The updated positions are subjected to boundary constraint processing, and path points that exceed the passable area are projected back onto the legal area boundary.
6. The path planning method for an unmanned surface vessel according to claim 1, characterized in that, The iteration termination conditions include: The current iteration count is greater than the maximum iteration count, or the absolute value of the change in the global optimal fitness value over a consecutive preset number of iterations is less than a preset threshold.